| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.018739751698289998, | |
| "eval_steps": 2, | |
| "global_step": 5, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0037479503396579995, | |
| "grad_norm": 0.060596615076065063, | |
| "learning_rate": 1e-05, | |
| "loss": 10.3571, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0037479503396579995, | |
| "eval_loss": 10.36337661743164, | |
| "eval_runtime": 10.1138, | |
| "eval_samples_per_second": 44.494, | |
| "eval_steps_per_second": 22.247, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.007495900679315999, | |
| "grad_norm": 0.054265379905700684, | |
| "learning_rate": 2e-05, | |
| "loss": 10.3617, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.007495900679315999, | |
| "eval_loss": 10.36336612701416, | |
| "eval_runtime": 1.6558, | |
| "eval_samples_per_second": 271.778, | |
| "eval_steps_per_second": 135.889, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.011243851018973999, | |
| "grad_norm": 0.05552271753549576, | |
| "learning_rate": 3e-05, | |
| "loss": 10.3668, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.014991801358631998, | |
| "grad_norm": 0.06884723156690598, | |
| "learning_rate": 4e-05, | |
| "loss": 10.3545, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.014991801358631998, | |
| "eval_loss": 10.363312721252441, | |
| "eval_runtime": 1.6467, | |
| "eval_samples_per_second": 273.275, | |
| "eval_steps_per_second": 136.637, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.018739751698289998, | |
| "grad_norm": 0.08110053092241287, | |
| "learning_rate": 5e-05, | |
| "loss": 10.3606, | |
| "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": 258618163200.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |