{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.19598236158745713, "eval_steps": 500, "global_step": 100, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.019598236158745713, "grad_norm": 0.2793342191899106, "learning_rate": 9.901960784313727e-05, "loss": 1.0852, "step": 10 }, { "epoch": 0.039196472317491425, "grad_norm": 0.20185545177118225, "learning_rate": 9.80392156862745e-05, "loss": 0.6248, "step": 20 }, { "epoch": 0.05879470847623714, "grad_norm": 0.060826473159884153, "learning_rate": 9.705882352941177e-05, "loss": 0.5504, "step": 30 }, { "epoch": 0.07839294463498285, "grad_norm": 0.03512127282064425, "learning_rate": 9.607843137254903e-05, "loss": 0.5362, "step": 40 }, { "epoch": 0.09799118079372857, "grad_norm": 0.03284847311332698, "learning_rate": 9.509803921568627e-05, "loss": 0.5119, "step": 50 }, { "epoch": 0.11758941695247428, "grad_norm": 0.031703289623195, "learning_rate": 9.411764705882353e-05, "loss": 0.5181, "step": 60 }, { "epoch": 0.13718765311122, "grad_norm": 0.043354619631025194, "learning_rate": 9.313725490196079e-05, "loss": 0.518, "step": 70 }, { "epoch": 0.1567858892699657, "grad_norm": 0.05831134411316817, "learning_rate": 9.215686274509804e-05, "loss": 0.5112, "step": 80 }, { "epoch": 0.1763841254287114, "grad_norm": 0.042535052090752985, "learning_rate": 9.11764705882353e-05, "loss": 0.5088, "step": 90 }, { "epoch": 0.19598236158745713, "grad_norm": 0.03440989557319712, "learning_rate": 9.019607843137255e-05, "loss": 0.5005, "step": 100 } ], "logging_steps": 10, "max_steps": 1020, "num_input_tokens_seen": 0, "num_train_epochs": 2, "save_steps": 100, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 15669531770880.0, "train_batch_size": 8, "trial_name": null, "trial_params": null }