Training in progress, step 12000

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

@@ -11,3 +11,4 @@ epoch,steps,cosine-Accuracy@1,cosine-Accuracy@3,cosine-Accuracy@5,cosine-Precisi
 -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
 -1,-1,0.82585,0.902175,0.930075,0.82585,0.82585,0.30072499999999996,0.902175,0.186015,0.930075,0.82585,0.8661279166666617,0.8703281448412645,0.8922105025555344,0.8724788643099791
 -1,-1,0.00065,0.7986,0.880825,0.00065,0.00065,0.26619999999999994,0.7986,0.17616500000000002,0.880825,0.00065,0.288667083333407,0.2951483234127803,0.45147470340355694,0.2980051496600344
+-1,-1,0.827675,0.9006,0.9272,0.827675,0.827675,0.3001999999999999,0.9006,0.18544000000000002,0.9272,0.827675,0.8661058333333287,0.8703261011904707,0.8916124422761306,0.8726181110807445

README.md

@@ -5,124 +5,51 @@ tags:
 - feature-extraction
 - dense
 - generated_from_trainer
-- dataset_size:359997
+- dataset_size:100000
 - loss:MultipleNegativesRankingLoss
-base_model: sentence-transformers/all-MiniLM-L6-v2
+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 sentence-transformers/all-MiniLM-L6-v2
-  results:
-  - task:
-      type: information-retrieval
-      name: Information Retrieval
-    dataset:
-      name: val
-      type: val
-    metrics:
-    - type: cosine_accuracy@1
-      value: 0.827675
-      name: Cosine Accuracy@1
-    - type: cosine_accuracy@3
-      value: 0.9006
-      name: Cosine Accuracy@3
-    - type: cosine_accuracy@5
-      value: 0.9272
-      name: Cosine Accuracy@5
-    - type: cosine_precision@1
-      value: 0.827675
-      name: Cosine Precision@1
-    - type: cosine_precision@3
-      value: 0.3001999999999999
-      name: Cosine Precision@3
-    - type: cosine_precision@5
-      value: 0.18544000000000002
-      name: Cosine Precision@5
-    - type: cosine_recall@1
-      value: 0.827675
-      name: Cosine Recall@1
-    - type: cosine_recall@3
-      value: 0.9006
-      name: Cosine Recall@3
-    - type: cosine_recall@5
-      value: 0.9272
-      name: Cosine Recall@5
-    - type: cosine_ndcg@10
-      value: 0.8916124422761306
-      name: Cosine Ndcg@10
-    - type: cosine_mrr@1
-      value: 0.827675
-      name: Cosine Mrr@1
-    - type: cosine_mrr@5
-      value: 0.8661058333333287
-      name: Cosine Mrr@5
-    - type: cosine_mrr@10
-      value: 0.8703261011904707
-      name: Cosine Mrr@10
-    - type: cosine_map@100
-      value: 0.8726181110807445
-      name: Cosine Map@100
 ---
 
-# SentenceTransformer based on sentence-transformers/all-MiniLM-L6-v2
+# SentenceTransformer based on prajjwal1/bert-small
 
-This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [sentence-transformers/all-MiniLM-L6-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2). 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:** [sentence-transformers/all-MiniLM-L6-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2) <!-- at revision c9745ed1d9f207416be6d2e6f8de32d1f16199bf -->
+- **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 [s
 ```
 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, 0.9965, 0.0032],
-#         [0.9965, 1.0000, 0.0081],
-#         [0.0032, 0.0081, 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  | 0.8277     |
-| cosine_accuracy@3  | 0.9006     |
-| cosine_accuracy@5  | 0.9272     |
-| cosine_precision@1 | 0.8277     |
-| cosine_precision@3 | 0.3002     |
-| cosine_precision@5 | 0.1854     |
-| cosine_recall@1    | 0.8277     |
-| cosine_recall@3    | 0.9006     |
-| cosine_recall@5    | 0.9272     |
-| **cosine_ndcg@10** | **0.8916** |
-| cosine_mrr@1       | 0.8277     |
-| cosine_mrr@5       | 0.8661     |
-| 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`: 256
-- `per_device_eval_batch_size`: 256
-- `learning_rate`: 2e-05
-- `weight_decay`: 0.0001
-- `max_steps`: 12000
-- `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`: 256
-- `per_device_eval_batch_size`: 256
+- `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`: 12000
+- `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
@@ -427,71 +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     | -             | 0.8447          | 0.8942             |
-| 0.1778 | 250   | 0.9708        | 0.6818          | 0.8918             |
-| 0.3556 | 500   | 0.8656        | 0.6666          | 0.8911             |
-| 0.5334 | 750   | 0.835         | 0.6549          | 0.8910             |
-| 0.7112 | 1000  | 0.816         | 0.6453          | 0.8910             |
-| 0.8890 | 1250  | 0.7974        | 0.6371          | 0.8907             |
-| 1.0669 | 1500  | 0.7797        | 0.6307          | 0.8906             |
-| 1.2447 | 1750  | 0.767         | 0.6264          | 0.8910             |
-| 1.4225 | 2000  | 0.7567        | 0.6225          | 0.8904             |
-| 1.6003 | 2250  | 0.749         | 0.6205          | 0.8909             |
-| 1.7781 | 2500  | 0.7438        | 0.6158          | 0.8910             |
-| 1.9559 | 2750  | 0.7381        | 0.6136          | 0.8910             |
-| 2.1337 | 3000  | 0.729         | 0.6115          | 0.8906             |
-| 2.3115 | 3250  | 0.725         | 0.6097          | 0.8912             |
-| 2.4893 | 3500  | 0.7229        | 0.6079          | 0.8908             |
-| 2.6671 | 3750  | 0.716         | 0.6057          | 0.8909             |
-| 2.8450 | 4000  | 0.7139        | 0.6039          | 0.8911             |
-| 3.0228 | 4250  | 0.7124        | 0.6025          | 0.8911             |
-| 3.2006 | 4500  | 0.7055        | 0.6015          | 0.8910             |
-| 3.3784 | 4750  | 0.7048        | 0.6002          | 0.8909             |
-| 3.5562 | 5000  | 0.7025        | 0.5999          | 0.8911             |
-| 3.7340 | 5250  | 0.6999        | 0.5979          | 0.8912             |
-| 3.9118 | 5500  | 0.6974        | 0.5974          | 0.8912             |
-| 4.0896 | 5750  | 0.6955        | 0.5962          | 0.8912             |
-| 4.2674 | 6000  | 0.6919        | 0.5954          | 0.8911             |
-| 4.4452 | 6250  | 0.6903        | 0.5945          | 0.8914             |
-| 4.6230 | 6500  | 0.6888        | 0.5937          | 0.8914             |
-| 4.8009 | 6750  | 0.6876        | 0.5931          | 0.8916             |
-| 4.9787 | 7000  | 0.6871        | 0.5925          | 0.8914             |
-| 5.1565 | 7250  | 0.6819        | 0.5919          | 0.8915             |
-| 5.3343 | 7500  | 0.6827        | 0.5914          | 0.8919             |
-| 5.5121 | 7750  | 0.6815        | 0.5908          | 0.8917             |
-| 5.6899 | 8000  | 0.6806        | 0.5902          | 0.8916             |
-| 5.8677 | 8250  | 0.6807        | 0.5897          | 0.8916             |
-| 6.0455 | 8500  | 0.6771        | 0.5892          | 0.8916             |
-| 6.2233 | 8750  | 0.6748        | 0.5889          | 0.8914             |
-| 6.4011 | 9000  | 0.6756        | 0.5883          | 0.8916             |
-| 6.5789 | 9250  | 0.6763        | 0.5879          | 0.8915             |
-| 6.7568 | 9500  | 0.6747        | 0.5877          | 0.8916             |
-| 6.9346 | 9750  | 0.6743        | 0.5874          | 0.8917             |
-| 7.1124 | 10000 | 0.6726        | 0.5873          | 0.8918             |
-| 7.2902 | 10250 | 0.6715        | 0.5869          | 0.8917             |
-| 7.4680 | 10500 | 0.6715        | 0.5869          | 0.8917             |
-| 7.6458 | 10750 | 0.6688        | 0.5867          | 0.8917             |
-| 7.8236 | 11000 | 0.6718        | 0.5865          | 0.8917             |
-| 8.0014 | 11250 | 0.6734        | 0.5865          | 0.8917             |
-| 8.1792 | 11500 | 0.6692        | 0.5862          | 0.8917             |
-| 8.3570 | 11750 | 0.6705        | 0.5861          | 0.8916             |
-| 8.5349 | 12000 | 0.6698        | 0.5861          | 0.8916             |
+| 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

config.json

@@ -15,7 +15,7 @@
   "max_position_embeddings": 512,
   "model_type": "bert",
   "num_attention_heads": 12,
-  "num_hidden_layers": 6,
+  "num_hidden_layers": 12,
   "pad_token_id": 0,
   "position_embedding_type": "absolute",
   "transformers_version": "4.57.3",

config_sentence_transformers.json

@@ -1,10 +1,10 @@
 {
+  "model_type": "SentenceTransformer",
   "__version__": {
     "sentence_transformers": "5.2.0",
     "transformers": "4.57.3",
     "pytorch": "2.9.1+cu128"
   },
-  "model_type": "SentenceTransformer",
   "prompts": {
     "query": "",
     "document": ""

eval/Information-Retrieval_evaluation_val_results.csv

@@ -867,3 +867,52 @@ epoch,steps,cosine-Accuracy@1,cosine-Accuracy@3,cosine-Accuracy@5,cosine-Precisi
 8.17923186344239,11500,0.827775,0.90055,0.9272,0.827775,0.827775,0.30018333333333325,0.90055,0.18544000000000005,0.9272,0.827775,0.8661820833333286,0.8704046329365026,0.8916719767589327,0.8726965525672397
 8.357041251778094,11750,0.827725,0.900575,0.9273,0.827725,0.827725,0.3001916666666666,0.900575,0.18546,0.9273,0.827725,0.8661516666666623,0.8703490972222169,0.8916142319118482,0.8726456646970746
 8.534850640113799,12000,0.827675,0.9006,0.9272,0.827675,0.827675,0.3001999999999999,0.9006,0.18544000000000002,0.9272,0.827675,0.8661058333333287,0.8703261011904707,0.8916124422761306,0.8726181110807445
+0,0,0.831625,0.904825,0.930275,0.831625,0.831625,0.3016083333333333,0.904825,0.18605500000000003,0.930275,0.831625,0.8700020833333297,0.8740149702380903,0.8947956228329856,0.8761202191912003
+0.17780938833570412,250,0.8309,0.902175,0.928025,0.8309,0.8309,0.3007249999999999,0.902175,0.18560500000000002,0.928025,0.8309,0.8685729166666637,0.8725017162698372,0.8929538326746335,0.8747333227558265
+0.35561877667140823,500,0.830325,0.901275,0.926725,0.830325,0.830325,0.30042499999999994,0.901275,0.185345,0.926725,0.830325,0.8676833333333298,0.8716772619047575,0.8921279801127974,0.8739299710019109
+0.5334281650071123,750,0.83005,0.90135,0.92655,0.83005,0.83005,0.30044999999999994,0.90135,0.18531000000000003,0.92655,0.83005,0.8674479166666631,0.8715112202380917,0.8920520906211146,0.8737437000129952
+0.7112375533428165,1000,0.82965,0.901625,0.927075,0.82965,0.82965,0.3005416666666666,0.901625,0.18541500000000002,0.927075,0.82965,0.8673416666666631,0.8713230753968207,0.8918970863179578,0.8735992012066941
+0.8890469416785206,1250,0.82985,0.901375,0.926625,0.82985,0.82985,0.30045833333333327,0.901375,0.18532500000000005,0.926625,0.82985,0.8672583333333292,0.8713413194444398,0.8919456773959668,0.8736069337201386
+1.0668563300142249,1500,0.82845,0.900825,0.92675,0.82845,0.82845,0.3002749999999999,0.900825,0.18535,0.92675,0.82845,0.8665154166666634,0.8705226190476147,0.8912653496095391,0.8728247615160977
+1.2446657183499288,1750,0.82955,0.901025,0.926625,0.82955,0.82955,0.3003416666666666,0.901025,0.18532500000000005,0.926625,0.82955,0.8670879166666633,0.8712592559523779,0.892052086854967,0.8735261480766443
+1.422475106685633,2000,0.829025,0.9009,0.926575,0.829025,0.829025,0.30029999999999996,0.9009,0.185315,0.926575,0.829025,0.8667866666666623,0.8709597321428515,0.8918234296855311,0.8732313918966004
