| { | |
| "best_metric": 1.0, | |
| "best_model_checkpoint": "hf-sentiment-production/checkpoint-337", | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 337, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02967359050445104, | |
| "grad_norm": 0.0003316526999697089, | |
| "learning_rate": 2.9761904761904765e-07, | |
| "loss": 0.0003, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.05934718100890208, | |
| "grad_norm": 0.0005845068953931332, | |
| "learning_rate": 5.952380952380953e-07, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.08902077151335312, | |
| "grad_norm": 6.946044595679268e-05, | |
| "learning_rate": 8.928571428571429e-07, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.11869436201780416, | |
| "grad_norm": 0.00013723627489525825, | |
| "learning_rate": 1.1904761904761906e-06, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.14836795252225518, | |
| "grad_norm": 5.739806510973722e-05, | |
| "learning_rate": 1.4880952380952381e-06, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.17804154302670624, | |
| "grad_norm": 7.3791602517303545e-06, | |
| "learning_rate": 1.7857142857142859e-06, | |
| "loss": 0.0004, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.20771513353115728, | |
| "grad_norm": 1.4184925021254458e-05, | |
| "learning_rate": 2.0833333333333334e-06, | |
| "loss": 0.0, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.23738872403560832, | |
| "grad_norm": 1.2190222378194449e-06, | |
| "learning_rate": 2.380952380952381e-06, | |
| "loss": 0.0, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.26706231454005935, | |
| "grad_norm": 1.4691991964355111e-05, | |
| "learning_rate": 2.6785714285714285e-06, | |
| "loss": 0.0, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.29673590504451036, | |
| "grad_norm": 6.091187606216408e-05, | |
| "learning_rate": 2.9761904761904763e-06, | |
| "loss": 0.0, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.3264094955489614, | |
| "grad_norm": 1.0290184945915826e-05, | |
| "learning_rate": 3.273809523809524e-06, | |
| "loss": 0.0, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.3560830860534125, | |
| "grad_norm": 5.887858060305007e-05, | |
| "learning_rate": 3.5714285714285718e-06, | |
| "loss": 0.0, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.3857566765578635, | |
| "grad_norm": 0.00019515887834131718, | |
| "learning_rate": 3.869047619047619e-06, | |
| "loss": 0.0, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.41543026706231456, | |
| "grad_norm": 7.377419478871161e-06, | |
| "learning_rate": 4.166666666666667e-06, | |
| "loss": 0.0, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.44510385756676557, | |
| "grad_norm": 7.4168701758026145e-06, | |
| "learning_rate": 4.464285714285715e-06, | |
| "loss": 0.0, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.47477744807121663, | |
| "grad_norm": 0.00012300463276915252, | |
| "learning_rate": 4.761904761904762e-06, | |
| "loss": 0.0, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.5044510385756676, | |
| "grad_norm": 1.722447996144183e-05, | |
| "learning_rate": 5.05952380952381e-06, | |
| "loss": 0.0, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.5341246290801187, | |
| "grad_norm": 0.0006671595619991422, | |
| "learning_rate": 5.357142857142857e-06, | |
| "loss": 0.0, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.5637982195845698, | |
| "grad_norm": 2.224778290838003e-05, | |
| "learning_rate": 5.654761904761905e-06, | |
| "loss": 0.0, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.5934718100890207, | |
| "grad_norm": 0.00016540104115847498, | |
| "learning_rate": 5.9523809523809525e-06, | |
| "loss": 0.0, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.6231454005934718, | |
| "grad_norm": 0.00019113092275802046, | |
| "learning_rate": 6.25e-06, | |
| "loss": 0.0, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.6528189910979229, | |
| "grad_norm": 0.2549625039100647, | |
| "learning_rate": 6.547619047619048e-06, | |
| "loss": 0.0, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.6824925816023739, | |
| "grad_norm": 5.711175253964029e-05, | |
| "learning_rate": 6.845238095238096e-06, | |
| "loss": 0.0, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.712166172106825, | |
| "grad_norm": 6.6464672272559255e-06, | |
| "learning_rate": 7.1428571428571436e-06, | |
| "loss": 0.0, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.7418397626112759, | |
| "grad_norm": 1.1021610589523334e-05, | |
| "learning_rate": 7.440476190476191e-06, | |
| "loss": 0.0, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.771513353115727, | |
| "grad_norm": 4.050310451475525e-07, | |
| "learning_rate": 7.738095238095238e-06, | |
| "loss": 0.0, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.8011869436201781, | |
| "grad_norm": 5.8233334129909053e-05, | |
| "learning_rate": 8.035714285714286e-06, | |
| "loss": 0.0, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.8308605341246291, | |
| "grad_norm": 1.0179860510106664e-05, | |
| "learning_rate": 8.333333333333334e-06, | |
| "loss": 0.0, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.8605341246290801, | |
| "grad_norm": 7.523889962612884e-06, | |
| "learning_rate": 8.630952380952381e-06, | |
| "loss": 0.0, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.8902077151335311, | |
| "grad_norm": 9.157076419796795e-06, | |
| "learning_rate": 8.92857142857143e-06, | |
| "loss": 0.0, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.9198813056379822, | |
| "grad_norm": 8.59304127516225e-05, | |
| "learning_rate": 9.226190476190477e-06, | |
| "loss": 0.0, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.9495548961424333, | |
| "grad_norm": 4.281292262930947e-07, | |
| "learning_rate": 9.523809523809525e-06, | |
| "loss": 0.0, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.9792284866468842, | |
| "grad_norm": 7.248609108501114e-06, | |
| "learning_rate": 9.821428571428573e-06, | |
| "loss": 0.0, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 1.0, | |
| "eval_f1": 1.0, | |
| "eval_f1_macro": 1.0, | |
| "eval_loss": 0.00040641959640197456, | |
| "eval_precision": 1.0, | |
| "eval_precision_macro": 1.0, | |
| "eval_recall": 1.0, | |
| "eval_recall_macro": 1.0, | |
| "eval_runtime": 248.5056, | |
| "eval_samples_per_second": 1.811, | |
| "eval_steps_per_second": 0.455, | |
| "step": 337 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 674, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 354413773679616.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |