{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.015306122448979591, "eval_steps": 3, "global_step": 3, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.00510204081632653, "grad_norm": 0.07761654257774353, "learning_rate": 2e-05, "loss": 10.3789, "step": 1 }, { "epoch": 0.00510204081632653, "eval_loss": 10.380595207214355, "eval_runtime": 0.3069, "eval_samples_per_second": 136.845, "eval_steps_per_second": 68.423, "step": 1 }, { "epoch": 0.01020408163265306, "grad_norm": 0.07940847426652908, "learning_rate": 4e-05, "loss": 10.3877, "step": 2 }, { "epoch": 0.015306122448979591, "grad_norm": 0.06227846071124077, "learning_rate": 6e-05, "loss": 10.3831, "step": 3 }, { "epoch": 0.015306122448979591, "eval_loss": 10.380550384521484, "eval_runtime": 0.3046, "eval_samples_per_second": 137.879, "eval_steps_per_second": 68.939, "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": 2, "trial_name": null, "trial_params": null }