Training in progress, epoch 1

config.json

@@ -1,40 +1,37 @@
 {
-  "_name_or_path": "finiteautomata/bertweet-base-sentiment-analysis",
+  "_name_or_path": "bert-base-uncased",
   "architectures": [
-    "RobertaForSequenceClassification"
+    "BertForSequenceClassification"
   ],
   "attention_probs_dropout_prob": 0.1,
-  "bos_token_id": 0,
   "classifier_dropout": null,
-  "eos_token_id": 2,
   "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
   "hidden_size": 768,
   "id2label": {
-    "0": "NEG",
-    "1": "NEU",
-    "2": "POS"
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
   },
   "initializer_range": 0.02,
   "intermediate_size": 3072,
   "label2id": {
-    "NEG": 0,
-    "NEU": 1,
-    "POS": 2
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
   },
-  "layer_norm_eps": 1e-05,
-  "max_position_embeddings": 130,
-  "model_type": "roberta",
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
   "num_attention_heads": 12,
   "num_hidden_layers": 12,
-  "pad_token_id": 1,
+  "pad_token_id": 0,
   "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",
-  "tokenizer_class": "BertweetTokenizer",
   "torch_dtype": "float32",
   "transformers_version": "4.33.1",
-  "type_vocab_size": 1,
+  "type_vocab_size": 2,
   "use_cache": true,
-  "vocab_size": 64001
+  "vocab_size": 30522
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a93236f7cd112a9fa12172faa429e0671ea9d55ca99957854fce50161f2e957b
-size 539678065
+oid sha256:3d5855d595ccd2627fa3bc744452928a73cd46ea6414a3a13c741a9efde03263
+size 438006577

special_tokens_map.json

@@ -1,9 +1,7 @@
 {
-  "bos_token": "<s>",
-  "cls_token": "<s>",
-  "eos_token": "</s>",
-  "mask_token": "<mask>",
-  "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

@@ -1,13 +1,13 @@
 {
-  "bos_token": "<s>",
   "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": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "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 sha256:437fc4ccffa619f509bd7c98f6b859575fdf486bd52cb9b3309a7128ae605657
+oid sha256:4f454a5fba37c516e412631913b453f9e75b84123140ac46562288fe850dc5b3
 size 4091