| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 4.0, | |
| "eval_steps": 100, | |
| "global_step": 84, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.47619047619047616, | |
| "grad_norm": 6.1757893562316895, | |
| "learning_rate": 0.0001785714285714286, | |
| "loss": 0.5829, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.9523809523809523, | |
| "grad_norm": 3.337554931640625, | |
| "learning_rate": 0.00015476190476190478, | |
| "loss": 0.7423, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.4285714285714286, | |
| "grad_norm": 0.07775535434484482, | |
| "learning_rate": 0.00013095238095238096, | |
| "loss": 0.0198, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.9047619047619047, | |
| "grad_norm": 0.0923432782292366, | |
| "learning_rate": 0.00010714285714285715, | |
| "loss": 0.2508, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.380952380952381, | |
| "grad_norm": 0.010310073383152485, | |
| "learning_rate": 8.333333333333334e-05, | |
| "loss": 0.0006, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.857142857142857, | |
| "grad_norm": 0.022837914526462555, | |
| "learning_rate": 5.9523809523809524e-05, | |
| "loss": 0.0011, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 3.3333333333333335, | |
| "grad_norm": 0.0032586820889264345, | |
| "learning_rate": 3.571428571428572e-05, | |
| "loss": 0.0002, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 3.8095238095238093, | |
| "grad_norm": 0.00261130603030324, | |
| "learning_rate": 1.1904761904761905e-05, | |
| "loss": 0.0001, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "step": 84, | |
| "total_flos": 2.5417372593586176e+16, | |
| "train_loss": 0.1902264037302562, | |
| "train_runtime": 30.4122, | |
| "train_samples_per_second": 10.785, | |
| "train_steps_per_second": 2.762 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 84, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.5417372593586176e+16, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |