Corrected README

README.md

@@ -1,126 +1,59 @@
 ---
-pipeline_tag: sentence-similarity
+language: es
+datasets:
+- stsb_multi_mt
 tags:
-- sentence-transformers
-- feature-extraction
 - sentence-similarity
-- transformers
+- sentence-transformers
 ---
 
-# {MODEL_NAME}
-
-This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.
-
-<!--- Describe your model here -->
-
-## Usage (Sentence-Transformers)
-
-Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
-
-```
-pip install -U sentence-transformers
-```
-
-Then you can use the model like this:
-
-```python
-from sentence_transformers import SentenceTransformer
-sentences = ["This is an example sentence", "Each sentence is converted"]
-
-model = SentenceTransformer('{MODEL_NAME}')
-embeddings = model.encode(sentences)
-print(embeddings)
-```
-
 
+This is a test model that was fine-tuned using the Spanish datasets from [stsb_multi_mt](https://huggingface.co/datasets/stsb_multi_mt) in order to understand and benchmark STS models.
 
-## Usage (HuggingFace Transformers)
-Without [sentence-transformers](https://www.SBERT.net), you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.
+## Model and training data description
 
-```python
-from transformers import AutoTokenizer, AutoModel
-import torch
+This model was built taking `distiluse-base-multilingual-cased-v1` and training it on a Semantic Textual Similarity task using a modified version of the training script for STS from Sentece Transformers (the modified script is included in the repo). It was trained using the Spanish datasets from [stsb_multi_mt](https://huggingface.co/datasets/stsb_multi_mt) which are the STSBenchmark datasets automatically translated to other languages using deepl.com. Refer to the dataset repository for more details.
 
+## Intended uses & limitations
 
-#Mean Pooling - Take attention mask into account for correct averaging
-def mean_pooling(model_output, attention_mask):
-    token_embeddings = model_output[0] #First element of model_output contains all token embeddings
-    input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
-    return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)
+This model was built just as a proof-of-concept on STS fine-tuning using Spanish data and no specific use other than getting a sense on how this training works.
 
+## How to use
 
-# Sentences we want sentence embeddings for
-sentences = ['This is an example sentence', 'Each sentence is converted']
+You may use it as any other STS trained model to extract sentence embeddings. Check Sentence Transformers documentation. 
 
-# Load model from HuggingFace Hub
-tokenizer = AutoTokenizer.from_pretrained('{MODEL_NAME}')
-model = AutoModel.from_pretrained('{MODEL_NAME}')
+## Training procedure
 
-# Tokenize sentences
-encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
+This model was trained using this [Colab Notebook](https://colab.research.google.com/drive/1ZNjDMFdy_lKhnD9BtbqzSbQ4LNz638ZA?usp=sharing)
 
-# Compute token embeddings
-with torch.no_grad():
-    model_output = model(**encoded_input)
+## Evaluation results
 
-# Perform pooling. In this case, max pooling.
-sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
+Evaluating `distiluse-base-multilingual-cased-v1` on the Spanish test dataset before training results in:
 
-print("Sentence embeddings:")
-print(sentence_embeddings)
 ```
-
-
-
-## Evaluation Results
-
-<!--- Describe how your model was evaluated -->
-
-For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name={MODEL_NAME})
-
-
-## Training
-The model was trained with the parameters:
-
-**DataLoader**:
-
-`torch.utils.data.dataloader.DataLoader` of length 360 with parameters:
-```
-{'batch_size': 16, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}
+2021-07-06 17:44:46 - EmbeddingSimilarityEvaluator: Evaluating the model on  dataset:
+2021-07-06 17:45:00 - Cosine-Similarity :	Pearson: 0.7662	Spearman: 0.7583
+2021-07-06 17:45:00 - Manhattan-Distance:	Pearson: 0.7805	Spearman: 0.7772
+2021-07-06 17:45:00 - Euclidean-Distance:	Pearson: 0.7816	Spearman: 0.7778
+2021-07-06 17:45:00 - Dot-Product-Similarity:	Pearson: 0.6610	Spearman: 0.6536
 ```
 
-**Loss**:
+While the fine-tuned version with the defaults of the training script and the Spanish training dataset results in:
 
-`sentence_transformers.losses.CosineSimilarityLoss.CosineSimilarityLoss` 
-
-Parameters of the fit()-Method:
 ```
-{
-    "callback": null,
-    "epochs": 4,
-    "evaluation_steps": 1000,
-    "evaluator": "sentence_transformers.evaluation.EmbeddingSimilarityEvaluator.EmbeddingSimilarityEvaluator",
-    "max_grad_norm": 1,
-    "optimizer_class": "<class 'transformers.optimization.AdamW'>",
-    "optimizer_params": {
-        "lr": 2e-05
-    },
-    "scheduler": "WarmupLinear",
-    "steps_per_epoch": null,
-    "warmup_steps": 144,
-    "weight_decay": 0.01
-}
+2021-07-06 17:49:22 - EmbeddingSimilarityEvaluator: Evaluating the model on stsb-multi-mt-test dataset:
+2021-07-06 17:49:24 - Cosine-Similarity :	Pearson: 0.8265	Spearman: 0.8207
+2021-07-06 17:49:24 - Manhattan-Distance:	Pearson: 0.8131	Spearman: 0.8190
+2021-07-06 17:49:24 - Euclidean-Distance:	Pearson: 0.8129	Spearman: 0.8190
+2021-07-06 17:49:24 - Dot-Product-Similarity:	Pearson: 0.7773	Spearman: 0.7692
 ```
 
+In our [STS Evaluation repository](https://github.com/eduardofv/sts_eval) we compare the performance of this model with other models from Sentence Transformers and Tensorflow Hub using the standard STSBenchmark and the 2017 STSBenchmark Task 3 for Spanish.
 
-## Full Model Architecture
-```
-SentenceTransformer(
-  (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: DistilBertModel 
-  (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False})
-)
-```
 
-## Citing & Authors
+## Resources
 
-<!--- Describe where people can find more information -->
+- Training dataset [stsb_multi_mt](https://huggingface.co/datasets/stsb_multi_mt)
+- Sentence Transformers [Semantic Textual Similarity](https://www.sbert.net/examples/training/sts/README.html)
+- Check [sts_eval](https://github.com/eduardofv/sts_eval) for a comparison with Tensorflow and Sentence-Transformers models
+- Check the [development environment to run the scripts and evaluation](https://github.com/eduardofv/ai-denv)