| { | |
| "best_metric": 0.058695483952760696, | |
| "best_model_checkpoint": "/content/drive/MyDrive/dataset_for_research/ct_rate/data/ct_rate_jpn/model_output/tohoku_bert/checkpoint-9112", | |
| "epoch": 4.0, | |
| "eval_steps": 500, | |
| "global_step": 9112, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.21949078138718173, | |
| "grad_norm": 1.1410490274429321, | |
| "learning_rate": 1.8902546093064093e-05, | |
| "loss": 0.3733, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.43898156277436345, | |
| "grad_norm": 0.5691537857055664, | |
| "learning_rate": 1.7805092186128183e-05, | |
| "loss": 0.2073, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.6584723441615452, | |
| "grad_norm": 0.36492520570755005, | |
| "learning_rate": 1.6707638279192274e-05, | |
| "loss": 0.1498, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.8779631255487269, | |
| "grad_norm": 0.948626697063446, | |
| "learning_rate": 1.561018437225637e-05, | |
| "loss": 0.1187, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.9789288849868305, | |
| "eval_f1": 0.9471656576774904, | |
| "eval_loss": 0.09360361844301224, | |
| "eval_precision": 0.9523487456960157, | |
| "eval_recall": 0.9420386814256173, | |
| "eval_runtime": 54.2042, | |
| "eval_samples_per_second": 84.053, | |
| "eval_steps_per_second": 10.516, | |
| "step": 2278 | |
| }, | |
| { | |
| "epoch": 1.0974539069359086, | |
| "grad_norm": 0.35782086849212646, | |
| "learning_rate": 1.4512730465320458e-05, | |
| "loss": 0.0979, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 1.3169446883230904, | |
| "grad_norm": 0.49497029185295105, | |
| "learning_rate": 1.3415276558384549e-05, | |
| "loss": 0.0849, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.536435469710272, | |
| "grad_norm": 0.45342519879341125, | |
| "learning_rate": 1.2317822651448641e-05, | |
| "loss": 0.0756, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 1.755926251097454, | |
| "grad_norm": 0.5025061368942261, | |
| "learning_rate": 1.122036874451273e-05, | |
| "loss": 0.0719, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.9754170324846356, | |
| "grad_norm": 0.8253716826438904, | |
| "learning_rate": 1.0122914837576823e-05, | |
| "loss": 0.0687, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.9834162520729685, | |
| "eval_f1": 0.9583103427135062, | |
| "eval_loss": 0.06783699989318848, | |
| "eval_precision": 0.9660692212608158, | |
| "eval_recall": 0.9506751003527552, | |
| "eval_runtime": 54.005, | |
| "eval_samples_per_second": 84.362, | |
| "eval_steps_per_second": 10.555, | |
| "step": 4556 | |
| }, | |
| { | |
| "epoch": 2.194907813871817, | |
| "grad_norm": 1.1863067150115967, | |
| "learning_rate": 9.025460930640914e-06, | |
| "loss": 0.0585, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 2.4143985952589992, | |
| "grad_norm": 0.6489052176475525, | |
| "learning_rate": 7.928007023705005e-06, | |
| "loss": 0.0573, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 2.633889376646181, | |
| "grad_norm": 0.8411669731140137, | |
| "learning_rate": 6.830553116769097e-06, | |
| "loss": 0.0534, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 2.853380158033363, | |
| "grad_norm": 1.2083945274353027, | |
| "learning_rate": 5.7330992098331876e-06, | |
| "loss": 0.0528, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.9838796215003415, | |
| "eval_f1": 0.959547123623011, | |
| "eval_loss": 0.06107071042060852, | |
| "eval_precision": 0.9655745781500185, | |
| "eval_recall": 0.9535944532295341, | |
| "eval_runtime": 54.1061, | |
| "eval_samples_per_second": 84.205, | |
| "eval_steps_per_second": 10.535, | |
| "step": 6834 | |
| }, | |
| { | |
| "epoch": 3.0728709394205445, | |
| "grad_norm": 0.5386723279953003, | |
| "learning_rate": 4.6356453028972785e-06, | |
| "loss": 0.0496, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 3.292361720807726, | |
| "grad_norm": 0.5504190921783447, | |
| "learning_rate": 3.53819139596137e-06, | |
| "loss": 0.0441, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 3.511852502194908, | |
| "grad_norm": 0.8231956958770752, | |
| "learning_rate": 2.440737489025461e-06, | |
| "loss": 0.0456, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 3.7313432835820897, | |
| "grad_norm": 1.272826910018921, | |
| "learning_rate": 1.3432835820895524e-06, | |
| "loss": 0.0447, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 3.9508340649692713, | |
| "grad_norm": 1.6443417072296143, | |
| "learning_rate": 2.458296751536436e-07, | |
| "loss": 0.0434, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.9843429909277144, | |
| "eval_f1": 0.9607147228001469, | |
| "eval_loss": 0.058695483952760696, | |
| "eval_precision": 0.9666297254032754, | |
| "eval_recall": 0.9548716701131249, | |
| "eval_runtime": 54.169, | |
| "eval_samples_per_second": 84.107, | |
| "eval_steps_per_second": 10.523, | |
| "step": 9112 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 9112, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "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": 1.755253733461956e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |