2024-11-27 20:27:51.845022: I tensorflow/core/platform/cpu_feature_guard.cc:193] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations: AVX2 FMA To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags. 2024-11-27 20:27:52.768738: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer_plugin.so.7'; dlerror: libcudnn.so.8: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: :/home/gpu/NLP/.env/lib/python3.10/site-packages/tensorrt:/home/gpu/NLP/.env/lib/python3.10/site-packages/tensorrt 2024-11-27 20:27:52.768771: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Cannot dlopen some TensorRT libraries. If you would like to use Nvidia GPU with TensorRT, please make sure the missing libraries mentioned above are installed properly. HooshvareLab/bert-base-parsbert-ner-uncased ################################################## ################################################## 2024-11-27 20:27:54,011 Reading data from data 2024-11-27 20:27:54,012 Train: data/data110.txt 2024-11-27 20:27:54,012 Dev: None 2024-11-27 20:27:54,012 Test: None 2024-11-27 20:27:54,081 No test split found. Using 10% (i.e. 11 samples) of the train split as test data 2024-11-27 20:27:54,082 No dev split found. Using 10% (i.e. 10 samples) of the train split as dev data 2024-11-27 20:27:54,082 Computing label dictionary. Progress: 0it [00:00, ?it/s] 0it [00:00, ?it/s] 0it [00:00, ?it/s] 89it [00:00, 16180.19it/s] 2024-11-27 20:27:54,090 Dictionary created for label 'ner' with 12 values: Org (seen 187 times), Sub (seen 125 times), Href (seen 123 times), Adv (seen 81 times), Aim (seen 37 times), Ref (seen 24 times), Act (seen 22 times), Pro (seen 15 times), Date (seen 14 times), Fac (seen 3 times), Num (seen 3 times), Event (seen 2 times) tf_model.h5: 0%| | 0.00/652M [00:00<?, ?B/s] tf_model.h5: 2%|█ | 10.5M/652M [00:01<01:21, 7.86MB/s] tf_model.h5: 3%|██ | 21.0M/652M [00:02<01:00, 10.4MB/s] tf_model.h5: 5%|███ | 31.5M/652M [00:03<00:57, 10.8MB/s] tf_model.h5: 6%|████ | 41.9M/652M [00:03<00:55, 11.0MB/s]^[[B tf_model.h5: 8%|█████▏ | 52.4M/652M [00:04<00:53, 11.1MB/s]^[[B tf_model.h5: 10%|██████▏ | 62.9M/652M [00:05<00:52, 11.3MB/s]^[[B^[[B tf_model.h5: 11%|███████▏ | 73.4M/652M [00:06<00:52, 11.0MB/s] tf_model.h5: 13%|████████▏ | 83.9M/652M [00:07<00:48, 11.8MB/s] tf_model.h5: 14%|█████████▎ | 94.4M/652M [00:08<00:46, 11.9MB/s] tf_model.h5: 16%|██████████▍ | 105M/652M [00:09<00:45, 12.0MB/s] tf_model.h5: 18%|███████████▌ | 115M/652M [00:10<00:44, 12.0MB/s] tf_model.h5: 19%|████████████▌ | 126M/652M [00:11<00:43, 12.0MB/s] tf_model.h5: 21%|█████████████▌ | 136M/652M [00:12<00:46, 11.2MB/s] tf_model.h5: 23%|██████████████▋ | 147M/652M [00:12<00:43, 11.7MB/s] tf_model.h5: 24%|███████████████▋ | 157M/652M [00:13<00:42, 11.7MB/s] tf_model.h5: 26%|████████████████▋ | 168M/652M [00:14<00:40, 11.9MB/s] tf_model.h5: 27%|█████████████████▊ | 178M/652M [00:15<00:39, 11.9MB/s] tf_model.h5: 29%|██████████████████▊ | 189M/652M [00:16<00:38, 11.9MB/s]^[[B tf_model.h5: 31%|███████████████████▊ | 199M/652M [00:17<00:38, 11.9MB/s]^[[B^[[B tf_model.h5: 32%|████████████████████▉ | 210M/652M [00:18<00:37, 11.7MB/s] tf_model.h5: 34%|█████████████████████▉ | 220M/652M [00:19<00:36, 11.9MB/s]^[[B tf_model.h5: 35%|███████████████████████ | 231M/652M [00:19<00:35, 12.0MB/s] tf_model.h5: 37%|████████████████████████ | 241M/652M [00:20<00:34, 12.0MB/s] tf_model.h5: 39%|█████████████████████████ | 252M/652M [00:21<00:33, 12.0MB/s] tf_model.h5: 40%|██████████████████████████▏ | 262M/652M [00:22<00:34, 11.4MB/s] tf_model.h5: 42%|███████████████████████████▏ | 273M/652M [00:23<00:32, 11.5MB/s] tf_model.h5: 43%|████████████████████████████▏ | 283M/652M [00:24<00:31, 11.8MB/s] tf_model.h5: 45%|█████████████████████████████▎ | 294M/652M [00:25<00:30, 11.9MB/s] tf_model.h5: 47%|██████████████████████████████▎ | 304M/652M [00:26<00:29, 11.9MB/s] tf_model.h5: 48%|███████████████████████████████▍ | 315M/652M [00:27<00:28, 12.0MB/s] tf_model.h5: 50%|████████████████████████████████▍ | 325M/652M [00:27<00:27, 12.0MB/s] tf_model.h5: 51%|█████████████████████████████████▍ | 336M/652M [00:28<00:26, 11.9MB/s] tf_model.h5: 53%|██████████████████████████████████▌ | 346M/652M [00:29<00:25, 12.0MB/s] tf_model.h5: 55%|███████████████████████████████████▌ | 357M/652M [00:30<00:25, 11.8MB/s] tf_model.h5: 56%|████████████████████████████████████▌ | 367M/652M [00:31<00:23, 11.9MB/s] tf_model.h5: 58%|█████████████████████████████████████▋ | 377M/652M [00:32<00:24, 11.1MB/s] tf_model.h5: 60%|██████████████████████████████████████▋ | 388M/652M [00:33<00:23, 11.3MB/s] tf_model.h5: 61%|███████████████████████████████████████▋ | 398M/652M [00:34<00:21, 11.5MB/s] tf_model.h5: 63%|████████████████████████████████████████▊ | 409M/652M [00:35<00:20, 11.7MB/s] tf_model.h5: 64%|█████████████████████████████████████████▊ | 419M/652M [00:36<00:19, 11.8MB/s] tf_model.h5: 66%|██████████████████████████████████████████▉ | 430M/652M [00:36<00:18, 11.8MB/s] tf_model.h5: 68%|███████████████████████████████████████████▉ | 440M/652M [00:37<00:17, 12.2MB/s] tf_model.h5: 69%|████████████████████████████████████████████▉ | 451M/652M [00:38<00:16, 11.9MB/s] tf_model.h5: 71%|██████████████████████████████████████████████ | 461M/652M [00:39<00:15, 11.9MB/s] tf_model.h5: 72%|███████████████████████████████████████████████ | 472M/652M [00:40<00:15, 12.0MB/s] tf_model.h5: 74%|████████████████████████████████████████████████ | 482M/652M [00:41<00:14, 12.0MB/s] tf_model.h5: 76%|█████████████████████████████████████████████████▏ | 493M/652M [00:42<00:13, 12.0MB/s] tf_model.h5: 77%|██████████████████████████████████████████████████▏ | 503M/652M [00:43<00:13, 11.2MB/s] tf_model.h5: 79%|███████████████████████████████████████████████████▏ | 514M/652M [00:44<00:12, 11.1MB/s] tf_model.h5: 80%|████████████████████████████████████████████████████▎ | 524M/652M [00:44<00:10, 11.8MB/s] tf_model.h5: 82%|█████████████████████████████████████████████████████▎ | 535M/652M [00:45<00:09, 11.9MB/s] tf_model.h5: 84%|██████████████████████████████████████████████████████▍ | 545M/652M [00:46<00:09, 11.8MB/s] tf_model.h5: 85%|███████████████████████████████████████████████████████▍ | 556M/652M [00:47<00:08, 11.9MB/s] tf_model.h5: 87%|████████████████████████████████████████████████████████▍ | 566M/652M [00:48<00:07, 11.9MB/s] tf_model.h5: 88%|█████████████████████████████████████████████████████████▌ | 577M/652M [00:49<00:06, 12.3MB/s] tf_model.h5: 90%|██████████████████████████████████████████████████████████▌ | 587M/652M [00:50<00:05, 11.9MB/s] tf_model.h5: 92%|███████████████████████████████████████████████████████████▌ | 598M/652M [00:51<00:04, 12.0MB/s] tf_model.h5: 93%|████████████████████████████████████████████████████████████▋ | 608M/652M [00:51<00:03, 12.0MB/s] tf_model.h5: 95%|█████████████████████████████████████████████████████████████▋ | 619M/652M [00:53<00:02, 11.1MB/s] tf_model.h5: 97%|██████████████████████████████████████████████████████████████▊ | 629M/652M [00:53<00:02, 11.2MB/s] tf_model.h5: 98%|███████████████████████████████████████████████████████████████▊ | 640M/652M [00:54<00:01, 12.0MB/s] tf_model.h5: 100%|████████████████████████████████████████████████████████████████▊| 650M/652M [00:55<00:00, 11.9MB/s] tf_model.h5: 100%|█████████████████████████████████████████████████████████████████| 652M/652M [00:55<00:00, 11.9MB/s] tf_model.h5: 100%|█████████████████████████████████████████████████████████████████| 652M/652M [00:55<00:00, 11.7MB/s] 2024-11-27 20:28:57.220417: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcudnn.so.8'; dlerror: libcudnn.so.8: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: :/home/gpu/NLP/.env/lib/python3.10/site-packages/tensorrt:/home/gpu/NLP/.env/lib/python3.10/site-packages/tensorrt 2024-11-27 20:28:57.220472: W tensorflow/core/common_runtime/gpu/gpu_device.cc:1934] Cannot dlopen some GPU libraries. Please make sure the missing libraries mentioned above are installed properly if you would like to use GPU. Follow the guide at https://www.tensorflow.org/install/gpu for how to download and setup the required libraries for your platform. Skipping registering GPU devices... model read successfully ! ################################################## ################################################## 2024-11-27 20:29:00,586 SequenceTagger predicts: Dictionary with 49 tags: O, S-Org, B-Org, E-Org, I-Org, S-Sub, B-Sub, E-Sub, I-Sub, S-Href, B-Href, E-Href, I-Href, S-Adv, B-Adv, E-Adv, I-Adv, S-Aim, B-Aim, E-Aim, I-Aim, S-Ref, B-Ref, E-Ref, I-Ref, S-Act, B-Act, E-Act, I-Act, S-Pro, B-Pro, E-Pro, I-Pro, S-Date, B-Date, E-Date, I-Date, S-Fac, B-Fac, E-Fac, I-Fac, S-Num, B-Num, E-Num, I-Num, S-Event, B-Event, E-Event, I-Event /home/gpu/NLP/.env/lib/python3.10/site-packages/flair/trainers/trainer.py:499: FutureWarning: `torch.cuda.amp.GradScaler(args...)` is deprecated. Please use `torch.amp.GradScaler('cuda', args...)` instead. scaler = torch.cuda.amp.GradScaler(enabled=use_amp and flair.device.type != "cpu") 2024-11-27 20:29:00,591 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:29:00,593 Model: "SequenceTagger( (embeddings): TransformerWordEmbeddings( (model): BertModel( (embeddings): BertEmbeddings( (word_embeddings): Embedding(100001, 768, padding_idx=0) (position_embeddings): Embedding(512, 768) (token_type_embeddings): Embedding(2, 768) (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True) (dropout): Dropout(p=0.1, inplace=False) ) (encoder): BertEncoder( (layer): ModuleList( (0-11): 12 x BertLayer( (attention): BertAttention( (self): BertSdpaSelfAttention( (query): Linear(in_features=768, out_features=768, bias=True) (key): Linear(in_features=768, out_features=768, bias=True) (value): Linear(in_features=768, out_features=768, bias=True) (dropout): Dropout(p=0.1, inplace=False) ) (output): BertSelfOutput( (dense): Linear(in_features=768, out_features=768, bias=True) (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True) (dropout): Dropout(p=0.1, inplace=False) ) ) (intermediate): BertIntermediate( (dense): Linear(in_features=768, out_features=3072, bias=True) (intermediate_act_fn): GELUActivation() ) (output): BertOutput( (dense): Linear(in_features=3072, out_features=768, bias=True) (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True) (dropout): Dropout(p=0.1, inplace=False) ) ) ) ) (pooler): BertPooler( (dense): Linear(in_features=768, out_features=768, bias=True) (activation): Tanh() ) ) ) (locked_dropout): LockedDropout(p=0.5) (linear): Linear(in_features=768, out_features=49, bias=True) (loss_function): CrossEntropyLoss() )" 2024-11-27 20:29:00,593 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:29:00,593 Corpus: 89 train + 10 dev + 11 test sentences 2024-11-27 20:29:00,593 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:29:00,593 Train: 89 sentences 2024-11-27 20:29:00,593 (train_with_dev=False, train_with_test=False) 2024-11-27 20:29:00,593 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:29:00,593 Training Params: 2024-11-27 20:29:00,593 - learning_rate: "4e-05" 2024-11-27 20:29:00,593 - mini_batch_size: "10" 2024-11-27 20:29:00,593 - max_epochs: "200" 2024-11-27 20:29:00,593 - shuffle: "True" 2024-11-27 20:29:00,594 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:29:00,594 Plugins: 2024-11-27 20:29:00,594 - LinearScheduler | warmup_fraction: '0.1' 2024-11-27 20:29:00,594 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:29:00,594 Final evaluation on model after last epoch (final-model.pt) 2024-11-27 20:29:00,594 - metric: "('micro avg', 'f1-score')" 2024-11-27 20:29:00,594 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:29:00,594 Computation: 2024-11-27 20:29:00,594 - compute on device: cuda:0 2024-11-27 20:29:00,594 - embedding storage: none 2024-11-27 20:29:00,594 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:29:00,594 Model training base path: "taggers" 2024-11-27 20:29:00,594 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:29:00,594 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:29:01,631 epoch 1 - iter 1/9 - loss 4.65710957 - time (sec): 1.04 - samples/sec: 533.89 - lr: 0.000000 - momentum: 0.000000 2024-11-27 20:29:01,717 epoch 1 - iter 2/9 - loss 4.65563200 - time (sec): 1.12 - samples/sec: 968.58 - lr: 0.000000 - momentum: 0.000000 2024-11-27 20:29:01,846 epoch 1 - iter 3/9 - loss 4.63586331 - time (sec): 1.25 - samples/sec: 1342.62 - lr: 0.000000 - momentum: 0.000000 2024-11-27 20:29:01,979 epoch 1 - iter 4/9 - loss 4.59567359 - time (sec): 1.38 - samples/sec: 1642.39 - lr: 0.000001 - momentum: 0.000000 2024-11-27 20:29:02,117 epoch 1 - iter 5/9 - loss 4.62587248 - time (sec): 1.52 - samples/sec: 1882.69 - lr: 0.000001 - momentum: 0.000000 2024-11-27 20:29:02,253 epoch 1 - iter 6/9 - loss 4.64331523 - time (sec): 1.66 - samples/sec: 2109.53 - lr: 0.000001 - momentum: 0.000000 2024-11-27 20:29:02,388 epoch 1 - iter 7/9 - loss 4.64093422 - time (sec): 1.79 - samples/sec: 2241.83 - lr: 0.000001 - momentum: 0.000000 2024-11-27 20:29:02,524 epoch 1 - iter 8/9 - loss 4.60011713 - time (sec): 1.93 - samples/sec: 2425.15 - lr: 0.000001 - momentum: 0.000000 2024-11-27 20:29:02,646 epoch 1 - iter 9/9 - loss 4.62793420 - time (sec): 2.05 - samples/sec: 2534.08 - lr: 0.000002 - momentum: 0.000000 2024-11-27 20:29:02,646 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:29:02,647 EPOCH 1 done: loss 4.6279 - lr: 0.000002 0%| | 0/1 [00:00<?, ?it/s] 100%|███████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 3.10it/s] 100%|███████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 3.09it/s] 2024-11-27 20:29:02,993 DEV : loss 3.9344329833984375 - f1-score (micro avg) 0.0 2024-11-27 20:29:02,994 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:29:03,095 epoch 2 - iter 1/9 - loss 4.37824857 - time (sec): 0.10 - samples/sec: 6053.26 - lr: 0.000002 - momentum: 0.000000 2024-11-27 20:29:03,223 epoch 2 - iter 2/9 - loss 4.38069158 - time (sec): 0.23 - samples/sec: 5253.47 - lr: 0.000002 - momentum: 0.000000 2024-11-27 20:29:03,339 epoch 2 - iter 3/9 - loss 4.39503646 - time (sec): 0.34 - samples/sec: 5208.31 - lr: 0.000002 - momentum: 0.000000 2024-11-27 20:29:03,469 epoch 2 - iter 4/9 - loss 4.34063966 - time (sec): 0.47 - samples/sec: 4935.00 - lr: 0.000002 - momentum: 0.000000 2024-11-27 20:29:03,595 epoch 2 - iter 5/9 - loss 4.36152841 - time (sec): 0.60 - samples/sec: 4634.64 - lr: 0.000003 - momentum: 0.000000 2024-11-27 20:29:03,747 epoch 2 - iter 6/9 - loss 4.34590180 - time (sec): 0.75 - samples/sec: 4631.33 - lr: 0.000003 - momentum: 0.000000 2024-11-27 20:29:03,896 epoch 2 - iter 7/9 - loss 4.36621268 - time (sec): 0.90 - samples/sec: 4514.09 - lr: 0.000003 - momentum: 0.000000 2024-11-27 20:29:04,017 epoch 2 - iter 8/9 - loss 4.35754908 - time (sec): 1.02 - samples/sec: 4516.87 - lr: 0.000003 - momentum: 0.000000 2024-11-27 20:29:04,151 epoch 2 - iter 9/9 - loss 4.30139411 - time (sec): 1.16 - samples/sec: 4496.23 - lr: 0.000003 - momentum: 0.000000 2024-11-27 20:29:04,151 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:29:04,152 EPOCH 2 done: loss 4.3014 - lr: 0.000003 0%| | 0/1 [00:00<?, ?it/s] 100%|███████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 5.84it/s] 100%|███████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 5.83it/s] 2024-11-27 20:29:04,345 DEV : loss 3.539954423904419 - f1-score (micro avg) 0.0 2024-11-27 20:29:04,346 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:29:04,438 epoch 3 - iter 1/9 - loss 3.73002616 - time (sec): 0.09 - samples/sec: 5805.17 - lr: 0.000004 - momentum: 0.000000 2024-11-27 20:29:04,566 epoch 3 - iter 2/9 - loss 3.84019942 - time (sec): 0.22 - samples/sec: 4646.47 - lr: 0.000004 - momentum: 0.000000 2024-11-27 20:29:04,700 epoch 3 - iter 3/9 - loss 3.88445774 - time (sec): 0.35 - samples/sec: 4591.36 - lr: 0.000004 - momentum: 0.000000 2024-11-27 20:29:04,821 epoch 3 - iter 4/9 - loss 3.94652426 - time (sec): 0.47 - samples/sec: 4403.03 - lr: 0.000004 - momentum: 0.000000 2024-11-27 20:29:05,020 epoch 3 - iter 5/9 - loss 3.99284617 - time (sec): 0.67 - samples/sec: 3955.20 - lr: 0.000004 - momentum: 0.000000 2024-11-27 20:29:05,127 epoch 3 - iter 6/9 - loss 3.96889081 - time (sec): 0.78 - samples/sec: 4298.33 - lr: 0.000005 - momentum: 0.000000 2024-11-27 20:29:05,275 epoch 3 - iter 7/9 - loss 3.88889752 - time (sec): 0.93 - samples/sec: 4330.64 - lr: 0.000005 - momentum: 0.000000 2024-11-27 20:29:05,419 epoch 3 - iter 8/9 - loss 3.85103200 - time (sec): 1.07 - samples/sec: 4285.06 - lr: 0.000005 - momentum: 0.000000 2024-11-27 20:29:05,569 epoch 3 - iter 9/9 - loss 3.78396775 - time (sec): 1.22 - samples/sec: 4253.19 - lr: 0.000005 - momentum: 0.000000 2024-11-27 20:29:05,569 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:29:05,569 EPOCH 3 done: loss 3.7840 - lr: 0.000005 0%| | 0/1 [00:00<?, ?it/s] 100%|███████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 7.07it/s] 100%|███████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 7.06it/s] 2024-11-27 20:29:05,730 DEV : loss 2.900636911392212 - f1-score (micro avg) 0.0 2024-11-27 20:29:05,731 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:29:05,832 epoch 4 - iter 1/9 - loss 3.22742473 - time (sec): 0.10 - samples/sec: 5855.19 - lr: 0.000006 - momentum: 0.000000 2024-11-27 20:29:05,979 epoch 4 - iter 2/9 - loss 3.31094363 - time (sec): 0.25 - samples/sec: 4459.48 - lr: 0.000006 - momentum: 0.000000 2024-11-27 20:29:06,116 epoch 4 - iter 3/9 - loss 3.28288037 - time (sec): 0.38 - samples/sec: 4452.01 - lr: 0.000006 - momentum: 0.000000 2024-11-27 20:29:06,253 epoch 4 - iter 4/9 - loss 3.28166289 - time (sec): 0.52 - samples/sec: 4478.27 - lr: 0.000006 - momentum: 0.000000 2024-11-27 20:29:06,390 epoch 4 - iter 5/9 - loss 3.24330797 - time (sec): 0.66 - samples/sec: 4530.80 - lr: 0.000006 - momentum: 0.000000 2024-11-27 20:29:06,519 epoch 4 - iter 6/9 - loss 3.24703410 - time (sec): 0.79 - samples/sec: 4569.48 - lr: 0.000007 - momentum: 0.000000 2024-11-27 20:29:06,645 epoch 4 - iter 7/9 - loss 3.23159396 - time (sec): 0.91 - samples/sec: 4488.35 - lr: 0.000007 - momentum: 0.000000 2024-11-27 20:29:06,779 epoch 4 - iter 8/9 - loss 3.15571434 - time (sec): 1.05 - samples/sec: 4458.77 - lr: 0.000007 - momentum: 0.000000 2024-11-27 20:29:06,928 epoch 4 - iter 9/9 - loss 3.13214054 - time (sec): 1.20 - samples/sec: 4345.86 - lr: 0.000007 - momentum: 0.000000 2024-11-27 20:29:06,928 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:29:06,929 EPOCH 4 done: loss 3.1321 - lr: 0.000007 0%| | 0/1 [00:00<?, ?it/s] 100%|███████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 6.50it/s] 100%|███████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 6.49it/s] 2024-11-27 20:29:07,101 DEV : loss 2.1738452911376953 - f1-score (micro avg) 0.0 2024-11-27 20:29:07,103 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:29:07,180 epoch 5 - iter 1/9 - loss 2.62938865 - time (sec): 0.08 - samples/sec: 5414.43 - lr: 0.000007 - momentum: 0.000000 2024-11-27 20:29:07,310 epoch 5 - iter 2/9 - loss 2.71079555 - time (sec): 0.21 - samples/sec: 5510.62 - lr: 0.000008 - momentum: 0.000000 2024-11-27 20:29:07,456 epoch 5 - iter 3/9 - loss 2.68516902 - time (sec): 0.35 - samples/sec: 5081.50 - lr: 0.000008 - momentum: 0.000000 2024-11-27 20:29:07,613 epoch 5 - iter 4/9 - loss 2.69871886 - time (sec): 0.51 - samples/sec: 4937.57 - lr: 0.000008 - momentum: 0.000000 2024-11-27 20:29:07,766 epoch 5 - iter 5/9 - loss 2.65938070 - time (sec): 0.66 - samples/sec: 4810.36 - lr: 0.000008 - momentum: 0.000000 2024-11-27 20:29:07,895 epoch 5 - iter 6/9 - loss 2.60109779 - time (sec): 0.79 - samples/sec: 4598.49 - lr: 0.000008 - momentum: 0.000000 2024-11-27 20:29:08,028 epoch 5 - iter 7/9 - loss 2.60479700 - time (sec): 0.92 - samples/sec: 4562.93 - lr: 0.000009 - momentum: 0.000000 2024-11-27 20:29:08,152 epoch 5 - iter 8/9 - loss 2.57236534 - time (sec): 1.05 - samples/sec: 4499.91 - lr: 0.000009 - momentum: 0.000000 2024-11-27 20:29:08,267 epoch 5 - iter 9/9 - loss 2.54716352 - time (sec): 1.16 - samples/sec: 4466.45 - lr: 0.000009 - momentum: 0.000000 2024-11-27 20:29:08,268 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:29:08,268 EPOCH 5 done: loss 2.5472 - lr: 0.000009 0%| | 0/1 [00:00<?, ?it/s] 100%|███████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 8.06it/s] 100%|███████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 8.04it/s] 2024-11-27 20:29:08,411 DEV : loss 2.0339701175689697 - f1-score (micro avg) 0.0 2024-11-27 20:29:08,412 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:29:08,509 epoch 6 - iter 1/9 - loss 1.99921950 - time (sec): 0.10 - samples/sec: 4896.39 - lr: 0.000009 - momentum: 0.000000 2024-11-27 20:29:08,657 epoch 6 - iter 2/9 - loss 2.07233029 - time (sec): 0.24 - samples/sec: 4068.45 - lr: 0.000009 - momentum: 0.000000 2024-11-27 20:29:08,797 epoch 6 - iter 3/9 - loss 2.24569257 - time (sec): 0.38 - samples/sec: 3883.09 - lr: 0.000010 - momentum: 0.000000 2024-11-27 20:29:08,931 epoch 6 - iter 4/9 - loss 2.44873776 - time (sec): 0.52 - samples/sec: 4055.94 - lr: 0.000010 - momentum: 0.000000 2024-11-27 20:29:09,050 epoch 6 - iter 5/9 - loss 2.41291128 - time (sec): 0.64 - samples/sec: 4140.87 - lr: 0.000010 - momentum: 0.000000 2024-11-27 20:29:09,185 epoch 6 - iter 6/9 - loss 2.36885264 - time (sec): 0.77 - samples/sec: 4233.26 - lr: 0.000010 - momentum: 0.000000 2024-11-27 20:29:09,329 epoch 6 - iter 7/9 - loss 2.32401940 - time (sec): 0.92 - samples/sec: 4237.50 - lr: 0.000010 - momentum: 0.000000 2024-11-27 20:29:09,462 epoch 6 - iter 8/9 - loss 2.36411761 - time (sec): 1.05 - samples/sec: 4469.21 - lr: 0.000011 - momentum: 0.000000 2024-11-27 20:29:09,595 epoch 6 - iter 9/9 - loss 2.33427041 - time (sec): 1.18 - samples/sec: 4397.27 - lr: 0.000011 - momentum: 0.000000 2024-11-27 20:29:09,595 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:29:09,595 EPOCH 6 done: loss 2.3343 - lr: 0.000011 0%| | 0/1 [00:00<?, ?it/s] 100%|███████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 7.09it/s] 100%|███████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 7.08it/s] 2024-11-27 20:29:09,755 DEV : loss 1.879949688911438 - f1-score (micro avg) 0.0 2024-11-27 20:29:09,757 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:29:09,844 epoch 7 - iter 1/9 - loss 2.16848339 - time (sec): 0.09 - samples/sec: 6112.29 - lr: 0.000011 - momentum: 0.000000 2024-11-27 20:29:09,962 epoch 7 - iter 2/9 - loss 2.29448985 - time (sec): 0.20 - samples/sec: 4672.31 - lr: 0.000011 - momentum: 0.000000 2024-11-27 20:29:10,114 epoch 7 - iter 3/9 - loss 2.13111173 - time (sec): 0.36 - samples/sec: 4469.31 - lr: 0.000011 - momentum: 0.000000 2024-11-27 20:29:10,253 epoch 7 - iter 4/9 - loss 2.16561873 - time (sec): 0.50 - samples/sec: 4470.61 - lr: 0.000012 - momentum: 0.000000 2024-11-27 20:29:10,392 epoch 7 - iter 5/9 - loss 2.14808656 - time (sec): 0.63 - samples/sec: 4406.26 - lr: 0.000012 - momentum: 0.000000 2024-11-27 20:29:10,533 epoch 7 - iter 6/9 - loss 2.11914668 - time (sec): 0.78 - samples/sec: 4472.05 - lr: 0.000012 - momentum: 0.000000 2024-11-27 20:29:10,666 epoch 7 - iter 7/9 - loss 2.07698398 - time (sec): 0.91 - samples/sec: 4475.94 - lr: 0.000012 - momentum: 0.000000 2024-11-27 20:29:10,807 epoch 7 - iter 8/9 - loss 2.07106576 - time (sec): 1.05 - samples/sec: 4434.39 - lr: 0.000012 - momentum: 0.000000 2024-11-27 20:29:10,953 epoch 7 - iter 9/9 - loss 2.07483418 - time (sec): 1.20 - samples/sec: 4347.57 - lr: 0.000013 - momentum: 0.000000 2024-11-27 20:29:10,953 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:29:10,953 EPOCH 7 done: loss 2.0748 - lr: 0.000013 0%| | 0/1 [00:00<?, ?it/s] 100%|███████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 7.32it/s] 100%|███████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 7.31it/s] 2024-11-27 20:29:11,109 DEV : loss 1.8713529109954834 - f1-score (micro avg) 0.0632 2024-11-27 20:29:11,110 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:29:11,217 epoch 8 - iter 1/9 - loss 1.87273206 - time (sec): 0.11 - samples/sec: 6649.05 - lr: 0.000013 - momentum: 0.000000 2024-11-27 20:29:11,387 epoch 8 - iter 2/9 - loss 1.78886561 - time (sec): 0.28 - samples/sec: 5059.36 - lr: 0.000013 - momentum: 0.000000 2024-11-27 20:29:11,539 epoch 8 - iter 3/9 - loss 1.84165413 - time (sec): 0.43 - samples/sec: 4463.17 - lr: 0.000013 - momentum: 0.000000 2024-11-27 20:29:11,675 epoch 8 - iter 4/9 - loss 1.84900604 - time (sec): 0.56 - samples/sec: 4660.83 - lr: 0.000013 - momentum: 0.000000 2024-11-27 20:29:11,799 epoch 8 - iter 5/9 - loss 1.85377756 - time (sec): 0.69 - samples/sec: 4475.71 - lr: 0.000014 - momentum: 0.000000 2024-11-27 20:29:11,927 epoch 8 - iter 6/9 - loss 1.84083789 - time (sec): 0.82 - samples/sec: 4361.48 - lr: 0.000014 - momentum: 0.000000 2024-11-27 20:29:12,050 epoch 8 - iter 7/9 - loss 1.84613008 - time (sec): 0.94 - samples/sec: 4277.72 - lr: 0.000014 - momentum: 0.000000 2024-11-27 20:29:12,185 epoch 8 - iter 8/9 - loss 1.86877101 - time (sec): 1.07 - samples/sec: 4227.27 - lr: 0.000014 - momentum: 0.000000 2024-11-27 20:29:12,337 epoch 8 - iter 9/9 - loss 1.88354012 - time (sec): 1.23 - samples/sec: 4238.73 - lr: 0.000014 - momentum: 0.000000 2024-11-27 20:29:12,338 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:29:12,338 EPOCH 8 done: loss 1.8835 - lr: 0.000014 0%| | 0/1 [00:00<?, ?it/s] 100%|███████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 6.43it/s] 100%|███████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 6.42it/s] 2024-11-27 20:29:12,512 DEV : loss 1.7369611263275146 - f1-score (micro avg) 0.2143 2024-11-27 20:29:12,514 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:29:12,613 epoch 9 - iter 1/9 - loss 1.78296490 - time (sec): 0.10 - samples/sec: 5226.98 - lr: 0.000015 - momentum: 0.000000 2024-11-27 20:29:12,752 epoch 9 - iter 2/9 - loss 1.83527719 - time (sec): 0.24 - samples/sec: 4826.98 - lr: 0.000015 - momentum: 0.000000 2024-11-27 20:29:12,900 epoch 9 - iter 3/9 - loss 1.82313075 - time (sec): 0.39 - samples/sec: 4671.66 - lr: 0.000015 - momentum: 0.000000 2024-11-27 20:29:13,038 epoch 9 - iter 4/9 - loss 1.80609907 - time (sec): 0.52 - samples/sec: 4782.25 - lr: 0.000015 - momentum: 0.000000 2024-11-27 20:29:13,167 epoch 9 - iter 5/9 - loss 1.79152546 - time (sec): 0.65 - samples/sec: 4531.94 - lr: 0.000016 - momentum: 0.000000 2024-11-27 20:29:13,294 epoch 9 - iter 6/9 - loss 1.80673774 - time (sec): 0.78 - samples/sec: 4504.62 - lr: 0.000016 - momentum: 0.000000 2024-11-27 20:29:13,430 epoch 9 - iter 7/9 - loss 1.77034694 - time (sec): 0.92 - samples/sec: 4393.34 - lr: 0.000016 - momentum: 0.000000 2024-11-27 20:29:13,592 epoch 9 - iter 8/9 - loss 1.76966631 - time (sec): 1.08 - samples/sec: 4320.26 - lr: 0.000016 - momentum: 0.000000 2024-11-27 20:29:13,745 epoch 9 - iter 9/9 - loss 1.78298214 - time (sec): 1.23 - samples/sec: 4225.88 - lr: 0.000016 - momentum: 0.000000 2024-11-27 20:29:13,745 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:29:13,745 EPOCH 9 done: loss 1.7830 - lr: 0.000016 0%| | 0/1 [00:00<?, ?it/s] 100%|███████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 7.18it/s] 100%|███████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 7.17it/s] 2024-11-27 20:29:13,904 DEV : loss 1.7234623432159424 - f1-score (micro avg) 0.283 2024-11-27 20:29:13,905 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:29:14,020 epoch 10 - iter 1/9 - loss 1.46885790 - time (sec): 0.11 - samples/sec: 6490.95 - lr: 0.000017 - momentum: 0.000000 2024-11-27 20:29:14,193 epoch 10 - iter 2/9 - loss 1.60625023 - time (sec): 0.29 - samples/sec: 4478.17 - lr: 0.000017 - momentum: 0.000000 2024-11-27 20:29:14,339 epoch 10 - iter 3/9 - loss 1.55650434 - time (sec): 0.43 - samples/sec: 4131.59 - lr: 0.000017 - momentum: 0.000000 2024-11-27 20:29:14,489 epoch 10 - iter 4/9 - loss 1.61630698 - time (sec): 0.58 - samples/sec: 4151.85 - lr: 0.000017 - momentum: 0.000000 2024-11-27 20:29:14,629 epoch 10 - iter 5/9 - loss 1.61318645 - time (sec): 0.72 - samples/sec: 4081.29 - lr: 0.000017 - momentum: 0.000000 2024-11-27 20:29:14,767 epoch 10 - iter 6/9 - loss 1.58353285 - time (sec): 0.86 - samples/sec: 3974.33 - lr: 0.000018 - momentum: 0.000000 2024-11-27 20:29:14,913 epoch 10 - iter 7/9 - loss 1.58295703 - time (sec): 1.01 - samples/sec: 4056.63 - lr: 0.000018 - momentum: 0.000000 2024-11-27 20:29:15,191 epoch 10 - iter 8/9 - loss 1.60262613 - time (sec): 1.28 - samples/sec: 3664.89 - lr: 0.000018 - momentum: 0.000000 2024-11-27 20:29:15,323 epoch 10 - iter 9/9 - loss 1.61272190 - time (sec): 1.42 - samples/sec: 3667.08 - lr: 0.000018 - momentum: 0.000000 2024-11-27 20:29:15,323 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:29:15,324 EPOCH 10 done: loss 1.6127 - lr: 0.000018 0%| | 0/1 [00:00<?, ?it/s] 100%|███████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 7.12it/s] 100%|███████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 7.10it/s] 2024-11-27 20:29:15,483 DEV : loss 1.7543907165527344 - f1-score (micro avg) 0.3137 2024-11-27 20:29:15,485 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:29:15,588 epoch 11 - iter 1/9 - loss 1.52427195 - time (sec): 0.10 - samples/sec: 5204.30 - lr: 0.000018 - momentum: 0.000000 2024-11-27 20:29:15,723 epoch 11 - iter 2/9 - loss 1.46047124 - time (sec): 0.24 - samples/sec: 5212.79 - lr: 0.000019 - momentum: 0.000000 2024-11-27 20:29:15,862 epoch 11 - iter 3/9 - loss 1.46857593 - time (sec): 0.38 - samples/sec: 4956.56 - lr: 0.000019 - momentum: 0.000000 2024-11-27 20:29:15,998 epoch 11 - iter 4/9 - loss 1.52389318 - time (sec): 0.51 - samples/sec: 4807.75 - lr: 0.000019 - momentum: 0.000000 2024-11-27 20:29:16,147 epoch 11 - iter 5/9 - loss 1.49680630 - time (sec): 0.66 - samples/sec: 4657.72 - lr: 0.000019 - momentum: 0.000000 2024-11-27 20:29:16,311 epoch 11 - iter 6/9 - loss 1.47908682 - time (sec): 0.82 - samples/sec: 4434.95 - lr: 0.000019 - momentum: 0.000000 2024-11-27 20:29:16,450 epoch 11 - iter 7/9 - loss 1.45410125 - time (sec): 0.96 - samples/sec: 4412.70 - lr: 0.000020 - momentum: 0.000000 2024-11-27 20:29:16,582 epoch 11 - iter 8/9 - loss 1.46786505 - time (sec): 1.10 - samples/sec: 4307.29 - lr: 0.000020 - momentum: 0.000000 2024-11-27 20:29:16,697 epoch 11 - iter 9/9 - loss 1.43482754 - time (sec): 1.21 - samples/sec: 4288.83 - lr: 0.000020 - momentum: 0.000000 2024-11-27 20:29:16,698 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:29:16,698 EPOCH 11 done: loss 1.4348 - lr: 0.000020 0%| | 0/1 [00:00<?, ?it/s] 100%|███████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 7.54it/s] 100%|███████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 7.52it/s] 2024-11-27 20:29:16,851 DEV : loss 1.6048448085784912 - f1-score (micro avg) 0.2807 2024-11-27 20:29:16,852 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:29:16,948 epoch 12 - iter 1/9 - loss 1.23830875 - time (sec): 0.09 - samples/sec: 5886.08 - lr: 0.000020 - momentum: 0.000000 2024-11-27 20:29:17,085 epoch 12 - iter 2/9 - loss 1.30954938 - time (sec): 0.23 - samples/sec: 4903.04 - lr: 0.000020 - momentum: 0.000000 2024-11-27 20:29:17,217 epoch 12 - iter 3/9 - loss 1.34112733 - time (sec): 0.36 - samples/sec: 4459.92 - lr: 0.000021 - momentum: 0.000000 2024-11-27 20:29:17,352 epoch 12 - iter 4/9 - loss 1.41620322 - time (sec): 0.50 - samples/sec: 4311.65 - lr: 0.000021 - momentum: 0.000000 2024-11-27 20:29:17,508 epoch 12 - iter 5/9 - loss 1.37333150 - time (sec): 0.65 - samples/sec: 4390.79 - lr: 0.000021 - momentum: 0.000000 2024-11-27 20:29:17,675 epoch 12 - iter 6/9 - loss 1.31723633 - time (sec): 0.82 - samples/sec: 4343.49 - lr: 0.000021 - momentum: 0.000000 2024-11-27 20:29:17,819 epoch 12 - iter 7/9 - loss 1.32293562 - time (sec): 0.97 - samples/sec: 4212.61 - lr: 0.000021 - momentum: 0.000000 2024-11-27 20:29:17,965 epoch 12 - iter 8/9 - loss 1.33313049 - time (sec): 1.11 - samples/sec: 4164.25 - lr: 0.000022 - momentum: 0.000000 2024-11-27 20:29:18,102 epoch 12 - iter 9/9 - loss 1.34291191 - time (sec): 1.25 - samples/sec: 4160.81 - lr: 0.000022 - momentum: 0.000000 2024-11-27 20:29:18,102 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:29:18,102 EPOCH 12 done: loss 1.3429 - lr: 0.000022 0%| | 0/1 [00:00<?, ?it/s] 100%|███████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 6.72it/s] 100%|███████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 6.71it/s] 2024-11-27 20:29:18,271 DEV : loss 1.5551443099975586 - f1-score (micro avg) 0.2958 2024-11-27 20:29:18,272 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:29:18,382 epoch 13 - iter 1/9 - loss 1.11624752 - time (sec): 0.11 - samples/sec: 5368.20 - lr: 0.000022 - momentum: 0.000000 2024-11-27 20:29:18,522 epoch 13 - iter 2/9 - loss 1.23846520 - time (sec): 0.25 - samples/sec: 4922.43 - lr: 0.000022 - momentum: 0.000000 2024-11-27 20:29:18,652 epoch 13 - iter 3/9 - loss 1.27966323 - time (sec): 0.38 - samples/sec: 4580.73 - lr: 0.000022 - momentum: 0.000000 2024-11-27 20:29:18,775 epoch 13 - iter 4/9 - loss 1.16550886 - time (sec): 0.50 - samples/sec: 4830.16 - lr: 0.000023 - momentum: 0.000000 2024-11-27 20:29:18,914 epoch 13 - iter 5/9 - loss 1.20383874 - time (sec): 0.64 - samples/sec: 4630.94 - lr: 0.000023 - momentum: 0.000000 2024-11-27 20:29:19,042 epoch 13 - iter 6/9 - loss 1.19953740 - time (sec): 0.77 - samples/sec: 4546.74 - lr: 0.000023 - momentum: 0.000000 2024-11-27 20:29:19,161 epoch 13 - iter 7/9 - loss 1.21007009 - time (sec): 0.89 - samples/sec: 4536.14 - lr: 0.000023 - momentum: 0.000000 2024-11-27 20:29:19,292 epoch 13 - iter 8/9 - loss 1.23645585 - time (sec): 1.02 - samples/sec: 4500.64 - lr: 0.000023 - momentum: 0.000000 2024-11-27 20:29:19,439 epoch 13 - iter 9/9 - loss 1.21980619 - time (sec): 1.17 - samples/sec: 4455.40 - lr: 0.000024 - momentum: 0.000000 2024-11-27 20:29:19,440 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:29:19,440 EPOCH 13 done: loss 1.2198 - lr: 0.000024 0%| | 0/1 [00:00<?, ?it/s] 100%|███████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 5.91it/s] 100%|███████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 5.91it/s] 2024-11-27 20:29:19,629 DEV : loss 1.5637989044189453 - f1-score (micro avg) 0.3309 2024-11-27 20:29:19,630 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:29:19,737 epoch 14 - iter 1/9 - loss 1.09814238 - time (sec): 0.11 - samples/sec: 6143.78 - lr: 0.000024 - momentum: 0.000000 2024-11-27 20:29:19,892 epoch 14 - iter 2/9 - loss 1.23113839 - time (sec): 0.26 - samples/sec: 5068.37 - lr: 0.000024 - momentum: 0.000000 2024-11-27 20:29:20,035 epoch 14 - iter 3/9 - loss 1.21173445 - time (sec): 0.40 - samples/sec: 4628.99 - lr: 0.000024 - momentum: 0.000000 2024-11-27 20:29:20,175 epoch 14 - iter 4/9 - loss 1.18221412 - time (sec): 0.54 - samples/sec: 4377.43 - lr: 0.000024 - momentum: 0.000000 2024-11-27 20:29:20,303 epoch 14 - iter 5/9 - loss 1.15910906 - time (sec): 0.67 - samples/sec: 4261.29 - lr: 0.000025 - momentum: 0.000000 2024-11-27 20:29:20,441 epoch 14 - iter 6/9 - loss 1.12550807 - time (sec): 0.81 - samples/sec: 4288.70 - lr: 0.000025 - momentum: 0.000000 2024-11-27 20:29:20,601 epoch 14 - iter 7/9 - loss 1.10136577 - time (sec): 0.97 - samples/sec: 4300.73 - lr: 0.000025 - momentum: 0.000000 2024-11-27 20:29:20,939 epoch 14 - iter 8/9 - loss 1.12143781 - time (sec): 1.31 - samples/sec: 3584.66 - lr: 0.000025 - momentum: 0.000000 2024-11-27 20:29:21,074 epoch 14 - iter 9/9 - loss 1.10769044 - time (sec): 1.44 - samples/sec: 3599.92 - lr: 0.000026 - momentum: 0.000000 2024-11-27 20:29:21,075 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:29:21,075 EPOCH 14 done: loss 1.1077 - lr: 0.000026 0%| | 0/1 [00:00<?, ?it/s] 100%|███████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 7.21it/s] 100%|███████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 7.20it/s] 2024-11-27 20:29:21,233 DEV : loss 1.540261149406433 - f1-score (micro avg) 0.3636 2024-11-27 20:29:21,234 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:29:21,334 epoch 15 - iter 1/9 - loss 1.11011481 - time (sec): 0.10 - samples/sec: 6834.17 - lr: 0.000026 - momentum: 0.000000 2024-11-27 20:29:21,465 epoch 15 - iter 2/9 - loss 1.16364276 - time (sec): 0.23 - samples/sec: 5550.76 - lr: 0.000026 - momentum: 0.000000 2024-11-27 20:29:21,595 epoch 15 - iter 3/9 - loss 1.05183530 - time (sec): 0.36 - samples/sec: 5133.89 - lr: 0.000026 - momentum: 0.000000 2024-11-27 20:29:21,735 epoch 15 - iter 4/9 - loss 1.06076362 - time (sec): 0.50 - samples/sec: 4756.13 - lr: 0.000026 - momentum: 0.000000 2024-11-27 20:29:21,878 epoch 15 - iter 5/9 - loss 1.01150052 - time (sec): 0.64 - samples/sec: 4512.08 - lr: 0.000027 - momentum: 0.000000 2024-11-27 20:29:22,022 epoch 15 - iter 6/9 - loss 1.00936649 - time (sec): 0.79 - samples/sec: 4340.66 - lr: 0.000027 - momentum: 0.000000 2024-11-27 20:29:22,171 epoch 15 - iter 7/9 - loss 0.98042386 - time (sec): 0.94 - samples/sec: 4236.16 - lr: 0.000027 - momentum: 0.000000 2024-11-27 20:29:22,328 epoch 15 - iter 8/9 - loss 0.97703855 - time (sec): 1.09 - samples/sec: 4183.64 - lr: 0.000027 - momentum: 0.000000 2024-11-27 20:29:22,482 epoch 15 - iter 9/9 - loss 0.96891336 - time (sec): 1.25 - samples/sec: 4168.17 - lr: 0.000027 - momentum: 0.000000 2024-11-27 20:29:22,482 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:29:22,482 EPOCH 15 done: loss 0.9689 - lr: 0.000027 0%| | 0/1 [00:00<?, ?it/s] 100%|███████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 7.08it/s] 100%|███████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 7.06it/s] 2024-11-27 20:29:22,643 DEV : loss 1.6106945276260376 - f1-score (micro avg) 0.3566 2024-11-27 20:29:22,644 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:29:22,743 epoch 16 - iter 1/9 - loss 0.67864396 - time (sec): 0.10 - samples/sec: 6373.81 - lr: 0.000028 - momentum: 0.000000 2024-11-27 20:29:22,878 epoch 16 - iter 2/9 - loss 0.72796478 - time (sec): 0.23 - samples/sec: 5037.74 - lr: 0.000028 - momentum: 0.000000 2024-11-27 20:29:23,015 epoch 16 - iter 3/9 - loss 0.71037902 - time (sec): 0.37 - samples/sec: 4669.28 - lr: 0.000028 - momentum: 0.000000 2024-11-27 20:29:23,166 epoch 16 - iter 4/9 - loss 0.76522151 - time (sec): 0.52 - samples/sec: 4543.61 - lr: 0.000028 - momentum: 0.000000 2024-11-27 20:29:23,366 epoch 16 - iter 5/9 - loss 0.77929607 - time (sec): 0.72 - samples/sec: 4089.48 - lr: 0.000028 - momentum: 0.000000 2024-11-27 20:29:23,591 epoch 16 - iter 6/9 - loss 0.81672054 - time (sec): 0.95 - samples/sec: 3793.74 - lr: 0.000029 - momentum: 0.000000 2024-11-27 20:29:23,734 epoch 16 - iter 7/9 - loss 0.81104267 - time (sec): 1.09 - samples/sec: 3849.61 - lr: 0.000029 - momentum: 0.000000 2024-11-27 20:29:23,874 epoch 16 - iter 8/9 - loss 0.81759425 - time (sec): 1.23 - samples/sec: 3902.58 - lr: 0.000029 - momentum: 0.000000 2024-11-27 20:29:23,998 epoch 16 - iter 9/9 - loss 0.82073339 - time (sec): 1.35 - samples/sec: 3841.03 - lr: 0.000029 - momentum: 0.000000 2024-11-27 20:29:23,998 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:29:23,998 EPOCH 16 done: loss 0.8207 - lr: 0.000029 0%| | 0/1 [00:00<?, ?it/s] 100%|███████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 7.67it/s] 100%|███████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 7.65it/s] 2024-11-27 20:29:24,148 DEV : loss 1.5810456275939941 - f1-score (micro avg) 0.3407 2024-11-27 20:29:24,149 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:29:24,250 epoch 17 - iter 1/9 - loss 0.57284213 - time (sec): 0.10 - samples/sec: 5972.17 - lr: 0.000029 - momentum: 0.000000 2024-11-27 20:29:24,399 epoch 17 - iter 2/9 - loss 0.65595718 - time (sec): 0.25 - samples/sec: 5032.29 - lr: 0.000030 - momentum: 0.000000 2024-11-27 20:29:24,550 epoch 17 - iter 3/9 - loss 0.67987346 - time (sec): 0.40 - samples/sec: 4503.70 - lr: 0.000030 - momentum: 0.000000 2024-11-27 20:29:24,700 epoch 17 - iter 4/9 - loss 0.66112536 - time (sec): 0.55 - samples/sec: 4500.44 - lr: 0.000030 - momentum: 0.000000 2024-11-27 20:29:24,833 epoch 17 - iter 5/9 - loss 0.69180893 - time (sec): 0.68 - samples/sec: 4331.86 - lr: 0.000030 - momentum: 0.000000 2024-11-27 20:29:24,961 epoch 17 - iter 6/9 - loss 0.67681233 - time (sec): 0.81 - samples/sec: 4301.68 - lr: 0.000030 - momentum: 0.000000 2024-11-27 20:29:25,101 epoch 17 - iter 7/9 - loss 0.68173757 - time (sec): 0.95 - samples/sec: 4266.12 - lr: 0.000031 - momentum: 0.000000 2024-11-27 20:29:25,245 epoch 17 - iter 8/9 - loss 0.67496161 - time (sec): 1.09 - samples/sec: 4273.66 - lr: 0.000031 - momentum: 0.000000 2024-11-27 20:29:25,386 epoch 17 - iter 9/9 - loss 0.68725066 - time (sec): 1.24 - samples/sec: 4207.20 - lr: 0.000031 - momentum: 0.000000 2024-11-27 20:29:25,386 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:29:25,386 EPOCH 17 done: loss 0.6873 - lr: 0.000031 0%| | 0/1 [00:00<?, ?it/s] 100%|███████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 6.62it/s] 100%|███████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 6.61it/s] 2024-11-27 20:29:25,557 DEV : loss 1.642511010169983 - f1-score (micro avg) 0.3566 2024-11-27 20:29:25,558 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:29:25,649 epoch 18 - iter 1/9 - loss 0.78564389 - time (sec): 0.09 - samples/sec: 5264.33 - lr: 0.000031 - momentum: 0.000000 2024-11-27 20:29:25,785 epoch 18 - iter 2/9 - loss 0.71524547 - time (sec): 0.23 - samples/sec: 4686.82 - lr: 0.000031 - momentum: 0.000000 2024-11-27 20:29:25,929 epoch 18 - iter 3/9 - loss 0.70257258 - time (sec): 0.37 - samples/sec: 4767.31 - lr: 0.000032 - momentum: 0.000000 2024-11-27 20:29:26,066 epoch 18 - iter 4/9 - loss 0.68090267 - time (sec): 0.51 - samples/sec: 4520.05 - lr: 0.000032 - momentum: 0.000000 2024-11-27 20:29:26,208 epoch 18 - iter 5/9 - loss 0.65315040 - time (sec): 0.65 - samples/sec: 4438.17 - lr: 0.000032 - momentum: 0.000000 2024-11-27 20:29:26,340 epoch 18 - iter 6/9 - loss 0.64000930 - time (sec): 0.78 - samples/sec: 4307.33 - lr: 0.000032 - momentum: 0.000000 2024-11-27 20:29:26,475 epoch 18 - iter 7/9 - loss 0.63304207 - time (sec): 0.92 - samples/sec: 4414.64 - lr: 0.000032 - momentum: 0.000000 2024-11-27 20:29:26,620 epoch 18 - iter 8/9 - loss 0.60347502 - time (sec): 1.06 - samples/sec: 4371.89 - lr: 0.000033 - momentum: 0.000000 2024-11-27 20:29:26,775 epoch 18 - iter 9/9 - loss 0.58457908 - time (sec): 1.22 - samples/sec: 4272.77 - lr: 0.000033 - momentum: 0.000000 2024-11-27 20:29:26,776 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:29:26,776 EPOCH 18 done: loss 0.5846 - lr: 0.000033 0%| | 0/1 [00:00<?, ?it/s] 100%|███████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 6.02it/s] 100%|███████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 6.02it/s] 2024-11-27 20:29:26,962 DEV : loss 1.6325932741165161 - f1-score (micro avg) 0.3288 2024-11-27 20:29:26,963 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:29:27,187 epoch 19 - iter 1/9 - loss 0.53870540 - time (sec): 0.22 - samples/sec: 2532.70 - lr: 0.000033 - momentum: 0.000000 2024-11-27 20:29:27,338 epoch 19 - iter 2/9 - loss 0.51635178 - time (sec): 0.37 - samples/sec: 3098.46 - lr: 0.000033 - momentum: 0.000000 2024-11-27 20:29:27,469 epoch 19 - iter 3/9 - loss 0.47709909 - time (sec): 0.51 - samples/sec: 3382.05 - lr: 0.000033 - momentum: 0.000000 2024-11-27 20:29:27,613 epoch 19 - iter 4/9 - loss 0.52798308 - time (sec): 0.65 - samples/sec: 3560.79 - lr: 0.000034 - momentum: 0.000000 2024-11-27 20:29:27,758 epoch 19 - iter 5/9 - loss 0.50519193 - time (sec): 0.79 - samples/sec: 3621.64 - lr: 0.000034 - momentum: 0.000000 2024-11-27 20:29:27,894 epoch 19 - iter 6/9 - loss 0.50885023 - time (sec): 0.93 - samples/sec: 3723.01 - lr: 0.000034 - momentum: 0.000000 2024-11-27 20:29:28,040 epoch 19 - iter 7/9 - loss 0.47256950 - time (sec): 1.08 - samples/sec: 3776.15 - lr: 0.000034 - momentum: 0.000000 2024-11-27 20:29:28,202 epoch 19 - iter 8/9 - loss 0.45971542 - time (sec): 1.24 - samples/sec: 3769.89 - lr: 0.000034 - momentum: 0.000000 2024-11-27 