End of training

README.md

@@ -18,8 +18,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1349
-- Accuracy: 0.9542
+- Loss: 0.1745
+- Accuracy: 0.9545
 
 ## Model description
 
@@ -39,8 +39,8 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 2e-05
-- train_batch_size: 64
-- eval_batch_size: 64
+- train_batch_size: 32
+- eval_batch_size: 32
 - seed: 42
 - 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
@@ -50,8 +50,8 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 1.0   | 391  | 0.1396          | 0.9482   |
-| 0.2014        | 2.0   | 782  | 0.1349          | 0.9542   |
+| 0.1604        | 1.0   | 782  | 0.1369          | 0.9511   |
+| 0.0867        | 2.0   | 1564 | 0.1745          | 0.9545   |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4fe274232ce0cdfa85eb229dccb879b6ba9aaa378e6f318ae589db2b034a158f
+oid sha256:c7327324f5e9c6fbb49fd52975ed079bf4d14ab465cbb3aba2d01bd21eb63b08
 size 498612824