| { | |
| "best_metric": 0.9314045730284647, | |
| "best_model_checkpoint": "/content/dissertation/scripts/ner/output/checkpoint-3038", | |
| "epoch": 10.0, | |
| "eval_steps": 500, | |
| "global_step": 4340, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.9980813775011861, | |
| "eval_f1": 0.8937558247903076, | |
| "eval_loss": 0.005673006176948547, | |
| "eval_precision": 0.8937558247903076, | |
| "eval_recall": 0.8937558247903076, | |
| "eval_runtime": 13.5502, | |
| "eval_samples_per_second": 512.611, | |
| "eval_steps_per_second": 64.132, | |
| "step": 434 | |
| }, | |
| { | |
| "epoch": 1.1520737327188941, | |
| "grad_norm": 0.324382483959198, | |
| "learning_rate": 4.423963133640553e-05, | |
| "loss": 0.0182, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.9985418469009014, | |
| "eval_f1": 0.9160165213400643, | |
| "eval_loss": 0.004419892560690641, | |
| "eval_precision": 0.9023508137432188, | |
| "eval_recall": 0.9301025163094129, | |
| "eval_runtime": 13.4449, | |
| "eval_samples_per_second": 516.626, | |
| "eval_steps_per_second": 64.634, | |
| "step": 868 | |
| }, | |
| { | |
| "epoch": 2.3041474654377883, | |
| "grad_norm": 0.0693276971578598, | |
| "learning_rate": 3.847926267281106e-05, | |
| "loss": 0.0039, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.9986534758462869, | |
| "eval_f1": 0.9205175600739371, | |
| "eval_loss": 0.0044819144532084465, | |
| "eval_precision": 0.9129239230064161, | |
| "eval_recall": 0.9282385834109972, | |
| "eval_runtime": 13.422, | |
| "eval_samples_per_second": 517.51, | |
| "eval_steps_per_second": 64.745, | |
| "step": 1302 | |
| }, | |
| { | |
| "epoch": 3.456221198156682, | |
| "grad_norm": 0.06998981535434723, | |
| "learning_rate": 3.271889400921659e-05, | |
| "loss": 0.0024, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.9983255658192169, | |
| "eval_f1": 0.9076923076923078, | |
| "eval_loss": 0.005129755008965731, | |
| "eval_precision": 0.882145998240985, | |
| "eval_recall": 0.934762348555452, | |
| "eval_runtime": 13.6729, | |
| "eval_samples_per_second": 508.013, | |
| "eval_steps_per_second": 63.556, | |
| "step": 1736 | |
| }, | |
| { | |
| "epoch": 4.6082949308755765, | |
| "grad_norm": 0.0027600331231951714, | |
| "learning_rate": 2.6958525345622122e-05, | |
| "loss": 0.0017, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.9986464990372004, | |
| "eval_f1": 0.9285051067780873, | |
| "eval_loss": 0.0056963409297168255, | |
| "eval_precision": 0.9250693802035153, | |
| "eval_recall": 0.9319664492078286, | |
| "eval_runtime": 13.4387, | |
| "eval_samples_per_second": 516.864, | |
| "eval_steps_per_second": 64.664, | |
| "step": 2170 | |
| }, | |
| { | |
| "epoch": 5.76036866359447, | |
| "grad_norm": 0.018086101859807968, | |
| "learning_rate": 2.1198156682027652e-05, | |
| "loss": 0.0012, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.9984023107191695, | |
| "eval_f1": 0.9116835326586937, | |
| "eval_loss": 0.006062328349798918, | |
| "eval_precision": 0.9000908265213442, | |
| "eval_recall": 0.923578751164958, | |
| "eval_runtime": 13.3783, | |
| "eval_samples_per_second": 519.199, | |
| "eval_steps_per_second": 64.956, | |
| "step": 2604 | |
| }, | |
| { | |
| "epoch": 6.912442396313364, | |
| "grad_norm": 0.009607589803636074, | |
| "learning_rate": 1.543778801843318e-05, | |
| "loss": 0.0009, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.9986953367008066, | |
| "eval_f1": 0.9314045730284647, | |
| "eval_loss": 0.005624314770102501, | |
| "eval_precision": 0.9327102803738317, | |
| "eval_recall": 0.9301025163094129, | |
| "eval_runtime": 13.399, | |
| "eval_samples_per_second": 518.397, | |
| "eval_steps_per_second": 64.856, | |
| "step": 3038 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.9985837077554209, | |
| "eval_f1": 0.9231477220432582, | |
| "eval_loss": 0.006831143982708454, | |
| "eval_precision": 0.9118181818181819, | |
| "eval_recall": 0.934762348555452, | |
| "eval_runtime": 13.3718, | |
| "eval_samples_per_second": 519.45, | |
| "eval_steps_per_second": 64.987, | |
| "step": 3472 | |
| }, | |
| { | |
| "epoch": 8.064516129032258, | |
| "grad_norm": 0.0005392630700953305, | |
| "learning_rate": 9.67741935483871e-06, | |
| "loss": 0.0006, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.9986813830826333, | |
| "eval_f1": 0.9288702928870293, | |
| "eval_loss": 0.0071532572619616985, | |
| "eval_precision": 0.9267161410018553, | |
| "eval_recall": 0.9310344827586207, | |
| "eval_runtime": 13.5255, | |
| "eval_samples_per_second": 513.548, | |
| "eval_steps_per_second": 64.249, | |
| "step": 3906 | |
| }, | |
| { | |
| "epoch": 9.216589861751151, | |
| "grad_norm": 0.0045371875166893005, | |
| "learning_rate": 3.9170506912442395e-06, | |
| "loss": 0.0004, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.998618591800854, | |
| "eval_f1": 0.9259944495837187, | |
| "eval_loss": 0.007294897455722094, | |
| "eval_precision": 0.9191919191919192, | |
| "eval_recall": 0.9328984156570364, | |
| "eval_runtime": 13.8041, | |
| "eval_samples_per_second": 503.184, | |
| "eval_steps_per_second": 62.952, | |
| "step": 4340 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "step": 4340, | |
| "total_flos": 1.0996932656642544e+16, | |
| "train_loss": 0.003382195293697344, | |
| "train_runtime": 1039.0596, | |
| "train_samples_per_second": 267.242, | |
| "train_steps_per_second": 4.177 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 4340, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.0996932656642544e+16, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |