{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.006938421509106678, "eval_steps": 10, "global_step": 26, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0002668623657348722, "eval_loss": 1.4171478748321533, "eval_runtime": 51.4601, "eval_samples_per_second": 30.665, "eval_steps_per_second": 15.332, "step": 1 }, { "epoch": 0.0013343118286743613, "grad_norm": 0.20870009064674377, "learning_rate": 5e-05, "loss": 1.1958, "step": 5 }, { "epoch": 0.0026686236573487225, "grad_norm": 0.3936935365200043, "learning_rate": 0.0001, "loss": 1.4671, "step": 10 }, { "epoch": 0.0026686236573487225, "eval_loss": 1.3937021493911743, "eval_runtime": 51.4019, "eval_samples_per_second": 30.699, "eval_steps_per_second": 15.35, "step": 10 }, { "epoch": 0.004002935486023084, "grad_norm": 0.2306661754846573, "learning_rate": 9.619397662556435e-05, "loss": 1.3999, "step": 15 }, { "epoch": 0.005337247314697445, "grad_norm": 0.28997236490249634, "learning_rate": 8.535533905932738e-05, "loss": 1.3391, "step": 20 }, { "epoch": 0.005337247314697445, "eval_loss": 1.331410527229309, "eval_runtime": 51.2329, "eval_samples_per_second": 30.801, "eval_steps_per_second": 15.4, "step": 20 }, { "epoch": 0.006671559143371806, "grad_norm": 0.2963295876979828, "learning_rate": 6.91341716182545e-05, "loss": 1.3088, "step": 25 } ], "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": 940035520069632.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }