| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.07623888182973317, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0025412960609911056, | |
| "eval_loss": 5.483310699462891, | |
| "eval_runtime": 14.4248, | |
| "eval_samples_per_second": 11.508, | |
| "eval_steps_per_second": 5.754, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.007623888182973317, | |
| "grad_norm": 1.5771654844284058, | |
| "learning_rate": 6e-05, | |
| "loss": 5.4298, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.015247776365946633, | |
| "grad_norm": 0.9005434513092041, | |
| "learning_rate": 0.00012, | |
| "loss": 5.2949, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.020330368487928845, | |
| "eval_loss": 5.176393032073975, | |
| "eval_runtime": 14.0012, | |
| "eval_samples_per_second": 11.856, | |
| "eval_steps_per_second": 5.928, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.022871664548919948, | |
| "grad_norm": 1.1106324195861816, | |
| "learning_rate": 0.00018, | |
| "loss": 5.1815, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.030495552731893267, | |
| "grad_norm": 1.0094770193099976, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 5.1039, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.03811944091486658, | |
| "grad_norm": 0.7473834753036499, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 5.0451, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.04066073697585769, | |
| "eval_loss": 4.955931663513184, | |
| "eval_runtime": 14.087, | |
| "eval_samples_per_second": 11.784, | |
| "eval_steps_per_second": 5.892, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.045743329097839895, | |
| "grad_norm": 0.9738025665283203, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 4.8306, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.053367217280813214, | |
| "grad_norm": 0.6494523882865906, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 4.9165, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.060991105463786534, | |
| "grad_norm": 0.6389119625091553, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 5.0326, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.060991105463786534, | |
| "eval_loss": 4.910366058349609, | |
| "eval_runtime": 14.1471, | |
| "eval_samples_per_second": 11.734, | |
| "eval_steps_per_second": 5.867, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.06861499364675985, | |
| "grad_norm": 0.6531729102134705, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 4.8767, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.07623888182973317, | |
| "grad_norm": 0.5290908813476562, | |
| "learning_rate": 0.0, | |
| "loss": 4.9477, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.112850252693504e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |