{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.03334722801167153, "eval_steps": 2, "global_step": 5, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.006669445602334306, "grad_norm": 0.34966224431991577, "learning_rate": 1e-05, "loss": 6.9466, "step": 1 }, { "epoch": 0.006669445602334306, "eval_loss": 6.940125942230225, "eval_runtime": 18.3412, "eval_samples_per_second": 13.794, "eval_steps_per_second": 6.924, "step": 1 }, { "epoch": 0.013338891204668612, "grad_norm": 0.299949049949646, "learning_rate": 2e-05, "loss": 6.9427, "step": 2 }, { "epoch": 0.013338891204668612, "eval_loss": 6.940037727355957, "eval_runtime": 0.7981, "eval_samples_per_second": 317.004, "eval_steps_per_second": 159.129, "step": 2 }, { "epoch": 0.020008336807002917, "grad_norm": 0.33689865469932556, "learning_rate": 3e-05, "loss": 6.9413, "step": 3 }, { "epoch": 0.026677782409337224, "grad_norm": 0.3205243647098541, "learning_rate": 4e-05, "loss": 6.9515, "step": 4 }, { "epoch": 0.026677782409337224, "eval_loss": 6.9397125244140625, "eval_runtime": 0.8145, "eval_samples_per_second": 310.604, "eval_steps_per_second": 155.916, "step": 4 }, { "epoch": 0.03334722801167153, "grad_norm": 0.29895299673080444, "learning_rate": 5e-05, "loss": 6.9477, "step": 5 } ], "logging_steps": 1, "max_steps": 5, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 2, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 26366607360.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }