Model save

README.md

@@ -17,14 +17,14 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [vinai/bertweet-base](https://huggingface.co/vinai/bertweet-base) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.5414
-- F1 Macro: 0.7179
-- F1: 0.8053
-- F1 Neg: 0.6304
-- Acc: 0.745
-- Prec: 0.7873
-- Recall: 0.8242
-- Mcc: 0.4373
+- Loss: 0.6138
+- F1 Macro: 0.8316
+- F1: 0.8834
+- F1 Neg: 0.7798
+- Acc: 0.8475
+- Prec: 0.8652
+- Recall: 0.9023
+- Mcc: 0.6647
 
 ## Model description
 
@@ -50,14 +50,16 @@ The following hyperparameters were used during training:
 - distributed_type: multi-GPU
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 1
+- num_epochs: 3
 - mixed_precision_training: Native AMP
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | F1 Macro | F1     | F1 Neg | Acc   | Prec   | Recall | Mcc    |
-|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:------:|:-----:|:------:|:------:|:------:|
-| 0.6385        | 1.0   | 614  | 0.5414          | 0.7179   | 0.8053 | 0.6304 | 0.745 | 0.7873 | 0.8242 | 0.4373 |
+| Training Loss | Epoch | Step | Validation Loss | F1 Macro | F1     | F1 Neg | Acc    | Prec   | Recall | Mcc    |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:------:|:------:|:------:|:------:|:------:|
+| 0.646         | 1.0   | 614  | 0.4778          | 0.7714   | 0.8366 | 0.7063 | 0.79   | 0.8333 | 0.8398 | 0.5429 |
+| 0.4482        | 2.0   | 1228 | 0.4859          | 0.7700   | 0.8597 | 0.6803 | 0.805  | 0.7967 | 0.9336 | 0.5653 |
+| 0.3669        | 3.0   | 1842 | 0.6138          | 0.8316   | 0.8834 | 0.7798 | 0.8475 | 0.8652 | 0.9023 | 0.6647 |
 
 
 ### Framework versions