{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 0.006396929473852551, "eval_steps": 500, "global_step": 100, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0006396929473852551, "grad_norm": 0.8444250226020813, "learning_rate": 3.6e-05, "loss": 0.8966, "step": 10 }, { "epoch": 0.0012793858947705101, "grad_norm": 0.6855414509773254, "learning_rate": 7.6e-05, "loss": 0.7299, "step": 20 }, { "epoch": 0.0019190788421557653, "grad_norm": 0.7116178870201111, "learning_rate": 0.000116, "loss": 0.5625, "step": 30 }, { "epoch": 0.0025587717895410203, "grad_norm": 0.5287570953369141, "learning_rate": 0.00015600000000000002, "loss": 0.481, "step": 40 }, { "epoch": 0.0031984647369262755, "grad_norm": 0.4259079694747925, "learning_rate": 0.000196, "loss": 0.4765, "step": 50 }, { "epoch": 0.0038381576843115306, "grad_norm": 0.5958250761032104, "learning_rate": 0.000236, "loss": 0.44, "step": 60 }, { "epoch": 0.004477850631696785, "grad_norm": 0.4068315923213959, "learning_rate": 0.000276, "loss": 0.4348, "step": 70 }, { "epoch": 0.005117543579082041, "grad_norm": 0.6012944579124451, "learning_rate": 0.00031600000000000004, "loss": 0.4497, "step": 80 }, { "epoch": 0.005757236526467296, "grad_norm": 0.39029160141944885, "learning_rate": 0.00035600000000000003, "loss": 0.4214, "step": 90 }, { "epoch": 0.006396929473852551, "grad_norm": 0.3756840229034424, "learning_rate": 0.00039600000000000003, "loss": 0.4643, "step": 100 } ], "logging_steps": 10, "max_steps": 100, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 20, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 3.502292152831181e+16, "train_batch_size": 4, "trial_name": null, "trial_params": null }