Training in progress, epoch 1

added_tokens.json

@@ -1,3 +1,7 @@
 {
-  "<mask>": 64000
+  "</s>": 2,
+  "<mask>": 64000,
+  "<pad>": 1,
+  "<s>": 0,
+  "<unk>": 3
 }

config.json

@@ -1,33 +1,40 @@
 {
-  "_name_or_path": "distilbert-base-uncased",
-  "activation": "gelu",
+  "_name_or_path": "finiteautomata/bertweet-base-sentiment-analysis",
   "architectures": [
-    "DistilBertForSequenceClassification"
+    "RobertaForSequenceClassification"
   ],
-  "attention_dropout": 0.1,
-  "dim": 768,
-  "dropout": 0.1,
-  "hidden_dim": 3072,
+  "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": "NEGATIVE",
-    "1": "POSITIVE"
+    "0": "NEG",
+    "1": "NEU",
+    "2": "POS"
   },
   "initializer_range": 0.02,
+  "intermediate_size": 3072,
   "label2id": {
-    "NEGATIVE": 0,
-    "POSITIVE": 1
+    "NEG": 0,
+    "NEU": 1,
+    "POS": 2
   },
-  "max_position_embeddings": 512,
-  "model_type": "distilbert",
-  "n_heads": 12,
-  "n_layers": 6,
-  "pad_token_id": 0,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 130,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",
-  "qa_dropout": 0.1,
-  "seq_classif_dropout": 0.2,
-  "sinusoidal_pos_embds": false,
-  "tie_weights_": true,
+  "tokenizer_class": "BertweetTokenizer",
   "torch_dtype": "float32",
-  "transformers_version": "4.35.2",
-  "vocab_size": 30522
+  "transformers_version": "4.34.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 64001
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f8d3ddd6aa52e024c07e26be876108d6c2d6aaa4375dbf725d54aee1d5cd587
-size 267855533
+oid sha256:2bd8fcc972c53d32c69c7fe64e3ba0b9c0d5539252afed54ba4ee3848a71f884
+size 539678065

tokenizer_config.json

@@ -41,6 +41,7 @@
       "special": true
     }
   },
+  "additional_special_tokens": [],
   "bos_token": "<s>",
   "clean_up_tokenization_spaces": true,
   "cls_token": "<s>",
@@ -51,5 +52,6 @@
   "pad_token": "<pad>",
   "sep_token": "</s>",
   "tokenizer_class": "BertweetTokenizer",
+  "tokenizer_file": null,
   "unk_token": "<unk>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68f31cc0c25785040c95b3b51f6c29f6b9e0c23f9f71bf420819f02266f19cf0
-size 4600
+oid sha256:eefc423b8bfe7921de4f9984686523f4934afb712e4bcaad9232bb40ba15087e
+size 4091