{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.0016820150540347335, "eval_steps": 8, "global_step": 20, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 8.410075270173668e-05, "eval_loss": NaN, "eval_runtime": 115.977, "eval_samples_per_second": 43.172, "eval_steps_per_second": 21.59, "step": 1 }, { "epoch": 0.00025230225810521004, "grad_norm": NaN, "learning_rate": 6e-05, "loss": 0.0, "step": 3 }, { "epoch": 0.0005046045162104201, "grad_norm": NaN, "learning_rate": 0.00012, "loss": 0.0, "step": 6 }, { "epoch": 0.0006728060216138935, "eval_loss": NaN, "eval_runtime": 115.4012, "eval_samples_per_second": 43.388, "eval_steps_per_second": 21.698, "step": 8 }, { "epoch": 0.0007569067743156302, "grad_norm": NaN, "learning_rate": 0.00018, "loss": 0.0, "step": 9 }, { "epoch": 0.0010092090324208402, "grad_norm": NaN, "learning_rate": 0.00019510565162951537, "loss": 0.0, "step": 12 }, { "epoch": 0.0012615112905260501, "grad_norm": NaN, "learning_rate": 0.00017071067811865476, "loss": 0.0, "step": 15 }, { "epoch": 0.001345612043227787, "eval_loss": NaN, "eval_runtime": 115.0922, "eval_samples_per_second": 43.504, "eval_steps_per_second": 21.756, "step": 16 }, { "epoch": 0.0015138135486312604, "grad_norm": NaN, "learning_rate": 0.00013090169943749476, "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 }