5300-biased-word-detection

README.md

@@ -21,11 +21,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 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: 0.9194
-- Precision: 0.2097
-- Recall: 0.4470
-- F1: 0.2855
-- Accuracy: 0.8070
+- Loss: 0.5440
+- Precision: 0.3143
+- Recall: 0.2170
+- F1: 0.2568
+- Accuracy: 0.8900
 
 ## Model description
 
@@ -56,17 +56,17 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:------:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| 0.3763        | 0.4292 | 100  | 0.7423          | 0.2075    | 0.4476 | 0.2836 | 0.8021   |
-| 0.3614        | 0.8584 | 200  | 0.8232          | 0.2185    | 0.4382 | 0.2916 | 0.8137   |
-| 0.2886        | 1.2876 | 300  | 1.0804          | 0.2526    | 0.3084 | 0.2777 | 0.8596   |
-| 0.2722        | 1.7167 | 400  | 1.0374          | 0.2475    | 0.3593 | 0.2931 | 0.8483   |
-| 0.2642        | 2.1459 | 500  | 0.9183          | 0.2117    | 0.4652 | 0.2910 | 0.8016   |
-| 0.2843        | 2.5751 | 600  | 1.0185          | 0.2286    | 0.4081 | 0.2931 | 0.8277   |
+| 0.2733        | 0.4292 | 100  | 0.4491          | 0.3382    | 0.1454 | 0.2033 | 0.9003   |
+| 0.2635        | 0.8584 | 200  | 0.4566          | 0.3327    | 0.1848 | 0.2377 | 0.8962   |
+| 0.202         | 1.2876 | 300  | 0.5266          | 0.3377    | 0.1599 | 0.2171 | 0.8990   |
+| 0.1981        | 1.7167 | 400  | 0.5384          | 0.3529    | 0.1495 | 0.2101 | 0.9016   |
+| 0.1904        | 2.1459 | 500  | 0.5169          | 0.3004    | 0.2399 | 0.2667 | 0.8846   |
+| 0.1682        | 2.5751 | 600  | 0.5660          | 0.3339    | 0.1963 | 0.2472 | 0.8954   |
 
 
 ### Framework versions
 
-- Transformers 4.46.3
+- Transformers 4.47.0
 - Pytorch 2.5.1+cu121
 - Datasets 3.2.0
-- Tokenizers 0.20.3
+- Tokenizers 0.21.0

config.json

@@ -25,7 +25,7 @@
   "pad_token_id": 1,
   "position_embedding_type": "absolute",
   "torch_dtype": "float32",
-  "transformers_version": "4.46.3",
+  "transformers_version": "4.47.0",
   "type_vocab_size": 1,
   "use_cache": true,
   "vocab_size": 50265

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd1ac5462e33b4593afc4595d32dfe5c7acaaae093ef4bbe4ca285c8d965a3e9
+oid sha256:949cf9f33ed21b2ec68af94c78f67e7f6f85df5070ff2dd584e530d72a9bd459
 size 496250232

tokenizer_config.json

@@ -47,6 +47,7 @@
   "cls_token": "<s>",
   "eos_token": "</s>",
   "errors": "replace",
+  "extra_special_tokens": {},
   "mask_token": "<mask>",
   "model_max_length": 512,
   "pad_token": "<pad>",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e8e4f59b70f3003dcea7559179d4765689beb4a2aad1a80f5190dc9a88e40fe
-size 5240
+oid sha256:e39f762a2751fee49b68c8831d061741e73e55051e13c6e089ee385be29a9729
+size 5304