| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.015585427625170466, | |
| "eval_steps": 2, | |
| "global_step": 5, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.003117085525034093, | |
| "grad_norm": 4.10905122756958, | |
| "learning_rate": 1e-05, | |
| "loss": 3.1548, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.003117085525034093, | |
| "eval_loss": 3.1840431690216064, | |
| "eval_runtime": 150.4556, | |
| "eval_samples_per_second": 3.596, | |
| "eval_steps_per_second": 1.801, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006234171050068186, | |
| "grad_norm": 3.9939048290252686, | |
| "learning_rate": 2e-05, | |
| "loss": 2.8185, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.006234171050068186, | |
| "eval_loss": 3.0775887966156006, | |
| "eval_runtime": 49.391, | |
| "eval_samples_per_second": 10.953, | |
| "eval_steps_per_second": 5.487, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.009351256575102279, | |
| "grad_norm": 3.3020169734954834, | |
| "learning_rate": 3e-05, | |
| "loss": 2.6586, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.012468342100136372, | |
| "grad_norm": 3.3821675777435303, | |
| "learning_rate": 4e-05, | |
| "loss": 2.6943, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.012468342100136372, | |
| "eval_loss": 2.876417398452759, | |
| "eval_runtime": 50.6504, | |
| "eval_samples_per_second": 10.681, | |
| "eval_steps_per_second": 5.35, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.015585427625170466, | |
| "grad_norm": 4.055932521820068, | |
| "learning_rate": 5e-05, | |
| "loss": 2.8792, | |
| "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": 3699128496291840.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |