End of training

README.md

@@ -21,11 +21,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [cardiffnlp/twitter-roberta-large-hate-latest](https://huggingface.co/cardiffnlp/twitter-roberta-large-hate-latest) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4201
-- Accuracy: 0.8178
-- Precision: 0.8218
-- Recall: 0.8178
-- F1: 0.8172
+- Loss: 0.0281
+- Accuracy: 0.9938
+- Precision: 0.9938
+- Recall: 0.9938
+- F1: 0.9938
 
 ## Model description
 
@@ -44,30 +44,30 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 1e-05
-- train_batch_size: 16
+- learning_rate: 5e-05
+- train_batch_size: 32
 - eval_batch_size: 128
 - seed: 42
 - gradient_accumulation_steps: 2
-- total_train_batch_size: 32
+- total_train_batch_size: 64
 - 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 | Precision | Recall | F1     |
-|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
-| 0.5941        | 1.0   | 61   | 0.6001          | 0.6940   | 0.6990    | 0.6938 | 0.6919 |
-| 0.5937        | 2.0   | 122  | 0.6043          | 0.7036   | 0.7076    | 0.7034 | 0.7021 |
-| 0.4383        | 3.0   | 183  | 0.6916          | 0.6723   | 0.6828    | 0.6720 | 0.6673 |
-| 0.3597        | 4.0   | 244  | 0.6627          | 0.6988   | 0.7001    | 0.6987 | 0.6982 |
-| 0.2675        | 5.0   | 305  | 0.8241          | 0.6723   | 0.6723    | 0.6723 | 0.6722 |
-| 0.2511        | 6.0   | 366  | 1.1261          | 0.6337   | 0.6613    | 0.6332 | 0.6169 |
-| 0.2169        | 7.0   | 427  | 1.0857          | 0.6723   | 0.6723    | 0.6723 | 0.6723 |
-| 0.1566        | 8.0   | 488  | 1.2781          | 0.6723   | 0.6782    | 0.6721 | 0.6694 |
-| 0.0971        | 9.0   | 549  | 1.3272          | 0.6867   | 0.6874    | 0.6867 | 0.6864 |
-| 0.083         | 10.0  | 610  | 1.4338          | 0.6795   | 0.6807    | 0.6794 | 0.6789 |
+| Training Loss | Epoch  | Step | Validation Loss | Accuracy | Precision | Recall | F1     |
+|:-------------:|:------:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
+| 0.6832        | 0.9836 | 30   | 0.6742          | 0.5084   | 0.7524    | 0.5072 | 0.3498 |
+| 0.5977        | 2.0    | 61   | 0.8033          | 0.5253   | 0.6631    | 0.5242 | 0.3960 |
+| 0.5943        | 2.9836 | 91   | 0.6655          | 0.6482   | 0.6846    | 0.6487 | 0.6304 |
+| 0.3755        | 4.0    | 122  | 0.7484          | 0.6916   | 0.6983    | 0.6918 | 0.6891 |
+| 0.4144        | 4.9836 | 152  | 0.6091          | 0.6988   | 0.6992    | 0.6988 | 0.6987 |
+| 0.2831        | 6.0    | 183  | 0.7688          | 0.7205   | 0.7330    | 0.7208 | 0.7169 |
+| 0.1818        | 6.9836 | 213  | 0.9114          | 0.7277   | 0.7361    | 0.7279 | 0.7254 |
+| 0.0987        | 8.0    | 244  | 1.0269          | 0.7205   | 0.7207    | 0.7205 | 0.7204 |
+| 0.0523        | 8.9836 | 274  | 1.1469          | 0.7301   | 0.7344    | 0.7303 | 0.7290 |
+| 0.0329        | 9.8361 | 300  | 1.3097          | 0.7253   | 0.7301    | 0.7255 | 0.7240 |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0404a370c325d621a020021d7ef4f7bf53c52736a406ed9e4e3c9533c49a63e5
+oid sha256:f004798464c6bcb6821d1cd04c816148c9a86f17fdf2c8609bd26570da76f287
 size 1421495416