| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.00133973428603327, | |
| "eval_steps": 3, | |
| "global_step": 3, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0004465780953444234, | |
| "grad_norm": 2.851041316986084, | |
| "learning_rate": 2e-05, | |
| "loss": 10.0642, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0004465780953444234, | |
| "eval_loss": 2.1306488513946533, | |
| "eval_runtime": 41.7266, | |
| "eval_samples_per_second": 22.599, | |
| "eval_steps_per_second": 11.312, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0008931561906888468, | |
| "grad_norm": 0.8493361473083496, | |
| "learning_rate": 4e-05, | |
| "loss": 9.0667, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00133973428603327, | |
| "grad_norm": 1.4644571542739868, | |
| "learning_rate": 6e-05, | |
| "loss": 8.6212, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00133973428603327, | |
| "eval_loss": 2.1303281784057617, | |
| "eval_runtime": 41.7184, | |
| "eval_samples_per_second": 22.604, | |
| "eval_steps_per_second": 11.314, | |
| "step": 3 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 570062234714112.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |