Training in progress, epoch 0

config.json

@@ -1,10 +1,27 @@
 {
-  "_name_or_path": "bert-base-cased",
+  "_name_or_path": "allenai/longformer-base-4096",
   "architectures": [
-    "BertForTokenClassification"
+    "LongformerForTokenClassification"
   ],
+  "attention_mode": "longformer",
   "attention_probs_dropout_prob": 0.1,
+  "attention_window": [
+    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,
@@ -18,6 +35,7 @@
     "5": "Counterclaim",
     "6": "Rebuttal"
   },
+  "ignore_attention_mask": false,
   "initializer_range": 0.02,
   "intermediate_size": 3072,
   "label2id": {
@@ -29,16 +47,17 @@
     "Position": "1",
     "Rebuttal": "6"
   },
-  "layer_norm_eps": 1e-12,
-  "max_position_embeddings": 512,
-  "model_type": "bert",
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 4098,
+  "model_type": "longformer",
   "num_attention_heads": 12,
   "num_hidden_layers": 12,
-  "pad_token_id": 0,
+  "pad_token_id": 1,
   "position_embedding_type": "absolute",
+  "sep_token_id": 2,
   "torch_dtype": "float32",
-  "transformers_version": "4.16.1",
-  "type_vocab_size": 2,
+  "transformers_version": "4.17.0",
+  "type_vocab_size": 1,
   "use_cache": true,
-  "vocab_size": 28996
+  "vocab_size": 50265
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bdd4299b9009ba132a59bf93d87eed978a6d49006bac51c347fa14977fe833cd
-size 430983665
+oid sha256:222e7a9ae3b73889cd33adac6da3bf8d6d5b6a1aed755e126fe00816255b8c00
+size 592439777

runs/Mar08_05-09-00_8cee193dd1b4/1646716335.400526/events.out.tfevents.1646716335.8cee193dd1b4.87.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bbd0552c2bbce2bb09909b23f2ceefef44bee1d575142b74c90e77d93622921f
+size 4763

runs/Mar08_05-09-00_8cee193dd1b4/events.out.tfevents.1646716335.8cee193dd1b4.87.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9bc8e68e2305997f0409d252a28d795b7fc51971100808912b11cae07625bc51
+size 4513

special_tokens_map.json

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

tokenizer_config.json

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

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b0b77d2466f2479f6517da191f4367ab2b9eff28191715f4ac0208d955f27140
+oid sha256:4f1b09a018264279c19a519e4bfd4c69c01a9a746467e4fa0b6ec62ecc3bb96c
 size 2991