5300-biased-word-detection

README.md

@@ -1,7 +1,7 @@
 ---
 library_name: transformers
 license: mit
-base_model: charisgao/pretrain_model
+base_model: roberta-base
 tags:
 - generated_from_trainer
 metrics:
@@ -19,13 +19,13 @@ should probably proofread and complete it, then remove this comment. -->
 
 # model
 
-This model is a fine-tuned version of [charisgao/pretrain_model](https://huggingface.co/charisgao/pretrain_model) on the None dataset.
+This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.5988
-- Precision: 0.7906
-- Recall: 0.925
-- F1: 0.8525
-- Accuracy: 0.7942
+- Loss: 0.3309
+- Precision: 0.6214
+- Recall: 0.5332
+- F1: 0.5410
+- Accuracy: 0.9060
 
 ## Model description
 
@@ -56,14 +56,14 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:------:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| 0.5484        | 0.8547 | 100  | 0.5398          | 0.7911    | 0.8725 | 0.8298 | 0.7645   |
-| 0.4185        | 1.7094 | 200  | 0.5482          | 0.8034    | 0.9216 | 0.8584 | 0.8      |
-| 0.3595        | 2.5641 | 300  | 0.6521          | 0.776     | 0.9510 | 0.8546 | 0.7871   |
+| 0.1159        | 0.8547 | 100  | 0.3248          | 0.6055    | 0.5785 | 0.5888 | 0.8852   |
+| 0.202         | 1.7094 | 200  | 0.3075          | 0.6661    | 0.5444 | 0.5581 | 0.9087   |
+| 0.1593        | 2.5641 | 300  | 0.3221          | 0.6624    | 0.5473 | 0.5622 | 0.9079   |
 
 
 ### Framework versions
 
 - Transformers 4.46.3
 - Pytorch 2.5.1+cu121
-- Datasets 3.1.0
+- Datasets 3.2.0
 - Tokenizers 0.20.3

config.json

@@ -1,7 +1,7 @@
 {
-  "_name_or_path": "charisgao/pretrain_model",
+  "_name_or_path": "roberta-base",
   "architectures": [
-    "RobertaForSequenceClassification"
+    "RobertaForTokenClassification"
   ],
   "attention_probs_dropout_prob": 0.1,
   "bos_token_id": 0,
@@ -10,6 +10,10 @@
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
   "hidden_size": 768,
+  "id2label": {
+    "0": "Non-biased",
+    "1": "Biased"
+  },
   "initializer_range": 0.02,
   "intermediate_size": 3072,
   "layer_norm_eps": 1e-05,
@@ -19,7 +23,6 @@
   "num_hidden_layers": 12,
   "pad_token_id": 1,
   "position_embedding_type": "absolute",
-  "problem_type": "single_label_classification",
   "torch_dtype": "float32",
   "transformers_version": "4.46.3",
   "type_vocab_size": 1,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95d3df44056589767f2483300c4a04574c4887bb2ace9f0bf32ff09deec64623
-size 498612824
+oid sha256:74973004aa8b8820abde4063cc091b52506d8d9c6fe0d5f8819c330a960fbe44
+size 496250232

special_tokens_map.json

@@ -1,25 +1,7 @@
 {
-  "bos_token": {
-    "content": "<s>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "cls_token": {
-    "content": "<s>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "eos_token": {
-    "content": "</s>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
   "mask_token": {
     "content": "<mask>",
     "lstrip": true,
@@ -27,25 +9,7 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": {
-    "content": "<pad>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "sep_token": {
-    "content": "</s>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "unk_token": {
-    "content": "<unk>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  }
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
 }

tokenizer.json

@@ -1,6 +1,11 @@
 {
   "version": "1.0",
-  "truncation": null,
+  "truncation": {
+    "direction": "Right",
+    "max_length": 512,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
   "padding": null,
   "added_tokens": [
     {