Training in progress, epoch 1

config.json

@@ -1,34 +1,64 @@
 {
-  "_name_or_path": "allenai/scibert_scivocab_uncased",
+  "_name_or_path": "allenai/longformer-large-4096",
   "architectures": [
-    "BertForSequenceClassification"
+    "LongformerForSequenceClassification"
   ],
+  "attention_mode": "longformer",
   "attention_probs_dropout_prob": 0.1,
-  "classifier_dropout": null,
+  "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,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
+  "hidden_size": 1024,
   "id2label": {
     "0": "NOT_REJECTED",
     "1": "REJECTED"
   },
+  "ignore_attention_mask": false,
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
+  "intermediate_size": 4096,
   "label2id": {
     "NOT_REJECTED": 0,
     "REJECTED": 1
   },
-  "layer_norm_eps": 1e-12,
-  "max_position_embeddings": 512,
-  "model_type": "bert",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
-  "pad_token_id": 0,
-  "position_embedding_type": "absolute",
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 4098,
+  "model_type": "longformer",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "onnx_export": false,
+  "pad_token_id": 1,
   "problem_type": "single_label_classification",
+  "sep_token_id": 2,
   "torch_dtype": "float32",
   "transformers_version": "4.31.0",
-  "type_vocab_size": 2,
-  "use_cache": true,
-  "vocab_size": 31090
+  "type_vocab_size": 1,
+  "vocab_size": 50265
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8521849c8e693f132523549c6a062b456f8f8db79ce7e04651ab2ee5f3cab8df
-size 439748401
+oid sha256:311de5f66a12b554ab435e9d794330d2b7a3b541a33561051d9461ae5ae326f9
+size 1738600369

special_tokens_map.json

@@ -1,7 +1,15 @@
 {
-  "cls_token": "[CLS]",
-  "mask_token": "[MASK]",
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
-  "unk_token": "[UNK]"
+  "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>"
 }

tokenizer_config.json

@@ -1,15 +1,15 @@
 {
+  "add_prefix_space": false,
+  "bos_token": "<s>",
   "clean_up_tokenization_spaces": true,
-  "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]"
+  "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>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd9b2346427ad8479649f6e02a9f1857bd2a1b1597d675c825856fbe600cd3df
+oid sha256:92618aa86596d829134c574e0109d26bab9dc979adc0c7c61ddfc56add6fc92c
 size 3963