{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 2.977777777777778, "eval_steps": 500, "global_step": 66, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.4444444444444444, "grad_norm": 2.359058141708374, "learning_rate": 4.985837000525343e-05, "loss": 1.4524, "step": 10 }, { "epoch": 0.8888888888888888, "grad_norm": 0.3728153705596924, "learning_rate": 4.5067790948274094e-05, "loss": 0.6241, "step": 20 }, { "epoch": 1.3555555555555556, "grad_norm": 0.23920179903507233, "learning_rate": 3.472060438683302e-05, "loss": 0.6292, "step": 30 }, { "epoch": 1.8, "grad_norm": 0.23902089893817902, "learning_rate": 2.1681861817906954e-05, "loss": 0.5744, "step": 40 }, { "epoch": 2.2666666666666666, "grad_norm": 0.24401122331619263, "learning_rate": 9.561884626345205e-06, "loss": 0.6269, "step": 50 }, { "epoch": 2.7111111111111112, "grad_norm": 0.3997255563735962, "learning_rate": 1.7165955636915392e-06, "loss": 0.5659, "step": 60 }, { "epoch": 2.977777777777778, "step": 66, "total_flos": 2.191733634052915e+16, "train_loss": 0.7293135975346421, "train_runtime": 410.9066, "train_samples_per_second": 2.606, "train_steps_per_second": 0.161 } ], "logging_steps": 10, "max_steps": 66, "num_input_tokens_seen": 0, "num_train_epochs": 3, "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": 2.191733634052915e+16, "train_batch_size": 4, "trial_name": null, "trial_params": null }