{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.005306122448979592, "eval_steps": 10, "global_step": 13, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.00040816326530612246, "eval_loss": 1.038622498512268, "eval_runtime": 100.2598, "eval_samples_per_second": 10.293, "eval_steps_per_second": 5.147, "step": 1 }, { "epoch": 0.0020408163265306124, "grad_norm": 1.570367455482483, "learning_rate": 5e-05, "loss": 4.0227, "step": 5 }, { "epoch": 0.004081632653061225, "grad_norm": 1.5186132192611694, "learning_rate": 0.0001, "loss": 3.7081, "step": 10 }, { "epoch": 0.004081632653061225, "eval_loss": 0.9728806614875793, "eval_runtime": 100.715, "eval_samples_per_second": 10.247, "eval_steps_per_second": 5.123, "step": 10 } ], "logging_steps": 5, "max_steps": 50, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 13, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 4493168439459840.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }