| { |
| "best_global_step": 3351, |
| "best_metric": 0.8114824335904027, |
| "best_model_checkpoint": "/content/drive/MyDrive/NER_finetune/checkpoints/checkpoint-3351", |
| "epoch": 3.0, |
| "eval_steps": 500, |
| "global_step": 3351, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.4476275738585497, |
| "grad_norm": 1.5675565004348755, |
| "learning_rate": 2.7898313027179006e-05, |
| "loss": 0.2287205810546875, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.8952551477170994, |
| "grad_norm": 1.4967564344406128, |
| "learning_rate": 2.4383786316776008e-05, |
| "loss": 0.08755873107910156, |
| "step": 1000 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_f1": 0.7730870712401056, |
| "eval_loss": 0.10428160429000854, |
| "eval_precision": 0.752568493150685, |
| "eval_recall": 0.794755877034358, |
| "eval_runtime": 7.8273, |
| "eval_samples_per_second": 116.899, |
| "eval_steps_per_second": 7.41, |
| "step": 1117 |
| }, |
| { |
| "epoch": 1.3428827215756491, |
| "grad_norm": 1.0879971981048584, |
| "learning_rate": 2.086925960637301e-05, |
| "loss": 0.06404219818115234, |
| "step": 1500 |
| }, |
| { |
| "epoch": 1.7905102954341987, |
| "grad_norm": 2.3005924224853516, |
| "learning_rate": 1.735473289597001e-05, |
| "loss": 0.05874628067016602, |
| "step": 2000 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_f1": 0.8012205754141238, |
| "eval_loss": 0.10272369533777237, |
| "eval_precision": 0.7735690235690236, |
| "eval_recall": 0.8309222423146474, |
| "eval_runtime": 7.5056, |
| "eval_samples_per_second": 121.909, |
| "eval_steps_per_second": 7.728, |
| "step": 2234 |
| }, |
| { |
| "epoch": 2.2381378692927485, |
| "grad_norm": 1.1057658195495605, |
| "learning_rate": 1.3840206185567012e-05, |
| "loss": 0.04509225463867188, |
| "step": 2500 |
| }, |
| { |
| "epoch": 2.6857654431512983, |
| "grad_norm": 1.9436335563659668, |
| "learning_rate": 1.032567947516401e-05, |
| "loss": 0.03907421112060547, |
| "step": 3000 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_f1": 0.8114824335904027, |
| "eval_loss": 0.10077907890081406, |
| "eval_precision": 0.7711726384364821, |
| "eval_recall": 0.85623869801085, |
| "eval_runtime": 7.7226, |
| "eval_samples_per_second": 118.484, |
| "eval_steps_per_second": 7.51, |
| "step": 3351 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 4468, |
| "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": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.4002480955713536e+16, |
| "train_batch_size": 16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
