End of training

README.md

@@ -67,11 +67,11 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Sacrebleu | Gen Len |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:-------:|
-| 4.8114        | 1.0   | 825  | 1.4552          | 28.698    | 45.0965 |
-| 1.3328        | 2.0   | 1650 | 1.2516          | 30.4316   | 45.683  |
-| 1.163         | 3.0   | 2475 | 1.1934          | 30.9199   | 45.474  |
-| 0.9982        | 4.0   | 3300 | 1.1762          | 31.635    | 45.254  |
-| 0.9001        | 5.0   | 4125 | 1.1713          | 31.5851   | 45.311  |
+| 3.6041        | 1.0   | 825  | 1.4552          | 28.698    | 45.0965 |
+| 1.3318        | 2.0   | 1650 | 1.2516          | 30.4316   | 45.683  |
+| 1.103         | 3.0   | 2475 | 1.1934          | 30.9199   | 45.474  |
+| 0.9875        | 4.0   | 3300 | 1.1762          | 31.635    | 45.254  |
+| 0.9204        | 5.0   | 4125 | 1.1713          | 31.5851   | 45.311  |
 
 
 ### Framework versions

generation_config.json

@@ -1,5 +1,8 @@
 {
+  "bos_token_id": 0,
+  "decoder_start_token_id": 2,
+  "eos_token_id": 2,
   "max_length": 200,
-  "push_to_hub": true,
+  "pad_token_id": 1,
   "transformers_version": "4.41.2"
 }