End of training

README.md

@@ -1,6 +1,6 @@
 ---
-license: apache-2.0
-base_model: distilbert-base-uncased
+license: mit
+base_model: roberta-base
 tags:
 - generated_from_trainer
 model-index:
@@ -13,10 +13,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # Sentiment-Analysis-Model
 
-This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
+This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6064
-- F1 Score: 0.7343
+- Loss: 0.6099
+- F1 Score: 0.7455
 
 ## Model description
 
@@ -41,27 +41,37 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 5
+- num_epochs: 10
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | F1 Score |
-|:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 0.7496        | 0.5   | 500  | 0.7056          | 0.6853   |
-| 0.6707        | 1.0   | 1000 | 0.6539          | 0.7240   |
-| 0.5505        | 1.5   | 1500 | 0.6562          | 0.7459   |
-| 0.5418        | 2.0   | 2000 | 0.6064          | 0.7343   |
-| 0.3717        | 2.5   | 2500 | 0.9214          | 0.7443   |
-| 0.3713        | 3.0   | 3000 | 0.8631          | 0.7397   |
-| 0.2445        | 3.5   | 3500 | 1.0991          | 0.7386   |
-| 0.2438        | 4.0   | 4000 | 1.1678          | 0.7402   |
-| 0.1594        | 4.5   | 4500 | 1.3197          | 0.7314   |
-| 0.1554        | 5.0   | 5000 | 1.3487          | 0.7343   |
+| Training Loss | Epoch | Step  | Validation Loss | F1 Score |
+|:-------------:|:-----:|:-----:|:---------------:|:--------:|
+| 0.7757        | 0.5   | 500   | 0.7391          | 0.6777   |
+| 0.7274        | 1.0   | 1000  | 0.7487          | 0.6850   |
+| 0.6895        | 1.5   | 1500  | 0.6636          | 0.7252   |
+| 0.6588        | 2.0   | 2000  | 0.6453          | 0.7388   |
+| 0.5942        | 2.5   | 2500  | 0.7994          | 0.7433   |
+| 0.5943        | 3.0   | 3000  | 0.6099          | 0.7455   |
+| 0.5081        | 3.5   | 3500  | 0.7501          | 0.7475   |
+| 0.5252        | 4.0   | 4000  | 0.7490          | 0.7537   |
+| 0.4445        | 4.5   | 4500  | 1.0240          | 0.7316   |
+| 0.4357        | 5.0   | 5000  | 0.9267          | 0.7455   |
+| 0.3588        | 5.5   | 5500  | 1.1925          | 0.7345   |
+| 0.3886        | 6.0   | 6000  | 1.0273          | 0.7252   |
+| 0.3234        | 6.5   | 6500  | 1.0530          | 0.7541   |
+| 0.3214        | 7.0   | 7000  | 1.2064          | 0.7506   |
+| 0.2868        | 7.5   | 7500  | 1.3049          | 0.7350   |
+| 0.2444        | 8.0   | 8000  | 1.3876          | 0.7439   |
+| 0.2076        | 8.5   | 8500  | 1.4192          | 0.7354   |
+| 0.2124        | 9.0   | 9000  | 1.5205          | 0.7353   |
+| 0.1819        | 9.5   | 9500  | 1.5081          | 0.7449   |
+| 0.1722        | 10.0  | 10000 | 1.5103          | 0.7425   |
 
 
 ### Framework versions
 
-- Transformers 4.33.1
+- Transformers 4.33.2
 - Pytorch 2.0.1+cu118
 - Datasets 2.14.5
 - Tokenizers 0.13.3

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b569a244abafd62462a66823a814ef14b0f460c2595d8fbaaf83081e309bc2b3
+oid sha256:a71c618542df186a331b842fe75643bcdc3f432177bbaa6199eda0789896cb66
 size 498660721