{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.013726835964310227, "eval_steps": 3, "global_step": 10, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0013726835964310226, "grad_norm": NaN, "learning_rate": 2e-05, "loss": 0.0, "step": 1 }, { "epoch": 0.0013726835964310226, "eval_loss": NaN, "eval_runtime": 28.271, "eval_samples_per_second": 10.859, "eval_steps_per_second": 5.447, "step": 1 }, { "epoch": 0.002745367192862045, "grad_norm": NaN, "learning_rate": 4e-05, "loss": 0.0, "step": 2 }, { "epoch": 0.004118050789293068, "grad_norm": NaN, "learning_rate": 6e-05, "loss": 0.0, "step": 3 }, { "epoch": 0.004118050789293068, "eval_loss": NaN, "eval_runtime": 26.5161, "eval_samples_per_second": 11.578, "eval_steps_per_second": 5.808, "step": 3 }, { "epoch": 0.00549073438572409, "grad_norm": NaN, "learning_rate": 8e-05, "loss": 0.0, "step": 4 }, { "epoch": 0.0068634179821551134, "grad_norm": NaN, "learning_rate": 0.0001, "loss": 0.0, "step": 5 }, { "epoch": 0.008236101578586136, "grad_norm": NaN, "learning_rate": 0.00012, "loss": 0.0, "step": 6 }, { "epoch": 0.008236101578586136, "eval_loss": NaN, "eval_runtime": 26.5539, "eval_samples_per_second": 11.561, "eval_steps_per_second": 5.8, "step": 6 }, { "epoch": 0.009608785175017159, "grad_norm": NaN, "learning_rate": 0.00014, "loss": 0.0, "step": 7 }, { "epoch": 0.01098146877144818, "grad_norm": NaN, "learning_rate": 0.00016, "loss": 0.0, "step": 8 }, { "epoch": 0.012354152367879203, "grad_norm": NaN, "learning_rate": 0.00018, "loss": 0.0, "step": 9 }, { "epoch": 0.012354152367879203, "eval_loss": NaN, "eval_runtime": 26.4934, "eval_samples_per_second": 11.588, "eval_steps_per_second": 5.813, "step": 9 }, { "epoch": 0.013726835964310227, "grad_norm": NaN, "learning_rate": 0.0002, "loss": 0.0, "step": 10 } ], "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": true }, "attributes": {} } }, "total_flos": 5343937617199104.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }