| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.003145395926712275, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0003145395926712275, | |
| "grad_norm": 0.026611553505063057, | |
| "learning_rate": 2e-05, | |
| "loss": 10.3693, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0003145395926712275, | |
| "eval_loss": 10.374354362487793, | |
| "eval_runtime": 4.0911, | |
| "eval_samples_per_second": 327.292, | |
| "eval_steps_per_second": 163.768, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.000629079185342455, | |
| "grad_norm": 0.026462724432349205, | |
| "learning_rate": 4e-05, | |
| "loss": 10.3736, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0009436187780136825, | |
| "grad_norm": 0.022061211988329887, | |
| "learning_rate": 6e-05, | |
| "loss": 10.3805, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0009436187780136825, | |
| "eval_loss": 10.374333381652832, | |
| "eval_runtime": 4.0971, | |
| "eval_samples_per_second": 326.815, | |
| "eval_steps_per_second": 163.53, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00125815837068491, | |
| "grad_norm": 0.023239031434059143, | |
| "learning_rate": 8e-05, | |
| "loss": 10.3747, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0015726979633561376, | |
| "grad_norm": 0.024116482585668564, | |
| "learning_rate": 0.0001, | |
| "loss": 10.3744, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.001887237556027365, | |
| "grad_norm": 0.024123243987560272, | |
| "learning_rate": 0.00012, | |
| "loss": 10.3782, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.001887237556027365, | |
| "eval_loss": 10.374226570129395, | |
| "eval_runtime": 4.223, | |
| "eval_samples_per_second": 317.072, | |
| "eval_steps_per_second": 158.654, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0022017771486985923, | |
| "grad_norm": 0.02399708330631256, | |
| "learning_rate": 0.00014, | |
| "loss": 10.3763, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.00251631674136982, | |
| "grad_norm": 0.023350700736045837, | |
| "learning_rate": 0.00016, | |
| "loss": 10.3769, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0028308563340410475, | |
| "grad_norm": 0.025544174015522003, | |
| "learning_rate": 0.00018, | |
| "loss": 10.3759, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0028308563340410475, | |
| "eval_loss": 10.374049186706543, | |
| "eval_runtime": 4.1818, | |
| "eval_samples_per_second": 320.198, | |
| "eval_steps_per_second": 160.219, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.003145395926712275, | |
| "grad_norm": 0.03307681158185005, | |
| "learning_rate": 0.0002, | |
| "loss": 10.3718, | |
| "step": 10 | |
| } | |
| ], | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 168101806080.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |