{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.00023078831518760207, "eval_steps": 8, "global_step": 20, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 1.1539415759380102e-05, "eval_loss": NaN, "eval_runtime": 1324.7781, "eval_samples_per_second": 27.543, "eval_steps_per_second": 13.772, "step": 1 }, { "epoch": 3.4618247278140306e-05, "grad_norm": NaN, "learning_rate": 3e-05, "loss": 0.0, "step": 3 }, { "epoch": 6.923649455628061e-05, "grad_norm": NaN, "learning_rate": 6e-05, "loss": 0.0, "step": 6 }, { "epoch": 9.231532607504082e-05, "eval_loss": NaN, "eval_runtime": 1327.3751, "eval_samples_per_second": 27.49, "eval_steps_per_second": 13.745, "step": 8 }, { "epoch": 0.00010385474183442092, "grad_norm": NaN, "learning_rate": 9e-05, "loss": 0.0, "step": 9 }, { "epoch": 0.00013847298911256122, "grad_norm": NaN, "learning_rate": 9.755282581475769e-05, "loss": 0.0, "step": 12 }, { "epoch": 0.00017309123639070153, "grad_norm": NaN, "learning_rate": 8.535533905932738e-05, "loss": 0.0, "step": 15 }, { "epoch": 0.00018463065215008163, "eval_loss": NaN, "eval_runtime": 1328.9321, "eval_samples_per_second": 27.457, "eval_steps_per_second": 13.729, "step": 16 }, { "epoch": 0.00020770948366884183, "grad_norm": NaN, "learning_rate": 6.545084971874738e-05, "loss": 0.0, "step": 18 } ], "logging_steps": 3, "max_steps": 30, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 10, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 317835234508800.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }