update model card README.md

README.md

@@ -2,6 +2,8 @@
 license: apache-2.0
 tags:
 - generated_from_trainer
+metrics:
+- bleu
 model-index:
 - name: mt5-aym-lex
   results: []
@@ -12,7 +14,12 @@ should probably proofread and complete it, then remove this comment. -->
 
 # mt5-aym-lex
 
-This model is a fine-tuned version of [google/mt5-base](https://huggingface.co/google/mt5-base) on the None dataset.
+This model is a fine-tuned version of [alvations/mt5-aym-lex](https://huggingface.co/alvations/mt5-aym-lex) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1844
+- Chrf: 24.2586
+- Bleu: 2.9344
+- Gen Len: 17.5005
 
 ## Model description
 
@@ -38,11 +45,18 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 500
-- training_steps: 200000
+- training_steps: 20000
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss | Chrf    | Bleu   | Gen Len |
+|:-------------:|:-----:|:-----:|:---------------:|:-------:|:------:|:-------:|
+| 0.067         | 4.86  | 20000 | 0.1844          | 24.2586 | 2.9344 | 17.5005 |
+
 
 ### Framework versions
 
-- Transformers 4.28.1
+- Transformers 4.29.2
 - Pytorch 2.0.0+cu118
 - Datasets 2.12.0
 - Tokenizers 0.13.3