{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.030636785588456058, "eval_steps": 500, "global_step": 1000, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.003063678558845606, "grad_norm": 3.035543918609619, "learning_rate": 4.000000000000001e-06, "loss": 3.0534, "step": 100 }, { "epoch": 0.006127357117691212, "grad_norm": 2.96189546585083, "learning_rate": 8.000000000000001e-06, "loss": 2.9361, "step": 200 }, { "epoch": 0.009191035676536818, "grad_norm": 2.852346420288086, "learning_rate": 9.987820251299121e-06, "loss": 2.9092, "step": 300 }, { "epoch": 0.012254714235382424, "grad_norm": 2.963131904602051, "learning_rate": 9.890738003669029e-06, "loss": 2.8945, "step": 400 }, { "epoch": 0.015318392794228029, "grad_norm": 2.8017725944519043, "learning_rate": 9.698463103929542e-06, "loss": 2.8791, "step": 500 }, { "epoch": 0.018382071353073636, "grad_norm": 2.877586841583252, "learning_rate": 9.414737964294636e-06, "loss": 2.8601, "step": 600 }, { "epoch": 0.02144574991191924, "grad_norm": 2.7040741443634033, "learning_rate": 9.045084971874738e-06, "loss": 2.8706, "step": 700 }, { "epoch": 0.024509428470764847, "grad_norm": 2.8546905517578125, "learning_rate": 8.596699001693257e-06, "loss": 2.8554, "step": 800 }, { "epoch": 0.027573107029610452, "grad_norm": 2.643134355545044, "learning_rate": 8.078307376628292e-06, "loss": 2.8639, "step": 900 }, { "epoch": 0.030636785588456058, "grad_norm": 2.577639579772949, "learning_rate": 7.500000000000001e-06, "loss": 2.8588, "step": 1000 } ], "logging_steps": 100, "max_steps": 2500, "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": 9.5664155394048e+16, "train_batch_size": 4, "trial_name": null, "trial_params": null }