{ "best_metric": null, "best_model_checkpoint": null, "epoch": 1.993142857142857, "eval_steps": 500, "global_step": 218, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.22857142857142856, "grad_norm": 7.164783477783203, "learning_rate": 5e-05, "loss": 6.0925, "step": 25 }, { "epoch": 0.45714285714285713, "grad_norm": 0.9276559352874756, "learning_rate": 0.0001, "loss": 0.03, "step": 50 }, { "epoch": 0.6857142857142857, "grad_norm": 2.69968581199646, "learning_rate": 8.511904761904762e-05, "loss": 0.0149, "step": 75 }, { "epoch": 0.9142857142857143, "grad_norm": 0.35357868671417236, "learning_rate": 7.023809523809524e-05, "loss": 0.0108, "step": 100 }, { "epoch": 1.1428571428571428, "grad_norm": 0.19637013971805573, "learning_rate": 5.535714285714286e-05, "loss": 0.0073, "step": 125 }, { "epoch": 1.3714285714285714, "grad_norm": 0.08578420430421829, "learning_rate": 4.047619047619048e-05, "loss": 0.0052, "step": 150 }, { "epoch": 1.6, "grad_norm": 0.17291192710399628, "learning_rate": 2.5595238095238093e-05, "loss": 0.0064, "step": 175 }, { "epoch": 1.8285714285714287, "grad_norm": 0.08965189754962921, "learning_rate": 1.0714285714285714e-05, "loss": 0.0049, "step": 200 } ], "logging_steps": 25, "max_steps": 218, "num_input_tokens_seen": 0, "num_train_epochs": 2, "save_steps": 25, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 1.5553403260393152e+16, "train_batch_size": 2, "trial_name": null, "trial_params": null }