| { | |
| "base_model_name": "Llama-2-13b-hf", | |
| "base_model_class": "LlamaForCausalLM", | |
| "base_loaded_in_4bit": true, | |
| "base_loaded_in_8bit": false, | |
| "projections": "q, v", | |
| "loss": 1.0499, | |
| "grad_norm": 5.645450592041016, | |
| "learning_rate": 1.3043478260869564e-08, | |
| "epoch": 5.0, | |
| "current_steps": 559, | |
| "current_steps_adjusted": 559, | |
| "epoch_adjusted": 5.0, | |
| "train_runtime": 1468.5439, | |
| "train_samples_per_second": 1.515, | |
| "train_steps_per_second": 0.381, | |
| "total_flos": 4.4012668649472e+16, | |
| "train_loss": 0.7355319578732763 | |
| } |