| { | |
| "model_config": { | |
| "n_layer": 12, | |
| "n_head": 12, | |
| "n_embd": 768, | |
| "block_size": 1024, | |
| "bias": false, | |
| "dropout": 0.0, | |
| "n_codes_total": 8, | |
| "n_codes_given": 1, | |
| "input_vocab_size": 1056, | |
| "output_vocab_size": 1056 | |
| }, | |
| "model_type": "fine", | |
| "parameter_count": 97924608, | |
| "needs_tokenizer": true, | |
| "best_val_loss": 2.5150986952781675, | |
| "torch_dtype": "bfloat16" | |
| } | |