{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.0020083682008368202, "eval_steps": 3, "global_step": 3, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0006694560669456067, "grad_norm": 0.34888479113578796, "learning_rate": 2e-05, "loss": 10.35, "step": 1 }, { "epoch": 0.0006694560669456067, "eval_loss": 10.36190414428711, "eval_runtime": 5.6591, "eval_samples_per_second": 55.663, "eval_steps_per_second": 55.663, "step": 1 }, { "epoch": 0.0013389121338912135, "grad_norm": 0.3063121736049652, "learning_rate": 4e-05, "loss": 10.3663, "step": 2 }, { "epoch": 0.0020083682008368202, "grad_norm": 0.30662232637405396, "learning_rate": 6e-05, "loss": 10.3876, "step": 3 }, { "epoch": 0.0020083682008368202, "eval_loss": 10.36156940460205, "eval_runtime": 5.663, "eval_samples_per_second": 55.624, "eval_steps_per_second": 55.624, "step": 3 } ], "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": false }, "attributes": {} } }, "total_flos": 156907339776.0, "train_batch_size": 1, "trial_name": null, "trial_params": null }