{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.07048458149779736, "eval_steps": 2, "global_step": 5, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.014096916299559472, "grad_norm": 149.59339904785156, "learning_rate": 1e-05, "loss": 128.4375, "step": 1 }, { "epoch": 0.014096916299559472, "eval_loss": 8.011458396911621, "eval_runtime": 29.7179, "eval_samples_per_second": 4.038, "eval_steps_per_second": 2.019, "step": 1 }, { "epoch": 0.028193832599118944, "grad_norm": 154.22264099121094, "learning_rate": 2e-05, "loss": 126.6875, "step": 2 }, { "epoch": 0.028193832599118944, "eval_loss": 7.824479103088379, "eval_runtime": 0.9427, "eval_samples_per_second": 127.292, "eval_steps_per_second": 63.646, "step": 2 }, { "epoch": 0.04229074889867841, "grad_norm": 143.23622131347656, "learning_rate": 3e-05, "loss": 126.6562, "step": 3 }, { "epoch": 0.05638766519823789, "grad_norm": 145.47706604003906, "learning_rate": 4e-05, "loss": 121.875, "step": 4 }, { "epoch": 0.05638766519823789, "eval_loss": 7.481770992279053, "eval_runtime": 0.9623, "eval_samples_per_second": 124.708, "eval_steps_per_second": 62.354, "step": 4 }, { "epoch": 0.07048458149779736, "grad_norm": 142.44354248046875, "learning_rate": 5e-05, "loss": 120.5938, "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": 597144738201600.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }