fusersam
/

Sentiment-Analysis-Model

Text Classification

Transformers

PyTorch

roberta

Generated from Trainer

Inference Endpoints

Model card Files Files and versions Community

fusersam commited on Sep 15, 2023

Commit

cdbb689

1 Parent(s): 54643de

End of training

Browse files

Files changed (1) hide show

README.md +18 -28

README.md CHANGED Viewed

@@ -1,6 +1,6 @@
 ---
-license: apache-2.0
-base_model: distilbert-base-cased
 tags:
 - generated_from_trainer
 metrics:
@@ -15,10 +15,10 @@ should probably proofread and complete it, then remove this comment. -->
 # Sentiment-Analysis-Model
-This model is a fine-tuned version of [distilbert-base-cased](https://huggingface.co/distilbert-base-cased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6064
-- Accuracy: 0.7515
 ## Model description
@@ -43,32 +43,22 @@ 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: 10
 ### Training results
-| Training Loss | Epoch | Step  | Validation Loss | Accuracy |
-|:-------------:|:-----:|:-----:|:---------------:|:--------:|
-| 0.75          | 0.5   | 500   | 0.7256          | 0.7015   |
-| 0.7029        | 1.0   | 1000  | 0.6558          | 0.7375   |
-| 0.603         | 1.5   | 1500  | 0.6782          | 0.7435   |
-| 0.5837        | 2.0   | 2000  | 0.6064          | 0.7515   |
-| 0.4341        | 2.5   | 2500  | 0.7703          | 0.756    |
-| 0.4229        | 3.0   | 3000  | 0.6850          | 0.7525   |
-| 0.2562        | 3.5   | 3500  | 1.0519          | 0.7465   |
-| 0.2975        | 4.0   | 4000  | 1.1673          | 0.729    |
-| 0.174         | 4.5   | 4500  | 1.3483          | 0.7235   |
-| 0.1931        | 5.0   | 5000  | 1.4196          | 0.7405   |
-| 0.1005        | 5.5   | 5500  | 1.6459          | 0.7415   |
-| 0.1145        | 6.0   | 6000  | 1.4333          | 0.746    |
-| 0.0764        | 6.5   | 6500  | 1.5973          | 0.741    |
-| 0.0741        | 7.0   | 7000  | 1.8235          | 0.7295   |
-| 0.0349        | 7.5   | 7500  | 2.0046          | 0.7415   |
-| 0.0509        | 8.0   | 8000  | 1.8520          | 0.74     |
-| 0.0273        | 8.5   | 8500  | 1.9855          | 0.7465   |
-| 0.0295        | 9.0   | 9000  | 2.0323          | 0.733    |
-| 0.0221        | 9.5   | 9500  | 2.0907          | 0.7415   |
-| 0.0192        | 10.0  | 10000 | 2.0653          | 0.7455   |
 ### Framework versions

 ---
+license: mit
+base_model: roberta-base
 tags:
 - generated_from_trainer
 metrics:
 # Sentiment-Analysis-Model
+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: 0.7000
+- Accuracy: 0.7165
 ## Model description
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
+- num_epochs: 5
 ### Training results
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 0.8648        | 0.5   | 500  | 0.9848          | 0.703    |
+| 0.8367        | 1.0   | 1000 | 0.8764          | 0.683    |
+| 0.7815        | 1.5   | 1500 | 0.7792          | 0.7145   |
+| 0.7751        | 2.0   | 2000 | 0.7516          | 0.7095   |
+| 0.8081        | 2.5   | 2500 | 0.7783          | 0.7055   |
+| 0.8142        | 3.0   | 3000 | 0.8125          | 0.688    |
+| 0.8497        | 3.5   | 3500 | 0.8383          | 0.6575   |
+| 0.8006        | 4.0   | 4000 | 0.7412          | 0.705    |
+| 0.7363        | 4.5   | 4500 | 0.7299          | 0.718    |
+| 0.7151        | 5.0   | 5000 | 0.7000          | 0.7165   |
 ### Framework versions