End of training

README.md

@@ -18,7 +18,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [FacebookAI/xlm-roberta-large](https://huggingface.co/FacebookAI/xlm-roberta-large) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.2426
+- Loss: 1.2092
 - Accuracy: 0.9190
 
 ## Model description
@@ -46,19 +46,18 @@ The following hyperparameters were used during training:
 - total_train_batch_size: 16
 - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED 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
+- lr_scheduler_warmup_ratio: 0.2
 - num_epochs: 10
 - mixed_precision_training: Native AMP
-- label_smoothing_factor: 0.1
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 1.5387        | 1.0   | 80   | 1.2426          | 0.9190   |
-| 1.2412        | 2.0   | 160  | 1.4491          | 0.9190   |
-| 1.3159        | 3.0   | 240  | 1.8370          | 0.9190   |
-| 1.367         | 4.0   | 320  | 1.2772          | 0.9190   |
+| 1.4484        | 1.0   | 80   | 1.2092          | 0.9190   |
+| 1.2845        | 2.0   | 160  | 1.3536          | 0.9190   |
+| 1.2898        | 3.0   | 240  | 1.4628          | 0.9190   |
+| 1.2482        | 4.0   | 320  | 1.3628          | 0.9190   |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd740e253bfe92a788dc7e845f3627dad86dbf947acddecca67812480401e2f2
+oid sha256:d4623bbfad7655d1c5a2ea3a5047d6817fa1d17d930e99663db21c843ac1d840
 size 2239630972