{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 0.1, "eval_steps": 500, "global_step": 100, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.01, "grad_norm": 4.967028743863011e-08, "learning_rate": 0.000192, "loss": 2.1803, "step": 10 }, { "epoch": 0.02, "grad_norm": 163.9561767578125, "learning_rate": 0.000174, "loss": 5.3708, "step": 20 }, { "epoch": 0.03, "grad_norm": 10.285516738891602, "learning_rate": 0.00015800000000000002, "loss": 1.9787, "step": 30 }, { "epoch": 0.04, "grad_norm": 0.2226715236902237, "learning_rate": 0.000138, "loss": 2.7079, "step": 40 }, { "epoch": 0.05, "grad_norm": 364.0879211425781, "learning_rate": 0.000118, "loss": 3.3824, "step": 50 }, { "epoch": 0.06, "grad_norm": 5.139416694641113, "learning_rate": 9.8e-05, "loss": 2.3572, "step": 60 }, { "epoch": 0.07, "grad_norm": 419.88128662109375, "learning_rate": 7.800000000000001e-05, "loss": 4.058, "step": 70 }, { "epoch": 0.08, "grad_norm": 192.04869079589844, "learning_rate": 5.8e-05, "loss": 2.2558, "step": 80 }, { "epoch": 0.09, "grad_norm": 168.4913787841797, "learning_rate": 3.8e-05, "loss": 1.9433, "step": 90 }, { "epoch": 0.1, "grad_norm": 0.12165103852748871, "learning_rate": 1.8e-05, "loss": 1.3696, "step": 100 } ], "logging_steps": 10, "max_steps": 100, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 100, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 9598821885542400.0, "train_batch_size": 1, "trial_name": null, "trial_params": null }