{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.002733454060887689, "eval_steps": 2, "global_step": 5, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0005466908121775379, "grad_norm": 1.0991544723510742, "learning_rate": 1e-05, "loss": 5.7542, "step": 1 }, { "epoch": 0.0005466908121775379, "eval_loss": 5.824239253997803, "eval_runtime": 223.8931, "eval_samples_per_second": 13.761, "eval_steps_per_second": 6.883, "step": 1 }, { "epoch": 0.0010933816243550757, "grad_norm": 1.129905343055725, "learning_rate": 2e-05, "loss": 5.735, "step": 2 }, { "epoch": 0.0010933816243550757, "eval_loss": 5.79716682434082, "eval_runtime": 85.2292, "eval_samples_per_second": 36.15, "eval_steps_per_second": 18.081, "step": 2 }, { "epoch": 0.0016400724365326135, "grad_norm": 1.0068832635879517, "learning_rate": 3e-05, "loss": 5.7607, "step": 3 }, { "epoch": 0.0021867632487101514, "grad_norm": 1.0093982219696045, "learning_rate": 4e-05, "loss": 5.7081, "step": 4 }, { "epoch": 0.0021867632487101514, "eval_loss": 5.755589962005615, "eval_runtime": 87.5727, "eval_samples_per_second": 35.182, "eval_steps_per_second": 17.597, "step": 4 }, { "epoch": 0.002733454060887689, "grad_norm": 1.0666111707687378, "learning_rate": 5e-05, "loss": 5.821, "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": 4438954195550208.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }