updated and added multiple files

finance/finbert_large_emotion_model/config.json

@@ -0,0 +1,45 @@
+{
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "anger",
+    "1": "disgust",
+    "2": "fear",
+    "3": "joy",
+    "4": "neutral",
+    "5": "sadness",
+    "6": "shame",
+    "7": "surprise"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "anger": 0,
+    "disgust": 1,
+    "fear": 2,
+    "joy": 3,
+    "neutral": 4,
+    "sadness": 5,
+    "shame": 6,
+    "surprise": 7
+  },
+  "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",
+  "problem_type": "single_label_classification",
+  "transformers_version": "4.56.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30873
+}

finance/finbert_large_emotion_model/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

finance/finbert_large_emotion_model/tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

finance/train_finbert.py

@@ -27,7 +27,6 @@ def compute_metrics(p):
 
 def main():
     """Main function to load data, fine-tune the FinBERT model, and save it."""
-    # --- 1. Define Paths for Colab's Temporary Session Storage ---
     # This path points to the file you just uploaded.
     data_path = "/content/emotion_dataset.csv"
     # The final model will be saved here, in the temporary storage.
@@ -59,7 +58,7 @@ def main():
 
     # --- 3. Load Tokenizer and Model ---
     print("Loading FinBERT tokenizer and model...")
-    model_name = "ProsusAI/finbert"
+    model_name = 'yiyanghkust/finbert-pretrai'
     tokenizer = AutoTokenizer.from_pretrained(model_name)
     
     model = AutoModelForSequenceClassification.from_pretrained(
@@ -82,12 +81,12 @@ def main():
 
     training_args = TrainingArguments(
         output_dir=output_dir,
-        num_train_epochs=1,
+        num_train_epochs=3,
         per_device_train_batch_size=16,
         per_device_eval_batch_size=16,
         logging_steps=100,
         evaluation_strategy="epoch",
-        save_strategy="epoch",
+        save_strategy="no",
         load_best_model_at_end=True,
     )