End of training

README.md

@@ -1,7 +1,7 @@
 ---
 library_name: transformers
-license: apache-2.0
-base_model: bert-base-uncased
+license: mit
+base_model: roberta-base
 tags:
 - generated_from_trainer
 metrics:
@@ -16,10 +16,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # roberta-base-uncased-finetuned-swag
 
-This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
+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: 0.5432
-- Accuracy: 0.7913
+- Loss: 0.4967
+- Accuracy: 0.8099
 
 ## Model description
 
@@ -38,21 +38,23 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 2e-05
-- train_batch_size: 10
-- eval_batch_size: 10
+- learning_rate: 5e-05
+- train_batch_size: 32
+- eval_batch_size: 8
 - 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
-- num_epochs: 3
+- num_epochs: 4
+- mixed_precision_training: Native AMP
 
 ### Training results
 
-| Training Loss | Epoch | Step  | Validation Loss | Accuracy |
-|:-------------:|:-----:|:-----:|:---------------:|:--------:|
-| 0.7263        | 1.0   | 7355  | 0.5432          | 0.7913   |
-| 0.4169        | 2.0   | 14710 | 0.5825          | 0.8066   |
-| 0.2445        | 3.0   | 22065 | 0.8614          | 0.8091   |
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 0.791         | 1.0   | 2299 | 0.5549          | 0.7824   |
+| 0.5334        | 2.0   | 4598 | 0.4967          | 0.8099   |
+| 0.3262        | 3.0   | 6897 | 0.5730          | 0.8157   |
+| 0.1798        | 4.0   | 9196 | 0.6544          | 0.8257   |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1807caea1a3e2f710e5d27628e2af854f468122b6be67839128a47ede27a474e
+oid sha256:5e070e4ed6e8a97fcd1e4030439090c1c45f34b86d40deb18d10cd25b43a8863
 size 498609724