{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 0.9980806142034548, "eval_steps": 1000, "global_step": 65, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.15355086372360843, "grad_norm": 1.4006431754631588, "learning_rate": 9.835138623956603e-06, "loss": 1.4169, "step": 10 }, { "epoch": 0.30710172744721687, "grad_norm": 0.7865151207585618, "learning_rate": 8.580760941571968e-06, "loss": 0.9093, "step": 20 }, { "epoch": 0.46065259117082535, "grad_norm": 0.6596663676849375, "learning_rate": 6.397428174258048e-06, "loss": 0.8678, "step": 30 }, { "epoch": 0.6142034548944337, "grad_norm": 0.6327966112391097, "learning_rate": 3.851561289341023e-06, "loss": 0.8513, "step": 40 }, { "epoch": 0.7677543186180422, "grad_norm": 0.584384805845296, "learning_rate": 1.6036333055135345e-06, "loss": 0.8226, "step": 50 }, { "epoch": 0.9213051823416507, "grad_norm": 0.6131092052449295, "learning_rate": 2.368230959830875e-07, "loss": 0.8493, "step": 60 }, { "epoch": 0.9980806142034548, "step": 65, "total_flos": 241189655674880.0, "train_loss": 0.9516184660104605, "train_runtime": 3860.317, "train_samples_per_second": 2.158, "train_steps_per_second": 0.017 } ], "logging_steps": 10, "max_steps": 65, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 1000, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 241189655674880.0, "train_batch_size": 1, "trial_name": null, "trial_params": null }