Training in progress, epoch 1

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "vinai/bertweet-base",
+  "_name_or_path": "cardiffnlp/twitter-roberta-base-sentiment",
   "architectures": [
     "RobertaForSequenceClassification"
   ],
@@ -24,17 +24,16 @@
     "LABEL_2": 2
   },
   "layer_norm_eps": 1e-05,
-  "max_position_embeddings": 130,
+  "max_position_embeddings": 514,
   "model_type": "roberta",
   "num_attention_heads": 12,
   "num_hidden_layers": 12,
   "pad_token_id": 1,
   "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",
-  "tokenizer_class": "BertweetTokenizer",
   "torch_dtype": "float32",
   "transformers_version": "4.28.0",
   "type_vocab_size": 1,
   "use_cache": true,
-  "vocab_size": 64001
+  "vocab_size": 50265
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74d58da11f28093eb6b446fe4141304b1d8b78d63a7602d21d52920bce2852a3
-size 539676597
+oid sha256:f9bdc3b1ed38f7815103782411956136f30978a17793ec5e040b32da1ac176cd
+size 498662325

special_tokens_map.json

@@ -2,7 +2,13 @@
   "bos_token": "<s>",
   "cls_token": "<s>",
   "eos_token": "</s>",
-  "mask_token": "<mask>",
+  "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

@@ -1,13 +1,64 @@
 {
-  "bos_token": "<s>",
+  "add_prefix_space": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
   "clean_up_tokenization_spaces": true,
-  "cls_token": "<s>",
-  "eos_token": "</s>",
-  "mask_token": "<mask>",
-  "model_max_length": 128,
-  "normalization": false,
-  "pad_token": "<pad>",
-  "sep_token": "</s>",
-  "tokenizer_class": "BertweetTokenizer",
-  "unk_token": "<unk>"
+  "cls_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "errors": "replace",
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": {
+    "__type": "AddedToken",
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:435edb4176e789af0389cbc4004ac393cd6954924176038b048a99635c801ce4
+oid sha256:d97b50ff5b3e0acc1eb8c9c50d601c006a7562c49096ee299cbb72a46d6a9011
 size 3643