{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.001171760570256811, "eval_steps": 3, "global_step": 3, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.00039058685675227026, "grad_norm": 30.679697036743164, "learning_rate": 2e-05, "loss": 38.7076, "step": 1 }, { "epoch": 0.00039058685675227026, "eval_loss": 9.116019248962402, "eval_runtime": 95.3874, "eval_samples_per_second": 11.301, "eval_steps_per_second": 5.651, "step": 1 }, { "epoch": 0.0007811737135045405, "grad_norm": 43.26640319824219, "learning_rate": 4e-05, "loss": 33.6181, "step": 2 }, { "epoch": 0.001171760570256811, "grad_norm": 39.603065490722656, "learning_rate": 6e-05, "loss": 35.1822, "step": 3 }, { "epoch": 0.001171760570256811, "eval_loss": 9.003752708435059, "eval_runtime": 95.4521, "eval_samples_per_second": 11.294, "eval_steps_per_second": 5.647, "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": 732937158918144.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }