Training complete

README.md

@@ -1,7 +1,7 @@
 ---
 library_name: transformers
-license: mit
-base_model: facebook/mbart-large-50
+license: apache-2.0
+base_model: google/byt5-small
 tags:
 - simplification
 - generated_from_trainer
@@ -17,11 +17,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 # mbart-neutralization
 
-This model is a fine-tuned version of [facebook/mbart-large-50](https://huggingface.co/facebook/mbart-large-50) on an unknown dataset.
+This model is a fine-tuned version of [google/byt5-small](https://huggingface.co/google/byt5-small) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2295
-- Bleu: 80.6008
-- Gen Len: 27.6616
+- Loss: 0.0584
+- Bleu: 6.8362
+- Gen Len: 20.0
 
 ## Model description
 
@@ -50,10 +50,10 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Bleu    | Gen Len |
-|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|
-| No log        | 1.0   | 402  | 0.2902          | 77.5374 | 19.1027 |
-| 0.5693        | 2.0   | 804  | 0.2295          | 80.6008 | 27.6616 |
+| Training Loss | Epoch | Step | Validation Loss | Bleu   | Gen Len |
+|:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|
+| No log        | 1.0   | 440  | 0.0804          | 4.0275 | 20.0    |
+| 0.2774        | 2.0   | 880  | 0.0584          | 6.8362 | 20.0    |
 
 
 ### Framework versions

generation_config.json

@@ -1,11 +1,6 @@
 {
-  "bos_token_id": 0,
-  "decoder_start_token_id": 2,
-  "early_stopping": true,
-  "eos_token_id": 2,
-  "forced_eos_token_id": 2,
-  "max_length": 200,
-  "num_beams": 5,
-  "pad_token_id": 1,
+  "decoder_start_token_id": 0,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
   "transformers_version": "4.49.0"
 }