{ "base_model_name": "TheBloke_rocket-3B-GPTQ", "base_model_class": "StableLMEpochForCausalLM", "base_loaded_in_4bit": false, "base_loaded_in_8bit": false, "projections": "q, v", "loss": 0.8275, "learning_rate": 0.0, "epoch": 8.42, "current_steps": 607, "train_runtime": 397.4378, "train_samples_per_second": 7.599, "train_steps_per_second": 0.025, "total_flos": 668408186142720.0, "train_loss": 1.0486467838287354 }