Training in progress, step 5000

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

@@ -7,3 +7,4 @@ epoch,steps,cosine-Accuracy@1,cosine-Accuracy@3,cosine-Accuracy@5,cosine-Precisi
 -1,-1,0.802275,0.8676,0.89495,0.802275,0.802275,0.28919999999999996,0.8676,0.17899,0.89495,0.802275,0.8373504166666614,0.8418555952380918,0.8626142815266079,0.8448604581747029
 -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

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: 0.8288
-      name: Cosine Accuracy@1
-    - type: cosine_accuracy@3
-      value: 0.899775
-      name: Cosine Accuracy@3
-    - type: cosine_accuracy@5
-      value: 0.925775
-      name: Cosine Accuracy@5
-    - type: cosine_precision@1
-      value: 0.8288
-      name: Cosine Precision@1
-    - type: cosine_precision@3
-      value: 0.29992499999999994
-      name: Cosine Precision@3
-    - type: cosine_precision@5
-      value: 0.185155
-      name: Cosine Precision@5
-    - type: cosine_recall@1
-      value: 0.8288
-      name: Cosine Recall@1
-    - type: cosine_recall@3
-      value: 0.899775
-      name: Cosine Recall@3
-    - type: cosine_recall@5
-      value: 0.925775
-      name: Cosine Recall@5
-    - type: cosine_ndcg@10
-      value: 0.8910978019383597
-      name: Cosine Ndcg@10
-    - type: cosine_mrr@1
-      value: 0.8288
-      name: Cosine Mrr@1
-    - type: cosine_mrr@5
-      value: 0.8661879166666627
-      name: Cosine Mrr@5
-    - type: cosine_mrr@10
-      value: 0.8703450396825356
-      name: Cosine Mrr@10
-    - type: cosine_map@100
-      value: 0.8726020537429935
-      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, 0.9939, 0.0183],
-#         [0.9939, 1.0001, 0.0223],
-#         [0.0183, 0.0223, 1.0000]])
+# 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  | 0.8288     |
-| cosine_accuracy@3  | 0.8998     |
-| cosine_accuracy@5  | 0.9258     |
-| cosine_precision@1 | 0.8288     |
-| cosine_precision@3 | 0.2999     |
-| cosine_precision@5 | 0.1852     |
-| cosine_recall@1    | 0.8288     |
-| cosine_recall@3    | 0.8998     |
-| cosine_recall@5    | 0.9258     |
-| **cosine_ndcg@10** | **0.8911** |
-| cosine_mrr@1       | 0.8288     |
-| cosine_mrr@5       | 0.8662     |
-| cosine_mrr@10      | 0.8703     |
-| cosine_map@100     | 0.8726     |
-
 <!--
 ## 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`: 2e-05
-- `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`: 2e-05
-- `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          | 0.8927             |
-| 0.0889 | 250  | 2.5091        | 0.4913          | 0.8873             |
-| 0.1778 | 500  | 0.6206        | 0.4434          | 0.8906             |
-| 0.2667 | 750  | 0.5549        | 0.4244          | 0.8909             |
-| 0.3556 | 1000 | 0.5305        | 0.4144          | 0.8906             |
-| 0.4445 | 1250 | 0.5155        | 0.4080          | 0.8911             |
-| 0.5334 | 1500 | 0.5101        | 0.4031          | 0.8913             |
-| 0.6223 | 1750 | 0.5035        | 0.4002          | 0.8916             |
-| 0.7112 | 2000 | 0.4955        | 0.3965          | 0.8912             |
-| 0.8001 | 2250 | 0.4906        | 0.3941          | 0.8912             |
-| 0.8890 | 2500 | 0.4882        | 0.3919          | 0.8913             |
-| 0.9780 | 2750 | 0.4845        | 0.3904          | 0.8913             |
-| 1.0669 | 3000 | 0.4769        | 0.3885          | 0.8911             |
-| 1.1558 | 3250 | 0.4745        | 0.3876          | 0.8912             |
-| 1.2447 | 3500 | 0.4718        | 0.3867          | 0.8909             |
-| 1.3336 | 3750 | 0.47          | 0.3863          | 0.8909             |
-| 1.4225 | 4000 | 0.4681        | 0.3855          | 0.8910             |
-| 1.5114 | 4250 | 0.4668        | 0.3846          | 0.8911             |
-| 1.6003 | 4500 | 0.4669        | 0.3843          | 0.8910             |
-| 1.6892 | 4750 | 0.4661        | 0.3840          | 0.8911             |
-| 1.7781 | 5000 | 0.467         | 0.3838          | 0.8911             |
+| 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

@@ -734,3 +734,24 @@ epoch,steps,cosine-Accuracy@1,cosine-Accuracy@3,cosine-Accuracy@5,cosine-Precisi
 1.600284495021337,4500,0.828575,0.899625,0.925675,0.828575,0.828575,0.29987499999999995,0.899625,0.18513500000000002,0.925675,0.828575,0.8660541666666626,0.8702173115079318,0.8909902899298062,0.8724766698003134
 1.689189189189189,4750,0.8286,0.899825,0.925875,0.8286,0.8286,0.29994166666666666,0.899825,0.185175,0.925875,0.8286,0.8661354166666628,0.8702819642857099,0.8910552930249616,0.8725407589971798
 1.7780938833570412,5000,0.8288,0.899775,0.925775,0.8288,0.8288,0.29992499999999994,0.899775,0.185155,0.925775,0.8288,0.8661879166666627,0.8703450396825356,0.8910978019383597,0.8726020537429935
+0,0,0.8319,0.90225,0.92745,0.8319,0.8319,0.30074999999999996,0.90225,0.18549000000000002,0.92745,0.8319,0.8689541666666625,0.8726801289682479,0.8926199303765392,0.8748805276919244
+0.08890469416785206,250,0.8288,0.897675,0.9232,0.8288,0.8288,0.299225,0.897675,0.18464,0.9232,0.8288,0.8653316666666627,0.8694904761904724,0.889843598315805,0.8717693425259888
+0.17780938833570412,500,0.826275,0.897775,0.92375,0.826275,0.826275,0.2992583333333333,0.897775,0.18475000000000003,0.92375,0.826275,0.863926249999995,0.8679417857142809,0.8885813065465965,0.8702881731300135
+0.26671408250355616,750,0.826025,0.897375,0.9228,0.826025,0.826025,0.299125,0.897375,0.18456,0.9228,0.826025,0.8636179166666623,0.8678008730158692,0.8885134074486496,0.8701865475154951
+0.35561877667140823,1000,0.8258,0.896675,0.92355,0.8258,0.8258,0.2988916666666666,0.896675,0.18471000000000004,0.92355,0.8258,0.8635258333333279,0.8676962996031691,0.8885599872488738,0.870042255602252
+0.4445234708392603,1250,0.824875,0.89635,0.92335,0.824875,0.824875,0.2987833333333333,0.89635,0.18467000000000003,0.92335,0.824875,0.8627141666666621,0.8670277876984089,0.8882794354354085,0.8693239539919134
+0.5334281650071123,1500,0.825125,0.897525,0.924175,0.825125,0.825125,0.29917499999999997,0.897525,0.18483500000000003,0.924175,0.825125,0.8633949999999962,0.867706269841266,0.8889730887065863,0.8700247113841982
+0.6223328591749644,1750,0.8267,0.89935,0.925875,0.8267,0.8267,0.2997833333333333,0.89935,0.18517500000000003,0.925875,0.8267,0.8650112499999958,0.8691327777777728,0.8902040050530053,0.871439741677958
+0.7112375533428165,2000,0.825975,0.89815,0.924575,0.825975,0.825975,0.2993833333333333,0.89815,0.184915,0.924575,0.825975,0.8642737499999955,0.8687038988095179,0.8900460941031945,0.870943904816002
+0.8001422475106685,2250,0.825875,0.89965,0.927075,0.825875,0.825875,0.2998833333333333,0.89965,0.185415,0.927075,0.825875,0.8649395833333295,0.8690806646825362,0.8905136853139216,0.8713076851028642
+0.8890469416785206,2500,0.826725,0.89945,0.927275,0.826725,0.826725,0.2998166666666667,0.89945,0.185455,0.927275,0.826725,0.8656320833333302,0.8697662599206316,0.8910286540981277,0.8720342672229079
+0.9779516358463727,2750,0.826325,0.899475,0.9268,0.826325,0.826325,0.299825,0.899475,0.18536000000000002,0.9268,0.826325,0.8651916666666609,0.8693570833333281,0.8906481591036978,0.8716483693806231
+1.0668563300142249,3000,0.8251,0.89875,0.926775,0.8251,0.8251,0.2995833333333333,0.89875,0.18535500000000002,0.926775,0.8251,0.8644283333333289,0.868718333333329,0.8903800746652023,0.8709735043059803
+1.1557610241820768,3250,0.825875,0.8984,0.9264,0.825875,0.825875,0.2994666666666666,0.8984,0.18528000000000003,0.9264,0.825875,0.8645599999999954,0.8687453968253911,0.8900891643934595,0.871080869444009
+1.2446657183499288,3500,0.8257,0.8988,0.926425,0.8257,0.8257,0.2996,0.8988,0.18528500000000003,0.926425,0.8257,0.864509166666662,0.8688920634920582,0.8905771361958603,0.8711022392762224
+1.333570412517781,3750,0.82695,0.900425,0.927875,0.82695,0.82695,0.3001416666666666,0.900425,0.185575,0.927875,0.82695,0.8660504166666626,0.8702353472222183,0.8916015091549829,0.8724690370100244
+1.422475106685633,4000,0.826375,0.900325,0.926925,0.826375,0.826375,0.3001083333333333,0.900325,0.18538500000000002,0.926925,0.826375,0.8655024999999967,0.8698252579365039,0.8913176126453107,0.8721023558877614
+1.5113798008534851,4250,0.826575,0.900525,0.9275,0.826575,0.826575,0.30017499999999997,0.900525,0.18550000000000003,0.9275,0.826575,0.8657658333333297,0.8701011309523772,0.8916906338596331,0.8723343455421415
+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

final_metrics.json

@@ -1,16 +1,16 @@
 {
-  "val_cosine_accuracy@1": 0.82975,
-  "val_cosine_accuracy@3": 0.903025,
-  "val_cosine_accuracy@5": 0.9308,
-  "val_cosine_precision@1": 0.82975,
-  "val_cosine_precision@3": 0.3010083333333333,
-  "val_cosine_precision@5": 0.18616000000000002,
-  "val_cosine_recall@1": 0.82975,
-  "val_cosine_recall@3": 0.903025,
-  "val_cosine_recall@5": 0.9308,
-  "val_cosine_ndcg@10": 0.894185079953941,
-  "val_cosine_mrr@1": 0.82975,
-  "val_cosine_mrr@5": 0.8688179166666645,
-  "val_cosine_mrr@10": 0.8729221527777756,
-  "val_cosine_map@100": 0.8751251735048098
+  "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
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8047d77ced88713240245a68d96f88c650644e287418c20b245e56ea70742aa
+oid sha256:25f963c4800c329ff4ed642d169b94e70ff851553fb77c0d7b4cf1aa65ac7635
 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 sha256:3726ece5e3c076eec5b76be95311c502c97d1d84d6588af421499557cb47e84d
+oid sha256:f9ea4e4ae0572c1ec6cf4f6b909ede35f27b9076fe79a8e80be98205658efeff
 size 6161