Faith-theAnalyst
/

twitter_roberta_sentiment_model

Text Classification

Transformers

Safetensors

roberta

Generated from Trainer

Model card Files Files and versions Community

Faith-theAnalyst commited on Nov 12, 2023

Commit

3ac8a5c

1 Parent(s): c4bbf2f

End of training

Browse files

Files changed (1) hide show

README.md +14 -19

README.md CHANGED Viewed

@@ -16,8 +16,8 @@ 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: 0.3658
-- Accuracy: 0.8045
 ## Model description
@@ -36,34 +36,29 @@ More information needed
 ### Training hyperparameters
 The following hyperparameters were used during training:
-- learning_rate: 5e-05
 - train_batch_size: 16
 - eval_batch_size: 16
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 500
-- num_epochs: 3
 ### Training results
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 0.6116        | 0.2   | 100  | 0.4453          | 0.6965   |
-| 0.4047        | 0.4   | 200  | 0.3999          | 0.735    |
-| 0.3979        | 0.6   | 300  | 0.3641          | 0.7655   |
-| 0.3828        | 0.8   | 400  | 0.3512          | 0.7635   |
-| 0.3805        | 1.0   | 500  | 0.3489          | 0.776    |
-| 0.3454        | 1.2   | 600  | 0.3488          | 0.774    |
-| 0.3135        | 1.4   | 700  | 0.3529          | 0.785    |
-| 0.3216        | 1.6   | 800  | 0.3344          | 0.7845   |
-| 0.3005        | 1.8   | 900  | 0.3793          | 0.789    |
-| 0.3041        | 2.0   | 1000 | 0.3324          | 0.7925   |
-| 0.2126        | 2.2   | 1100 | 0.3839          | 0.7895   |
-| 0.2218        | 2.4   | 1200 | 0.3653          | 0.7955   |
-| 0.1986        | 2.6   | 1300 | 0.3745          | 0.803    |
-| 0.2049        | 2.8   | 1400 | 0.3586          | 0.802    |
-| 0.1911        | 3.0   | 1500 | 0.3658          | 0.8045   |
 ### Framework versions

 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: 0.3189
+- Accuracy: 0.805
 ## Model description
 ### Training hyperparameters
 The following hyperparameters were used during training:
+- learning_rate: 2e-05
 - train_batch_size: 16
 - eval_batch_size: 16
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 500
+- num_epochs: 2
 ### Training results
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 0.6619        | 0.2   | 100  | 0.5226          | 0.6285   |
+| 0.4526        | 0.4   | 200  | 0.4150          | 0.716    |
+| 0.4092        | 0.6   | 300  | 0.3898          | 0.728    |
+| 0.3886        | 0.8   | 400  | 0.3441          | 0.773    |
+| 0.3822        | 1.0   | 500  | 0.3494          | 0.767    |
+| 0.3396        | 1.2   | 600  | 0.3470          | 0.7865   |
+| 0.3156        | 1.4   | 700  | 0.3418          | 0.7875   |
+| 0.3099        | 1.6   | 800  | 0.3231          | 0.794    |
+| 0.2994        | 1.8   | 900  | 0.3371          | 0.7885   |
+| 0.2907        | 2.0   | 1000 | 0.3189          | 0.805    |
 ### Framework versions