{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.06920415224913495, "eval_steps": 10, "global_step": 50, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.001384083044982699, "eval_loss": NaN, "eval_runtime": 153.9103, "eval_samples_per_second": 1.982, "eval_steps_per_second": 0.994, "step": 1 }, { "epoch": 0.006920415224913495, "grad_norm": NaN, "learning_rate": 5e-05, "loss": 0.0, "step": 5 }, { "epoch": 0.01384083044982699, "grad_norm": NaN, "learning_rate": 0.0001, "loss": 0.0, "step": 10 }, { "epoch": 0.01384083044982699, "eval_loss": NaN, "eval_runtime": 123.8592, "eval_samples_per_second": 2.462, "eval_steps_per_second": 1.235, "step": 10 }, { "epoch": 0.020761245674740483, "grad_norm": NaN, "learning_rate": 9.619397662556435e-05, "loss": 0.0, "step": 15 }, { "epoch": 0.02768166089965398, "grad_norm": NaN, "learning_rate": 8.535533905932738e-05, "loss": 0.0, "step": 20 }, { "epoch": 0.02768166089965398, "eval_loss": NaN, "eval_runtime": 88.124, "eval_samples_per_second": 3.461, "eval_steps_per_second": 1.736, "step": 20 }, { "epoch": 0.03460207612456748, "grad_norm": NaN, "learning_rate": 6.91341716182545e-05, "loss": 0.0, "step": 25 }, { "epoch": 0.04152249134948097, "grad_norm": NaN, "learning_rate": 5e-05, "loss": 0.0, "step": 30 }, { "epoch": 0.04152249134948097, "eval_loss": NaN, "eval_runtime": 89.2948, "eval_samples_per_second": 3.416, "eval_steps_per_second": 1.713, "step": 30 }, { "epoch": 0.04844290657439446, "grad_norm": NaN, "learning_rate": 3.086582838174551e-05, "loss": 0.0, "step": 35 }, { "epoch": 0.05536332179930796, "grad_norm": NaN, "learning_rate": 1.4644660940672627e-05, "loss": 0.0, "step": 40 }, { "epoch": 0.05536332179930796, "eval_loss": NaN, "eval_runtime": 111.5157, "eval_samples_per_second": 2.735, "eval_steps_per_second": 1.372, "step": 40 }, { "epoch": 0.06228373702422145, "grad_norm": NaN, "learning_rate": 3.8060233744356633e-06, "loss": 0.0, "step": 45 }, { "epoch": 0.06920415224913495, "grad_norm": NaN, "learning_rate": 0.0, "loss": 0.0, "step": 50 }, { "epoch": 0.06920415224913495, "eval_loss": NaN, "eval_runtime": 52.8393, "eval_samples_per_second": 5.772, "eval_steps_per_second": 2.896, "step": 50 } ], "logging_steps": 5, "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": 1.7439064370184192e+16, "train_batch_size": 2, "trial_name": null, "trial_params": null }