{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 2.96, "eval_steps": 500, "global_step": 1000, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.2962962962962963, "grad_norm": 3.8120243549346924, "learning_rate": 9.938823863528065e-06, "loss": 0.0004, "step": 100 }, { "epoch": 0.5925925925925926, "grad_norm": 0.0018049710197374225, "learning_rate": 9.428445774703444e-06, "loss": 0.0004, "step": 200 }, { "epoch": 0.8888888888888888, "grad_norm": 0.001558819436468184, "learning_rate": 8.450931618533601e-06, "loss": 0.0, "step": 300 }, { "epoch": 1.1837037037037037, "grad_norm": 0.0011788058327510953, "learning_rate": 7.109394799115268e-06, "loss": 0.0, "step": 400 }, { "epoch": 1.48, "grad_norm": 0.0010272902436554432, "learning_rate": 5.545347771586018e-06, "loss": 0.004, "step": 500 }, { "epoch": 1.7762962962962963, "grad_norm": 0.0011670357780531049, "learning_rate": 3.92377455398589e-06, "loss": 0.0001, "step": 600 }, { "epoch": 2.071111111111111, "grad_norm": 0.0010163792176172137, "learning_rate": 2.4157273335425296e-06, "loss": 0.0, "step": 700 }, { "epoch": 2.3674074074074074, "grad_norm": 0.0008961952407844365, "learning_rate": 1.1802829701224183e-06, "loss": 0.0, "step": 800 }, { "epoch": 2.6637037037037037, "grad_norm": 0.0008640048909001052, "learning_rate": 3.4776272104986966e-07, "loss": 0.0, "step": 900 }, { "epoch": 2.96, "grad_norm": 0.0008631945238448679, "learning_rate": 5.985260171704199e-09, "loss": 0.0, "step": 1000 } ], "logging_steps": 100, "max_steps": 1014, "num_input_tokens_seen": 0, "num_train_epochs": 3, "save_steps": 1000, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 102343869414864.0, "train_batch_size": 4, "trial_name": null, "trial_params": null }