henryscheible/eval_v3_stsb
09
1{2 "_name_or_path": "bert-base-uncased",3 "architectures": [4 "BertForSequenceClassification"5 ],6 "attention_probs_dropout_prob": 0.1,7 "classifier_dropout": null,8 "finetuning_task": "stsb",9 "gradient_checkpointing": false,10 "hidden_act": "gelu",11 "hidden_dropout_prob": 0.1,12 "hidden_size": 768,13 "id2label": {14 "0": "LABEL_0"15 },16 "initializer_range": 0.02,17 "intermediate_size": 3072,18 "label2id": {19 "LABEL_0": 020 },21 "layer_norm_eps": 1e-12,22 "max_position_embeddings": 512,23 "model_type": "bert",24 "num_attention_heads": 12,25 "num_hidden_layers": 12,26 "pad_token_id": 0,27 "position_embedding_type": "absolute",28 "problem_type": "regression",29 "torch_dtype": "float32",30 "transformers_version": "4.23.1",31 "type_vocab_size": 2,32 "use_cache": true,33 "vocab_size": 3052234}35 