{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.0014346944997399617, "eval_steps": 2, "global_step": 5, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0002869388999479923, "grad_norm": NaN, "learning_rate": 1e-05, "loss": 0.0, "step": 1 }, { "epoch": 0.0002869388999479923, "eval_loss": NaN, "eval_runtime": 615.0609, "eval_samples_per_second": 9.544, "eval_steps_per_second": 4.772, "step": 1 }, { "epoch": 0.0005738777998959846, "grad_norm": NaN, "learning_rate": 2e-05, "loss": 5.6133, "step": 2 }, { "epoch": 0.0005738777998959846, "eval_loss": NaN, "eval_runtime": 483.7684, "eval_samples_per_second": 12.134, "eval_steps_per_second": 6.067, "step": 2 }, { "epoch": 0.000860816699843977, "grad_norm": NaN, "learning_rate": 3e-05, "loss": 0.8038, "step": 3 }, { "epoch": 0.0011477555997919692, "grad_norm": NaN, "learning_rate": 4e-05, "loss": 196.9275, "step": 4 }, { "epoch": 0.0011477555997919692, "eval_loss": NaN, "eval_runtime": 484.2776, "eval_samples_per_second": 12.121, "eval_steps_per_second": 6.061, "step": 4 }, { "epoch": 0.0014346944997399617, "grad_norm": NaN, "learning_rate": 5e-05, "loss": 0.6038, "step": 5 } ], "logging_steps": 1, "max_steps": 5, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 2, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 6038628530651136.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }