Model save

README.md

@@ -17,9 +17,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [ai4bharat/IndicBART](https://huggingface.co/ai4bharat/IndicBART) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 3.5032
-- Bleu: 17.4363
-- Gen Len: 20.978
+- Loss: 2.6479
+- Bleu: 24.5576
+- Gen Len: 20.998
 
 ## Model description
 
@@ -52,16 +52,16 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Bleu    | Gen Len |
 |:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|
-| 5.8666        | 1.0   | 1004 | 4.9742          | 13.3823 | 21.0    |
-| 4.8088        | 2.0   | 2008 | 4.0212          | 15.3375 | 21.0    |
-| 4.2735        | 3.0   | 3012 | 3.6499          | 16.3145 | 21.0    |
-| 4.0836        | 4.0   | 4016 | 3.5329          | 17.3835 | 20.996  |
-| 4.0152        | 5.0   | 5020 | 3.5032          | 17.4363 | 20.978  |
+| 4.2073        | 1.0   | 1004 | 3.9699          | 19.0075 | 21.0    |
+| 3.4057        | 2.0   | 2008 | 3.1345          | 22.672  | 21.0    |
+| 3.0025        | 3.0   | 3012 | 2.7964          | 23.002  | 21.0    |
+| 2.8408        | 4.0   | 4016 | 2.6781          | 23.8397 | 20.998  |
+| 2.7925        | 5.0   | 5020 | 2.6479          | 24.5576 | 20.998  |
 
 
 ### Framework versions
 
-- Transformers 4.52.3
+- Transformers 4.52.4
 - Pytorch 2.6.0+cu124
 - Datasets 2.14.4
 - Tokenizers 0.21.1

generation_config.json

@@ -3,5 +3,5 @@
   "eos_token_id": 64001,
   "forced_eos_token_id": 2,
   "pad_token_id": 0,
-  "transformers_version": "4.52.3"
+  "transformers_version": "4.52.4"
 }