{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.009707559762164785, "eval_steps": 2, "global_step": 5, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.001941511952432957, "grad_norm": NaN, "learning_rate": 1e-05, "loss": 275.2264, "step": 1 }, { "epoch": 0.001941511952432957, "eval_loss": NaN, "eval_runtime": 100.0491, "eval_samples_per_second": 8.676, "eval_steps_per_second": 4.338, "step": 1 }, { "epoch": 0.003883023904865914, "grad_norm": NaN, "learning_rate": 2e-05, "loss": 0.0, "step": 2 }, { "epoch": 0.003883023904865914, "eval_loss": NaN, "eval_runtime": 49.8996, "eval_samples_per_second": 17.395, "eval_steps_per_second": 8.697, "step": 2 }, { "epoch": 0.005824535857298871, "grad_norm": NaN, "learning_rate": 3e-05, "loss": 4661.3799, "step": 3 }, { "epoch": 0.007766047809731828, "grad_norm": NaN, "learning_rate": 4e-05, "loss": 3542.4739, "step": 4 }, { "epoch": 0.007766047809731828, "eval_loss": NaN, "eval_runtime": 49.9084, "eval_samples_per_second": 17.392, "eval_steps_per_second": 8.696, "step": 4 }, { "epoch": 0.009707559762164785, "grad_norm": NaN, "learning_rate": 5e-05, "loss": 3794.8223, "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": 7013771520245760.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }