| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.00579584148373542, | |
| "eval_steps": 2, | |
| "global_step": 5, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.001159168296747084, | |
| "grad_norm": 0.02830873429775238, | |
| "learning_rate": 1e-05, | |
| "loss": 11.7637, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.001159168296747084, | |
| "eval_loss": 11.76246452331543, | |
| "eval_runtime": 13.8592, | |
| "eval_samples_per_second": 104.84, | |
| "eval_steps_per_second": 52.456, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002318336593494168, | |
| "grad_norm": 0.0266997329890728, | |
| "learning_rate": 2e-05, | |
| "loss": 11.7608, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.002318336593494168, | |
| "eval_loss": 11.762459754943848, | |
| "eval_runtime": 1.842, | |
| "eval_samples_per_second": 788.832, | |
| "eval_steps_per_second": 394.687, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.003477504890241252, | |
| "grad_norm": 0.02610933966934681, | |
| "learning_rate": 3e-05, | |
| "loss": 11.7593, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.004636673186988336, | |
| "grad_norm": 0.02823724038898945, | |
| "learning_rate": 4e-05, | |
| "loss": 11.765, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.004636673186988336, | |
| "eval_loss": 11.762443542480469, | |
| "eval_runtime": 1.8622, | |
| "eval_samples_per_second": 780.259, | |
| "eval_steps_per_second": 390.398, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00579584148373542, | |
| "grad_norm": 0.03290804103016853, | |
| "learning_rate": 5e-05, | |
| "loss": 11.7584, | |
| "step": 5 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 5, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 2, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1015606149120.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |