| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 14, | |
| "global_step": 14, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.07142857142857142, | |
| "grad_norm": 0.57421875, | |
| "learning_rate": 1e-05, | |
| "loss": 2.3009, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.14285714285714285, | |
| "grad_norm": 0.5703125, | |
| "learning_rate": 9.285714285714288e-06, | |
| "loss": 2.3288, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.21428571428571427, | |
| "grad_norm": 0.55078125, | |
| "learning_rate": 8.571428571428571e-06, | |
| "loss": 2.3301, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.2857142857142857, | |
| "grad_norm": 0.5234375, | |
| "learning_rate": 7.857142857142858e-06, | |
| "loss": 2.2918, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.35714285714285715, | |
| "grad_norm": 0.50390625, | |
| "learning_rate": 7.1428571428571436e-06, | |
| "loss": 2.2832, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.42857142857142855, | |
| "grad_norm": 0.5, | |
| "learning_rate": 6.4285714285714295e-06, | |
| "loss": 2.3478, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 0.478515625, | |
| "learning_rate": 5.7142857142857145e-06, | |
| "loss": 2.2625, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.5714285714285714, | |
| "grad_norm": 0.458984375, | |
| "learning_rate": 5e-06, | |
| "loss": 2.1765, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.6428571428571429, | |
| "grad_norm": 0.447265625, | |
| "learning_rate": 4.2857142857142855e-06, | |
| "loss": 2.2547, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.7142857142857143, | |
| "grad_norm": 0.447265625, | |
| "learning_rate": 3.5714285714285718e-06, | |
| "loss": 2.1873, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.7857142857142857, | |
| "grad_norm": 0.451171875, | |
| "learning_rate": 2.8571428571428573e-06, | |
| "loss": 2.2084, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.8571428571428571, | |
| "grad_norm": 0.43359375, | |
| "learning_rate": 2.1428571428571427e-06, | |
| "loss": 2.1916, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.9285714285714286, | |
| "grad_norm": 0.439453125, | |
| "learning_rate": 1.4285714285714286e-06, | |
| "loss": 2.2463, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.44140625, | |
| "learning_rate": 7.142857142857143e-07, | |
| "loss": 2.2161, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 2.191540479660034, | |
| "eval_runtime": 13.6819, | |
| "eval_samples_per_second": 0.804, | |
| "eval_steps_per_second": 0.146, | |
| "step": 14 | |
| } | |
| ], | |
| "logging_steps": 1.0, | |
| "max_steps": 14, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 0, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.442908533120041e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |