Model save

README.md

@@ -18,8 +18,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [FacebookAI/roberta-base](https://huggingface.co/FacebookAI/roberta-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.8849
-- Accuracy: 0.7485
+- Loss: 0.6232
+- Accuracy: 0.7953
 
 ## Model description
 
@@ -45,14 +45,21 @@ The following hyperparameters were used during training:
 - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.1
-- num_epochs: 1
+- num_epochs: 8
 - mixed_precision_training: Native AMP
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Accuracy |
-|:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 0.9931        | 1.0   | 1585 | 0.8849          | 0.7485   |
+| Training Loss | Epoch | Step  | Validation Loss | Accuracy |
+|:-------------:|:-----:|:-----:|:---------------:|:--------:|
+| 1.156         | 1.0   | 1585  | 0.8263          | 0.7540   |
+| 0.6895        | 2.0   | 3170  | 0.6674          | 0.7868   |
+| 0.5994        | 3.0   | 4755  | 0.6469          | 0.7878   |
+| 0.5539        | 4.0   | 6340  | 0.6289          | 0.7930   |
+| 0.5228        | 5.0   | 7925  | 0.6235          | 0.7934   |
+| 0.5095        | 6.0   | 9510  | 0.6202          | 0.7934   |
+| 0.4845        | 7.0   | 11095 | 0.6232          | 0.7933   |
+| 0.4863        | 8.0   | 12680 | 0.6232          | 0.7953   |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b593cd6155d724da34542a89dba1229fd3a64a01fc20a7c3c2ca665003e055f
+oid sha256:bf0611d191c0ee1d86a17e5b4e4399328f604cdcfa32f6f44c291e5f5d90f1fa
 size 498640508