Training in progress, step 10000

1_Pooling/config.json

@@ -1,7 +1,7 @@
 {
-    "word_embedding_dimension": 384,
-    "pooling_mode_cls_token": false,
-    "pooling_mode_mean_tokens": true,
+    "word_embedding_dimension": 512,
+    "pooling_mode_cls_token": true,
+    "pooling_mode_mean_tokens": false,
     "pooling_mode_max_tokens": false,
     "pooling_mode_mean_sqrt_len_tokens": false,
     "pooling_mode_weightedmean_tokens": false,

Information-Retrieval_evaluation_val_results.csv

@@ -8,3 +8,4 @@ epoch,steps,cosine-Accuracy@1,cosine-Accuracy@3,cosine-Accuracy@5,cosine-Precisi
 -1,-1,0.76535,0.820425,0.8436,0.76535,0.76535,0.27347499999999997,0.820425,0.16872,0.8436,0.76535,0.7948791666666619,0.798946091269839,0.8168396181783457,0.8022530766472562
 -1,-1,0.82975,0.903025,0.9308,0.82975,0.82975,0.3010083333333333,0.903025,0.18616000000000002,0.9308,0.82975,0.8688179166666645,0.8729221527777756,0.894185079953941,0.8751251735048098
 -1,-1,0.8288,0.899775,0.925775,0.8288,0.8288,0.29992499999999994,0.899775,0.185155,0.925775,0.8288,0.8661879166666627,0.8703450396825356,0.8910978019383597,0.8726020537429935
+-1,-1,0.826575,0.900725,0.92805,0.826575,0.826575,0.30024166666666663,0.900725,0.18561000000000002,0.92805,0.826575,0.8658308333333287,0.8701137103174557,0.891705546917102,0.8723575730144177

README.md

@@ -5,124 +5,51 @@ tags:
 - feature-extraction
 - dense
 - generated_from_trainer
-- dataset_size:359997
+- dataset_size:100000
 - loss:MultipleNegativesRankingLoss
-base_model: thenlper/gte-small
+base_model: prajjwal1/bert-small
 widget:
-- source_sentence: When do you use Ms. or Mrs.? Is one for a married woman and one
-    for one that's not married? Which one is for what?
+- source_sentence: How do I polish my English skills?
   sentences:
-  - When do you use Ms. or Mrs.? Is one for a married woman and one for one that's
-    not married? Which one is for what?
-  - Nations that do/does otherwise? Which one do I use?
-  - Why don't bikes have a gear indicator?
-- source_sentence: Which ointment is applied to the face of UFC fighters at the commencement
-    of a bout? What does it do?
+  - 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?
   sentences:
-  - How can I save a Snapchat video that others posted?
-  - Which ointment is applied to the face of UFC fighters at the commencement of a
-    bout? What does it do?
-  - How do I get the body of a UFC Fighter?
-- source_sentence: Do you love the life you live?
+  - 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?
   sentences:
-  - Can I do shoulder and triceps workout on same day? What other combinations like
-    this can I do?
-  - Do you love the life you're living?
-  - Where can you find an online TI-84 calculator?
-- source_sentence: Ordered food on Swiggy 3 days ago.After accepting my money, said
-    no more on Menu! When if ever will I atleast get refund in cr card a/c?
+  - 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?
   sentences:
-  - Is getting to the Tel Aviv airport to catch a 5:30 AM flight very expensive?
-  - How do I die and make it look like an accident?
-  - Ordered food on Swiggy 3 days ago.After accepting my money, said no more on Menu!
-    When if ever will I atleast get refund in cr card a/c?
-- source_sentence: How do you earn money on Quora?
+  - 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?
   sentences:
-  - What is a cheap healthy diet I can keep the same and eat every day?
-  - What are some things new employees should know going into their first day at Maximus?
-  - What is the best way to make money on Quora?
+  - 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?
 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 thenlper/gte-small
-  results:
-  - task:
-      type: information-retrieval
-      name: Information Retrieval
-    dataset:
-      name: val
-      type: val
-    metrics:
-    - type: cosine_accuracy@1
-      value: 0.826575
-      name: Cosine Accuracy@1
-    - type: cosine_accuracy@3
-      value: 0.900725
-      name: Cosine Accuracy@3
-    - type: cosine_accuracy@5
-      value: 0.92805
-      name: Cosine Accuracy@5
-    - type: cosine_precision@1
-      value: 0.826575
-      name: Cosine Precision@1
-    - type: cosine_precision@3
-      value: 0.30024166666666663
-      name: Cosine Precision@3
-    - type: cosine_precision@5
-      value: 0.18561000000000002
-      name: Cosine Precision@5
-    - type: cosine_recall@1
-      value: 0.826575
-      name: Cosine Recall@1
-    - type: cosine_recall@3
-      value: 0.900725
-      name: Cosine Recall@3
-    - type: cosine_recall@5
-      value: 0.92805
-      name: Cosine Recall@5
-    - type: cosine_ndcg@10
-      value: 0.891705546917102
-      name: Cosine Ndcg@10
-    - type: cosine_mrr@1
-      value: 0.826575
-      name: Cosine Mrr@1
-    - type: cosine_mrr@5
-      value: 0.8658308333333287
-      name: Cosine Mrr@5
-    - type: cosine_mrr@10
-      value: 0.8701137103174557
-      name: Cosine Mrr@10
-    - type: cosine_map@100
-      value: 0.8723575730144177
-      name: Cosine Map@100
 ---
 
-# SentenceTransformer based on thenlper/gte-small
+# SentenceTransformer based on prajjwal1/bert-small
 
-This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [thenlper/gte-small](https://huggingface.co/thenlper/gte-small). It maps sentences & paragraphs to a 384-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [prajjwal1/bert-small](https://huggingface.co/prajjwal1/bert-small). It maps sentences & paragraphs to a 512-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
 
 ## Model Details
 
 ### Model Description
 - **Model Type:** Sentence Transformer
-- **Base model:** [thenlper/gte-small](https://huggingface.co/thenlper/gte-small) <!-- at revision 17e1f347d17fe144873b1201da91788898c639cd -->
+- **Base model:** [prajjwal1/bert-small](https://huggingface.co/prajjwal1/bert-small) <!-- at revision 0ec5f86f27c1a77d704439db5e01c307ea11b9d4 -->
 - **Maximum Sequence Length:** 128 tokens
-- **Output Dimensionality:** 384 dimensions
+- **Output Dimensionality:** 512 dimensions
 - **Similarity Function:** Cosine Similarity
 <!-- - **Training Dataset:** Unknown -->
 <!-- - **Language:** Unknown -->
@@ -139,8 +66,7 @@ This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [t
 ```
 SentenceTransformer(
   (0): Transformer({'max_seq_length': 128, 'do_lower_case': False, 'architecture': 'BertModel'})
-  (1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
-  (2): Normalize()
+  (1): Pooling({'word_embedding_dimension': 512, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
 )
 ```
 
@@ -159,23 +85,23 @@ Then you can load this model and run inference.
 from sentence_transformers import SentenceTransformer
 
 # Download from the 🤗 Hub
-model = SentenceTransformer("redis/model-a-baseline")
+model = SentenceTransformer("sentence_transformers_model_id")
 # Run inference
 sentences = [
-    'How do you earn money on Quora?',
-    'What is the best way to make money on Quora?',
-    'What are some things new employees should know going into their first day at Maximus?',
+    '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?',
 ]
 embeddings = model.encode(sentences)
 print(embeddings.shape)
-# [3, 384]
+# [3, 512]
 
 # Get the similarity scores for the embeddings
 similarities = model.similarity(embeddings, embeddings)
 print(similarities)
-# tensor([[1.0000, 0.9976, 0.0376],
-#         [0.9976, 1.0000, 0.0418],
-#         [0.0376, 0.0418, 0.9999]])
+# tensor([[ 1.0000,  0.7596, -0.0398],
+#         [ 0.7596,  1.0000, -0.0308],
+#         [-0.0398, -0.0308,  1.0000]])
 ```
 
 <!--
@@ -202,32 +128,6 @@ 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  | 0.8266     |
-| cosine_accuracy@3  | 0.9007     |
-| cosine_accuracy@5  | 0.9281     |
-| cosine_precision@1 | 0.8266     |
-| cosine_precision@3 | 0.3002     |
-| cosine_precision@5 | 0.1856     |
-| cosine_recall@1    | 0.8266     |
-| cosine_recall@3    | 0.9007     |
-| cosine_recall@5    | 0.9281     |
-| **cosine_ndcg@10** | **0.8917** |
-| cosine_mrr@1       | 0.8266     |
-| cosine_mrr@5       | 0.8658     |
-| cosine_mrr@10      | 0.8701     |
-| cosine_map@100     | 0.8724     |
-
 <!--
 ## Bias, Risks and Limitations
 
@@ -246,49 +146,23 @@ You can finetune this model on your own dataset.
 
 #### Unnamed Dataset
 
-* Size: 359,997 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: 4 tokens</li><li>mean: 15.46 tokens</li><li>max: 49 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 15.52 tokens</li><li>max: 49 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 16.99 tokens</li><li>max: 128 tokens</li></ul> |
-* Samples:
-  | anchor                                                                          | positive                                                                                             | negative                                                                                                                 |
-  |:--------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------------------------|
-  | <code>Shall I upgrade my iPhone 5s to iOS 10 final version?</code>              | <code>Should I upgrade an iPhone 5s to iOS 10?</code>                                                | <code>Whether extension of CA-articleship is to be served at same firm/company?</code>                                   |
-  | <code>Is Donald Trump really going to be the president of United States?</code> | <code>Do you think Donald Trump could conceivably be the next President of the United States?</code> | <code>Since solid carbon dioxide is dry ice and incredibly cold, why doesn't it have an effect on global warming?</code> |
-  | <code>What are real tips to improve work life balance?</code>                   | <code>What are the best ways to create a work life balance?</code>                                   | <code>How do you open a briefcase combination lock without the combination?</code>                                       |
-* Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
-  ```json
-  {
-      "scale": 7.0,
-      "similarity_fct": "cos_sim",
-      "gather_across_devices": false
-  }
-  ```
-
-### Evaluation Dataset
-
-#### Unnamed Dataset
-
-* Size: 40,000 evaluation samples
-* Columns: <code>anchor</code>, <code>positive</code>, and <code>negative</code>
+* Size: 100,000 training samples
+* Columns: <code>sentence_0</code>, <code>sentence_1</code>, and <code>sentence_2</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: 15.71 tokens</li><li>max: 65 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 15.79 tokens</li><li>max: 65 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 16.97 tokens</li><li>max: 78 tokens</li></ul> |
+  |         | 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> |
 * Samples:
-  | anchor                                                                                                            | positive                                                                                                          | negative                                                                                                                                  |
-  |:------------------------------------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------------------------------------------------|
-  | <code>Why were feathered dinosaur fossils only found in the last 20 years?</code>                                 | <code>Why were feathered dinosaur fossils only found in the last 20 years?</code>                                 | <code>Why are only few people aware that many dinosaurs had feathers?</code>                                                              |
-  | <code>If FOX News is the conservative news station, which cable news network is for liberals/progressives?</code> | <code>If FOX News is the conservative news station, which cable news network is for liberals/progressives?</code> | <code>How much did Fox News and conservative leaning media networks stoke the anger that contributed to Donald Trump's popularity?</code> |
-  | <code>How can guys last longer during sex?</code>                                                                 | <code>How do I last longer in sex?</code>                                                                         | <code>What is a permanent solution for rough and puffy hair?</code>                                                                       |
+  | 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> |
 * Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
   ```json
   {
-      "scale": 7.0,
+      "scale": 20.0,
       "similarity_fct": "cos_sim",
       "gather_across_devices": false
   }
@@ -297,49 +171,36 @@ You can finetune this model on your own dataset.
 ### Training Hyperparameters
 #### Non-Default Hyperparameters
 
-- `eval_strategy`: steps
-- `per_device_train_batch_size`: 128
-- `per_device_eval_batch_size`: 128
-- `learning_rate`: 0.0002
-- `weight_decay`: 0.0001
-- `max_steps`: 5000
-- `warmup_ratio`: 0.1
+- `per_device_train_batch_size`: 64
+- `per_device_eval_batch_size`: 64
 - `fp16`: True
-- `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
+- `multi_dataset_batch_sampler`: round_robin
 
 #### All Hyperparameters
 <details><summary>Click to expand</summary>
 
 - `overwrite_output_dir`: False
 - `do_predict`: False
-- `eval_strategy`: steps
+- `eval_strategy`: no
 - `prediction_loss_only`: True
-- `per_device_train_batch_size`: 128
-- `per_device_eval_batch_size`: 128
+- `per_device_train_batch_size`: 64
+- `per_device_eval_batch_size`: 64
 - `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`: 0.0002
-- `weight_decay`: 0.0001
+- `learning_rate`: 5e-05
+- `weight_decay`: 0.0
 - `adam_beta1`: 0.9
 - `adam_beta2`: 0.999
 - `adam_epsilon`: 1e-08
-- `max_grad_norm`: 1.0
-- `num_train_epochs`: 3.0
-- `max_steps`: 5000
+- `max_grad_norm`: 1
+- `num_train_epochs`: 3
+- `max_steps`: -1
 - `lr_scheduler_type`: linear
 - `lr_scheduler_kwargs`: {}
-- `warmup_ratio`: 0.1
+- `warmup_ratio`: 0.0
 - `warmup_steps`: 0
 - `log_level`: passive
 - `log_level_replica`: warning
@@ -367,14 +228,14 @@ You can finetune this model on your own dataset.
 - `tpu_num_cores`: None
 - `tpu_metrics_debug`: False
 - `debug`: []
-- `dataloader_drop_last`: True
-- `dataloader_num_workers`: 1
-- `dataloader_prefetch_factor`: 1
+- `dataloader_drop_last`: False
+- `dataloader_num_workers`: 0
+- `dataloader_prefetch_factor`: None
 - `past_index`: -1
 - `disable_tqdm`: False
 - `remove_unused_columns`: True
 - `label_names`: None
-- `load_best_model_at_end`: True
+- `load_best_model_at_end`: False
 - `ignore_data_skip`: False
 - `fsdp`: []
 - `fsdp_min_num_params`: 0
@@ -384,23 +245,23 @@ You can finetune this model on your own dataset.
 - `parallelism_config`: None
 - `deepspeed`: None
 - `label_smoothing_factor`: 0.0
-- `optim`: adamw_torch
+- `optim`: adamw_torch_fused
 - `optim_args`: None
 - `adafactor`: False
 - `group_by_length`: False
 - `length_column_name`: length
 - `project`: huggingface
 - `trackio_space_id`: trackio
-- `ddp_find_unused_parameters`: False
+- `ddp_find_unused_parameters`: None
 - `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`: True
+- `push_to_hub`: False
 - `resume_from_checkpoint`: None
-- `hub_model_id`: redis/model-a-baseline
+- `hub_model_id`: None
 - `hub_strategy`: every_save
 - `hub_private_repo`: None
 - `hub_always_push`: False
@@ -427,43 +288,31 @@ You can finetune this model on your own dataset.
 - `neftune_noise_alpha`: None
 - `optim_target_modules`: None
 - `batch_eval_metrics`: False
-- `eval_on_start`: True
+- `eval_on_start`: False
 - `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`: proportional
+- `multi_dataset_batch_sampler`: round_robin
 - `router_mapping`: {}
 - `learning_rate_mapping`: {}
 
 </details>
 
 ### Training Logs
-| Epoch  | Step | Training Loss | Validation Loss | val_cosine_ndcg@10 |
-|:------:|:----:|:-------------:|:---------------:|:------------------:|
-| 0      | 0    | -             | 3.6640          | 0.8926             |
-| 0.0889 | 250  | 1.2618        | 0.4304          | 0.8898             |
-| 0.1778 | 500  | 0.5222        | 0.4138          | 0.8886             |
-| 0.2667 | 750  | 0.4927        | 0.3987          | 0.8885             |
-| 0.3556 | 1000 | 0.4737        | 0.3942          | 0.8886             |
-| 0.4445 | 1250 | 0.4591        | 0.3874          | 0.8883             |
-| 0.5334 | 1500 | 0.4547        | 0.3825          | 0.8890             |
-| 0.6223 | 1750 | 0.4468        | 0.3771          | 0.8902             |
-| 0.7112 | 2000 | 0.4398        | 0.3750          | 0.8900             |
-| 0.8001 | 2250 | 0.4331        | 0.3715          | 0.8905             |
-| 0.8890 | 2500 | 0.4303        | 0.3682          | 0.8910             |
-| 0.9780 | 2750 | 0.4252        | 0.3656          | 0.8906             |
-| 1.0669 | 3000 | 0.4071        | 0.3621          | 0.8904             |
-| 1.1558 | 3250 | 0.4006        | 0.3605          | 0.8901             |
-| 1.2447 | 3500 | 0.3972        | 0.3592          | 0.8906             |
-| 1.3336 | 3750 | 0.3951        | 0.3573          | 0.8916             |
-| 1.4225 | 4000 | 0.3925        | 0.3552          | 0.8913             |
-| 1.5114 | 4250 | 0.3912        | 0.3536          | 0.8917             |
-| 1.6003 | 4500 | 0.3905        | 0.3530          | 0.8915             |
-| 1.6892 | 4750 | 0.3881        | 0.3519          | 0.8915             |
-| 1.7781 | 5000 | 0.3889        | 0.3512          | 0.8917             |
+| 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        |
 
 
 ### Framework Versions

eval/Information-Retrieval_evaluation_val_results.csv

@@ -755,3 +755,44 @@ epoch,steps,cosine-Accuracy@1,cosine-Accuracy@3,cosine-Accuracy@5,cosine-Precisi
 1.600284495021337,4500,0.826325,0.90075,0.927975,0.826325,0.826325,0.30024999999999996,0.90075,0.18559500000000004,0.927975,0.826325,0.8657179166666625,0.869968283730155,0.8915372597597095,0.872218739585088
 1.689189189189189,4750,0.8262,0.9006,0.92795,0.8262,0.8262,0.3001999999999999,0.9006,0.18559000000000006,0.92795,0.8262,0.8656516666666626,0.8699246726190432,0.8915453849606725,0.8721779867768037
 1.7780938833570412,5000,0.826575,0.900725,0.92805,0.826575,0.826575,0.30024166666666663,0.900725,0.18561000000000002,0.92805,0.826575,0.8658308333333287,0.8701137103174557,0.891705546917102,0.8723575730144177
+0,0,0.83195,0.902225,0.92745,0.83195,0.83195,0.30074166666666663,0.902225,0.18549000000000002,0.92745,0.83195,0.8689883333333294,0.8727168253968192,0.8926526897161345,0.8749147588029799
+0.08890469416785206,250,0.82945,0.89915,0.9232,0.82945,0.82945,0.29971666666666663,0.89915,0.18464,0.9232,0.82945,0.8659070833333276,0.8701056349206286,0.8903875436825469,0.8723244684866377
+0.17780938833570412,500,0.828825,0.899275,0.92495,0.828825,0.828825,0.29975833333333324,0.899275,0.18499000000000002,0.92495,0.828825,0.8660495833333293,0.8701326785714227,0.8906687992093922,0.8723727841161746
+0.26671408250355616,750,0.8275,0.8982,0.924575,0.8275,0.8275,0.2994,0.8982,0.18491500000000002,0.924575,0.8275,0.8650570833333291,0.8691504761904709,0.8898680740527514,0.8714249021225311
+0.35561877667140823,1000,0.82635,0.89685,0.9231,0.82635,0.82635,0.29894999999999994,0.89685,0.18462000000000003,0.9231,0.82635,0.8637624999999958,0.8679554861111068,0.8887040412306829,0.870291019763184
+0.4445234708392603,1250,0.8253,0.895875,0.922775,0.8253,0.8253,0.298625,0.895875,0.18455500000000002,0.922775,0.8253,0.8627333333333284,0.8670970039682474,0.8882788258642533,0.8693715465326811
+0.5334281650071123,1500,0.825625,0.897825,0.923775,0.825625,0.825625,0.29927499999999996,0.897825,0.18475500000000003,0.923775,0.825625,0.8636204166666622,0.8678676091269802,0.888922782755731,0.8701965562510977
+0.6223328591749644,1750,0.826475,0.898275,0.924975,0.826475,0.826475,0.299425,0.898275,0.18499500000000002,0.924975,0.826475,0.8645712499999963,0.8687563988095197,0.8897878318432946,0.8710728393614929
+0.7112375533428165,2000,0.8243,0.898325,0.9246,0.8243,0.8243,0.2994416666666666,0.898325,0.18492000000000003,0.9246,0.8243,0.863249166666662,0.8675520238095187,0.8889727476905229,0.8698474878821617
+0.8001422475106685,2250,0.824325,0.897975,0.92505,0.824325,0.824325,0.29932499999999995,0.897975,0.18501,0.92505,0.824325,0.8633704166666619,0.8677559821428534,0.8893584960932963,0.8699944340323269
+0.8890469416785206,2500,0.8261,0.89915,0.9255,0.8261,0.8261,0.29971666666666663,0.89915,0.1851,0.9255,0.8261,0.8647033333333278,0.8690019047618991,0.8902527863682662,0.8713242079822332
+0.9779516358463727,2750,0.8243,0.897975,0.926225,0.8243,0.8243,0.29932499999999995,0.897975,0.185245,0.926225,0.8243,0.8635870833333281,0.8677371428571375,0.8892831528851212,0.8700284032741374
+1.0668563300142249,3000,0.8241,0.897225,0.926125,0.8241,0.8241,0.299075,0.897225,0.185225,0.926125,0.8241,0.8632970833333293,0.8676181646825338,0.8894654858943166,0.8698620537754669
+1.1557610241820768,3250,0.8232,0.896875,0.924575,0.8232,0.8232,0.2989583333333333,0.896875,0.184915,0.924575,0.8232,0.8622312499999951,0.86657932539682,0.888277484428848,0.8689135119631752
+1.2446657183499288,3500,0.824625,0.8974,0.925225,0.824625,0.824625,0.2991333333333333,0.8974,0.18504500000000002,0.925225,0.824625,0.8633899999999974,0.8677500793650761,0.8893532183136286,0.8700126753383629
+1.333570412517781,3750,0.826,0.89965,0.9274,0.826,0.826,0.2998833333333333,0.89965,0.18548,0.9274,0.826,0.8652645833333301,0.8692946031746002,0.8905441078139272,0.8716340150356571
+1.422475106685633,4000,0.824425,0.89975,0.92645,0.824425,0.824425,0.29991666666666666,0.89975,0.18529,0.92645,0.824425,0.864125416666662,0.8684265079365019,0.8901440317447908,0.8706873112589667
+1.5113798008534851,4250,0.8253,0.8996,0.9269,0.8253,0.8253,0.29986666666666667,0.8996,0.18538000000000002,0.9269,0.8253,0.8645183333333296,0.8687556845238067,0.8903151579796685,0.8710479547612955
+1.600284495021337,4500,0.826075,0.900525,0.92735,0.826075,0.826075,0.30017499999999997,0.900525,0.18547000000000002,0.92735,0.826075,0.8653399999999947,0.869614682539678,0.8911142625274466,0.8718910537743053
+1.689189189189189,4750,0.8254,0.9008,0.927875,0.8254,0.8254,0.3002666666666666,0.9008,0.18557500000000002,0.927875,0.8254,0.8651308333333289,0.869415744047615,0.8911338067941118,0.8716287595062117
+1.7780938833570412,5000,0.826125,0.900825,0.928125,0.826125,0.826125,0.3002749999999999,0.900825,0.185625,0.928125,0.826125,0.8655674999999943,0.8698457936507872,0.8915358469035347,0.8720385960804306
+1.8669985775248934,5250,0.826275,0.90085,0.92775,0.826275,0.826275,0.3002833333333333,0.90085,0.18555000000000002,0.92775,0.826275,0.8654874999999954,0.8697801388888855,0.8913376793363903,0.8720369105761234
+1.9559032716927454,5500,0.826475,0.90055,0.928375,0.826475,0.826475,0.3001833333333333,0.90055,0.185675,0.928375,0.826475,0.86594458333333,0.870266646825393,0.8919597636631106,0.872453372055676
+2.0448079658605973,5750,0.82555,0.9003,0.928675,0.82555,0.82555,0.3001,0.9003,0.18573500000000004,0.928675,0.82555,0.8653429166666625,0.8695566865079313,0.8913477139850707,0.8717820455069423
+2.1337126600284497,6000,0.825625,0.90055,0.9282,0.825625,0.825625,0.30018333333333325,0.90055,0.18564,0.9282,0.825625,0.8653099999999962,0.8694939682539629,0.8910947639818653,0.8717650504829683
+2.2226173541963017,6250,0.825825,0.900275,0.9287,0.825825,0.825825,0.3000916666666666,0.900275,0.18574000000000004,0.9287,0.825825,0.8653583333333296,0.8695507738095194,0.8912904891754598,0.8717973081254348
+2.3115220483641536,6500,0.825825,0.901125,0.927775,0.825825,0.825825,0.300375,0.901125,0.18555500000000003,0.927775,0.825825,0.8654291666666617,0.8697767757936467,0.891514369172863,0.8719817031068368
+2.4004267425320056,6750,0.826675,0.901875,0.929025,0.826675,0.826675,0.3006249999999999,0.901875,0.18580500000000003,0.929025,0.826675,0.8663541666666639,0.8705783234126955,0.8921849188857959,0.8727623767605248
+2.4893314366998576,7000,0.82605,0.901425,0.9289,0.82605,0.82605,0.300475,0.901425,0.18578000000000003,0.9289,0.82605,0.8659991666666632,0.8702431547618993,0.8919562929679258,0.8724513470162975
+2.57823613086771,7250,0.82535,0.901225,0.9295,0.82535,0.82535,0.3004083333333333,0.901225,0.1859,0.9295,0.82535,0.8656245833333279,0.8697893353174546,0.8916239078178946,0.8720247276958484
+2.667140825035562,7500,0.8255,0.90085,0.929125,0.8255,0.8255,0.30028333333333324,0.90085,0.18582500000000002,0.929125,0.8255,0.8654579166666619,0.8696643650793607,0.8914895705223879,0.8718709723722498
+2.756045519203414,7750,0.8253,0.9018,0.929375,0.8253,0.8253,0.3006,0.9018,0.185875,0.929375,0.8253,0.8656070833333277,0.8698574900793603,0.8917621026635288,0.872042398621568
+2.844950213371266,8000,0.825225,0.902025,0.929475,0.825225,0.825225,0.30067499999999997,0.902025,0.185895,0.929475,0.825225,0.8657299999999958,0.8700055456349186,0.8919347492329193,0.8721763851752837
+2.933854907539118,8250,0.8261,0.902,0.929725,0.8261,0.8261,0.3006666666666666,0.902,0.18594500000000003,0.929725,0.8261,0.8661191666666619,0.8703794742063435,0.892261072894104,0.8725470379235181
+3.0227596017069702,8500,0.825875,0.9021,0.930325,0.825875,0.825875,0.30069999999999997,0.9021,0.18606500000000004,0.930325,0.825875,0.8660287499999948,0.8701407440476129,0.892015406424538,0.8723150001203079
+3.111664295874822,8750,0.825075,0.902025,0.9298,0.825075,0.825075,0.30067499999999997,0.902025,0.18596000000000001,0.9298,0.825075,0.8655766666666621,0.8697728769841233,0.8917401059637062,0.871920385377115
+3.200568990042674,9000,0.825375,0.9015,0.9299,0.825375,0.825375,0.30049999999999993,0.9015,0.18598,0.9299,0.825375,0.8657895833333293,0.8700066964285663,0.8919692320325127,0.8721514502415741
+3.2894736842105265,9250,0.82545,0.901775,0.92975,0.82545,0.82545,0.3005916666666666,0.901775,0.18595,0.92975,0.82545,0.8658466666666634,0.8700841567460282,0.8920252801584724,0.8722283525901668
+3.3783783783783785,9500,0.825675,0.9017,0.930125,0.825675,0.825675,0.30056666666666665,0.9017,0.186025,0.930125,0.825675,0.8659704166666623,0.8701954761904717,0.8921878189564996,0.87231294268874
+3.4672830725462305,9750,0.82565,0.902125,0.930125,0.82565,0.82565,0.3007083333333333,0.902125,0.186025,0.930125,0.82565,0.865978333333329,0.8701194940476146,0.8919567604167592,0.8723131653149703
+3.5561877667140824,10000,0.82585,0.902175,0.930075,0.82585,0.82585,0.30072499999999996,0.902175,0.186015,0.930075,0.82585,0.8661279166666617,0.8703281448412645,0.8922105025555344,0.8724788643099791

final_metrics.json

@@ -1,16 +1,16 @@
 {
-  "val_cosine_accuracy@1": 0.8288,
-  "val_cosine_accuracy@3": 0.899775,
-  "val_cosine_accuracy@5": 0.925775,
-  "val_cosine_precision@1": 0.8288,
-  "val_cosine_precision@3": 0.29992499999999994,
-  "val_cosine_precision@5": 0.185155,
-  "val_cosine_recall@1": 0.8288,
-  "val_cosine_recall@3": 0.899775,
-  "val_cosine_recall@5": 0.925775,
-  "val_cosine_ndcg@10": 0.8910978019383597,
-  "val_cosine_mrr@1": 0.8288,
-  "val_cosine_mrr@5": 0.8661879166666627,
-  "val_cosine_mrr@10": 0.8703450396825356,
-  "val_cosine_map@100": 0.8726020537429935
+  "val_cosine_accuracy@1": 0.826575,
+  "val_cosine_accuracy@3": 0.900725,
+  "val_cosine_accuracy@5": 0.92805,
+  "val_cosine_precision@1": 0.826575,
+  "val_cosine_precision@3": 0.30024166666666663,
+  "val_cosine_precision@5": 0.18561000000000002,
+  "val_cosine_recall@1": 0.826575,
+  "val_cosine_recall@3": 0.900725,
+  "val_cosine_recall@5": 0.92805,
+  "val_cosine_ndcg@10": 0.891705546917102,
+  "val_cosine_mrr@1": 0.826575,
+  "val_cosine_mrr@5": 0.8658308333333287,
+  "val_cosine_mrr@10": 0.8701137103174557,
+  "val_cosine_map@100": 0.8723575730144177
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25f963c4800c329ff4ed642d169b94e70ff851553fb77c0d7b4cf1aa65ac7635
+oid sha256:368ea36921477c1e5c05b855edd91867c031b131e8d9b5c31b5b7d66e904530f
 size 133462128

modules.json

@@ -10,11 +10,5 @@
     "name": "1",
     "path": "1_Pooling",
     "type": "sentence_transformers.models.Pooling"
-  },
-  {
-    "idx": 2,
-    "name": "2",
-    "path": "2_Normalize",
-    "type": "sentence_transformers.models.Normalize"
   }
 ]

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9ea4e4ae0572c1ec6cf4f6b909ede35f27b9076fe79a8e80be98205658efeff
+oid sha256:c4b7fb9f1bde49d5d0ac89d63b3b97256d730788bbc479278759fa6f4c5faa36
 size 6161