| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.04092699647004656, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0008185399294009311, | |
| "eval_loss": 11.93117618560791, | |
| "eval_runtime": 48.7806, | |
| "eval_samples_per_second": 168.715, | |
| "eval_steps_per_second": 21.094, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.008185399294009311, | |
| "grad_norm": 0.01417671050876379, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 11.9313, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.008185399294009311, | |
| "eval_loss": 11.931010246276855, | |
| "eval_runtime": 48.6221, | |
| "eval_samples_per_second": 169.265, | |
| "eval_steps_per_second": 21.163, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.016370798588018622, | |
| "grad_norm": 0.016160357743501663, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 11.9308, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.016370798588018622, | |
| "eval_loss": 11.93083667755127, | |
| "eval_runtime": 48.6409, | |
| "eval_samples_per_second": 169.199, | |
| "eval_steps_per_second": 21.155, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.02455619788202793, | |
| "grad_norm": 0.015912150964140892, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 11.9311, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.02455619788202793, | |
| "eval_loss": 11.930720329284668, | |
| "eval_runtime": 48.7641, | |
| "eval_samples_per_second": 168.772, | |
| "eval_steps_per_second": 21.102, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.032741597176037245, | |
| "grad_norm": 0.016216600313782692, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 11.9312, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.032741597176037245, | |
| "eval_loss": 11.930665969848633, | |
| "eval_runtime": 48.5505, | |
| "eval_samples_per_second": 169.514, | |
| "eval_steps_per_second": 21.194, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.04092699647004656, | |
| "grad_norm": 0.01642616279423237, | |
| "learning_rate": 0.0, | |
| "loss": 11.9304, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.04092699647004656, | |
| "eval_loss": 11.930656433105469, | |
| "eval_runtime": 48.9823, | |
| "eval_samples_per_second": 168.02, | |
| "eval_steps_per_second": 21.008, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 180668792832.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |