{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.00018030950820581638, "eval_steps": 10, "global_step": 13, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 1.3869962169678183e-05, "eval_loss": 0.3170296847820282, "eval_runtime": 1026.3822, "eval_samples_per_second": 29.578, "eval_steps_per_second": 14.789, "step": 1 }, { "epoch": 6.934981084839092e-05, "grad_norm": 0.6361538171768188, "learning_rate": 5e-05, "loss": 0.2943, "step": 5 }, { "epoch": 0.00013869962169678183, "grad_norm": 0.7165965437889099, "learning_rate": 0.0001, "loss": 0.2509, "step": 10 }, { "epoch": 0.00013869962169678183, "eval_loss": 0.20657119154930115, "eval_runtime": 1002.4208, "eval_samples_per_second": 30.285, "eval_steps_per_second": 15.142, "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": 411303432683520.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }