{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.0001913753508548099, "eval_steps": 3, "global_step": 3, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 6.379178361826996e-05, "grad_norm": 0.4255746006965637, "learning_rate": 2e-05, "loss": 0.2181, "step": 1 }, { "epoch": 6.379178361826996e-05, "eval_loss": 0.3880921006202698, "eval_runtime": 136.531, "eval_samples_per_second": 48.348, "eval_steps_per_second": 24.178, "step": 1 }, { "epoch": 0.00012758356723653993, "grad_norm": 0.5769761800765991, "learning_rate": 4e-05, "loss": 0.2823, "step": 2 }, { "epoch": 0.0001913753508548099, "grad_norm": 0.5068990588188171, "learning_rate": 6e-05, "loss": 0.3933, "step": 3 }, { "epoch": 0.0001913753508548099, "eval_loss": 0.38571253418922424, "eval_runtime": 133.3112, "eval_samples_per_second": 49.516, "eval_steps_per_second": 24.762, "step": 3 } ], "logging_steps": 1, "max_steps": 10, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 3, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 53422898282496.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }