{ "base_model_name": "TheBloke_rocket-3B-GPTQ", "base_model_class": "StableLMEpochForCausalLM", "base_loaded_in_4bit": false, "base_loaded_in_8bit": false, "projections": "q, v", "train_runtime": 16258.3042, "train_samples_per_second": 9.551, "train_steps_per_second": 0.009, "total_flos": 4.03146824220672e+16, "train_loss": 1.0195273685455322, "epoch": 2.96, "current_steps": 1197, "loss": 0.9271, "learning_rate": 0.0 }