{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 3.0, "eval_steps": 500, "global_step": 102, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.29411764705882354, "grad_norm": 1.5918463468551636, "learning_rate": 1.8e-05, "loss": 1.0492, "step": 10 }, { "epoch": 0.5882352941176471, "grad_norm": 1.0894666910171509, "learning_rate": 3.8e-05, "loss": 1.0001, "step": 20 }, { "epoch": 0.8823529411764706, "grad_norm": 1.1242390871047974, "learning_rate": 5.8e-05, "loss": 0.9192, "step": 30 }, { "epoch": 1.1764705882352942, "grad_norm": 1.2691138982772827, "learning_rate": 7.800000000000001e-05, "loss": 0.749, "step": 40 }, { "epoch": 1.4705882352941178, "grad_norm": 1.6192694902420044, "learning_rate": 9.8e-05, "loss": 0.537, "step": 50 }, { "epoch": 1.7647058823529411, "grad_norm": 1.2546160221099854, "learning_rate": 0.000118, "loss": 0.2958, "step": 60 }, { "epoch": 2.0588235294117645, "grad_norm": 1.426198959350586, "learning_rate": 0.000138, "loss": 0.1433, "step": 70 }, { "epoch": 2.3529411764705883, "grad_norm": 1.1286216974258423, "learning_rate": 0.00015800000000000002, "loss": 0.0871, "step": 80 }, { "epoch": 2.6470588235294117, "grad_norm": 1.5918883085250854, "learning_rate": 0.00017800000000000002, "loss": 0.0575, "step": 90 }, { "epoch": 2.9411764705882355, "grad_norm": 0.5912705659866333, "learning_rate": 0.00019800000000000002, "loss": 0.0518, "step": 100 } ], "logging_steps": 10, "max_steps": 102, "num_input_tokens_seen": 0, "num_train_epochs": 3, "save_steps": 500, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 2403535345238016.0, "train_batch_size": 4, "trial_name": null, "trial_params": null }