| { | |
| "model_args": { | |
| "n_layer": 4, | |
| "n_head": 4, | |
| "n_embd": 256, | |
| "block_size": 256, | |
| "bias": false, | |
| "vocab_size": 50257, | |
| "dropout": 0.1 | |
| }, | |
| "val_loss": 1.7955214977264404, | |
| "iter_num": 10000, | |
| "task": "grammar correction + essay generation", | |
| "base_model": "Syndra", | |
| "architecture": "GPT / transformer decoder", | |
| "tokenizer": "gpt2 (tiktoken, vocab 50257)" | |
| } |