{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.0008429393294417634, "eval_steps": 3, "global_step": 10, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 8.429393294417634e-05, "grad_norm": NaN, "learning_rate": 2e-05, "loss": 0.0, "step": 1 }, { "epoch": 8.429393294417634e-05, "eval_loss": NaN, "eval_runtime": 151.8805, "eval_samples_per_second": 32.888, "eval_steps_per_second": 16.447, "step": 1 }, { "epoch": 0.00016858786588835268, "grad_norm": NaN, "learning_rate": 4e-05, "loss": 0.0, "step": 2 }, { "epoch": 0.00025288179883252904, "grad_norm": NaN, "learning_rate": 6e-05, "loss": 0.0, "step": 3 }, { "epoch": 0.00025288179883252904, "eval_loss": NaN, "eval_runtime": 150.4613, "eval_samples_per_second": 33.198, "eval_steps_per_second": 16.602, "step": 3 }, { "epoch": 0.00033717573177670536, "grad_norm": NaN, "learning_rate": 8e-05, "loss": 0.0, "step": 4 }, { "epoch": 0.0004214696647208817, "grad_norm": NaN, "learning_rate": 0.0001, "loss": 0.0, "step": 5 }, { "epoch": 0.0005057635976650581, "grad_norm": NaN, "learning_rate": 0.00012, "loss": 0.0, "step": 6 }, { "epoch": 0.0005057635976650581, "eval_loss": NaN, "eval_runtime": 150.6111, "eval_samples_per_second": 33.165, "eval_steps_per_second": 16.586, "step": 6 }, { "epoch": 0.0005900575306092345, "grad_norm": NaN, "learning_rate": 0.00014, "loss": 0.0, "step": 7 }, { "epoch": 0.0006743514635534107, "grad_norm": NaN, "learning_rate": 0.00016, "loss": 0.0, "step": 8 }, { "epoch": 0.0007586453964975871, "grad_norm": NaN, "learning_rate": 0.00018, "loss": 0.0, "step": 9 }, { "epoch": 0.0007586453964975871, "eval_loss": NaN, "eval_runtime": 153.3619, "eval_samples_per_second": 32.57, "eval_steps_per_second": 16.288, "step": 9 }, { "epoch": 0.0008429393294417634, "grad_norm": NaN, "learning_rate": 0.0002, "loss": 0.0, "step": 10 } ], "logging_steps": 1, "max_steps": 10, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 3, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 1752671799214080.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }