End of training

README.md

@@ -21,11 +21,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [VRLLab/TurkishBERTweet](https://huggingface.co/VRLLab/TurkishBERTweet) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1403
-- Precision: 0.5373
-- Recall: 0.3243
-- F1: 0.4045
-- Accuracy: 0.9629
+- Loss: 0.2451
+- Precision: 0.3393
+- Recall: 0.1098
+- F1: 0.1659
+- Accuracy: 0.9261
 
 ## Model description
 
@@ -56,16 +56,15 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| 0.1645        | 1.0   | 230  | 0.1246          | 0.1988    | 0.375  | 0.2598 | 0.9565   |
-| 0.1285        | 2.0   | 460  | 0.1091          | 0.3077    | 0.4091 | 0.3512 | 0.9706   |
-| 0.0771        | 3.0   | 690  | 0.1623          | 0.5397    | 0.3864 | 0.4503 | 0.9751   |
-| 0.0535        | 4.0   | 920  | 0.1468          | 0.4521    | 0.375  | 0.4099 | 0.9750   |
-| 0.0331        | 5.0   | 1150 | 0.1831          | 0.4333    | 0.4432 | 0.4382 | 0.9743   |
+| 0.2144        | 1.0   | 328  | 0.1995          | 0.4647    | 0.2380 | 0.3147 | 0.9394   |
+| 0.1404        | 2.0   | 656  | 0.2230          | 0.3410    | 0.4036 | 0.3697 | 0.9253   |
+| 0.0939        | 3.0   | 984  | 0.2399          | 0.4864    | 0.3223 | 0.3877 | 0.9436   |
+| 0.0568        | 4.0   | 1312 | 0.2954          | 0.4086    | 0.4578 | 0.4318 | 0.9326   |
 
 
 ### Framework versions
 
-- Transformers 4.47.1
+- Transformers 4.48.1
 - Pytorch 2.5.1+cu124
 - Datasets 3.2.0
 - Tokenizers 0.21.0

config.json

@@ -30,7 +30,7 @@
   "pad_token_id": 1,
   "position_embedding_type": "absolute",
   "torch_dtype": "float32",
-  "transformers_version": "4.47.1",
+  "transformers_version": "4.48.1",
   "type_vocab_size": 1,
   "use_cache": true,
   "vocab_size": 100000

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2753afcaf836493962da5606bbf8312244d0f142fd709771a7215016629141b8
+oid sha256:d56a8e617e152554b6abbc1d46491f774acfdd44cce7bbb1468e3bec19e62f67
 size 649039236