adediu25/implicit-hatebert-all

README.md

@@ -1,11 +1,10 @@
 ---
-license: mit
 library_name: peft
 tags:
 - generated_from_trainer
+base_model: GroNLP/hateBERT
 metrics:
 - accuracy
-base_model: microsoft/deberta-v3-base
 model-index:
 - name: trainer
   results: []
@@ -16,10 +15,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # trainer
 
-This model is a fine-tuned version of [microsoft/deberta-v3-base](https://huggingface.co/microsoft/deberta-v3-base) on an unknown dataset.
+This model is a fine-tuned version of [GroNLP/hateBERT](https://huggingface.co/GroNLP/hateBERT) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.5146
-- Accuracy: {'accuracy': 0.8154339363407374}
+- Loss: 0.5228
+- Accuracy: {'accuracy': 0.7989466452942523}
 
 ## Model description
 
@@ -39,27 +38,29 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 0.001
-- train_batch_size: 16
-- eval_batch_size: 16
+- train_batch_size: 10
+- eval_batch_size: 10
 - seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 20
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - num_epochs: 4
 
 ### Training results
 
-| Training Loss | Epoch | Step  | Validation Loss | Accuracy                         |
-|:-------------:|:-----:|:-----:|:---------------:|:--------------------------------:|
-| 0.3938        | 1.0   | 2772  | 0.5646          | {'accuracy': 0.7842912754751545} |
-| 0.3103        | 2.0   | 5544  | 0.5375          | {'accuracy': 0.7945958323792077} |
-| 0.2796        | 3.0   | 8316  | 0.5112          | {'accuracy': 0.8124570643462331} |
-| 0.2611        | 4.0   | 11088 | 0.5146          | {'accuracy': 0.8154339363407374} |
+| Training Loss | Epoch | Step | Validation Loss | Accuracy                         |
+|:-------------:|:-----:|:----:|:---------------:|:--------------------------------:|
+| 0.4295        | 1.0   | 2217 | 0.6655          | {'accuracy': 0.7348294023356996} |
+| 0.3365        | 2.0   | 4434 | 0.5471          | {'accuracy': 0.7874971376230822} |
+| 0.2882        | 3.0   | 6651 | 0.5133          | {'accuracy': 0.8014655369819098} |
+| 0.2574        | 4.0   | 8868 | 0.5228          | {'accuracy': 0.7989466452942523} |
 
 
 ### Framework versions
 
 - PEFT 0.10.0
-- Transformers 4.38.2
-- Pytorch 2.2.1+cu121
+- Transformers 4.39.3
+- Pytorch 2.2.2+cu121
 - Datasets 2.18.0
 - Tokenizers 0.15.2

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "microsoft/deberta-v3-base",
+  "base_model_name_or_path": "GroNLP/hateBERT",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -20,11 +20,11 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "key_proj",
-    "query_proj",
-    "value_proj",
+    "dense",
+    "value",
+    "key",
     "classifier",
-    "dense"
+    "query"
   ],
   "task_type": "SEQ_CLS",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34b3e7a18d001089251e2e2cef126b2aaafb6b73b7f16fd7d399459f32c444ad
-size 5462676
+oid sha256:48f745e93cb5c6a66812e30fccf8b4b6c6fea527b555638e24448d5d9be3eb60
+size 5461916

special_tokens_map.json

@@ -1,15 +1,7 @@
 {
-  "bos_token": "[CLS]",
   "cls_token": "[CLS]",
-  "eos_token": "[SEP]",
   "mask_token": "[MASK]",
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",
-  "unk_token": {
-    "content": "[UNK]",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  }
+  "unk_token": "[UNK]"
 }

tokenizer_config.json

@@ -8,31 +8,31 @@
       "single_word": false,
       "special": true
     },
-    "1": {
-      "content": "[CLS]",
+    "100": {
+      "content": "[UNK]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "2": {
-      "content": "[SEP]",
+    "101": {
+      "content": "[CLS]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "3": {
-      "content": "[UNK]",
+    "102": {
+      "content": "[SEP]",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128000": {
+    "103": {
       "content": "[MASK]",
       "lstrip": false,
       "normalized": false,
@@ -41,18 +41,18 @@
       "special": true
     }
   },
-  "bos_token": "[CLS]",
   "clean_up_tokenization_spaces": true,
   "cls_token": "[CLS]",
-  "do_lower_case": false,
-  "eos_token": "[SEP]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
   "mask_token": "[MASK]",
-  "model_max_length": 1000000000000000019884624838656,
+  "max_len": 512,
+  "model_max_length": 512,
+  "never_split": null,
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",
-  "sp_model_kwargs": {},
-  "split_by_punct": false,
-  "tokenizer_class": "DebertaV2Tokenizer",
-  "unk_token": "[UNK]",
-  "vocab_type": "spm"
+  "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 sha256:9137612d3c6735586176c8ca4b89907557fddf395a5286a996f11876025bb30b
+oid sha256:906648a7de0aa95ca86231ac26a736c55ebe6924ba92d8588ea9323a8eab51e6
 size 4856