{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.029465930018416207, "eval_steps": 2, "global_step": 5, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.005893186003683241, "grad_norm": 8.563546180725098, "learning_rate": 1e-05, "loss": 44.2619, "step": 1 }, { "epoch": 0.005893186003683241, "eval_loss": 3.2567617893218994, "eval_runtime": 140.4224, "eval_samples_per_second": 2.037, "eval_steps_per_second": 1.018, "step": 1 }, { "epoch": 0.011786372007366482, "grad_norm": 12.657698631286621, "learning_rate": 2e-05, "loss": 58.2185, "step": 2 }, { "epoch": 0.011786372007366482, "eval_loss": 3.2391741275787354, "eval_runtime": 6.4304, "eval_samples_per_second": 44.476, "eval_steps_per_second": 22.238, "step": 2 }, { "epoch": 0.017679558011049725, "grad_norm": 11.54467487335205, "learning_rate": 3e-05, "loss": 45.2464, "step": 3 }, { "epoch": 0.023572744014732964, "grad_norm": 9.715700149536133, "learning_rate": 4e-05, "loss": 49.2271, "step": 4 }, { "epoch": 0.023572744014732964, "eval_loss": 3.22546648979187, "eval_runtime": 6.439, "eval_samples_per_second": 44.417, "eval_steps_per_second": 22.208, "step": 4 }, { "epoch": 0.029465930018416207, "grad_norm": 7.524972438812256, "learning_rate": 5e-05, "loss": 46.4934, "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": 3298217215131648.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }