Training in progress, epoch 1

config.json

@@ -1,67 +1,34 @@
 {
-  "_name_or_path": "C:\\Research\\haas-mfe-g28-cg\\model\\patentClassfication2\\",
+  "_name_or_path": "allenai/scibert_scivocab_uncased",
   "architectures": [
     "BertForSequenceClassification"
   ],
-  "attention_mode": "longformer",
   "attention_probs_dropout_prob": 0.1,
-  "attention_window": [
-    512,
-    512,
-    512,
-    512,
-    512,
-    512,
-    512,
-    512,
-    512,
-    512,
-    512,
-    512,
-    512,
-    512,
-    512,
-    512,
-    512,
-    512,
-    512,
-    512,
-    512,
-    512,
-    512,
-    512
-  ],
-  "bos_token_id": 0,
   "classifier_dropout": null,
-  "eos_token_id": 2,
-  "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
-  "hidden_size": 1024,
+  "hidden_size": 768,
   "id2label": {
     "0": "NOT_REJECTED",
     "1": "REJECTED"
   },
-  "ignore_attention_mask": false,
   "initializer_range": 0.02,
-  "intermediate_size": 4096,
+  "intermediate_size": 3072,
   "label2id": {
     "NOT_REJECTED": 0,
     "REJECTED": 1
   },
-  "layer_norm_eps": 1e-05,
-  "max_position_embeddings": 4098,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
   "model_type": "bert",
-  "num_attention_heads": 16,
-  "num_hidden_layers": 24,
-  "onnx_export": false,
-  "pad_token_id": 1,
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
   "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",
-  "sep_token_id": 2,
   "torch_dtype": "float32",
   "transformers_version": "4.31.0",
-  "type_vocab_size": 1,
+  "type_vocab_size": 2,
   "use_cache": true,
-  "vocab_size": 50265
+  "vocab_size": 31090
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4e5619f912c51d6e78b8546db09f5d91c81068978d9b751f18a0cc354d6fb2b
-size 1436261681
+oid sha256:6f2fee94789e720d48dfe18ca40284a4264780e2f0c70de853edcd1940a13bea
+size 439748401

special_tokens_map.json

@@ -1,15 +1,7 @@
 {
-  "bos_token": "<s>",
-  "cls_token": "<s>",
-  "eos_token": "</s>",
-  "mask_token": {
-    "content": "<mask>",
-    "lstrip": true,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": "<pad>",
-  "sep_token": "</s>",
-  "unk_token": "<unk>"
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
 }

tokenizer_config.json

@@ -1,15 +1,15 @@
 {
-  "add_prefix_space": false,
-  "bos_token": "<s>",
   "clean_up_tokenization_spaces": true,
-  "cls_token": "<s>",
-  "eos_token": "</s>",
-  "errors": "replace",
-  "mask_token": "<mask>",
-  "model_max_length": 4096,
-  "pad_token": "<pad>",
-  "sep_token": "</s>",
-  "tokenizer_class": "LongformerTokenizer",
-  "trim_offsets": true,
-  "unk_token": "<unk>"
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cdab9ac8f8024ad006c6764549fd220ce2f6fdb654551c8bf0004e269af0088a
+oid sha256:a80012863f2942aca51e0049c0dd5c36bfc5d5591a468a3fef6847758b3fbece
 size 3963