| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.028119507908611598, | |
| "eval_steps": 2, | |
| "global_step": 4, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.007029876977152899, | |
| "grad_norm": NaN, | |
| "learning_rate": 1e-05, | |
| "loss": 26.9517, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.007029876977152899, | |
| "eval_loss": NaN, | |
| "eval_runtime": 87.8883, | |
| "eval_samples_per_second": 2.731, | |
| "eval_steps_per_second": 1.365, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.014059753954305799, | |
| "grad_norm": NaN, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.014059753954305799, | |
| "eval_loss": NaN, | |
| "eval_runtime": 6.616, | |
| "eval_samples_per_second": 36.276, | |
| "eval_steps_per_second": 18.138, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0210896309314587, | |
| "grad_norm": NaN, | |
| "learning_rate": 3e-05, | |
| "loss": 979.7983, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.028119507908611598, | |
| "grad_norm": NaN, | |
| "learning_rate": 4e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.028119507908611598, | |
| "eval_loss": NaN, | |
| "eval_runtime": 7.8958, | |
| "eval_samples_per_second": 30.396, | |
| "eval_steps_per_second": 15.198, | |
| "step": 4 | |
| } | |
| ], | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2768848042328064.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |