| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0557361820715281, | |
| "eval_steps": 5, | |
| "global_step": 15, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0037157454714352067, | |
| "grad_norm": 0.32735493779182434, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5292, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0037157454714352067, | |
| "eval_loss": 0.4839753806591034, | |
| "eval_runtime": 100.0543, | |
| "eval_samples_per_second": 4.538, | |
| "eval_steps_per_second": 2.269, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0074314909428704135, | |
| "grad_norm": 0.3177517354488373, | |
| "learning_rate": 2e-05, | |
| "loss": 0.4889, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.01114723641430562, | |
| "grad_norm": 0.36739614605903625, | |
| "learning_rate": 3e-05, | |
| "loss": 0.3446, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.014862981885740827, | |
| "grad_norm": 0.36301374435424805, | |
| "learning_rate": 4e-05, | |
| "loss": 0.5337, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.018578727357176035, | |
| "grad_norm": 0.3157189190387726, | |
| "learning_rate": 5e-05, | |
| "loss": 0.5449, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.018578727357176035, | |
| "eval_loss": 0.4614884853363037, | |
| "eval_runtime": 9.8273, | |
| "eval_samples_per_second": 46.198, | |
| "eval_steps_per_second": 23.099, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.02229447282861124, | |
| "grad_norm": 0.2971644699573517, | |
| "learning_rate": 6e-05, | |
| "loss": 0.3722, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.026010218300046448, | |
| "grad_norm": 0.3282870054244995, | |
| "learning_rate": 7e-05, | |
| "loss": 0.6116, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.029725963771481654, | |
| "grad_norm": 0.23263013362884521, | |
| "learning_rate": 8e-05, | |
| "loss": 0.3409, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.03344170924291686, | |
| "grad_norm": 0.2565314471721649, | |
| "learning_rate": 9e-05, | |
| "loss": 0.4412, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.03715745471435207, | |
| "grad_norm": 0.27301663160324097, | |
| "learning_rate": 0.0001, | |
| "loss": 0.5082, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03715745471435207, | |
| "eval_loss": 0.3971236050128937, | |
| "eval_runtime": 9.8535, | |
| "eval_samples_per_second": 46.075, | |
| "eval_steps_per_second": 23.037, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.04087320018578727, | |
| "grad_norm": 0.23618359863758087, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 0.2925, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.04458894565722248, | |
| "grad_norm": 0.26923471689224243, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 0.4487, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.048304691128657685, | |
| "grad_norm": 0.24448110163211823, | |
| "learning_rate": 7.938926261462366e-05, | |
| "loss": 0.4403, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.052020436600092895, | |
| "grad_norm": 0.21692927181720734, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 0.3711, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0557361820715281, | |
| "grad_norm": 0.24978867173194885, | |
| "learning_rate": 5e-05, | |
| "loss": 0.532, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0557361820715281, | |
| "eval_loss": 0.3599291443824768, | |
| "eval_runtime": 9.841, | |
| "eval_samples_per_second": 46.133, | |
| "eval_steps_per_second": 23.067, | |
| "step": 15 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 20, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 5, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5488568204525568.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |