| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0028308563340410475, | |
| "eval_steps": 3, | |
| "global_step": 9, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0003145395926712275, | |
| "grad_norm": 0.029093239456415176, | |
| "learning_rate": 2e-05, | |
| "loss": 10.3693, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0003145395926712275, | |
| "eval_loss": 10.374354362487793, | |
| "eval_runtime": 4.0659, | |
| "eval_samples_per_second": 329.325, | |
| "eval_steps_per_second": 164.785, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.000629079185342455, | |
| "grad_norm": 0.028805788606405258, | |
| "learning_rate": 4e-05, | |
| "loss": 10.3736, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0009436187780136825, | |
| "grad_norm": 0.024539368227124214, | |
| "learning_rate": 6e-05, | |
| "loss": 10.3805, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0009436187780136825, | |
| "eval_loss": 10.374330520629883, | |
| "eval_runtime": 4.1038, | |
| "eval_samples_per_second": 326.286, | |
| "eval_steps_per_second": 163.265, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00125815837068491, | |
| "grad_norm": 0.02643374539911747, | |
| "learning_rate": 8e-05, | |
| "loss": 10.3747, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0015726979633561376, | |
| "grad_norm": 0.02621520310640335, | |
| "learning_rate": 0.0001, | |
| "loss": 10.3744, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.001887237556027365, | |
| "grad_norm": 0.027438007295131683, | |
| "learning_rate": 0.00012, | |
| "loss": 10.3782, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.001887237556027365, | |
| "eval_loss": 10.37421703338623, | |
| "eval_runtime": 4.2253, | |
| "eval_samples_per_second": 316.9, | |
| "eval_steps_per_second": 158.568, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0022017771486985923, | |
| "grad_norm": 0.028805077075958252, | |
| "learning_rate": 0.00014, | |
| "loss": 10.3763, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.00251631674136982, | |
| "grad_norm": 0.026216376572847366, | |
| "learning_rate": 0.00016, | |
| "loss": 10.3769, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0028308563340410475, | |
| "grad_norm": 0.029605017974972725, | |
| "learning_rate": 0.00018, | |
| "loss": 10.3759, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0028308563340410475, | |
| "eval_loss": 10.374030113220215, | |
| "eval_runtime": 4.1887, | |
| "eval_samples_per_second": 319.671, | |
| "eval_steps_per_second": 159.955, | |
| "step": 9 | |
| } | |
| ], | |
| "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": 148705443840.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |