{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.990578734858681, "eval_steps": 500, "global_step": 92, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.010767160161507403, "grad_norm": 0.006398230325430632, "learning_rate": 2e-05, "loss": 0.8417, "step": 1 }, { "epoch": 0.10767160161507403, "grad_norm": 0.03447544574737549, "learning_rate": 0.0002, "loss": 1.5005, "step": 10 }, { "epoch": 0.21534320323014805, "grad_norm": 0.020084939897060394, "learning_rate": 0.000175609756097561, "loss": 1.4079, "step": 20 }, { "epoch": 0.32301480484522205, "grad_norm": 0.01294423546642065, "learning_rate": 0.00015121951219512197, "loss": 1.4586, "step": 30 }, { "epoch": 0.4306864064602961, "grad_norm": 0.007237937767058611, "learning_rate": 0.00012682926829268293, "loss": 1.3782, "step": 40 }, { "epoch": 0.5383580080753702, "grad_norm": 0.022302279248833656, "learning_rate": 0.0001024390243902439, "loss": 1.4701, "step": 50 }, { "epoch": 0.6460296096904441, "grad_norm": 0.01918647438287735, "learning_rate": 7.804878048780489e-05, "loss": 1.268, "step": 60 }, { "epoch": 0.7537012113055181, "grad_norm": 0.017452461645007133, "learning_rate": 5.365853658536586e-05, "loss": 1.2663, "step": 70 }, { "epoch": 0.8613728129205922, "grad_norm": 0.012683959677815437, "learning_rate": 2.926829268292683e-05, "loss": 1.3445, "step": 80 }, { "epoch": 0.9690444145356663, "grad_norm": 0.012110305018723011, "learning_rate": 4.8780487804878055e-06, "loss": 1.3767, "step": 90 } ], "logging_steps": 10, "max_steps": 92, "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": true }, "attributes": {} } }, "total_flos": 2.325540472262492e+18, "train_batch_size": 64, "trial_name": null, "trial_params": null }