First version of the model

README.md

@@ -6,7 +6,7 @@ tags:
 datasets:
 - dcep europarl jrc-acquis
 widget:
-- text: "Approvazione dei processi verbali delle riunioni del:"
+- text: "Estensione del campo di applicazione del regolamento (UE) del Parlamento europeo e del Consiglio sul trasporto transfrontaliero professionale su strada del contante in euro tra gli Stati membri dell’area dell’euro"
 
 ---
 
@@ -38,7 +38,7 @@ tokenizer=AutoTokenizer.from_pretrained(pretrained_model_name_or_path = "SEBIS/l
     device=0
 )
 
-it_text = "Approvazione dei processi verbali delle riunioni del:"
+it_text = "Estensione del campo di applicazione del regolamento (UE) del Parlamento europeo e del Consiglio sul trasporto transfrontaliero professionale su strada del contante in euro tra gli Stati membri dell’area dell’euro"
 
 pipeline([it_text], max_length=512)
 ```
@@ -49,10 +49,14 @@ The legal_t5_small_trans_it_en model was trained on [JRC-ACQUIS](https://wt-publ
 
 ## Training procedure
 
+An unigram model trained with 88M lines of text from the parallel corpus (of all possible language pairs) to get the vocabulary (with byte pair encoding), which is used with this model.
+
+The model was trained on a single TPU Pod V3-8 for 250K steps in total, using sequence length 512 (batch size 4096). It has a total of approximately 220M parameters and was trained using the encoder-decoder architecture. The optimizer used is AdaFactor with inverse square root learning rate schedule for pre-training.
+
 ### Preprocessing
 
 ### Pretraining
-An unigram model with 88M parameters is trained over the complete parallel corpus to get the vocabulary (with byte pair encoding), which is used with this model.
+
 
 
 ## Evaluation results
@@ -63,7 +67,7 @@ Test results :
 
 | Model | BLEU score |
 |:-----:|:-----:|
-|   legal_t5_small_trans_it_en | 50.068|
+|   legal_t5_small_trans_it_en | 50.07|
 
 
 ### BibTeX entry and citation info