{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 2.0, "eval_steps": 500, "global_step": 46, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.2222222222222222, "grad_norm": 1.7720335721969604, "learning_rate": 4e-05, "loss": 1.8513454437255858, "step": 5 }, { "epoch": 0.4444444444444444, "grad_norm": 0.8282597064971924, "learning_rate": 9e-05, "loss": 1.5823555946350099, "step": 10 }, { "epoch": 0.6666666666666666, "grad_norm": 0.36486729979515076, "learning_rate": 8.888888888888889e-05, "loss": 1.2854082107543945, "step": 15 }, { "epoch": 0.8888888888888888, "grad_norm": 0.24048180878162384, "learning_rate": 7.500000000000001e-05, "loss": 1.1841246604919433, "step": 20 }, { "epoch": 1.0888888888888888, "grad_norm": 0.21784241497516632, "learning_rate": 6.111111111111112e-05, "loss": 1.1314145088195802, "step": 25 }, { "epoch": 1.3111111111111111, "grad_norm": 0.19807986915111542, "learning_rate": 4.722222222222222e-05, "loss": 1.0636117935180665, "step": 30 }, { "epoch": 1.5333333333333332, "grad_norm": 0.18359264731407166, "learning_rate": 3.3333333333333335e-05, "loss": 1.0325389862060548, "step": 35 }, { "epoch": 1.7555555555555555, "grad_norm": 0.21023069322109222, "learning_rate": 1.9444444444444445e-05, "loss": 1.0241660118103026, "step": 40 }, { "epoch": 1.9777777777777779, "grad_norm": 0.1694304645061493, "learning_rate": 5.555555555555556e-06, "loss": 0.9998549461364746, "step": 45 } ], "logging_steps": 5, "max_steps": 46, "num_input_tokens_seen": 0, "num_train_epochs": 2, "save_steps": 50, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 7184027049689088.0, "train_batch_size": 1, "trial_name": null, "trial_params": null }