Training complete

README.md

@@ -18,8 +18,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [t5-base](https://huggingface.co/t5-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2879
-- Bleu: 66.4554
+- Loss: 0.2885
+- Bleu: 66.5293
 
 ## Model description
 
@@ -50,14 +50,14 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Bleu    |
 |:-------------:|:-----:|:----:|:---------------:|:-------:|
-| 0.3751        | 1.0   | 1019 | 0.3149          | 65.4313 |
-| 0.3368        | 2.0   | 2038 | 0.2931          | 66.2663 |
-| 0.3254        | 3.0   | 3057 | 0.2879          | 66.4554 |
+| 0.3777        | 1.0   | 1019 | 0.3172          | 65.4600 |
+| 0.3352        | 2.0   | 2038 | 0.2945          | 66.2206 |
+| 0.3228        | 3.0   | 3057 | 0.2885          | 66.5293 |
 
 
 ### Framework versions
 
-- Transformers 4.33.3
+- Transformers 4.34.0
 - Pytorch 2.0.1+cu118
 - Datasets 2.14.5
-- Tokenizers 0.13.3
+- Tokenizers 0.14.1

generation_config.json

@@ -2,5 +2,5 @@
   "decoder_start_token_id": 0,
   "eos_token_id": 1,
   "pad_token_id": 0,
-  "transformers_version": "4.33.3"
+  "transformers_version": "4.34.0"
 }