20:29:28,359 epoch 19 - iter 9/9 - loss 0.46459373 - time (sec): 1.39 - samples/sec: 3726.52 - lr: 0.000035 - momentum: 0.000000 2024-11-27 20:29:28,359 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:29:28,359 EPOCH 19 done: loss 0.4646 - lr: 0.000035 0%| | 0/1 [00:00<?, ?it/s] 100%|███████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 6.71it/s] 100%|███████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 6.70it/s] 2024-11-27 20:29:28,528 DEV : loss 1.651373267173767 - f1-score (micro avg) 0.3194 2024-11-27 20:29:28,529 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:29:28,646 epoch 20 - iter 1/9 - loss 0.30202963 - time (sec): 0.12 - samples/sec: 5715.91 - lr: 0.000035 - momentum: 0.000000 2024-11-27 20:29:28,807 epoch 20 - iter 2/9 - loss 0.36676713 - time (sec): 0.28 - samples/sec: 4391.02 - lr: 0.000035 - momentum: 0.000000 2024-11-27 20:29:28,943 epoch 20 - iter 3/9 - loss 0.38591658 - time (sec): 0.41 - samples/sec: 4185.20 - lr: 0.000035 - momentum: 0.000000 2024-11-27 20:29:29,098 epoch 20 - iter 4/9 - loss 0.34878419 - time (sec): 0.57 - samples/sec: 4010.76 - lr: 0.000036 - momentum: 0.000000 2024-11-27 20:29:29,259 epoch 20 - iter 5/9 - loss 0.38364523 - time (sec): 0.73 - samples/sec: 3905.49 - lr: 0.000036 - momentum: 0.000000 2024-11-27 20:29:29,482 epoch 20 - iter 6/9 - loss 0.38373751 - time (sec): 0.95 - samples/sec: 3557.29 - lr: 0.000036 - momentum: 0.000000 2024-11-27 20:29:29,635 epoch 20 - iter 7/9 - loss 0.41862790 - time (sec): 1.11 - samples/sec: 3673.81 - lr: 0.000036 - momentum: 0.000000 2024-11-27 20:29:29,756 epoch 20 - iter 8/9 - loss 0.41846545 - time (sec): 1.23 - samples/sec: 3742.62 - lr: 0.000036 - momentum: 0.000000 2024-11-27 20:29:29,883 epoch 20 - iter 9/9 - loss 0.39449129 - time (sec): 1.35 - samples/sec: 3840.69 - lr: 0.000037 - momentum: 0.000000 2024-11-27 20:29:29,883 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:29:29,884 EPOCH 20 done: loss 0.3945 - lr: 0.000037 0%| | 0/1 [00:00<?, ?it/s] 100%|███████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 6.71it/s] 100%|███████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 6.70it/s] 2024-11-27 20:29:30,052 DEV : loss 1.719744086265564 - f1-score (micro avg) 0.3288 2024-11-27 20:29:30,053 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:29:30,215 epoch 21 - iter 1/9 - loss 0.30412179 - time (sec): 0.16 - samples/sec: 3791.18 - lr: 0.000037 - momentum: 0.000000 2024-11-27 20:29:30,406 epoch 21 - iter 2/9 - loss 0.32552722 - time (sec): 0.35 - samples/sec: 3492.84 - lr: 0.000037 - momentum: 0.000000 2024-11-27 20:29:30,575 epoch 21 - iter 3/9 - loss 0.32240375 - time (sec): 0.52 - samples/sec: 3727.70 - lr: 0.000037 - momentum: 0.000000 2024-11-27 20:29:30,715 epoch 21 - iter 4/9 - loss 0.31591572 - time (sec): 0.66 - samples/sec: 3710.26 - lr: 0.000037 - momentum: 0.000000 2024-11-27 20:29:30,837 epoch 21 - iter 5/9 - loss 0.31931353 - time (sec): 0.78 - samples/sec: 3769.45 - lr: 0.000038 - momentum: 0.000000 2024-11-27 20:29:31,026 epoch 21 - iter 6/9 - loss 0.32774859 - time (sec): 0.97 - samples/sec: 3581.98 - lr: 0.000038 - momentum: 0.000000 2024-11-27 20:29:31,179 epoch 21 - iter 7/9 - loss 0.33016453 - time (sec): 1.12 - samples/sec: 3622.03 - lr: 0.000038 - momentum: 0.000000 2024-11-27 20:29:31,330 epoch 21 - iter 8/9 - loss 0.33195475 - time (sec): 1.28 - samples/sec: 3720.72 - lr: 0.000038 - momentum: 0.000000 2024-11-27 20:29:31,452 epoch 21 - iter 9/9 - loss 0.32063925 - time (sec): 1.40 - samples/sec: 3719.95 - lr: 0.000038 - momentum: 0.000000 2024-11-27 20:29:31,452 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:29:31,452 EPOCH 21 done: loss 0.3206 - lr: 0.000038 0%| | 0/1 [00:00<?, ?it/s] 100%|███████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 7.61it/s] 100%|███████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 7.59it/s] 2024-11-27 20:29:31,604 DEV : loss 1.8332433700561523 - f1-score (micro avg) 0.2822 2024-11-27 20:29:31,605 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:29:31,706 epoch 22 - iter 1/9 - loss 0.24405557 - time (sec): 0.10 - samples/sec: 6419.31 - lr: 0.000039 - momentum: 0.000000 2024-11-27 20:29:31,848 epoch 22 - iter 2/9 - loss 0.31744915 - time (sec): 0.24 - samples/sec: 5289.88 - lr: 0.000039 - momentum: 0.000000 2024-11-27 20:29:31,992 epoch 22 - iter 3/9 - loss 0.29536304 - time (sec): 0.39 - samples/sec: 4783.02 - lr: 0.000039 - momentum: 0.000000 2024-11-27 20:29:32,130 epoch 22 - iter 4/9 - loss 0.28426973 - time (sec): 0.52 - samples/sec: 4635.63 - lr: 0.000039 - momentum: 0.000000 2024-11-27 20:29:32,272 epoch 22 - iter 5/9 - loss 0.29420009 - time (sec): 0.67 - samples/sec: 4491.02 - lr: 0.000039 - momentum: 0.000000 2024-11-27 20:29:32,403 epoch 22 - iter 6/9 - loss 0.28778741 - time (sec): 0.80 - samples/sec: 4517.52 - lr: 0.000040 - momentum: 0.000000 2024-11-27 20:29:32,571 epoch 22 - iter 7/9 - loss 0.28940440 - time (sec): 0.96 - samples/sec: 4237.50 - lr: 0.000040 - momentum: 0.000000 2024-11-27 20:29:32,743 epoch 22 - iter 8/9 - loss 0.27989311 - time (sec): 1.14 - samples/sec: 4071.97 - lr: 0.000040 - momentum: 0.000000 2024-11-27 20:29:32,881 epoch 22 - iter 9/9 - loss 0.28181222 - time (sec): 1.27 - samples/sec: 4076.74 - lr: 0.000040 - momentum: 0.000000 2024-11-27 20:29:32,881 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:29:32,881 EPOCH 22 done: loss 0.2818 - lr: 0.000040 0%| | 0/1 [00:00<?, ?it/s] 100%|███████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 6.72it/s] 100%|███████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 6.71it/s] 2024-11-27 20:29:33,049 DEV : loss 1.7695988416671753 - f1-score (micro avg) 0.3253 2024-11-27 20:29:33,050 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:29:33,142 epoch 23 - iter 1/9 - loss 0.14634586 - time (sec): 0.09 - samples/sec: 6101.15 - lr: 0.000040 - momentum: 0.000000 2024-11-27 20:29:33,287 epoch 23 - iter 2/9 - loss 0.25852382 - time (sec): 0.24 - samples/sec: 5068.61 - lr: 0.000040 - momentum: 0.000000 2024-11-27 20:29:33,441 epoch 23 - iter 3/9 - loss 0.25600427 - time (sec): 0.39 - samples/sec: 4862.03 - lr: 0.000040 - momentum: 0.000000 2024-11-27 20:29:33,581 epoch 23 - iter 4/9 - loss 0.24798095 - time (sec): 0.53 - samples/sec: 4521.24 - lr: 0.000040 - momentum: 0.000000 2024-11-27 20:29:33,717 epoch 23 - iter 5/9 - loss 0.25810789 - time (sec): 0.67 - samples/sec: 4455.79 - lr: 0.000040 - momentum: 0.000000 2024-11-27 20:29:33,863 epoch 23 - iter 6/9 - loss 0.25028436 - time (sec): 0.81 - samples/sec: 4386.94 - lr: 0.000040 - momentum: 0.000000 2024-11-27 20:29:34,029 epoch 23 - iter 7/9 - loss 0.24810417 - time (sec): 0.98 - samples/sec: 4278.31 - lr: 0.000040 - momentum: 0.000000 2024-11-27 20:29:34,180 epoch 23 - iter 8/9 - loss 0.24774735 - time (sec): 1.13 - samples/sec: 4167.37 - lr: 0.000040 - momentum: 0.000000 2024-11-27 20:29:34,312 epoch 23 - iter 9/9 - loss 0.24613656 - time (sec): 1.26 - samples/sec: 4123.52 - lr: 0.000040 - momentum: 0.000000 2024-11-27 20:29:34,312 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:29:34,312 EPOCH 23 done: loss 0.2461 - lr: 0.000040 0%| | 0/1 [00:00<?, ?it/s] 100%|███████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 6.67it/s] 100%|███████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 6.66it/s] 2024-11-27 20:29:34,482 DEV : loss 1.8034638166427612 - f1-score (micro avg) 0.3023 2024-11-27 20:29:34,483 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:29:34,584 epoch 24 - iter 1/9 - loss 0.25845982 - time (sec): 0.10 - samples/sec: 5467.87 - lr: 0.000040 - momentum: 0.000000 2024-11-27 20:29:34,723 epoch 24 - iter 2/9 - loss 0.29897947 - time (sec): 0.24 - samples/sec: 4874.32 - lr: 0.000040 - momentum: 0.000000 2024-11-27 20:29:34,860 epoch 24 - iter 3/9 - loss 0.26403058 - time (sec): 0.38 - samples/sec: 4816.05 - lr: 0.000040 - momentum: 0.000000 2024-11-27 20:29:35,020 epoch 24 - iter 4/9 - loss 0.26099352 - time (sec): 0.54 - samples/sec: 4582.85 - lr: 0.000040 - momentum: 0.000000 2024-11-27 20:29:35,222 epoch 24 - iter 5/9 - loss 0.23768698 - time (sec): 0.74 - samples/sec: 4222.11 - lr: 0.000040 - momentum: 0.000000 2024-11-27 20:29:35,400 epoch 24 - iter 6/9 - loss 0.22878765 - time (sec): 0.92 - samples/sec: 3924.56 - lr: 0.000040 - momentum: 0.000000 2024-11-27 20:29:35,538 epoch 24 - iter 7/9 - loss 0.22962068 - time (sec): 1.05 - samples/sec: 3980.59 - lr: 0.000040 - momentum: 0.000000 2024-11-27 20:29:35,875 epoch 24 - iter 8/9 - loss 0.22404527 - time (sec): 1.39 - samples/sec: 3372.86 - lr: 0.000040 - momentum: 0.000000 2024-11-27 20:29:35,993 epoch 24 - iter 9/9 - loss 0.22333034 - time (sec): 1.51 - samples/sec: 3445.02 - lr: 0.000040 - momentum: 0.000000 2024-11-27 20:29:35,993 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:29:35,993 EPOCH 24 done: loss 0.2233 - lr: 0.000040 0%| | 0/1 [00:00<?, ?it/s] 100%|███████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 6.91it/s] 100%|███████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 6.90it/s] 2024-11-27 20:29:36,157 DEV : loss 1.8028219938278198 - f1-score (micro avg) 0.3247 2024-11-27 20:29:36,158 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:29:36,255 epoch 25 - iter 1/9 - loss 0.24806407 - time (sec): 0.10 - samples/sec: 6177.16 - lr: 0.000040 - momentum: 0.000000 2024-11-27 20:29:36,401 epoch 25 - iter 2/9 - loss 0.19669651 - time (sec): 0.24 - samples/sec: 4667.18 - lr: 0.000040 - momentum: 0.000000 2024-11-27 20:29:36,553 epoch 25 - iter 3/9 - loss 0.19849301 - time (sec): 0.39 - samples/sec: 4246.29 - lr: 0.000040 - momentum: 0.000000 2024-11-27 20:29:36,689 epoch 25 - iter 4/9 - loss 0.19590233 - time (sec): 0.53 - samples/sec: 4149.50 - lr: 0.000039 - momentum: 0.000000 2024-11-27 20:29:36,836 epoch 25 - iter 5/9 - loss 0.19105098 - time (sec): 0.68 - samples/sec: 4252.05 - lr: 0.000039 - momentum: 0.000000 2024-11-27 20:29:37,019 epoch 25 - iter 6/9 - loss 0.19283279 - time (sec): 0.86 - samples/sec: 4141.69 - lr: 0.000039 - momentum: 0.000000 2024-11-27 20:29:37,180 epoch 25 - iter 7/9 - loss 0.18422220 - time (sec): 1.02 - samples/sec: 4137.26 - lr: 0.000039 - momentum: 0.000000 2024-11-27 20:29:37,317 epoch 25 - iter 8/9 - loss 0.18291770 - time (sec): 1.16 - samples/sec: 4017.65 - lr: 0.000039 - momentum: 0.000000 2024-11-27 20:29:37,440 epoch 25 - iter 9/9 - loss 0.18873051 - time (sec): 1.28 - samples/sec: 4056.18 - lr: 0.000039 - momentum: 0.000000 2024-11-27 20:29:37,441 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:29:37,441 EPOCH 25 done: loss 0.1887 - lr: 0.000039 0%| | 0/1 [00:00<?, ?it/s] 100%|███████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 4.21it/s] 100%|███████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 4.20it/s] 2024-11-27 20:29:37,698 DEV : loss 2.215428590774536 - f1-score (micro avg) 0.3538 2024-11-27 20:29:37,699 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:29:37,794 epoch 26 - iter 1/9 - loss 0.23973020 - time (sec): 0.09 - samples/sec: 5360.71 - lr: 0.000039 - momentum: 0.000000 2024-11-27 20:29:37,939 epoch 26 - iter 2/9 - loss 0.19144385 - time (sec): 0.24 - samples/sec: 4925.00 - lr: 0.000039 - momentum: 0.000000 2024-11-27 20:29:38,071 epoch 26 - iter 3/9 - loss 0.22279702 - time (sec): 0.37 - samples/sec: 4738.92 - lr: 0.000039 - momentum: 0.000000 2024-11-27 20:29:38,212 epoch 26 - iter 4/9 - loss 0.19676925 - time (sec): 0.51 - samples/sec: 4588.61 - lr: 0.000039 - momentum: 0.000000 2024-11-27 20:29:38,518 epoch 26 - iter 5/9 - loss 0.19104402 - time (sec): 0.82 - samples/sec: 3603.09 - lr: 0.000039 - momentum: 0.000000 2024-11-27 20:29:38,655 epoch 26 - iter 6/9 - loss 0.20646592 - time (sec): 0.96 - samples/sec: 3680.52 - lr: 0.000039 - momentum: 0.000000 2024-11-27 20:29:38,808 epoch 26 - iter 7/9 - loss 0.21389936 - time (sec): 1.11 - samples/sec: 3815.81 - lr: 0.000039 - momentum: 0.000000 2024-11-27 20:29:38,971 epoch 26 - iter 8/9 - loss 0.20860614 - time (sec): 1.27 - samples/sec: 3734.11 - lr: 0.000039 - momentum: 0.000000 2024-11-27 20:29:39,098 epoch 26 - iter 9/9 - loss 0.20370074 - time (sec): 1.40 - samples/sec: 3716.57 - lr: 0.000039 - momentum: 0.000000 2024-11-27 20:29:39,098 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:29:39,099 EPOCH 26 done: loss 0.2037 - lr: 0.000039 0%| | 0/1 [00:00<?, ?it/s] 100%|███████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 6.06it/s] 100%|███████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 6.05it/s] 2024-11-27 20:29:39,283 DEV : loss 1.8412730693817139 - f1-score (micro avg) 0.2994 2024-11-27 20:29:39,285 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:29:39,398 epoch 27 - iter 1/9 - loss 0.12948648 - time (sec): 0.11 - samples/sec: 5552.87 - lr: 0.000039 - momentum: 0.000000 2024-11-27 20:29:39,545 epoch 27 - iter 2/9 - loss 0.12638788 - time (sec): 0.26 - samples/sec: 4350.09 - lr: 0.000039 - momentum: 0.000000 2024-11-27 20:29:39,682 epoch 27 - iter 3/9 - loss 0.11755740 - time (sec): 0.40 - samples/sec: 4644.71 - lr: 0.000039 - momentum: 0.000000 2024-11-27 20:29:39,822 epoch 27 - iter 4/9 - loss 0.13916747 - time (sec): 0.54 - samples/sec: 4427.71 - lr: 0.000039 - momentum: 0.000000 2024-11-27 20:29:39,964 epoch 27 - iter 5/9 - loss 0.15252048 - time (sec): 0.68 - samples/sec: 4430.36 - lr: 0.000039 - momentum: 0.000000 2024-11-27 20:29:40,081 epoch 27 - iter 6/9 - loss 0.14197444 - time (sec): 0.80 - samples/sec: 4415.32 - lr: 0.000039 - momentum: 0.000000 2024-11-27 20:29:40,215 epoch 27 - iter 7/9 - loss 0.13497825 - time (sec): 0.93 - samples/sec: 4436.88 - lr: 0.000039 - momentum: 0.000000 2024-11-27 20:29:40,347 epoch 27 - iter 8/9 - loss 0.13609403 - time (sec): 1.06 - samples/sec: 4273.69 - lr: 0.000039 - momentum: 0.000000 2024-11-27 20:29:40,466 epoch 27 - iter 9/9 - loss 0.14042081 - time (sec): 1.18 - samples/sec: 4402.51 - lr: 0.000039 - momentum: 0.000000 2024-11-27 20:29:40,466 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:29:40,467 EPOCH 27 done: loss 0.1404 - lr: 0.000039 0%| | 0/1 [00:00<?, ?it/s] 100%|███████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 7.30it/s] 100%|███████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 7.28it/s] 2024-11-27 20:29:40,623 DEV : loss 1.8396930694580078 - f1-score (micro avg) 0.3185 2024-11-27 20:29:40,624 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:29:40,727 epoch 28 - iter 1/9 - loss 0.24403885 - time (sec): 0.10 - samples/sec: 5379.31 - lr: 0.000039 - momentum: 0.000000 2024-11-27 20:29:40,880 epoch 28 - iter 2/9 - loss 0.17667473 - time (sec): 0.25 - samples/sec: 5140.13 - lr: 0.000039 - momentum: 0.000000 2024-11-27 20:29:41,113 epoch 28 - iter 3/9 - loss 0.15627949 - time (sec): 0.49 - samples/sec: 3843.23 - lr: 0.000039 - momentum: 0.000000 2024-11-27 20:29:41,258 epoch 28 - iter 4/9 - loss 0.14060784 - time (sec): 0.63 - samples/sec: 3720.43 - lr: 0.000039 - momentum: 0.000000 2024-11-27 20:29:41,394 epoch 28 - iter 5/9 - loss 0.13880241 - time (sec): 0.77 - samples/sec: 4005.51 - lr: 0.000039 - momentum: 0.000000 2024-11-27 20:29:41,553 epoch 28 - iter 6/9 - loss 0.13416378 - time (sec): 0.93 - samples/sec: 3908.93 - lr: 0.000039 - momentum: 0.000000 2024-11-27 20:29:41,737 epoch 28 - iter 7/9 - loss 0.12297955 - time (sec): 1.11 - samples/sec: 3757.31 - lr: 0.000039 - momentum: 0.000000 2024-11-27 20:29:41,884 epoch 28 - iter 8/9 - loss 0.12000340 - time (sec): 1.26 - samples/sec: 3760.07 - lr: 0.000039 - momentum: 0.000000 2024-11-27 20:29:42,018 epoch 28 - iter 9/9 - loss 0.11764506 - time (sec): 1.39 - samples/sec: 3730.75 - lr: 0.000039 - momentum: 0.000000 2024-11-27 20:29:42,019 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:29:42,019 EPOCH 28 done: loss 0.1176 - lr: 0.000039 0%| | 0/1 [00:00<?, ?it/s] 100%|███████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 6.94it/s] 100%|███████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 6.93it/s] 2024-11-27 20:29:42,182 DEV : loss 2.0064477920532227 - f1-score (micro avg) 0.3158 2024-11-27 20:29:42,183 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:29:42,276 epoch 29 - iter 1/9 - loss 0.07072657 - time (sec): 0.09 - samples/sec: 5193.55 - lr: 0.000039 - momentum: 0.000000 2024-11-27 20:29:42,405 epoch 29 - iter 2/9 - loss 0.08915551 - time (sec): 0.22 - samples/sec: 4368.92 - lr: 0.000039 - momentum: 0.000000 2024-11-27 20:29:42,550 epoch 29 - iter 3/9 - loss 0.11660870 - time (sec): 0.37 - samples/sec: 4596.60 - lr: 0.000039 - momentum: 0.000000 2024-11-27 20:29:42,705 epoch 29 - iter 4/9 - loss 0.11134081 - time (sec): 0.52 - samples/sec: 4447.33 - lr: 0.000039 - momentum: 0.000000 2024-11-27 20:29:42,846 epoch 29 - iter 5/9 - loss 0.10819549 - time (sec): 0.66 - samples/sec: 4463.15 - lr: 0.000039 - momentum: 0.000000 2024-11-27 20:29:42,991 epoch 29 - iter 6/9 - loss 0.10099508 - time (sec): 0.81 - samples/sec: 4469.02 - lr: 0.000039 - momentum: 0.000000 2024-11-27 20:29:43,134 epoch 29 - iter 7/9 - loss 0.10101614 - time (sec): 0.95 - samples/sec: 4313.01 - lr: 0.000039 - momentum: 0.000000 2024-11-27 20:29:43,276 epoch 29 - iter 8/9 - loss 0.10052274 - time (sec): 1.09 - samples/sec: 4340.85 - lr: 0.000039 - momentum: 0.000000 2024-11-27 20:29:43,423 epoch 29 - iter 9/9 - loss 0.10270482 - time (sec): 1.24 - samples/sec: 4195.91 - lr: 0.000039 - momentum: 0.000000 2024-11-27 20:29:43,423 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:29:43,423 EPOCH 29 done: loss 0.1027 - lr: 0.000039 0%| | 0/1 [00:00<?, ?it/s] 100%|███████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 6.72it/s] 100%|███████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 6.71it/s] 2024-11-27 20:29:43,592 DEV : loss 1.974439263343811 - f1-score (micro avg) 0.3293 2024-11-27 20:29:43,593 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:29:43,685 epoch 30 - iter 1/9 - loss 0.08529913 - time (sec): 0.09 - samples/sec: 6360.00 - lr: 0.000039 - momentum: 0.000000 2024-11-27 20:29:43,818 epoch 30 - iter 2/9 - loss 0.08772351 - time (sec): 0.22 - samples/sec: 5357.69 - lr: 0.000039 - momentum: 0.000000 2024-11-27 20:29:43,953 epoch 30 - iter 3/9 - loss 0.08385826 - time (sec): 0.36 - samples/sec: 5083.11 - lr: 0.000038 - momentum: 0.000000 2024-11-27 20:29:44,094 epoch 30 - iter 4/9 - loss 0.08394754 - time (sec): 0.50 - samples/sec: 4780.55 - lr: 0.000038 - momentum: 0.000000 2024-11-27 20:29:44,263 epoch 30 - iter 5/9 - loss 0.08671976 - time (sec): 0.67 - samples/sec: 4369.41 - lr: 0.000038 - momentum: 0.000000 2024-11-27 20:29:44,463 epoch 30 - iter 6/9 - loss 0.08464771 - time (sec): 0.87 - samples/sec: 4174.60 - lr: 0.000038 - momentum: 0.000000 2024-11-27 20:29:44,669 epoch 30 - iter 7/9 - loss 0.08866241 - time (sec): 1.08 - samples/sec: 3877.27 - lr: 0.000038 - momentum: 0.000000 2024-11-27 20:29:44,800 epoch 30 - iter 8/9 - loss 0.08949286 - time (sec): 1.21 - samples/sec: 3890.58 - lr: 0.000038 - momentum: 0.000000 2024-11-27 20:29:44,930 epoch 30 - iter 9/9 - loss 0.08734323 - time (sec): 1.34 - samples/sec: 3888.62 - lr: 0.000038 - momentum: 0.000000 2024-11-27 20:29:44,931 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:29:44,931 EPOCH 30 done: loss 0.0873 - lr: 0.000038 0%| | 0/1 [00:00<?, ?it/s] 100%|███████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 6.39it/s] 100%|███████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 6.38it/s] 2024-11-27 20:29:45,107 DEV : loss 1.9621577262878418 - f1-score (micro avg) 0.284 2024-11-27 20:29:45,108 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:29:45,206 epoch 31 - iter 1/9 - loss 0.10894401 - time (sec): 0.10 - samples/sec: 5638.78 - lr: 0.000038 - momentum: 0.000000 2024-11-27 20:29:45,331 epoch 31 - iter 2/9 - loss 0.06853830 - time (sec): 0.22 - samples/sec: 4903.57 - lr: 0.000038 - momentum: 0.000000 2024-11-27 20:29:45,487 epoch 31 - iter 3/9 - loss 0.06072976 - time (sec): 0.38 - samples/sec: 4275.49 - lr: 0.000038 - momentum: 0.000000 2024-11-27 20:29:45,629 epoch 31 - iter 4/9 - loss 0.05827872 - time (sec): 0.52 - samples/sec: 4191.66 - lr: 0.000038 - momentum: 0.000000 2024-11-27 20:29:45,812 epoch 31 - iter 5/9 - loss 0.06146793 - time (sec): 0.70 - samples/sec: 3902.80 - lr: 0.000038 - momentum: 0.000000 2024-11-27 20:29:45,960 epoch 31 - iter 6/9 - loss 0.05644323 - time (sec): 0.85 - samples/sec: 4008.53 - lr: 0.000038 - momentum: 0.000000 2024-11-27 20:29:46,109 epoch 31 - iter 7/9 - loss 0.05952600 - time (sec): 1.00 - samples/sec: 4069.09 - lr: 0.000038 - momentum: 0.000000 2024-11-27 20:29:46,263 epoch 31 - iter 8/9 - loss 0.06427407 - time (sec): 1.15 - samples/sec: 4044.48 - lr: 0.000038 - momentum: 0.000000 2024-11-27 20:29:46,451 epoch 31 - iter 9/9 - loss 0.06498138 - time (sec): 1.34 - samples/sec: 3872.61 - lr: 0.000038 - momentum: 0.000000 2024-11-27 20:29:46,452 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:29:46,452 EPOCH 31 done: loss 0.0650 - lr: 0.000038 0%| | 0/1 [00:00<?, ?it/s] 100%|███████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 6.81it/s] 100%|███████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 6.80it/s] 2024-11-27 20:29:46,619 DEV : loss 2.0545997619628906 - f1-score (micro avg) 0.3046 2024-11-27 20:29:46,620 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:29:46,731 epoch 32 - iter 1/9 - loss 0.08193054 - time (sec): 0.11 - samples/sec: 6265.76 - lr: 0.000038 - momentum: 0.000000 2024-11-27 20:29:46,878 epoch 32 - iter 2/9 - loss 0.07055888 - time (sec): 0.26 - samples/sec: 4745.47 - lr: 0.000038 - momentum: 0.000000 2024-11-27 20:29:47,031 epoch 32 - iter 3/9 - loss 0.06693102 - time (sec): 0.41 - samples/sec: 4417.14 - lr: 0.000038 - momentum: 0.000000 2024-11-27 20:29:47,193 epoch 32 - iter 4/9 - loss 0.06096321 - time (sec): 0.57 - samples/sec: 4230.42 - lr: 0.000038 - momentum: 0.000000 2024-11-27 20:29:47,360 epoch 32 - iter 5/9 - loss 0.05510763 - time (sec): 0.74 - samples/sec: 4203.82 - lr: 0.000038 - momentum: 0.000000 2024-11-27 20:29:47,525 epoch 32 - iter 6/9 - loss 0.05367134 - time (sec): 0.90 - samples/sec: 4006.54 - lr: 0.000038 - momentum: 0.000000 2024-11-27 20:29:47,668 epoch 32 - iter 7/9 - loss 0.05510440 - time (sec): 1.05 - samples/sec: 4005.63 - lr: 0.000038 - momentum: 0.000000 2024-11-27 20:29:47,819 epoch 32 - iter 8/9 - loss 0.05804760 - time (sec): 1.20 - samples/sec: 3914.75 - lr: 0.000038 - momentum: 0.000000 2024-11-27 20:29:47,963 epoch 32 - iter 9/9 - loss 0.05953212 - time (sec): 1.34 - samples/sec: 3872.79 - lr: 0.000038 - momentum: 0.000000 2024-11-27 20:29:47,963 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:29:47,963 EPOCH 32 done: loss 0.0595 - lr: 0.000038 0%| | 0/1 [00:00<?, ?it/s] 100%|███████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 6.60it/s] 100%|███████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 6.59it/s] 2024-11-27 20:29:48,134 DEV : loss 1.991340160369873 - f1-score (micro avg) 0.3077 2024-11-27 20:29:48,136 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:29:48,243 epoch 33 - iter 1/9 - loss 0.06266447 - time (sec): 0.11 - samples/sec: 5394.33 - lr: 0.000038 - momentum: 0.000000 2024-11-27 20:29:48,398 epoch 33 - iter 2/9 - loss 0.05396916 - time (sec): 0.26 - samples/sec: 4686.78 - lr: 0.000038 - momentum: 0.000000 2024-11-27 20:29:48,553 epoch 33 - iter 3/9 - loss 0.06727400 - time (sec): 0.42 - samples/sec: 4392.09 - lr: 0.000038 - momentum: 0.000000 2024-11-27 20:29:48,678 epoch 33 - iter 4/9 - loss 0.06543379 - time (sec): 0.54 - samples/sec: 4308.99 - lr: 0.000038 - momentum: 0.000000 2024-11-27 20:29:48,829 epoch 33 - iter 5/9 - loss 0.06359310 - time (sec): 0.69 - samples/sec: 4281.60 - lr: 0.000038 - momentum: 0.000000 2024-11-27 20:29:48,984 epoch 33 - iter 6/9 - loss 0.05946740 - time (sec): 0.85 - samples/sec: 4169.72 - lr: 0.000038 - momentum: 0.000000 2024-11-27 20:29:49,118 epoch 33 - iter 7/9 - loss 0.05657876 - time (sec): 0.98 - samples/sec: 4123.14 - lr: 0.000038 - momentum: 0.000000 2024-11-27 20:29:49,269 epoch 33 - iter 8/9 - loss 0.05650697 - time (sec): 1.13 - samples/sec: 4123.91 - lr: 0.000038 - momentum: 0.000000 2024-11-27 20:29:49,582 epoch 33 - iter 9/9 - loss 0.05409143 - time (sec): 1.45 - samples/sec: 3594.82 - lr: 0.000038 - momentum: 0.000000 2024-11-27 20:29:49,583 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:29:49,583 EPOCH 33 done: loss 0.0541 - lr: 0.000038 0%| | 0/1 [00:00<?, ?it/s] 100%|███████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 6.27it/s] 100%|███████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 6.26it/s] 2024-11-27 20:29:49,762 DEV : loss 2.1849007606506348 - f1-score (micro avg) 0.3497 2024-11-27 20:29:49,763 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:29:49,864 epoch 34 - iter 1/9 - loss 0.02477097 - time (sec): 0.10 - samples/sec: 6767.93 - lr: 0.000038 - momentum: 0.000000 2024-11-27 20:29:50,012 epoch 34 - iter 2/9 - loss 0.02851112 - time (sec): 0.25 - samples/sec: 5211.77 - lr: 0.000038 - momentum: 0.000000 2024-11-27 20:29:50,155 epoch 34 - iter 3/9 - loss 0.03854129 - time (sec): 0.39 - samples/sec: 4810.79 - lr: 0.000038 - momentum: 0.000000 2024-11-27 20:29:50,312 epoch 34 - iter 4/9 - loss 0.03930109 - time (sec): 0.55 - samples/sec: 4626.13 - lr: 0.000038 - momentum: 0.000000 2024-11-27 20:29:50,456 epoch 34 - iter 5/9 - loss 0.03981364 - time (sec): 0.69 - samples/sec: 4428.77 - lr: 0.000038 - momentum: 0.000000 2024-11-27 20:29:50,591 epoch 34 - iter 6/9 - loss 0.04359152 - time (sec): 0.83 - samples/sec: 4380.51 - lr: 0.000038 - momentum: 0.000000 2024-11-27 20:29:50,717 epoch 34 - iter 7/9 - loss 0.04639099 - time (sec): 0.95 - samples/sec: 4281.53 - lr: 0.000038 - momentum: 0.000000 2024-11-27 20:29:50,840 epoch 34 - iter 8/9 - loss 0.04586801 - time (sec): 1.08 - samples/sec: 4364.35 - lr: 0.000038 - momentum: 0.000000 2024-11-27 20:29:50,976 epoch 34 - iter 9/9 - loss 0.04611400 - time (sec): 1.21 - samples/sec: 4288.19 - lr: 0.000038 - momentum: 0.000000 2024-11-27 20:29:50,976 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:29:50,977 EPOCH 34 done: loss 0.0461 - lr: 0.000038 0%| | 0/1 [00:00<?, ?it/s] 100%|███████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 6.24it/s] 100%|███████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 6.23it/s] 2024-11-27 20:29:51,157 DEV : loss 2.0644054412841797 - f1-score (micro avg) 0.3164 2024-11-27 20:29:51,158 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:29:51,267 epoch 35 - iter 1/9 - loss 0.02517174 - time (sec): 0.11 - samples/sec: 5628.13 - lr: 0.000038 - momentum: 0.000000 2024-11-27 20:29:51,421 epoch 35 - iter 2/9 - loss 0.04054492 - time (sec): 0.26 - samples/sec: 4769.75 - lr: 0.000037 - momentum: 0.000000 2024-11-27 20:29:51,568 epoch 35 - iter 3/9 - loss 0.04279313 - time (sec): 0.41 - samples/sec: 4460.37 - lr: 0.000037 - momentum: 0.000000 2024-11-27 20:29:51,733 epoch 35 - iter 4/9 - loss 0.04895540 - time (sec): 0.57 - samples/sec: 4456.41 - lr: 0.000037 - momentum: 0.000000 2024-11-27 20:29:51,907 epoch 35 - iter 5/9 - loss 0.04383236 - time (sec): 0.75 - samples/sec: 4113.59 - lr: 0.000037 - momentum: 0.000000 2024-11-27 20:29:52,057 epoch 35 - iter 6/9 - loss 0.04692451 - time (sec): 0.90 - samples/sec: 4015.52 - lr: 0.000037 - momentum: 0.000000 2024-11-27 20:29:52,178 epoch 35 - iter 7/9 - loss 0.04695995 - time (sec): 1.02 - samples/sec: 3998.26 - lr: 0.000037 - momentum: 0.000000 2024-11-27 20:29:52,300 epoch 35 - iter 8/9 - loss 0.04591715 - time (sec): 1.14 - samples/sec: 4043.60 - lr: 0.000037 - momentum: 0.000000 2024-11-27 20:29:52,437 epoch 35 - iter 9/9 - loss 0.04275513 - time (sec): 1.28 - samples/sec: 4068.02 - lr: 0.000037 - momentum: 0.000000 2024-11-27 20:29:52,437 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:29:52,437 EPOCH 35 done: loss 0.0428 - lr: 0.000037 0%| | 0/1 [00:00<?, ?it/s] 100%|███████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 7.29it/s] 100%|███████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 7.27it/s] 2024-11-27 20:29:52,594 DEV : loss 2.1733546257019043 - f1-score (micro avg) 0.3356 2024-11-27 20:29:52,595 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:29:52,687 epoch 36 - iter 1/9 - loss 0.02704067 - time (sec): 0.09 - samples/sec: 4855.42 - lr: 0.000037 - momentum: 0.000000 2024-11-27 20:29:52,830 epoch 36 - iter 2/9 - loss 0.03457557 - time (sec): 0.23 - samples/sec: 4550.44 - lr: 0.000037 - momentum: 0.000000 2024-11-27 20:29:52,968 epoch 36 - iter 3/9 - loss 0.03757709 - time (sec): 0.37 - samples/sec: 4325.63 - lr: 0.000037 - momentum: 0.000000 2024-11-27 20:29:53,116 epoch 36 - iter 4/9 - loss 0.03182234 - time (sec): 0.52 - samples/sec: 4405.25 - lr: 0.000037 - momentum: 0.000000 2024-11-27 20:29:53,265 epoch 36 - iter 5/9 - loss 0.04247795 - time (sec): 0.67 - samples/sec: 4439.15 - lr: 0.000037 - momentum: 0.000000 2024-11-27 20:29:53,425 epoch 36 - iter 6/9 - loss 0.04114452 - time (sec): 0.83 - samples/sec: 4241.36 - lr: 0.000037 - momentum: 0.000000 2024-11-27 20:29:53,674 epoch 36 - iter 7/9 - loss 0.03808348 - time (sec): 1.08 - samples/sec: 3929.61 - lr: 0.000037 - momentum: 0.000000 2024-11-27 20:29:53,823 epoch 36 - iter 8/9 - loss 0.03736671 - time (sec): 1.23 - samples/sec: 3841.59 - lr: 0.000037 - momentum: 0.000000 2024-11-27 20:29:53,943 epoch 36 - iter 9/9 - loss 0.04206421 - time (sec): 1.35 - samples/sec: 3857.45 - lr: 0.000037 - momentum: 0.000000 2024-11-27 20:29:53,943 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:29:53,943 EPOCH 36 done: loss 0.0421 - lr: 0.000037 0%| | 0/1 [00:00<?, ?it/s] 100%|███████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 6.58it/s] 100%|███████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 6.56it/s] 2024-11-27 20:29:54,115 DEV : loss 2.1078429222106934 - f1-score (micro avg) 0.3636 2024-11-27 20:29:54,116 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:29:54,224 epoch 37 - iter 1/9 - loss 0.01503284 - time (sec): 0.11 - samples/sec: 5016.07 - lr: 0.000037 - momentum: 0.000000 2024-11-27 20:29:54,361 epoch 37 - iter 2/9 - loss 0.02121967 - time (sec): 0.24 - samples/sec: 4296.07 - lr: 0.000037 - momentum: 0.000000 2024-11-27 20:29:54,489 epoch 37 - iter 3/9 - loss 0.02231252 - time (sec): 0.37 - samples/sec: 4406.55 - lr: 0.000037 - momentum: 0.000000 2024-11-27 20:29:54,674 epoch 37 - iter 4/9 - loss 0.02649754 - time (sec): 0.56 - samples/sec: 4159.25 - lr: 0.000037 - momentum: 0.000000 2024-11-27 20:29:54,930 epoch 37 - iter 5/9 - loss 0.03344334 - time (sec): 0.81 - samples/sec: 3694.70 - lr: 0.000037 - momentum: 0.000000 2024-11-27 20:29:55,106 epoch 37 - iter 6/9 - loss 0.03271569 - time (sec): 0.99 - samples/sec: 3654.13 - lr: 0.000037 - momentum: 0.000000 2024-11-27 20:29:55,261 epoch 37 - iter 7/9 - loss 0.03073919 - time (sec): 1.14 - samples/sec: 3676.16 - lr: 0.000037 - momentum: 0.000000 2024-11-27 20:29:55,413 epoch 37 - iter 8/9 - loss 0.02882891 - time (sec): 1.30 - samples/sec: 3642.65 - lr: 0.000037 - momentum: 0.000000 2024-11-27 20:29:55,560 epoch 37 - iter 9/9 - loss 0.02967874 - time (sec): 1.44 - samples/sec: 3601.93 - lr: 0.000037 - momentum: 0.000000 2024-11-27 20:29:55,560 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:29:55,561 EPOCH 37 done: loss 0.0297 - lr: 0.000037 0%| | 0/1 [00:00<?, ?it/s] 100%|███████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 6.19it/s] 100%|███████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 6.18it/s] 2024-11-27 20:29:55,742 DEV : loss 2.1725172996520996 - f1-score (micro avg) 0.3067 2024-11-27 20:29:55,743 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:29:55,848 epoch 38 - iter 1/9 - loss 0.02305206 - time (sec): 0.10 - samples/sec: 5840.69 - lr: 0.000037 - momentum: 0.000000 2024-11-27 20:29:55,988 epoch 38 - iter 2/9 - loss 0.02535708 - time (sec): 0.24 - samples/sec: 4688.38 - lr: 0.000037 - momentum: 0.000000 2024-11-27 20:29:56,130 epoch 38 - iter 3/9 - loss 0.02573898 - time (sec): 0.39 - samples/sec: 4417.13 - lr: 0.000037 - momentum: 0.000000 2024-11-27 20:29:56,283 epoch 38 - iter 4/9 - loss 0.02925730 - time (sec): 0.54 - samples/sec: 4051.22 - lr: 0.000037 - momentum: 0.000000 2024-11-27 20:29:56,410 epoch 38 - iter 5/9 - loss 0.03000310 - time (sec): 0.67 - samples/sec: 3993.27 - lr: 0.000037 - momentum: 0.000000 2024-11-27 20:29:56,573 epoch 38 - iter 6/9 - loss 0.03182305 - time (sec): 0.83 - samples/sec: 4086.96 - lr: 0.000037 - momentum: 0.000000 2024-11-27 20:29:56,720 epoch 38 - iter 7/9 - loss 0.02968052 - time (sec): 0.98 - samples/sec: 3993.61 - lr: 0.000037 - momentum: 0.000000 2024-11-27 20:29:56,863 epoch 38 - iter 8/9 - loss 0.03118254 - time (sec): 1.12 - samples/sec: 4098.72 - lr: 0.000037 - momentum: 0.000000 2024-11-27 20:29:56,998 epoch 38 - iter 9/9 - loss 0.03038164 - time (sec): 1.25 - samples/sec: 4144.32 - lr: 0.000037 - momentum: 0.000000 2024-11-27 20:29:56,998 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:29:56,998 EPOCH 38 done: loss 0.0304 - lr: 0.000037 0%| | 0/1 [00:00<?, ?it/s] 100%|███████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 6.25it/s] 100%|███████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 6.24it/s] 2024-11-27 20:29:57,178 DEV : loss 2.232577085494995 - f1-score (micro avg) 0.3185 2024-11-27 20:29:57,179 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:29:57,270 epoch 39 - iter 1/9 - loss 0.01314354 - time (sec): 0.09 - samples/sec: 6413.12 - lr: 0.000037 - momentum: 0.000000 2024-11-27 20:29:57,401 epoch 39 - iter 2/9 - loss 0.01683950 - time (sec): 0.22 - samples/sec: 4756.44 - lr: 0.000037 - momentum: 0.000000 2024-11-27 20:29:57,537 epoch 39 - iter 3/9 - loss 0.01565205 - time (sec): 0.36 - samples/sec: 4551.86 - lr: 0.000037 - momentum: 0.000000 2024-11-27 20:29:57,694 epoch 39 - iter 4/9 - loss 0.01997316 - time (sec): 0.51 - samples/sec: 4571.30 - lr: 0.000037 - momentum: 0.000000 2024-11-27 20:29:57,873 epoch 39 - iter 5/9 - loss 0.02114608 - time (sec): 0.69 - samples/sec: 4285.47 - lr: 0.000037 - momentum: 0.000000 2024-11-27 20:29:58,035 epoch 39 - iter 6/9 - loss 0.02007915 - time (sec): 0.85 - samples/sec: 4138.04 - lr: 0.000037 - momentum: 0.000000 2024-11-27 20:29:58,200 epoch 39 - iter 7/9 - loss 0.02126286 - time (sec): 1.02 - samples/sec: 4018.52 - lr: 0.000037 - momentum: 0.000000 2024-11-27 20:29:58,345 epoch 39 - iter 8/9 - loss 0.02270155 - time (sec): 1.17 - samples/sec: 4062.97 - lr: 0.000037 - momentum: 0.000000 2024-11-27 20:29:58,494 epoch 39 - iter 9/9 - loss 0.02151240 - time (sec): 1.31 - samples/sec: 3955.48 - lr: 0.000037 - momentum: 0.000000 2024-11-27 20:29:58,494 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:29:58,494 EPOCH 39 done: loss 0.0215 - lr: 0.000037 0%| | 0/1 [00:00<?, ?it/s] 100%|███████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 6.01it/s] 100%|███████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 6.00it/s] 2024-11-27 20:29:58,680 DEV : loss 2.1884210109710693 - f1-score (micro avg) 0.323 2024-11-27 20:29:58,681 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:29:58,772 epoch 40 - iter 1/9 - loss 0.03571283 - time (sec): 0.09 - samples/sec: 5997.84 - lr: 0.000036 - momentum: 0.000000 2024-11-27 20:29:58,918 epoch 40 - iter 2/9 - loss 0.02882457 - time (sec): 0.24 - samples/sec: 5160.95 - lr: 0.000036 - momentum: 0.000000 2024-11-27 20:29:59,073 epoch 40 - iter 3/9 - loss 0.02376341 - time (sec): 0.39 - samples/sec: 4343.53 - lr: 0.000036 - momentum: 0.000000 2024-11-27 20:29:59,211 epoch 40 - iter 4/9 - loss 0.02166937 - time (sec): 0.53 - samples/sec: 4333.11 - lr: 0.000036 - momentum: 0.000000 2024-11-27 20:29:59,341 epoch 40 - iter 5/9 - loss 0.01925959 - time (sec): 0.66 - samples/sec: 4328.38 - lr: 0.000036 - momentum: 0.000000 2024-11-27 20:29:59,508 epoch 40 - iter 6/9 - loss 0.02146943 - time (sec): 0.83 - samples/sec: 4252.27 - lr: 0.000036 - momentum: 0.000000 2024-11-27 20:29:59,652 epoch 40 - iter 7/9 - loss 0.02092201 - time (sec): 0.97 - samples/sec: 4232.63 - lr: 0.000036 - momentum: 0.000000 2024-11-27 20:29:59,794 epoch 40 - iter 8/9 - loss 0.02164045 - time (sec): 1.11 - samples/sec: 4184.81 - lr: 0.000036 - momentum: 0.000000 2024-11-27 20:29:59,949 epoch 40 - iter 9/9 - loss 0.02072032 - time (sec): 1.27 - samples/sec: 4104.58 - lr: 0.000036 - momentum: 0.000000 2024-11-27 20:29:59,949 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:29:59,949 EPOCH 40 done: loss 0.0207 - lr: 0.000036 0%| | 0/1 [00:00<?, ?it/s] 100%|███████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 5.66it/s] 100%|███████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 5.65it/s] 2024-11-27 20:30:00,145 DEV : loss 2.2572319507598877 - f1-score (micro avg) 0.321 2024-11-27 20:30:00,146 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:30:00,253 epoch 41 - iter 1/9 - loss 0.01133918 - time (sec): 0.11 - samples/sec: 7916.80 - lr: 0.000036 - momentum: 0.000000 2024-11-27 20:30:00,492 epoch 41 - iter 2/9 - loss 0.01408810 - time (sec): 0.34 - samples/sec: 4340.32 - lr: 0.000036 - momentum: 0.000000 2024-11-27 20:30:00,635 epoch 41 - iter 3/9 - loss 0.01283532 - time (sec): 0.49 - samples/sec: 4028.42 - lr: 0.000036 - momentum: 0.000000 2024-11-27 20:30:00,789 epoch 41 - iter 4/9 - loss 0.01181448 - time (sec): 0.64 - samples/sec: 3976.46 - lr: 0.000036 - momentum: 0.000000 2024-11-27 20:30:00,926 epoch 41 - iter 5/9 - loss 0.01796051 - time (sec): 0.78 - samples/sec: 4023.75 - lr: 0.000036 - momentum: 0.000000 2024-11-27 20:30:01,064 epoch 41 - iter 6/9 - loss 0.02027897 - time (sec): 0.92 - samples/sec: 3941.15 - lr: 0.000036 - momentum: 0.000000 2024-11-27 20:30:01,206 epoch 41 - iter 7/9 - loss 0.02065363 - time (sec): 1.06 - samples/sec: 3984.40 - lr: 0.000036 - momentum: 0.000000 2024-11-27 20:30:01,340 epoch 41 - iter 8/9 - loss 0.02122454 - time (sec): 1.19 - samples/sec: 3899.19 - lr: 0.000036 - momentum: 0.000000 2024-11-27 20:30:01,479 epoch 41 - iter 9/9 - loss 0.01989865 - time (sec): 1.33 - samples/sec: 3903.80 - lr: 0.000036 - momentum: 0.000000 2024-11-27 20:30:01,479 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:30:01,479 EPOCH 41 done: loss 0.0199 - lr: 0.000036 0%| | 0/1 [00:00<?, ?it/s] 100%|███████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 6.77it/s] 100%|███████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 6.76it/s] 2024-11-27 20:30:01,646 DEV : loss 2.2987847328186035 - f1-score (micro avg) 0.3226 2024-11-27 20:30:01,647 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:30:01,743 epoch 42 - iter 1/9 - loss 0.01384202 - time (sec): 0.09 - samples/sec: 5299.86 - lr: 0.000036 - momentum: 0.000000 2024-11-27 20:30:01,886 epoch 42 - iter 2/9 - loss 0.01376080 - time (sec): 0.24 - samples/sec: 4835.42 - lr: 0.000036 - momentum: 0.000000 2024-11-27 20:30:02,018 epoch 42 - iter 3/9 - loss 0.02260501 - time (sec): 0.37 - samples/sec: 4690.28 - lr: 0.000036 - momentum: 0.000000 2024-11-27 20:30:02,150 epoch 42 - iter 4/9 - loss 0.02096437 - time (sec): 0.50 - samples/sec: 4983.06 - lr: 0.000036 - momentum: 0.000000 2024-11-27 20:30:02,315 epoch 42 - iter 5/9 - loss 0.01968164 - time (sec): 0.67 - samples/sec: 4598.69 - lr: 0.000036 - momentum: 0.000000 2024-11-27 20:30:02,477 epoch 42 - iter 6/9 - loss 0.01981044 - time (sec): 0.83 - samples/sec: 4389.35 - lr: 0.000036 - momentum: 0.000000 2024-11-27 20:30:02,625 epoch 42 - iter 7/9 - loss 0.01811143 - time (sec): 0.98 - samples/sec: 4289.70 - lr: 0.000036 - momentum: 0.000000 2024-11-27 20:30:02,787 epoch 42 - iter 8/9 - loss 0.01820150 - time (sec): 1.14 - samples/sec: 4136.83 - lr: 0.000036 - momentum: 0.000000 2024-11-27 20:30:02,894 epoch 42 - iter 9/9 - loss 0.01895619 - time (sec): 1.25 - samples/sec: 4169.92 - lr: 0.000036 - momentum: 0.000000 2024-11-27 20:30:02,895 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:30:02,895 EPOCH 42 done: loss 0.0190 - lr: 0.000036 0%| | 0/1 [00:00<?, ?it/s] 100%|███████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 7.34it/s] 100%|███████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 7.32it/s] 2024-11-27 20:30:03,051 DEV : loss 2.255535125732422 - f1-score (micro avg) 0.3121 2024-11-27 20:30:03,052 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:30:03,154 epoch 43 - iter 1/9 - loss 0.02027431 - time (sec): 0.10 - samples/sec: 4848.03 - lr: 0.000036 - momentum: 0.000000 2024-11-27 20:30:03,295 epoch 43 - iter 2/9 - loss 0.01653461 - time (sec): 0.24 - samples/sec: 4384.09 - lr: 0.000036 - momentum: 0.000000 2024-11-27 20:30:03,461 epoch 43 - iter 3/9 - loss 0.01435258 - time (sec): 0.41 - samples/sec: 3873.52 - lr: 0.000036 - momentum: 0.000000 2024-11-27 20:30:03,706 epoch 43 - iter 4/9 - loss 0.01345101 - time (sec): 0.65 - samples/sec: 3333.68 - lr: 0.000036 - momentum: 0.000000 2024-11-27 20:30:03,857 epoch 43 - iter 5/9 - loss 0.01368461 - time (sec): 0.80 - samples/sec: 3475.27 - lr: 0.000036 - momentum: 0.000000 2024-11-27 20:30:03,993 epoch 43 - iter 6/9 - loss 0.01578658 - time (sec): 0.94 - samples/sec: 3741.96 - lr: 0.000036 - momentum: 0.000000 2024-11-27 20:30:04,161 epoch 43 - iter 7/9 - loss 0.01624349 - time (sec): 1.11 - samples/sec: 3724.97 - lr: 0.000036 - momentum: 0.000000 2024-11-27 20:30:04,352 epoch 43 - iter 8/9 - loss 0.02133874 - time (sec): 1.30 - samples/sec: 3609.96 - lr: 0.000036 - momentum: 0.000000 2024-11-27 20:30:04,498 epoch 43 - iter 9/9 - loss 0.02035639 - time (sec): 1.44 - samples/sec: 3597.03 - lr: 0.000036 - momentum: 0.000000 2024-11-27 20:30:04,498 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:30:04,498 EPOCH 43 done: loss 0.0204 - lr: 0.000036 0%| | 0/1 [00:00<?, ?it/s] 100%|███████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 6.94it/s] 100%|███████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 6.92it/s] 2024-11-27 20:30:04,662 DEV : loss 2.283066511154175 - f1-score (micro avg) 0.32 2024-11-27 20:30:04,663 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:30:04,758 epoch 44 - iter 1/9 - loss 0.00932349 - time (sec): 0.09 - samples/sec: 5317.46 - lr: 0.000036 - momentum: 0.000000 2024-11-27 20:30:04,958 epoch 44 - iter 2/9 - loss 0.01364547 - time (sec): 0.29 - samples/sec: 4138.55 - lr: 0.000036 - momentum: 0.000000 2024-11-27 20:30:05,104 epoch 44 - iter 3/9 - loss 0.01391222 - time (sec): 0.44 - samples/sec: 4130.48 - lr: 0.000036 - momentum: 0.000000 2024-11-27 20:30:05,247 epoch 44 - iter 4/9 - loss 0.01459760 - time (sec): 0.58 - samples/sec: 4296.36 - lr: 0.000036 - momentum: 0.000000 2024-11-27 20:30:05,544 epoch 44 - iter 5/9 - loss 0.01751072 - time (sec): 0.88 - samples/sec: 3361.83 - lr: 0.000036 - momentum: 0.000000 2024-11-27 20:30:05,672 epoch 44 - iter 6/9 - loss 0.01780812 - time (sec): 1.01 - samples/sec: 3501.93 - lr: 0.000036 - momentum: 0.000000 2024-11-27 20:30:05,813 epoch 44 - iter 7/9 - loss 0.01590627 - time (sec): 1.15 - samples/sec: 3566.68 - lr: 0.000036 - momentum: 0.000000 2024-11-27 20:30:05,942 epoch 44 - iter 8/9 - loss 0.01474644 - time (sec): 1.28 - samples/sec: 3624.48 - lr: 0.000036 - momentum: 0.000000 2024-11-27 20:30:06,087 epoch 44 - iter 9/9 - loss 0.01503946 - time (sec): 1.42 - samples/sec: 3651.43 - lr: 0.000035 - momentum: 0.000000 2024-11-27 20:30:06,088 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:30:06,088 EPOCH 44 done: loss 0.0150 - lr: 0.000035 0%| | 0/1 [00:00<?, ?it/s] 100%|███████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 5.90it/s] 100%|███████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 5.89it/s] 2024-11-27 20:30:06,277 DEV : loss 2.304168462753296 - f1-score (micro avg) 0.3067 2024-11-27 20:30:06,278 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:30:06,374 epoch 45 - iter 1/9 - loss 0.00474904 - time (sec): 0.09 - samples/sec: 5373.33 - lr: 0.000035 - momentum: 0.000000 2024-11-27 20:30:06,506 epoch 45 - iter 2/9 - loss 0.00508487 - time (sec): 0.23 - samples/sec: 4823.94 - lr: 0.000035 - momentum: 0.000000 2024-11-27 20:30:06,652 epoch 45 - iter 3/9 - loss 0.00892930 - time (sec): 0.37 - samples/sec: 4612.78 - lr: 0.000035 - momentum: 0.000000 2024-11-27 20:30:06,903 