Russian-BERT-Finetune

README.md

@@ -20,12 +20,12 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [Priyanka-Balivada/bert-3-epoch-sentiment](https://huggingface.co/Priyanka-Balivada/bert-3-epoch-sentiment) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.8612
-- Accuracy: 0.864
-- Precision: 0.8639
-- Recall: 0.864
-- Micro-avg-recall: 0.864
-- Micro-avg-precision: 0.864
+- Loss: 1.0910
+- Accuracy: 0.869
+- Precision: 0.8687
+- Recall: 0.869
+- Micro-avg-recall: 0.869
+- Micro-avg-precision: 0.869
 
 ## Model description
 
@@ -56,11 +56,11 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | Micro-avg-recall | Micro-avg-precision |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:----------------:|:-------------------:|
-| 0.4019        | 1.0   | 750  | 0.4185          | 0.837    | 0.8378    | 0.837  | 0.837            | 0.837               |
-| 0.2925        | 2.0   | 1500 | 0.3874          | 0.8593   | 0.8611    | 0.8593 | 0.8593           | 0.8593              |
-| 0.0298        | 3.0   | 2250 | 0.5673          | 0.8667   | 0.8664    | 0.8667 | 0.8667           | 0.8667              |
-| 0.0632        | 4.0   | 3000 | 0.7953          | 0.8667   | 0.8668    | 0.8667 | 0.8667           | 0.8667              |
-| 0.052         | 5.0   | 3750 | 0.8612          | 0.864    | 0.8639    | 0.864  | 0.864            | 0.864               |
+| 0.1014        | 1.0   | 750  | 0.8994          | 0.845    | 0.8457    | 0.845  | 0.845            | 0.845               |
+| 0.1351        | 2.0   | 1500 | 1.0207          | 0.858    | 0.8629    | 0.858  | 0.858            | 0.858               |
+| 0.0001        | 3.0   | 2250 | 1.1304          | 0.8563   | 0.8566    | 0.8563 | 0.8563           | 0.8563              |
+| 0.0733        | 4.0   | 3000 | 1.0855          | 0.862    | 0.8624    | 0.862  | 0.862            | 0.862               |
+| 0.0005        | 5.0   | 3750 | 1.0910          | 0.869    | 0.8687    | 0.869  | 0.869            | 0.869               |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99698c64ee7f5eeea4f30ff9d3a3d1b896b0b71d127d95dbd901646acf4795cc
+oid sha256:29d2de9b23217763abe94c7f93a9041878b44e17d77fc84948104053fe6d070e
 size 437961724