Add new SentenceTransformer model

README.md

@@ -5,38 +5,109 @@ tags:
 - feature-extraction
 - dense
 - generated_from_trainer
-- dataset_size:100000
+- dataset_size:90000
 - loss:MultipleNegativesRankingLoss
 base_model: prajjwal1/bert-small
 widget:
-- source_sentence: How do I polish my English skills?
+- source_sentence: How do I cope with my depression to keep my girlfriend?
   sentences:
-  - How can we polish English skills?
-  - Why should I move to Israel as a Jew?
-  - What are vitamins responsible for?
-- source_sentence: Can I use the Kozuka Gothic Pro font as a font-face on my web site?
+  - How do you cope with depression?
+  - How do I cope with my depression to keep my girlfriend?
+  - What does science say about crop circles?
+- source_sentence: Which is the best college for MBA in Delhi?
   sentences:
-  - Can I use the Kozuka Gothic Pro font as a font-face on my web site?
-  - Why are Google, Facebook, YouTube and other social networking sites banned in
-    China?
-  - What font is used in Bloomberg Terminal?
-- source_sentence: Is Quora the best Q&A site?
+  - Will time travel be possible in future?
+  - What will be the picture quality if a Standard STB is Connected to a Full HD 40"
+    Led TV?
+  - Which is the best college to do an MBA in Delhi?
+- source_sentence: What is poison mailbox?
   sentences:
-  - What was the best Quora question ever?
-  - Is Quora the best inquiry site?
-  - Where do I buy Oway hair products online?
-- source_sentence: How can I customize my walking speed on Google Maps?
+  - What are examples of homonyms with meanings and sentences?
+  - What is poison mailbox?
+  - I was born on 29 may 1994 in pakistan city lahore my name is Ali Fraz Virk what
+    is my horoscope in details plz?
+- source_sentence: What are the differences between eccentric and concentric contraction?
+    What are some examples?
   sentences:
-  - How do I bring back Google maps icon in my home screen?
-  - How many pages are there in all the Harry Potter books combined?
-  - How can I customize my walking speed on Google Maps?
-- source_sentence: DId something exist before the Big Bang?
+  - Why is it when I pass my crush he always looks down at his phone?
+  - How widely accepted are credit cards at small businesses and restaurants in Bahrain?
+  - What are the differences between a concentric and eccentric movement?
+- source_sentence: I've got an online coupon for Domino's pizza through the freecharge
+    app. Is it necessary to use that coupon only when I order online?
   sentences:
-  - How can I improve my memory problem?
-  - Where can I buy Fairy Tail Manga?
-  - Is there a scientific name for what existed before the Big Bang?
+  - Who played the character of 'Russ' in friends?
+  - How do you use Dominos India WalkIn coupon code?
+  - I've got an online coupon for Domino's pizza through the freecharge app. Is it
+    necessary to use that coupon only when I order online?
 pipeline_tag: sentence-similarity
 library_name: sentence-transformers
+metrics:
+- cosine_accuracy@1
+- cosine_accuracy@3
+- cosine_accuracy@5
+- cosine_precision@1
+- cosine_precision@3
+- cosine_precision@5
+- cosine_recall@1
+- cosine_recall@3
+- cosine_recall@5
+- cosine_ndcg@10
+- cosine_mrr@1
+- cosine_mrr@5
+- cosine_mrr@10
+- cosine_map@100
+model-index:
+- name: SentenceTransformer based on prajjwal1/bert-small
+  results:
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: val
+      type: val
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.9184
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.97
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.9852
+      name: Cosine Accuracy@5
+    - type: cosine_precision@1
+      value: 0.9184
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.3233333333333333
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.19703999999999997
+      name: Cosine Precision@5
+    - type: cosine_recall@1
+      value: 0.9184
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.97
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.9852
+      name: Cosine Recall@5
+    - type: cosine_ndcg@10
+      value: 0.9585962869405669
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@1
+      value: 0.9184
+      name: Cosine Mrr@1
+    - type: cosine_mrr@5
+      value: 0.9451033333333331
+      name: Cosine Mrr@5
+    - type: cosine_mrr@10
+      value: 0.9465657142857136
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.9469212791024237
+      name: Cosine Map@100
 ---
 
 # SentenceTransformer based on prajjwal1/bert-small
@@ -85,12 +156,12 @@ Then you can load this model and run inference.
 from sentence_transformers import SentenceTransformer
 
 # Download from the 🤗 Hub
-model = SentenceTransformer("sentence_transformers_model_id")
+model = SentenceTransformer("redis/model-a-baseline")
 # Run inference
 sentences = [
-    'DId something exist before the Big Bang?',
-    'Is there a scientific name for what existed before the Big Bang?',
-    'Where can I buy Fairy Tail Manga?',
+    "I've got an online coupon for Domino's pizza through the freecharge app. Is it necessary to use that coupon only when I order online?",
+    "I've got an online coupon for Domino's pizza through the freecharge app. Is it necessary to use that coupon only when I order online?",
+    'How do you use Dominos India WalkIn coupon code?',
 ]
 embeddings = model.encode(sentences)
 print(embeddings.shape)
@@ -99,9 +170,9 @@ print(embeddings.shape)
 # Get the similarity scores for the embeddings
 similarities = model.similarity(embeddings, embeddings)
 print(similarities)
-# tensor([[ 1.0000,  0.7596, -0.0398],
-#         [ 0.7596,  1.0000, -0.0308],
-#         [-0.0398, -0.0308,  1.0000]])
+# tensor([[1.0000, 1.0000, 0.3427],
+#         [1.0000, 1.0000, 0.3427],
+#         [0.3427, 0.3427, 1.0001]])
 ```
 
 <!--
@@ -128,6 +199,32 @@ You can finetune this model on your own dataset.
 *List how the model may foreseeably be misused and address what users ought not to do with the model.*
 -->
 
+## Evaluation
+
+### Metrics
+
+#### Information Retrieval
+
+* Dataset: `val`
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
+
+| Metric             | Value      |
+|:-------------------|:-----------|
+| cosine_accuracy@1  | 0.9184     |
+| cosine_accuracy@3  | 0.97       |
+| cosine_accuracy@5  | 0.9852     |
+| cosine_precision@1 | 0.9184     |
+| cosine_precision@3 | 0.3233     |
+| cosine_precision@5 | 0.197      |
+| cosine_recall@1    | 0.9184     |
+| cosine_recall@3    | 0.97       |
+| cosine_recall@5    | 0.9852     |
+| **cosine_ndcg@10** | **0.9586** |
+| cosine_mrr@1       | 0.9184     |
+| cosine_mrr@5       | 0.9451     |
+| cosine_mrr@10      | 0.9466     |
+| cosine_map@100     | 0.9469     |
+
 <!--
 ## Bias, Risks and Limitations
 
@@ -146,19 +243,45 @@ You can finetune this model on your own dataset.
 
 #### Unnamed Dataset
 
-* Size: 100,000 training samples
-* Columns: <code>sentence_0</code>, <code>sentence_1</code>, and <code>sentence_2</code>
+* Size: 90,000 training samples
+* Columns: <code>anchor</code>, <code>positive</code>, and <code>negative</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | anchor                                                                            | positive                                                                          | negative                                                                         |
+  |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|
+  | type    | string                                                                            | string                                                                            | string                                                                           |
+  | details | <ul><li>min: 6 tokens</li><li>mean: 15.63 tokens</li><li>max: 75 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 15.77 tokens</li><li>max: 75 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 16.5 tokens</li><li>max: 67 tokens</li></ul> |
+* Samples:
+  | anchor                                                   | positive                                                 | negative                                                                    |
+  |:---------------------------------------------------------|:---------------------------------------------------------|:----------------------------------------------------------------------------|
+  | <code>How long did it take to develop Pokémon GO?</code> | <code>How long did it take to develop Pokémon GO?</code> | <code>Can I take more than one gym in Pokémon GO?</code>                    |
+  | <code>How bad is 6/18 eyesight?</code>                   | <code>How bad is 6/18 eyesight?</code>                   | <code>How was bad eyesight dealt with in ancient and medieval times?</code> |
+  | <code>How can I do learn speaking English easily?</code> | <code>How can I learn speaking English easily?</code>    | <code>How do you hack an Instagram account?</code>                          |
+* Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
+  ```json
+  {
+      "scale": 20.0,
+      "similarity_fct": "cos_sim",
+      "gather_across_devices": false
+  }
+  ```
+
+### Evaluation Dataset
+
+#### Unnamed Dataset
+
+* Size: 5,000 evaluation samples
+* Columns: <code>anchor</code>, <code>positive</code>, and <code>negative</code>
 * Approximate statistics based on the first 1000 samples:
-  |         | sentence_0                                                                        | sentence_1                                                                       | sentence_2                                                                         |
-  |:--------|:----------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|
-  | type    | string                                                                            | string                                                                           | string                                                                             |
-  | details | <ul><li>min: 3 tokens</li><li>mean: 15.53 tokens</li><li>max: 59 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 15.5 tokens</li><li>max: 59 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 16.87 tokens</li><li>max: 128 tokens</li></ul> |
+  |         | anchor                                                                            | positive                                                                          | negative                                                                          |
+  |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
+  | type    | string                                                                            | string                                                                            | string                                                                            |
+  | details | <ul><li>min: 6 tokens</li><li>mean: 15.65 tokens</li><li>max: 49 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 15.69 tokens</li><li>max: 49 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 16.77 tokens</li><li>max: 67 tokens</li></ul> |
 * Samples:
-  | sentence_0                                                                              | sentence_1                                                                              | sentence_2                                                             |
-  |:----------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------------|:-----------------------------------------------------------------------|
-  | <code>Is there visitor entry facility in Jaipur airport. How much is the ticket?</code> | <code>Is there visitor entry facility in Jaipur airport. How much is the ticket?</code> | <code>How much is the airport tax in bogota?</code>                    |
-  | <code>Which concept is more important: good planning or hard work?</code>               | <code>Which concept is more important: good planning or hard work?</code>               | <code>What is important in life: luck or hard work?</code>             |
-  | <code>What is the most efficient way to make money?</code>                              | <code>How can I make my money make money?</code>                                        | <code>What can one learn about Quantum Mechanics in 10 minutes?</code> |
+  | anchor                                                                                                                                                             | positive                                                                                                                                                           | negative                                                                                       |
+  |:-------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------------------|
+  | <code>What's it like working in IT for Goldman Sachs?</code>                                                                                                       | <code>What's it like working in IT for Goldman Sachs?</code>                                                                                                       | <code>What is the work done at Goldman Sachs?</code>                                           |
+  | <code>Will time travel be possible in future?</code>                                                                                                               | <code>Is time travel still theorized as being possible?</code>                                                                                                     | <code>What are the things that would make you fail a Canadian immigration medical exam?</code> |
+  | <code>For creating a software based service for SME’s, we need to tie up with a bank. Need the best way to contact the right person in big banks like HDFC.</code> | <code>For creating a software based service for SME’s, we need to tie up with a bank. Need the best way to contact the right person in big banks like HDFC.</code> | <code>What does it feel like to be eaten alive by a Pachycephalosaurus?</code>                 |
 * Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
   ```json
   {
@@ -171,36 +294,49 @@ You can finetune this model on your own dataset.
 ### Training Hyperparameters
 #### Non-Default Hyperparameters
 
-- `per_device_train_batch_size`: 64
-- `per_device_eval_batch_size`: 64
+- `eval_strategy`: steps
+- `per_device_train_batch_size`: 256
+- `per_device_eval_batch_size`: 256
+- `learning_rate`: 2e-05
+- `weight_decay`: 0.001
+- `max_steps`: 3510
+- `warmup_ratio`: 0.1
 - `fp16`: True
-- `multi_dataset_batch_sampler`: round_robin
+- `dataloader_drop_last`: True
+- `dataloader_num_workers`: 1
+- `dataloader_prefetch_factor`: 1
+- `load_best_model_at_end`: True
+- `optim`: adamw_torch
+- `ddp_find_unused_parameters`: False
+- `push_to_hub`: True
+- `hub_model_id`: redis/model-a-baseline
+- `eval_on_start`: True
 
 #### All Hyperparameters
 <details><summary>Click to expand</summary>
 
 - `overwrite_output_dir`: False
 - `do_predict`: False
-- `eval_strategy`: no
+- `eval_strategy`: steps
 - `prediction_loss_only`: True
-- `per_device_train_batch_size`: 64
-- `per_device_eval_batch_size`: 64
+- `per_device_train_batch_size`: 256
+- `per_device_eval_batch_size`: 256
 - `per_gpu_train_batch_size`: None
 - `per_gpu_eval_batch_size`: None
 - `gradient_accumulation_steps`: 1
 - `eval_accumulation_steps`: None
 - `torch_empty_cache_steps`: None
-- `learning_rate`: 5e-05
-- `weight_decay`: 0.0
+- `learning_rate`: 2e-05
+- `weight_decay`: 0.001
 - `adam_beta1`: 0.9
 - `adam_beta2`: 0.999
 - `adam_epsilon`: 1e-08
-- `max_grad_norm`: 1
-- `num_train_epochs`: 3
-- `max_steps`: -1
+- `max_grad_norm`: 1.0
+- `num_train_epochs`: 3.0
+- `max_steps`: 3510
 - `lr_scheduler_type`: linear
 - `lr_scheduler_kwargs`: {}
-- `warmup_ratio`: 0.0
+- `warmup_ratio`: 0.1
 - `warmup_steps`: 0
 - `log_level`: passive
 - `log_level_replica`: warning
@@ -228,14 +364,14 @@ You can finetune this model on your own dataset.
 - `tpu_num_cores`: None
 - `tpu_metrics_debug`: False
 - `debug`: []
-- `dataloader_drop_last`: False
-- `dataloader_num_workers`: 0
-- `dataloader_prefetch_factor`: None
+- `dataloader_drop_last`: True
+- `dataloader_num_workers`: 1
+- `dataloader_prefetch_factor`: 1
 - `past_index`: -1
 - `disable_tqdm`: False
 - `remove_unused_columns`: True
 - `label_names`: None
-- `load_best_model_at_end`: False
+- `load_best_model_at_end`: True
 - `ignore_data_skip`: False
 - `fsdp`: []
 - `fsdp_min_num_params`: 0
@@ -245,23 +381,23 @@ You can finetune this model on your own dataset.
 - `parallelism_config`: None
 - `deepspeed`: None
 - `label_smoothing_factor`: 0.0
-- `optim`: adamw_torch_fused
+- `optim`: adamw_torch
 - `optim_args`: None
 - `adafactor`: False
 - `group_by_length`: False
 - `length_column_name`: length
 - `project`: huggingface
 - `trackio_space_id`: trackio
-- `ddp_find_unused_parameters`: None
+- `ddp_find_unused_parameters`: False
 - `ddp_bucket_cap_mb`: None
 - `ddp_broadcast_buffers`: False
 - `dataloader_pin_memory`: True
 - `dataloader_persistent_workers`: False
 - `skip_memory_metrics`: True
 - `use_legacy_prediction_loop`: False
-- `push_to_hub`: False
+- `push_to_hub`: True
 - `resume_from_checkpoint`: None
-- `hub_model_id`: None
+- `hub_model_id`: redis/model-a-baseline
 - `hub_strategy`: every_save
 - `hub_private_repo`: None
 - `hub_always_push`: False
@@ -288,31 +424,58 @@ You can finetune this model on your own dataset.
 - `neftune_noise_alpha`: None
 - `optim_target_modules`: None
 - `batch_eval_metrics`: False
-- `eval_on_start`: False
+- `eval_on_start`: True
 - `use_liger_kernel`: False
 - `liger_kernel_config`: None
 - `eval_use_gather_object`: False
 - `average_tokens_across_devices`: True
 - `prompts`: None
 - `batch_sampler`: batch_sampler
-- `multi_dataset_batch_sampler`: round_robin
+- `multi_dataset_batch_sampler`: proportional
 - `router_mapping`: {}
 - `learning_rate_mapping`: {}
 
 </details>
 
 ### Training Logs
-| Epoch  | Step | Training Loss |
-|:------:|:----:|:-------------:|
-| 0.3199 | 500  | 0.2284        |
-| 0.6398 | 1000 | 0.0571        |
-| 0.9597 | 1500 | 0.0486        |
-| 1.2796 | 2000 | 0.0378        |
-| 1.5995 | 2500 | 0.0367        |
-| 1.9194 | 3000 | 0.0338        |
-| 2.2393 | 3500 | 0.0327        |
-| 2.5592 | 4000 | 0.0285        |
-| 2.8791 | 4500 | 0.0285        |
+| Epoch  | Step | Training Loss | Validation Loss | val_cosine_ndcg@10 |
+|:------:|:----:|:-------------:|:---------------:|:------------------:|
+| 0      | 0    | -             | 1.6082          | 0.8775             |
+| 0.2849 | 100  | 1.2224        | 0.1085          | 0.9385             |
+| 0.5698 | 200  | 0.181         | 0.0711          | 0.9484             |
+| 0.8547 | 300  | 0.1372        | 0.0593          | 0.9521             |
+| 1.1396 | 400  | 0.1161        | 0.0548          | 0.9524             |
+| 1.4245 | 500  | 0.1005        | 0.0516          | 0.9535             |
+| 1.7094 | 600  | 0.1023        | 0.0491          | 0.9545             |
+| 1.9943 | 700  | 0.0885        | 0.0469          | 0.9556             |
+| 2.2792 | 800  | 0.0836        | 0.0453          | 0.9552             |
+| 2.5641 | 900  | 0.0782        | 0.0439          | 0.9562             |
+| 2.8490 | 1000 | 0.0745        | 0.0436          | 0.9572             |
+| 3.1339 | 1100 | 0.0732        | 0.0421          | 0.9570             |
+| 3.4188 | 1200 | 0.0688        | 0.0417          | 0.9577             |
+| 3.7037 | 1300 | 0.0687        | 0.0411          | 0.9576             |
+| 3.9886 | 1400 | 0.07          | 0.0412          | 0.9573             |
+| 4.2735 | 1500 | 0.0635        | 0.0402          | 0.9578             |
+| 4.5584 | 1600 | 0.0638        | 0.0397          | 0.9575             |
+| 4.8433 | 1700 | 0.0613        | 0.0394          | 0.9579             |
+| 5.1282 | 1800 | 0.0625        | 0.0388          | 0.9584             |
+| 5.4131 | 1900 | 0.0585        | 0.0382          | 0.9586             |
+| 5.6980 | 2000 | 0.0594        | 0.0379          | 0.9585             |
+| 5.9829 | 2100 | 0.0566        | 0.0377          | 0.9584             |
+| 6.2678 | 2200 | 0.0545        | 0.0376          | 0.9583             |
+| 6.5527 | 2300 | 0.0535        | 0.0376          | 0.9580             |
+| 6.8376 | 2400 | 0.0573        | 0.0373          | 0.9584             |
+| 7.1225 | 2500 | 0.0528        | 0.0373          | 0.9583             |
+| 7.4074 | 2600 | 0.053         | 0.0371          | 0.9587             |
+| 7.6923 | 2700 | 0.0528        | 0.0368          | 0.9587             |
+| 7.9772 | 2800 | 0.0531        | 0.0366          | 0.9585             |
+| 8.2621 | 2900 | 0.0532        | 0.0365          | 0.9586             |
+| 8.5470 | 3000 | 0.0516        | 0.0365          | 0.9584             |
+| 8.8319 | 3100 | 0.0509        | 0.0364          | 0.9585             |
+| 9.1168 | 3200 | 0.0544        | 0.0363          | 0.9587             |
+| 9.4017 | 3300 | 0.0505        | 0.0364          | 0.9585             |
+| 9.6866 | 3400 | 0.052         | 0.0363          | 0.9587             |
+| 9.9715 | 3500 | 0.0536        | 0.0362          | 0.9586             |
 
 
 ### Framework Versions