epoch 45 - iter 4/9 - loss 0.00824941 - time (sec): 0.62 - samples/sec: 3719.66 - lr: 0.000035 - momentum: 0.000000 2024-11-27 20:30:07,085 epoch 45 - iter 5/9 - loss 0.00822924 - time (sec): 0.81 - samples/sec: 3608.53 - lr: 0.000035 - momentum: 0.000000 2024-11-27 20:30:07,225 epoch 45 - iter 6/9 - loss 0.00836672 - time (sec): 0.95 - samples/sec: 3712.22 - lr: 0.000035 - momentum: 0.000000 2024-11-27 20:30:07,354 epoch 45 - iter 7/9 - loss 0.00963688 - time (sec): 1.07 - samples/sec: 3730.24 - lr: 0.000035 - momentum: 0.000000 2024-11-27 20:30:07,498 epoch 45 - iter 8/9 - loss 0.00946574 - time (sec): 1.22 - samples/sec: 3852.20 - lr: 0.000035 - momentum: 0.000000 2024-11-27 20:30:07,663 epoch 45 - iter 9/9 - loss 0.00976081 - time (sec): 1.38 - samples/sec: 3755.77 - lr: 0.000035 - momentum: 0.000000 2024-11-27 20:30:07,663 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:30:07,663 EPOCH 45 done: loss 0.0098 - lr: 0.000035 0%| | 0/1 [00:00<?, ?it/s] 100%|███████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 6.15it/s] 100%|███████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 6.14it/s] 2024-11-27 20:30:07,845 DEV : loss 2.358428478240967 - f1-score (micro avg) 0.3247 2024-11-27 20:30:07,846 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:30:08,166 epoch 46 - iter 1/9 - loss 0.02119955 - time (sec): 0.32 - samples/sec: 1514.62 - lr: 0.000035 - momentum: 0.000000 2024-11-27 20:30:08,321 epoch 46 - iter 2/9 - loss 0.01518660 - time (sec): 0.47 - samples/sec: 2154.03 - lr: 0.000035 - momentum: 0.000000 2024-11-27 20:30:08,483 epoch 46 - iter 3/9 - loss 0.01438913 - time (sec): 0.64 - samples/sec: 2548.02 - lr: 0.000035 - momentum: 0.000000 2024-11-27 20:30:08,610 epoch 46 - iter 4/9 - loss 0.01472523 - time (sec): 0.76 - samples/sec: 2742.30 - lr: 0.000035 - momentum: 0.000000 2024-11-27 20:30:08,751 epoch 46 - iter 5/9 - loss 0.01479580 - time (sec): 0.90 - samples/sec: 2972.54 - lr: 0.000035 - momentum: 0.000000 2024-11-27 20:30:08,897 epoch 46 - iter 6/9 - loss 0.01250385 - time (sec): 1.05 - samples/sec: 3225.93 - lr: 0.000035 - momentum: 0.000000 2024-11-27 20:30:09,054 epoch 46 - iter 7/9 - loss 0.01193812 - time (sec): 1.21 - samples/sec: 3303.54 - lr: 0.000035 - momentum: 0.000000 2024-11-27 20:30:09,192 epoch 46 - iter 8/9 - loss 0.01268973 - time (sec): 1.34 - samples/sec: 3399.39 - lr: 0.000035 - momentum: 0.000000 2024-11-27 20:30:09,332 epoch 46 - iter 9/9 - loss 0.01191948 - time (sec): 1.48 - samples/sec: 3502.06 - lr: 0.000035 - momentum: 0.000000 2024-11-27 20:30:09,332 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:30:09,332 EPOCH 46 done: loss 0.0119 - lr: 0.000035 0%| | 0/1 [00:00<?, ?it/s] 100%|███████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 5.47it/s] 100%|███████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 5.46it/s] 2024-11-27 20:30:09,534 DEV : loss 2.394437074661255 - f1-score (micro avg) 0.3011 2024-11-27 20:30:09,536 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:30:09,639 epoch 47 - iter 1/9 - loss 0.01614049 - time (sec): 0.10 - samples/sec: 5788.63 - lr: 0.000035 - momentum: 0.000000 2024-11-27 20:30:09,786 epoch 47 - iter 2/9 - loss 0.01194475 - time (sec): 0.25 - samples/sec: 4919.06 - lr: 0.000035 - momentum: 0.000000 2024-11-27 20:30:09,939 epoch 47 - iter 3/9 - loss 0.00876992 - time (sec): 0.40 - samples/sec: 4813.72 - lr: 0.000035 - momentum: 0.000000 2024-11-27 20:30:10,103 epoch 47 - iter 4/9 - loss 0.01037120 - time (sec): 0.57 - samples/sec: 4410.29 - lr: 0.000035 - momentum: 0.000000 2024-11-27 20:30:10,237 epoch 47 - iter 5/9 - loss 0.00941951 - time (sec): 0.70 - samples/sec: 4279.51 - lr: 0.000035 - momentum: 0.000000 2024-11-27 20:30:10,388 epoch 47 - iter 6/9 - loss 0.01715916 - time (sec): 0.85 - samples/sec: 4218.36 - lr: 0.000035 - momentum: 0.000000 2024-11-27 20:30:10,569 epoch 47 - iter 7/9 - loss 0.01607052 - time (sec): 1.03 - samples/sec: 4037.89 - lr: 0.000035 - momentum: 0.000000 2024-11-27 20:30:10,715 epoch 47 - iter 8/9 - loss 0.01759386 - time (sec): 1.18 - samples/sec: 3981.89 - lr: 0.000035 - momentum: 0.000000 2024-11-27 20:30:10,848 epoch 47 - iter 9/9 - loss 0.01673850 - time (sec): 1.31 - samples/sec: 3962.93 - lr: 0.000035 - momentum: 0.000000 2024-11-27 20:30:10,849 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:30:10,849 EPOCH 47 done: loss 0.0167 - lr: 0.000035 0%| | 0/1 [00:00<?, ?it/s] 100%|███████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 6.91it/s] 100%|███████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 6.89it/s] 2024-11-27 20:30:11,013 DEV : loss 2.389173746109009 - f1-score (micro avg) 0.325 2024-11-27 20:30:11,014 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:30:11,120 epoch 48 - iter 1/9 - loss 0.00726273 - time (sec): 0.10 - samples/sec: 6568.23 - lr: 0.000035 - momentum: 0.000000 2024-11-27 20:30:11,268 epoch 48 - iter 2/9 - loss 0.01534297 - time (sec): 0.25 - samples/sec: 5069.64 - lr: 0.000035 - momentum: 0.000000 2024-11-27 20:30:11,390 epoch 48 - iter 3/9 - loss 0.01309683 - time (sec): 0.38 - samples/sec: 4468.75 - lr: 0.000035 - momentum: 0.000000 2024-11-27 20:30:11,518 epoch 48 - iter 4/9 - loss 0.01353218 - time (sec): 0.50 - samples/sec: 4475.07 - lr: 0.000035 - momentum: 0.000000 2024-11-27 20:30:11,657 epoch 48 - iter 5/9 - loss 0.01165366 - time (sec): 0.64 - samples/sec: 4367.41 - lr: 0.000035 - momentum: 0.000000 2024-11-27 20:30:11,806 epoch 48 - iter 6/9 - loss 0.01062727 - time (sec): 0.79 - samples/sec: 4242.21 - lr: 0.000035 - momentum: 0.000000 2024-11-27 20:30:11,969 epoch 48 - iter 7/9 - loss 0.01066934 - time (sec): 0.95 - samples/sec: 4214.16 - lr: 0.000035 - momentum: 0.000000 2024-11-27 20:30:12,118 epoch 48 - iter 8/9 - loss 0.00965068 - time (sec): 1.10 - samples/sec: 4269.60 - lr: 0.000035 - momentum: 0.000000 2024-11-27 20:30:12,242 epoch 48 - iter 9/9 - loss 0.01024349 - time (sec): 1.23 - samples/sec: 4236.40 - lr: 0.000035 - momentum: 0.000000 2024-11-27 20:30:12,242 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:30:12,242 EPOCH 48 done: loss 0.0102 - lr: 0.000035 0%| | 0/1 [00:00<?, ?it/s] 100%|███████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 6.50it/s] 100%|███████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 6.49it/s] 2024-11-27 20:30:12,416 DEV : loss 2.3745615482330322 - f1-score (micro avg) 0.3218 2024-11-27 20:30:12,417 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:30:12,513 epoch 49 - iter 1/9 - loss 0.00468337 - time (sec): 0.10 - samples/sec: 6143.47 - lr: 0.000035 - momentum: 0.000000 2024-11-27 20:30:12,653 epoch 49 - iter 2/9 - loss 0.00568933 - time (sec): 0.24 - samples/sec: 4523.03 - lr: 0.000035 - momentum: 0.000000 2024-11-27 20:30:12,905 epoch 49 - iter 3/9 - loss 0.00660388 - time (sec): 0.49 - samples/sec: 3389.93 - lr: 0.000035 - momentum: 0.000000 2024-11-27 20:30:13,042 epoch 49 - iter 4/9 - loss 0.00623670 - time (sec): 0.62 - samples/sec: 3440.67 - lr: 0.000035 - momentum: 0.000000 2024-11-27 20:30:13,188 epoch 49 - iter 5/9 - loss 0.01087049 - time (sec): 0.77 - samples/sec: 3787.57 - lr: 0.000035 - momentum: 0.000000 2024-11-27 20:30:13,326 epoch 49 - iter 6/9 - loss 0.01022001 - time (sec): 0.91 - samples/sec: 3884.74 - lr: 0.000035 - momentum: 0.000000 2024-11-27 20:30:13,458 epoch 49 - iter 7/9 - loss 0.00929257 - time (sec): 1.04 - samples/sec: 3978.31 - lr: 0.000035 - momentum: 0.000000 2024-11-27 20:30:13,702 epoch 49 - iter 8/9 - loss 0.00917913 - time (sec): 1.28 - samples/sec: 3719.88 - lr: 0.000034 - momentum: 0.000000 2024-11-27 20:30:13,846 epoch 49 - iter 9/9 - loss 0.00982031 - time (sec): 1.43 - samples/sec: 3639.12 - lr: 0.000034 - momentum: 0.000000 2024-11-27 20:30:13,846 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:30:13,846 EPOCH 49 done: loss 0.0098 - lr: 0.000034 0%| | 0/1 [00:00<?, ?it/s] 100%|███████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 6.98it/s] 100%|███████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 6.97it/s] 2024-11-27 20:30:14,009 DEV : loss 2.4018661975860596 - f1-score (micro avg) 0.3312 2024-11-27 20:30:14,010 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:30:14,110 epoch 50 - iter 1/9 - loss 0.00331556 - time (sec): 0.10 - samples/sec: 5165.11 - lr: 0.000034 - momentum: 0.000000 2024-11-27 20:30:14,252 epoch 50 - iter 2/9 - loss 0.00587876 - time (sec): 0.24 - samples/sec: 4430.56 - lr: 0.000034 - momentum: 0.000000 2024-11-27 20:30:14,382 epoch 50 - iter 3/9 - loss 0.00816786 - time (sec): 0.37 - samples/sec: 4200.38 - lr: 0.000034 - momentum: 0.000000 2024-11-27 20:30:14,537 epoch 50 - iter 4/9 - loss 0.01441424 - time (sec): 0.53 - samples/sec: 3909.86 - lr: 0.000034 - momentum: 0.000000 2024-11-27 20:30:14,712 epoch 50 - iter 5/9 - loss 0.01326250 - time (sec): 0.70 - samples/sec: 4007.17 - lr: 0.000034 - momentum: 0.000000 2024-11-27 20:30:14,853 epoch 50 - iter 6/9 - loss 0.01182071 - time (sec): 0.84 - samples/sec: 4041.38 - lr: 0.000034 - momentum: 0.000000 2024-11-27 20:30:14,989 epoch 50 - iter 7/9 - loss 0.01123430 - time (sec): 0.98 - samples/sec: 4110.65 - lr: 0.000034 - momentum: 0.000000 2024-11-27 20:30:15,147 epoch 50 - iter 8/9 - loss 0.01108795 - time (sec): 1.14 - samples/sec: 4081.59 - lr: 0.000034 - momentum: 0.000000 2024-11-27 20:30:15,297 epoch 50 - iter 9/9 - loss 0.01222468 - time (sec): 1.29 - samples/sec: 4040.77 - lr: 0.000034 - momentum: 0.000000 2024-11-27 20:30:15,298 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:30:15,298 EPOCH 50 done: loss 0.0122 - lr: 0.000034 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████| 1/1 [00:00<00:00, 5.78it/s] 100%|██████████████████████| 1/1 [00:00<00:00, 5.78it/s] 2024-11-27 20:30:15,490 DEV : loss 2.390753984451294 - f1-score (micro avg) 0.3171 2024-11-27 20:30:15,492 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:30:15,609 epoch 51 - iter 1/9 - loss 0.01280199 - time (sec): 0.12 - samples/sec: 4941.97 - lr: 0.000034 - momentum: 0.000000 2024-11-27 20:30:15,762 epoch 51 - iter 2/9 - loss 0.00963598 - time (sec): 0.27 - samples/sec: 4299.16 - lr: 0.000034 - momentum: 0.000000 2024-11-27 20:30:15,890 epoch 51 - iter 3/9 - loss 0.00769124 - time (sec): 0.40 - samples/sec: 4288.60 - lr: 0.000034 - momentum: 0.000000 2024-11-27 20:30:16,049 epoch 51 - iter 4/9 - loss 0.00640485 - time (sec): 0.56 - samples/sec: 4210.57 - lr: 0.000034 - momentum: 0.000000 2024-11-27 20:30:16,200 epoch 51 - iter 5/9 - loss 0.00746846 - time (sec): 0.71 - samples/sec: 4154.93 - lr: 0.000034 - momentum: 0.000000 2024-11-27 20:30:16,352 epoch 51 - iter 6/9 - loss 0.00689191 - time (sec): 0.86 - samples/sec: 4042.23 - lr: 0.000034 - momentum: 0.000000 2024-11-27 20:30:16,628 epoch 51 - iter 7/9 - loss 0.00665944 - time (sec): 1.14 - samples/sec: 3517.91 - lr: 0.000034 - momentum: 0.000000 2024-11-27 20:30:16,768 epoch 51 - iter 8/9 - loss 0.00758152 - time (sec): 1.28 - samples/sec: 3646.57 - lr: 0.000034 - momentum: 0.000000 2024-11-27 20:30:16,893 epoch 51 - iter 9/9 - loss 0.00800138 - time (sec): 1.40 - samples/sec: 3710.92 - lr: 0.000034 - momentum: 0.000000 2024-11-27 20:30:16,893 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:30:16,894 EPOCH 51 done: loss 0.0080 - lr: 0.000034 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████| 1/1 [00:00<00:00, 6.72it/s] 100%|██████████████████████| 1/1 [00:00<00:00, 6.71it/s] 2024-11-27 20:30:17,062 DEV : loss 2.3302414417266846 - f1-score (micro avg) 0.3012 2024-11-27 20:30:17,063 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:30:17,163 epoch 52 - iter 1/9 - loss 0.00391796 - time (sec): 0.10 - samples/sec: 5797.12 - lr: 0.000034 - momentum: 0.000000 2024-11-27 20:30:17,295 epoch 52 - iter 2/9 - loss 0.00301290 - time (sec): 0.23 - samples/sec: 4472.19 - lr: 0.000034 - momentum: 0.000000 2024-11-27 20:30:17,428 epoch 52 - iter 3/9 - loss 0.00557838 - time (sec): 0.36 - samples/sec: 4232.37 - lr: 0.000034 - momentum: 0.000000 2024-11-27 20:30:17,663 epoch 52 - iter 4/9 - loss 0.00652454 - time (sec): 0.60 - samples/sec: 3717.77 - lr: 0.000034 - momentum: 0.000000 2024-11-27 20:30:17,895 epoch 52 - iter 5/9 - loss 0.00617854 - time (sec): 0.83 - samples/sec: 3581.30 - lr: 0.000034 - momentum: 0.000000 2024-11-27 20:30:18,040 epoch 52 - iter 6/9 - loss 0.00554341 - time (sec): 0.98 - samples/sec: 3550.66 - lr: 0.000034 - momentum: 0.000000 2024-11-27 20:30:18,176 epoch 52 - iter 7/9 - loss 0.00614053 - time (sec): 1.11 - samples/sec: 3725.87 - lr: 0.000034 - momentum: 0.000000 2024-11-27 20:30:18,318 epoch 52 - iter 8/9 - loss 0.00606837 - time (sec): 1.25 - samples/sec: 3807.26 - lr: 0.000034 - momentum: 0.000000 2024-11-27 20:30:18,456 epoch 52 - iter 9/9 - loss 0.00596942 - time (sec): 1.39 - samples/sec: 3732.57 - lr: 0.000034 - momentum: 0.000000 2024-11-27 20:30:18,457 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:30:18,457 EPOCH 52 done: loss 0.0060 - lr: 0.000034 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████| 1/1 [00:00<00:00, 6.67it/s] 100%|██████████████████████| 1/1 [00:00<00:00, 6.66it/s] 2024-11-27 20:30:18,626 DEV : loss 2.41654896736145 - f1-score (micro avg) 0.319 2024-11-27 20:30:18,627 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:30:18,736 epoch 53 - iter 1/9 - loss 0.00407109 - time (sec): 0.11 - samples/sec: 5753.54 - lr: 0.000034 - momentum: 0.000000 2024-11-27 20:30:18,906 epoch 53 - iter 2/9 - loss 0.00326639 - time (sec): 0.28 - samples/sec: 4371.27 - lr: 0.000034 - momentum: 0.000000 2024-11-27 20:30:19,049 epoch 53 - iter 3/9 - loss 0.00503746 - time (sec): 0.42 - samples/sec: 4110.70 - lr: 0.000034 - momentum: 0.000000 2024-11-27 20:30:19,203 epoch 53 - iter 4/9 - loss 0.00534572 - time (sec): 0.57 - samples/sec: 4090.16 - lr: 0.000034 - momentum: 0.000000 2024-11-27 20:30:19,360 epoch 53 - iter 5/9 - loss 0.00848489 - time (sec): 0.73 - samples/sec: 3925.10 - lr: 0.000034 - momentum: 0.000000 2024-11-27 20:30:19,503 epoch 53 - iter 6/9 - loss 0.00751204 - time (sec): 0.87 - samples/sec: 3981.14 - lr: 0.000034 - momentum: 0.000000 2024-11-27 20:30:19,654 epoch 53 - iter 7/9 - loss 0.00705039 - time (sec): 1.03 - samples/sec: 3951.08 - lr: 0.000034 - momentum: 0.000000 2024-11-27 20:30:19,814 epoch 53 - iter 8/9 - loss 0.00693163 - time (sec): 1.19 - samples/sec: 3900.28 - lr: 0.000034 - momentum: 0.000000 2024-11-27 20:30:19,941 epoch 53 - iter 9/9 - loss 0.00637118 - time (sec): 1.31 - samples/sec: 3960.28 - lr: 0.000034 - momentum: 0.000000 2024-11-27 20:30:19,941 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:30:19,941 EPOCH 53 done: loss 0.0064 - lr: 0.000034 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████| 1/1 [00:00<00:00, 7.28it/s] 100%|██████████████████████| 1/1 [00:00<00:00, 7.27it/s] 2024-11-27 20:30:20,098 DEV : loss 2.4050440788269043 - f1-score (micro avg) 0.3209 2024-11-27 20:30:20,099 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:30:20,196 epoch 54 - iter 1/9 - loss 0.00214258 - time (sec): 0.10 - samples/sec: 5094.47 - lr: 0.000034 - momentum: 0.000000 2024-11-27 20:30:20,344 epoch 54 - iter 2/9 - loss 0.00243728 - time (sec): 0.24 - samples/sec: 4564.48 - lr: 0.000034 - momentum: 0.000000 2024-11-27 20:30:20,535 epoch 54 - iter 3/9 - loss 0.00496421 - time (sec): 0.43 - samples/sec: 4038.61 - lr: 0.000034 - momentum: 0.000000 2024-11-27 20:30:20,701 epoch 54 - iter 4/9 - loss 0.00521582 - time (sec): 0.60 - samples/sec: 3782.53 - lr: 0.000034 - momentum: 0.000000 2024-11-27 20:30:20,847 epoch 54 - iter 5/9 - loss 0.00456017 - time (sec): 0.75 - samples/sec: 3728.44 - lr: 0.000034 - momentum: 0.000000 2024-11-27 20:30:21,001 epoch 54 - iter 6/9 - loss 0.00435335 - time (sec): 0.90 - samples/sec: 3776.65 - lr: 0.000034 - momentum: 0.000000 2024-11-27 20:30:21,349 epoch 54 - iter 7/9 - loss 0.00517606 - time (sec): 1.25 - samples/sec: 3185.93 - lr: 0.000033 - momentum: 0.000000 2024-11-27 20:30:21,507 epoch 54 - iter 8/9 - loss 0.00514149 - time (sec): 1.41 - samples/sec: 3313.11 - lr: 0.000033 - momentum: 0.000000 2024-11-27 20:30:21,655 epoch 54 - iter 9/9 - loss 0.00500332 - time (sec): 1.55 - samples/sec: 3343.66 - lr: 0.000033 - momentum: 0.000000 2024-11-27 20:30:21,655 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:30:21,655 EPOCH 54 done: loss 0.0050 - lr: 0.000033 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████| 1/1 [00:00<00:00, 7.34it/s] 100%|██████████████████████| 1/1 [00:00<00:00, 7.33it/s] 2024-11-27 20:30:21,811 DEV : loss 2.3808412551879883 - f1-score (micro avg) 0.3636 2024-11-27 20:30:21,812 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:30:21,914 epoch 55 - iter 1/9 - loss 0.00527985 - time (sec): 0.10 - samples/sec: 5247.10 - lr: 0.000033 - momentum: 0.000000 2024-11-27 20:30:22,052 epoch 55 - iter 2/9 - loss 0.00324015 - time (sec): 0.24 - samples/sec: 4708.99 - lr: 0.000033 - momentum: 0.000000 2024-11-27 20:30:22,200 epoch 55 - iter 3/9 - loss 0.00285844 - time (sec): 0.39 - samples/sec: 4312.54 - lr: 0.000033 - momentum: 0.000000 2024-11-27 20:30:22,349 epoch 55 - iter 4/9 - loss 0.00372293 - time (sec): 0.54 - samples/sec: 4092.01 - lr: 0.000033 - momentum: 0.000000 2024-11-27 20:30:22,501 epoch 55 - iter 5/9 - loss 0.00347103 - time (sec): 0.69 - samples/sec: 3941.48 - lr: 0.000033 - momentum: 0.000000 2024-11-27 20:30:22,771 epoch 55 - iter 6/9 - loss 0.00470361 - time (sec): 0.96 - samples/sec: 3577.83 - lr: 0.000033 - momentum: 0.000000 2024-11-27 20:30:22,912 epoch 55 - iter 7/9 - loss 0.00449261 - time (sec): 1.10 - samples/sec: 3665.94 - lr: 0.000033 - momentum: 0.000000 2024-11-27 20:30:23,059 epoch 55 - iter 8/9 - loss 0.00414455 - time (sec): 1.25 - samples/sec: 3745.59 - lr: 0.000033 - momentum: 0.000000 2024-11-27 20:30:23,190 epoch 55 - iter 9/9 - loss 0.00523043 - time (sec): 1.38 - samples/sec: 3772.32 - lr: 0.000033 - momentum: 0.000000 2024-11-27 20:30:23,191 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:30:23,191 EPOCH 55 done: loss 0.0052 - lr: 0.000033 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████| 1/1 [00:00<00:00, 5.78it/s] 100%|██████████████████████| 1/1 [00:00<00:00, 5.77it/s] 2024-11-27 20:30:23,384 DEV : loss 2.4994852542877197 - f1-score (micro avg) 0.3333 2024-11-27 20:30:23,385 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:30:23,480 epoch 56 - iter 1/9 - loss 0.00185968 - time (sec): 0.09 - samples/sec: 6337.50 - lr: 0.000033 - momentum: 0.000000 2024-11-27 20:30:23,620 epoch 56 - iter 2/9 - loss 0.00142754 - time (sec): 0.23 - samples/sec: 4917.59 - lr: 0.000033 - momentum: 0.000000 2024-11-27 20:30:23,753 epoch 56 - iter 3/9 - loss 0.00224254 - time (sec): 0.37 - samples/sec: 4829.33 - lr: 0.000033 - momentum: 0.000000 2024-11-27 20:30:23,899 epoch 56 - iter 4/9 - loss 0.00262260 - time (sec): 0.51 - samples/sec: 4578.80 - lr: 0.000033 - momentum: 0.000000 2024-11-27 20:30:24,065 epoch 56 - iter 5/9 - loss 0.00274407 - time (sec): 0.68 - samples/sec: 4302.23 - lr: 0.000033 - momentum: 0.000000 2024-11-27 20:30:24,212 epoch 56 - iter 6/9 - loss 0.00260480 - time (sec): 0.83 - samples/sec: 4172.73 - lr: 0.000033 - momentum: 0.000000 2024-11-27 20:30:24,357 epoch 56 - iter 7/9 - loss 0.00271966 - time (sec): 0.97 - samples/sec: 4084.50 - lr: 0.000033 - momentum: 0.000000 2024-11-27 20:30:24,516 epoch 56 - iter 8/9 - loss 0.00245030 - time (sec): 1.13 - samples/sec: 4116.86 - lr: 0.000033 - momentum: 0.000000 2024-11-27 20:30:24,667 epoch 56 - iter 9/9 - loss 0.00232434 - time (sec): 1.28 - samples/sec: 4059.08 - lr: 0.000033 - momentum: 0.000000 2024-11-27 20:30:24,667 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:30:24,667 EPOCH 56 done: loss 0.0023 - lr: 0.000033 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████| 1/1 [00:00<00:00, 5.84it/s] 100%|██████████████████████| 1/1 [00:00<00:00, 5.83it/s] 2024-11-27 20:30:24,858 DEV : loss 2.576669216156006 - f1-score (micro avg) 0.3114 2024-11-27 20:30:24,860 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:30:24,970 epoch 57 - iter 1/9 - loss 0.01460225 - time (sec): 0.11 - samples/sec: 6591.42 - lr: 0.000033 - momentum: 0.000000 2024-11-27 20:30:25,123 epoch 57 - iter 2/9 - loss 0.00967470 - time (sec): 0.26 - samples/sec: 4670.95 - lr: 0.000033 - momentum: 0.000000 2024-11-27 20:30:25,253 epoch 57 - iter 3/9 - loss 0.00812889 - time (sec): 0.39 - samples/sec: 4410.51 - lr: 0.000033 - momentum: 0.000000 2024-11-27 20:30:25,402 epoch 57 - iter 4/9 - loss 0.00672702 - time (sec): 0.54 - samples/sec: 4290.03 - lr: 0.000033 - momentum: 0.000000 2024-11-27 20:30:25,546 epoch 57 - iter 5/9 - loss 0.00574167 - time (sec): 0.69 - samples/sec: 4248.37 - lr: 0.000033 - momentum: 0.000000 2024-11-27 20:30:25,693 epoch 57 - iter 6/9 - loss 0.00680386 - time (sec): 0.83 - samples/sec: 4124.23 - lr: 0.000033 - momentum: 0.000000 2024-11-27 20:30:25,851 epoch 57 - iter 7/9 - loss 0.00704530 - time (sec): 0.99 - samples/sec: 4138.91 - lr: 0.000033 - momentum: 0.000000 2024-11-27 20:30:26,019 epoch 57 - iter 8/9 - loss 0.00660930 - time (sec): 1.16 - samples/sec: 4061.66 - lr: 0.000033 - momentum: 0.000000 2024-11-27 20:30:26,160 epoch 57 - iter 9/9 - loss 0.00619036 - time (sec): 1.30 - samples/sec: 3999.13 - lr: 0.000033 - momentum: 0.000000 2024-11-27 20:30:26,161 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:30:26,161 EPOCH 57 done: loss 0.0062 - lr: 0.000033 0%| | 0/1 [00:00<?, 100%|█| 1/1 [00:00<00 100%|█| 1/1 [00:00<00 2024-11-27 20:30:26,334 DEV : loss 2.6235127449035645 - f1-score (micro avg) 0.2989 2024-11-27 20:30:26,336 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:30:26,431 epoch 58 - iter 1/9 - loss 0.00449373 - time (sec): 0.09 - samples/sec: 5278.51 - lr: 0.000033 - momentum: 0.000000 2024-11-27 20:30:26,569 epoch 58 - iter 2/9 - loss 0.00286330 - time (sec): 0.23 - samples/sec: 4697.85 - lr: 0.000033 - momentum: 0.000000 2024-11-27 20:30:26,704 epoch 58 - iter 3/9 - loss 0.00250136 - time (sec): 0.37 - samples/sec: 4557.32 - lr: 0.000033 - momentum: 0.000000 2024-11-27 20:30:26,863 epoch 58 - iter 4/9 - loss 0.00268704 - time (sec): 0.53 - samples/sec: 4334.48 - lr: 0.000033 - momentum: 0.000000 2024-11-27 20:30:27,012 epoch 58 - iter 5/9 - loss 0.00239891 - time (sec): 0.68 - samples/sec: 4103.29 - lr: 0.000033 - momentum: 0.000000 2024-11-27 20:30:27,156 epoch 58 - iter 6/9 - loss 0.00247133 - time (sec): 0.82 - samples/sec: 4080.31 - lr: 0.000033 - momentum: 0.000000 2024-11-27 20:30:27,282 epoch 58 - iter 7/9 - loss 0.00476094 - time (sec): 0.95 - samples/sec: 4113.04 - lr: 0.000033 - momentum: 0.000000 2024-11-27 20:30:27,425 epoch 58 - iter 8/9 - loss 0.00690358 - time (sec): 1.09 - samples/sec: 4205.61 - lr: 0.000033 - momentum: 0.000000 2024-11-27 20:30:27,565 epoch 58 - iter 9/9 - loss 0.00617149 - time (sec): 1.23 - samples/sec: 4229.24 - lr: 0.000033 - momentum: 0.000000 2024-11-27 20:30:27,566 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:30:27,566 EPOCH 58 done: loss 0.0062 - lr: 0.000033 0%| | 0/1 [00: 100%|█| 1/1 [00: 100%|█| 1/1 [00: 2024-11-27 20:30:27,740 DEV : loss 2.6644835472106934 - f1-score (micro avg) 0.3418 2024-11-27 20:30:27,741 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:30:27,844 epoch 59 - iter 1/9 - loss 0.00195573 - time (sec): 0.10 - samples/sec: 6224.82 - lr: 0.000033 - momentum: 0.000000 2024-11-27 20:30:28,006 epoch 59 - iter 2/9 - loss 0.00169438 - time (sec): 0.26 - samples/sec: 4844.54 - lr: 0.000033 - momentum: 0.000000 2024-11-27 20:30:28,168 epoch 59 - iter 3/9 - loss 0.00205756 - time (sec): 0.43 - samples/sec: 4091.75 - lr: 0.000033 - momentum: 0.000000 2024-11-27 20:30:28,295 epoch 59 - iter 4/9 - loss 0.00180200 - time (sec): 0.55 - samples/sec: 4146.03 - lr: 0.000033 - momentum: 0.000000 2024-11-27 20:30:28,480 epoch 59 - iter 5/9 - loss 0.00392736 - time (sec): 0.74 - samples/sec: 3889.60 - lr: 0.000033 - momentum: 0.000000 2024-11-27 20:30:28,709 epoch 59 - iter 6/9 - loss 0.00401945 - time (sec): 0.97 - samples/sec: 3534.07 - lr: 0.000032 - momentum: 0.000000 2024-11-27 20:30:28,828 epoch 59 - iter 7/9 - loss 0.00520183 - time (sec): 1.09 - samples/sec: 3691.58 - lr: 0.000032 - momentum: 0.000000 2024-11-27 20:30:28,962 epoch 59 - iter 8/9 - loss 0.00471358 - time (sec): 1.22 - samples/sec: 3765.86 - lr: 0.000032 - momentum: 0.000000 2024-11-27 20:30:29,104 epoch 59 - iter 9/9 - loss 0.00428617 - time (sec): 1.36 - samples/sec: 3816.16 - lr: 0.000032 - momentum: 0.000000 2024-11-27 20:30:29,104 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:30:29,104 EPOCH 59 done: loss 0.0043 - lr: 0.000032 0%| | 0/1 [00:00<?, ?it/s] 100%|█| 1/1 [00:00<00:00, 5.93it/s] 100%|█| 1/1 [00:00<00:00, 5.92it/s] 2024-11-27 20:30:29,293 DEV : loss 2.674125909805298 - f1-score (micro avg) 0.2963 2024-11-27 20:30:29,294 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:30:29,398 epoch 60 - iter 1/9 - loss 0.00255731 - time (sec): 0.10 - samples/sec: 5176.74 - lr: 0.000032 - momentum: 0.000000 2024-11-27 20:30:29,540 epoch 60 - iter 2/9 - loss 0.00134832 - time (sec): 0.24 - samples/sec: 5266.83 - lr: 0.000032 - momentum: 0.000000 2024-11-27 20:30:29,675 epoch 60 - iter 3/9 - loss 0.00121503 - time (sec): 0.38 - samples/sec: 4787.64 - lr: 0.000032 - momentum: 0.000000 2024-11-27 20:30:29,840 epoch 60 - iter 4/9 - loss 0.00515176 - time (sec): 0.54 - samples/sec: 4392.01 - lr: 0.000032 - momentum: 0.000000 2024-11-27 20:30:30,011 epoch 60 - iter 5/9 - loss 0.00490777 - time (sec): 0.72 - samples/sec: 4162.18 - lr: 0.000032 - momentum: 0.000000 2024-11-27 20:30:30,179 epoch 60 - iter 6/9 - loss 0.00428745 - time (sec): 0.88 - samples/sec: 3957.50 - lr: 0.000032 - momentum: 0.000000 2024-11-27 20:30:30,335 epoch 60 - iter 7/9 - loss 0.00389781 - time (sec): 1.04 - samples/sec: 3954.78 - lr: 0.000032 - momentum: 0.000000 2024-11-27 20:30:30,521 epoch 60 - iter 8/9 - loss 0.00358861 - time (sec): 1.23 - samples/sec: 3844.83 - lr: 0.000032 - momentum: 0.000000 2024-11-27 20:30:30,694 epoch 60 - iter 9/9 - loss 0.00334223 - time (sec): 1.40 - samples/sec: 3717.05 - lr: 0.000032 - momentum: 0.000000 2024-11-27 20:30:30,694 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:30:30,694 EPOCH 60 done: loss 0.0033 - lr: 0.000032 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 5.73it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 5.72it/s] 2024-11-27 20:30:30,888 DEV : loss 2.661932945251465 - f1-score (micro avg) 0.2857 2024-11-27 20:30:30,889 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:30:31,009 epoch 61 - iter 1/9 - loss 0.00367383 - time (sec): 0.12 - samples/sec: 4492.02 - lr: 0.000032 - momentum: 0.000000 2024-11-27 20:30:31,162 epoch 61 - iter 2/9 - loss 0.00234736 - time (sec): 0.27 - samples/sec: 3976.69 - lr: 0.000032 - momentum: 0.000000 2024-11-27 20:30:31,329 epoch 61 - iter 3/9 - loss 0.00787357 - time (sec): 0.44 - samples/sec: 3823.93 - lr: 0.000032 - momentum: 0.000000 2024-11-27 20:30:31,582 epoch 61 - iter 4/9 - loss 0.00644642 - time (sec): 0.69 - samples/sec: 3372.39 - lr: 0.000032 - momentum: 0.000000 2024-11-27 20:30:31,726 epoch 61 - iter 5/9 - loss 0.00546942 - time (sec): 0.84 - samples/sec: 3493.31 - lr: 0.000032 - momentum: 0.000000 2024-11-27 20:30:31,857 epoch 61 - iter 6/9 - loss 0.00504069 - time (sec): 0.97 - samples/sec: 3582.28 - lr: 0.000032 - momentum: 0.000000 2024-11-27 20:30:31,987 epoch 61 - iter 7/9 - loss 0.00637908 - time (sec): 1.10 - samples/sec: 3654.31 - lr: 0.000032 - momentum: 0.000000 2024-11-27 20:30:32,163 epoch 61 - iter 8/9 - loss 0.00806558 - time (sec): 1.27 - samples/sec: 3628.00 - lr: 0.000032 - momentum: 0.000000 2024-11-27 20:30:32,451 epoch 61 - iter 9/9 - loss 0.00783262 - time (sec): 1.56 - samples/sec: 3328.85 - lr: 0.000032 - momentum: 0.000000 2024-11-27 20:30:32,452 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:30:32,452 EPOCH 61 done: loss 0.0078 - lr: 0.000032 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.19it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.18it/s] 2024-11-27 20:30:32,633 DEV : loss 2.789830446243286 - f1-score (micro avg) 0.3333 2024-11-27 20:30:32,634 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:30:32,728 epoch 62 - iter 1/9 - loss 0.00122362 - time (sec): 0.09 - samples/sec: 5800.62 - lr: 0.000032 - momentum: 0.000000 2024-11-27 20:30:32,856 epoch 62 - iter 2/9 - loss 0.00106563 - time (sec): 0.22 - samples/sec: 4875.18 - lr: 0.000032 - momentum: 0.000000 2024-11-27 20:30:32,985 epoch 62 - iter 3/9 - loss 0.00108902 - time (sec): 0.35 - samples/sec: 4598.32 - lr: 0.000032 - momentum: 0.000000 2024-11-27 20:30:33,129 epoch 62 - iter 4/9 - loss 0.00173859 - time (sec): 0.49 - samples/sec: 4419.23 - lr: 0.000032 - momentum: 0.000000 2024-11-27 20:30:33,289 epoch 62 - iter 5/9 - loss 0.00162051 - time (sec): 0.65 - samples/sec: 4284.25 - lr: 0.000032 - momentum: 0.000000 2024-11-27 20:30:33,630 epoch 62 - iter 6/9 - loss 0.00171717 - time (sec): 1.00 - samples/sec: 3520.47 - lr: 0.000032 - momentum: 0.000000 2024-11-27 20:30:33,785 epoch 62 - iter 7/9 - loss 0.00206084 - time (sec): 1.15 - samples/sec: 3578.09 - lr: 0.000032 - momentum: 0.000000 2024-11-27 20:30:33,946 epoch 62 - iter 8/9 - loss 0.00222345 - time (sec): 1.31 - samples/sec: 3656.52 - lr: 0.000032 - momentum: 0.000000 2024-11-27 20:30:34,075 epoch 62 - iter 9/9 - loss 0.00215674 - time (sec): 1.44 - samples/sec: 3609.26 - lr: 0.000032 - momentum: 0.000000 2024-11-27 20:30:34,075 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:30:34,075 EPOCH 62 done: loss 0.0022 - lr: 0.000032 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.89it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.88it/s] 2024-11-27 20:30:34,240 DEV : loss 2.6965525150299072 - f1-score (micro avg) 0.3185 2024-11-27 20:30:34,242 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:30:34,353 epoch 63 - iter 1/9 - loss 0.00774906 - time (sec): 0.11 - samples/sec: 7604.80 - lr: 0.000032 - momentum: 0.000000 2024-11-27 20:30:34,490 epoch 63 - iter 2/9 - loss 0.00551831 - time (sec): 0.25 - samples/sec: 5411.76 - lr: 0.000032 - momentum: 0.000000 2024-11-27 20:30:34,625 epoch 63 - iter 3/9 - loss 0.00403787 - time (sec): 0.38 - samples/sec: 4944.88 - lr: 0.000032 - momentum: 0.000000 2024-11-27 20:30:34,773 epoch 63 - iter 4/9 - loss 0.00368907 - time (sec): 0.53 - samples/sec: 4571.34 - lr: 0.000032 - momentum: 0.000000 2024-11-27 20:30:34,940 epoch 63 - iter 5/9 - loss 0.00329401 - time (sec): 0.70 - samples/sec: 4372.53 - lr: 0.000032 - momentum: 0.000000 2024-11-27 20:30:35,109 epoch 63 - iter 6/9 - loss 0.00299634 - time (sec): 0.87 - samples/sec: 4209.49 - lr: 0.000032 - momentum: 0.000000 2024-11-27 20:30:35,242 epoch 63 - iter 7/9 - loss 0.00287536 - time (sec): 1.00 - samples/sec: 4186.64 - lr: 0.000032 - momentum: 0.000000 2024-11-27 20:30:35,407 epoch 63 - iter 8/9 - loss 0.00324038 - time (sec): 1.16 - samples/sec: 4027.57 - lr: 0.000032 - momentum: 0.000000 2024-11-27 20:30:35,668 epoch 63 - iter 9/9 - loss 0.00374640 - time (sec): 1.43 - samples/sec: 3646.50 - lr: 0.000032 - momentum: 0.000000 2024-11-27 20:30:35,668 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:30:35,668 EPOCH 63 done: loss 0.0037 - lr: 0.000032 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 7.34it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 7.33it/s] 2024-11-27 20:30:35,824 DEV : loss 2.613720417022705 - f1-score (micro avg) 0.3214 2024-11-27 20:30:35,825 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:30:35,923 epoch 64 - iter 1/9 - loss 0.00172739 - time (sec): 0.10 - samples/sec: 5656.82 - lr: 0.000032 - momentum: 0.000000 2024-11-27 20:30:36,073 epoch 64 - iter 2/9 - loss 0.00203934 - time (sec): 0.25 - samples/sec: 4869.53 - lr: 0.000032 - momentum: 0.000000 2024-11-27 20:30:36,200 epoch 64 - iter 3/9 - loss 0.00183696 - time (sec): 0.37 - samples/sec: 4573.07 - lr: 0.000032 - momentum: 0.000000 2024-11-27 20:30:36,334 epoch 64 - iter 4/9 - loss 0.00172182 - time (sec): 0.51 - samples/sec: 4407.32 - lr: 0.000032 - momentum: 0.000000 2024-11-27 20:30:36,478 epoch 64 - iter 5/9 - loss 0.00627130 - time (sec): 0.65 - samples/sec: 4504.47 - lr: 0.000031 - momentum: 0.000000 2024-11-27 20:30:36,593 epoch 64 - iter 6/9 - loss 0.00544231 - time (sec): 0.77 - samples/sec: 4552.10 - lr: 0.000031 - momentum: 0.000000 2024-11-27 20:30:36,727 epoch 64 - iter 7/9 - loss 0.00491628 - time (sec): 0.90 - samples/sec: 4503.51 - lr: 0.000031 - momentum: 0.000000 2024-11-27 20:30:36,878 epoch 64 - iter 8/9 - loss 0.00454948 - time (sec): 1.05 - samples/sec: 4338.81 - lr: 0.000031 - momentum: 0.000000 2024-11-27 20:30:37,064 epoch 64 - iter 9/9 - loss 0.00406654 - time (sec): 1.24 - samples/sec: 4198.75 - lr: 0.000031 - momentum: 0.000000 2024-11-27 20:30:37,065 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:30:37,065 EPOCH 64 done: loss 0.0041 - lr: 0.000031 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 3.75it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 3.75it/s] 2024-11-27 20:30:37,350 DEV : loss 2.7119054794311523 - f1-score (micro avg) 0.3247 2024-11-27 20:30:37,352 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:30:37,461 epoch 65 - iter 1/9 - loss 0.00723419 - time (sec): 0.11 - samples/sec: 7268.63 - lr: 0.000031 - momentum: 0.000000 2024-11-27 20:30:37,610 epoch 65 - iter 2/9 - loss 0.01103440 - time (sec): 0.26 - samples/sec: 4954.57 - lr: 0.000031 - momentum: 0.000000 2024-11-27 20:30:37,736 epoch 65 - iter 3/9 - loss 0.00830430 - time (sec): 0.38 - samples/sec: 4664.22 - lr: 0.000031 - momentum: 0.000000 2024-11-27 20:30:37,863 epoch 65 - iter 4/9 - loss 0.00662726 - time (sec): 0.51 - samples/sec: 4576.79 - lr: 0.000031 - momentum: 0.000000 2024-11-27 20:30:37,986 epoch 65 - iter 5/9 - loss 0.01010828 - time (sec): 0.63 - samples/sec: 4497.17 - lr: 0.000031 - momentum: 0.000000 2024-11-27 20:30:38,140 epoch 65 - iter 6/9 - loss 0.00863645 - time (sec): 0.79 - samples/sec: 4400.87 - lr: 0.000031 - momentum: 0.000000 2024-11-27 20:30:38,292 epoch 65 - iter 7/9 - loss 0.00741187 - time (sec): 0.94 - samples/sec: 4370.40 - lr: 0.000031 - momentum: 0.000000 2024-11-27 20:30:38,452 epoch 65 - iter 8/9 - loss 0.00667307 - time (sec): 1.10 - samples/sec: 4282.60 - lr: 0.000031 - momentum: 0.000000 2024-11-27 20:30:38,606 epoch 65 - iter 9/9 - loss 0.00759974 - time (sec): 1.25 - samples/sec: 4147.62 - lr: 0.000031 - momentum: 0.000000 2024-11-27 20:30:38,606 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:30:38,606 EPOCH 65 done: loss 0.0076 - lr: 0.000031 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.66it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.65it/s] 2024-11-27 20:30:38,775 DEV : loss 2.6408851146698 - f1-score (micro avg) 0.3152 2024-11-27 20:30:38,777 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:30:38,883 epoch 66 - iter 1/9 - loss 0.00070387 - time (sec): 0.11 - samples/sec: 6156.62 - lr: 0.000031 - momentum: 0.000000 2024-11-27 20:30:39,033 epoch 66 - iter 2/9 - loss 0.00074410 - time (sec): 0.26 - samples/sec: 5173.87 - lr: 0.000031 - momentum: 0.000000 2024-11-27 20:30:39,183 epoch 66 - iter 3/9 - loss 0.00071880 - time (sec): 0.41 - samples/sec: 4627.09 - lr: 0.000031 - momentum: 0.000000 2024-11-27 20:30:39,312 epoch 66 - iter 4/9 - loss 0.00183268 - time (sec): 0.53 - samples/sec: 4406.89 - lr: 0.000031 - momentum: 0.000000 2024-11-27 20:30:39,670 epoch 66 - iter 5/9 - loss 0.00426036 - time (sec): 0.89 - samples/sec: 3370.48 - lr: 0.000031 - momentum: 0.000000 2024-11-27 20:30:39,806 epoch 66 - iter 6/9 - loss 0.00380742 - time (sec): 1.03 - samples/sec: 3440.17 - lr: 0.000031 - momentum: 0.000000 2024-11-27 20:30:39,953 epoch 66 - iter 7/9 - loss 0.00452197 - time (sec): 1.18 - samples/sec: 3619.95 - lr: 0.000031 - momentum: 0.000000 2024-11-27 20:30:40,088 epoch 66 - iter 8/9 - loss 0.00420461 - time (sec): 1.31 - samples/sec: 3580.97 - lr: 0.000031 - momentum: 0.000000 2024-11-27 20:30:40,273 epoch 66 - iter 9/9 - loss 0.00417601 - time (sec): 1.49 - samples/sec: 3476.44 - lr: 0.000031 - momentum: 0.000000 2024-11-27 20:30:40,273 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:30:40,273 EPOCH 66 done: loss 0.0042 - lr: 0.000031 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.30it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.28it/s] 2024-11-27 20:30:40,451 DEV : loss 2.7103917598724365 - f1-score (micro avg) 0.3023 2024-11-27 20:30:40,453 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:30:40,550 epoch 67 - iter 1/9 - loss 0.00621380 - time (sec): 0.10 - samples/sec: 5262.38 - lr: 0.000031 - momentum: 0.000000 2024-11-27 20:30:40,686 epoch 67 - iter 2/9 - loss 0.00373714 - time (sec): 0.23 - samples/sec: 4814.70 - lr: 0.000031 - momentum: 0.000000 2024-11-27 20:30:40,814 epoch 67 - iter 3/9 - loss 0.00333986 - time (sec): 0.36 - samples/sec: 4418.64 - lr: 0.000031 - momentum: 0.000000 2024-11-27 20:30:40,980 epoch 67 - iter 4/9 - loss 0.00238499 - time (sec): 0.53 - samples/sec: 4492.79 - lr: 0.000031 - momentum: 0.000000 2024-11-27 20:30:41,138 epoch 67 - iter 5/9 - loss 0.00214980 - time (sec): 0.68 - samples/sec: 4101.97 - lr: 0.000031 - momentum: 0.000000 2024-11-27 20:30:41,323 epoch 67 - iter 6/9 - loss 0.00197207 - time (sec): 0.87 - samples/sec: 4002.34 - lr: 0.000031 - momentum: 0.000000 2024-11-27 20:30:41,488 epoch 67 - iter 7/9 - loss 0.00183958 - time (sec): 1.03 - samples/sec: 3898.81 - lr: 0.000031 - momentum: 0.000000 2024-11-27 20:30:41,644 epoch 67 - iter 8/9 - loss 0.00173321 - time (sec): 1.19 - samples/sec: 3868.66 - lr: 0.000031 - momentum: 0.000000 2024-11-27 20:30:41,800 epoch 67 - iter 9/9 - loss 0.00165077 - time (sec): 1.35 - samples/sec: 3860.45 - lr: 0.000031 - momentum: 0.000000 2024-11-27 20:30:41,800 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:30:41,800 EPOCH 67 done: loss 0.0017 - lr: 0.000031 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.12it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.12it/s] 2024-11-27 20:30:41,983 DEV : loss 2.758021354675293 - f1-score (micro avg) 0.2875 2024-11-27 20:30:41,984 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:30:42,078 epoch 68 - iter 1/9 - loss 0.00097752 - time (sec): 0.09 - samples/sec: 5955.69 - lr: 0.000031 - momentum: 0.000000 2024-11-27 20:30:42,216 epoch 68 - iter 2/9 - loss 0.01909907 - time (sec): 0.23 - samples/sec: 4725.34 - lr: 0.000031 - momentum: 0.000000 2024-11-27 20:30:42,363 epoch 68 - iter 3/9 - loss 0.02397638 - time (sec): 0.38 - samples/sec: 4410.85 - lr: 0.000031 - momentum: 0.000000 2024-11-27 20:30:42,506 epoch 68 - iter 4/9 - loss 0.02391126 - time (sec): 0.52 - samples/sec: 4496.78 - lr: 0.000031 - momentum: 0.000000 2024-11-27 20:30:42,652 epoch 68 - iter 5/9 - loss 0.01948060 - time (sec): 0.67 - samples/sec: 4337.66 - lr: 0.000031 - momentum: 0.000000 2024-11-27 20:30:42,785 epoch 68 - iter 6/9 - loss 0.01720057 - time (sec): 0.80 - samples/sec: 4216.23 - lr: 0.000031 - momentum: 0.000000 2024-11-27 20:30:42,953 epoch 68 - iter 7/9 - loss 0.01442123 - time (sec): 0.97 - samples/sec: 4186.55 - lr: 0.000031 - momentum: 0.000000 2024-11-27 20:30:43,137 epoch 68 - iter 8/9 - loss 0.01268084 - time (sec): 1.15 - samples/sec: 4049.98 - lr: 0.000031 - momentum: 0.000000 2024-11-27 20:30:43,469 epoch 68 - iter 9/9 - loss 0.01156280 - time (sec): 1.48 - samples/sec: 3501.88 - lr: 0.000031 - momentum: 0.000000 2024-11-27 20:30:43,469 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:30:43,470 EPOCH 68 done: loss 0.0116 - lr: 0.000031 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.94it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.93it/s] 2024-11-27 20:30:43,633 DEV : loss 2.752422571182251 - f1-score (micro avg) 0.3169 2024-11-27 20:30:43,634 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:30:43,728 epoch 69 - iter 1/9 - loss 0.00682956 - time (sec): 0.09 - samples/sec: 5286.80 - lr: 0.000031 - momentum: 0.000000 2024-11-27 20:30:43,865 epoch 69 - iter 2/9 - loss 0.00360909 - time (sec): 0.23 - samples/sec: 4537.55 - lr: 0.000031 - momentum: 0.000000 2024-11-27 20:30:44,087 epoch 69 - iter 3/9 - loss 0.00251589 - time (sec): 0.45 - samples/sec: 3490.75 - lr: 0.000031 - momentum: 0.000000 2024-11-27 20:30:44,294 epoch 69 - iter 4/9 - loss 0.00218956 - time (sec): 0.66 - samples/sec: 3212.00 - lr: 0.000030 - momentum: 0.000000 2024-11-27 20:30:44,428 epoch 69 - iter 5/9 - loss 0.00386519 - time (sec): 0.79 - samples/sec: 3464.62 - lr: 0.000030 - momentum: 0.000000 2024-11-27 20:30:44,563 epoch 69 - iter 6/9 - loss 0.00395190 - time (sec): 0.93 - samples/sec: 3625.97 - lr: 0.000030 - momentum: 0.000000 2024-11-27 20:30:44,708 epoch 69 - iter 7/9 - loss 0.00477124 - time (sec): 1.07 - samples/sec: 3820.25 - lr: 0.000030 - momentum: 0.000000 2024-11-27 20:30:44,852 epoch 69 - iter 8/9 - loss 0.00487862 - time (sec): 1.22 - samples/sec: 3899.43 - lr: 0.000030 - momentum: 0.000000 2024-11-27 20:30:44,986 epoch 69 - iter 9/9 - loss 0.00459630 - time (sec): 1.35 - samples/sec: 3847.82 - lr: 0.000030 - momentum: 0.000000 2024-11-27 20:30:44,986 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:30:44,986 EPOCH 69 done: loss 0.0046 - lr: 0.000030 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.37it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.36it/s] 2024-11-27 20:30:45,163 DEV : loss 2.7715141773223877 - f1-score (micro avg) 0.3109 2024-11-27 20:30:45,164 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:30:45,255 epoch 70 - iter 1/9 - loss 0.00498575 - time (sec): 0.09 - samples/sec: 5356.68 - lr: 0.000030 - momentum: 0.000000 2024-11-27 20:30:45,399 epoch 70 - iter 2/9 - loss 0.00268321 - time (sec): 0.23 - samples/sec: 4614.20 - lr: 0.000030 - momentum: 0.000000 2024-11-27 20:30:45,568 epoch 70 - iter 3/9 - loss 0.00361831 - time (sec): 0.40 - samples/sec: 4409.04 - lr: 0.000030 - momentum: 0.000000 2024-11-27 20:30:45,727 epoch 70 - iter 4/9 - loss 0.00366595 - time (sec): 0.56 - samples/sec: 4170.03 - lr: 0.000030 - momentum: 0.000000 2024-11-27 20:30:45,881 epoch 70 - iter 5/9 - loss 0.00307795 - time (sec): 0.72 - samples/sec: 4097.94 - lr: 0.000030 - momentum: 0.000000 2024-11-27 20:30:46,041 epoch 70 - iter 6/9 - loss 0.00269474 - time (sec): 0.88 - samples/sec: 4005.69 - lr: 0.000030 - momentum: 0.000000 2024-11-27 20:30:46,193 epoch 70 - iter 7/9 - loss 0.00254692 - time (sec): 1.03 - samples/sec: 3963.76 - lr: 0.000030 - momentum: 0.000000 2024-11-27 20:30:46,334 epoch 70 - iter 8/9 - loss 0.00398214 - time (sec): 1.17 - samples/sec: 4038.36 - lr: 0.000030 - momentum: 0.000000 2024-11-27 20:30:46,448 epoch 70 - iter 9/9 - loss 0.00365077 - time (sec): 1.28 - samples/sec: 4051.93 - lr: 0.000030 - momentum: 0.000000 2024-11-27 20:30:46,448 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:30:46,449 EPOCH 70 done: loss 0.0037 - lr: 0.000030 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 7.41it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 7.39it/s] 2024-11-27 20:30:46,603 DEV : loss 2.8470406532287598 - f1-score (micro avg) 0.3226 2024-11-27 20:30:46,604 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:30:46,706 epoch 71 - iter 1/9 - loss 0.01662168 - time (sec): 0.10 - samples/sec: 5376.21 - lr: 0.000030 - momentum: 0.000000 2024-11-27 20:30:46,841 epoch 71 - iter 2/9 - loss 0.00873959 - time (sec): 0.24 - samples/sec: 4650.51 - lr: 0.000030 - momentum: 0.000000 2024-11-27 20:30:47,002 epoch 71 - iter 3/9 - loss 0.00810899 - time (sec): 0.40 - samples/sec: 4581.13 - lr: 0.000030 - momentum: 0.000000 2024-11-27 20:30:47,146 epoch 71 - iter 4/9 - loss 0.00634689 - time (sec): 0.54 - samples/sec: 4471.04 - lr: 0.000030 - momentum: 0.000000 2024-11-27 20:30:47,298 epoch 71 - iter 5/9 - loss 0.01022171 - time (sec): 0.69 - samples/sec: 4248.62 - lr: 0.000030 - momentum: 0.000000 2024-11-27 20:30:47,546 epoch 71 - iter 6/9 - loss 0.01084034 - time (sec): 0.94 - samples/sec: 3830.60 - lr: 0.000030 - momentum: 0.000000 2024-11-27 20:30:47,688 epoch 71 - iter 7/9 - loss 0.00951377 - time (sec): 1.08 - samples/sec: 3844.14 - lr: 0.000030 - momentum: 0.000000 2024-11-27 20:30:47,809 epoch 71 - iter 8/9 - loss 0.01090644 - time (sec): 1.20 - samples/sec: 3777.20 - lr: 0.000030 - momentum: 0.000000 2024-11-27 20:30:47,951 epoch 71 - iter 9/9 - loss 0.01523054 - time (sec): 1.35 - samples/sec: 3860.73 - lr: 0.000030 - momentum: 0.000000 2024-11-27 20:30:47,952 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:30:47,952 EPOCH 71 done: loss 0.0152 - lr: 0.000030 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 5.63it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 5.62it/s] 2024-11-27 20:30:48,149 DEV : loss 2.7537691593170166 - f1-score (micro avg) 0.3 2024-11-27 20:30:48,150 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:30:48,253 epoch 72 - iter 1/9 - loss 0.00046243 - time (sec): 0.10 - samples/sec: 6683.17 - lr: 0.000030 - momentum: 0.000000 2024-11-27 20:30:48,393 epoch 72 - iter 2/9 - loss 0.00038062 - time (sec): 0.24 - samples/sec: 4882.41 - lr: 0.000030 - momentum: 0.000000 2024-11-27 20:30:48,532 epoch 72 - iter 3/9 - loss 0.00041283 - time (sec): 0.38 - samples/sec: 5015.66 - lr: 0.000030 - momentum: 0.000000 2024-11-27 20:30:48,687 epoch 72 - iter 4/9 - loss 0.00037717 - time (sec): 0.54 - samples/sec: 4742.05 - lr: 0.000030 - momentum: 0.000000 2024-11-27 20:30:48,839 epoch 72 - iter 5/9 - loss 0.00038095 - time (sec): 0.69 - samples/sec: 4393.55 - lr: 0.000030 - momentum: 0.000000 2024-11-27 20:30:48,989 epoch 72 - iter 6/9 - loss 0.00039321 - time (sec): 0.84 - samples/sec: 4479.88 - lr: 0.000030 - momentum: 0.000000 2024-11-27 20:30:49,133 epoch 72 - iter 7/9 - loss 0.00046056 - time (sec): 0.98 - samples/sec: 4319.50 - lr: 0.000030 - momentum: 0.000000 2024-11-27 20:30:49,256 epoch 72 - iter 8/9 - loss 0.00048704 - time (sec): 1.10 - samples/sec: 4275.97 - lr: 0.000030 - momentum: 0.000000 2024-11-27 20:30:49,388 epoch 72 - iter 9/9 - loss 0.00049311 - time (sec): 1.24 - samples/sec: 4202.96 - lr: 0.000030 - momentum: 0.000000 2024-11-27 20:30:49,388 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:30:49,389 EPOCH 72 done: loss 0.0005 - lr: 0.000030 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.21it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.20it/s] 2024-11-27 20:30:49,569 DEV : loss 2.795046806335449 - f1-score (micro avg) 0.323 2024-11-27 20:30:49,570 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:30:49,665 epoch 73 - iter 1/9 - loss 0.00032773 - time (sec): 0.09 - samples/sec: 5289.23 - lr: 0.000030 - momentum: 0.000000 2024-11-27 20:30:49,787 epoch 73 - iter 2/9 - loss 0.00228652 - time (sec): 0.22 - samples/sec: 4719.79 - lr: 0.000030 - momentum: 0.000000 2024-11-27 20:30:49,924 epoch 73 - iter 3/9 - loss 0.00462292 - time (sec): 0.35 - samples/sec: 4273.67 - lr: 0.000030 - momentum: 0.000000 2024-11-27 20:30:50,096 epoch 73 - iter 4/9 - loss 0.00335683 - time (sec): 0.53 - samples/sec: 4123.88 - lr: 0.000030 - momentum: 0.000000 2024-11-27 20:30:50,245 epoch 73 - iter 5/9 - loss 0.00276688 - time (sec): 0.67 - samples/sec: 3979.49 - lr: 0.000030 - momentum: 0.000000 2024-11-27 20:30:50,402 epoch 73 - iter 6/9 - loss 0.00238219 - time (sec): 0.83 - samples/sec: 3941.95 - lr: 0.000030 - momentum: 0.000000 2024-11-27 20:30:50,566 epoch 73 - iter 7/9 - loss 0.00211103 - time (sec): 0.99 - samples/sec: 3856.98 - lr: 0.000030 - momentum: 0.000000 2024-11-27 20:30:50,730 epoch 73 - iter 8/9 - loss 0.00189454 - time (sec): 1.16 - samples/sec: 3992.42 - lr: 0.000030 - momentum: 0.000000 2024-11-27 20:30:50,881 epoch 73 - iter 9/9 - loss 0.00283469 - time (sec): 1.31 - samples/sec: 3967.11 - lr: 0.000030 - momentum: 0.000000 2024-11-27 20:30:50,882 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:30:50,882 EPOCH 73 done: loss 0.0028 - lr: 0.000030 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.59it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.58it/s] 2024-11-27 20:30:51,052 DEV : loss 2.862443208694458 - f1-score (micro avg) 0.3179 2024-11-27 20:30:51,054 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:30:51,154 epoch 74 - iter 1/9 - loss 0.00071612 - time (sec): 0.10 - samples/sec: 5362.14 - lr: 0.000030 - momentum: 0.000000 2024-11-27 20:30:51,305 epoch 74 - iter 2/9 - loss 0.00171475 - time (sec): 0.25 - samples/sec: 4402.38 - lr: 0.000030 - momentum: 0.000000 2024-11-27 20:30:51,442 epoch 74 - iter 3/9 - loss 0.00663373 - time (sec): 0.39 - samples/sec: 4256.26 - lr: 0.000030 - momentum: 0.000000 2024-11-27 20:30:51,612 epoch 74 - iter 4/9 - loss 0.00487036 - time (sec): 0.56 - samples/sec: 4111.41 - lr: 0.000029 - momentum: 0.000000 2024-11-27 20:30:51,841 epoch 74 - iter 5/9 - loss 0.00394050 - time (sec): 0.79 - samples/sec: 3687.57 - lr: 0.000029 - momentum: 0.000000 2024-11-27 20:30:51,984 epoch 74 - iter 6/9 - loss 0.00347780 - time (sec): 0.93 - samples/sec: 3725.79 - lr: 0.000029 - momentum: 0.000000 2024-11-27 20:30:52,116 epoch 74 - iter 7/9 - loss 0.00301150 - time (sec): 1.06 - samples/sec: 3818.85 - lr: 0.000029 - momentum: 0.000000 2024-11-27 20:30:52,397 epoch 74 - iter 8/9 - loss 0.00271338 - time (sec): 1.34 - samples/sec: 3427.24 - lr: 0.000029 - momentum: 0.000000 2024-11-27 20:30:52,542 epoch 74 - iter 9/9 - loss 0.00242806 - time (sec): 1.49 - samples/sec: 3494.30 - lr: 0.000029 - momentum: 0.000000 2024-11-27 20:30:52,542 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:30:52,542 EPOCH 74 done: loss 0.0024 - lr: 0.000029 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 7.38it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 7.37it/s] 2024-11-27 20:30:52,697 DEV : loss 2.9047720432281494 - f1-score (micro avg) 0.3137 2024-11-27 20:30:52,699 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:30:52,804 epoch 75 - iter 1/9 - loss 0.00117637 - time (sec): 0.10 - samples/sec: 6331.01 - lr: 0.000029 - momentum: 0.000000 2024-11-27 20:30:52,942 epoch 75 - iter 2/9 - loss 0.00126667 - time (sec): 0.24 - samples/sec: 4742.13 - lr: 0.000029 - momentum: 0.000000 2024-11-27 20:30:53,086 epoch 75 - iter 3/9 - loss 0.00097552 - time (sec): 0.39 - samples/sec: 4548.77 - lr: 0.000029 - momentum: 0.000000 2024-11-27 20:30:53,213 epoch 75 - iter 4/9 - loss 0.00327432 - time (sec): 0.51 - samples/sec: 4427.60 - lr: 0.000029 - momentum: 0.000000 2024-11-27 20:30:53,470 epoch 75 - iter 5/9 - loss 0.00606360 - time (sec): 0.77 - samples/sec: 3777.14 - lr: 0.000029 - momentum: 0.000000 2024-11-27 20:30:53,632 epoch 75 - iter 6/9 - loss 0.00536478 - time (sec): 0.93 - samples/sec: 3780.75 - lr: 0.000029 - momentum: 0.000000 2024-11-27 20:30:53,771 epoch 75 - iter 7/9 - loss 0.00460365 - time (sec): 1.07 - samples/sec: 3886.06 - lr: 0.000029 - momentum: 0.000000 2024-11-27 20:30:53,916 epoch 75 - iter 8/9 - loss 0.00407721 - time (sec): 1.22 - samples/sec: 3899.37 - lr: 0.000029 - momentum: 0.000000 2024-11-27 20:30:54,049 epoch 75 - iter 9/9 - loss 0.00373761 - time (sec): 1.35 - samples/sec: 3851.29 - lr: 0.000029 - momentum: 0.000000 2024-11-27 20:30:54,049 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:30:54,049 EPOCH 75 done: loss 0.0037 - lr: 0.000029 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 5.09it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 5.09it/s] 2024-11-27 20:30:54,265 DEV : loss 2.9019179344177246 - f1-score (micro avg) 0.3293 2024-11-27 20:30:54,266 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:30:54,378 epoch 76 - iter 1/9 - loss 0.00041769 - time (sec): 0.11 - samples/sec: 4844.84 - lr: 0.000029 - momentum: 0.000000 2024-11-27 20:30:54,530 epoch 76 - iter 2/9 - loss 0.00770244 - time (sec): 0.26 - samples/sec: 4332.75 - lr: 0.000029 - momentum: 0.000000 2024-11-27 20:30:54,666 epoch 76 - iter 3/9 - loss 0.00509379 - time (sec): 0.40 - samples/sec: 4442.84 - lr: 0.000029 - momentum: 0.000000 2024-11-27 20:30:54,808 epoch 76 - iter 4/9 - loss 0.00404445 - time (sec): 0.54 - samples/sec: 4348.55 - lr: 0.000029 - momentum: 0.000000 2024-11-27 20:30:54,970 epoch 76 - iter 5/9 - loss 0.00348082 - time (sec): 0.70 - samples/sec: 4508.58 - lr: 0.000029 - momentum: 0.000000 2024-11-27 20:30:55,127 epoch 76 - iter 6/9 - loss 0.00358447 - time (sec): 0.86 - samples/sec: 4318.98 - lr: 0.000029 - momentum: 0.000000 2024-11-27 20:30:55,251 epoch 76 - iter 7/9 - loss 0.00344761 - time (sec): 0.98 - samples/sec: 4273.17 - lr: 0.000029 - momentum: 0.000000 2024-11-27 20:30:55,400 epoch 76 - iter 8/9 - loss 0.00312172 - time (sec): 1.13 - samples/sec: 4261.31 - lr: 0.000029 - momentum: 0.000000 2024-11-27 20:30:55,529 epoch 76 - iter 9/9 - loss 0.00293586 - time (sec): 1.26 - samples/sec: 4121.51 - lr: 0.000029 - momentum: 0.000000 2024-11-27 20:30:55,529 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:30:55,529 EPOCH 76 done: loss 0.0029 - lr: 0.000029 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.51it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.50it/s] 2024-11-27 20:30:55,702 DEV : loss 3.004276990890503 - f1-score (micro avg) 0.3158 2024-11-27 20:30:55,703 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:30:55,793 epoch 77 - iter 1/9 - loss 0.00768509 - time (sec): 0.09 - samples/sec: 5860.02 - lr: 0.000029 - momentum: 0.000000 2024-11-27 20:30:55,925 epoch 77 - iter 2/9 - loss 0.00448289 - time (sec): 0.22 - samples/sec: 5291.01 - lr: 0.000029 - momentum: 0.000000 2024-11-27 20:30:56,090 epoch 77 - iter 3/9 - loss 0.00361531 - time (sec): 0.39 - samples/sec: 4584.46 - lr: 0.000029 - momentum: 0.000000 2024-11-27 20:30:56,240 epoch 77 - iter 4/9 - loss 0.00286998 - time (sec): 0.54 - samples/sec: 4428.74 - lr: 0.000029 - momentum: 0.000000 2024-11-27 20:30:56,355 epoch 77 - iter 5/9 - loss 0.00236038 - time (sec): 0.65 - samples/sec: 4506.22 - lr: 0.000029 - momentum: 0.000000 2024-11-27 20:30:56,493 epoch 77 - iter 6/9 - loss 0.00444246 - time (sec): 0.79 - samples/sec: 4397.81 - lr: 0.000029 - momentum: 0.000000 2024-11-27 20:30:56,685 epoch 77 - iter 7/9 - loss 0.00654019 - time (sec): 0.98 - samples/sec: 4225.13 - lr: 0.000029 - momentum: 0.000000 2024-11-27 20:30:56,869 epoch 77 - iter 8/9 - loss 0.00577428 - time (sec): 1.16 - samples/sec: 4054.33 - lr: 0.000029 - momentum: 0.000000 2024-11-27 20:30:56,993 epoch 77 - iter 9/9 - loss 0.00526441 - time (sec): 1.29 - samples/sec: 4033.48 - lr: 0.000029 - momentum: 0.000000 2024-11-27 20:30:56,993 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:30:56,993 EPOCH 77 done: loss 0.0053 - lr: 0.000029 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 7.38it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 7.37it/s] 2024-11-27 20:30:57,147 DEV : loss 3.0884292125701904 - f1-score (micro avg) 0.3158 2024-11-27 20:30:57,149 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:30:57,252 epoch 78 - iter 1/9 - loss 0.00038064 - time (sec): 0.10 - samples/sec: 5399.29 - lr: 0.000029 - momentum: 0.000000 2024-11-27 20:30:57,390 epoch 78 - iter 2/9 - loss 0.00062170 - time (sec): 0.24 - samples/sec: 4422.23 - lr: 0.000029 - momentum: 0.000000 2024-11-27 20:30:57,542 epoch 78 - iter 3/9 - loss 0.00097063 - time (sec): 0.39 - samples/sec: 3948.89 - lr: 0.000029 - momentum: 0.000000 2024-11-27 20:30:57,714 epoch 78 - iter 4/9 - loss 0.00076355 - time (sec): 0.56 - samples/sec: 3830.14 - lr: 0.000029 - momentum: 0.000000 2024-11-27 20:30:57,870 epoch 78 - iter 5/9 - loss 0.00064867 - time (sec): 0.72 - samples/sec: 3833.02 - lr: 0.000029 - momentum: 0.000000 2024-11-27 20:30:58,023 epoch 78 - iter 6/9 - loss 0.00103575 - time (sec): 0.87 - samples/sec: 3787.40 - lr: 0.000029 - momentum: 0.000000 2024-11-27 20:30:58,198 epoch 78 - iter 7/9 - loss 0.00253138 - time (sec): 1.05 - samples/sec: 3837.85 - lr: 0.000029 - momentum: 0.000000 2024-11-27 20:30:58,351 epoch 78 - iter 8/9 - loss 0.00228990 - time (sec): 1.20 - samples/sec: 3741.31 - lr: 0.000029 - momentum: 0.000000 2024-11-27 20:30:58,495 epoch 78 - iter 9/9 - loss 0.00448834 - time (sec): 1.35 - samples/sec: 3861.74 - lr: 0.000029 - momentum: 0.000000 2024-11-27 20:30:58,496 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:30:58,496 EPOCH 78 done: loss 0.0045 - lr: 0.000029 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.03it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.02it/s] 2024-11-27 20:30:58,681 DEV : loss 3.059201717376709 - f1-score (micro avg) 0.2976 2024-11-27 20:30:58,682 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:30:58,782 epoch 79 - iter 1/9 - loss 0.02757956 - time (sec): 0.10 - samples/sec: 5859.02 - lr: 0.000029 - momentum: 0.000000 2024-11-27 20:30:58,909 epoch 79 - iter 2/9 - loss 0.01521814 - time (sec): 0.23 - samples/sec: 4825.22 - lr: 0.000029 - momentum: 0.000000 2024-11-27 20:30:59,039 epoch 79 - iter 3/9 - loss 0.01388265 - time (sec): 0.36 - samples/sec: 4503.27 - lr: 0.000028 - momentum: 0.000000 2024-11-27 20:30:59,202 epoch 79 - iter 4/9 - loss 0.01011755 - time (sec): 0.52 - samples/sec: 4282.95 - lr: 0.000028 - momentum: 0.000000 2024-11-27 20:30:59,417 epoch 79 - iter 5/9 - loss 0.00795404 - time (sec): 0.73 - samples/sec: 3939.53 - lr: 0.000028 - momentum: 0.000000 2024-11-27 20:30:59,569 epoch 79 - iter 6/9 - loss 0.00769618 - time (sec): 0.89 - samples/sec: 4080.74 - lr: 0.000028 - momentum: 0.000000 2024-11-27 20:30:59,731 epoch 79 - iter 7/9 - loss 0.00842673 - time (sec): 1.05 - samples/sec: 4078.88 - lr: 0.000028 - momentum: 0.000000 2024-11-27 20:30:59,883 epoch 79 - iter 8/9 - loss 0.00753505 - time (sec): 1.20 - samples/sec: 4003.20 - lr: 0.000028 - momentum: 0.000000 2024-11-27 20:31:00,012 epoch 79 - iter 9/9 - loss 0.00733639 - time (sec): 1.33 - samples/sec: 3910.74 - lr: 0.000028 - momentum: 0.000000 2024-11-27 20:31:00,013 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:31:00,013 EPOCH 79 done: loss 0.0073 - lr: 0.000028 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.29it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.28it/s] 2024-11-27 20:31:00,192 DEV : loss 3.008697509765625 - f1-score (micro avg) 0.2941 2024-11-27 20:31:00,193 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:31:00,291 epoch 80 - iter 1/9 - loss 0.00055353 - time (sec): 0.10 - samples/sec: 6378.69 - lr: 0.000028 - momentum: 0.000000 2024-11-27 20:31:00,436 epoch 80 - iter 2/9 - loss 0.00052827 - time (sec): 0.24 - samples/sec: 4893.96 - lr: 0.000028 - momentum: 0.000000 2024-11-27 20:31:00,572 epoch 80 - iter 3/9 - loss 0.00044081 - time (sec): 0.38 - samples/sec: 4606.91 - lr: 0.000028 - momentum: 0.000000 2024-11-27 20:31:00,706 epoch 80 - iter 4/9 - loss 0.00040466 - time (sec): 0.51 - samples/sec: 4557.38 - lr: 0.000028 - momentum: 0.000000 2024-11-27 20:31:00,838 epoch 80 - iter 5/9 - loss 0.00036843 - time (sec): 0.64 - samples/sec: 4372.44 - lr: 0.000028 - momentum: 0.000000 2024-11-27 20:31:00,976 epoch 80 - iter 6/9 - loss 0.00036305 - time (sec): 0.78 - samples/sec: 4155.93 - lr: 0.000028 - momentum: 0.000000 2024-11-27 20:31:01,119 epoch 80 - iter 7/9 - loss 0.00035365 - time (sec): 0.93 - samples/sec: 4135.87 - lr: 0.000028 - momentum: 0.000000 2024-11-27 20:31:01,267 epoch 80 - iter 8/9 - loss 0.00046581 - time (sec): 1.07 - samples/sec: 4331.48 - lr: 0.000028 - momentum: 0.000000 2024-11-27 20:31:01,410 epoch 80 - iter 9/9 - loss 0.00043896 - time (sec): 1.22 - samples/sec: 4271.70 - lr: 0.000028 - momentum: 0.000000 2024-11-27 20:31:01,411 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:31:01,411 EPOCH 80 done: loss 0.0004 - lr: 0.000028 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 5.14it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 5.13it/s] 2024-11-27 20:31:01,625 DEV : loss 2.992372751235962 - f1-score (micro avg) 0.3 2024-11-27 20:31:01,626 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:31:01,730 epoch 81 - iter 1/9 - loss 0.00033040 - time (sec): 0.10 - samples/sec: 5426.79 - lr: 0.000028 - momentum: 0.000000 2024-11-27 20:31:01,897 epoch 81 - iter 2/9 - loss 0.00028842 - time (sec): 0.27 - samples/sec: 4138.40 - lr: 0.000028 - momentum: 0.000000 2024-11-27 20:31:02,028 epoch 81 - iter 3/9 - loss 0.00025463 - time (sec): 0.40 - samples/sec: 4321.47 - lr: 0.000028 - momentum: 0.000000 2024-11-27 20:31:02,166 epoch 81 - iter 4/9 - loss 0.00027488 - time (sec): 0.54 - samples/sec: 4359.19 - lr: 0.000028 - momentum: 0.000000 2024-11-27 20:31:02,325 epoch 81 - iter 5/9 - loss 0.00026257 - time (sec): 0.70 - samples/sec: 4352.25 - lr: 0.000028 - momentum: 0.000000 2024-11-27 20:31:02,472 epoch 81 - iter 6/9 - loss 0.00025327 - time (sec): 0.84 - samples/sec: 4234.74 - lr: 0.000028 - momentum: 0.000000 2024-11-27 20:31:02,637 epoch 81 - iter 7/9 - loss 0.00027290 - time (sec): 1.01 - samples/sec: 4116.50 - lr: 0.000028 - momentum: 0.000000 2024-11-27 20:31:02,800 epoch 81 - iter 8/9 - loss 0.00238037 - time (sec): 1.17 - samples/sec: 4026.59 - lr: 0.000028 - momentum: 0.000000 2024-11-27 20:31:02,954 epoch 81 - iter 9/9 - loss 0.00296462 - time (sec): 1.33 - samples/sec: 3918.33 - lr: 0.000028 - momentum: 0.000000 2024-11-27 20:31:02,954 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:31:02,954 EPOCH 81 done: loss 0.0030 - lr: 0.000028 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 5.77it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 5.77it/s] 2024-11-27 20:31:03,147 DEV : loss 3.032306432723999 - f1-score (micro avg) 0.3106 2024-11-27 20:31:03,148 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:31:03,239 epoch 82 - iter 1/9 - loss 0.00049057 - time (sec): 0.09 - samples/sec: 5194.62 - lr: 0.000028 - momentum: 0.000000 2024-11-27 20:31:03,386 epoch 82 - iter 2/9 - loss 0.00047738 - time (sec): 0.24 - samples/sec: 4729.05 - lr: 0.000028 - momentum: 0.000000 2024-11-27 20:31:03,528 epoch 82 - iter 3/9 - loss 0.00036921 - time (sec): 0.38 - samples/sec: 4641.18 - lr: 0.000028 - momentum: 0.000000 2024-11-27 20:31:03,696 epoch 82 - iter 4/9 - loss 0.00031489 - time (sec): 0.55 - samples/sec: 4270.66 - lr: 0.000028 - momentum: 0.000000 2024-11-27 20:31:03,822 epoch 82 - iter 5/9 - loss 0.00028017 - time (sec): 0.67 - samples/sec: 4275.40 - lr: 0.000028 - momentum: 0.000000 2024-11-27 20:31:03,963 epoch 82 - iter 6/9 - loss 0.00024863 - time (sec): 0.81 - samples/sec: 4282.21 - lr: 0.000028 - momentum: 0.000000 2024-11-27 20:31:04,139 epoch 82 - iter 7/9 - loss 0.00024798 - time (sec): 0.99 - samples/sec: 4162.40 - lr: 0.000028 - momentum: 0.000000 2024-11-27 20:31:04,291 epoch 82 - iter 8/9 - loss 0.00169149 - time (sec): 1.14 - samples/sec: 4057.93 - lr: 0.000028 - momentum: 0.000000 2024-11-27 20:31:04,464 epoch 82 - iter 9/9 - loss 0.00346115 - time (sec): 1.31 - samples/sec: 3952.54 - lr: 0.000028 - momentum: 0.000000 2024-11-27 20:31:04,464 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:31:04,464 EPOCH 82 done: loss 0.0035 - lr: 0.000028 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 5.81it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 5.80it/s] 2024-11-27 20:31:04,655 DEV : loss 3.1230416297912598 - f1-score (micro avg) 0.3289 2024-11-27 20:31:04,657 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:31:04,758 epoch 83 - iter 1/9 - loss 0.01034884 - time (sec): 0.10 - samples/sec: 5082.55 - lr: 0.000028 - momentum: 0.000000 2024-11-27 20:31:04,885 epoch 83 - iter 2/9 - loss 0.00494849 - time (sec): 0.23 - samples/sec: 4770.26 - lr: 0.000028 - momentum: 0.000000 2024-11-27 20:31:05,042 epoch 83 - iter 3/9 - loss 0.00340208 - time (sec): 0.38 - samples/sec: 4244.97 - lr: 0.000028 - momentum: 0.000000 2024-11-27 20:31:05,386 epoch 83 - iter 4/9 - loss 0.00253481 - time (sec): 0.73 - samples/sec: 3053.83 - lr: 0.000028 - momentum: 0.000000 2024-11-27 20:31:05,532 epoch 83 - iter 5/9 - loss 0.00198712 - time (sec): 0.87 - samples/sec: 3286.89 - lr: 0.000028 - momentum: 0.000000 2024-11-27 20:31:05,663 epoch 83 - iter 6/9 - loss 0.00173084 - time (sec): 1.01 - samples/sec: 3334.50 - lr: 0.000028 - momentum: 0.000000 2024-11-27 20:31:05,797 epoch 83 - iter 7/9 - loss 0.00152592 - time (sec): 1.14 - samples/sec: 3451.86 - lr: 0.000028 - momentum: 0.000000 2024-11-27 20:31:05,951 epoch 83 - iter 8/9 - loss 0.00302858 - time (sec): 1.29 - samples/sec: 3484.62 - lr: 0.000028 - momentum: 0.000000 2024-11-27 20:31:06,090 epoch 83 - iter 9/9 - loss 0.00274890 - time (sec): 1.43 - samples/sec: 3629.95 - lr: 0.000028 - momentum: 0.000000 2024-11-27 20:31:06,090 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:31:06,090 EPOCH 83 done: loss 0.0027 - lr: 0.000028 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 5.92it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 5.91it/s] 2024-11-27 20:31:06,278 DEV : loss 3.1518452167510986 - f1-score (micro avg) 0.3425 2024-11-27 20:31:06,280 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:31:06,383 epoch 84 - iter 1/9 - loss 0.01607548 - time (sec): 0.10 - samples/sec: 5279.40 - lr: 0.000028 - momentum: 0.000000 2024-11-27 20:31:06,513 epoch 84 - iter 2/9 - loss 0.00797164 - time (sec): 0.23 - samples/sec: 4721.58 - lr: 0.000027 - momentum: 0.000000 2024-11-27 20:31:06,656 epoch 84 - iter 3/9 - loss 0.00538678 - time (sec): 0.37 - samples/sec: 4371.07 - lr: 0.000027 - momentum: 0.000000 2024-11-27 20:31:06,805 epoch 84 - iter 4/9 - loss 0.00414733 - time (sec): 0.52 - samples/sec: 4097.99 - lr: 0.000027 - momentum: 0.000000 2024-11-27 20:31:06,977 epoch 84 - iter 5/9 - loss 0.00543071 - time (sec): 0.70 - samples/sec: 3910.31 - lr: 0.000027 - momentum: 0.000000 2024-11-27 20:31:07,226 epoch 84 - iter 6/9 - loss 0.00427921 - time (sec): 0.95 - samples/sec: 3674.21 - lr: 0.000027 - momentum: 0.000000 2024-11-27 20:31:07,388 epoch 84 - iter 7/9 - loss 0.00404325 - time (sec): 1.11 - samples/sec: 3747.13 - lr: 0.000027 - momentum: 0.000000 2024-11-27 20:31:07,526 epoch 84 - iter 8/9 - loss 0.00364770 - time (sec): 1.25 - samples/sec: 3809.03 - lr: 0.000027 - momentum: 0.000000 2024-11-27 20:31:07,654 epoch 84 - iter 9/9 - loss 0.00334092 - time (sec): 1.37 - samples/sec: 3785.42 - lr: 0.000027 - momentum: 0.000000 2024-11-27 20:31:07,654 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:31:07,654 EPOCH 84 done: loss 0.0033 - lr: 0.000027 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.60it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.58it/s] 2024-11-27 20:31:07,825 DEV : loss 3.0999324321746826 - f1-score (micro avg) 0.327 2024-11-27 20:31:07,826 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:31:07,933 epoch 85 - iter 1/9 - loss 0.00028118 - time (sec): 0.11 - samples/sec: 6855.54 - lr: 0.000027 - momentum: 0.000000 2024-11-27 20:31:08,077 epoch 85 - iter 2/9 - loss 0.00025908 - time (sec): 0.25 - samples/sec: 5258.72 - lr: 0.000027 - momentum: 0.000000 2024-11-27 20:31:08,224 epoch 85 - iter 3/9 - loss 0.00068822 - time (sec): 0.40 - samples/sec: 4783.47 - lr: 0.000027 - momentum: 0.000000 2024-11-27 20:31:08,365 epoch 85 - iter 4/9 - loss 0.00056996 - time (sec): 0.54 - samples/sec: 4605.71 - lr: 0.000027 - momentum: 0.000000 2024-11-27 20:31:08,663 epoch 85 - iter 5/9 - loss 0.00047264 - time (sec): 0.84 - samples/sec: 3801.90 - lr: 0.000027 - momentum: 0.000000 2024-11-27 20:31:08,790 epoch 85 - iter 6/9 - loss 0.00043800 - time (sec): 0.96 - samples/sec: 3688.38 - lr: 0.000027 - momentum: 0.000000 2024-11-27 20:31:08,924 epoch 85 - iter 7/9 - loss 0.00138056 - time (sec): 1.10 - samples/sec: 3768.12 - lr: 0.000027 - momentum: 0.000000 2024-11-27 20:31:09,078 epoch 85 - iter 8/9 - loss 0.00254845 - time (sec): 1.25 - samples/sec: 3746.46 - lr: 0.000027 - momentum: 0.000000 2024-11-27 20:31:09,238 epoch 85 - iter 9/9 - loss 0.00231472 - time (sec): 1.41 - samples/sec: 3684.07 - lr: 0.000027 - momentum: 0.000000 2024-11-27 20:31:09,238 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:31:09,238 EPOCH 85 done: loss 0.0023 - lr: 0.000027 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.84it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.83it/s] 2024-11-27 20:31:09,404 DEV : loss 3.144559860229492 - f1-score (micro avg) 0.3165 2024-11-27 20:31:09,405 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:31:09,512 epoch 86 - iter 1/9 - loss 0.00026241 - time (sec): 0.11 - samples/sec: 6390.36 - lr: 0.000027 - momentum: 0.000000 2024-11-27 20:31:09,655 epoch 86 - iter 2/9 - loss 0.00469387 - time (sec): 0.25 - samples/sec: 5158.44 - lr: 0.000027 - momentum: 0.000000 2024-11-27 20:31:09,844 epoch 86 - iter 3/9 - loss 0.00328459 - time (sec): 0.44 - samples/sec: 4247.63 - lr: 0.000027 - momentum: 0.000000 2024-11-27 20:31:10,051 epoch 86 - iter 4/9 - loss 0.00261187 - time (sec): 0.64 - samples/sec: 3699.92 - lr: 0.000027 - momentum: 0.000000 2024-11-27 20:31:10,192 epoch 86 - iter 5/9 - loss 0.00206463 - time (sec): 0.79 - samples/sec: 3889.94 - lr: 0.000027 - momentum: 0.000000 2024-11-27 20:31:10,326 epoch 86 - iter 6/9 - loss 0.00178871 - time (sec): 0.92 - samples/sec: 3893.47 - lr: 0.000027 - momentum: 0.000000 2024-11-27 20:31:10,457 epoch 86 - iter 7/9 - loss 0.00163459 - time (sec): 1.05 - samples/sec: 3850.93 - lr: 0.000027 - momentum: 0.000000 2024-11-27 20:31:10,600 epoch 86 - iter 8/9 - loss 0.00157901 - time (sec): 1.19 - samples/sec: 3964.49 - lr: 0.000027 - momentum: 0.000000 2024-11-27 20:31:10,738 epoch 86 - iter 9/9 - loss 0.00144461 - time (sec): 1.33 - samples/sec: 3900.05 - lr: 0.000027 - momentum: 0.000000 2024-11-27 20:31:10,739 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:31:10,739 EPOCH 86 done: loss 0.0014 - lr: 0.000027 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.72it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.71it/s] 2024-11-27 20:31:10,907 DEV : loss 3.1602885723114014 - f1-score (micro avg) 0.3333 2024-11-27 20:31:10,908 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:31:11,014 epoch 87 - iter 1/9 - loss 0.00012574 - time (sec): 0.11 - samples/sec: 6548.52 - lr: 0.000027 - momentum: 0.000000 2024-11-27 20:31:11,143 epoch 87 - iter 2/9 - loss 0.00012543 - time (sec): 0.23 - samples/sec: 4631.32 - lr: 0.000027 - momentum: 0.000000 2024-11-27 20:31:11,287 epoch 87 - iter 3/9 - loss 0.00014804 - time (sec): 0.38 - samples/sec: 4632.94 - lr: 0.000027 - momentum: 0.000000 2024-11-27 20:31:11,485 epoch 87 - iter 4/9 - loss 0.00022358 - time (sec): 0.58 - samples/sec: 4037.87 - lr: 0.000027 - momentum: 0.000000 2024-11-27 20:31:11,704 epoch 87 - iter 5/9 - loss 0.00108662 - time (sec): 0.79 - samples/sec: 3774.10 - lr: 0.000027 - momentum: 0.000000 2024-11-27 20:31:11,842 epoch 87 - iter 6/9 - loss 0.00130413 - time (sec): 0.93 - samples/sec: 3834.81 - lr: 0.000027 - momentum: 0.000000 2024-11-27 20:31:11,976 epoch 87 - iter 7/9 - loss 0.00115527 - time (sec): 1.07 - samples/sec: 3849.88 - lr: 0.000027 - momentum: 0.000000 2024-11-27 20:31:12,113 epoch 87 - iter 8/9 - loss 0.00102955 - time (sec): 1.20 - samples/sec: 3884.99 - lr: 0.000027 - momentum: 0.000000 2024-11-27 20:31:12,259 epoch 87 - iter 9/9 - loss 0.00222071 - time (sec): 1.35 - samples/sec: 3848.02 - lr: 0.000027 - momentum: 0.000000 2024-11-27 20:31:12,260 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:31:12,260 EPOCH 87 done: loss 0.0022 - lr: 0.000027 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 5.13it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 5.12it/s] 2024-11-27 20:31:12,474 DEV : loss 3.098705530166626 - f1-score (micro avg) 0.323 2024-11-27 20:31:12,475 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:31:12,567 epoch 88 - iter 1/9 - loss 0.00043640 - time (sec): 0.09 - samples/sec: 5026.21 - lr: 0.000027 - momentum: 0.000000 2024-11-27 20:31:12,903 epoch 88 - iter 2/9 - loss 0.00029989 - time (sec): 0.43 - samples/sec: 2283.29 - lr: 0.000027 - momentum: 0.000000 2024-11-27 20:31:13,033 epoch 88 - iter 3/9 - loss 0.00028328 - time (sec): 0.56 - samples/sec: 3007.40 - lr: 0.000027 - momentum: 0.000000 2024-11-27 20:31:13,174 epoch 88 - iter 4/9 - loss 0.00024906 - time (sec): 0.70 - samples/sec: 3377.81 - lr: 0.000027 - momentum: 0.000000 2024-11-27 20:31:13,303 epoch 88 - iter 5/9 - loss 0.00022068 - time (sec): 0.83 - samples/sec: 3568.27 - lr: 0.000027 - momentum: 0.000000 2024-11-27 20:31:13,462 epoch 88 - iter 6/9 - loss 0.00020237 - time (sec): 0.99 - samples/sec: 3595.88 - lr: 0.000027 - momentum: 0.000000 2024-11-27 20:31:13,597 epoch 88 - iter 7/9 - loss 0.00019221 - time (sec): 1.12 - samples/sec: 3627.19 - lr: 0.000027 - momentum: 0.000000 2024-11-27 20:31:13,744 epoch 88 - iter 8/9 - loss 0.00018520 - time (sec): 1.27 - samples/sec: 3634.63 - lr: 0.000027 - momentum: 0.000000 2024-11-27 20:31:13,879 epoch 88 - iter 9/9 - loss 0.00019567 - time (sec): 1.40 - samples/sec: 3704.71 - lr: 0.000027 - momentum: 0.000000 2024-11-27 20:31:13,879 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:31:13,880 EPOCH 88 done: loss 0.0002 - lr: 0.000027 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 4.01it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 4.00it/s] 2024-11-27 20:31:14,148 DEV : loss 3.110564708709717 - f1-score (micro avg) 0.3375 2024-11-27 20:31:14,150 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:31:14,257 epoch 89 - iter 1/9 - loss 0.00021561 - time (sec): 0.11 - samples/sec: 5668.04 - lr: 0.000026 - momentum: 0.000000 2024-11-27 20:31:14,405 epoch 89 - iter 2/9 - loss 0.00016770 - time (sec): 0.25 - samples/sec: 4543.11 - lr: 0.000026 - momentum: 0.000000 2024-11-27 20:31:14,541 epoch 89 - iter 3/9 - loss 0.00014407 - time (sec): 0.39 - samples/sec: 4245.97 - lr: 0.000026 - momentum: 0.000000 2024-11-27 20:31:14,689 epoch 89 - iter 4/9 - loss 0.00012575 - time (sec): 0.54 - samples/sec: 4153.09 - lr: 0.000026 - momentum: 0.000000 2024-11-27 20:31:14,838 epoch 89 - iter 5/9 - loss 0.00011589 - time (sec): 0.69 - samples/sec: 4155.51 - lr: 0.000026 - momentum: 0.000000 2024-11-27 20:31:14,988 epoch 89 - iter 6/9 - loss 0.00014106 - time (sec): 0.84 - samples/sec: 4071.44 - lr: 0.000026 - momentum: 0.000000 2024-11-27 20:31:15,138 epoch 89 - iter 7/9 - loss 0.00013417 - time (sec): 0.99 - samples/sec: 3986.04 - lr: 0.000026 - momentum: 0.000000 2024-11-27 20:31:15,356 epoch 89 - iter 8/9 - loss 0.00013439 - time (sec): 1.21 - samples/sec: 3844.69 - lr: 0.000026 - momentum: 0.000000 2024-11-27 20:31:15,487 epoch 89 - iter 9/9 - loss 0.00174080 - time (sec): 1.34 - samples/sec: 3888.75 - lr: 0.000026 - momentum: 0.000000 2024-11-27 20:31:15,487 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:31:15,488 EPOCH 89 done: loss 0.0017 - lr: 0.000026 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.54it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.53it/s] 2024-11-27 20:31:15,660 DEV : loss 3.1478018760681152 - f1-score (micro avg) 0.3375 2024-11-27 20:31:15,661 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:31:15,751 epoch 90 - iter 1/9 - loss 0.00238092 - time (sec): 0.09 - samples/sec: 5710.38 - lr: 0.000026 - momentum: 0.000000 2024-11-27 20:31:15,881 epoch 90 - iter 2/9 - loss 0.00113998 - time (sec): 0.22 - samples/sec: 5011.34 - lr: 0.000026 - momentum: 0.000000 2024-11-27 20:31:16,024 epoch 90 - iter 3/9 - loss 0.00075252 - time (sec): 0.36 - samples/sec: 4807.75 - lr: 0.000026 - momentum: 0.000000 2024-11-27 20:31:16,210 epoch 90 - iter 4/9 - loss 0.00064703 - time (sec): 0.55 - samples/sec: 4215.70 - lr: 0.000026 - momentum: 0.000000 2024-11-27 20:31:16,412 epoch 90 - iter 5/9 - loss 0.00314873 - time (sec): 0.75 - samples/sec: 3961.72 - lr: 0.000026 - momentum: 0.000000 2024-11-27 20:31:16,537 epoch 90 - iter 6/9 - loss 0.00267451 - time (sec): 0.88 - samples/sec: 4026.42 - lr: 0.000026 - momentum: 0.000000 2024-11-27 20:31:16,682 epoch 90 - iter 7/9 - loss 0.00230390 - time (sec): 1.02 - samples/sec: 4026.89 - lr: 0.000026 - momentum: 0.000000 2024-11-27 20:31:16,834 epoch 90 - iter 8/9 - loss 0.00199683 - time (sec): 1.17 - samples/sec: 4069.57 - lr: 0.000026 - momentum: 0.000000 2024-11-27 20:31:16,976 epoch 90 - iter 9/9 - loss 0.00183862 - time (sec): 1.31 - samples/sec: 3955.76 - lr: 0.000026 - momentum: 0.000000 2024-11-27 20:31:16,976 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:31:16,976 EPOCH 90 done: loss 0.0018 - lr: 0.000026 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 5.03it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 5.03it/s] 2024-11-27 20:31:17,194 DEV : loss 3.169376850128174 - f1-score (micro avg) 0.3494 2024-11-27 20:31:17,195 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:31:17,304 epoch 91 - iter 1/9 - loss 0.00009424 - time (sec): 0.11 - samples/sec: 6094.26 - lr: 0.000026 - momentum: 0.000000 2024-11-27 20:31:17,432 epoch 91 - iter 2/9 - loss 0.00008627 - time (sec): 0.24 - samples/sec: 4887.75 - lr: 0.000026 - momentum: 0.000000 2024-11-27 20:31:17,567 epoch 91 - iter 3/9 - loss 0.00009804 - time (sec): 0.37 - samples/sec: 5081.54 - lr: 0.000026 - momentum: 0.000000 2024-11-27 20:31:17,700 epoch 91 - iter 4/9 - loss 0.00010284 - time (sec): 0.50 - samples/sec: 4713.43 - lr: 0.000026 - momentum: 0.000000 2024-11-27 20:31:17,843 epoch 91 - iter 5/9 - loss 0.00009662 - time (sec): 0.65 - samples/sec: 4491.22 - lr: 0.000026 - momentum: 0.000000 2024-11-27 20:31:17,985 epoch 91 - iter 6/9 - loss 0.00011616 - time (sec): 0.79 - samples/sec: 4603.29 - lr: 0.000026 - momentum: 0.000000 2024-11-27 20:31:18,182 epoch 91 - iter 7/9 - loss 0.00011019 - time (sec): 0.99 - samples/sec: 4174.42 - lr: 0.000026 - momentum: 0.000000 2024-11-27 20:31:18,325 epoch 91 - iter 8/9 - loss 0.00012382 - time (sec): 1.13 - samples/sec: 4216.55 - lr: 0.000026 - momentum: 0.000000 2024-11-27 20:31:18,451 epoch 91 - iter 9/9 - loss 0.00012502 - time (sec): 1.26 - samples/sec: 4140.76 - lr: 0.000026 - momentum: 0.000000 2024-11-27 20:31:18,452 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:31:18,452 EPOCH 91 done: loss 0.0001 - lr: 0.000026 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.01it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.00it/s] 2024-11-27 20:31:18,637 DEV : loss 3.151057720184326 - f1-score (micro avg) 0.3924 2024-11-27 20:31:18,639 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:31:18,736 epoch 92 - iter 1/9 - loss 0.01879840 - time (sec): 0.10 - samples/sec: 6435.23 - lr: 0.000026 - momentum: 0.000000 2024-11-27 20:31:18,875 epoch 92 - iter 2/9 - loss 0.00961940 - time (sec): 0.24 - samples/sec: 5181.59 - lr: 0.000026 - momentum: 0.000000 2024-11-27 20:31:19,046 epoch 92 - iter 3/9 - loss 0.00893772 - time (sec): 0.41 - samples/sec: 4823.94 - lr: 0.000026 - momentum: 0.000000 2024-11-27 20:31:19,213 epoch 92 - iter 4/9 - loss 0.00701138 - time (sec): 0.57 - samples/sec: 4376.33 - lr: 0.000026 - momentum: 0.000000 2024-11-27 20:31:19,342 epoch 92 - iter 5/9 - loss 0.00592634 - time (sec): 0.70 - samples/sec: 4234.17 - lr: 0.000026 - momentum: 0.000000 2024-11-27 20:31:19,460 epoch 92 - iter 6/9 - loss 0.00504355 - time (sec): 0.82 - samples/sec: 4272.34 - lr: 0.000026 - momentum: 0.000000 2024-11-27 20:31:19,600 epoch 92 - iter 7/9 - loss 0.00490234 - time (sec): 0.96 - samples/sec: 4149.47 - lr: 0.000026 - momentum: 0.000000 2024-11-27 20:31:19,749 epoch 92 - iter 8/9 - loss 0.00415550 - time (sec): 1.11 - samples/sec: 4244.80 - lr: 0.000026 - momentum: 0.000000 2024-11-27 20:31:19,896 epoch 92 - iter 9/9 - loss 0.00455736 - time (sec): 1.26 - samples/sec: 4136.51 - lr: 0.000026 - momentum: 0.000000 2024-11-27 20:31:19,896 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:31:19,896 EPOCH 92 done: loss 0.0046 - lr: 0.000026 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.50it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.49it/s] 2024-11-27 20:31:20,070 DEV : loss 3.1767635345458984 - f1-score (micro avg) 0.3758 2024-11-27 20:31:20,071 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:31:20,183 epoch 93 - iter 1/9 - loss 0.00009318 - time (sec): 0.11 - samples/sec: 4865.46 - lr: 0.000026 - momentum: 0.000000 2024-11-27 20:31:20,352 epoch 93 - iter 2/9 - loss 0.00018979 - time (sec): 0.28 - samples/sec: 4415.53 - lr: 0.000026 - momentum: 0.000000 2024-11-27 20:31:20,484 epoch 93 - iter 3/9 - loss 0.00015008 - time (sec): 0.41 - samples/sec: 4360.72 - lr: 0.000026 - momentum: 0.000000 2024-11-27 20:31:20,633 epoch 93 - iter 4/9 - loss 0.00013799 - time (sec): 0.56 - samples/sec: 4053.69 - lr: 0.000026 - momentum: 0.000000 2024-11-27 20:31:20,853 epoch 93 - iter 5/9 - loss 0.00012403 - time (sec): 0.78 - samples/sec: 3810.27 - lr: 0.000026 - momentum: 0.000000 2024-11-27 20:31:20,987 epoch 93 - iter 6/9 - loss 0.00221843 - time (sec): 0.92 - samples/sec: 3951.43 - lr: 0.000026 - momentum: 0.000000 2024-11-27 20:31:21,116 epoch 93 - iter 7/9 - loss 0.00195104 - time (sec): 1.04 - samples/sec: 3959.94 - lr: 0.000026 - momentum: 0.000000 2024-11-27 20:31:21,259 epoch 93 - iter 8/9 - loss 0.00176048 - time (sec): 1.19 - samples/sec: 3886.16 - lr: 0.000026 - momentum: 0.000000 2024-11-27 20:31:21,450 epoch 93 - iter 9/9 - loss 0.00158192 - time (sec): 1.38 - samples/sec: 3770.04 - lr: 0.000025 - momentum: 0.000000 2024-11-27 20:31:21,451 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:31:21,451 EPOCH 93 done: loss 0.0016 - lr: 0.000025 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.78it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.77it/s] 2024-11-27 20:31:21,617 DEV : loss 3.212688446044922 - f1-score (micro avg) 0.381 2024-11-27 20:31:21,619 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:31:21,719 epoch 94 - iter 1/9 - loss 0.00015145 - time (sec): 0.10 - samples/sec: 5941.68 - lr: 0.000025 - momentum: 0.000000 2024-11-27 20:31:21,851 epoch 94 - iter 2/9 - loss 0.00522763 - time (sec): 0.23 - samples/sec: 4724.56 - lr: 0.000025 - momentum: 0.000000 2024-11-27 20:31:21,990 epoch 94 - iter 3/9 - loss 0.00345974 - time (sec): 0.37 - samples/sec: 4516.69 - lr: 0.000025 - momentum: 0.000000 2024-11-27 20:31:22,121 epoch 94 - iter 4/9 - loss 0.00266814 - time (sec): 0.50 - samples/sec: 4399.73 - lr: 0.000025 - momentum: 0.000000 2024-11-27 20:31:22,266 epoch 94 - iter 5/9 - loss 0.00423990 - time (sec): 0.65 - samples/sec: 4324.89 - lr: 0.000025 - momentum: 0.000000 2024-11-27 20:31:22,446 epoch 94 - iter 6/9 - loss 0.00347314 - time (sec): 0.83 - samples/sec: 4151.67 - lr: 0.000025 - momentum: 0.000000 2024-11-27 20:31:22,790 epoch 94 - iter 7/9 - loss 0.00302196 - time (sec): 1.17 - samples/sec: 3411.85 - lr: 0.000025 - momentum: 0.000000 2024-11-27 20:31:22,926 epoch 94 - iter 8/9 - loss 0.00267019 - time (sec): 1.31 - samples/sec: 3480.99 - lr: 0.000025 - momentum: 0.000000 2024-11-27 20:31:23,063 epoch 94 - iter 9/9 - loss 0.00234928 - time (sec): 1.44 - samples/sec: 3601.35 - lr: 0.000025 - momentum: 0.000000 2024-11-27 20:31:23,063 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:31:23,063 EPOCH 94 done: loss 0.0023 - lr: 0.000025 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.32it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.31it/s] 2024-11-27 20:31:23,240 DEV : loss 3.2408180236816406 - f1-score (micro avg) 0.3553 2024-11-27 20:31:23,242 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:31:23,362 epoch 95 - iter 1/9 - loss 0.00005885 - time (sec): 0.12 - samples/sec: 4971.61 - lr: 0.000025 - momentum: 0.000000 2024-11-27 20:31:23,538 epoch 95 - iter 2/9 - loss 0.00010683 - time (sec): 0.29 - samples/sec: 4123.55 - lr: 0.000025 - momentum: 0.000000 2024-11-27 20:31:23,703 epoch 95 - iter 3/9 - loss 0.00015488 - time (sec): 0.46 - samples/sec: 3750.90 - lr: 0.000025 - momentum: 0.000000 2024-11-27 20:31:23,860 epoch 95 - iter 4/9 - loss 0.00013916 - time (sec): 0.62 - samples/sec: 3899.73 - lr: 0.000025 - momentum: 0.000000 2024-11-27 20:31:24,021 epoch 95 - iter 5/9 - loss 0.00013036 - time (sec): 0.78 - samples/sec: 3859.62 - lr: 0.000025 - momentum: 0.000000 2024-11-27 20:31:24,182 epoch 95 - iter 6/9 - loss 0.00014904 - time (sec): 0.94 - samples/sec: 3920.73 - lr: 0.000025 - momentum: 0.000000 2024-11-27 20:31:24,323 epoch 95 - iter 7/9 - loss 0.00014099 - time (sec): 1.08 - samples/sec: 3922.64 - lr: 0.000025 - momentum: 0.000000 2024-11-27 20:31:24,449 epoch 95 - iter 8/9 - loss 0.00014163 - time (sec): 1.21 - samples/sec: 3904.06 - lr: 0.000025 - momentum: 0.000000 2024-11-27 20:31:24,582 epoch 95 - iter 9/9 - loss 0.00269287 - time (sec): 1.34 - samples/sec: 3879.86 - lr: 0.000025 - momentum: 0.000000 2024-11-27 20:31:24,583 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:31:24,583 EPOCH 95 done: loss 0.0027 - lr: 0.000025 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.27it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.26it/s] 2024-11-27 20:31:24,761 DEV : loss 3.3781378269195557 - f1-score (micro avg) 0.3421 2024-11-27 20:31:24,763 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:31:24,855 epoch 96 - iter 1/9 - loss 0.00016175 - time (sec): 0.09 - samples/sec: 6088.80 - lr: 0.000025 - momentum: 0.000000 2024-11-27 20:31:24,991 epoch 96 - iter 2/9 - loss 0.00060690 - time (sec): 0.23 - samples/sec: 4853.48 - lr: 0.000025 - momentum: 0.000000 2024-11-27 20:31:25,152 epoch 96 - iter 3/9 - loss 0.00037386 - time (sec): 0.39 - samples/sec: 5097.19 - lr: 0.000025 - momentum: 0.000000 2024-11-27 20:31:25,334 epoch 96 - iter 4/9 - loss 0.00032122 - time (sec): 0.57 - samples/sec: 4412.82 - lr: 0.000025 - momentum: 0.000000 2024-11-27 20:31:25,482 epoch 96 - iter 5/9 - loss 0.00029490 - time (sec): 0.72 - samples/sec: 4132.10 - lr: 0.000025 - momentum: 0.000000 2024-11-27 20:31:25,624 epoch 96 - iter 6/9 - loss 0.00026421 - time (sec): 0.86 - samples/sec: 3987.39 - lr: 0.000025 - momentum: 0.000000 2024-11-27 20:31:25,795 epoch 96 - iter 7/9 - loss 0.00023703 - time (sec): 1.03 - samples/sec: 3963.52 - lr: 0.000025 - momentum: 0.000000 2024-11-27 20:31:26,035 epoch 96 - iter 8/9 - loss 0.00022010 - time (sec): 1.27 - samples/sec: 3736.60 - lr: 0.000025 - momentum: 0.000000 2024-11-27 20:31:26,288 epoch 96 - iter 9/9 - loss 0.00020767 - time (sec): 1.52 - samples/sec: 3409.60 - lr: 0.000025 - momentum: 0.000000 2024-11-27 20:31:26,288 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:31:26,288 EPOCH 96 done: loss 0.0002 - lr: 0.000025 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.75it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.74it/s] 2024-11-27 20:31:26,455 DEV : loss 3.379178524017334 - f1-score (micro avg) 0.3355 2024-11-27 20:31:26,457 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:31:26,563 epoch 97 - iter 1/9 - loss 0.00011496 - time (sec): 0.11 - samples/sec: 6018.22 - lr: 0.000025 - momentum: 0.000000 2024-11-27 20:31:26,712 epoch 97 - iter 2/9 - loss 0.00009459 - time (sec): 0.25 - samples/sec: 4903.91 - lr: 0.000025 - momentum: 0.000000 2024-11-27 20:31:26,864 epoch 97 - iter 3/9 - loss 0.00014395 - time (sec): 0.41 - samples/sec: 4691.95 - lr: 0.000025 - momentum: 0.000000 2024-11-27 20:31:27,001 epoch 97 - iter 4/9 - loss 0.00014086 - time (sec): 0.54 - samples/sec: 4732.60 - lr: 0.000025 - momentum: 0.000000 2024-11-27 20:31:27,203 epoch 97 - iter 5/9 - loss 0.00012606 - time (sec): 0.74 - samples/sec: 4163.27 - lr: 0.000025 - momentum: 0.000000 2024-11-27 20:31:27,352 epoch 97 - iter 6/9 - loss 0.00029167 - time (sec): 0.89 - samples/sec: 4114.93 - lr: 0.000025 - momentum: 0.000000 2024-11-27 20:31:27,493 epoch 97 - iter 7/9 - loss 0.00026015 - time (sec): 1.04 - samples/sec: 4092.78 - lr: 0.000025 - momentum: 0.000000 2024-11-27 20:31:27,637 epoch 97 - iter 8/9 - loss 0.00023335 - time (sec): 1.18 - samples/sec: 4087.51 - lr: 0.000025 - momentum: 0.000000 2024-11-27 20:31:27,766 epoch 97 - iter 9/9 - loss 0.00024043 - time (sec): 1.31 - samples/sec: 3971.56 - lr: 0.000025 - momentum: 0.000000 2024-11-27 20:31:27,767 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:31:27,767 EPOCH 97 done: loss 0.0002 - lr: 0.000025 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.48it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.47it/s] 2024-11-27 20:31:27,941 DEV : loss 3.3330307006835938 - f1-score (micro avg) 0.3333 2024-11-27 20:31:27,942 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:31:28,036 epoch 98 - iter 1/9 - loss 0.00006373 - time (sec): 0.09 - samples/sec: 5052.33 - lr: 0.000025 - momentum: 0.000000 2024-11-27 20:31:28,189 epoch 98 - iter 2/9 - loss 0.00006579 - time (sec): 0.25 - samples/sec: 4193.21 - lr: 0.000025 - momentum: 0.000000 2024-11-27 20:31:28,343 epoch 98 - iter 3/9 - loss 0.00007464 - time (sec): 0.40 - samples/sec: 4345.43 - lr: 0.000025 - momentum: 0.000000 2024-11-27 20:31:28,481 epoch 98 - iter 4/9 - loss 0.00006784 - time (sec): 0.54 - samples/sec: 4567.16 - lr: 0.000025 - momentum: 0.000000 2024-11-27 20:31:28,612 epoch 98 - iter 5/9 - loss 0.00006848 - time (sec): 0.67 - samples/sec: 4518.93 - lr: 0.000025 - momentum: 0.000000 2024-11-27 20:31:28,766 epoch 98 - iter 6/9 - loss 0.00008500 - time (sec): 0.82 - samples/sec: 4375.87 - lr: 0.000025 - momentum: 0.000000 2024-11-27 20:31:28,904 epoch 98 - iter 7/9 - loss 0.00008807 - time (sec): 0.96 - samples/sec: 4316.75 - lr: 0.000025 - momentum: 0.000000 2024-11-27 20:31:29,064 epoch 98 - iter 8/9 - loss 0.00009037 - time (sec): 1.12 - samples/sec: 4187.76 - lr: 0.000024 - momentum: 0.000000 2024-11-27 20:31:29,268 epoch 98 - iter 9/9 - loss 0.00071842 - time (sec): 1.32 - samples/sec: 3923.70 - lr: 0.000024 - momentum: 0.000000 2024-11-27 20:31:29,268 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:31:29,268 EPOCH 98 done: loss 0.0007 - lr: 0.000024 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.82it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.81it/s] 2024-11-27 20:31:29,434 DEV : loss 3.3695895671844482 - f1-score (micro avg) 0.35 2024-11-27 20:31:29,435 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:31:29,528 epoch 99 - iter 1/9 - loss 0.00002267 - time (sec): 0.09 - samples/sec: 5171.01 - lr: 0.000024 - momentum: 0.000000 2024-11-27 20:31:29,662 epoch 99 - iter 2/9 - loss 0.00006187 - time (sec): 0.23 - samples/sec: 5070.65 - lr: 0.000024 - momentum: 0.000000 2024-11-27 20:31:29,796 epoch 99 - iter 3/9 - loss 0.00005747 - time (sec): 0.36 - samples/sec: 4531.40 - lr: 0.000024 - momentum: 0.000000 2024-11-27 20:31:29,932 epoch 99 - iter 4/9 - loss 0.00007564 - time (sec): 0.50 - samples/sec: 4235.96 - lr: 0.000024 - momentum: 0.000000 2024-11-27 20:31:30,093 epoch 99 - iter 5/9 - loss 0.00007166 - time (sec): 0.66 - samples/sec: 4151.79 - lr: 0.000024 - momentum: 0.000000 2024-11-27 20:31:30,261 epoch 99 - iter 6/9 - loss 0.00006318 - time (sec): 0.83 - samples/sec: 4040.84 - lr: 0.000024 - momentum: 0.000000 2024-11-27 20:31:30,418 epoch 99 - iter 7/9 - loss 0.00006456 - time (sec): 0.98 - samples/sec: 4110.75 - lr: 0.000024 - momentum: 0.000000 2024-11-27 20:31:30,552 epoch 99 - iter 8/9 - loss 0.00007375 - time (sec): 1.12 - samples/sec: 4141.82 - lr: 0.000024 - momentum: 0.000000 2024-11-27 20:31:30,687 epoch 99 - iter 9/9 - loss 0.00007864 - time (sec): 1.25 - samples/sec: 4156.46 - lr: 0.000024 - momentum: 0.000000 2024-11-27 20:31:30,687 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:31:30,687 EPOCH 99 done: loss 0.0001 - lr: 0.000024 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 5.45it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 5.44it/s] 2024-11-27 20:31:30,890 DEV : loss 3.39043927192688 - f1-score (micro avg) 0.3694 2024-11-27 20:31:30,891 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:31:30,994 epoch 100 - iter 1/9 - loss 0.00006628 - time (sec): 0.10 - samples/sec: 6329.79 - lr: 0.000024 - momentum: 0.000000 2024-11-27 20:31:31,134 epoch 100 - iter 2/9 - loss 0.00005070 - time (sec): 0.24 - samples/sec: 4964.87 - lr: 0.000024 - momentum: 0.000000 2024-11-27 20:31:31,285 epoch 100 - iter 3/9 - loss 0.00004986 - time (sec): 0.39 - samples/sec: 4635.13 - lr: 0.000024 - momentum: 0.000000 2024-11-27 20:31:31,437 epoch 100 - iter 4/9 - loss 0.00004479 - time (sec): 0.55 - samples/sec: 4248.73 - lr: 0.000024 - momentum: 0.000000 2024-11-27 20:31:31,574 epoch 100 - iter 5/9 - loss 0.00005057 - time (sec): 0.68 - samples/sec: 4150.93 - lr: 0.000024 - momentum: 0.000000 2024-11-27 20:31:31,722 epoch 100 - iter 6/9 - loss 0.00247902 - time (sec): 0.83 - samples/sec: 4139.00 - lr: 0.000024 - momentum: 0.000000 2024-11-27 20:31:31,871 epoch 100 - iter 7/9 - loss 0.00209669 - time (sec): 0.98 - samples/sec: 4177.91 - lr: 0.000024 - momentum: 0.000000 2024-11-27 20:31:32,017 epoch 100 - iter 8/9 - loss 0.00180022 - time (sec): 1.12 - samples/sec: 4274.04 - lr: 0.000024 - momentum: 0.000000 2024-11-27 20:31:32,142 epoch 100 - iter 9/9 - loss 0.00166955 - time (sec): 1.25 - samples/sec: 4156.36 - lr: 0.000024 - momentum: 0.000000 2024-11-27 20:31:32,143 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:31:32,143 EPOCH 100 done: loss 0.0017 - lr: 0.000024 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.59it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.58it/s] 2024-11-27 20:31:32,314 DEV : loss 3.38008189201355 - f1-score (micro avg) 0.359 2024-11-27 20:31:32,315 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:31:32,442 epoch 101 - iter 1/9 - loss 0.00002390 - time (sec): 0.13 - samples/sec: 4014.27 - lr: 0.000024 - momentum: 0.000000 2024-11-27 20:31:32,641 epoch 101 - iter 2/9 - loss 0.00003324 - time (sec): 0.33 - samples/sec: 3553.74 - lr: 0.000024 - momentum: 0.000000 2024-11-27 20:31:32,791 epoch 101 - iter 3/9 - loss 0.00005123 - time (sec): 0.48 - samples/sec: 3948.86 - lr: 0.000024 - momentum: 0.000000 2024-11-27 20:31:32,945 epoch 101 - iter 4/9 - loss 0.00004632 - time (sec): 0.63 - samples/sec: 3930.41 - lr: 0.000024 - momentum: 0.000000 2024-11-27 20:31:33,087 epoch 101 - iter 5/9 - loss 0.00004335 - time (sec): 0.77 - samples/sec: 4016.15 - lr: 0.000024 - momentum: 0.000000 2024-11-27 20:31:33,315 epoch 101 - iter 6/9 - loss 0.00006754 - time (sec): 1.00 - samples/sec: 3728.97 - lr: 0.000024 - momentum: 0.000000 2024-11-27 20:31:33,442 epoch 101 - iter 7/9 - loss 0.00006641 - time (sec): 1.13 - samples/sec: 3663.97 - lr: 0.000024 - momentum: 0.000000 2024-11-27 20:31:33,562 epoch 101 - iter 8/9 - loss 0.00006316 - time (sec): 1.25 - samples/sec: 3763.34 - lr: 0.000024 - momentum: 0.000000 2024-11-27 20:31:33,691 epoch 101 - iter 9/9 - loss 0.00006482 - time (sec): 1.38 - samples/sec: 3778.68 - lr: 0.000024 - momentum: 0.000000 2024-11-27 20:31:33,692 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:31:33,692 EPOCH 101 done: loss 0.0001 - lr: 0.000024 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.08it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.07it/s] 2024-11-27 20:31:33,875 DEV : loss 3.3984036445617676 - f1-score (micro avg) 0.366 2024-11-27 20:31:33,877 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:31:33,979 epoch 102 - iter 1/9 - loss 0.00010625 - time (sec): 0.10 - samples/sec: 5079.98 - lr: 0.000024 - momentum: 0.000000 2024-11-27 20:31:34,120 epoch 102 - iter 2/9 - loss 0.00007440 - time (sec): 0.24 - samples/sec: 4356.42 - lr: 0.000024 - momentum: 0.000000 2024-11-27 20:31:34,283 epoch 102 - iter 3/9 - loss 0.00007267 - time (sec): 0.41 - samples/sec: 4593.07 - lr: 0.000024 - momentum: 0.000000 2024-11-27 20:31:34,431 epoch 102 - iter 4/9 - loss 0.00007621 - time (sec): 0.55 - samples/sec: 4252.52 - lr: 0.000024 - momentum: 0.000000 2024-11-27 20:31:34,562 epoch 102 - iter 5/9 - loss 0.00007284 - time (sec): 0.68 - samples/sec: 4143.50 - lr: 0.000024 - momentum: 0.000000 2024-11-27 20:31:34,713 epoch 102 - iter 6/9 - loss 0.00007428 - time (sec): 0.84 - samples/sec: 4051.53 - lr: 0.000024 - momentum: 0.000000 2024-11-27 20:31:34,855 epoch 102 - iter 7/9 - loss 0.00007177 - time (sec): 0.98 - samples/sec: 4061.54 - lr: 0.000024 - momentum: 0.000000 2024-11-27 20:31:35,046 epoch 102 - iter 8/9 - loss 0.00006511 - time (sec): 1.17 - samples/sec: 3999.25 - lr: 0.000024 - momentum: 0.000000 2024-11-27 20:31:35,243 epoch 102 - iter 9/9 - loss 0.00007054 - time (sec): 1.37 - samples/sec: 3806.30 - lr: 0.000024 - momentum: 0.000000 2024-11-27 20:31:35,243 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:31:35,243 EPOCH 102 done: loss 0.0001 - lr: 0.000024 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.62it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.61it/s] 2024-11-27 20:31:35,414 DEV : loss 3.4379866123199463 - f1-score (micro avg) 0.3313 2024-11-27 20:31:35,415 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:31:35,508 epoch 103 - iter 1/9 - loss 0.00016933 - time (sec): 0.09 - samples/sec: 5953.90 - lr: 0.000024 - momentum: 0.000000 2024-11-27 20:31:35,640 epoch 103 - iter 2/9 - loss 0.00011052 - time (sec): 0.22 - samples/sec: 5276.71 - lr: 0.000024 - momentum: 0.000000 2024-11-27 20:31:35,780 epoch 103 - iter 3/9 - loss 0.00009634 - time (sec): 0.36 - samples/sec: 5170.27 - lr: 0.000024 - momentum: 0.000000 2024-11-27 20:31:35,934 epoch 103 - iter 4/9 - loss 0.00008049 - time (sec): 0.52 - samples/sec: 5022.98 - lr: 0.000024 - momentum: 0.000000 2024-11-27 20:31:36,113 epoch 103 - iter 5/9 - loss 0.00007565 - time (sec): 0.70 - samples/sec: 4686.75 - lr: 0.000024 - momentum: 0.000000 2024-11-27 20:31:36,256 epoch 103 - iter 6/9 - loss 0.00007259 - time (sec): 0.84 - samples/sec: 4416.10 - lr: 0.000024 - momentum: 0.000000 2024-11-27 20:31:36,393 epoch 103 - iter 7/9 - loss 0.00006969 - time (sec): 0.98 - samples/sec: 4311.06 - lr: 0.000023 - momentum: 0.000000 2024-11-27 20:31:36,531 epoch 103 - iter 8/9 - loss 0.00007052 - time (sec): 1.12 - samples/sec: 4174.50 - lr: 0.000023 - momentum: 0.000000 2024-11-27 20:31:36,667 epoch 103 - iter 9/9 - loss 0.00006868 - time (sec): 1.25 - samples/sec: 4153.77 - lr: 0.000023 - momentum: 0.000000 2024-11-27 20:31:36,668 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:31:36,668 EPOCH 103 done: loss 0.0001 - lr: 0.000023 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 7.50it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 7.49it/s] 2024-11-27 20:31:36,820 DEV : loss 3.448495864868164 - f1-score (micro avg) 0.3133 2024-11-27 20:31:36,821 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:31:36,924 epoch 104 - iter 1/9 - loss 0.00010691 - time (sec): 0.10 - samples/sec: 4921.25 - lr: 0.000023 - momentum: 0.000000 2024-11-27 20:31:37,093 epoch 104 - iter 2/9 - loss 0.00007087 - time (sec): 0.27 - samples/sec: 3812.75 - lr: 0.000023 - momentum: 0.000000 2024-11-27 20:31:37,223 epoch 104 - iter 3/9 - loss 0.00005640 - time (sec): 0.40 - samples/sec: 3956.19 - lr: 0.000023 - momentum: 0.000000 2024-11-27 20:31:37,350 epoch 104 - iter 4/9 - loss 0.00005462 - time (sec): 0.53 - samples/sec: 4094.77 - lr: 0.000023 - momentum: 0.000000 2024-11-27 20:31:37,493 epoch 104 - iter 5/9 - loss 0.00005893 - time (sec): 0.67 - samples/sec: 3946.44 - lr: 0.000023 - momentum: 0.000000 2024-11-27 20:31:37,639 epoch 104 - iter 6/9 - loss 0.00005745 - time (sec): 0.82 - samples/sec: 4034.27 - lr: 0.000023 - momentum: 0.000000 2024-11-27 20:31:37,817 epoch 104 - iter 7/9 - loss 0.00006652 - time (sec): 0.99 - samples/sec: 3992.99 - lr: 0.000023 - momentum: 0.000000 2024-11-27 20:31:38,173 epoch 104 - iter 8/9 - loss 0.00007274 - time (sec): 1.35 - samples/sec: 3422.99 - lr: 0.000023 - momentum: 0.000000 2024-11-27 20:31:38,309 epoch 104 - iter 9/9 - loss 0.00006804 - time (sec): 1.49 - samples/sec: 3497.03 - lr: 0.000023 - momentum: 0.000000 2024-11-27 20:31:38,309 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:31:38,309 EPOCH 104 done: loss 0.0001 - lr: 0.000023 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.99it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.97it/s] 2024-11-27 20:31:38,472 DEV : loss 3.4504647254943848 - f1-score (micro avg) 0.3333 2024-11-27 20:31:38,473 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:31:38,571 epoch 105 - iter 1/9 - loss 0.00004794 - time (sec): 0.10 - samples/sec: 6101.22 - lr: 0.000023 - momentum: 0.000000 2024-11-27 20:31:38,695 epoch 105 - iter 2/9 - loss 0.00004787 - time (sec): 0.22 - samples/sec: 4904.16 - lr: 0.000023 - momentum: 0.000000 2024-11-27 20:31:38,834 epoch 105 - iter 3/9 - loss 0.00005027 - time (sec): 0.36 - samples/sec: 4619.20 - lr: 0.000023 - momentum: 0.000000 2024-11-27 20:31:38,974 epoch 105 - iter 4/9 - loss 0.00006986 - time (sec): 0.50 - samples/sec: 4222.70 - lr: 0.000023 - momentum: 0.000000 2024-11-27 20:31:39,141 epoch 105 - iter 5/9 - loss 0.00006703 - time (sec): 0.67 - samples/sec: 4044.77 - lr: 0.000023 - momentum: 0.000000 2024-11-27 20:31:39,303 epoch 105 - iter 6/9 - loss 0.00006970 - time (sec): 0.83 - samples/sec: 3920.73 - lr: 0.000023 - momentum: 0.000000 2024-11-27 20:31:39,455 epoch 105 - iter 7/9 - loss 0.00006676 - time (sec): 0.98 - samples/sec: 3878.76 - lr: 0.000023 - momentum: 0.000000 2024-11-27 20:31:39,603 epoch 105 - iter 8/9 - loss 0.00006249 - time (sec): 1.13 - samples/sec: 4000.22 - lr: 0.000023 - momentum: 0.000000 2024-11-27 20:31:39,758 epoch 105 - iter 9/9 - loss 0.00006723 - time (sec): 1.28 - samples/sec: 4048.60 - lr: 0.000023 - momentum: 0.000000 2024-11-27 20:31:39,758 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:31:39,758 EPOCH 105 done: loss 0.0001 - lr: 0.000023 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.10it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.09it/s] 2024-11-27 20:31:39,942 DEV : loss 3.4530105590820312 - f1-score (micro avg) 0.3602 2024-11-27 20:31:39,943 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:31:40,043 epoch 106 - iter 1/9 - loss 0.00005992 - time (sec): 0.10 - samples/sec: 5617.72 - lr: 0.000023 - momentum: 0.000000 2024-11-27 20:31:40,179 epoch 106 - iter 2/9 - loss 0.00005490 - time (sec): 0.24 - samples/sec: 4955.21 - lr: 0.000023 - momentum: 0.000000 2024-11-27 20:31:40,324 epoch 106 - iter 3/9 - loss 0.00007200 - time (sec): 0.38 - samples/sec: 5215.02 - lr: 0.000023 - momentum: 0.000000 2024-11-27 20:31:40,500 epoch 106 - iter 4/9 - loss 0.00006725 - time (sec): 0.56 - samples/sec: 4656.24 - lr: 0.000023 - momentum: 0.000000 2024-11-27 20:31:40,642 epoch 106 - iter 5/9 - loss 0.00006537 - time (sec): 0.70 - samples/sec: 4350.02 - lr: 0.000023 - momentum: 0.000000 2024-11-27 20:31:40,786 epoch 106 - iter 6/9 - loss 0.00006968 - time (sec): 0.84 - samples/sec: 4318.21 - lr: 0.000023 - momentum: 0.000000 2024-11-27 20:31:40,944 epoch 106 - iter 7/9 - loss 0.00006621 - time (sec): 1.00 - samples/sec: 4201.10 - lr: 0.000023 - momentum: 0.000000 2024-11-27 20:31:41,097 epoch 106 - iter 8/9 - loss 0.00007740 - time (sec): 1.15 - samples/sec: 4107.79 - lr: 0.000023 - momentum: 0.000000 2024-11-27 20:31:41,227 epoch 106 - iter 9/9 - loss 0.00007767 - time (sec): 1.28 - samples/sec: 4050.59 - lr: 0.000023 - momentum: 0.000000 2024-11-27 20:31:41,227 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:31:41,227 EPOCH 106 done: loss 0.0001 - lr: 0.000023 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 5.81it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 5.80it/s] 2024-11-27 20:31:41,419 DEV : loss 3.449488878250122 - f1-score (micro avg) 0.3537 2024-11-27 20:31:41,420 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:31:41,514 epoch 107 - iter 1/9 - loss 0.00003876 - time (sec): 0.09 - samples/sec: 5355.40 - lr: 0.000023 - momentum: 0.000000 2024-11-27 20:31:41,648 epoch 107 - iter 2/9 - loss 0.00003509 - time (sec): 0.23 - samples/sec: 4601.53 - lr: 0.000023 - momentum: 0.000000 2024-11-27 20:31:41,800 epoch 107 - iter 3/9 - loss 0.00007090 - time (sec): 0.38 - samples/sec: 4790.18 - lr: 0.000023 - momentum: 0.000000 2024-11-27 20:31:41,993 epoch 107 - iter 4/9 - loss 0.00006407 - time (sec): 0.57 - samples/sec: 4232.42 - lr: 0.000023 - momentum: 0.000000 2024-11-27 20:31:42,183 epoch 107 - iter 5/9 - loss 0.00013012 - time (sec): 0.76 - samples/sec: 3932.48 - lr: 0.000023 - momentum: 0.000000 2024-11-27 20:31:42,320 epoch 107 - iter 6/9 - loss 0.00011599 - time (sec): 0.90 - samples/sec: 4040.43 - lr: 0.000023 - momentum: 0.000000 2024-11-27 20:31:42,464 epoch 107 - iter 7/9 - loss 0.00098281 - time (sec): 1.04 - samples/sec: 4105.65 - lr: 0.000023 - momentum: 0.000000 2024-11-27 20:31:42,595 epoch 107 - iter 8/9 - loss 0.00089306 - time (sec): 1.17 - samples/sec: 4039.46 - lr: 0.000023 - momentum: 0.000000 2024-11-27 20:31:42,726 epoch 107 - iter 9/9 - loss 0.00081806 - time (sec): 1.30 - samples/sec: 3983.03 - lr: 0.000023 - momentum: 0.000000 2024-11-27 20:31:42,726 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:31:42,726 EPOCH 107 done: loss 0.0008 - lr: 0.000023 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.00it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.00it/s] 2024-11-27 20:31:42,912 DEV : loss 3.462603807449341 - f1-score (micro avg) 0.3415 2024-11-27 20:31:42,913 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:31:43,031 epoch 108 - iter 1/9 - loss 0.00003452 - time (sec): 0.12 - samples/sec: 5856.66 - lr: 0.000023 - momentum: 0.000000 2024-11-27 20:31:43,207 epoch 108 - iter 2/9 - loss 0.00004110 - time (sec): 0.29 - samples/sec: 4010.58 - lr: 0.000023 - momentum: 0.000000 2024-11-27 20:31:43,426 epoch 108 - iter 3/9 - loss 0.00004142 - time (sec): 0.51 - samples/sec: 3318.42 - lr: 0.000023 - momentum: 0.000000 2024-11-27 20:31:43,579 epoch 108 - iter 4/9 - loss 0.00005022 - time (sec): 0.67 - samples/sec: 3565.35 - lr: 0.000023 - momentum: 0.000000 2024-11-27 20:31:43,733 epoch 108 - iter 5/9 - loss 0.00005240 - time (sec): 0.82 - samples/sec: 3657.03 - lr: 0.000023 - momentum: 0.000000 2024-11-27 20:31:43,854 epoch 108 - iter 6/9 - loss 0.00005866 - time (sec): 0.94 - samples/sec: 3663.02 - lr: 0.000022 - momentum: 0.000000 2024-11-27 20:31:44,003 epoch 108 - iter 7/9 - loss 0.00005706 - time (sec): 1.09 - samples/sec: 3787.76 - lr: 0.000022 - momentum: 0.000000 2024-11-27 20:31:44,147 epoch 108 - iter 8/9 - loss 0.00005281 - time (sec): 1.23 - samples/sec: 3825.01 - lr: 0.000022 - momentum: 0.000000 2024-11-27 20:31:44,279 epoch 108 - iter 9/9 - loss 0.00005146 - time (sec): 1.37 - samples/sec: 3807.02 - lr: 0.000022 - momentum: 0.000000 2024-11-27 20:31:44,280 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:31:44,280 EPOCH 108 done: loss 0.0001 - lr: 0.000022 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 5.71it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 5.71it/s] 2024-11-27 20:31:44,474 DEV : loss 3.4482975006103516 - f1-score (micro avg) 0.3291 2024-11-27 20:31:44,475 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:31:44,573 epoch 109 - iter 1/9 - loss 0.00002734 - time (sec): 0.10 - samples/sec: 6245.55 - lr: 0.000022 - momentum: 0.000000 2024-11-27 20:31:44,709 epoch 109 - iter 2/9 - loss 0.00004021 - time (sec): 0.23 - samples/sec: 5297.24 - lr: 0.000022 - momentum: 0.000000 2024-11-27 20:31:44,855 epoch 109 - iter 3/9 - loss 0.00005338 - time (sec): 0.38 - samples/sec: 5243.05 - lr: 0.000022 - momentum: 0.000000 2024-11-27 20:31:45,017 epoch 109 - iter 4/9 - loss 0.00005156 - time (sec): 0.54 - samples/sec: 4676.99 - lr: 0.000022 - momentum: 0.000000 2024-11-27 20:31:45,161 epoch 109 - iter 5/9 - loss 0.00005278 - time (sec): 0.68 - samples/sec: 4438.79 - lr: 0.000022 - momentum: 0.000000 2024-11-27 20:31:45,476 epoch 109 - iter 6/9 - loss 0.00005090 - time (sec): 1.00 - samples/sec: 3535.62 - lr: 0.000022 - momentum: 0.000000 2024-11-27 20:31:45,608 epoch 109 - iter 7/9 - loss 0.00005113 - time (sec): 1.13 - samples/sec: 3552.67 - lr: 0.000022 - momentum: 0.000000 2024-11-27 20:31:45,753 epoch 109 - iter 8/9 - loss 0.00122752 - time (sec): 1.28 - samples/sec: 3649.21 - lr: 0.000022 - momentum: 0.000000 2024-11-27 20:31:45,887 epoch 109 - iter 9/9 - loss 0.00111068 - time (sec): 1.41 - samples/sec: 3685.03 - lr: 0.000022 - momentum: 0.000000 2024-11-27 20:31:45,887 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:31:45,887 EPOCH 109 done: loss 0.0011 - lr: 0.000022 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 2.34it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 2.34it/s] 2024-11-27 20:31:46,334 DEV : loss 3.4284870624542236 - f1-score (micro avg) 0.3396 2024-11-27 20:31:46,336 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:31:46,431 epoch 110 - iter 1/9 - loss 0.00012559 - time (sec): 0.09 - samples/sec: 5596.45 - lr: 0.000022 - momentum: 0.000000 2024-11-27 20:31:46,574 epoch 110 - iter 2/9 - loss 0.00009311 - time (sec): 0.24 - samples/sec: 4533.59 - lr: 0.000022 - momentum: 0.000000 2024-11-27 20:31:46,712 epoch 110 - iter 3/9 - loss 0.00012689 - time (sec): 0.38 - samples/sec: 4400.43 - lr: 0.000022 - momentum: 0.000000 2024-11-27 20:31:46,921 epoch 110 - iter 4/9 - loss 0.00009991 - time (sec): 0.58 - samples/sec: 4014.75 - lr: 0.000022 - momentum: 0.000000 2024-11-27 20:31:47,158 epoch 110 - iter 5/9 - loss 0.00008624 - time (sec): 0.82 - samples/sec: 3564.21 - lr: 0.000022 - momentum: 0.000000 2024-11-27 20:31:47,292 epoch 110 - iter 6/9 - loss 0.00008023 - time (sec): 0.95 - samples/sec: 3582.90 - lr: 0.000022 - momentum: 0.000000 2024-11-27 20:31:47,441 epoch 110 - iter 7/9 - loss 0.00007539 - time (sec): 1.10 - samples/sec: 3787.23 - lr: 0.000022 - momentum: 0.000000 2024-11-27 20:31:47,639 epoch 110 - iter 8/9 - loss 0.00007201 - time (sec): 1.30 - samples/sec: 3673.05 - lr: 0.000022 - momentum: 0.000000 2024-11-27 20:31:47,772 epoch 110 - iter 9/9 - loss 0.00007007 - time (sec): 1.44 - samples/sec: 3620.47 - lr: 0.000022 - momentum: 0.000000 2024-11-27 20:31:47,773 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:31:47,773 EPOCH 110 done: loss 0.0001 - lr: 0.000022 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.89it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.88it/s] 2024-11-27 20:31:47,937 DEV : loss 3.4355270862579346 - f1-score (micro avg) 0.3375 2024-11-27 20:31:47,938 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:31:48,037 epoch 111 - iter 1/9 - loss 0.00005570 - time (sec): 0.10 - samples/sec: 5081.60 - lr: 0.000022 - momentum: 0.000000 2024-11-27 20:31:48,164 epoch 111 - iter 2/9 - loss 0.00007821 - time (sec): 0.22 - samples/sec: 4729.35 - lr: 0.000022 - momentum: 0.000000 2024-11-27 20:31:48,290 epoch 111 - iter 3/9 - loss 0.00007472 - time (sec): 0.35 - samples/sec: 4717.10 - lr: 0.000022 - momentum: 0.000000 2024-11-27 20:31:48,431 epoch 111 - iter 4/9 - loss 0.00009777 - time (sec): 0.49 - samples/sec: 4796.35 - lr: 0.000022 - momentum: 0.000000 2024-11-27 20:31:48,584 epoch 111 - iter 5/9 - loss 0.00009096 - time (sec): 0.64 - samples/sec: 4585.84 - lr: 0.000022 - momentum: 0.000000 2024-11-27 20:31:48,715 epoch 111 - iter 6/9 - loss 0.00008556 - time (sec): 0.78 - samples/sec: 4384.96 - lr: 0.000022 - momentum: 0.000000 2024-11-27 20:31:48,832 epoch 111 - iter 7/9 - loss 0.00007885 - time (sec): 0.89 - samples/sec: 4400.42 - lr: 0.000022 - momentum: 0.000000 2024-11-27 20:31:48,990 epoch 111 - iter 8/9 - loss 0.00007563 - time (sec): 1.05 - samples/sec: 4426.09 - lr: 0.000022 - momentum: 0.000000 2024-11-27 20:31:49,146 epoch 111 - iter 9/9 - loss 0.00007159 - time (sec): 1.21 - samples/sec: 4308.19 - lr: 0.000022 - momentum: 0.000000 2024-11-27 20:31:49,146 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:31:49,146 EPOCH 111 done: loss 0.0001 - lr: 0.000022 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 5.87it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 5.86it/s] 2024-11-27 20:31:49,336 DEV : loss 3.4463729858398438 - f1-score (micro avg) 0.319 2024-11-27 20:31:49,337 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:31:49,439 epoch 112 - iter 1/9 - loss 0.00003903 - time (sec): 0.10 - samples/sec: 5117.25 - lr: 0.000022 - momentum: 0.000000 2024-11-27 20:31:49,585 epoch 112 - iter 2/9 - loss 0.00006521 - time (sec): 0.25 - samples/sec: 4642.51 - lr: 0.000022 - momentum: 0.000000 2024-11-27 20:31:49,730 epoch 112 - iter 3/9 - loss 0.00006278 - time (sec): 0.39 - samples/sec: 4470.86 - lr: 0.000022 - momentum: 0.000000 2024-11-27 20:31:49,858 epoch 112 - iter 4/9 - loss 0.00005667 - time (sec): 0.52 - samples/sec: 4187.57 - lr: 0.000022 - momentum: 0.000000 2024-11-27 20:31:50,010 epoch 112 - iter 5/9 - loss 0.00005369 - time (sec): 0.67 - samples/sec: 4216.10 - lr: 0.000022 - momentum: 0.000000 2024-11-27 20:31:50,195 epoch 112 - iter 6/9 - loss 0.00005445 - time (sec): 0.86 - samples/sec: 3969.51 - lr: 0.000022 - momentum: 0.000000 2024-11-27 20:31:50,350 epoch 112 - iter 7/9 - loss 0.00005754 - time (sec): 1.01 - samples/sec: 3908.84 - lr: 0.000022 - momentum: 0.000000 2024-11-27 20:31:50,488 epoch 112 - iter 8/9 - loss 0.00005370 - time (sec): 1.15 - samples/sec: 4017.85 - lr: 0.000022 - momentum: 0.000000 2024-11-27 20:31:50,652 epoch 112 - iter 9/9 - loss 0.00005866 - time (sec): 1.31 - samples/sec: 3954.72 - lr: 0.000022 - momentum: 0.000000 2024-11-27 20:31:50,653 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:31:50,653 EPOCH 112 done: loss 0.0001 - lr: 0.000022 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.01it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.00it/s] 2024-11-27 20:31:50,839 DEV : loss 3.4570696353912354 - f1-score (micro avg) 0.325 2024-11-27 20:31:50,840 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:31:50,940 epoch 113 - iter 1/9 - loss 0.00001828 - time (sec): 0.10 - samples/sec: 5452.53 - lr: 0.000022 - momentum: 0.000000 2024-11-27 20:31:51,074 epoch 113 - iter 2/9 - loss 0.00553074 - time (sec): 0.23 - samples/sec: 4480.07 - lr: 0.000022 - momentum: 0.000000 2024-11-27 20:31:51,219 epoch 113 - iter 3/9 - loss 0.00966804 - time (sec): 0.38 - samples/sec: 4281.43 - lr: 0.000022 - momentum: 0.000000 2024-11-27 20:31:51,401 epoch 113 - iter 4/9 - loss 0.00674156 - time (sec): 0.56 - samples/sec: 4152.96 - lr: 0.000022 - momentum: 0.000000 2024-11-27 20:31:51,577 epoch 113 - iter 5/9 - loss 0.00540324 - time (sec): 0.74 - samples/sec: 3950.26 - lr: 0.000021 - momentum: 0.000000 2024-11-27 20:31:51,729 epoch 113 - iter 6/9 - loss 0.00462859 - time (sec): 0.89 - samples/sec: 3826.19 - lr: 0.000021 - momentum: 0.000000 2024-11-27 20:31:51,871 epoch 113 - iter 7/9 - loss 0.00403025 - time (sec): 1.03 - samples/sec: 3795.42 - lr: 0.000021 - momentum: 0.000000 2024-11-27 20:31:52,019 epoch 113 - iter 8/9 - loss 0.00344988 - time (sec): 1.18 - samples/sec: 3882.75 - lr: 0.000021 - momentum: 0.000000 2024-11-27 20:31:52,179 epoch 113 - iter 9/9 - loss 0.00304808 - time (sec): 1.34 - samples/sec: 3883.26 - lr: 0.000021 - momentum: 0.000000 2024-11-27 20:31:52,180 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:31:52,180 EPOCH 113 done: loss 0.0030 - lr: 0.000021 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 5.87it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 5.86it/s] 2024-11-27 20:31:52,370 DEV : loss 3.478675603866577 - f1-score (micro avg) 0.3106 2024-11-27 20:31:52,371 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:31:52,474 epoch 114 - iter 1/9 - loss 0.00007668 - time (sec): 0.10 - samples/sec: 5920.33 - lr: 0.000021 - momentum: 0.000000 2024-11-27 20:31:52,621 epoch 114 - iter 2/9 - loss 0.00106193 - time (sec): 0.25 - samples/sec: 4607.87 - lr: 0.000021 - momentum: 0.000000 2024-11-27 20:31:52,769 epoch 114 - iter 3/9 - loss 0.00070050 - time (sec): 0.40 - samples/sec: 4478.14 - lr: 0.000021 - momentum: 0.000000 2024-11-27 20:31:52,907 epoch 114 - iter 4/9 - loss 0.00053840 - time (sec): 0.53 - samples/sec: 4459.94 - lr: 0.000021 - momentum: 0.000000 2024-11-27 20:31:53,060 epoch 114 - iter 5/9 - loss 0.00043523 - time (sec): 0.69 - samples/sec: 4330.96 - lr: 0.000021 - momentum: 0.000000 2024-11-27 20:31:53,207 epoch 114 - iter 6/9 - loss 0.00037710 - time (sec): 0.83 - samples/sec: 4208.81 - lr: 0.000021 - momentum: 0.000000 2024-11-27 20:31:53,347 epoch 114 - iter 7/9 - loss 0.00033259 - time (sec): 0.97 - samples/sec: 4159.22 - lr: 0.000021 - momentum: 0.000000 2024-11-27 20:31:53,484 epoch 114 - iter 8/9 - loss 0.00029805 - time (sec): 1.11 - samples/sec: 4100.37 - lr: 0.000021 - momentum: 0.000000 2024-11-27 20:31:53,695 epoch 114 - iter 9/9 - loss 0.00026611 - time (sec): 1.32 - samples/sec: 3927.91 - lr: 0.000021 - momentum: 0.000000 2024-11-27 20:31:53,696 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:31:53,696 EPOCH 114 done: loss 0.0003 - lr: 0.000021 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 4.03it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 4.03it/s] 2024-11-27 20:31:53,964 DEV : loss 3.5007450580596924 - f1-score (micro avg) 0.3171 2024-11-27 20:31:53,965 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:31:54,060 epoch 115 - iter 1/9 - loss 0.00004844 - time (sec): 0.09 - samples/sec: 6654.14 - lr: 0.000021 - momentum: 0.000000 2024-11-27 20:31:54,184 epoch 115 - iter 2/9 - loss 0.00004956 - time (sec): 0.22 - samples/sec: 5434.42 - lr: 0.000021 - momentum: 0.000000 2024-11-27 20:31:54,323 epoch 115 - iter 3/9 - loss 0.00004766 - time (sec): 0.36 - samples/sec: 4615.76 - lr: 0.000021 - momentum: 0.000000 2024-11-27 20:31:54,468 epoch 115 - iter 4/9 - loss 0.00004432 - time (sec): 0.50 - samples/sec: 4541.01 - lr: 0.000021 - momentum: 0.000000 2024-11-27 20:31:54,615 epoch 115 - iter 5/9 - loss 0.00005664 - time (sec): 0.65 - samples/sec: 4583.10 - lr: 0.000021 - momentum: 0.000000 2024-11-27 20:31:54,762 epoch 115 - iter 6/9 - loss 0.00005179 - time (sec): 0.80 - samples/sec: 4396.29 - lr: 0.000021 - momentum: 0.000000 2024-11-27 20:31:54,922 epoch 115 - iter 7/9 - loss 0.00005025 - time (sec): 0.96 - samples/sec: 4287.23 - lr: 0.000021 - momentum: 0.000000 2024-11-27 20:31:55,074 epoch 115 - iter 8/9 - loss 0.00004853 - time (sec): 1.11 - samples/sec: 4212.90 - lr: 0.000021 - momentum: 0.000000 2024-11-27 20:31:55,226 epoch 115 - iter 9/9 - loss 0.00004776 - time (sec): 1.26 - samples/sec: 4125.79 - lr: 0.000021 - momentum: 0.000000 2024-11-27 20:31:55,226 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:31:55,226 EPOCH 115 done: loss 0.0000 - lr: 0.000021 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.28it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.27it/s] 2024-11-27 20:31:55,405 DEV : loss 3.560791015625 - f1-score (micro avg) 0.3114 2024-11-27 20:31:55,406 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:31:55,491 epoch 116 - iter 1/9 - loss 0.00003810 - time (sec): 0.08 - samples/sec: 6007.80 - lr: 0.000021 - momentum: 0.000000 2024-11-27 20:31:55,608 epoch 116 - iter 2/9 - loss 0.00005477 - time (sec): 0.20 - samples/sec: 5875.65 - lr: 0.000021 - momentum: 0.000000 2024-11-27 20:31:55,737 epoch 116 - iter 3/9 - loss 0.00004514 - time (sec): 0.33 - samples/sec: 5058.70 - lr: 0.000021 - momentum: 0.000000 2024-11-27 20:31:55,912 epoch 116 - iter 4/9 - loss 0.00003963 - time (sec): 0.50 - samples/sec: 4455.39 - lr: 0.000021 - momentum: 0.000000 2024-11-27 20:31:56,153 epoch 116 - iter 5/9 - loss 0.00005746 - time (sec): 0.75 - samples/sec: 3695.11 - lr: 0.000021 - momentum: 0.000000 2024-11-27 20:31:56,287 epoch 116 - iter 6/9 - loss 0.00005136 - time (sec): 0.88 - samples/sec: 3942.16 - lr: 0.000021 - momentum: 0.000000 2024-11-27 20:31:56,411 epoch 116 - iter 7/9 - loss 0.00078480 - time (sec): 1.00 - samples/sec: 4024.74 - lr: 0.000021 - momentum: 0.000000 2024-11-27 20:31:56,569 epoch 116 - iter 8/9 - loss 0.00068638 - time (sec): 1.16 - samples/sec: 4034.27 - lr: 0.000021 - momentum: 0.000000 2024-11-27 20:31:56,729 epoch 116 - iter 9/9 - loss 0.00062341 - time (sec): 1.32 - samples/sec: 3931.03 - lr: 0.000021 - momentum: 0.000000 2024-11-27 20:31:56,730 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:31:56,730 EPOCH 116 done: loss 0.0006 - lr: 0.000021 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.06it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.05it/s] 2024-11-27 20:31:56,914 DEV : loss 3.5853145122528076 - f1-score (micro avg) 0.3133 2024-11-27 20:31:56,915 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:31:57,029 epoch 117 - iter 1/9 - loss 0.00006614 - time (sec): 0.11 - samples/sec: 5450.62 - lr: 0.000021 - momentum: 0.000000 2024-11-27 20:31:57,189 epoch 117 - iter 2/9 - loss 0.00006177 - time (sec): 0.27 - samples/sec: 4237.09 - lr: 0.000021 - momentum: 0.000000 2024-11-27 20:31:57,355 epoch 117 - iter 3/9 - loss 0.00005494 - time (sec): 0.44 - samples/sec: 4134.01 - lr: 0.000021 - momentum: 0.000000 2024-11-27 20:31:57,503 epoch 117 - iter 4/9 - loss 0.00004943 - time (sec): 0.59 - samples/sec: 4078.48 - lr: 0.000021 - momentum: 0.000000 2024-11-27 20:31:57,650 epoch 117 - iter 5/9 - loss 0.00005580 - time (sec): 0.73 - samples/sec: 4041.87 - lr: 0.000021 - momentum: 0.000000 2024-11-27 20:31:57,793 epoch 117 - iter 6/9 - loss 0.00005474 - time (sec): 0.88 - samples/sec: 4009.58 - lr: 0.000021 - momentum: 0.000000 2024-11-27 20:31:57,934 epoch 117 - iter 7/9 - loss 0.00005447 - time (sec): 1.02 - samples/sec: 4126.50 - lr: 0.000021 - momentum: 0.000000 2024-11-27 20:31:58,063 epoch 117 - iter 8/9 - loss 0.00005230 - time (sec): 1.15 - samples/sec: 4143.52 - lr: 0.000021 - momentum: 0.000000 2024-11-27 20:31:58,206 epoch 117 - iter 9/9 - loss 0.00005036 - time (sec): 1.29 - samples/sec: 4030.84 - lr: 0.000021 - momentum: 0.000000 2024-11-27 20:31:58,206 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:31:58,206 EPOCH 117 done: loss 0.0001 - lr: 0.000021 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.32it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.31it/s] 2024-11-27 20:31:58,384 DEV : loss 3.5504486560821533 - f1-score (micro avg) 0.3354 2024-11-27 20:31:58,385 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:31:58,485 epoch 118 - iter 1/9 - loss 0.00001898 - time (sec): 0.10 - samples/sec: 5360.29 - lr: 0.000021 - momentum: 0.000000 2024-11-27 20:31:58,632 epoch 118 - iter 2/9 - loss 0.00003136 - time (sec): 0.25 - samples/sec: 5112.43 - lr: 0.000021 - momentum: 0.000000 2024-11-27 20:31:58,766 epoch 118 - iter 3/9 - loss 0.00003124 - time (sec): 0.38 - samples/sec: 4631.48 - lr: 0.000021 - momentum: 0.000000 2024-11-27 20:31:58,910 epoch 118 - iter 4/9 - loss 0.00004374 - time (sec): 0.52 - samples/sec: 4651.65 - lr: 0.000020 - momentum: 0.000000 2024-11-27 20:31:59,236 epoch 118 - iter 5/9 - loss 0.00003960 - time (sec): 0.85 - samples/sec: 3431.26 - lr: 0.000020 - momentum: 0.000000 2024-11-27 20:31:59,376 epoch 118 - iter 6/9 - loss 0.00004202 - time (sec): 0.99 - samples/sec: 3526.15 - lr: 0.000020 - momentum: 0.000000 2024-11-27 20:31:59,516 epoch 118 - iter 7/9 - loss 0.00009402 - time (sec): 1.13 - samples/sec: 3607.36 - lr: 0.000020 - momentum: 0.000000 2024-11-27 20:31:59,663 epoch 118 - iter 8/9 - loss 0.00008543 - time (sec): 1.28 - samples/sec: 3681.45 - lr: 0.000020 - momentum: 0.000000 2024-11-27 20:31:59,804 epoch 118 - iter 9/9 - loss 0.00007977 - time (sec): 1.42 - samples/sec: 3666.18 - lr: 0.000020 - momentum: 0.000000 2024-11-27 20:31:59,804 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:31:59,804 EPOCH 118 done: loss 0.0001 - lr: 0.000020 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 5.71it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 5.70it/s] 2024-11-27 20:31:59,999 DEV : loss 3.531055212020874 - f1-score (micro avg) 0.3312 2024-11-27 20:32:00,000 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:32:00,111 epoch 119 - iter 1/9 - loss 0.00020802 - time (sec): 0.11 - samples/sec: 5331.74 - lr: 0.000020 - momentum: 0.000000 2024-11-27 20:32:00,282 epoch 119 - iter 2/9 - loss 0.00011565 - time (sec): 0.28 - samples/sec: 4279.70 - lr: 0.000020 - momentum: 0.000000 2024-11-27 20:32:00,436 epoch 119 - iter 3/9 - loss 0.00009836 - time (sec): 0.43 - samples/sec: 4048.44 - lr: 0.000020 - momentum: 0.000000 2024-11-27 20:32:00,586 epoch 119 - iter 4/9 - loss 0.00009150 - time (sec): 0.58 - samples/sec: 3849.49 - lr: 0.000020 - momentum: 0.000000 2024-11-27 20:32:00,758 epoch 119 - iter 5/9 - loss 0.00008145 - time (sec): 0.76 - samples/sec: 3687.55 - lr: 0.000020 - momentum: 0.000000 2024-11-27 20:32:00,919 epoch 119 - iter 6/9 - loss 0.00007141 - time (sec): 0.92 - samples/sec: 3638.34 - lr: 0.000020 - momentum: 0.000000 2024-11-27 20:32:01,099 epoch 119 - iter 7/9 - loss 0.00006235 - time (sec): 1.10 - samples/sec: 3657.16 - lr: 0.000020 - momentum: 0.000000 2024-11-27 20:32:01,264 epoch 119 - iter 8/9 - loss 0.00005712 - time (sec): 1.26 - samples/sec: 3768.87 - lr: 0.000020 - momentum: 0.000000 2024-11-27 20:32:01,395 epoch 119 - iter 9/9 - loss 0.00071906 - time (sec): 1.39 - samples/sec: 3728.36 - lr: 0.000020 - momentum: 0.000000 2024-11-27 20:32:01,396 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:32:01,396 EPOCH 119 done: loss 0.0007 - lr: 0.000020 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.40it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.39it/s] 2024-11-27 20:32:01,571 DEV : loss 3.5202183723449707 - f1-score (micro avg) 0.3484 2024-11-27 20:32:01,572 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:32:01,664 epoch 120 - iter 1/9 - loss 0.00001575 - time (sec): 0.09 - samples/sec: 5189.31 - lr: 0.000020 - momentum: 0.000000 2024-11-27 20:32:01,810 epoch 120 - iter 2/9 - loss 0.00004077 - time (sec): 0.24 - samples/sec: 4324.53 - lr: 0.000020 - momentum: 0.000000 2024-11-27 20:32:02,003 epoch 120 - iter 3/9 - loss 0.00003938 - time (sec): 0.43 - samples/sec: 3743.98 - lr: 0.000020 - momentum: 0.000000 2024-11-27 20:32:02,169 epoch 120 - iter 4/9 - loss 0.00004028 - time (sec): 0.60 - samples/sec: 3585.99 - lr: 0.000020 - momentum: 0.000000 2024-11-27 20:32:02,309 epoch 120 - iter 5/9 - loss 0.00003897 - time (sec): 0.74 - samples/sec: 3760.84 - lr: 0.000020 - momentum: 0.000000 2024-11-27 20:32:02,461 epoch 120 - iter 6/9 - loss 0.00003775 - time (sec): 0.89 - samples/sec: 3841.44 - lr: 0.000020 - momentum: 0.000000 2024-11-27 20:32:02,604 epoch 120 - iter 7/9 - loss 0.00003612 - time (sec): 1.03 - samples/sec: 3776.07 - lr: 0.000020 - momentum: 0.000000 2024-11-27 20:32:02,755 epoch 120 - iter 8/9 - loss 0.00003582 - time (sec): 1.18 - samples/sec: 3831.67 - lr: 0.000020 - momentum: 0.000000 2024-11-27 20:32:02,908 epoch 120 - iter 9/9 - loss 0.00003868 - time (sec): 1.33 - samples/sec: 3894.86 - lr: 0.000020 - momentum: 0.000000 2024-11-27 20:32:02,908 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:32:02,908 EPOCH 120 done: loss 0.0000 - lr: 0.000020 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 5.78it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 5.78it/s] 2024-11-27 20:32:03,101 DEV : loss 3.513798952102661 - f1-score (micro avg) 0.3355 2024-11-27 20:32:03,102 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:32:03,212 epoch 121 - iter 1/9 - loss 0.00006220 - time (sec): 0.11 - samples/sec: 4812.99 - lr: 0.000020 - momentum: 0.000000 2024-11-27 20:32:03,373 epoch 121 - iter 2/9 - loss 0.00003975 - time (sec): 0.27 - samples/sec: 4333.57 - lr: 0.000020 - momentum: 0.000000 2024-11-27 20:32:03,525 epoch 121 - iter 3/9 - loss 0.00005133 - time (sec): 0.42 - samples/sec: 4049.52 - lr: 0.000020 - momentum: 0.000000 2024-11-27 20:32:03,667 epoch 121 - iter 4/9 - loss 0.00005271 - time (sec): 0.56 - samples/sec: 4092.33 - lr: 0.000020 - momentum: 0.000000 2024-11-27 20:32:03,831 epoch 121 - iter 5/9 - loss 0.00004594 - time (sec): 0.73 - samples/sec: 4044.82 - lr: 0.000020 - momentum: 0.000000 2024-11-27 20:32:03,985 epoch 121 - iter 6/9 - loss 0.00004340 - time (sec): 0.88 - samples/sec: 3958.39 - lr: 0.000020 - momentum: 0.000000 2024-11-27 20:32:04,132 epoch 121 - iter 7/9 - loss 0.00003999 - time (sec): 1.03 - samples/sec: 3917.44 - lr: 0.000020 - momentum: 0.000000 2024-11-27 20:32:04,272 epoch 121 - iter 8/9 - loss 0.00003837 - time (sec): 1.17 - samples/sec: 4005.38 - lr: 0.000020 - momentum: 0.000000 2024-11-27 20:32:04,455 epoch 121 - iter 9/9 - loss 0.00003770 - time (sec): 1.35 - samples/sec: 3843.35 - lr: 0.000020 - momentum: 0.000000 2024-11-27 20:32:04,456 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:32:04,456 EPOCH 121 done: loss 0.0000 - lr: 0.000020 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.78it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.77it/s] 2024-11-27 20:32:04,622 DEV : loss 3.525623083114624 - f1-score (micro avg) 0.3185 2024-11-27 20:32:04,624 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:32:04,717 epoch 122 - iter 1/9 - loss 0.00003838 - time (sec): 0.09 - samples/sec: 6466.96 - lr: 0.000020 - momentum: 0.000000 2024-11-27 20:32:04,852 epoch 122 - iter 2/9 - loss 0.00002816 - time (sec): 0.23 - samples/sec: 5098.02 - lr: 0.000020 - momentum: 0.000000 2024-11-27 20:32:04,980 epoch 122 - iter 3/9 - loss 0.00003279 - time (sec): 0.36 - samples/sec: 4575.40 - lr: 0.000020 - momentum: 0.000000 2024-11-27 20:32:05,142 epoch 122 - iter 4/9 - loss 0.00004357 - time (sec): 0.52 - samples/sec: 4506.42 - lr: 0.000020 - momentum: 0.000000 2024-11-27 20:32:05,298 epoch 122 - iter 5/9 - loss 0.00003817 - time (sec): 0.67 - samples/sec: 4363.86 - lr: 0.000020 - momentum: 0.000000 2024-11-27 20:32:05,458 epoch 122 - iter 6/9 - loss 0.00003825 - time (sec): 0.83 - samples/sec: 4275.17 - lr: 0.000020 - momentum: 0.000000 2024-11-27 20:32:05,612 epoch 122 - iter 7/9 - loss 0.00003730 - time (sec): 0.99 - samples/sec: 4085.42 - lr: 0.000020 - momentum: 0.000000 2024-11-27 20:32:05,773 epoch 122 - iter 8/9 - loss 0.00003697 - time (sec): 1.15 - samples/sec: 4085.76 - lr: 0.000020 - momentum: 0.000000 2024-11-27 20:32:05,910 epoch 122 - iter 9/9 - loss 0.00003728 - time (sec): 1.29 - samples/sec: 4042.39 - lr: 0.000020 - momentum: 0.000000 2024-11-27 20:32:05,911 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:32:05,911 EPOCH 122 done: loss 0.0000 - lr: 0.000020 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 5.25it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 5.24it/s] 2024-11-27 20:32:06,121 DEV : loss 3.496140956878662 - f1-score (micro avg) 0.3125 2024-11-27 20:32:06,122 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:32:06,212 epoch 123 - iter 1/9 - loss 0.00004032 - time (sec): 0.09 - samples/sec: 5834.94 - lr: 0.000020 - momentum: 0.000000 2024-11-27 20:32:06,342 epoch 123 - iter 2/9 - loss 0.00004409 - time (sec): 0.22 - samples/sec: 4983.86 - lr: 0.000020 - momentum: 0.000000 2024-11-27 20:32:06,496 epoch 123 - iter 3/9 - loss 0.00004200 - time (sec): 0.37 - samples/sec: 4494.06 - lr: 0.000020 - momentum: 0.000000 2024-11-27 20:32:06,722 epoch 123 - iter 4/9 - loss 0.00004209 - time (sec): 0.60 - samples/sec: 3982.89 - lr: 0.000019 - momentum: 0.000000 2024-11-27 20:32:06,918 epoch 123 - iter 5/9 - loss 0.00003777 - time (sec): 0.79 - samples/sec: 3677.91 - lr: 0.000019 - momentum: 0.000000 2024-11-27 20:32:07,053 epoch 123 - iter 6/9 - loss 0.00003606 - time (sec): 0.93 - samples/sec: 3729.33 - lr: 0.000019 - momentum: 0.000000 2024-11-27 20:32:07,204 epoch 123 - iter 7/9 - loss 0.00003714 - time (sec): 1.08 - samples/sec: 3798.05 - lr: 0.000019 - momentum: 0.000000 2024-11-27 20:32:07,372 epoch 123 - iter 8/9 - loss 0.00003491 - time (sec): 1.25 - samples/sec: 3743.88 - lr: 0.000019 - momentum: 0.000000 2024-11-27 20:32:07,591 epoch 123 - iter 9/9 - loss 0.00195355 - time (sec): 1.47 - samples/sec: 3539.39 - lr: 0.000019 - momentum: 0.000000 2024-11-27 20:32:07,592 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:32:07,592 EPOCH 123 done: loss 0.0020 - lr: 0.000019 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.82it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.80it/s] 2024-11-27 20:32:07,758 DEV : loss 3.481231689453125 - f1-score (micro avg) 0.325 2024-11-27 20:32:07,759 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:32:07,849 epoch 124 - iter 1/9 - loss 0.00013382 - time (sec): 0.09 - samples/sec: 5630.78 - lr: 0.000019 - momentum: 0.000000 2024-11-27 20:32:07,989 epoch 124 - iter 2/9 - loss 0.00007803 - time (sec): 0.23 - samples/sec: 5201.82 - lr: 0.000019 - momentum: 0.000000 2024-11-27 20:32:08,144 epoch 124 - iter 3/9 - loss 0.00006707 - time (sec): 0.38 - samples/sec: 4333.67 - lr: 0.000019 - momentum: 0.000000 2024-11-27 20:32:08,301 epoch 124 - iter 4/9 - loss 0.00005782 - time (sec): 0.54 - samples/sec: 4096.58 - lr: 0.000019 - momentum: 0.000000 2024-11-27 20:32:08,459 epoch 124 - iter 5/9 - loss 0.00005307 - time (sec): 0.70 - samples/sec: 3976.78 - lr: 