v1.0.3 best_threshold: 0.691

config.json

@@ -3,12 +3,13 @@
   "architectures": [
     "BertForSequenceClassification"
   ],
-  "attention_probs_dropout_prob": 0.1,
+  "attention_probs_dropout_prob": 0.05,
+  "bos_token_id": 0,
   "classifier_dropout": null,
   "directionality": "bidi",
-  "gradient_checkpointing": false,
+  "eos_token_id": 2,
   "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.1,
+  "hidden_dropout_prob": 0.3,
   "hidden_size": 768,
   "id2label": {
     "0": "E/I",
@@ -29,6 +30,7 @@
   "model_type": "bert",
   "num_attention_heads": 12,
   "num_hidden_layers": 12,
+  "output_past": true,
   "pad_token_id": 0,
   "pooler_fc_size": 768,
   "pooler_num_attention_heads": 12,
@@ -37,7 +39,6 @@
   "pooler_type": "first_token_transform",
   "position_embedding_type": "absolute",
   "problem_type": "multi_label_classification",
-  "tokenizer_class": "BertTokenizerFast",
   "torch_dtype": "float32",
   "transformers_version": "4.24.0",
   "type_vocab_size": 2,

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c325747b60905bf66d646f56e71b4f1663ea92156f9420d29d04940f219c8d9
+oid sha256:9f45aeda1539940c82e7aa0363b63de62c4058c4d2d451833bed0cfebc24c8cf
 size 409153901

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00c880023710e61ba41447e9f89d3fc3f103122206b351561c7f0770dc03888f
+oid sha256:d8b845ae9cc05e221d5ee24412b2fb954c013ccd12e50fbd752770faf3b23068
 size 3375