| { |
| "best_global_step": 180, |
| "best_metric": 0.9811938061938061, |
| "best_model_checkpoint": "task_classifier_output/checkpoint-180", |
| "epoch": 5.0, |
| "eval_steps": 500, |
| "global_step": 225, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.90625, |
| "eval_f1": 0.9063951526529118, |
| "eval_loss": 1.2780158519744873, |
| "eval_runtime": 0.2861, |
| "eval_samples_per_second": 559.171, |
| "eval_steps_per_second": 17.474, |
| "step": 45 |
| }, |
| { |
| "epoch": 1.1111111111111112, |
| "grad_norm": 0.7980117201805115, |
| "learning_rate": 1.5644444444444448e-05, |
| "loss": 1.3336, |
| "step": 50 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.9375, |
| "eval_f1": 0.9384057761035448, |
| "eval_loss": 1.1573435068130493, |
| "eval_runtime": 0.2207, |
| "eval_samples_per_second": 724.836, |
| "eval_steps_per_second": 22.651, |
| "step": 90 |
| }, |
| { |
| "epoch": 2.2222222222222223, |
| "grad_norm": 1.1813886165618896, |
| "learning_rate": 1.1200000000000001e-05, |
| "loss": 1.1986, |
| "step": 100 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.975, |
| "eval_f1": 0.9749526335733233, |
| "eval_loss": 1.0562200546264648, |
| "eval_runtime": 0.2421, |
| "eval_samples_per_second": 660.969, |
| "eval_steps_per_second": 20.655, |
| "step": 135 |
| }, |
| { |
| "epoch": 3.3333333333333335, |
| "grad_norm": 1.406683325767517, |
| "learning_rate": 6.755555555555556e-06, |
| "loss": 1.0763, |
| "step": 150 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.98125, |
| "eval_f1": 0.9811938061938061, |
| "eval_loss": 0.9907373189926147, |
| "eval_runtime": 0.2405, |
| "eval_samples_per_second": 665.339, |
| "eval_steps_per_second": 20.792, |
| "step": 180 |
| }, |
| { |
| "epoch": 4.444444444444445, |
| "grad_norm": 2.066603899002075, |
| "learning_rate": 2.311111111111111e-06, |
| "loss": 1.0026, |
| "step": 200 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.98125, |
| "eval_f1": 0.9811938061938061, |
| "eval_loss": 0.969234824180603, |
| "eval_runtime": 0.2384, |
| "eval_samples_per_second": 671.108, |
| "eval_steps_per_second": 20.972, |
| "step": 225 |
| } |
| ], |
| "logging_steps": 50, |
| "max_steps": 225, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 5, |
| "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": 92565645494784.0, |
| "train_batch_size": 32, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