0.000019 - momentum: 0.000000 2024-11-27 20:32:08,611 epoch 124 - iter 6/9 - loss 0.00004601 - time (sec): 0.85 - samples/sec: 3961.41 - lr: 0.000019 - momentum: 0.000000 2024-11-27 20:32:08,783 epoch 124 - iter 7/9 - loss 0.00004613 - time (sec): 1.02 - samples/sec: 3968.56 - lr: 0.000019 - momentum: 0.000000 2024-11-27 20:32:08,941 epoch 124 - iter 8/9 - loss 0.00004703 - time (sec): 1.18 - samples/sec: 3933.78 - lr: 0.000019 - momentum: 0.000000 2024-11-27 20:32:09,096 epoch 124 - iter 9/9 - loss 0.00004693 - time (sec): 1.34 - samples/sec: 3889.46 - lr: 0.000019 - momentum: 0.000000 2024-11-27 20:32:09,096 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:32:09,096 EPOCH 124 done: loss 0.0000 - lr: 0.000019 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.59it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.58it/s] 2024-11-27 20:32:09,267 DEV : loss 3.4837658405303955 - f1-score (micro avg) 0.3462 2024-11-27 20:32:09,269 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:32:09,369 epoch 125 - iter 1/9 - loss 0.00003737 - time (sec): 0.10 - samples/sec: 5589.45 - lr: 0.000019 - momentum: 0.000000 2024-11-27 20:32:09,506 epoch 125 - iter 2/9 - loss 0.00003054 - time (sec): 0.24 - samples/sec: 4651.23 - lr: 0.000019 - momentum: 0.000000 2024-11-27 20:32:09,646 epoch 125 - iter 3/9 - loss 0.00004844 - time (sec): 0.38 - samples/sec: 4386.12 - lr: 0.000019 - momentum: 0.000000 2024-11-27 20:32:09,862 epoch 125 - iter 4/9 - loss 0.00004683 - time (sec): 0.59 - samples/sec: 3935.52 - lr: 0.000019 - momentum: 0.000000 2024-11-27 20:32:10,125 epoch 125 - iter 5/9 - loss 0.00004417 - time (sec): 0.86 - samples/sec: 3347.08 - lr: 0.000019 - momentum: 0.000000 2024-11-27 20:32:10,269 epoch 125 - iter 6/9 - loss 0.00004866 - time (sec): 1.00 - samples/sec: 3457.82 - lr: 0.000019 - momentum: 0.000000 2024-11-27 20:32:10,422 epoch 125 - iter 7/9 - loss 0.00004470 - time (sec): 1.15 - samples/sec: 3405.21 - lr: 0.000019 - momentum: 0.000000 2024-11-27 20:32:10,658 epoch 125 - iter 8/9 - loss 0.00004182 - time (sec): 1.39 - samples/sec: 3346.40 - lr: 0.000019 - momentum: 0.000000 2024-11-27 20:32:10,817 epoch 125 - iter 9/9 - loss 0.00004294 - time (sec): 1.55 - samples/sec: 3358.75 - lr: 0.000019 - momentum: 0.000000 2024-11-27 20:32:10,817 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:32:10,817 EPOCH 125 done: loss 0.0000 - lr: 0.000019 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.12it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.11it/s] 2024-11-27 20:32:11,000 DEV : loss 3.4854319095611572 - f1-score (micro avg) 0.3418 2024-11-27 20:32:11,001 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:32:11,104 epoch 126 - iter 1/9 - loss 0.00005422 - time (sec): 0.10 - samples/sec: 6001.07 - lr: 0.000019 - momentum: 0.000000 2024-11-27 20:32:11,248 epoch 126 - iter 2/9 - loss 0.00004891 - time (sec): 0.25 - samples/sec: 4803.27 - lr: 0.000019 - momentum: 0.000000 2024-11-27 20:32:11,448 epoch 126 - iter 3/9 - loss 0.00004618 - time (sec): 0.45 - samples/sec: 3839.81 - lr: 0.000019 - momentum: 0.000000 2024-11-27 20:32:11,586 epoch 126 - iter 4/9 - loss 0.00004695 - time (sec): 0.58 - samples/sec: 4150.33 - lr: 0.000019 - momentum: 0.000000 2024-11-27 20:32:11,724 epoch 126 - iter 5/9 - loss 0.00004139 - time (sec): 0.72 - samples/sec: 4232.59 - lr: 0.000019 - momentum: 0.000000 2024-11-27 20:32:11,884 epoch 126 - iter 6/9 - loss 0.00003977 - time (sec): 0.88 - samples/sec: 4201.64 - lr: 0.000019 - momentum: 0.000000 2024-11-27 20:32:12,056 epoch 126 - iter 7/9 - loss 0.00004143 - time (sec): 1.05 - samples/sec: 3965.17 - lr: 0.000019 - momentum: 0.000000 2024-11-27 20:32:12,233 epoch 126 - iter 8/9 - loss 0.00004302 - time (sec): 1.23 - samples/sec: 3870.70 - lr: 0.000019 - momentum: 0.000000 2024-11-27 20:32:12,368 epoch 126 - iter 9/9 - loss 0.00004149 - time (sec): 1.37 - samples/sec: 3807.21 - lr: 0.000019 - momentum: 0.000000 2024-11-27 20:32:12,368 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:32:12,368 EPOCH 126 done: loss 0.0000 - lr: 0.000019 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 7.04it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 7.03it/s] 2024-11-27 20:32:12,529 DEV : loss 3.490959882736206 - f1-score (micro avg) 0.325 2024-11-27 20:32:12,531 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:32:12,630 epoch 127 - iter 1/9 - loss 0.00003381 - time (sec): 0.10 - samples/sec: 5539.83 - lr: 0.000019 - momentum: 0.000000 2024-11-27 20:32:12,772 epoch 127 - iter 2/9 - loss 0.00004056 - time (sec): 0.24 - samples/sec: 4273.69 - lr: 0.000019 - momentum: 0.000000 2024-11-27 20:32:12,925 epoch 127 - iter 3/9 - loss 0.00003593 - time (sec): 0.39 - samples/sec: 4267.07 - lr: 0.000019 - momentum: 0.000000 2024-11-27 20:32:13,060 epoch 127 - iter 4/9 - loss 0.00003341 - time (sec): 0.53 - samples/sec: 4179.13 - lr: 0.000019 - momentum: 0.000000 2024-11-27 20:32:13,237 epoch 127 - iter 5/9 - loss 0.00051929 - time (sec): 0.70 - samples/sec: 3983.25 - lr: 0.000019 - momentum: 0.000000 2024-11-27 20:32:13,382 epoch 127 - iter 6/9 - loss 0.00044459 - time (sec): 0.85 - samples/sec: 3901.28 - lr: 0.000019 - momentum: 0.000000 2024-11-27 20:32:13,542 epoch 127 - iter 7/9 - loss 0.00037838 - time (sec): 1.01 - samples/sec: 3927.54 - lr: 0.000019 - momentum: 0.000000 2024-11-27 20:32:13,677 epoch 127 - iter 8/9 - loss 0.00033376 - time (sec): 1.15 - samples/sec: 3979.05 - lr: 0.000019 - momentum: 0.000000 2024-11-27 20:32:13,844 epoch 127 - iter 9/9 - loss 0.00030061 - time (sec): 1.31 - samples/sec: 3960.66 - lr: 0.000019 - momentum: 0.000000 2024-11-27 20:32:13,844 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:32:13,844 EPOCH 127 done: loss 0.0003 - lr: 0.000019 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 5.36it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 5.35it/s] 2024-11-27 20:32:14,050 DEV : loss 3.509634494781494 - f1-score (micro avg) 0.3396 2024-11-27 20:32:14,052 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:32:14,135 epoch 128 - iter 1/9 - loss 0.00005715 - time (sec): 0.08 - samples/sec: 5197.21 - lr: 0.000019 - momentum: 0.000000 2024-11-27 20:32:14,276 epoch 128 - iter 2/9 - loss 0.00003945 - time (sec): 0.22 - samples/sec: 4418.06 - lr: 0.000019 - momentum: 0.000000 2024-11-27 20:32:14,554 epoch 128 - iter 3/9 - loss 0.00004026 - time (sec): 0.50 - samples/sec: 2991.48 - lr: 0.000018 - momentum: 0.000000 2024-11-27 20:32:14,711 epoch 128 - iter 4/9 - loss 0.00004595 - time (sec): 0.66 - samples/sec: 3296.32 - lr: 0.000018 - momentum: 0.000000 2024-11-27 20:32:14,870 epoch 128 - iter 5/9 - loss 0.00004007 - time (sec): 0.82 - samples/sec: 3353.49 - lr: 0.000018 - momentum: 0.000000 2024-11-27 20:32:15,069 epoch 128 - iter 6/9 - loss 0.00376090 - time (sec): 1.02 - samples/sec: 3366.18 - lr: 0.000018 - momentum: 0.000000 2024-11-27 20:32:15,241 epoch 128 - iter 7/9 - loss 0.00318946 - time (sec): 1.19 - samples/sec: 3402.69 - lr: 0.000018 - momentum: 0.000000 2024-11-27 20:32:15,385 epoch 128 - iter 8/9 - loss 0.00279232 - time (sec): 1.33 - samples/sec: 3471.72 - lr: 0.000018 - momentum: 0.000000 2024-11-27 20:32:15,523 epoch 128 - iter 9/9 - loss 0.00248819 - time (sec): 1.47 - samples/sec: 3534.02 - lr: 0.000018 - momentum: 0.000000 2024-11-27 20:32:15,523 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:32:15,524 EPOCH 128 done: loss 0.0025 - lr: 0.000018 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.24it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.23it/s] 2024-11-27 20:32:15,703 DEV : loss 3.5323877334594727 - f1-score (micro avg) 0.3506 2024-11-27 20:32:15,704 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:32:15,792 epoch 129 - iter 1/9 - loss 0.00004832 - time (sec): 0.09 - samples/sec: 5917.80 - lr: 0.000018 - momentum: 0.000000 2024-11-27 20:32:15,930 epoch 129 - iter 2/9 - loss 0.00003913 - time (sec): 0.22 - samples/sec: 5345.03 - lr: 0.000018 - momentum: 0.000000 2024-11-27 20:32:16,066 epoch 129 - iter 3/9 - loss 0.00170386 - time (sec): 0.36 - samples/sec: 4835.83 - lr: 0.000018 - momentum: 0.000000 2024-11-27 20:32:16,195 epoch 129 - iter 4/9 - loss 0.00128668 - time (sec): 0.49 - samples/sec: 4730.20 - lr: 0.000018 - momentum: 0.000000 2024-11-27 20:32:16,350 epoch 129 - iter 5/9 - loss 0.00103045 - time (sec): 0.64 - samples/sec: 4508.72 - lr: 0.000018 - momentum: 0.000000 2024-11-27 20:32:16,519 epoch 129 - iter 6/9 - loss 0.00083558 - time (sec): 0.81 - samples/sec: 4470.87 - lr: 0.000018 - momentum: 0.000000 2024-11-27 20:32:16,657 epoch 129 - iter 7/9 - loss 0.00073083 - time (sec): 0.95 - samples/sec: 4382.42 - lr: 0.000018 - momentum: 0.000000 2024-11-27 20:32:16,786 epoch 129 - iter 8/9 - loss 0.00065128 - time (sec): 1.08 - samples/sec: 4342.94 - lr: 0.000018 - momentum: 0.000000 2024-11-27 20:32:16,961 epoch 129 - iter 9/9 - loss 0.00059154 - time (sec): 1.26 - samples/sec: 4140.26 - lr: 0.000018 - momentum: 0.000000 2024-11-27 20:32:16,961 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:32:16,961 EPOCH 129 done: loss 0.0006 - lr: 0.000018 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 5.33it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 5.33it/s] 2024-11-27 20:32:17,168 DEV : loss 3.5502419471740723 - f1-score (micro avg) 0.3529 2024-11-27 20:32:17,169 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:32:17,265 epoch 130 - iter 1/9 - loss 0.00003077 - time (sec): 0.10 - samples/sec: 6044.23 - lr: 0.000018 - momentum: 0.000000 2024-11-27 20:32:17,408 epoch 130 - iter 2/9 - loss 0.00003990 - time (sec): 0.24 - samples/sec: 5146.29 - lr: 0.000018 - momentum: 0.000000 2024-11-27 20:32:17,551 epoch 130 - iter 3/9 - loss 0.00003956 - time (sec): 0.38 - samples/sec: 4436.16 - lr: 0.000018 - momentum: 0.000000 2024-11-27 20:32:17,768 epoch 130 - iter 4/9 - loss 0.00004053 - time (sec): 0.60 - samples/sec: 3755.40 - lr: 0.000018 - momentum: 0.000000 2024-11-27 20:32:17,929 epoch 130 - iter 5/9 - loss 0.00003697 - time (sec): 0.76 - samples/sec: 3664.22 - lr: 0.000018 - momentum: 0.000000 2024-11-27 20:32:18,082 epoch 130 - iter 6/9 - loss 0.00003701 - time (sec): 0.91 - samples/sec: 3798.45 - lr: 0.000018 - momentum: 0.000000 2024-11-27 20:32:18,257 epoch 130 - iter 7/9 - loss 0.00003671 - time (sec): 1.09 - samples/sec: 3655.99 - lr: 0.000018 - momentum: 0.000000 2024-11-27 20:32:18,473 epoch 130 - iter 8/9 - loss 0.00003508 - time (sec): 1.30 - samples/sec: 3629.77 - lr: 0.000018 - momentum: 0.000000 2024-11-27 20:32:18,652 epoch 130 - iter 9/9 - loss 0.00003455 - time (sec): 1.48 - samples/sec: 3506.73 - lr: 0.000018 - momentum: 0.000000 2024-11-27 20:32:18,652 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:32:18,652 EPOCH 130 done: loss 0.0000 - lr: 0.000018 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 2.91it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 2.91it/s] 2024-11-27 20:32:19,015 DEV : loss 3.5602526664733887 - f1-score (micro avg) 0.3529 2024-11-27 20:32:19,016 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:32:19,120 epoch 131 - iter 1/9 - loss 0.00002209 - time (sec): 0.10 - samples/sec: 5474.52 - lr: 0.000018 - momentum: 0.000000 2024-11-27 20:32:19,267 epoch 131 - iter 2/9 - loss 0.00002471 - time (sec): 0.25 - samples/sec: 5073.26 - lr: 0.000018 - momentum: 0.000000 2024-11-27 20:32:19,403 epoch 131 - iter 3/9 - loss 0.00002471 - time (sec): 0.39 - samples/sec: 4769.93 - lr: 0.000018 - momentum: 0.000000 2024-11-27 20:32:19,537 epoch 131 - iter 4/9 - loss 0.00002349 - time (sec): 0.52 - samples/sec: 4438.44 - lr: 0.000018 - momentum: 0.000000 2024-11-27 20:32:19,686 epoch 131 - iter 5/9 - loss 0.00002358 - time (sec): 0.67 - samples/sec: 4316.44 - lr: 0.000018 - momentum: 0.000000 2024-11-27 20:32:19,895 epoch 131 - iter 6/9 - loss 0.00002818 - time (sec): 0.88 - samples/sec: 4128.15 - lr: 0.000018 - momentum: 0.000000 2024-11-27 20:32:20,144 epoch 131 - iter 7/9 - loss 0.00002982 - time (sec): 1.13 - samples/sec: 3661.11 - lr: 0.000018 - momentum: 0.000000 2024-11-27 20:32:20,276 epoch 131 - iter 8/9 - loss 0.00002869 - time (sec): 1.26 - samples/sec: 3661.19 - lr: 0.000018 - momentum: 0.000000 2024-11-27 20:32:20,410 epoch 131 - iter 9/9 - loss 0.00003009 - time (sec): 1.39 - samples/sec: 3732.30 - lr: 0.000018 - momentum: 0.000000 2024-11-27 20:32:20,410 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:32:20,410 EPOCH 131 done: loss 0.0000 - lr: 0.000018 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 4.80it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 4.79it/s] 2024-11-27 20:32:20,638 DEV : loss 3.5648226737976074 - f1-score (micro avg) 0.3529 2024-11-27 20:32:20,639 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:32:20,755 epoch 132 - iter 1/9 - loss 0.00006354 - time (sec): 0.12 - samples/sec: 5181.06 - lr: 0.000018 - momentum: 0.000000 2024-11-27 20:32:20,905 epoch 132 - iter 2/9 - loss 0.00005716 - time (sec): 0.27 - samples/sec: 3985.11 - lr: 0.000018 - momentum: 0.000000 2024-11-27 20:32:21,047 epoch 132 - iter 3/9 - loss 0.00005110 - time (sec): 0.41 - samples/sec: 4109.67 - lr: 0.000018 - momentum: 0.000000 2024-11-27 20:32:21,191 epoch 132 - iter 4/9 - loss 0.00005529 - time (sec): 0.55 - samples/sec: 4070.20 - lr: 0.000018 - momentum: 0.000000 2024-11-27 20:32:21,344 epoch 132 - iter 5/9 - loss 0.00004783 - time (sec): 0.70 - samples/sec: 4104.83 - lr: 0.000018 - momentum: 0.000000 2024-11-27 20:32:21,500 epoch 132 - iter 6/9 - loss 0.00004484 - time (sec): 0.86 - samples/sec: 4033.06 - lr: 0.000018 - momentum: 0.000000 2024-11-27 20:32:21,659 epoch 132 - iter 7/9 - loss 0.00004108 - time (sec): 1.02 - samples/sec: 3956.52 - lr: 0.000018 - momentum: 0.000000 2024-11-27 20:32:21,811 epoch 132 - iter 8/9 - loss 0.00004530 - time (sec): 1.17 - samples/sec: 4010.35 - lr: 0.000018 - momentum: 0.000000 2024-11-27 20:32:21,949 epoch 132 - iter 9/9 - loss 0.00004599 - time (sec): 1.31 - samples/sec: 3970.62 - lr: 0.000018 - momentum: 0.000000 2024-11-27 20:32:21,949 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:32:21,949 EPOCH 132 done: loss 0.0000 - lr: 0.000018 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.87it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.86it/s] 2024-11-27 20:32:22,115 DEV : loss 3.56364107131958 - f1-score (micro avg) 0.3506 2024-11-27 20:32:22,116 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:32:22,217 epoch 133 - iter 1/9 - loss 0.00002716 - time (sec): 0.10 - samples/sec: 6970.66 - lr: 0.000018 - momentum: 0.000000 2024-11-27 20:32:22,357 epoch 133 - iter 2/9 - loss 0.00003070 - time (sec): 0.24 - samples/sec: 5823.36 - lr: 0.000017 - momentum: 0.000000 2024-11-27 20:32:22,497 epoch 133 - iter 3/9 - loss 0.00002927 - time (sec): 0.38 - samples/sec: 5321.75 - lr: 0.000017 - momentum: 0.000000 2024-11-27 20:32:22,714 epoch 133 - iter 4/9 - loss 0.00002765 - time (sec): 0.60 - samples/sec: 4233.75 - lr: 0.000017 - momentum: 0.000000 2024-11-27 20:32:22,854 epoch 133 - iter 5/9 - loss 0.00002848 - time (sec): 0.74 - samples/sec: 4156.26 - lr: 0.000017 - momentum: 0.000000 2024-11-27 20:32:22,992 epoch 133 - iter 6/9 - loss 0.00002730 - time (sec): 0.87 - samples/sec: 4060.57 - lr: 0.000017 - momentum: 0.000000 2024-11-27 20:32:23,134 epoch 133 - iter 7/9 - loss 0.00002713 - time (sec): 1.02 - samples/sec: 3948.74 - lr: 0.000017 - momentum: 0.000000 2024-11-27 20:32:23,302 epoch 133 - iter 8/9 - loss 0.00002662 - time (sec): 1.18 - samples/sec: 3848.57 - lr: 0.000017 - momentum: 0.000000 2024-11-27 20:32:23,464 epoch 133 - iter 9/9 - loss 0.00002699 - time (sec): 1.35 - samples/sec: 3858.58 - lr: 0.000017 - momentum: 0.000000 2024-11-27 20:32:23,464 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:32:23,464 EPOCH 133 done: loss 0.0000 - lr: 0.000017 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.19it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.18it/s] 2024-11-27 20:32:23,645 DEV : loss 3.5605456829071045 - f1-score (micro avg) 0.3506 2024-11-27 20:32:23,646 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:32:23,758 epoch 134 - iter 1/9 - loss 0.00003282 - time (sec): 0.11 - samples/sec: 5896.89 - lr: 0.000017 - momentum: 0.000000 2024-11-27 20:32:23,895 epoch 134 - iter 2/9 - loss 0.00003046 - time (sec): 0.25 - samples/sec: 4923.64 - lr: 0.000017 - momentum: 0.000000 2024-11-27 20:32:24,038 epoch 134 - iter 3/9 - loss 0.00002586 - time (sec): 0.39 - samples/sec: 4857.36 - lr: 0.000017 - momentum: 0.000000 2024-11-27 20:32:24,250 epoch 134 - iter 4/9 - loss 0.00005026 - time (sec): 0.60 - samples/sec: 4241.32 - lr: 0.000017 - momentum: 0.000000 2024-11-27 20:32:24,429 epoch 134 - iter 5/9 - loss 0.00004925 - time (sec): 0.78 - samples/sec: 3989.75 - lr: 0.000017 - momentum: 0.000000 2024-11-27 20:32:24,605 epoch 134 - iter 6/9 - loss 0.00004895 - time (sec): 0.96 - samples/sec: 3871.86 - lr: 0.000017 - momentum: 0.000000 2024-11-27 20:32:24,754 epoch 134 - iter 7/9 - loss 0.00004539 - time (sec): 1.11 - samples/sec: 3846.16 - lr: 0.000017 - momentum: 0.000000 2024-11-27 20:32:24,875 epoch 134 - iter 8/9 - loss 0.00004567 - time (sec): 1.23 - samples/sec: 3858.43 - lr: 0.000017 - momentum: 0.000000 2024-11-27 20:32:25,014 epoch 134 - iter 9/9 - loss 0.00004501 - time (sec): 1.37 - samples/sec: 3801.77 - lr: 0.000017 - momentum: 0.000000 2024-11-27 20:32:25,015 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:32:25,015 EPOCH 134 done: loss 0.0000 - lr: 0.000017 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.16it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.15it/s] 2024-11-27 20:32:25,196 DEV : loss 3.560642957687378 - f1-score (micro avg) 0.3506 2024-11-27 20:32:25,197 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:32:25,298 epoch 135 - iter 1/9 - loss 0.00002145 - time (sec): 0.10 - samples/sec: 5669.96 - lr: 0.000017 - momentum: 0.000000 2024-11-27 20:32:25,459 epoch 135 - iter 2/9 - loss 0.00003375 - time (sec): 0.26 - samples/sec: 4411.12 - lr: 0.000017 - momentum: 0.000000 2024-11-27 20:32:25,595 epoch 135 - iter 3/9 - loss 0.00002938 - time (sec): 0.40 - samples/sec: 4256.76 - lr: 0.000017 - momentum: 0.000000 2024-11-27 20:32:25,755 epoch 135 - iter 4/9 - loss 0.00002803 - time (sec): 0.56 - samples/sec: 4249.93 - lr: 0.000017 - momentum: 0.000000 2024-11-27 20:32:25,921 epoch 135 - iter 5/9 - loss 0.00002643 - time (sec): 0.72 - samples/sec: 4024.95 - lr: 0.000017 - momentum: 0.000000 2024-11-27 20:32:26,072 epoch 135 - iter 6/9 - loss 0.00002535 - time (sec): 0.87 - samples/sec: 3942.32 - lr: 0.000017 - momentum: 0.000000 2024-11-27 20:32:26,246 epoch 135 - iter 7/9 - loss 0.00002611 - time (sec): 1.05 - samples/sec: 3931.59 - lr: 0.000017 - momentum: 0.000000 2024-11-27 20:32:26,421 epoch 135 - iter 8/9 - loss 0.00002715 - time (sec): 1.22 - samples/sec: 3806.15 - lr: 0.000017 - momentum: 0.000000 2024-11-27 20:32:26,588 epoch 135 - iter 9/9 - loss 0.00002738 - time (sec): 1.39 - samples/sec: 3738.55 - lr: 0.000017 - momentum: 0.000000 2024-11-27 20:32:26,589 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:32:26,589 EPOCH 135 done: loss 0.0000 - lr: 0.000017 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.50it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.49it/s] 2024-11-27 20:32:26,762 DEV : loss 3.5639891624450684 - f1-score (micro avg) 0.3506 2024-11-27 20:32:26,763 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:32:26,862 epoch 136 - iter 1/9 - loss 0.00002451 - time (sec): 0.10 - samples/sec: 6123.25 - lr: 0.000017 - momentum: 0.000000 2024-11-27 20:32:27,004 epoch 136 - iter 2/9 - loss 0.00002854 - time (sec): 0.24 - samples/sec: 4870.84 - lr: 0.000017 - momentum: 0.000000 2024-11-27 20:32:27,162 epoch 136 - iter 3/9 - loss 0.00004236 - time (sec): 0.40 - samples/sec: 4753.24 - lr: 0.000017 - momentum: 0.000000 2024-11-27 20:32:27,304 epoch 136 - iter 4/9 - loss 0.00003808 - time (sec): 0.54 - samples/sec: 4350.12 - lr: 0.000017 - momentum: 0.000000 2024-11-27 20:32:27,444 epoch 136 - iter 5/9 - loss 0.00003581 - time (sec): 0.68 - samples/sec: 4225.44 - lr: 0.000017 - momentum: 0.000000 2024-11-27 20:32:27,592 epoch 136 - iter 6/9 - loss 0.00003315 - time (sec): 0.83 - samples/sec: 4219.31 - lr: 0.000017 - momentum: 0.000000 2024-11-27 20:32:27,780 epoch 136 - iter 7/9 - loss 0.00003331 - time (sec): 1.02 - samples/sec: 3974.45 - lr: 0.000017 - momentum: 0.000000 2024-11-27 20:32:27,938 epoch 136 - iter 8/9 - loss 0.00003579 - time (sec): 1.17 - samples/sec: 3966.69 - lr: 0.000017 - momentum: 0.000000 2024-11-27 20:32:28,056 epoch 136 - iter 9/9 - loss 0.00003427 - time (sec): 1.29 - samples/sec: 4023.05 - lr: 0.000017 - momentum: 0.000000 2024-11-27 20:32:28,056 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:32:28,056 EPOCH 136 done: loss 0.0000 - lr: 0.000017 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.61it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.60it/s] 2024-11-27 20:32:28,227 DEV : loss 3.56695556640625 - f1-score (micro avg) 0.3484 2024-11-27 20:32:28,228 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:32:28,327 epoch 137 - iter 1/9 - loss 0.00002614 - time (sec): 0.10 - samples/sec: 7023.13 - lr: 0.000017 - momentum: 0.000000 2024-11-27 20:32:28,503 epoch 137 - iter 2/9 - loss 0.00003082 - time (sec): 0.27 - samples/sec: 4192.86 - lr: 0.000017 - momentum: 0.000000 2024-11-27 20:32:28,649 epoch 137 - iter 3/9 - loss 0.00002465 - time (sec): 0.42 - samples/sec: 4310.12 - lr: 0.000017 - momentum: 0.000000 2024-11-27 20:32:28,829 epoch 137 - iter 4/9 - loss 0.00003021 - time (sec): 0.60 - samples/sec: 4114.03 - lr: 0.000017 - momentum: 0.000000 2024-11-27 20:32:28,986 epoch 137 - iter 5/9 - loss 0.00002919 - time (sec): 0.76 - samples/sec: 4010.54 - lr: 0.000017 - momentum: 0.000000 2024-11-27 20:32:29,291 epoch 137 - iter 6/9 - loss 0.00003286 - time (sec): 1.06 - samples/sec: 3356.41 - lr: 0.000017 - momentum: 0.000000 2024-11-27 20:32:29,439 epoch 137 - iter 7/9 - loss 0.00003085 - time (sec): 1.21 - samples/sec: 3476.70 - lr: 0.000017 - momentum: 0.000000 2024-11-27 20:32:29,570 epoch 137 - iter 8/9 - loss 0.00003114 - time (sec): 1.34 - samples/sec: 3522.50 - lr: 0.000017 - momentum: 0.000000 2024-11-27 20:32:29,701 epoch 137 - iter 9/9 - loss 0.00002967 - time (sec): 1.47 - samples/sec: 3530.21 - lr: 0.000017 - momentum: 0.000000 2024-11-27 20:32:29,701 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:32:29,702 EPOCH 137 done: loss 0.0000 - lr: 0.000017 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 5.78it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 5.77it/s] 2024-11-27 20:32:29,894 DEV : loss 3.571380376815796 - f1-score (micro avg) 0.3484 2024-11-27 20:32:29,895 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:32:30,002 epoch 138 - iter 1/9 - loss 0.00003319 - time (sec): 0.11 - samples/sec: 6140.85 - lr: 0.000016 - momentum: 0.000000 2024-11-27 20:32:30,146 epoch 138 - iter 2/9 - loss 0.00003499 - time (sec): 0.25 - samples/sec: 4803.87 - lr: 0.000016 - momentum: 0.000000 2024-11-27 20:32:30,381 epoch 138 - iter 3/9 - loss 0.00003764 - time (sec): 0.48 - samples/sec: 3622.22 - lr: 0.000016 - momentum: 0.000000 2024-11-27 20:32:30,599 epoch 138 - iter 4/9 - loss 0.00003506 - time (sec): 0.70 - samples/sec: 3301.78 - lr: 0.000016 - momentum: 0.000000 2024-11-27 20:32:30,718 epoch 138 - iter 5/9 - loss 0.00003097 - time (sec): 0.82 - samples/sec: 3567.04 - lr: 0.000016 - momentum: 0.000000 2024-11-27 20:32:30,846 epoch 138 - iter 6/9 - loss 0.00002982 - time (sec): 0.95 - samples/sec: 3620.53 - lr: 0.000016 - momentum: 0.000000 2024-11-27 20:32:30,995 epoch 138 - iter 7/9 - loss 0.00003397 - time (sec): 1.10 - samples/sec: 3714.77 - lr: 0.000016 - momentum: 0.000000 2024-11-27 20:32:31,147 epoch 138 - iter 8/9 - loss 0.00003261 - time (sec): 1.25 - samples/sec: 3750.70 - lr: 0.000016 - momentum: 0.000000 2024-11-27 20:32:31,292 epoch 138 - iter 9/9 - loss 0.00003456 - time (sec): 1.40 - samples/sec: 3724.29 - lr: 0.000016 - momentum: 0.000000 2024-11-27 20:32:31,292 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:32:31,292 EPOCH 138 done: loss 0.0000 - lr: 0.000016 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.51it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.50it/s] 2024-11-27 20:32:31,465 DEV : loss 3.5762810707092285 - f1-score (micro avg) 0.3484 2024-11-27 20:32:31,467 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:32:31,576 epoch 139 - iter 1/9 - loss 0.00004016 - time (sec): 0.11 - samples/sec: 6831.02 - lr: 0.000016 - momentum: 0.000000 2024-11-27 20:32:31,727 epoch 139 - iter 2/9 - loss 0.00003491 - time (sec): 0.26 - samples/sec: 5284.58 - lr: 0.000016 - momentum: 0.000000 2024-11-27 20:32:31,866 epoch 139 - iter 3/9 - loss 0.00002984 - time (sec): 0.40 - samples/sec: 4749.10 - lr: 0.000016 - momentum: 0.000000 2024-11-27 20:32:32,094 epoch 139 - iter 4/9 - loss 0.00003170 - time (sec): 0.63 - samples/sec: 3801.26 - lr: 0.000016 - momentum: 0.000000 2024-11-27 20:32:32,232 epoch 139 - iter 5/9 - loss 0.00002983 - time (sec): 0.76 - samples/sec: 3948.65 - lr: 0.000016 - momentum: 0.000000 2024-11-27 20:32:32,359 epoch 139 - iter 6/9 - loss 0.00002952 - time (sec): 0.89 - samples/sec: 3916.43 - lr: 0.000016 - momentum: 0.000000 2024-11-27 20:32:32,498 epoch 139 - iter 7/9 - loss 0.00002923 - time (sec): 1.03 - samples/sec: 3983.16 - lr: 0.000016 - momentum: 0.000000 2024-11-27 20:32:32,817 epoch 139 - iter 8/9 - loss 0.00002924 - time (sec): 1.35 - samples/sec: 3516.48 - lr: 0.000016 - momentum: 0.000000 2024-11-27 20:32:32,967 epoch 139 - iter 9/9 - loss 0.00003007 - time (sec): 1.50 - samples/sec: 3466.41 - lr: 0.000016 - momentum: 0.000000 2024-11-27 20:32:32,967 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:32:32,967 EPOCH 139 done: loss 0.0000 - lr: 0.000016 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.09it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.08it/s] 2024-11-27 20:32:33,151 DEV : loss 3.585078477859497 - f1-score (micro avg) 0.3613 2024-11-27 20:32:33,153 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:32:33,276 epoch 140 - iter 1/9 - loss 0.00002414 - time (sec): 0.12 - samples/sec: 5549.95 - lr: 0.000016 - momentum: 0.000000 2024-11-27 20:32:33,446 epoch 140 - iter 2/9 - loss 0.00002985 - time (sec): 0.29 - samples/sec: 4277.54 - lr: 0.000016 - momentum: 0.000000 2024-11-27 20:32:33,607 epoch 140 - iter 3/9 - loss 0.00002763 - time (sec): 0.45 - samples/sec: 3995.78 - lr: 0.000016 - momentum: 0.000000 2024-11-27 20:32:33,784 epoch 140 - iter 4/9 - loss 0.00002381 - time (sec): 0.63 - samples/sec: 3923.42 - lr: 0.000016 - momentum: 0.000000 2024-11-27 20:32:33,944 epoch 140 - iter 5/9 - loss 0.00002555 - time (sec): 0.79 - samples/sec: 3891.86 - lr: 0.000016 - momentum: 0.000000 2024-11-27 20:32:34,088 epoch 140 - iter 6/9 - loss 0.00002407 - time (sec): 0.93 - samples/sec: 3773.43 - lr: 0.000016 - momentum: 0.000000 2024-11-27 20:32:34,232 epoch 140 - iter 7/9 - loss 0.00002918 - time (sec): 1.08 - samples/sec: 3814.90 - lr: 0.000016 - momentum: 0.000000 2024-11-27 20:32:34,371 epoch 140 - iter 8/9 - loss 0.00002876 - time (sec): 1.22 - samples/sec: 3772.25 - lr: 0.000016 - momentum: 0.000000 2024-11-27 20:32:34,527 epoch 140 - iter 9/9 - loss 0.00002858 - time (sec): 1.37 - samples/sec: 3784.89 - lr: 0.000016 - momentum: 0.000000 2024-11-27 20:32:34,527 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:32:34,527 EPOCH 140 done: loss 0.0000 - lr: 0.000016 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 5.65it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 5.64it/s] 2024-11-27 20:32:34,724 DEV : loss 3.593827962875366 - f1-score (micro avg) 0.3613 2024-11-27 20:32:34,725 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:32:34,830 epoch 141 - iter 1/9 - loss 0.00002784 - time (sec): 0.10 - samples/sec: 6349.11 - lr: 0.000016 - momentum: 0.000000 2024-11-27 20:32:34,972 epoch 141 - iter 2/9 - loss 0.00002310 - time (sec): 0.25 - samples/sec: 4939.30 - lr: 0.000016 - momentum: 0.000000 2024-11-27 20:32:35,118 epoch 141 - iter 3/9 - loss 0.00003800 - time (sec): 0.39 - samples/sec: 4750.75 - lr: 0.000016 - momentum: 0.000000 2024-11-27 20:32:35,269 epoch 141 - iter 4/9 - loss 0.00003282 - time (sec): 0.54 - samples/sec: 4557.56 - lr: 0.000016 - momentum: 0.000000 2024-11-27 20:32:35,439 epoch 141 - iter 5/9 - loss 0.00003796 - time (sec): 0.71 - samples/sec: 4334.85 - lr: 0.000016 - momentum: 0.000000 2024-11-27 20:32:35,650 epoch 141 - iter 6/9 - loss 0.00003750 - time (sec): 0.92 - samples/sec: 3881.90 - lr: 0.000016 - momentum: 0.000000 2024-11-27 20:32:35,781 epoch 141 - iter 7/9 - loss 0.00003566 - time (sec): 1.05 - samples/sec: 3835.26 - lr: 0.000016 - momentum: 0.000000 2024-11-27 20:32:35,923 epoch 141 - iter 8/9 - loss 0.00003470 - time (sec): 1.20 - samples/sec: 3929.82 - lr: 0.000016 - momentum: 0.000000 2024-11-27 20:32:36,054 epoch 141 - iter 9/9 - loss 0.00003315 - time (sec): 1.33 - samples/sec: 3913.20 - lr: 0.000016 - momentum: 0.000000 2024-11-27 20:32:36,054 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:32:36,054 EPOCH 141 done: loss 0.0000 - lr: 0.000016 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.10it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.09it/s] 2024-11-27 20:32:36,238 DEV : loss 3.6019721031188965 - f1-score (micro avg) 0.3636 2024-11-27 20:32:36,239 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:32:36,338 epoch 142 - iter 1/9 - loss 0.00001579 - time (sec): 0.10 - samples/sec: 5560.01 - lr: 0.000016 - momentum: 0.000000 2024-11-27 20:32:36,467 epoch 142 - iter 2/9 - loss 0.00001732 - time (sec): 0.23 - samples/sec: 5249.98 - lr: 0.000016 - momentum: 0.000000 2024-11-27 20:32:36,619 epoch 142 - iter 3/9 - loss 0.00001837 - time (sec): 0.38 - samples/sec: 4922.94 - lr: 0.000016 - momentum: 0.000000 2024-11-27 20:32:36,771 epoch 142 - iter 4/9 - loss 0.00002612 - time (sec): 0.53 - samples/sec: 4621.66 - lr: 0.000016 - momentum: 0.000000 2024-11-27 20:32:36,883 epoch 142 - iter 5/9 - loss 0.00002632 - time (sec): 0.64 - samples/sec: 4670.67 - lr: 0.000016 - momentum: 0.000000 2024-11-27 20:32:37,035 epoch 142 - iter 6/9 - loss 0.00002702 - time (sec): 0.80 - samples/sec: 4477.03 - lr: 0.000016 - momentum: 0.000000 2024-11-27 20:32:37,242 epoch 142 - iter 7/9 - loss 0.00003197 - time (sec): 1.00 - samples/sec: 4126.54 - lr: 0.000016 - momentum: 0.000000 2024-11-27 20:32:37,438 epoch 142 - iter 8/9 - loss 0.00003155 - time (sec): 1.20 - samples/sec: 3889.42 - lr: 0.000016 - momentum: 0.000000 2024-11-27 20:32:37,581 epoch 142 - iter 9/9 - loss 0.00003003 - time (sec): 1.34 - samples/sec: 3874.60 - lr: 0.000015 - momentum: 0.000000 2024-11-27 20:32:37,581 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:32:37,581 EPOCH 142 done: loss 0.0000 - lr: 0.000015 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.27it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.26it/s] 2024-11-27 20:32:37,760 DEV : loss 3.608346462249756 - f1-score (micro avg) 0.3636 2024-11-27 20:32:37,761 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:32:37,862 epoch 143 - iter 1/9 - loss 0.00001582 - time (sec): 0.10 - samples/sec: 6097.01 - lr: 0.000015 - momentum: 0.000000 2024-11-27 20:32:38,001 epoch 143 - iter 2/9 - loss 0.00003251 - time (sec): 0.24 - samples/sec: 5122.78 - lr: 0.000015 - momentum: 0.000000 2024-11-27 20:32:38,176 epoch 143 - iter 3/9 - loss 0.00002832 - time (sec): 0.41 - samples/sec: 4701.88 - lr: 0.000015 - momentum: 0.000000 2024-11-27 20:32:38,329 epoch 143 - iter 4/9 - loss 0.00003358 - time (sec): 0.57 - samples/sec: 4385.55 - lr: 0.000015 - momentum: 0.000000 2024-11-27 20:32:38,483 epoch 143 - iter 5/9 - loss 0.00003087 - time (sec): 0.72 - samples/sec: 4218.75 - lr: 0.000015 - momentum: 0.000000 2024-11-27 20:32:38,678 epoch 143 - iter 6/9 - loss 0.00003033 - time (sec): 0.92 - samples/sec: 3850.07 - lr: 0.000015 - momentum: 0.000000 2024-11-27 20:32:38,819 epoch 143 - iter 7/9 - loss 0.00002872 - time (sec): 1.06 - samples/sec: 3823.46 - lr: 0.000015 - momentum: 0.000000 2024-11-27 20:32:38,965 epoch 143 - iter 8/9 - loss 0.00002747 - time (sec): 1.20 - samples/sec: 3904.14 - lr: 0.000015 - momentum: 0.000000 2024-11-27 20:32:39,124 epoch 143 - iter 9/9 - loss 0.00002637 - time (sec): 1.36 - samples/sec: 3815.02 - lr: 0.000015 - momentum: 0.000000 2024-11-27 20:32:39,125 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:32:39,125 EPOCH 143 done: loss 0.0000 - lr: 0.000015 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 5.67it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 5.66it/s] 2024-11-27 20:32:39,321 DEV : loss 3.6145875453948975 - f1-score (micro avg) 0.3636 2024-11-27 20:32:39,322 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:32:39,421 epoch 144 - iter 1/9 - loss 0.00005235 - time (sec): 0.10 - samples/sec: 6570.20 - lr: 0.000015 - momentum: 0.000000 2024-11-27 20:32:39,561 epoch 144 - iter 2/9 - loss 0.00003551 - time (sec): 0.24 - samples/sec: 4801.67 - lr: 0.000015 - momentum: 0.000000 2024-11-27 20:32:39,703 epoch 144 - iter 3/9 - loss 0.00003055 - time (sec): 0.38 - samples/sec: 4821.00 - lr: 0.000015 - momentum: 0.000000 2024-11-27 20:32:39,868 epoch 144 - iter 4/9 - loss 0.00003001 - time (sec): 0.54 - samples/sec: 4426.73 - lr: 0.000015 - momentum: 0.000000 2024-11-27 20:32:40,122 epoch 144 - iter 5/9 - loss 0.00034028 - time (sec): 0.80 - samples/sec: 3739.63 - lr: 0.000015 - momentum: 0.000000 2024-11-27 20:32:40,284 epoch 144 - iter 6/9 - loss 0.00028662 - time (sec): 0.96 - samples/sec: 3758.04 - lr: 0.000015 - momentum: 0.000000 2024-11-27 20:32:40,440 epoch 144 - iter 7/9 - loss 0.00025110 - time (sec): 1.12 - samples/sec: 3747.84 - lr: 0.000015 - momentum: 0.000000 2024-11-27 20:32:40,596 epoch 144 - iter 8/9 - loss 0.00022402 - time (sec): 1.27 - samples/sec: 3718.42 - lr: 0.000015 - momentum: 0.000000 2024-11-27 20:32:40,748 epoch 144 - iter 9/9 - loss 0.00020774 - time (sec): 1.43 - samples/sec: 3646.49 - lr: 0.000015 - momentum: 0.000000 2024-11-27 20:32:40,748 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:32:40,748 EPOCH 144 done: loss 0.0002 - lr: 0.000015 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 4.58it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 4.58it/s] 2024-11-27 20:32:40,986 DEV : loss 3.6229591369628906 - f1-score (micro avg) 0.3613 2024-11-27 20:32:40,987 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:32:41,081 epoch 145 - iter 1/9 - loss 0.00005402 - time (sec): 0.09 - samples/sec: 5581.35 - lr: 0.000015 - momentum: 0.000000 2024-11-27 20:32:41,219 epoch 145 - iter 2/9 - loss 0.00004423 - time (sec): 0.23 - samples/sec: 5097.65 - lr: 0.000015 - momentum: 0.000000 2024-11-27 20:32:41,353 epoch 145 - iter 3/9 - loss 0.00005137 - time (sec): 0.36 - samples/sec: 4629.86 - lr: 0.000015 - momentum: 0.000000 2024-11-27 20:32:41,544 epoch 145 - iter 4/9 - loss 0.00004470 - time (sec): 0.56 - samples/sec: 4113.86 - lr: 0.000015 - momentum: 0.000000 2024-11-27 20:32:41,684 epoch 145 - iter 5/9 - loss 0.00004049 - time (sec): 0.70 - samples/sec: 4062.41 - lr: 0.000015 - momentum: 0.000000 2024-11-27 20:32:41,841 epoch 145 - iter 6/9 - loss 0.00003852 - time (sec): 0.85 - samples/sec: 4025.38 - lr: 0.000015 - momentum: 0.000000 2024-11-27 20:32:41,989 epoch 145 - iter 7/9 - loss 0.00003724 - time (sec): 1.00 - samples/sec: 3852.26 - lr: 0.000015 - momentum: 0.000000 2024-11-27 20:32:42,151 epoch 145 - iter 8/9 - loss 0.00060644 - time (sec): 1.16 - samples/sec: 3902.24 - lr: 0.000015 - momentum: 0.000000 2024-11-27 20:32:42,304 epoch 145 - iter 9/9 - loss 0.00053185 - time (sec): 1.32 - samples/sec: 3948.38 - lr: 0.000015 - momentum: 0.000000 2024-11-27 20:32:42,305 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:32:42,305 EPOCH 145 done: loss 0.0005 - lr: 0.000015 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 2.91it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 2.91it/s] 2024-11-27 20:32:42,668 DEV : loss 3.6278371810913086 - f1-score (micro avg) 0.3636 2024-11-27 20:32:42,669 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:32:42,778 epoch 146 - iter 1/9 - loss 0.00004007 - time (sec): 0.11 - samples/sec: 7128.05 - lr: 0.000015 - momentum: 0.000000 2024-11-27 20:32:42,914 epoch 146 - iter 2/9 - loss 0.00002987 - time (sec): 0.24 - samples/sec: 5159.46 - lr: 0.000015 - momentum: 0.000000 2024-11-27 20:32:43,050 epoch 146 - iter 3/9 - loss 0.00002567 - time (sec): 0.38 - samples/sec: 4898.61 - lr: 0.000015 - momentum: 0.000000 2024-11-27 20:32:43,199 epoch 146 - iter 4/9 - loss 0.00002249 - time (sec): 0.53 - samples/sec: 4574.56 - lr: 0.000015 - momentum: 0.000000 2024-11-27 20:32:43,409 epoch 146 - iter 5/9 - loss 0.00002884 - time (sec): 0.74 - samples/sec: 4219.00 - lr: 0.000015 - momentum: 0.000000 2024-11-27 20:32:43,604 epoch 146 - iter 6/9 - loss 0.00002799 - time (sec): 0.93 - samples/sec: 3944.87 - lr: 0.000015 - momentum: 0.000000 2024-11-27 20:32:43,751 epoch 146 - iter 7/9 - loss 0.00002774 - time (sec): 1.08 - samples/sec: 3912.07 - lr: 0.000015 - momentum: 0.000000 2024-11-27 20:32:43,897 epoch 146 - iter 8/9 - loss 0.00002840 - time (sec): 1.23 - samples/sec: 3844.87 - lr: 0.000015 - momentum: 0.000000 2024-11-27 20:32:44,038 epoch 146 - iter 9/9 - loss 0.00002928 - time (sec): 1.37 - samples/sec: 3798.94 - lr: 0.000015 - momentum: 0.000000 2024-11-27 20:32:44,039 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:32:44,039 EPOCH 146 done: loss 0.0000 - lr: 0.000015 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.26it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.24it/s] 2024-11-27 20:32:44,219 DEV : loss 3.632225275039673 - f1-score (micro avg) 0.3766 2024-11-27 20:32:44,220 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:32:44,320 epoch 147 - iter 1/9 - loss 0.00002855 - time (sec): 0.10 - samples/sec: 5428.46 - lr: 0.000015 - momentum: 0.000000 2024-11-27 20:32:44,468 epoch 147 - iter 2/9 - loss 0.00002049 - time (sec): 0.25 - samples/sec: 4674.71 - lr: 0.000015 - momentum: 0.000000 2024-11-27 20:32:44,660 epoch 147 - iter 3/9 - loss 0.00002231 - time (sec): 0.44 - samples/sec: 4071.24 - lr: 0.000015 - momentum: 0.000000 2024-11-27 20:32:44,900 epoch 147 - iter 4/9 - loss 0.00002046 - time (sec): 0.68 - samples/sec: 3360.90 - lr: 0.000015 - momentum: 0.000000 2024-11-27 20:32:45,028 epoch 147 - iter 5/9 - loss 0.00002225 - time (sec): 0.81 - samples/sec: 3448.66 - lr: 0.000015 - momentum: 0.000000 2024-11-27 20:32:45,157 epoch 147 - iter 6/9 - loss 0.00002203 - time (sec): 0.94 - samples/sec: 3559.42 - lr: 0.000015 - momentum: 0.000000 2024-11-27 20:32:45,293 epoch 147 - iter 7/9 - loss 0.00002154 - time (sec): 1.07 - samples/sec: 3654.53 - lr: 0.000015 - momentum: 0.000000 2024-11-27 20:32:45,434 epoch 147 - iter 8/9 - loss 0.00002267 - time (sec): 1.21 - samples/sec: 3782.10 - lr: 0.000014 - momentum: 0.000000 2024-11-27 20:32:45,659 epoch 147 - iter 9/9 - loss 0.00002178 - time (sec): 1.44 - samples/sec: 3613.52 - lr: 0.000014 - momentum: 0.000000 2024-11-27 20:32:45,659 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:32:45,659 EPOCH 147 done: loss 0.0000 - lr: 0.000014 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.24it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.23it/s] 2024-11-27 20:32:45,839 DEV : loss 3.6362242698669434 - f1-score (micro avg) 0.3742 2024-11-27 20:32:45,840 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:32:45,942 epoch 148 - iter 1/9 - loss 0.00000982 - time (sec): 0.10 - samples/sec: 6028.03 - lr: 0.000014 - momentum: 0.000000 2024-11-27 20:32:46,075 epoch 148 - iter 2/9 - loss 0.00001531 - time (sec): 0.23 - samples/sec: 4891.08 - lr: 0.000014 - momentum: 0.000000 2024-11-27 20:32:46,215 epoch 148 - iter 3/9 - loss 0.00002090 - time (sec): 0.37 - samples/sec: 4559.85 - lr: 0.000014 - momentum: 0.000000 2024-11-27 20:32:46,348 epoch 148 - iter 4/9 - loss 0.00002333 - time (sec): 0.51 - samples/sec: 4379.00 - lr: 0.000014 - momentum: 0.000000 2024-11-27 20:32:46,493 epoch 148 - iter 5/9 - loss 0.00002368 - time (sec): 0.65 - samples/sec: 4231.38 - lr: 0.000014 - momentum: 0.000000 2024-11-27 20:32:46,640 epoch 148 - iter 6/9 - loss 0.00002664 - time (sec): 0.80 - samples/sec: 4166.72 - lr: 0.000014 - momentum: 0.000000 2024-11-27 20:32:46,800 epoch 148 - iter 7/9 - loss 0.00002737 - time (sec): 0.96 - samples/sec: 4195.98 - lr: 0.000014 - momentum: 0.000000 2024-11-27 20:32:46,982 epoch 148 - iter 8/9 - loss 0.00002986 - time (sec): 1.14 - samples/sec: 4218.11 - lr: 0.000014 - momentum: 0.000000 2024-11-27 20:32:47,130 epoch 148 - iter 9/9 - loss 0.00003182 - time (sec): 1.29 - samples/sec: 4032.16 - lr: 0.000014 - momentum: 0.000000 2024-11-27 20:32:47,131 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:32:47,131 EPOCH 148 done: loss 0.0000 - lr: 0.000014 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.92it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.91it/s] 2024-11-27 20:32:47,294 DEV : loss 3.637704610824585 - f1-score (micro avg) 0.3742 2024-11-27 20:32:47,295 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:32:47,393 epoch 149 - iter 1/9 - loss 0.00002418 - time (sec): 0.10 - samples/sec: 6095.43 - lr: 0.000014 - momentum: 0.000000 2024-11-27 20:32:47,535 epoch 149 - iter 2/9 - loss 0.00003465 - time (sec): 0.24 - samples/sec: 5126.53 - lr: 0.000014 - momentum: 0.000000 2024-11-27 20:32:47,669 epoch 149 - iter 3/9 - loss 0.00003799 - time (sec): 0.37 - samples/sec: 4793.81 - lr: 0.000014 - momentum: 0.000000 2024-11-27 20:32:47,817 epoch 149 - iter 4/9 - loss 0.00003416 - time (sec): 0.52 - samples/sec: 4731.38 - lr: 0.000014 - momentum: 0.000000 2024-11-27 20:32:47,943 epoch 149 - iter 5/9 - loss 0.00003860 - time (sec): 0.65 - samples/sec: 4617.23 - lr: 0.000014 - momentum: 0.000000 2024-11-27 20:32:48,058 epoch 149 - iter 6/9 - loss 0.00003898 - time (sec): 0.76 - samples/sec: 4641.79 - lr: 0.000014 - momentum: 0.000000 2024-11-27 20:32:48,222 epoch 149 - iter 7/9 - loss 0.00336258 - time (sec): 0.93 - samples/sec: 4584.70 - lr: 0.000014 - momentum: 0.000000 2024-11-27 20:32:48,368 epoch 149 - iter 8/9 - loss 0.00299165 - time (sec): 1.07 - samples/sec: 4458.38 - lr: 0.000014 - momentum: 0.000000 2024-11-27 20:32:48,507 epoch 149 - iter 9/9 - loss 0.00275220 - time (sec): 1.21 - samples/sec: 4295.10 - lr: 0.000014 - momentum: 0.000000 2024-11-27 20:32:48,507 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:32:48,507 EPOCH 149 done: loss 0.0028 - lr: 0.000014 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 3.73it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 3.73it/s] 2024-11-27 20:32:48,794 DEV : loss 3.634815216064453 - f1-score (micro avg) 0.3694 2024-11-27 20:32:48,795 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:32:48,914 epoch 150 - iter 1/9 - loss 0.00002613 - time (sec): 0.12 - samples/sec: 5671.55 - lr: 0.000014 - momentum: 0.000000 2024-11-27 20:32:49,073 epoch 150 - iter 2/9 - loss 0.00002653 - time (sec): 0.28 - samples/sec: 4539.97 - lr: 0.000014 - momentum: 0.000000 2024-11-27 20:32:49,241 epoch 150 - iter 3/9 - loss 0.00002683 - time (sec): 0.44 - samples/sec: 4381.67 - lr: 0.000014 - momentum: 0.000000 2024-11-27 20:32:49,408 epoch 150 - iter 4/9 - loss 0.00002512 - time (sec): 0.61 - samples/sec: 4046.26 - lr: 0.000014 - momentum: 0.000000 2024-11-27 20:32:49,558 epoch 150 - iter 5/9 - loss 0.00002392 - time (sec): 0.76 - samples/sec: 4023.73 - lr: 0.000014 - momentum: 0.000000 2024-11-27 20:32:49,727 epoch 150 - iter 6/9 - loss 0.00003199 - time (sec): 0.93 - samples/sec: 3939.39 - lr: 0.000014 - momentum: 0.000000 2024-11-27 20:32:49,890 epoch 150 - iter 7/9 - loss 0.00003104 - time (sec): 1.09 - samples/sec: 3914.77 - lr: 0.000014 - momentum: 0.000000 2024-11-27 20:32:50,043 epoch 150 - iter 8/9 - loss 0.00003093 - time (sec): 1.25 - samples/sec: 3740.71 - lr: 0.000014 - momentum: 0.000000 2024-11-27 20:32:50,183 epoch 150 - iter 9/9 - loss 0.00002901 - time (sec): 1.39 - samples/sec: 3748.41 - lr: 0.000014 - momentum: 0.000000 2024-11-27 20:32:50,183 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:32:50,183 EPOCH 150 done: loss 0.0000 - lr: 0.000014 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.65it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.63it/s] 2024-11-27 20:32:50,354 DEV : loss 3.6325976848602295 - f1-score (micro avg) 0.3671 2024-11-27 20:32:50,356 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:32:50,449 epoch 151 - iter 1/9 - loss 0.00002614 - time (sec): 0.09 - samples/sec: 4869.73 - lr: 0.000014 - momentum: 0.000000 2024-11-27 20:32:50,603 epoch 151 - iter 2/9 - loss 0.00003205 - time (sec): 0.25 - samples/sec: 4070.08 - lr: 0.000014 - momentum: 0.000000 2024-11-27 20:32:50,759 epoch 151 - iter 3/9 - loss 0.00003646 - time (sec): 0.40 - samples/sec: 3941.96 - lr: 0.000014 - momentum: 0.000000 2024-11-27 20:32:50,965 epoch 151 - iter 4/9 - loss 0.00003178 - time (sec): 0.61 - samples/sec: 3613.54 - lr: 0.000014 - momentum: 0.000000 2024-11-27 20:32:51,114 epoch 151 - iter 5/9 - loss 0.00004171 - time (sec): 0.76 - samples/sec: 3668.53 - lr: 0.000014 - momentum: 0.000000 2024-11-27 20:32:51,273 epoch 151 - iter 6/9 - loss 0.00003948 - time (sec): 0.92 - samples/sec: 3671.68 - lr: 0.000014 - momentum: 0.000000 2024-11-27 20:32:51,434 epoch 151 - iter 7/9 - loss 0.00003484 - time (sec): 1.08 - samples/sec: 3735.77 - lr: 0.000014 - momentum: 0.000000 2024-11-27 20:32:51,576 epoch 151 - iter 8/9 - loss 0.00003855 - time (sec): 1.22 - samples/sec: 3783.10 - lr: 0.000014 - momentum: 0.000000 2024-11-27 20:32:51,743 epoch 151 - iter 9/9 - loss 0.00003915 - time (sec): 1.39 - samples/sec: 3750.03 - lr: 0.000014 - momentum: 0.000000 2024-11-27 20:32:51,743 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:32:51,743 EPOCH 151 done: loss 0.0000 - lr: 0.000014 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 3.36it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 3.35it/s] 2024-11-27 20:32:52,060 DEV : loss 3.63378643989563 - f1-score (micro avg) 0.3671 2024-11-27 20:32:52,061 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:32:52,375 epoch 152 - iter 1/9 - loss 0.00002760 - time (sec): 0.31 - samples/sec: 1891.29 - lr: 0.000014 - momentum: 0.000000 2024-11-27 20:32:52,514 epoch 152 - iter 2/9 - loss 0.00002179 - time (sec): 0.45 - samples/sec: 2658.86 - lr: 0.000014 - momentum: 0.000000 2024-11-27 20:32:52,662 epoch 152 - iter 3/9 - loss 0.00002194 - time (sec): 0.60 - samples/sec: 3059.48 - lr: 0.000014 - momentum: 0.000000 2024-11-27 20:32:52,814 epoch 152 - iter 4/9 - loss 0.00002200 - time (sec): 0.75 - samples/sec: 3185.80 - lr: 0.000014 - momentum: 0.000000 2024-11-27 20:32:52,960 epoch 152 - iter 5/9 - loss 0.00002147 - time (sec): 0.90 - samples/sec: 3273.09 - lr: 0.000014 - momentum: 0.000000 2024-11-27 20:32:53,251 epoch 152 - iter 6/9 - loss 0.00203506 - time (sec): 1.19 - samples/sec: 3053.03 - lr: 0.000014 - momentum: 0.000000 2024-11-27 20:32:53,379 epoch 152 - iter 7/9 - loss 0.00179231 - time (sec): 1.32 - samples/sec: 3134.99 - lr: 0.000013 - momentum: 0.000000 2024-11-27 20:32:53,509 epoch 152 - iter 8/9 - loss 0.00157833 - time (sec): 1.45 - samples/sec: 3247.31 - lr: 0.000013 - momentum: 0.000000 2024-11-27 20:32:53,652 epoch 152 - iter 9/9 - loss 0.00143028 - time (sec): 1.59 - samples/sec: 3269.68 - lr: 0.000013 - momentum: 0.000000 2024-11-27 20:32:53,652 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:32:53,652 EPOCH 152 done: loss 0.0014 - lr: 0.000013 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 4.73it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 4.72it/s] 2024-11-27 20:32:53,883 DEV : loss 3.6300904750823975 - f1-score (micro avg) 0.3694 2024-11-27 20:32:53,884 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:32:53,979 epoch 153 - iter 1/9 - loss 0.02443702 - time (sec): 0.09 - samples/sec: 5553.58 - lr: 0.000013 - momentum: 0.000000 2024-11-27 20:32:54,127 epoch 153 - iter 2/9 - loss 0.01138142 - time (sec): 0.24 - samples/sec: 4623.88 - lr: 0.000013 - momentum: 0.000000 2024-11-27 20:32:54,289 epoch 153 - iter 3/9 - loss 0.00773943 - time (sec): 0.40 - samples/sec: 4068.25 - lr: 0.000013 - momentum: 0.000000 2024-11-27 20:32:54,440 epoch 153 - iter 4/9 - loss 0.00561922 - time (sec): 0.55 - samples/sec: 4078.96 - lr: 0.000013 - momentum: 0.000000 2024-11-27 20:32:54,607 epoch 153 - iter 5/9 - loss 0.00445150 - time (sec): 0.72 - samples/sec: 3959.10 - lr: 0.000013 - momentum: 0.000000 2024-11-27 20:32:54,943 epoch 153 - iter 6/9 - loss 0.00381451 - time (sec): 1.06 - samples/sec: 3157.00 - lr: 0.000013 - momentum: 0.000000 2024-11-27 20:32:55,079 epoch 153 - iter 7/9 - loss 0.00315109 - time (sec): 1.19 - samples/sec: 3391.37 - lr: 0.000013 - momentum: 0.000000 2024-11-27 20:32:55,209 epoch 153 - iter 8/9 - loss 0.00282795 - time (sec): 1.32 - samples/sec: 3409.27 - lr: 0.000013 - momentum: 0.000000 2024-11-27 20:32:55,360 epoch 153 - iter 9/9 - loss 0.00245783 - time (sec): 1.47 - samples/sec: 3523.80 - lr: 0.000013 - momentum: 0.000000 2024-11-27 20:32:55,361 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:32:55,361 EPOCH 153 done: loss 0.0025 - lr: 0.000013 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 5.24it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 5.23it/s] 2024-11-27 20:32:55,571 DEV : loss 3.634286642074585 - f1-score (micro avg) 0.3766 2024-11-27 20:32:55,572 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:32:55,680 epoch 154 - iter 1/9 - loss 0.00003671 - time (sec): 0.11 - samples/sec: 5794.21 - lr: 0.000013 - momentum: 0.000000 2024-11-27 20:32:55,813 epoch 154 - iter 2/9 - loss 0.00002749 - time (sec): 0.24 - samples/sec: 4459.85 - lr: 0.000013 - momentum: 0.000000 2024-11-27 20:32:55,968 epoch 154 - iter 3/9 - loss 0.00003299 - time (sec): 0.39 - samples/sec: 4137.95 - lr: 0.000013 - momentum: 0.000000 2024-11-27 20:32:56,130 epoch 154 - iter 4/9 - loss 0.00003004 - time (sec): 0.56 - samples/sec: 4115.99 - lr: 0.000013 - momentum: 0.000000 2024-11-27 20:32:56,315 epoch 154 - iter 5/9 - loss 0.00002632 - time (sec): 0.74 - samples/sec: 4038.39 - lr: 0.000013 - momentum: 0.000000 2024-11-27 20:32:56,475 epoch 154 - iter 6/9 - loss 0.00002461 - time (sec): 0.90 - samples/sec: 3899.51 - lr: 0.000013 - momentum: 0.000000 2024-11-27 20:32:56,640 epoch 154 - iter 7/9 - loss 0.00002584 - time (sec): 1.07 - samples/sec: 3894.27 - lr: 0.000013 - momentum: 0.000000 2024-11-27 20:32:56,788 epoch 154 - iter 8/9 - loss 0.00002650 - time (sec): 1.21 - samples/sec: 3847.09 - lr: 0.000013 - momentum: 0.000000 2024-11-27 20:32:56,907 epoch 154 - iter 9/9 - loss 0.00002577 - time (sec): 1.33 - samples/sec: 3897.62 - lr: 0.000013 - momentum: 0.000000 2024-11-27 20:32:56,907 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:32:56,907 EPOCH 154 done: loss 0.0000 - lr: 0.000013 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 4.05it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 4.05it/s] 2024-11-27 20:32:57,173 DEV : loss 3.640815019607544 - f1-score (micro avg) 0.366 2024-11-27 20:32:57,174 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:32:57,275 epoch 155 - iter 1/9 - loss 0.00002131 - time (sec): 0.10 - samples/sec: 6791.45 - lr: 0.000013 - momentum: 0.000000 2024-11-27 20:32:57,404 epoch 155 - iter 2/9 - loss 0.00002429 - time (sec): 0.23 - samples/sec: 5357.34 - lr: 0.000013 - momentum: 0.000000 2024-11-27 20:32:57,553 epoch 155 - iter 3/9 - loss 0.00002140 - time (sec): 0.38 - samples/sec: 4784.91 - lr: 0.000013 - momentum: 0.000000 2024-11-27 20:32:57,750 epoch 155 - iter 4/9 - loss 0.00002274 - time (sec): 0.57 - samples/sec: 4217.81 - lr: 0.000013 - momentum: 0.000000 2024-11-27 20:32:57,920 epoch 155 - iter 5/9 - loss 0.00002101 - time (sec): 0.74 - samples/sec: 3974.56 - lr: 0.000013 - momentum: 0.000000 2024-11-27 20:32:58,067 epoch 155 - iter 6/9 - loss 0.00002290 - time (sec): 0.89 - samples/sec: 3920.68 - lr: 0.000013 - momentum: 0.000000 2024-11-27 20:32:58,242 epoch 155 - iter 7/9 - loss 0.00002582 - time (sec): 1.07 - samples/sec: 3867.42 - lr: 0.000013 - momentum: 0.000000 2024-11-27 20:32:58,431 epoch 155 - iter 8/9 - loss 0.00002539 - time (sec): 1.26 - samples/sec: 3704.51 - lr: 0.000013 - momentum: 0.000000 2024-11-27 20:32:58,583 epoch 155 - iter 9/9 - loss 0.00002665 - time (sec): 1.41 - samples/sec: 3691.28 - lr: 0.000013 - momentum: 0.000000 2024-11-27 20:32:58,584 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:32:58,584 EPOCH 155 done: loss 0.0000 - lr: 0.000013 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 4.71it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 4.71it/s] 2024-11-27 20:32:58,816 DEV : loss 3.6449172496795654 - f1-score (micro avg) 0.366 2024-11-27 20:32:58,817 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:32:58,910 epoch 156 - iter 1/9 - loss 0.00001367 - time (sec): 0.09 - samples/sec: 5047.31 - lr: 0.000013 - momentum: 0.000000 2024-11-27 20:32:59,081 epoch 156 - iter 2/9 - loss 0.00002442 - time (sec): 0.26 - samples/sec: 4597.42 - lr: 0.000013 - momentum: 0.000000 2024-11-27 20:32:59,247 epoch 156 - iter 3/9 - loss 0.00002359 - time (sec): 0.43 - samples/sec: 4180.20 - lr: 0.000013 - momentum: 0.000000 2024-11-27 20:32:59,389 epoch 156 - iter 4/9 - loss 0.00002301 - time (sec): 0.57 - samples/sec: 4146.62 - lr: 0.000013 - momentum: 0.000000 2024-11-27 20:32:59,537 epoch 156 - iter 5/9 - loss 0.00002042 - time (sec): 0.72 - samples/sec: 4107.69 - lr: 0.000013 - momentum: 0.000000 2024-11-27 20:32:59,693 epoch 156 - iter 6/9 - loss 0.00396493 - time (sec): 0.88 - samples/sec: 4133.21 - lr: 0.000013 - momentum: 0.000000 2024-11-27 20:32:59,858 epoch 156 - iter 7/9 - loss 0.00347272 - time (sec): 1.04 - samples/sec: 3975.64 - lr: 0.000013 - momentum: 0.000000 2024-11-27 20:33:00,024 epoch 156 - iter 8/9 - loss 0.00301327 - time (sec): 1.21 - samples/sec: 3953.73 - lr: 0.000013 - momentum: 0.000000 2024-11-27 20:33:00,160 epoch 156 - iter 9/9 - loss 0.00276791 - time (sec): 1.34 - samples/sec: 3872.46 - lr: 0.000013 - momentum: 0.000000 2024-11-27 20:33:00,160 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:33:00,160 EPOCH 156 done: loss 0.0028 - lr: 0.000013 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.42it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.41it/s] 2024-11-27 20:33:00,336 DEV : loss 3.6370391845703125 - f1-score (micro avg) 0.366 2024-11-27 20:33:00,338 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:33:00,437 epoch 157 - iter 1/9 - loss 0.00001517 - time (sec): 0.10 - samples/sec: 4969.60 - lr: 0.000013 - momentum: 0.000000 2024-11-27 20:33:00,574 epoch 157 - iter 2/9 - loss 0.00001406 - time (sec): 0.24 - samples/sec: 4487.68 - lr: 0.000013 - momentum: 0.000000 2024-11-27 20:33:00,712 epoch 157 - iter 3/9 - loss 0.00001560 - time (sec): 0.37 - samples/sec: 4467.11 - lr: 0.000013 - momentum: 0.000000 2024-11-27 20:33:00,869 epoch 157 - iter 4/9 - loss 0.00001659 - time (sec): 0.53 - samples/sec: 4074.98 - lr: 0.000013 - momentum: 0.000000 2024-11-27 20:33:01,060 epoch 157 - iter 5/9 - loss 0.00001538 - time (sec): 0.72 - samples/sec: 3810.48 - lr: 0.000013 - momentum: 0.000000 2024-11-27 20:33:01,288 epoch 157 - iter 6/9 - loss 0.00001677 - time (sec): 0.95 - samples/sec: 3545.34 - lr: 0.000012 - momentum: 0.000000 2024-11-27 20:33:01,463 epoch 157 - iter 7/9 - loss 0.00002055 - time (sec): 1.12 - samples/sec: 3541.18 - lr: 0.000012 - momentum: 0.000000 2024-11-27 20:33:01,633 epoch 157 - iter 8/9 - loss 0.00001987 - time (sec): 1.29 - samples/sec: 3590.66 - lr: 0.000012 - momentum: 0.000000 2024-11-27 20:33:01,786 epoch 157 - iter 9/9 - loss 0.00001913 - time (sec): 1.45 - samples/sec: 3590.95 - lr: 0.000012 - momentum: 0.000000 2024-11-27 20:33:01,786 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:33:01,786 EPOCH 157 done: loss 0.0000 - lr: 0.000012 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.15it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.15it/s] 2024-11-27 20:33:01,968 DEV : loss 3.632692337036133 - f1-score (micro avg) 0.366 2024-11-27 20:33:01,969 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:33:02,073 epoch 158 - iter 1/9 - loss 0.00003184 - time (sec): 0.10 - samples/sec: 5731.06 - lr: 0.000012 - momentum: 0.000000 2024-11-27 20:33:02,212 epoch 158 - iter 2/9 - loss 0.00002264 - time (sec): 0.24 - samples/sec: 4887.14 - lr: 0.000012 - momentum: 0.000000 2024-11-27 20:33:02,369 epoch 158 - iter 3/9 - loss 0.00002295 - time (sec): 0.40 - samples/sec: 4362.15 - lr: 0.000012 - momentum: 0.000000 2024-11-27 20:33:02,556 epoch 158 - iter 4/9 - loss 0.00002636 - time (sec): 0.59 - samples/sec: 3953.40 - lr: 0.000012 - momentum: 0.000000 2024-11-27 20:33:02,743 epoch 158 - iter 5/9 - loss 0.00002713 - time (sec): 0.77 - samples/sec: 3915.65 - lr: 0.000012 - momentum: 0.000000 2024-11-27 20:33:02,991 epoch 158 - iter 6/9 - loss 0.00002537 - time (sec): 1.02 - samples/sec: 3575.95 - lr: 0.000012 - momentum: 0.000000 2024-11-27 20:33:03,174 epoch 158 - iter 7/9 - loss 0.00002309 - time (sec): 1.20 - samples/sec: 3473.76 - lr: 0.000012 - momentum: 0.000000 2024-11-27 20:33:03,326 epoch 158 - iter 8/9 - loss 0.00002213 - time (sec): 1.36 - samples/sec: 3439.00 - lr: 0.000012 - momentum: 0.000000 2024-11-27 20:33:03,474 epoch 158 - iter 9/9 - loss 0.00002383 - time (sec): 1.50 - samples/sec: 3456.64 - lr: 0.000012 - momentum: 0.000000 2024-11-27 20:33:03,474 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:33:03,474 EPOCH 158 done: loss 0.0000 - lr: 0.000012 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 5.99it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 5.99it/s] 2024-11-27 20:33:03,660 DEV : loss 3.63285493850708 - f1-score (micro avg) 0.3636 2024-11-27 20:33:03,661 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:33:03,763 epoch 159 - iter 1/9 - loss 0.00001349 - time (sec): 0.10 - samples/sec: 6054.26 - lr: 0.000012 - momentum: 0.000000 2024-11-27 20:33:03,937 epoch 159 - iter 2/9 - loss 0.00001992 - time (sec): 0.28 - samples/sec: 4661.32 - lr: 0.000012 - momentum: 0.000000 2024-11-27 20:33:04,105 epoch 159 - iter 3/9 - loss 0.00002016 - time (sec): 0.44 - samples/sec: 3915.74 - lr: 0.000012 - momentum: 0.000000 2024-11-27 20:33:04,257 epoch 159 - iter 4/9 - loss 0.00002793 - time (sec): 0.59 - samples/sec: 3937.85 - lr: 0.000012 - momentum: 0.000000 2024-11-27 20:33:04,404 epoch 159 - iter 5/9 - loss 0.00002630 - time (sec): 0.74 - samples/sec: 3907.89 - lr: 0.000012 - momentum: 0.000000 2024-11-27 20:33:04,556 epoch 159 - iter 6/9 - loss 0.00002325 - time (sec): 0.89 - samples/sec: 3999.51 - lr: 0.000012 - momentum: 0.000000 2024-11-27 20:33:04,721 epoch 159 - iter 7/9 - loss 0.00002304 - time (sec): 1.06 - samples/sec: 3872.50 - lr: 0.000012 - momentum: 0.000000 2024-11-27 20:33:04,860 epoch 159 - iter 8/9 - loss 0.00002367 - time (sec): 1.20 - samples/sec: 3893.13 - lr: 0.000012 - momentum: 0.000000 2024-11-27 20:33:05,021 epoch 159 - iter 9/9 - loss 0.00002743 - time (sec): 1.36 - samples/sec: 3826.53 - lr: 0.000012 - momentum: 0.000000 2024-11-27 20:33:05,021 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:33:05,021 EPOCH 159 done: loss 0.0000 - lr: 0.000012 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 5.70it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 5.69it/s] 2024-11-27 20:33:05,216 DEV : loss 3.635685443878174 - f1-score (micro avg) 0.3636 2024-11-27 20:33:05,217 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:33:05,314 epoch 160 - iter 1/9 - loss 0.00005091 - time (sec): 0.10 - samples/sec: 5929.56 - lr: 0.000012 - momentum: 0.000000 2024-11-27 20:33:05,459 epoch 160 - iter 2/9 - loss 0.00003258 - time (sec): 0.24 - samples/sec: 4735.93 - lr: 0.000012 - momentum: 0.000000 2024-11-27 20:33:05,695 epoch 160 - iter 3/9 - loss 0.00002903 - time (sec): 0.48 - samples/sec: 3499.51 - lr: 0.000012 - momentum: 0.000000 2024-11-27 20:33:05,846 epoch 160 - iter 4/9 - loss 0.00004471 - time (sec): 0.63 - samples/sec: 3696.51 - lr: 0.000012 - momentum: 0.000000 2024-11-27 20:33:05,987 epoch 160 - iter 5/9 - loss 0.00003999 - time (sec): 0.77 - samples/sec: 3837.91 - lr: 0.000012 - momentum: 0.000000 2024-11-27 20:33:06,123 epoch 160 - iter 6/9 - loss 0.00003815 - time (sec): 0.91 - samples/sec: 3837.65 - lr: 0.000012 - momentum: 0.000000 2024-11-27 20:33:06,339 epoch 160 - iter 7/9 - loss 0.00385178 - time (sec): 1.12 - samples/sec: 3735.37 - lr: 0.000012 - momentum: 0.000000 2024-11-27 20:33:06,530 epoch 160 - iter 8/9 - loss 0.00345337 - time (sec): 1.31 - samples/sec: 3564.59 - lr: 0.000012 - momentum: 0.000000 2024-11-27 20:33:06,657 epoch 160 - iter 9/9 - loss 0.00501345 - time (sec): 1.44 - samples/sec: 3610.90 - lr: 0.000012 - momentum: 0.000000 2024-11-27 20:33:06,658 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:33:06,658 EPOCH 160 done: loss 0.0050 - lr: 0.000012 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.75it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.74it/s] 2024-11-27 20:33:06,825 DEV : loss 3.634061574935913 - f1-score (micro avg) 0.3766 2024-11-27 20:33:06,826 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:33:06,922 epoch 161 - iter 1/9 - loss 0.00003259 - time (sec): 0.09 - samples/sec: 5985.56 - lr: 0.000012 - momentum: 0.000000 2024-11-27 20:33:07,054 epoch 161 - iter 2/9 - loss 0.00003700 - time (sec): 0.23 - samples/sec: 4731.75 - lr: 0.000012 - momentum: 0.000000 2024-11-27 20:33:07,215 epoch 161 - iter 3/9 - loss 0.00003133 - time (sec): 0.39 - samples/sec: 4515.25 - lr: 0.000012 - momentum: 0.000000 2024-11-27 20:33:07,350 epoch 161 - iter 4/9 - loss 0.00002915 - time (sec): 0.52 - samples/sec: 4328.09 - lr: 0.000012 - momentum: 0.000000 2024-11-27 20:33:07,630 epoch 161 - iter 5/9 - loss 0.00002527 - time (sec): 0.80 - samples/sec: 3779.88 - lr: 0.000012 - momentum: 0.000000 2024-11-27 20:33:07,763 epoch 161 - iter 6/9 - loss 0.00002487 - time (sec): 0.94 - samples/sec: 3765.59 - lr: 0.000012 - momentum: 0.000000 2024-11-27 20:33:07,904 epoch 161 - iter 7/9 - loss 0.00002382 - time (sec): 1.08 - samples/sec: 3840.22 - lr: 0.000012 - momentum: 0.000000 2024-11-27 20:33:08,056 epoch 161 - iter 8/9 - loss 0.00002310 - time (sec): 1.23 - samples/sec: 3797.82 - lr: 0.000012 - momentum: 0.000000 2024-11-27 20:33:08,195 epoch 161 - iter 9/9 - loss 0.00002300 - time (sec): 1.37 - samples/sec: 3799.56 - lr: 0.000012 - momentum: 0.000000 2024-11-27 20:33:08,195 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:33:08,195 EPOCH 161 done: loss 0.0000 - lr: 0.000012 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 5.43it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 5.42it/s] 2024-11-27 20:33:08,399 DEV : loss 3.6327648162841797 - f1-score (micro avg) 0.3766 2024-11-27 20:33:08,400 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:33:08,497 epoch 162 - iter 1/9 - loss 0.00123379 - time (sec): 0.10 - samples/sec: 5666.28 - lr: 0.000012 - momentum: 0.000000 2024-11-27 20:33:08,648 epoch 162 - iter 2/9 - loss 0.00064434 - time (sec): 0.25 - samples/sec: 4291.42 - lr: 0.000012 - momentum: 0.000000 2024-11-27 20:33:08,783 epoch 162 - iter 3/9 - loss 0.00044021 - time (sec): 0.38 - samples/sec: 4114.15 - lr: 0.000012 - momentum: 0.000000 2024-11-27 20:33:08,944 epoch 162 - iter 4/9 - loss 0.00032408 - time (sec): 0.54 - samples/sec: 3979.79 - lr: 0.000012 - momentum: 0.000000 2024-11-27 20:33:09,104 epoch 162 - iter 5/9 - loss 0.00025104 - time (sec): 0.70 - samples/sec: 4013.25 - lr: 0.000011 - momentum: 0.000000 2024-11-27 20:33:09,254 epoch 162 - iter 6/9 - loss 0.00020689 - time (sec): 0.85 - samples/sec: 4064.89 - lr: 0.000011 - momentum: 0.000000 2024-11-27 20:33:09,398 epoch 162 - iter 7/9 - loss 0.00017782 - time (sec): 1.00 - samples/sec: 4166.16 - lr: 0.000011 - momentum: 0.000000 2024-11-27 20:33:09,535 epoch 162 - iter 8/9 - loss 0.00016166 - time (sec): 1.13 - samples/sec: 4086.04 - lr: 0.000011 - momentum: 0.000000 2024-11-27 20:33:09,671 epoch 162 - iter 9/9 - loss 0.00014609 - time (sec): 1.27 - samples/sec: 4094.63 - lr: 0.000011 - momentum: 0.000000 2024-11-27 20:33:09,671 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:33:09,671 EPOCH 162 done: loss 0.0001 - lr: 0.000011 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.58it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.57it/s] 2024-11-27 20:33:09,842 DEV : loss 3.6377456188201904 - f1-score (micro avg) 0.3484 2024-11-27 20:33:09,843 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:33:09,960 epoch 163 - iter 1/9 - loss 0.00001358 - time (sec): 0.12 - samples/sec: 6755.08 - lr: 0.000011 - momentum: 0.000000 2024-11-27 20:33:10,117 epoch 163 - iter 2/9 - loss 0.00001941 - time (sec): 0.27 - samples/sec: 4799.96 - lr: 0.000011 - momentum: 0.000000 2024-11-27 20:33:10,258 epoch 163 - iter 3/9 - loss 0.00001831 - time (sec): 0.41 - samples/sec: 4438.50 - lr: 0.000011 - momentum: 0.000000 2024-11-27 20:33:10,382 epoch 163 - iter 4/9 - loss 0.00002094 - time (sec): 0.54 - samples/sec: 4487.46 - lr: 0.000011 - momentum: 0.000000 2024-11-27 20:33:10,709 epoch 163 - iter 5/9 - loss 0.00005843 - time (sec): 0.86 - samples/sec: 3571.11 - lr: 0.000011 - momentum: 0.000000 2024-11-27 20:33:10,877 epoch 163 - iter 6/9 - loss 0.00005142 - time (sec): 1.03 - samples/sec: 3647.90 - lr: 0.000011 - momentum: 0.000000 2024-11-27 20:33:11,093 epoch 163 - iter 7/9 - loss 0.00004709 - time (sec): 1.25 - samples/sec: 3438.24 - lr: 0.000011 - momentum: 0.000000 2024-11-27 20:33:11,331 epoch 163 - iter 8/9 - loss 0.00004426 - time (sec): 1.49 - samples/sec: 3196.88 - lr: 0.000011 - momentum: 0.000000 2024-11-27 20:33:11,460 epoch 163 - iter 9/9 - loss 0.00004690 - time (sec): 1.62 - samples/sec: 3216.33 - lr: 0.000011 - momentum: 0.000000 2024-11-27 20:33:11,460 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:33:11,461 EPOCH 163 done: loss 0.0000 - lr: 0.000011 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 7.28it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 7.27it/s] 2024-11-27 20:33:11,617 DEV : loss 3.6343374252319336 - f1-score (micro avg) 0.3636 2024-11-27 20:33:11,618 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:33:11,766 epoch 164 - iter 1/9 - loss 0.00001312 - time (sec): 0.15 - samples/sec: 3437.42 - lr: 0.000011 - momentum: 0.000000 2024-11-27 20:33:11,967 epoch 164 - iter 2/9 - loss 0.00001535 - time (sec): 0.35 - samples/sec: 3186.58 - lr: 0.000011 - momentum: 0.000000 2024-11-27 20:33:12,099 epoch 164 - iter 3/9 - loss 0.00002801 - time (sec): 0.48 - samples/sec: 3440.52 - lr: 0.000011 - momentum: 0.000000 2024-11-27 20:33:12,245 epoch 164 - iter 4/9 - loss 0.00003322 - time (sec): 0.63 - samples/sec: 3690.52 - lr: 0.000011 - momentum: 0.000000 2024-11-27 20:33:12,417 epoch 164 - iter 5/9 - loss 0.00003388 - time (sec): 0.80 - samples/sec: 3606.37 - lr: 0.000011 - momentum: 0.000000 2024-11-27 20:33:12,667 epoch 164 - iter 6/9 - loss 0.00003645 - time (sec): 1.05 - samples/sec: 3221.53 - lr: 0.000011 - momentum: 0.000000 2024-11-27 20:33:12,799 epoch 164 - iter 7/9 - loss 0.00003373 - time (sec): 1.18 - samples/sec: 3353.28 - lr: 0.000011 - momentum: 0.000000 2024-11-27 20:33:12,924 epoch 164 - iter 8/9 - loss 0.00003290 - time (sec): 1.30 - samples/sec: 3454.94 - lr: 0.000011 - momentum: 0.000000 2024-11-27 20:33:13,063 epoch 164 - iter 9/9 - loss 0.00004277 - time (sec): 1.44 - samples/sec: 3598.13 - lr: 0.000011 - momentum: 0.000000 2024-11-27 20:33:13,064 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:33:13,064 EPOCH 164 done: loss 0.0000 - lr: 0.000011 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 5.65it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 5.64it/s] 2024-11-27 20:33:13,261 DEV : loss 3.6321775913238525 - f1-score (micro avg) 0.3544 2024-11-27 20:33:13,262 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:33:13,369 epoch 165 - iter 1/9 - loss 0.00002533 - time (sec): 0.11 - samples/sec: 7167.35 - lr: 0.000011 - momentum: 0.000000 2024-11-27 20:33:13,512 epoch 165 - iter 2/9 - loss 0.00003923 - time (sec): 0.25 - samples/sec: 5842.00 - lr: 0.000011 - momentum: 0.000000 2024-11-27 20:33:13,687 epoch 165 - iter 3/9 - loss 0.00003465 - time (sec): 0.42 - samples/sec: 4531.75 - lr: 0.000011 - momentum: 0.000000 2024-11-27 20:33:13,866 epoch 165 - iter 4/9 - loss 0.00003078 - time (sec): 0.60 - samples/sec: 4261.88 - lr: 0.000011 - momentum: 0.000000 2024-11-27 20:33:14,003 epoch 165 - iter 5/9 - loss 0.00003318 - time (sec): 0.74 - samples/sec: 4198.48 - lr: 0.000011 - momentum: 0.000000 2024-11-27 20:33:14,125 epoch 165 - iter 6/9 - loss 0.00003197 - time (sec): 0.86 - samples/sec: 4271.64 - lr: 0.000011 - momentum: 0.000000 2024-11-27 20:33:14,272 epoch 165 - iter 7/9 - loss 0.00002903 - time (sec): 1.01 - samples/sec: 4264.43 - lr: 0.000011 - momentum: 0.000000 2024-11-27 20:33:14,401 epoch 165 - iter 8/9 - loss 0.00027816 - time (sec): 1.14 - samples/sec: 4242.67 - lr: 0.000011 - momentum: 0.000000 2024-11-27 20:33:14,524 epoch 165 - iter 9/9 - loss 0.00025969 - time (sec): 1.26 - samples/sec: 4121.63 - lr: 0.000011 - momentum: 0.000000 2024-11-27 20:33:14,524 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:33:14,524 EPOCH 165 done: loss 0.0003 - lr: 0.000011 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.25it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.24it/s] 2024-11-27 20:33:14,703 DEV : loss 3.6271090507507324 - f1-score (micro avg) 0.3567 2024-11-27 20:33:14,705 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:33:14,799 epoch 166 - iter 1/9 - loss 0.00004538 - time (sec): 0.09 - samples/sec: 5219.30 - lr: 0.000011 - momentum: 0.000000 2024-11-27 20:33:14,940 epoch 166 - iter 2/9 - loss 0.00002970 - time (sec): 0.23 - samples/sec: 4577.41 - lr: 0.000011 - momentum: 0.000000 2024-11-27 20:33:15,085 epoch 166 - iter 3/9 - loss 0.00003652 - time (sec): 0.38 - samples/sec: 4093.80 - lr: 0.000011 - momentum: 0.000000 2024-11-27 20:33:15,232 epoch 166 - iter 4/9 - loss 0.00003661 - time (sec): 0.53 - samples/sec: 3928.92 - lr: 0.000011 - momentum: 0.000000 2024-11-27 20:33:15,376 epoch 166 - iter 5/9 - loss 0.00003025 - time (sec): 0.67 - samples/sec: 4081.33 - lr: 0.000011 - momentum: 0.000000 2024-11-27 20:33:15,507 epoch 166 - iter 6/9 - loss 0.00002894 - time (sec): 0.80 - samples/sec: 4178.10 - lr: 0.000011 - momentum: 0.000000 2024-11-27 20:33:15,655 epoch 166 - iter 7/9 - loss 0.00002675 - time (sec): 0.95 - samples/sec: 4164.07 - lr: 0.000011 - momentum: 0.000000 2024-11-27 20:33:15,818 epoch 166 - iter 8/9 - loss 0.00002603 - time (sec): 1.11 - samples/sec: 4086.36 - lr: 0.000011 - momentum: 0.000000 2024-11-27 20:33:15,977 epoch 166 - iter 9/9 - loss 0.00002391 - time (sec): 1.27 - samples/sec: 4087.27 - lr: 0.000011 - momentum: 0.000000 2024-11-27 20:33:15,977 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:33:15,978 EPOCH 166 done: loss 0.0000 - lr: 0.000011 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 5.54it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 5.54it/s] 2024-11-27 20:33:16,177 DEV : loss 3.6283810138702393 - f1-score (micro avg) 0.3648 2024-11-27 20:33:16,178 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:33:16,278 epoch 167 - iter 1/9 - loss 0.00001689 - time (sec): 0.10 - samples/sec: 4939.37 - lr: 0.000011 - momentum: 0.000000 2024-11-27 20:33:16,442 epoch 167 - iter 2/9 - loss 0.00002711 - time (sec): 0.26 - samples/sec: 4346.98 - lr: 0.000011 - momentum: 0.000000 2024-11-27 20:33:16,599 epoch 167 - iter 3/9 - loss 0.00002217 - time (sec): 0.42 - samples/sec: 4357.00 - lr: 0.000011 - momentum: 0.000000 2024-11-27 20:33:16,806 epoch 167 - iter 4/9 - loss 0.00002149 - time (sec): 0.63 - samples/sec: 3840.37 - lr: 0.000010 - momentum: 0.000000 2024-11-27 20:33:16,969 epoch 167 - iter 5/9 - loss 0.00002060 - time (sec): 0.79 - samples/sec: 3814.98 - lr: 0.000010 - momentum: 0.000000 2024-11-27 20:33:17,152 epoch 167 - iter 6/9 - loss 0.00001996 - time (sec): 0.97 - samples/sec: 3641.61 - lr: 0.000010 - momentum: 0.000000 2024-11-27 20:33:17,324 epoch 167 - iter 7/9 - loss 0.00001914 - time (sec): 1.14 - samples/sec: 3601.62 - lr: 0.000010 - momentum: 0.000000 2024-11-27 20:33:17,481 epoch 167 - iter 8/9 - loss 0.00001932 - time (sec): 1.30 - samples/sec: 3574.56 - lr: 0.000010 - momentum: 0.000000 2024-11-27 20:33:17,613 epoch 167 - iter 9/9 - loss 0.00001931 - time (sec): 1.43 - samples/sec: 3624.66 - lr: 0.000010 - momentum: 0.000000 2024-11-27 20:33:17,614 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:33:17,614 EPOCH 167 done: loss 0.0000 - lr: 0.000010 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 7.58it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 7.56it/s] 2024-11-27 20:33:17,765 DEV : loss 3.631713390350342 - f1-score (micro avg) 0.3648 2024-11-27 20:33:17,766 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:33:17,865 epoch 168 - iter 1/9 - loss 0.00001388 - time (sec): 0.10 - samples/sec: 5157.09 - lr: 0.000010 - momentum: 0.000000 2024-11-27 20:33:18,053 epoch 168 - iter 2/9 - loss 0.00001464 - time (sec): 0.29 - samples/sec: 3580.32 - lr: 0.000010 - momentum: 0.000000 2024-11-27 20:33:18,262 epoch 168 - iter 3/9 - loss 0.00001516 - time (sec): 0.50 - samples/sec: 3281.55 - lr: 0.000010 - momentum: 0.000000 2024-11-27 20:33:18,423 epoch 168 - iter 4/9 - loss 0.00001263 - time (sec): 0.66 - samples/sec: 3347.64 - lr: 0.000010 - momentum: 0.000000 2024-11-27 20:33:18,563 epoch 168 - iter 5/9 - loss 0.00001395 - time (sec): 0.80 - samples/sec: 3533.27 - lr: 0.000010 - momentum: 0.000000 2024-11-27 20:33:18,710 epoch 168 - iter 6/9 - loss 0.00001438 - time (sec): 0.94 - samples/sec: 3614.73 - lr: 0.000010 - momentum: 0.000000 2024-11-27 20:33:18,884 epoch 168 - iter 7/9 - loss 0.00002026 - time (sec): 1.12 - samples/sec: 3655.43 - lr: 0.000010 - momentum: 0.000000 2024-11-27 20:33:19,063 epoch 168 - iter 8/9 - loss 0.00002081 - time (sec): 1.30 - samples/sec: 3581.13 - lr: 0.000010 - momentum: 0.000000 2024-11-27 20:33:19,228 epoch 168 - iter 9/9 - loss 0.00002025 - time (sec): 1.46 - samples/sec: 3556.49 - lr: 0.000010 - momentum: 0.000000 2024-11-27 20:33:19,229 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:33:19,229 EPOCH 168 done: loss 0.0000 - lr: 0.000010 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 7.30it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 7.29it/s] 2024-11-27 20:33:19,385 DEV : loss 3.635556697845459 - f1-score (micro avg) 0.3648 2024-11-27 20:33:19,386 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:33:19,487 epoch 169 - iter 1/9 - loss 0.00001328 - time (sec): 0.10 - samples/sec: 5624.04 - lr: 0.000010 - momentum: 0.000000 2024-11-27 20:33:19,649 epoch 169 - iter 2/9 - loss 0.00001685 - time (sec): 0.26 - samples/sec: 4642.78 - lr: 0.000010 - momentum: 0.000000 2024-11-27 20:33:19,851 epoch 169 - iter 3/9 - loss 0.00002123 - time (sec): 0.46 - samples/sec: 4032.51 - lr: 0.000010 - momentum: 0.000000 2024-11-27 20:33:20,031 epoch 169 - iter 4/9 - loss 0.00339497 - time (sec): 0.64 - samples/sec: 3741.02 - lr: 0.000010 - momentum: 0.000000 2024-11-27 20:33:20,178 epoch 169 - iter 5/9 - loss 0.00267110 - time (sec): 0.79 - samples/sec: 3876.11 - lr: 0.000010 - momentum: 0.000000 2024-11-27 20:33:20,347 epoch 169 - iter 6/9 - loss 0.00223237 - time (sec): 0.96 - samples/sec: 3833.01 - lr: 0.000010 - momentum: 0.000000 2024-11-27 20:33:20,515 epoch 169 - iter 7/9 - loss 0.00192020 - time (sec): 1.13 - samples/sec: 3796.39 - lr: 0.000010 - momentum: 0.000000 2024-11-27 20:33:20,677 epoch 169 - iter 8/9 - loss 0.00173500 - time (sec): 1.29 - samples/sec: 3681.62 - lr: 0.000010 - momentum: 0.000000 2024-11-27 20:33:20,820 epoch 169 - iter 9/9 - loss 0.00158594 - time (sec): 1.43 - samples/sec: 3628.35 - lr: 0.000010 - momentum: 0.000000 2024-11-27 20:33:20,820 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:33:20,820 EPOCH 169 done: loss 0.0016 - lr: 0.000010 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.02it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.01it/s] 2024-11-27 20:33:21,006 DEV : loss 3.635467290878296 - f1-score (micro avg) 0.3648 2024-11-27 20:33:21,007 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:33:21,107 epoch 170 - iter 1/9 - loss 0.00001688 - time (sec): 0.10 - samples/sec: 5666.84 - lr: 0.000010 - momentum: 0.000000 2024-11-27 20:33:21,261 epoch 170 - iter 2/9 - loss 0.00001793 - time (sec): 0.25 - samples/sec: 4791.43 - lr: 0.000010 - momentum: 0.000000 2024-11-27 20:33:21,427 epoch 170 - iter 3/9 - loss 0.00003131 - time (sec): 0.42 - samples/sec: 4085.58 - lr: 0.000010 - momentum: 0.000000 2024-11-27 20:33:21,688 epoch 170 - iter 4/9 - loss 0.00002864 - time (sec): 0.68 - samples/sec: 3441.60 - lr: 0.000010 - momentum: 0.000000 2024-11-27 20:33:21,840 epoch 170 - iter 5/9 - loss 0.00002718 - time (sec): 0.83 - samples/sec: 3619.30 - lr: 0.000010 - momentum: 0.000000 2024-11-27 20:33:21,977 epoch 170 - iter 6/9 - loss 0.00003122 - time (sec): 0.97 - samples/sec: 3720.98 - lr: 0.000010 - momentum: 0.000000 2024-11-27 20:33:22,138 epoch 170 - iter 7/9 - loss 0.00002938 - time (sec): 1.13 - samples/sec: 3612.37 - lr: 0.000010 - momentum: 0.000000 2024-11-27 20:33:22,311 epoch 170 - iter 8/9 - loss 0.00003415 - time (sec): 1.30 - samples/sec: 3554.28 - lr: 0.000010 - momentum: 0.000000 2024-11-27 20:33:22,483 epoch 170 - iter 9/9 - loss 0.00003152 - time (sec): 1.48 - samples/sec: 3523.02 - lr: 0.000010 - momentum: 0.000000 2024-11-27 20:33:22,483 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:33:22,483 EPOCH 170 done: loss 0.0000 - lr: 0.000010 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 5.71it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 5.70it/s] 2024-11-27 20:33:22,678 DEV : loss 3.6433393955230713 - f1-score (micro avg) 0.3625 2024-11-27 20:33:22,679 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:33:22,788 epoch 171 - iter 1/9 - loss 0.00002155 - time (sec): 0.11 - samples/sec: 6666.11 - lr: 0.000010 - momentum: 0.000000 2024-11-27 20:33:22,931 epoch 171 - iter 2/9 - loss 0.00002293 - time (sec): 0.25 - samples/sec: 5202.20 - lr: 0.000010 - momentum: 0.000000 2024-11-27 20:33:23,102 epoch 171 - iter 3/9 - loss 0.00002363 - time (sec): 0.42 - samples/sec: 4555.68 - lr: 0.000010 - momentum: 0.000000 2024-11-27 20:33:23,331 epoch 171 - iter 4/9 - loss 0.00002501 - time (sec): 0.65 - samples/sec: 3650.22 - lr: 0.000010 - momentum: 0.000000 2024-11-27 20:33:23,470 epoch 171 - iter 5/9 - loss 0.00002684 - time (sec): 0.79 - samples/sec: 3623.64 - lr: 0.000010 - momentum: 0.000000 2024-11-27 20:33:23,611 epoch 171 - iter 6/9 - loss 0.00002380 - time (sec): 0.93 - samples/sec: 3689.40 - lr: 0.000010 - momentum: 0.000000 2024-11-27 20:33:23,787 epoch 171 - iter 7/9 - loss 0.00002313 - time (sec): 1.11 - samples/sec: 3664.79 - lr: 0.000010 - momentum: 0.000000 2024-11-27 20:33:23,960 epoch 171 - iter 8/9 - loss 0.00002131 - time (sec): 1.28 - samples/sec: 3650.70 - lr: 0.000010 - momentum: 0.000000 2024-11-27 20:33:24,116 epoch 171 - iter 9/9 - loss 0.00093722 - time (sec): 1.44 - samples/sec: 3619.29 - lr: 0.000010 - momentum: 0.000000 2024-11-27 20:33:24,117 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:33:24,117 EPOCH 171 done: loss 0.0009 - lr: 0.000010 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.49it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.48it/s] 2024-11-27 20:33:24,290 DEV : loss 3.655240297317505 - f1-score (micro avg) 0.3625 2024-11-27 20:33:24,291 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:33:24,410 epoch 172 - iter 1/9 - loss 0.00006867 - time (sec): 0.12 - samples/sec: 5221.80 - lr: 0.000010 - momentum: 0.000000 2024-11-27 20:33:24,569 epoch 172 - iter 2/9 - loss 0.00005796 - time (sec): 0.28 - samples/sec: 4263.05 - lr: 0.000010 - momentum: 0.000000 2024-11-27 20:33:24,773 epoch 172 - iter 3/9 - loss 0.00004564 - time (sec): 0.48 - samples/sec: 3671.68 - lr: 0.000010 - momentum: 0.000000 2024-11-27 20:33:24,913 epoch 172 - iter 4/9 - loss 0.00003889 - time (sec): 0.62 - samples/sec: 3900.46 - lr: 0.000009 - momentum: 0.000000 2024-11-27 20:33:25,047 epoch 172 - iter 5/9 - loss 0.00003789 - time (sec): 0.75 - samples/sec: 3893.14 - lr: 0.000009 - momentum: 0.000000 2024-11-27 20:33:25,223 epoch 172 - iter 6/9 - loss 0.00003437 - time (sec): 0.93 - samples/sec: 3660.96 - lr: 0.000009 - momentum: 0.000000 2024-11-27 20:33:25,398 epoch 172 - iter 7/9 - loss 0.00003461 - time (sec): 1.11 - samples/sec: 3607.87 - lr: 0.000009 - momentum: 0.000000 2024-11-27 20:33:25,548 epoch 172 - iter 8/9 - loss 0.00003157 - time (sec): 1.26 - samples/sec: 3709.24 - lr: 0.000009 - momentum: 0.000000 2024-11-27 20:33:25,867 epoch 172 - iter 9/9 - loss 0.00003086 - time (sec): 1.57 - samples/sec: 3300.02 - lr: 0.000009 - momentum: 0.000000 2024-11-27 20:33:25,868 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:33:25,868 EPOCH 172 done: loss 0.0000 - lr: 0.000009 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.58it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.56it/s] 2024-11-27 20:33:26,039 DEV : loss 3.6651318073272705 - f1-score (micro avg) 0.3648 2024-11-27 20:33:26,040 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:33:26,130 epoch 173 - iter 1/9 - loss 0.00002409 - time (sec): 0.09 - samples/sec: 6027.03 - lr: 0.000009 - momentum: 0.000000 2024-11-27 20:33:26,470 epoch 173 - iter 2/9 - loss 0.00001921 - time (sec): 0.43 - samples/sec: 2664.28 - lr: 0.000009 - momentum: 0.000000 2024-11-27 20:33:26,602 epoch 173 - iter 3/9 - loss 0.00001889 - time (sec): 0.56 - samples/sec: 3019.69 - lr: 0.000009 - momentum: 0.000000 2024-11-27 20:33:26,734 epoch 173 - iter 4/9 - loss 0.00001721 - time (sec): 0.69 - samples/sec: 3402.39 - lr: 0.000009 - momentum: 0.000000 2024-11-27 20:33:26,871 epoch 173 - iter 5/9 - loss 0.00001696 - time (sec): 0.83 - samples/sec: 3406.23 - lr: 0.000009 - momentum: 0.000000 2024-11-27 20:33:27,040 epoch 173 - iter 6/9 - loss 0.00001678 - time (sec): 1.00 - samples/sec: 3269.84 - lr: 0.000009 - momentum: 0.000000 2024-11-27 20:33:27,242 epoch 173 - iter 7/9 - loss 0.00001695 - time (sec): 1.20 - samples/sec: 3176.59 - lr: 0.000009 - momentum: 0.000000 2024-11-27 20:33:27,394 epoch 173 - iter 8/9 - loss 0.00001775 - time (sec): 1.35 - samples/sec: 3408.45 - lr: 0.000009 - momentum: 0.000000 2024-11-27 20:33:27,550 epoch 173 - iter 9/9 - loss 0.00002162 - time (sec): 1.51 - samples/sec: 3444.98 - lr: 0.000009 - momentum: 0.000000 2024-11-27 20:33:27,550 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:33:27,550 EPOCH 173 done: loss 0.0000 - lr: 0.000009 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 5.32it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 5.31it/s] 2024-11-27 20:33:27,758 DEV : loss 3.669160842895508 - f1-score (micro avg) 0.3648 2024-11-27 20:33:27,759 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:33:27,858 epoch 174 - iter 1/9 - loss 0.00028818 - time (sec): 0.10 - samples/sec: 6343.16 - lr: 0.000009 - momentum: 0.000000 2024-11-27 20:33:27,993 epoch 174 - iter 2/9 - loss 0.00017845 - time (sec): 0.23 - samples/sec: 4575.02 - lr: 0.000009 - momentum: 0.000000 2024-11-27 20:33:28,130 epoch 174 - iter 3/9 - loss 0.00012691 - time (sec): 0.37 - samples/sec: 4358.90 - lr: 0.000009 - momentum: 0.000000 2024-11-27 20:33:28,287 epoch 174 - iter 4/9 - loss 0.00010395 - time (sec): 0.53 - samples/sec: 4310.37 - lr: 0.000009 - momentum: 0.000000 2024-11-27 20:33:28,461 epoch 174 - iter 5/9 - loss 0.00008769 - time (sec): 0.70 - samples/sec: 3936.79 - lr: 0.000009 - momentum: 0.000000 2024-11-27 20:33:28,633 epoch 174 - iter 6/9 - loss 0.00007634 - time (sec): 0.87 - samples/sec: 3854.01 - lr: 0.000009 - momentum: 0.000000 2024-11-27 20:33:28,802 epoch 174 - iter 7/9 - loss 0.00006718 - time (sec): 1.04 - samples/sec: 3804.50 - lr: 0.000009 - momentum: 0.000000 2024-11-27 20:33:28,957 epoch 174 - iter 8/9 - loss 0.00006105 - time (sec): 1.20 - samples/sec: 3803.63 - lr: 0.000009 - momentum: 0.000000 2024-11-27 20:33:29,119 epoch 174 - iter 9/9 - loss 0.00005493 - time (sec): 1.36 - samples/sec: 3824.89 - lr: 0.000009 - momentum: 0.000000 2024-11-27 20:33:29,119 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:33:29,119 EPOCH 174 done: loss 0.0001 - lr: 0.000009 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 4.08it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 4.08it/s] 2024-11-27 20:33:29,383 DEV : loss 3.680607557296753 - f1-score (micro avg) 0.3648 2024-11-27 20:33:29,385 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:33:29,485 epoch 175 - iter 1/9 - loss 0.00001342 - time (sec): 0.10 - samples/sec: 5529.95 - lr: 0.000009 - momentum: 0.000000 2024-11-27 20:33:29,628 epoch 175 - iter 2/9 - loss 0.00001524 - time (sec): 0.24 - samples/sec: 4609.26 - lr: 0.000009 - momentum: 0.000000 2024-11-27 20:33:29,771 epoch 175 - iter 3/9 - loss 0.00002160 - time (sec): 0.39 - samples/sec: 4551.24 - lr: 0.000009 - momentum: 0.000000 2024-11-27 20:33:29,950 epoch 175 - iter 4/9 - loss 0.00001846 - time (sec): 0.56 - samples/sec: 4048.70 - lr: 0.000009 - momentum: 0.000000 2024-11-27 20:33:30,130 epoch 175 - iter 5/9 - loss 0.00001739 - time (sec): 0.74 - samples/sec: 3999.44 - lr: 0.000009 - momentum: 0.000000 2024-11-27 20:33:30,299 epoch 175 - iter 6/9 - loss 0.00001870 - time (sec): 0.91 - samples/sec: 3849.45 - lr: 0.000009 - momentum: 0.000000 2024-11-27 20:33:30,441 epoch 175 - iter 7/9 - loss 0.00013785 - time (sec): 1.06 - samples/sec: 3869.08 - lr: 0.000009 - momentum: 0.000000 2024-11-27 20:33:30,598 epoch 175 - iter 8/9 - loss 0.00012642 - time (sec): 1.21 - samples/sec: 3765.32 - lr: 0.000009 - momentum: 0.000000 2024-11-27 20:33:30,758 epoch 175 - iter 9/9 - loss 0.00011254 - time (sec): 1.37 - samples/sec: 3787.75 - lr: 0.000009 - momentum: 0.000000 2024-11-27 20:33:30,758 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:33:30,758 EPOCH 175 done: loss 0.0001 - lr: 0.000009 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 5.82it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 5.81it/s] 2024-11-27 20:33:30,949 DEV : loss 3.68860125541687 - f1-score (micro avg) 0.3694 2024-11-27 20:33:30,950 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:33:31,056 epoch 176 - iter 1/9 - loss 0.00001234 - time (sec): 0.10 - samples/sec: 6014.95 - lr: 0.000009 - momentum: 0.000000 2024-11-27 20:33:31,195 epoch 176 - iter 2/9 - loss 0.00001325 - time (sec): 0.24 - samples/sec: 4824.45 - lr: 0.000009 - momentum: 0.000000 2024-11-27 20:33:31,336 epoch 176 - iter 3/9 - loss 0.00001473 - time (sec): 0.38 - samples/sec: 4291.05 - lr: 0.000009 - momentum: 0.000000 2024-11-27 20:33:31,488 epoch 176 - iter 4/9 - loss 0.00001858 - time (sec): 0.54 - samples/sec: 4129.11 - lr: 0.000009 - momentum: 0.000000 2024-11-27 20:33:31,620 epoch 176 - iter 5/9 - loss 0.00001910 - time (sec): 0.67 - samples/sec: 4094.48 - lr: 0.000009 - momentum: 0.000000 2024-11-27 20:33:31,748 epoch 176 - iter 6/9 - loss 0.00001775 - time (sec): 0.80 - samples/sec: 4110.20 - lr: 0.000009 - momentum: 0.000000 2024-11-27 20:33:31,946 epoch 176 - iter 7/9 - loss 0.00001756 - time (sec): 0.99 - samples/sec: 4058.74 - lr: 0.000009 - momentum: 0.000000 2024-11-27 20:33:32,090 epoch 176 - iter 8/9 - loss 0.00001682 - time (sec): 1.14 - samples/sec: 4038.73 - lr: 0.000009 - momentum: 0.000000 2024-11-27 20:33:32,232 epoch 176 - iter 9/9 - loss 0.00001827 - time (sec): 1.28 - samples/sec: 4057.96 - lr: 0.000009 - momentum: 0.000000 2024-11-27 20:33:32,232 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:33:32,233 EPOCH 176 done: loss 0.0000 - lr: 0.000009 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 4.69it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 4.68it/s] 2024-11-27 20:33:32,465 DEV : loss 3.6966233253479004 - f1-score (micro avg) 0.3718 2024-11-27 20:33:32,466 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:33:32,573 epoch 177 - iter 1/9 - loss 0.00003322 - time (sec): 0.11 - samples/sec: 5932.00 - lr: 0.000009 - momentum: 0.000000 2024-11-27 20:33:32,710 epoch 177 - iter 2/9 - loss 0.00002224 - time (sec): 0.24 - samples/sec: 4920.09 - lr: 0.000009 - momentum: 0.000000 2024-11-27 20:33:32,866 epoch 177 - iter 3/9 - loss 0.00002127 - time (sec): 0.40 - samples/sec: 4965.53 - lr: 0.000008 - momentum: 0.000000 2024-11-27 20:33:33,027 epoch 177 - iter 4/9 - loss 0.00002057 - time (sec): 0.56 - samples/sec: 4512.31 - lr: 0.000008 - momentum: 0.000000 2024-11-27 20:33:33,155 epoch 177 - iter 5/9 - loss 0.00001848 - time (sec): 0.69 - samples/sec: 4507.55 - lr: 0.000008 - momentum: 0.000000 2024-11-27 20:33:33,415 epoch 177 - iter 6/9 - loss 0.00002314 - time (sec): 0.95 - samples/sec: 3905.81 - lr: 0.000008 - momentum: 0.000000 2024-11-27 20:33:33,562 epoch 177 - iter 7/9 - loss 0.00002128 - time (sec): 1.09 - samples/sec: 3903.91 - lr: 0.000008 - momentum: 0.000000 2024-11-27 20:33:33,714 epoch 177 - iter 8/9 - loss 0.00002107 - time (sec): 1.25 - samples/sec: 3825.01 - lr: 0.000008 - momentum: 0.000000 2024-11-27 20:33:33,999 epoch 177 - iter 9/9 - loss 0.00002034 - time (sec): 1.53 - samples/sec: 3392.35 - lr: 0.000008 - momentum: 0.000000 2024-11-27 20:33:34,000 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:33:34,000 EPOCH 177 done: loss 0.0000 - lr: 0.000008 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.48it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.46it/s] 2024-11-27 20:33:34,173 DEV : loss 3.701200246810913 - f1-score (micro avg) 0.3718 2024-11-27 20:33:34,174 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:33:34,277 epoch 178 - iter 1/9 - loss 0.00000999 - time (sec): 0.10 - samples/sec: 6141.42 - lr: 0.000008 - momentum: 0.000000 2024-11-27 20:33:34,414 epoch 178 - iter 2/9 - loss 0.00001521 - time (sec): 0.24 - samples/sec: 5281.37 - lr: 0.000008 - momentum: 0.000000 2024-11-27 20:33:34,552 epoch 178 - iter 3/9 - loss 0.00001788 - time (sec): 0.38 - samples/sec: 4972.00 - lr: 0.000008 - momentum: 0.000000 2024-11-27 20:33:34,701 epoch 178 - iter 4/9 - loss 0.00001808 - time (sec): 0.53 - samples/sec: 4485.36 - lr: 0.000008 - momentum: 0.000000 2024-11-27 20:33:34,848 epoch 178 - iter 5/9 - loss 0.00001796 - time (sec): 0.67 - samples/sec: 4377.12 - lr: 0.000008 - momentum: 0.000000 2024-11-27 20:33:35,009 epoch 178 - iter 6/9 - loss 0.00001859 - time (sec): 0.83 - samples/sec: 4298.02 - lr: 0.000008 - momentum: 0.000000 2024-11-27 20:33:35,171 epoch 178 - iter 7/9 - loss 0.00001908 - time (sec): 1.00 - samples/sec: 4088.23 - lr: 0.000008 - momentum: 0.000000 2024-11-27 20:33:35,337 epoch 178 - iter 8/9 - loss 0.00002139 - time (sec): 1.16 - samples/sec: 4024.92 - lr: 0.000008 - momentum: 0.000000 2024-11-27 20:33:35,491 epoch 178 - iter 9/9 - loss 0.00002130 - time (sec): 1.32 - samples/sec: 3952.03 - lr: 0.000008 - momentum: 0.000000 2024-11-27 20:33:35,491 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:33:35,491 EPOCH 178 done: loss 0.0000 - lr: 0.000008 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 5.45it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 5.45it/s] 2024-11-27 20:33:35,693 DEV : loss 3.7043612003326416 - f1-score (micro avg) 0.3718 2024-11-27 20:33:35,695 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:33:35,810 epoch 179 - iter 1/9 - loss 0.00001375 - time (sec): 0.11 - samples/sec: 4749.79 - lr: 0.000008 - momentum: 0.000000 2024-11-27 20:33:35,984 epoch 179 - iter 2/9 - loss 0.00001545 - time (sec): 0.29 - samples/sec: 3568.07 - lr: 0.000008 - momentum: 0.000000 2024-11-27 20:33:36,141 epoch 179 - iter 3/9 - loss 0.00002153 - time (sec): 0.45 - samples/sec: 3603.14 - lr: 0.000008 - momentum: 0.000000 2024-11-27 20:33:36,283 epoch 179 - iter 4/9 - loss 0.00001889 - time (sec): 0.59 - samples/sec: 3581.91 - lr: 0.000008 - momentum: 0.000000 2024-11-27 20:33:36,435 epoch 179 - iter 5/9 - loss 0.00001772 - time (sec): 0.74 - samples/sec: 3622.10 - lr: 0.000008 - momentum: 0.000000 2024-11-27 20:33:36,598 epoch 179 - iter 6/9 - loss 0.00001707 - time (sec): 0.90 - samples/sec: 3683.59 - lr: 0.000008 - momentum: 0.000000 2024-11-27 20:33:36,751 epoch 179 - iter 7/9 - loss 0.00001707 - time (sec): 1.06 - samples/sec: 3725.47 - lr: 0.000008 - momentum: 0.000000 2024-11-27 20:33:36,901 epoch 179 - iter 8/9 - loss 0.00001593 - time (sec): 1.20 - samples/sec: 3759.65 - lr: 0.000008 - momentum: 0.000000 2024-11-27 20:33:37,047 epoch 179 - iter 9/9 - loss 0.00001519 - time (sec): 1.35 - samples/sec: 3845.72 - lr: 0.000008 - momentum: 0.000000 2024-11-27 20:33:37,047 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:33:37,047 EPOCH 179 done: loss 0.0000 - lr: 0.000008 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.34it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.33it/s] 2024-11-27 20:33:37,224 DEV : loss 3.707120180130005 - f1-score (micro avg) 0.3718 2024-11-27 20:33:37,226 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:33:37,321 epoch 180 - iter 1/9 - loss 0.00001479 - time (sec): 0.09 - samples/sec: 5994.68 - lr: 0.000008 - momentum: 0.000000 2024-11-27 20:33:37,451 epoch 180 - iter 2/9 - loss 0.00001365 - time (sec): 0.22 - samples/sec: 4961.84 - lr: 0.000008 - momentum: 0.000000 2024-11-27 20:33:37,602 epoch 180 - iter 3/9 - loss 0.00001601 - time (sec): 0.38 - samples/sec: 4441.32 - lr: 0.000008 - momentum: 0.000000 2024-11-27 20:33:37,743 epoch 180 - iter 4/9 - loss 0.00002279 - time (sec): 0.52 - samples/sec: 4128.16 - lr: 0.000008 - momentum: 0.000000 2024-11-27 20:33:37,868 epoch 180 - iter 5/9 - loss 0.00002151 - time (sec): 0.64 - samples/sec: 4175.75 - lr: 0.000008 - momentum: 0.000000 2024-11-27 20:33:38,023 epoch 180 - iter 6/9 - loss 0.00002136 - time (sec): 0.80 - samples/sec: 4224.10 - lr: 0.000008 - momentum: 0.000000 2024-11-27 20:33:38,378 epoch 180 - iter 7/9 - loss 0.00002084 - time (sec): 1.15 - samples/sec: 3477.76 - lr: 0.000008 - momentum: 0.000000 2024-11-27 20:33:38,531 epoch 180 - iter 8/9 - loss 0.00002000 - time (sec): 1.30 - samples/sec: 3621.96 - lr: 0.000008 - momentum: 0.000000 2024-11-27 20:33:38,684 epoch 180 - iter 9/9 - loss 0.00002070 - time (sec): 1.46 - samples/sec: 3564.87 - lr: 0.000008 - momentum: 0.000000 2024-11-27 20:33:38,685 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:33:38,685 EPOCH 180 done: loss 0.0000 - lr: 0.000008 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 4.28it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 4.28it/s] 2024-11-27 20:33:38,937 DEV : loss 3.7095305919647217 - f1-score (micro avg) 0.3718 2024-11-27 20:33:38,938 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:33:39,037 epoch 181 - iter 1/9 - loss 0.00002416 - time (sec): 0.10 - samples/sec: 6483.41 - lr: 0.000008 - momentum: 0.000000 2024-11-27 20:33:39,180 epoch 181 - iter 2/9 - loss 0.00001985 - time (sec): 0.24 - samples/sec: 5069.43 - lr: 0.000008 - momentum: 0.000000 2024-11-27 20:33:39,320 epoch 181 - iter 3/9 - loss 0.00001596 - time (sec): 0.38 - samples/sec: 4708.56 - lr: 0.000008 - momentum: 0.000000 2024-11-27 20:33:39,513 epoch 181 - iter 4/9 - loss 0.00001513 - time (sec): 0.57 - samples/sec: 4081.18 - lr: 0.000008 - momentum: 0.000000 2024-11-27 20:33:39,695 epoch 181 - iter 5/9 - loss 0.00001703 - time (sec): 0.76 - samples/sec: 3935.86 - lr: 0.000008 - momentum: 0.000000 2024-11-27 20:33:39,838 epoch 181 - iter 6/9 - loss 0.00001620 - time (sec): 0.90 - samples/sec: 3970.39 - lr: 0.000008 - momentum: 0.000000 2024-11-27 20:33:39,970 epoch 181 - iter 7/9 - loss 0.00001830 - time (sec): 1.03 - samples/sec: 4002.97 - lr: 0.000008 - momentum: 0.000000 2024-11-27 20:33:40,118 epoch 181 - iter 8/9 - loss 0.00001805 - time (sec): 1.18 - samples/sec: 3966.30 - lr: 0.000008 - momentum: 0.000000 2024-11-27 20:33:40,392 epoch 181 - iter 9/9 - loss 0.00001847 - time (sec): 1.45 - samples/sec: 3578.13 - lr: 0.000008 - momentum: 0.000000 2024-11-27 20:33:40,392 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:33:40,393 EPOCH 181 done: loss 0.0000 - lr: 0.000008 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.16it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.15it/s] 2024-11-27 20:33:40,574 DEV : loss 3.712512254714966 - f1-score (micro avg) 0.3718 2024-11-27 20:33:40,575 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:33:40,683 epoch 182 - iter 1/9 - loss 0.00000933 - time (sec): 0.11 - samples/sec: 6273.49 - lr: 0.000008 - momentum: 0.000000 2024-11-27 20:33:40,811 epoch 182 - iter 2/9 - loss 0.00001202 - time (sec): 0.24 - samples/sec: 5038.24 - lr: 0.000007 - momentum: 0.000000 2024-11-27 20:33:40,965 epoch 182 - iter 3/9 - loss 0.00001329 - time (sec): 0.39 - samples/sec: 4589.85 - lr: 0.000007 - momentum: 0.000000 2024-11-27 20:33:41,198 epoch 182 - iter 4/9 - loss 0.00001666 - time (sec): 0.62 - samples/sec: 3879.28 - lr: 0.000007 - momentum: 0.000000 2024-11-27 20:33:41,346 epoch 182 - iter 5/9 - loss 0.00001766 - time (sec): 0.77 - samples/sec: 3912.54 - lr: 0.000007 - momentum: 0.000000 2024-11-27 20:33:41,485 epoch 182 - iter 6/9 - loss 0.00001709 - time (sec): 0.91 - samples/sec: 3930.83 - lr: 0.000007 - momentum: 0.000000 2024-11-27 20:33:41,622 epoch 182 - iter 7/9 - loss 0.00001726 - time (sec): 1.05 - samples/sec: 3902.97 - lr: 0.000007 - momentum: 0.000000 2024-11-27 20:33:41,787 epoch 182 - iter 8/9 - loss 0.00002956 - time (sec): 1.21 - samples/sec: 3874.46 - lr: 0.000007 - momentum: 0.000000 2024-11-27 20:33:42,016 epoch 182 - iter 9/9 - loss 0.00003006 - time (sec): 1.44 - samples/sec: 3609.74 - lr: 0.000007 - momentum: 0.000000 2024-11-27 20:33:42,016 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:33:42,016 EPOCH 182 done: loss 0.0000 - lr: 0.000007 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.55it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.54it/s] 2024-11-27 20:33:42,188 DEV : loss 3.7141895294189453 - f1-score (micro avg) 0.3718 2024-11-27 20:33:42,189 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:33:42,274 epoch 183 - iter 1/9 - loss 0.00001412 - time (sec): 0.08 - samples/sec: 5368.01 - lr: 0.000007 - momentum: 0.000000 2024-11-27 20:33:42,407 epoch 183 - iter 2/9 - loss 0.00002579 - time (sec): 0.22 - samples/sec: 5097.61 - lr: 0.000007 - momentum: 0.000000 2024-11-27 20:33:42,559 epoch 183 - iter 3/9 - loss 0.00002510 - time (sec): 0.37 - samples/sec: 4617.60 - lr: 0.000007 - momentum: 0.000000 2024-11-27 20:33:42,727 epoch 183 - iter 4/9 - loss 0.00002572 - time (sec): 0.54 - samples/sec: 4368.87 - lr: 0.000007 - momentum: 0.000000 2024-11-27 20:33:43,036 epoch 183 - iter 5/9 - loss 0.00002561 - time (sec): 0.85 - samples/sec: 3334.12 - lr: 0.000007 - momentum: 0.000000 2024-11-27 20:33:43,162 epoch 183 - iter 6/9 - loss 0.00002441 - time (sec): 0.97 - samples/sec: 3473.95 - lr: 0.000007 - momentum: 0.000000 2024-11-27 20:33:43,297 epoch 183 - iter 7/9 - loss 0.00002227 - time (sec): 1.11 - samples/sec: 3556.61 - lr: 0.000007 - momentum: 0.000000 2024-11-27 20:33:43,449 epoch 183 - iter 8/9 - loss 0.00002167 - time (sec): 1.26 - samples/sec: 3555.50 - lr: 0.000007 - momentum: 0.000000 2024-11-27 20:33:43,608 epoch 183 - iter 9/9 - loss 0.00002087 - time (sec): 1.42 - samples/sec: 3665.03 - lr: 0.000007 - momentum: 0.000000 2024-11-27 20:33:43,609 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:33:43,609 EPOCH 183 done: loss 0.0000 - lr: 0.000007 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 5.51it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 5.50it/s] 2024-11-27 20:33:43,809 DEV : loss 3.7137763500213623 - f1-score (micro avg) 0.3718 2024-11-27 20:33:43,811 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:33:43,911 epoch 184 - iter 1/9 - loss 0.00004354 - time (sec): 0.10 - samples/sec: 6047.70 - lr: 0.000007 - momentum: 0.000000 2024-11-27 20:33:44,053 epoch 184 - iter 2/9 - loss 0.00002817 - time (sec): 0.24 - samples/sec: 5044.47 - lr: 0.000007 - momentum: 0.000000 2024-11-27 20:33:44,192 epoch 184 - iter 3/9 - loss 0.00002191 - time (sec): 0.38 - samples/sec: 4686.88 - lr: 0.000007 - momentum: 0.000000 2024-11-27 20:33:44,343 epoch 184 - iter 4/9 - loss 0.00002304 - time (sec): 0.53 - samples/sec: 4278.38 - lr: 0.000007 - momentum: 0.000000 2024-11-27 20:33:44,461 epoch 184 - iter 5/9 - loss 0.00002086 - time (sec): 0.65 - samples/sec: 4193.01 - lr: 0.000007 - momentum: 0.000000 2024-11-27 20:33:44,710 epoch 184 - iter 6/9 - loss 0.00001895 - time (sec): 0.90 - samples/sec: 3736.42 - lr: 0.000007 - momentum: 0.000000 2024-11-27 20:33:44,944 epoch 184 - iter 7/9 - loss 0.00001905 - time (sec): 1.13 - samples/sec: 3464.37 - lr: 0.000007 - momentum: 0.000000 2024-11-27 20:33:45,086 epoch 184 - iter 8/9 - loss 0.00001816 - time (sec): 1.27 - samples/sec: 3586.31 - lr: 0.000007 - momentum: 0.000000 2024-11-27 20:33:45,300 epoch 184 - iter 9/9 - loss 0.00001766 - time (sec): 1.49 - samples/sec: 3491.75 - lr: 0.000007 - momentum: 0.000000 2024-11-27 20:33:45,300 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:33:45,301 EPOCH 184 done: loss 0.0000 - lr: 0.000007 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 4.01it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 4.00it/s] 2024-11-27 20:33:45,569 DEV : loss 3.7182493209838867 - f1-score (micro avg) 0.3671 2024-11-27 20:33:45,570 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:33:45,669 epoch 185 - iter 1/9 - loss 0.00000859 - time (sec): 0.10 - samples/sec: 5845.51 - lr: 0.000007 - momentum: 0.000000 2024-11-27 20:33:45,825 epoch 185 - iter 2/9 - loss 0.00001204 - time (sec): 0.25 - samples/sec: 5338.23 - lr: 0.000007 - momentum: 0.000000 2024-11-27 20:33:46,117 epoch 185 - iter 3/9 - loss 0.00001324 - time (sec): 0.55 - samples/sec: 3659.89 - lr: 0.000007 - momentum: 0.000000 2024-11-27 20:33:46,269 epoch 185 - iter 4/9 - loss 0.00001350 - time (sec): 0.70 - samples/sec: 3733.69 - lr: 0.000007 - momentum: 0.000000 2024-11-27 20:33:46,404 epoch 185 - iter 5/9 - loss 0.00001376 - time (sec): 0.83 - samples/sec: 3709.68 - lr: 0.000007 - momentum: 0.000000 2024-11-27 20:33:46,658 epoch 185 - iter 6/9 - loss 0.00001538 - time (sec): 1.09 - samples/sec: 3281.14 - lr: 0.000007 - momentum: 0.000000 2024-11-27 20:33:46,815 epoch 185 - iter 7/9 - loss 0.00001526 - time (sec): 1.24 - samples/sec: 3427.01 - lr: 0.000007 - momentum: 0.000000 2024-11-27 20:33:46,954 epoch 185 - iter 8/9 - loss 0.00001996 - time (sec): 1.38 - samples/sec: 3410.94 - lr: 0.000007 - momentum: 0.000000 2024-11-27 20:33:47,106 epoch 185 - iter 9/9 - loss 0.00002005 - time (sec): 1.53 - samples/sec: 3387.09 - lr: 0.000007 - momentum: 0.000000 2024-11-27 20:33:47,106 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:33:47,106 EPOCH 185 done: loss 0.0000 - lr: 0.000007 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 4.32it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 4.32it/s] 2024-11-27 20:33:47,357 DEV : loss 3.7258005142211914 - f1-score (micro avg) 0.3718 2024-11-27 20:33:47,358 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:33:47,451 epoch 186 - iter 1/9 - loss 0.00001463 - time (sec): 0.09 - samples/sec: 6084.87 - lr: 0.000007 - momentum: 0.000000 2024-11-27 20:33:47,581 epoch 186 - iter 2/9 - loss 0.00001657 - time (sec): 0.22 - samples/sec: 4933.91 - lr: 0.000007 - momentum: 0.000000 2024-11-27 20:33:47,726 epoch 186 - iter 3/9 - loss 0.00001916 - time (sec): 0.37 - samples/sec: 4999.95 - lr: 0.000007 - momentum: 0.000000 2024-11-27 20:33:47,897 epoch 186 - iter 4/9 - loss 0.00001832 - time (sec): 0.54 - samples/sec: 4245.60 - lr: 0.000007 - momentum: 0.000000 2024-11-27 20:33:48,077 epoch 186 - iter 5/9 - loss 0.00001904 - time (sec): 0.72 - samples/sec: 4229.69 - lr: 0.000007 - momentum: 0.000000 2024-11-27 20:33:48,218 epoch 186 - iter 6/9 - loss 0.00001909 - time (sec): 0.86 - samples/sec: 4228.11 - lr: 0.000007 - momentum: 0.000000 2024-11-27 20:33:48,335 epoch 186 - iter 7/9 - loss 0.00001981 - time (sec): 0.98 - samples/sec: 4199.94 - lr: 0.000007 - momentum: 0.000000 2024-11-27 20:33:48,483 epoch 186 - iter 8/9 - loss 0.00001989 - time (sec): 1.12 - samples/sec: 4145.58 - lr: 0.000007 - momentum: 0.000000 2024-11-27 20:33:48,648 epoch 186 - iter 9/9 - loss 0.00001887 - time (sec): 1.29 - samples/sec: 4031.20 - lr: 0.000007 - momentum: 0.000000 2024-11-27 20:33:48,648 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:33:48,648 EPOCH 186 done: loss 0.0000 - lr: 0.000007 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 4.96it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 4.95it/s] 2024-11-27 20:33:48,870 DEV : loss 3.73104190826416 - f1-score (micro avg) 0.3791 2024-11-27 20:33:48,871 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:33:48,968 epoch 187 - iter 1/9 - loss 0.00001609 - time (sec): 0.10 - samples/sec: 5186.43 - lr: 0.000006 - momentum: 0.000000 2024-11-27 20:33:49,123 epoch 187 - iter 2/9 - loss 0.00002299 - time (sec): 0.25 - samples/sec: 4305.25 - lr: 0.000006 - momentum: 0.000000 2024-11-27 20:33:49,318 epoch 187 - iter 3/9 - loss 0.00002092 - time (sec): 0.45 - samples/sec: 3845.14 - lr: 0.000006 - momentum: 0.000000 2024-11-27 20:33:49,502 epoch 187 - iter 4/9 - loss 0.00002197 - time (sec): 0.63 - samples/sec: 3552.52 - lr: 0.000006 - momentum: 0.000000 2024-11-27 20:33:49,674 epoch 187 - iter 5/9 - loss 0.00002033 - time (sec): 0.80 - samples/sec: 3569.17 - lr: 0.000006 - momentum: 0.000000 2024-11-27 20:33:49,855 epoch 187 - iter 6/9 - loss 0.00001914 - time (sec): 0.98 - samples/sec: 3533.67 - lr: 0.000006 - momentum: 0.000000 2024-11-27 20:33:50,013 epoch 187 - iter 7/9 - loss 0.00001908 - time (sec): 1.14 - samples/sec: 3481.92 - lr: 0.000006 - momentum: 0.000000 2024-11-27 20:33:50,145 epoch 187 - iter 8/9 - loss 0.00001939 - time (sec): 1.27 - samples/sec: 3569.31 - lr: 0.000006 - momentum: 0.000000 2024-11-27 20:33:50,277 epoch 187 - iter 9/9 - loss 0.00001955 - time (sec): 1.40 - samples/sec: 3699.18 - lr: 0.000006 - momentum: 0.000000 2024-11-27 20:33:50,277 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:33:50,277 EPOCH 187 done: loss 0.0000 - lr: 0.000006 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 5.86it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 5.85it/s] 2024-11-27 20:33:50,467 DEV : loss 3.7346949577331543 - f1-score (micro avg) 0.3791 2024-11-27 20:33:50,468 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:33:50,573 epoch 188 - iter 1/9 - loss 0.00002064 - time (sec): 0.10 - samples/sec: 6110.01 - lr: 0.000006 - momentum: 0.000000 2024-11-27 20:33:50,713 epoch 188 - iter 2/9 - loss 0.00001816 - time (sec): 0.24 - samples/sec: 4687.72 - lr: 0.000006 - momentum: 0.000000 2024-11-27 20:33:51,034 epoch 188 - iter 3/9 - loss 0.00001909 - time (sec): 0.57 - samples/sec: 3077.26 - lr: 0.000006 - momentum: 0.000000 2024-11-27 20:33:51,180 epoch 188 - iter 4/9 - loss 0.00446454 - time (sec): 0.71 - samples/sec: 3151.18 - lr: 0.000006 - momentum: 0.000000 2024-11-27 20:33:51,321 epoch 188 - iter 5/9 - loss 0.00357424 - time (sec): 0.85 - samples/sec: 3292.83 - lr: 0.000006 - momentum: 0.000000 2024-11-27 20:33:51,532 epoch 188 - iter 6/9 - loss 0.00290777 - time (sec): 1.06 - samples/sec: 3254.55 - lr: 0.000006 - momentum: 0.000000 2024-11-27 20:33:51,699 epoch 188 - iter 7/9 - loss 0.00248178 - time (sec): 1.23 - samples/sec: 3297.05 - lr: 0.000006 - momentum: 0.000000 2024-11-27 20:33:51,839 epoch 188 - iter 8/9 - loss 0.00216031 - time (sec): 1.37 - samples/sec: 3404.18 - lr: 0.000006 - momentum: 0.000000 2024-11-27 20:33:51,996 epoch 188 - iter 9/9 - loss 0.00194026 - time (sec): 1.53 - samples/sec: 3402.70 - lr: 0.000006 - momentum: 0.000000 2024-11-27 20:33:51,997 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:33:51,997 EPOCH 188 done: loss 0.0019 - lr: 0.000006 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 3.89it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 3.88it/s] 2024-11-27 20:33:52,273 DEV : loss 3.737330436706543 - f1-score (micro avg) 0.3791 2024-11-27 20:33:52,275 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:33:52,371 epoch 189 - iter 1/9 - loss 0.00001822 - time (sec): 0.10 - samples/sec: 5966.07 - lr: 0.000006 - momentum: 0.000000 2024-11-27 20:33:52,504 epoch 189 - iter 2/9 - loss 0.00001463 - time (sec): 0.23 - samples/sec: 5359.32 - lr: 0.000006 - momentum: 0.000000 2024-11-27 20:33:52,639 epoch 189 - iter 3/9 - loss 0.00002080 - time (sec): 0.36 - samples/sec: 5237.48 - lr: 0.000006 - momentum: 0.000000 2024-11-27 20:33:52,824 epoch 189 - iter 4/9 - loss 0.00002332 - time (sec): 0.55 - samples/sec: 4573.93 - lr: 0.000006 - momentum: 0.000000 2024-11-27 20:33:53,001 epoch 189 - iter 5/9 - loss 0.00002320 - time (sec): 0.72 - samples/sec: 4350.54 - lr: 0.000006 - momentum: 0.000000 2024-11-27 20:33:53,149 epoch 189 - iter 6/9 - loss 0.00002200 - time (sec): 0.87 - samples/sec: 4174.13 - lr: 0.000006 - momentum: 0.000000 2024-11-27 20:33:53,304 epoch 189 - iter 7/9 - loss 0.00002481 - time (sec): 1.03 - samples/sec: 4158.97 - lr: 0.000006 - momentum: 0.000000 2024-11-27 20:33:53,440 epoch 189 - iter 8/9 - loss 0.00002433 - time (sec): 1.16 - samples/sec: 4086.06 - lr: 0.000006 - momentum: 0.000000 2024-11-27 20:33:53,554 epoch 189 - iter 9/9 - loss 0.00002377 - time (sec): 1.28 - samples/sec: 4064.49 - lr: 0.000006 - momentum: 0.000000 2024-11-27 20:33:53,555 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:33:53,555 EPOCH 189 done: loss 0.0000 - lr: 0.000006 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.23it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.22it/s] 2024-11-27 20:33:53,735 DEV : loss 3.7402031421661377 - f1-score (micro avg) 0.3791 2024-11-27 20:33:53,736 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:33:53,843 epoch 190 - iter 1/9 - loss 0.00000911 - time (sec): 0.11 - samples/sec: 5388.07 - lr: 0.000006 - momentum: 0.000000 2024-11-27 20:33:53,979 epoch 190 - iter 2/9 - loss 0.00001100 - time (sec): 0.24 - samples/sec: 4796.75 - lr: 0.000006 - momentum: 0.000000 2024-11-27 20:33:54,123 epoch 190 - iter 3/9 - loss 0.00001288 - time (sec): 0.39 - samples/sec: 4364.42 - lr: 0.000006 - momentum: 0.000000 2024-11-27 20:33:54,276 epoch 190 - iter 4/9 - loss 0.00001233 - time (sec): 0.54 - samples/sec: 4249.35 - lr: 0.000006 - momentum: 0.000000 2024-11-27 20:33:54,480 epoch 190 - iter 5/9 - loss 0.00001228 - time (sec): 0.74 - samples/sec: 3789.66 - lr: 0.000006 - momentum: 0.000000 2024-11-27 20:33:54,620 epoch 190 - iter 6/9 - loss 0.00001126 - time (sec): 0.88 - samples/sec: 3995.84 - lr: 0.000006 - momentum: 0.000000 2024-11-27 20:33:54,779 epoch 190 - iter 7/9 - loss 0.00001097 - time (sec): 1.04 - samples/sec: 3875.24 - lr: 0.000006 - momentum: 0.000000 2024-11-27 20:33:54,959 epoch 190 - iter 8/9 - loss 0.00001165 - time (sec): 1.22 - samples/sec: 3790.37 - lr: 0.000006 - momentum: 0.000000 2024-11-27 20:33:55,140 epoch 190 - iter 9/9 - loss 0.00001241 - time (sec): 1.40 - samples/sec: 3704.08 - lr: 0.000006 - momentum: 0.000000 2024-11-27 20:33:55,140 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:33:55,140 EPOCH 190 done: loss 0.0000 - lr: 0.000006 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 5.19it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 5.18it/s] 2024-11-27 20:33:55,353 DEV : loss 3.7427141666412354 - f1-score (micro avg) 0.3791 2024-11-27 20:33:55,355 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:33:55,454 epoch 191 - iter 1/9 - loss 0.00000941 - time (sec): 0.10 - samples/sec: 5182.41 - lr: 0.000006 - momentum: 0.000000 2024-11-27 20:33:55,594 epoch 191 - iter 2/9 - loss 0.00001784 - time (sec): 0.24 - samples/sec: 4981.25 - lr: 0.000006 - momentum: 0.000000 2024-11-27 20:33:55,748 epoch 191 - iter 3/9 - loss 0.00001824 - time (sec): 0.39 - samples/sec: 4520.86 - lr: 0.000006 - momentum: 0.000000 2024-11-27 20:33:55,919 epoch 191 - iter 4/9 - loss 0.00002130 - time (sec): 0.56 - samples/sec: 4373.08 - lr: 0.000006 - momentum: 0.000000 2024-11-27 20:33:56,166 epoch 191 - iter 5/9 - loss 0.00002520 - time (sec): 0.81 - samples/sec: 3669.73 - lr: 0.000006 - momentum: 0.000000 2024-11-27 20:33:56,301 epoch 191 - iter 6/9 - loss 0.00002316 - time (sec): 0.95 - samples/sec: 3810.48 - lr: 0.000006 - momentum: 0.000000 2024-11-27 20:33:56,450 epoch 191 - iter 7/9 - loss 0.00002237 - time (sec): 1.09 - samples/sec: 3677.53 - lr: 0.000006 - momentum: 0.000000 2024-11-27 20:33:56,699 epoch 191 - iter 8/9 - loss 0.00002273 - time (sec): 1.34 - samples/sec: 3412.91 - lr: 0.000006 - momentum: 0.000000 2024-11-27 20:33:56,861 epoch 191 - iter 9/9 - loss 0.00002312 - time (sec): 1.50 - samples/sec: 3453.19 - lr: 0.000005 - momentum: 0.000000 2024-11-27 20:33:56,861 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:33:56,861 EPOCH 191 done: loss 0.0000 - lr: 0.000005 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 5.77it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 5.76it/s] 2024-11-27 20:33:57,054 DEV : loss 3.74379825592041 - f1-score (micro avg) 0.366 2024-11-27 20:33:57,055 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:33:57,163 epoch 192 - iter 1/9 - loss 0.00004383 - time (sec): 0.11 - samples/sec: 5583.06 - lr: 0.000005 - momentum: 0.000000 2024-11-27 20:33:57,426 epoch 192 - iter 2/9 - loss 0.00004117 - time (sec): 0.37 - samples/sec: 3282.69 - lr: 0.000005 - momentum: 0.000000 2024-11-27 20:33:57,635 epoch 192 - iter 3/9 - loss 0.00003405 - time (sec): 0.58 - samples/sec: 3020.04 - lr: 0.000005 - momentum: 0.000000 2024-11-27 20:33:57,770 epoch 192 - iter 4/9 - loss 0.00002785 - time (sec): 0.71 - samples/sec: 3442.34 - lr: 0.000005 - momentum: 0.000000 2024-11-27 20:33:57,903 epoch 192 - iter 5/9 - loss 0.00002879 - time (sec): 0.85 - samples/sec: 3517.40 - lr: 0.000005 - momentum: 0.000000 2024-11-27 20:33:58,086 epoch 192 - iter 6/9 - loss 0.00002627 - time (sec): 1.03 - samples/sec: 3621.22 - lr: 0.000005 - momentum: 0.000000 2024-11-27 20:33:58,394 epoch 192 - iter 7/9 - loss 0.00002482 - time (sec): 1.34 - samples/sec: 3184.96 - lr: 0.000005 - momentum: 0.000000 2024-11-27 20:33:58,538 epoch 192 - iter 8/9 - loss 0.00002306 - time (sec): 1.48 - samples/sec: 3262.67 - lr: 0.000005 - momentum: 0.000000 2024-11-27 20:33:58,673 epoch 192 - iter 9/9 - loss 0.00002235 - time (sec): 1.62 - samples/sec: 3214.47 - lr: 0.000005 - momentum: 0.000000 2024-11-27 20:33:58,673 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:33:58,673 EPOCH 192 done: loss 0.0000 - lr: 0.000005 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 5.94it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 5.93it/s] 2024-11-27 20:33:58,860 DEV : loss 3.745633602142334 - f1-score (micro avg) 0.366 2024-11-27 20:33:58,862 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:33:58,983 epoch 193 - iter 1/9 - loss 0.00003104 - time (sec): 0.12 - samples/sec: 5957.87 - lr: 0.000005 - momentum: 0.000000 2024-11-27 20:33:59,140 epoch 193 - iter 2/9 - loss 0.00002063 - time (sec): 0.28 - samples/sec: 4271.00 - lr: 0.000005 - momentum: 0.000000 2024-11-27 20:33:59,300 epoch 193 - iter 3/9 - loss 0.00001843 - time (sec): 0.44 - samples/sec: 3880.44 - lr: 0.000005 - momentum: 0.000000 2024-11-27 20:33:59,441 epoch 193 - iter 4/9 - loss 0.00002468 - time (sec): 0.58 - samples/sec: 3942.20 - lr: 0.000005 - momentum: 0.000000 2024-11-27 20:33:59,628 epoch 193 - iter 5/9 - loss 0.00002211 - time (sec): 0.77 - samples/sec: 3717.58 - lr: 0.000005 - momentum: 0.000000 2024-11-27 20:33:59,843 epoch 193 - iter 6/9 - loss 0.00002268 - time (sec): 0.98 - samples/sec: 3570.41 - lr: 0.000005 - momentum: 0.000000 2024-11-27 20:34:00,018 epoch 193 - iter 7/9 - loss 0.00002077 - time (sec): 1.16 - samples/sec: 3478.70 - lr: 0.000005 - momentum: 0.000000 2024-11-27 20:34:00,154 epoch 193 - iter 8/9 - loss 0.00002025 - time (sec): 1.29 - samples/sec: 3536.50 - lr: 0.000005 - momentum: 0.000000 2024-11-27 20:34:00,379 epoch 193 - iter 9/9 - loss 0.00002074 - time (sec): 1.52 - samples/sec: 3427.48 - lr: 0.000005 - momentum: 0.000000 2024-11-27 20:34:00,379 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:34:00,380 EPOCH 193 done: loss 0.0000 - lr: 0.000005 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.41it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.40it/s] 2024-11-27 20:34:00,555 DEV : loss 3.7475202083587646 - f1-score (micro avg) 0.366 2024-11-27 20:34:00,556 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:34:00,664 epoch 194 - iter 1/9 - loss 0.00001294 - time (sec): 0.11 - samples/sec: 6675.95 - lr: 0.000005 - momentum: 0.000000 2024-11-27 20:34:00,854 epoch 194 - iter 2/9 - loss 0.00001195 - time (sec): 0.30 - samples/sec: 3988.10 - lr: 0.000005 - momentum: 0.000000 2024-11-27 20:34:01,088 epoch 194 - iter 3/9 - loss 0.00001585 - time (sec): 0.53 - samples/sec: 3354.30 - lr: 0.000005 - momentum: 0.000000 2024-11-27 20:34:01,214 epoch 194 - iter 4/9 - loss 0.00001417 - time (sec): 0.66 - samples/sec: 3541.07 - lr: 0.000005 - momentum: 0.000000 2024-11-27 20:34:01,359 epoch 194 - iter 5/9 - loss 0.00001917 - time (sec): 0.80 - samples/sec: 3606.29 - lr: 0.000005 - momentum: 0.000000 2024-11-27 20:34:01,640 epoch 194 - iter 6/9 - loss 0.00001908 - time (sec): 1.08 - samples/sec: 3258.41 - lr: 0.000005 - momentum: 0.000000 2024-11-27 20:34:01,985 epoch 194 - iter 7/9 - loss 0.00001851 - time (sec): 1.43 - samples/sec: 2838.50 - lr: 0.000005 - momentum: 0.000000 2024-11-27 20:34:02,131 epoch 194 - iter 8/9 - loss 0.00002011 - time (sec): 1.57 - samples/sec: 2987.96 - lr: 0.000005 - momentum: 0.000000 2024-11-27 20:34:02,265 epoch 194 - iter 9/9 - loss 0.00002220 - time (sec): 1.71 - samples/sec: 3041.63 - lr: 0.000005 - momentum: 0.000000 2024-11-27 20:34:02,266 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:34:02,266 EPOCH 194 done: loss 0.0000 - lr: 0.000005 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 5.86it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 5.86it/s] 2024-11-27 20:34:02,456 DEV : loss 3.7494444847106934 - f1-score (micro avg) 0.3506 2024-11-27 20:34:02,457 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:34:02,569 epoch 195 - iter 1/9 - loss 0.00001768 - time (sec): 0.11 - samples/sec: 5806.94 - lr: 0.000005 - momentum: 0.000000 2024-11-27 20:34:02,746 epoch 195 - iter 2/9 - loss 0.00001603 - time (sec): 0.29 - samples/sec: 4152.59 - lr: 0.000005 - momentum: 0.000000 2024-11-27 20:34:02,907 epoch 195 - iter 3/9 - loss 0.00001483 - time (sec): 0.45 - samples/sec: 4353.20 - lr: 0.000005 - momentum: 0.000000 2024-11-27 20:34:03,044 epoch 195 - iter 4/9 - loss 0.00001437 - time (sec): 0.59 - samples/sec: 4156.56 - lr: 0.000005 - momentum: 0.000000 2024-11-27 20:34:03,175 epoch 195 - iter 5/9 - loss 0.00001443 - time (sec): 0.72 - samples/sec: 4180.31 - lr: 0.000005 - momentum: 0.000000 2024-11-27 20:34:03,308 epoch 195 - iter 6/9 - loss 0.00001485 - time (sec): 0.85 - samples/sec: 4030.06 - lr: 0.000005 - momentum: 0.000000 2024-11-27 20:34:03,467 epoch 195 - iter 7/9 - loss 0.00001789 - time (sec): 1.01 - samples/sec: 4068.74 - lr: 0.000005 - momentum: 0.000000 2024-11-27 20:34:03,624 epoch 195 - iter 8/9 - loss 0.00001878 - time (sec): 1.17 - samples/sec: 3971.17 - lr: 0.000005 - momentum: 0.000000 2024-11-27 20:34:03,790 epoch 195 - iter 9/9 - loss 0.00001886 - time (sec): 1.33 - samples/sec: 3902.97 - lr: 0.000005 - momentum: 0.000000 2024-11-27 20:34:03,790 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:34:03,790 EPOCH 195 done: loss 0.0000 - lr: 0.000005 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 5.65it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 5.64it/s] 2024-11-27 20:34:03,986 DEV : loss 3.751466751098633 - f1-score (micro avg) 0.366 2024-11-27 20:34:03,988 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:34:04,092 epoch 196 - iter 1/9 - loss 0.00003543 - time (sec): 0.10 - samples/sec: 5679.37 - lr: 0.000005 - momentum: 0.000000 2024-11-27 20:34:04,221 epoch 196 - iter 2/9 - loss 0.00002449 - time (sec): 0.23 - samples/sec: 4544.41 - lr: 0.000005 - momentum: 0.000000 2024-11-27 20:34:04,392 epoch 196 - iter 3/9 - loss 0.00002440 - time (sec): 0.40 - samples/sec: 4092.57 - lr: 0.000005 - momentum: 0.000000 2024-11-27 20:34:04,576 epoch 196 - iter 4/9 - loss 0.00002389 - time (sec): 0.59 - samples/sec: 3620.00 - lr: 0.000005 - momentum: 0.000000 2024-11-27 20:34:04,729 epoch 196 - iter 5/9 - loss 0.00002434 - time (sec): 0.74 - samples/sec: 3762.71 - lr: 0.000005 - momentum: 0.000000 2024-11-27 20:34:04,905 epoch 196 - iter 6/9 - loss 0.00002350 - time (sec): 0.92 - samples/sec: 3644.69 - lr: 0.000005 - momentum: 0.000000 2024-11-27 20:34:05,043 epoch 196 - iter 7/9 - loss 0.00002279 - time (sec): 1.05 - samples/sec: 3728.05 - lr: 0.000005 - momentum: 0.000000 2024-11-27 20:34:05,209 epoch 196 - iter 8/9 - loss 0.00002158 - time (sec): 1.22 - samples/sec: 3724.23 - lr: 0.000004 - momentum: 0.000000 2024-11-27 20:34:05,393 epoch 196 - iter 9/9 - loss 0.00002133 - time (sec): 1.40 - samples/sec: 3700.92 - lr: 0.000004 - momentum: 0.000000 2024-11-27 20:34:05,393 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:34:05,393 EPOCH 196 done: loss 0.0000 - lr: 0.000004 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 5.14it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 5.13it/s] 2024-11-27 20:34:05,608 DEV : loss 3.752992868423462 - f1-score (micro avg) 0.366 2024-11-27 20:34:05,609 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:34:05,700 epoch 197 - iter 1/9 - loss 0.00001909 - time (sec): 0.09 - samples/sec: 5730.64 - lr: 0.000004 - momentum: 0.000000 2024-11-27 20:34:05,827 epoch 197 - iter 2/9 - loss 0.00003085 - time (sec): 0.22 - samples/sec: 5595.57 - lr: 0.000004 - momentum: 0.000000 2024-11-27 20:34:05,961 epoch 197 - iter 3/9 - loss 0.00002391 - time (sec): 0.35 - samples/sec: 4969.52 - lr: 0.000004 - momentum: 0.000000 2024-11-27 20:34:06,110 epoch 197 - iter 4/9 - loss 0.00002165 - time (sec): 0.50 - samples/sec: 4604.97 - lr: 0.000004 - momentum: 0.000000 2024-11-27 20:34:06,291 epoch 197 - iter 5/9 - loss 0.00002097 - time (sec): 0.68 - samples/sec: 4503.04 - lr: 0.000004 - momentum: 0.000000 2024-11-27 20:34:06,631 epoch 197 - iter 6/9 - loss 0.00002069 - time (sec): 1.02 - samples/sec: 3570.35 - lr: 0.000004 - momentum: 0.000000 2024-11-27 20:34:06,772 epoch 197 - iter 7/9 - loss 0.00002214 - time (sec): 1.16 - samples/sec: 3596.53 - lr: 0.000004 - momentum: 0.000000 2024-11-27 20:34:06,933 epoch 197 - iter 8/9 - loss 0.00002110 - time (sec): 1.32 - samples/sec: 3599.21 - lr: 0.000004 - momentum: 0.000000 2024-11-27 20:34:07,073 epoch 197 - iter 9/9 - loss 0.00002040 - time (sec): 1.46 - samples/sec: 3552.37 - lr: 0.000004 - momentum: 0.000000 2024-11-27 20:34:07,073 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:34:07,073 EPOCH 197 done: loss 0.0000 - lr: 0.000004 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 5.64it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 5.63it/s] 2024-11-27 20:34:07,270 DEV : loss 3.754647970199585 - f1-score (micro avg) 0.366 2024-11-27 20:34:07,271 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:34:07,376 epoch 198 - iter 1/9 - loss 0.00006918 - time (sec): 0.10 - samples/sec: 6089.36 - lr: 0.000004 - momentum: 0.000000 2024-11-27 20:34:07,511 epoch 198 - iter 2/9 - loss 0.00004311 - time (sec): 0.24 - samples/sec: 5085.56 - lr: 0.000004 - momentum: 0.000000 2024-11-27 20:34:07,809 epoch 198 - iter 3/9 - loss 0.00003457 - time (sec): 0.54 - samples/sec: 3434.32 - lr: 0.000004 - momentum: 0.000000 2024-11-27 20:34:07,943 epoch 198 - iter 4/9 - loss 0.00003068 - time (sec): 0.67 - samples/sec: 3630.68 - lr: 0.000004 - momentum: 0.000000 2024-11-27 20:34:08,088 epoch 198 - iter 5/9 - loss 0.00002822 - time (sec): 0.82 - samples/sec: 3794.99 - lr: 0.000004 - momentum: 0.000000 2024-11-27 20:34:08,252 epoch 198 - iter 6/9 - loss 0.00002629 - time (sec): 0.98 - samples/sec: 3815.65 - lr: 0.000004 - momentum: 0.000000 2024-11-27 20:34:08,415 epoch 198 - iter 7/9 - loss 0.00002658 - time (sec): 1.14 - samples/sec: 3742.99 - lr: 0.000004 - momentum: 0.000000 2024-11-27 20:34:08,599 epoch 198 - iter 8/9 - loss 0.00002896 - time (sec): 1.33 - samples/sec: 3556.90 - lr: 0.000004 - momentum: 0.000000 2024-11-27 20:34:08,768 epoch 198 - iter 9/9 - loss 0.00002783 - time (sec): 1.50 - samples/sec: 3474.34 - lr: 0.000004 - momentum: 0.000000 2024-11-27 20:34:08,768 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:34:08,769 EPOCH 198 done: loss 0.0000 - lr: 0.000004 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.51it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.50it/s] 2024-11-27 20:34:08,941 DEV : loss 3.7638072967529297 - f1-score (micro avg) 0.3506 2024-11-27 20:34:08,942 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:34:09,052 epoch 199 - iter 1/9 - loss 0.00001649 - time (sec): 0.11 - samples/sec: 7162.70 - lr: 0.000004 - momentum: 0.000000 2024-11-27 20:34:09,241 epoch 199 - iter 2/9 - loss 0.00001436 - time (sec): 0.30 - samples/sec: 4510.27 - lr: 0.000004 - momentum: 0.000000 2024-11-27 20:34:09,476 epoch 199 - iter 3/9 - loss 0.00002056 - time (sec): 0.53 - samples/sec: 3497.60 - lr: 0.000004 - momentum: 0.000000 2024-11-27 20:34:09,615 epoch 199 - iter 4/9 - loss 0.00002523 - time (sec): 0.67 - samples/sec: 3778.83 - lr: 0.000004 - momentum: 0.000000 2024-11-27 20:34:09,748 epoch 199 - iter 5/9 - loss 0.00002542 - time (sec): 0.80 - samples/sec: 3756.95 - lr: 0.000004 - momentum: 0.000000 2024-11-27 20:34:09,949 epoch 199 - iter 6/9 - loss 0.00002945 - time (sec): 1.01 - samples/sec: 3653.33 - lr: 0.000004 - momentum: 0.000000 2024-11-27 20:34:10,100 epoch 199 - iter 7/9 - loss 0.00002728 - time (sec): 1.16 - samples/sec: 3589.02 - lr: 0.000004 - momentum: 0.000000 2024-11-27 20:34:10,270 epoch 199 - iter 8/9 - loss 0.00003084 - time (sec): 1.33 - samples/sec: 3557.08 - lr: 0.000004 - momentum: 0.000000 2024-11-27 20:34:10,523 epoch 199 - iter 9/9 - loss 0.00003165 - time (sec): 1.58 - samples/sec: 3290.63 - lr: 0.000004 - momentum: 0.000000 2024-11-27 20:34:10,523 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:34:10,523 EPOCH 199 done: loss 0.0000 - lr: 0.000004 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.90it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.88it/s] 2024-11-27 20:34:10,688 DEV : loss 3.7687571048736572 - f1-score (micro avg) 0.3333 2024-11-27 20:34:10,689 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:34:10,788 epoch 200 - iter 1/9 - loss 0.00001431 - time (sec): 0.10 - samples/sec: 5180.82 - lr: 0.000004 - momentum: 0.000000 2024-11-27 20:34:10,923 epoch 200 - iter 2/9 - loss 0.00001083 - time (sec): 0.23 - samples/sec: 4966.56 - lr: 0.000004 - momentum: 0.000000 2024-11-27 20:34:11,085 epoch 200 - iter 3/9 - loss 0.00001408 - time (sec): 0.39 - samples/sec: 4369.55 - lr: 0.000004 - momentum: 0.000000 2024-11-27 20:34:11,254 epoch 200 - iter 4/9 - loss 0.00001743 - time (sec): 0.56 - samples/sec: 4122.48 - lr: 0.000004 - momentum: 0.000000 2024-11-27 20:34:11,433 epoch 200 - iter 5/9 - loss 0.00001767 - time (sec): 0.74 - samples/sec: 4022.49 - lr: 0.000004 - momentum: 0.000000 2024-11-27 20:34:11,563 epoch 200 - iter 6/9 - loss 0.00001771 - time (sec): 0.87 - samples/sec: 4009.92 - lr: 0.000004 - momentum: 0.000000 2024-11-27 20:34:11,712 epoch 200 - iter 7/9 - loss 0.00001729 - time (sec): 1.02 - samples/sec: 3954.04 - lr: 0.000004 - momentum: 0.000000 2024-11-27 20:34:11,959 epoch 200 - iter 8/9 - loss 0.00001814 - time (sec): 1.27 - samples/sec: 3751.59 - lr: 0.000004 - momentum: 0.000000 2024-11-27 20:34:12,143 epoch 200 - iter 9/9 - loss 0.00001865 - time (sec): 1.45 - samples/sec: 3577.45 - lr: 0.000004 - momentum: 0.000000 2024-11-27 20:34:12,143 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:34:12,143 EPOCH 200 done: loss 0.0000 - lr: 0.000004 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 6.00it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 5.99it/s] 2024-11-27 20:34:12,330 DEV : loss 3.77131986618042 - f1-score (micro avg) 0.3333 2024-11-27 20:34:13,190 ---------------------------------------------------------------------------------------------------- 2024-11-27 20:34:13,191 Testing using last state of model ... 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████████████████████████████████████| 1/1 [00:00<00:00, 11.21it/s] 2024-11-27 20:34:13,298 Results: - F-score (micro) 0.4503 - F-score (macro) 0.2426 - Accuracy 0.2957 By class: precision recall f1-score support Org 0.5909 0.6842 0.6341 19 Aim 0.1875 0.1765 0.1818 17 Href 0.8667 1.0000 0.9286 13 Sub 0.3333 0.3333 0.3333 12 Adv 0.0909 0.1250 0.1053 8 Fac 0.0000 0.0000 0.0000 2 Ref 0.0000 0.0000 0.0000 0 Act 0.0000 0.0000 0.0000 1 Date 0.0000 0.0000 0.0000 0 micro avg 0.4304 0.4722 0.4503 72 macro avg 0.2299 0.2577 0.2426 72 weighted avg 0.4223 0.4722 0.4452 72 2024-11-27 20:34:13,298 ---------------------------------------------------------------------------------------------------- ###################################################################### ********** fine-tune operation finished ********** ********** 2024-11-27 20:34:13.300085 ********** ###################################################################### Try to evaluating the trained model! 2024-11-27 20:34:16,862 SequenceTagger predicts: Dictionary with 49 tags: O, S-Org, B-Org, E-Org, I-Org, S-Sub, B-Sub, E-Sub, I-Sub, S-Href, B-Href, E-Href, I-Href, S-Adv, B-Adv, E-Adv, I-Adv, S-Aim, B-Aim, E-Aim, I-Aim, S-Ref, B-Ref, E-Ref, I-Ref, S-Act, B-Act, E-Act, I-Act, S-Pro, B-Pro, E-Pro, I-Pro, S-Date, B-Date, E-Date, I-Date, S-Fac, B-Fac, E-Fac, I-Fac, S-Num, B-Num, E-Num, I-Num, S-Event, B-Event, E-Event, I-Event 2024-11-27 20:34:16,972 Reading data from data 2024-11-27 20:34:16,972 Train: data/peyma_train.txt 2024-11-27 20:34:16,972 Dev: None 2024-11-27 20:34:16,972 Test: data/test_ds.txt 2024-11-27 20:34:19,544 No dev split found. Using 10% (i.e. 803 samples) of the train split as dev data 0%| | 0/1 [00:00<?, ?it/s]2024-11-27 20:34:19,579 The string 'B-HALFREFERENCE' is not in dictionary! Dictionary contains only: ['O', 'S-Org', 'B-Org', 'E-Org', 'I-Org', 'S-Sub', 'B-Sub', 'E-Sub', 'I-Sub', 'S-Href', 'B-Href', 'E-Href', 'I-Href', 'S-Adv', 'B-Adv', 'E-Adv', 'I-Adv', 'S-Aim', 'B-Aim', 'E-Aim', 'I-Aim', 'S-Ref', 'B-Ref', 'E-Ref', 'I-Ref', 'S-Act', 'B-Act', 'E-Act', 'I-Act', 'S-Pro', 'B-Pro', 'E-Pro', 'I-Pro', 'S-Date', 'B-Date', 'E-Date', 'I-Date', 'S-Fac', 'B-Fac', 'E-Fac', 'I-Fac', 'S-Num', 'B-Num', 'E-Num', 'I-Num', 'S-Event', 'B-Event', 'E-Event', 'I-Event'] 2024-11-27 20:34:19,579 You can create a Dictionary that handles unknown items with an <unk>-key by setting add_unk = True in the construction. 0%| | 0/1 [00:00<?, ?it/s] do_evaluate function failed Traceback (most recent call last): File "/home/gpu/tnlp/jokar/Flair_NER/train.py", line 158, in <module> evaluate_result = do_evaluate() File "/home/gpu/tnlp/jokar/Flair_NER/evaluate_model.py", line 13, in do_evaluate result = tagger.evaluate(corpus.test, gold_label_type='ner', mini_batch_size=8) File "/home/gpu/NLP/.env/lib/python3.10/site-packages/flair/nn/model.py", line 297, in evaluate loss_and_count = self.predict( File "/home/gpu/NLP/.env/lib/python3.10/site-packages/flair/models/sequence_tagger_model.py", line 501, in predict gold_labels = self._prepare_label_tensor(batch) File "/home/gpu/NLP/.env/lib/python3.10/site-packages/flair/models/sequence_tagger_model.py", line 425, in _prepare_label_tensor [self.label_dictionary.get_idx_for_item(label) for label in gold_labels], File "/home/gpu/NLP/.env/lib/python3.10/site-packages/flair/models/sequence_tagger_model.py", line 425, in <listcomp> [self.label_dictionary.get_idx_for_item(label) for label in gold_labels], File "/home/gpu/NLP/.env/lib/python3.10/site-packages/flair/data.py", line 102, in get_idx_for_item raise IndexError IndexError During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/home/gpu/tnlp/jokar/Flair_NER/train.py", line 164, in <module> {str(e.args[0])}""" IndexError: tuple index out of range