{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.37593984962406013, "eval_steps": 500, "global_step": 100, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.03759398496240601, "grad_norm": 3.564216136932373, "learning_rate": 9.931806517013612e-05, "loss": 0.8386, "step": 10 }, { "epoch": 0.07518796992481203, "grad_norm": 0.8364839553833008, "learning_rate": 9.397368756032445e-05, "loss": 0.2794, "step": 20 }, { "epoch": 0.11278195488721804, "grad_norm": 0.7329896092414856, "learning_rate": 8.386407858128706e-05, "loss": 0.2106, "step": 30 }, { "epoch": 0.15037593984962405, "grad_norm": 0.7734127044677734, "learning_rate": 7.008477123264848e-05, "loss": 0.1644, "step": 40 }, { "epoch": 0.18796992481203006, "grad_norm": 0.5344420075416565, "learning_rate": 5.4128967273616625e-05, "loss": 0.1513, "step": 50 }, { "epoch": 0.22556390977443608, "grad_norm": 0.6934475302696228, "learning_rate": 3.772572564296005e-05, "loss": 0.1457, "step": 60 }, { "epoch": 0.2631578947368421, "grad_norm": 0.6167137026786804, "learning_rate": 2.2652592093878666e-05, "loss": 0.1204, "step": 70 }, { "epoch": 0.3007518796992481, "grad_norm": 0.44789060950279236, "learning_rate": 1.0542974530180327e-05, "loss": 0.1277, "step": 80 }, { "epoch": 0.3383458646616541, "grad_norm": 0.4527667760848999, "learning_rate": 2.7091379149682685e-06, "loss": 0.1181, "step": 90 }, { "epoch": 0.37593984962406013, "grad_norm": 0.42180800437927246, "learning_rate": 0.0, "loss": 0.1179, "step": 100 } ], "logging_steps": 10, "max_steps": 100, "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": 9899575539609600.0, "train_batch_size": 32, "trial_name": null, "trial_params": null }