{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.008676789587852495, "eval_steps": 4, "global_step": 8, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0010845986984815619, "grad_norm": NaN, "learning_rate": 2e-05, "loss": 0.0, "step": 1 }, { "epoch": 0.0010845986984815619, "eval_loss": NaN, "eval_runtime": 51.7259, "eval_samples_per_second": 7.52, "eval_steps_per_second": 3.77, "step": 1 }, { "epoch": 0.0021691973969631237, "grad_norm": NaN, "learning_rate": 4e-05, "loss": 0.0, "step": 2 }, { "epoch": 0.0032537960954446853, "grad_norm": NaN, "learning_rate": 6e-05, "loss": 0.0, "step": 3 }, { "epoch": 0.004338394793926247, "grad_norm": NaN, "learning_rate": 8e-05, "loss": 0.0, "step": 4 }, { "epoch": 0.004338394793926247, "eval_loss": NaN, "eval_runtime": 54.4666, "eval_samples_per_second": 7.142, "eval_steps_per_second": 3.58, "step": 4 }, { "epoch": 0.005422993492407809, "grad_norm": NaN, "learning_rate": 0.0001, "loss": 0.0, "step": 5 }, { "epoch": 0.006507592190889371, "grad_norm": NaN, "learning_rate": 0.00012, "loss": 0.0, "step": 6 }, { "epoch": 0.007592190889370932, "grad_norm": NaN, "learning_rate": 0.00014, "loss": 0.0, "step": 7 }, { "epoch": 0.008676789587852495, "grad_norm": NaN, "learning_rate": 0.00016, "loss": 0.0, "step": 8 }, { "epoch": 0.008676789587852495, "eval_loss": NaN, "eval_runtime": 80.2469, "eval_samples_per_second": 4.848, "eval_steps_per_second": 2.43, "step": 8 } ], "logging_steps": 1, "max_steps": 50, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 4, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 2235874343387136.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }