{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.03908692933083177, "eval_steps": 500, "global_step": 1000, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.003908692933083177, "grad_norm": 0.47716134786605835, "learning_rate": 4.98240400406663e-05, "loss": 1.3868, "step": 100 }, { "epoch": 0.007817385866166354, "grad_norm": 0.28900113701820374, "learning_rate": 4.9628528974739973e-05, "loss": 1.3348, "step": 200 }, { "epoch": 0.01172607879924953, "grad_norm": 0.37652796506881714, "learning_rate": 4.943301790881364e-05, "loss": 1.3298, "step": 300 }, { "epoch": 0.015634771732332707, "grad_norm": 0.24992702901363373, "learning_rate": 4.923750684288731e-05, "loss": 1.3309, "step": 400 }, { "epoch": 0.019543464665415886, "grad_norm": 0.3237004280090332, "learning_rate": 4.904199577696098e-05, "loss": 1.3228, "step": 500 }, { "epoch": 0.02345215759849906, "grad_norm": 0.259011447429657, "learning_rate": 4.884648471103465e-05, "loss": 1.3166, "step": 600 }, { "epoch": 0.02736085053158224, "grad_norm": 0.34121841192245483, "learning_rate": 4.8650973645108314e-05, "loss": 1.3145, "step": 700 }, { "epoch": 0.031269543464665414, "grad_norm": 0.41398781538009644, "learning_rate": 4.845546257918198e-05, "loss": 1.3081, "step": 800 }, { "epoch": 0.03517823639774859, "grad_norm": 0.4289904832839966, "learning_rate": 4.825995151325565e-05, "loss": 1.3073, "step": 900 }, { "epoch": 0.03908692933083177, "grad_norm": 0.21226634085178375, "learning_rate": 4.8064440447329324e-05, "loss": 1.3057, "step": 1000 } ], "logging_steps": 100, "max_steps": 25584, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 500, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 2796426362880000.0, "train_batch_size": 48, "trial_name": null, "trial_params": null }