| { | |
| "_name_or_path": "/n/fs/nlp-mengzhou/space2/out/MRPC/CoFi-test-v3/MRPC_sparsity0.6_reglr0.01_ce0.1_layerdistillv4/best", | |
| "architectures": [ | |
| "CoFiBertForSequenceClassification" | |
| ], | |
| "attention_probs_dropout_prob": 0.1, | |
| "classifier_dropout": null, | |
| "do_layer_distill": true, | |
| "finetuning_task": "mrpc", | |
| "gradient_checkpointing": false, | |
| "hidden_act": "gelu", | |
| "hidden_dropout_prob": 0.1, | |
| "hidden_size": 768, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 3072, | |
| "label2id": { | |
| "0": 0, | |
| "1": 1 | |
| }, | |
| "layer_norm_eps": 1e-12, | |
| "max_position_embeddings": 512, | |
| "model_type": "bert", | |
| "num_attention_heads": 12, | |
| "num_hidden_layers": 12, | |
| "output_attentions": true, | |
| "output_hidden_states": true, | |
| "pad_token_id": 0, | |
| "position_embedding_type": "absolute", | |
| "pruned_heads": { | |
| "0": [], | |
| "1": [ | |
| 3, | |
| 5, | |
| 6 | |
| ], | |
| "2": [ | |
| 3 | |
| ], | |
| "3": [ | |
| 4 | |
| ], | |
| "4": [], | |
| "5": [], | |
| "6": [ | |
| 10, | |
| 2, | |
| 3, | |
| 5 | |
| ], | |
| "7": [ | |
| 3, | |
| 7 | |
| ], | |
| "8": [], | |
| "9": [ | |
| 1, | |
| 2, | |
| 3, | |
| 4, | |
| 7, | |
| 8, | |
| 9, | |
| 10, | |
| 11 | |
| ], | |
| "10": [ | |
| 2, | |
| 3, | |
| 4, | |
| 6, | |
| 7, | |
| 8, | |
| 11 | |
| ], | |
| "11": [ | |
| 0, | |
| 1, | |
| 2, | |
| 3, | |
| 4, | |
| 5, | |
| 6, | |
| 7, | |
| 8, | |
| 9, | |
| 10, | |
| 11 | |
| ] | |
| }, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.17.0.dev0", | |
| "type_vocab_size": 2, | |
| "use_cache": true, | |
| "vocab_size": 30522 | |
| } | |