| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0001871760976123349, | |
| "eval_steps": 2, | |
| "global_step": 5, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 3.743521952246698e-05, | |
| "grad_norm": 11.421965599060059, | |
| "learning_rate": 1e-05, | |
| "loss": 6.2976, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 3.743521952246698e-05, | |
| "eval_loss": 6.473023891448975, | |
| "eval_runtime": 452.4929, | |
| "eval_samples_per_second": 99.427, | |
| "eval_steps_per_second": 49.713, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 7.487043904493396e-05, | |
| "grad_norm": 11.634509086608887, | |
| "learning_rate": 2e-05, | |
| "loss": 6.3354, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 7.487043904493396e-05, | |
| "eval_loss": 6.344751834869385, | |
| "eval_runtime": 418.5335, | |
| "eval_samples_per_second": 107.494, | |
| "eval_steps_per_second": 53.747, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00011230565856740095, | |
| "grad_norm": 11.153646469116211, | |
| "learning_rate": 3e-05, | |
| "loss": 6.7004, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00014974087808986792, | |
| "grad_norm": 10.927276611328125, | |
| "learning_rate": 4e-05, | |
| "loss": 6.0452, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00014974087808986792, | |
| "eval_loss": 6.055593490600586, | |
| "eval_runtime": 408.6674, | |
| "eval_samples_per_second": 110.09, | |
| "eval_steps_per_second": 55.045, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0001871760976123349, | |
| "grad_norm": 10.491527557373047, | |
| "learning_rate": 5e-05, | |
| "loss": 6.1208, | |
| "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": 178076327608320.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |