End of training

README.md

@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [microsoft/git-base](https://huggingface.co/microsoft/git-base) on the imagefolder dataset.
 It achieves the following results on the evaluation set:
-- Loss: 6.6548
-- Wer Score: 8.8
+- Loss: 6.7529
+- Wer Score: 8.92
 
 ## Model description
 
@@ -52,12 +52,12 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Wer Score |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|
-| 3.9097        | 50.0  | 50   | 6.6548          | 8.8       |
+| 3.844         | 50.0  | 50   | 6.7529          | 8.92      |
 
 
 ### Framework versions
 
-- Transformers 4.41.1
+- Transformers 4.41.2
 - Pytorch 2.3.0+cu121
 - Datasets 2.19.2
 - Tokenizers 0.19.1

generation_config.json

@@ -3,5 +3,5 @@
   "bos_token_id": 101,
   "eos_token_id": 102,
   "pad_token_id": 0,
-  "transformers_version": "4.41.1"
+  "transformers_version": "4.41.2"
 }