| { | |
| "architectures": [ | |
| "GPT2LMHeadModel" | |
| ], | |
| "model_type": "gpt2", | |
| "vocab_size": 50257, | |
| "n_positions": 1024, | |
| "n_embd": 1024, | |
| "n_layer": 16, | |
| "n_head": 16, | |
| "n_inner": 4096, | |
| "activation_function": "gelu_new", | |
| "resid_pdrop": 0.1, | |
| "embd_pdrop": 0.1, | |
| "attn_pdrop": 0.1, | |
| "layer_norm_epsilon": 1e-05, | |
| "initializer_range": 0.02, | |
| "use_cache": true, | |
| "bos_token_id": 50256, | |
| "eos_token_id": 50256, | |
| "torch_dtype": "float32", | |
| "_art_checkpoint_iter": 100000, | |
| "_art_best_val_loss": 2.970595359802246, | |
| "_art_total_params": 305335296 | |
| } |