{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.13928182807399347, "eval_steps": 8, "global_step": 8, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.017410228509249184, "grad_norm": 0.062456175684928894, "learning_rate": 1e-05, "loss": 11.7644, "step": 1 }, { "epoch": 0.017410228509249184, "eval_loss": 11.76516342163086, "eval_runtime": 19.3362, "eval_samples_per_second": 5.017, "eval_steps_per_second": 2.534, "step": 1 }, { "epoch": 0.03482045701849837, "grad_norm": 0.05811762437224388, "learning_rate": 2e-05, "loss": 11.7635, "step": 2 }, { "epoch": 0.05223068552774755, "grad_norm": 0.056335750967264175, "learning_rate": 3e-05, "loss": 11.7662, "step": 3 }, { "epoch": 0.06964091403699674, "grad_norm": 0.0577821359038353, "learning_rate": 4e-05, "loss": 11.7642, "step": 4 }, { "epoch": 0.08705114254624592, "grad_norm": 0.06373099237680435, "learning_rate": 5e-05, "loss": 11.765, "step": 5 }, { "epoch": 0.1044613710554951, "grad_norm": 0.05691263824701309, "learning_rate": 6e-05, "loss": 11.7642, "step": 6 }, { "epoch": 0.12187159956474429, "grad_norm": 0.050343748182058334, "learning_rate": 7e-05, "loss": 11.7632, "step": 7 }, { "epoch": 0.13928182807399347, "grad_norm": 0.05291908606886864, "learning_rate": 8e-05, "loss": 11.7633, "step": 8 }, { "epoch": 0.13928182807399347, "eval_loss": 11.764686584472656, "eval_runtime": 0.5287, "eval_samples_per_second": 183.453, "eval_steps_per_second": 92.672, "step": 8 } ], "logging_steps": 1, "max_steps": 30, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 8, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 13036802801664.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }