| { | |
| "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": 2.813, | |
| "learning_rate": 6.464906595023967e-09, | |
| "epoch": 2.96, | |
| "current_steps": 959, | |
| "train_runtime": 13914.3966, | |
| "train_samples_per_second": 4.459, | |
| "train_steps_per_second": 0.009, | |
| "total_flos": 4.013119292571648e+16, | |
| "train_loss": 2.8925536632537843 | |
| } |