| { | |
| "best_metric": NaN, | |
| "best_model_checkpoint": "/tmp/model/checkpoint-28", | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 28, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.42857142857142855, | |
| "eval_f1_macro": 0.19999999999999998, | |
| "eval_f1_micro": 0.42857142857142855, | |
| "eval_f1_weighted": 0.2571428571428571, | |
| "eval_loss": NaN, | |
| "eval_precision_macro": 0.14285714285714285, | |
| "eval_precision_micro": 0.42857142857142855, | |
| "eval_precision_weighted": 0.18367346938775508, | |
| "eval_recall_macro": 0.3333333333333333, | |
| "eval_recall_micro": 0.42857142857142855, | |
| "eval_recall_weighted": 0.42857142857142855, | |
| "eval_runtime": 0.1879, | |
| "eval_samples_per_second": 37.251, | |
| "eval_steps_per_second": 21.286, | |
| "step": 28 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 560, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 20, | |
| "save_steps": 500, | |
| "total_flos": 594643112534016.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |