{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.07136485280999108, "eval_steps": 2, "global_step": 5, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.014272970561998216, "grad_norm": 122.65941619873047, "learning_rate": 1e-05, "loss": 124.8761, "step": 1 }, { "epoch": 0.014272970561998216, "eval_loss": 7.847517490386963, "eval_runtime": 17.5573, "eval_samples_per_second": 6.721, "eval_steps_per_second": 3.36, "step": 1 }, { "epoch": 0.028545941123996433, "grad_norm": 119.40007781982422, "learning_rate": 2e-05, "loss": 124.0966, "step": 2 }, { "epoch": 0.028545941123996433, "eval_loss": 7.562459468841553, "eval_runtime": 4.1558, "eval_samples_per_second": 28.394, "eval_steps_per_second": 14.197, "step": 2 }, { "epoch": 0.042818911685994644, "grad_norm": 117.02621459960938, "learning_rate": 3e-05, "loss": 129.1238, "step": 3 }, { "epoch": 0.057091882247992866, "grad_norm": 128.15509033203125, "learning_rate": 4e-05, "loss": 123.3496, "step": 4 }, { "epoch": 0.057091882247992866, "eval_loss": 7.311307907104492, "eval_runtime": 4.2522, "eval_samples_per_second": 27.75, "eval_steps_per_second": 13.875, "step": 4 }, { "epoch": 0.07136485280999108, "grad_norm": 130.52099609375, "learning_rate": 5e-05, "loss": 126.2317, "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": 3257466271825920.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }