| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.23738872403560832, | |
| "eval_steps": 2, | |
| "global_step": 5, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04747774480712166, | |
| "grad_norm": NaN, | |
| "learning_rate": 1e-05, | |
| "loss": 1027.9601, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.04747774480712166, | |
| "eval_loss": NaN, | |
| "eval_runtime": 88.5965, | |
| "eval_samples_per_second": 0.406, | |
| "eval_steps_per_second": 0.203, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.09495548961424333, | |
| "grad_norm": NaN, | |
| "learning_rate": 2e-05, | |
| "loss": 5218.062, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.09495548961424333, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1.2227, | |
| "eval_samples_per_second": 29.443, | |
| "eval_steps_per_second": 14.721, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.142433234421365, | |
| "grad_norm": NaN, | |
| "learning_rate": 3e-05, | |
| "loss": 32761.8457, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.18991097922848665, | |
| "grad_norm": NaN, | |
| "learning_rate": 4e-05, | |
| "loss": 6005.3267, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.18991097922848665, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1.2395, | |
| "eval_samples_per_second": 29.043, | |
| "eval_steps_per_second": 14.521, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.23738872403560832, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 28251.8828, | |
| "step": 5 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 5, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 2, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5348000784187392.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |