Update README.md

README.md

@@ -10,21 +10,51 @@ tags:
 - pythorch
 - finetuning
 ---
-XLM-RoBERTa (base-sized model)
-XLM-RoBERTa model pre-trained on 2.5TB of filtered CommonCrawl data containing 100 languages. It was introduced in the paper Unsupervised Cross-lingual Representation Learning at Scale by Conneau et al. and first released in this repository.
+# XLM-RoBERTa (base-sized model) Fine-tuned for ticket classification
 
-Disclaimer: The team releasing XLM-RoBERTa did not write a model card for this model so this model card has been written by the Hugging Face team.
+This model has already been fine-tuned for the classification of IT tickets in English and Italian, you can use XLM-RoBERTa basic (no fine-tuned) at the following link: 
+https://huggingface.co/FacebookAI/xlm-roberta-base
 
-Model description
-XLM-RoBERTa is a multilingual version of RoBERTa. It is pre-trained on 2.5TB of filtered CommonCrawl data containing 100 languages.
+## Fine-Tuned Model description
+
+The fine tuned was done to recognize 18 classes related to the following macros: 
+* Database 3 class
+* Hardware 6 class
+* Inquiry/help 2 class
+* Network 5 class
+* software 2 class
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/6491c6dc3e081ef54fb4ded4/_Goanoewc1oe9JIrrs0eE.png)
+
+The data was generated using GPT 3.5-turbo and does not contain any sensitive data. 
+A total of 100 examples were generated for each class, all different from each other and not translated, 50 in Italian and 50 in English.
+
+The dataset contains a total of 1800 ticket texts, divided into the following numbers: 
+- Training 1440 (80%)
+- Validation 180 (10%)
+- Test 180 (10%)
+
+Fine-tuning is performed according to the following parameters: 
+* Batch size = 16
+* Epochs = 6
+* Learning rate = 2e-5
+* Weight decay = 0.01
 
-RoBERTa is a transformers model pretrained on a large corpus in a self-supervised fashion. This means it was pretrained on the raw texts only, with no humans labelling them in any way (which is why it can use lots of publicly available data) with an automatic process to generate inputs and labels from those texts.
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/6491c6dc3e081ef54fb4ded4/Laqhs1R2c45PwYZFh-4TF.png)
+
+## Model description
+
+XLM-RoBERTa model pre-trained on 2.5TB of filtered CommonCrawl data containing 100 languages. 
+It was introduced in the paper Unsupervised Cross-lingual Representation Learning at Scale by Conneau et al. and first released in this repository.
+
+XLM-RoBERTa is a multilingual version of RoBERTa. It is pre-trained on 2.5TB of filtered CommonCrawl data containing 100 languages.
+RoBERTa is a transformers model pretrained on a large corpus in a self-supervised fashion. 
+This means it was pretrained on the raw texts only, with no humans labelling them in any way (which is why it can use lots of publicly available data) with an automatic process to generate inputs and labels from those texts.
 
 More precisely, it was pretrained with the Masked language modeling (MLM) objective. Taking a sentence, the model randomly masks 15% of the words in the input then run the entire masked sentence through the model and has to predict the masked words. This is different from traditional recurrent neural networks (RNNs) that usually see the words one after the other, or from autoregressive models like GPT which internally mask the future tokens. It allows the model to learn a bidirectional representation of the sentence.
 
 This way, the model learns an inner representation of 100 languages that can then be used to extract features useful for downstream tasks: if you have a dataset of labeled sentences for instance, you can train a standard classifier using the features produced by the XLM-RoBERTa model as inputs.
 
-Intended uses & limitations
-You can use the raw model for masked language modeling, but it's mostly intended to be fine-tuned on a downstream task. See the model hub to look for fine-tuned versions on a task that interests you.
-
-Note that this model is primarily aimed at being fine-tuned on tasks that use the whole sentence (potentially masked) to make decisions, such as sequence classification, token classification or question answering. For tasks such as text generation, you should look at models like GPT2.
+### Notes:
+- This model is primarily aimed at being fine-tuned on tasks that use the whole sentence (potentially masked) to make decisions, such as sequence classification, token classification or question answering, not for text generation.
+- This model is fine-tuned for classification of ticket