| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9523809523809523, | |
| "eval_steps": 2, | |
| "global_step": 5, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.19047619047619047, | |
| "grad_norm": 0.6613984107971191, | |
| "learning_rate": 1e-05, | |
| "loss": 5.0702, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.19047619047619047, | |
| "eval_loss": 4.947175979614258, | |
| "eval_runtime": 70.5897, | |
| "eval_samples_per_second": 0.127, | |
| "eval_steps_per_second": 0.071, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.38095238095238093, | |
| "grad_norm": 0.6620290875434875, | |
| "learning_rate": 2e-05, | |
| "loss": 5.1144, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.38095238095238093, | |
| "eval_loss": 4.9326491355896, | |
| "eval_runtime": 0.1609, | |
| "eval_samples_per_second": 55.933, | |
| "eval_steps_per_second": 31.074, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.5714285714285714, | |
| "grad_norm": 0.6408684849739075, | |
| "learning_rate": 3e-05, | |
| "loss": 4.9994, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.7619047619047619, | |
| "grad_norm": 0.6830849051475525, | |
| "learning_rate": 4e-05, | |
| "loss": 4.8336, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.7619047619047619, | |
| "eval_loss": 4.910813331604004, | |
| "eval_runtime": 0.1605, | |
| "eval_samples_per_second": 56.063, | |
| "eval_steps_per_second": 31.146, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.9523809523809523, | |
| "grad_norm": 0.6951197385787964, | |
| "learning_rate": 5e-05, | |
| "loss": 5.0532, | |
| "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": 649047740252160.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |