{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.0013652809065465218, "eval_steps": 8, "global_step": 20, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 6.82640453273261e-05, "eval_loss": 11.5, "eval_runtime": 64.3905, "eval_samples_per_second": 95.79, "eval_steps_per_second": 47.895, "step": 1 }, { "epoch": 0.00020479213598197828, "grad_norm": 2.1372459741542116e-05, "learning_rate": 3e-05, "loss": 46.0, "step": 3 }, { "epoch": 0.00040958427196395656, "grad_norm": 1.6634101484669372e-05, "learning_rate": 6e-05, "loss": 46.0, "step": 6 }, { "epoch": 0.0005461123626186088, "eval_loss": 11.5, "eval_runtime": 64.1319, "eval_samples_per_second": 96.177, "eval_steps_per_second": 48.088, "step": 8 }, { "epoch": 0.0006143764079459349, "grad_norm": 2.0664107069023885e-05, "learning_rate": 9e-05, "loss": 46.0, "step": 9 }, { "epoch": 0.0008191685439279131, "grad_norm": 2.0053583284607157e-05, "learning_rate": 9.755282581475769e-05, "loss": 46.0, "step": 12 }, { "epoch": 0.0010239606799098914, "grad_norm": 2.8997801564401016e-05, "learning_rate": 8.535533905932738e-05, "loss": 46.0, "step": 15 }, { "epoch": 0.0010922247252372176, "eval_loss": 11.5, "eval_runtime": 63.3764, "eval_samples_per_second": 97.323, "eval_steps_per_second": 48.662, "step": 16 }, { "epoch": 0.0012287528158918697, "grad_norm": 2.1670148271368816e-05, "learning_rate": 6.545084971874738e-05, "loss": 46.0, "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": 847791882240.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }