| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.013654984069185253, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0004551661356395084, | |
| "eval_loss": 2.4697165489196777, | |
| "eval_runtime": 87.2234, | |
| "eval_samples_per_second": 10.605, | |
| "eval_steps_per_second": 5.308, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0013654984069185253, | |
| "grad_norm": 1.3676774501800537, | |
| "learning_rate": 3e-05, | |
| "loss": 2.5116, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0027309968138370506, | |
| "grad_norm": 1.582930326461792, | |
| "learning_rate": 6e-05, | |
| "loss": 2.4945, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0036413290851160674, | |
| "eval_loss": 1.823874831199646, | |
| "eval_runtime": 86.1457, | |
| "eval_samples_per_second": 10.738, | |
| "eval_steps_per_second": 5.375, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.004096495220755576, | |
| "grad_norm": 1.352651834487915, | |
| "learning_rate": 9e-05, | |
| "loss": 2.0455, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.005461993627674101, | |
| "grad_norm": 0.9622390866279602, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 1.4306, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.006827492034592627, | |
| "grad_norm": 0.6104026436805725, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.1061, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.007282658170232135, | |
| "eval_loss": 0.945639431476593, | |
| "eval_runtime": 86.1537, | |
| "eval_samples_per_second": 10.737, | |
| "eval_steps_per_second": 5.374, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.008192990441511151, | |
| "grad_norm": 0.513958752155304, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 0.9718, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.009558488848429678, | |
| "grad_norm": 0.5597707629203796, | |
| "learning_rate": 4.2178276747988446e-05, | |
| "loss": 0.9183, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.010923987255348202, | |
| "grad_norm": 0.5114228129386902, | |
| "learning_rate": 2.061073738537635e-05, | |
| "loss": 0.8586, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.010923987255348202, | |
| "eval_loss": 0.848564624786377, | |
| "eval_runtime": 86.1377, | |
| "eval_samples_per_second": 10.739, | |
| "eval_steps_per_second": 5.375, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.012289485662266727, | |
| "grad_norm": 0.4467601776123047, | |
| "learning_rate": 5.449673790581611e-06, | |
| "loss": 0.8333, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.013654984069185253, | |
| "grad_norm": 0.4542919099330902, | |
| "learning_rate": 0.0, | |
| "loss": 0.8337, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.90433766408192e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |