{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.04317323259579061, "eval_steps": 8, "global_step": 20, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0021586616297895305, "eval_loss": NaN, "eval_runtime": 11.8611, "eval_samples_per_second": 16.44, "eval_steps_per_second": 8.262, "step": 1 }, { "epoch": 0.0064759848893685915, "grad_norm": NaN, "learning_rate": 6e-05, "loss": 0.0, "step": 3 }, { "epoch": 0.012951969778737183, "grad_norm": NaN, "learning_rate": 0.00012, "loss": 0.0, "step": 6 }, { "epoch": 0.017269293038316244, "eval_loss": NaN, "eval_runtime": 10.7461, "eval_samples_per_second": 18.146, "eval_steps_per_second": 9.12, "step": 8 }, { "epoch": 0.019427954668105773, "grad_norm": NaN, "learning_rate": 0.00018, "loss": 0.0, "step": 9 }, { "epoch": 0.025903939557474366, "grad_norm": NaN, "learning_rate": 0.00019510565162951537, "loss": 0.0, "step": 12 }, { "epoch": 0.032379924446842956, "grad_norm": NaN, "learning_rate": 0.00017071067811865476, "loss": 0.0, "step": 15 }, { "epoch": 0.03453858607663249, "eval_loss": NaN, "eval_runtime": 10.7612, "eval_samples_per_second": 18.121, "eval_steps_per_second": 9.107, "step": 16 }, { "epoch": 0.038855909336211546, "grad_norm": NaN, "learning_rate": 0.00013090169943749476, "loss": 0.0, "step": 18 } ], "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": false }, "attributes": {} } }, "total_flos": 7031303039877120.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }