End of training

README.md

@@ -2,6 +2,11 @@
 base_model: cardiffnlp/twitter-roberta-base-sentiment-latest
 tags:
 - generated_from_trainer
+metrics:
+- precision
+- recall
+- f1
+- accuracy
 model-index:
 - name: roberta-imdb
   results: []
@@ -14,7 +19,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [cardiffnlp/twitter-roberta-base-sentiment-latest](https://huggingface.co/cardiffnlp/twitter-roberta-base-sentiment-latest) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1542
+- Loss: 0.1525
+- Precision: 0.9412
+- Recall: 0.9576
+- F1: 0.9493
+- Accuracy: 0.9489
 
 ## Model description
 
@@ -40,15 +49,14 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 300
-- num_epochs: 3
+- num_epochs: 2
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss |
-|:-------------:|:-----:|:----:|:---------------:|
-| 0.213         | 1.0   | 1563 | 0.1663          |
-| 0.1599        | 2.0   | 3126 | 0.1989          |
-| 0.0974        | 3.0   | 4689 | 0.2297          |
+| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| 0.2021        | 1.0   | 1563 | 0.1641          | 0.9368    | 0.9531 | 0.9449 | 0.9444   |
+| 0.1473        | 2.0   | 3126 | 0.2119          | 0.9445    | 0.9530 | 0.9487 | 0.9485   |
 
 
 ### Framework versions

logs/events.out.tfevents.1718844852.a281f955dda1.34.3

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85d16678e23c692cdb9565fabab3d0ad27ec66e8171e6e3d7954a97ca967e91d
-size 6191
+oid sha256:0181a645e867f1346f26b8d5128c4ba9bb54af1de64aeb633ec97410791cd47f
+size 7650

logs/events.out.tfevents.1718849115.a281f955dda1.34.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:793564ebda12f4e3b3848fd4189e70358e82562d1c3b8c3b5b0483f6d07693c9
+size 560