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/mt5-small
 tags:
 - simplification
 - generated_from_trainer
@@ -10,10 +10,6 @@ metrics:
 model-index:
 - name: mbart-neutralization
   results: []
-language:
-- es
-datasets:
-- somosnlp-hackathon-2022/neutral-es
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -21,11 +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 somosnlp-hackathon-2022/neutral-es dataset.
+This model is a fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0161
-- Bleu: 98.4007
-- Gen Len: 18.5625
+- Loss: 0.3279
+- Bleu: 72.1306
+- Gen Len: 17.1875
 
 ## Model description
 
@@ -56,8 +52,8 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Bleu    | Gen Len |
 |:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|
-| No log        | 1.0   | 440  | 0.0411          | 97.9038 | 18.7396 |
-| 0.2238        | 2.0   | 880  | 0.0161          | 98.4007 | 18.5625 |
+| No log        | 1.0   | 440  | 0.3966          | 66.1686 | 16.4583 |
+| 0.9189        | 2.0   | 880  | 0.3279          | 72.1306 | 17.1875 |
 
 
 ### Framework versions
@@ -65,4 +61,4 @@ The following hyperparameters were used during training:
 - Transformers 4.51.2
 - Pytorch 2.10.0+cu128
 - Datasets 4.0.0
-- Tokenizers 0.21.4
+- Tokenizers 0.21.4

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": "4.51.2"
 }