| { | |
| "model_type": "multiscale_transformer", | |
| "architectures": [ | |
| "MultiScaleForCausalLM" | |
| ], | |
| "vocab_size": 258, | |
| "d_model": 512, | |
| "n_heads": 4, | |
| "d_ff": 1376, | |
| "n_layers_per_scale": 5, | |
| "n_cross_attn_layers": 1, | |
| "max_seq_len": 512, | |
| "dropout": 0.0, | |
| "bias": false, | |
| "rope_theta": 10000.0, | |
| "downsample_factors": [ | |
| 1, | |
| 2, | |
| 4 | |
| ], | |
| "num_parameters": 66831872, | |
| "training_results": { | |
| "model": "AXL-Reasoning", | |
| "params": 70004224, | |
| "steps": 1478, | |
| "time": 3602.1849868297577, | |
| "final_loss": 0.6384159326553345, | |
| "perplexity": 1.93 | |
| } | |
| } |