+1.600284495021337,2250,0.82945,0.90095,0.926825,0.82945,0.82945,0.3003166666666667,0.90095,0.185365,0.926825,0.82945,0.8671574999999966,0.871418571428566,0.8924118112112361,0.8736261739430169
+1.7780938833570412,2500,0.829525,0.90105,0.92685,0.829525,0.829525,0.30034999999999995,0.90105,0.18537000000000003,0.92685,0.829525,0.8672737499999971,0.8715154563492026,0.8924613501410394,0.8737406680512708
+1.9559032716927454,2750,0.829675,0.90125,0.927475,0.829675,0.829675,0.30041666666666667,0.90125,0.18549500000000002,0.927475,0.829675,0.8674449999999956,0.8716037202380902,0.8925415615997252,0.8738450662235883
+2.1337126600284497,3000,0.829075,0.9008,0.92675,0.829075,0.829075,0.3002666666666666,0.9008,0.18535000000000001,0.92675,0.829075,0.8667741666666628,0.8710116964285664,0.8920264577161328,0.8732648935262536
+2.3115220483641536,3250,0.82915,0.901725,0.927225,0.82915,0.82915,0.300575,0.901725,0.18544500000000003,0.927225,0.82915,0.8672691666666625,0.8715357936507893,0.8926252728417705,0.8737524052827684
+2.4893314366998576,3500,0.828725,0.90075,0.927225,0.828725,0.828725,0.3002499999999999,0.90075,0.18544500000000003,0.927225,0.828725,0.8669262499999957,0.8711759424603118,0.8923208999638791,0.8734087810069759
+2.667140825035562,3750,0.82925,0.90105,0.926225,0.82925,0.82925,0.30034999999999995,0.90105,0.18524500000000002,0.926225,0.82925,0.8669612499999952,0.8714276289682487,0.892603862691297,0.873625909298415
+2.844950213371266,4000,0.828925,0.90155,0.9279,0.828925,0.828925,0.3005166666666666,0.90155,0.18558000000000002,0.9279,0.828925,0.8671687499999962,0.8713887996031692,0.8926037043285648,0.8736030360147775
+3.0227596017069702,4250,0.8292,0.90125,0.9282,0.8292,0.8292,0.3004166666666666,0.90125,0.18564000000000003,0.9282,0.8292,0.8673362499999951,0.8715186408730106,0.8926932877250805,0.8737421170004287
+3.200568990042674,4500,0.828725,0.9017,0.927925,0.828725,0.828725,0.3005666666666666,0.9017,0.185585,0.927925,0.828725,0.8671874999999957,0.8714773710317401,0.8928057244763989,0.8736715357231882
+3.3783783783783785,4750,0.82925,0.901825,0.9284,0.82925,0.82925,0.3006083333333333,0.901825,0.18568,0.9284,0.82925,0.8675054166666624,0.87171569444444,0.8929504439351491,0.8739172164473435
+3.5561877667140824,5000,0.82925,0.901975,0.928225,0.82925,0.82925,0.3006583333333333,0.901975,0.18564500000000003,0.928225,0.82925,0.8675583333333287,0.8718421428571371,0.8931189282508167,0.8740283561506716
+3.733997155049787,5250,0.828625,0.901675,0.928875,0.828625,0.828625,0.3005583333333333,0.901675,0.18577500000000002,0.928875,0.828625,0.8673216666666625,0.8715534226190428,0.8929745876875748,0.8737198830801384
+3.9118065433854907,5500,0.829,0.901675,0.928225,0.829,0.829,0.3005583333333333,0.901675,0.18564500000000003,0.928225,0.829,0.867338333333329,0.8716140773809468,0.8929217746043001,0.8738196655522955
+4.089615931721195,5750,0.8291,0.90215,0.928475,0.8291,0.8291,0.30071666666666663,0.90215,0.18569500000000003,0.928475,0.8291,0.867640416666663,0.8719272619047571,0.8932392181682497,0.874124583229975
+4.2674253200568995,6000,0.8286,0.90205,0.928525,0.8286,0.8286,0.3006833333333333,0.90205,0.185705,0.928525,0.8286,0.867340416666663,0.8715280654761857,0.8927936848185067,0.8737715728780511
+4.445234708392603,6250,0.828625,0.9024,0.929075,0.828625,0.828625,0.30079999999999996,0.9024,0.185815,0.929075,0.828625,0.8675708333333285,0.8717594841269786,0.8931152781348354,0.8739596599602293
+4.623044096728307,6500,0.8289,0.9024,0.9294,0.8289,0.8289,0.3007999999999999,0.9024,0.18588000000000005,0.9294,0.8289,0.867770416666663,0.87187758928571,0.8930975101343516,0.8741281183314473
+4.800853485064011,6750,0.8289,0.902375,0.92945,0.8289,0.8289,0.3007916666666667,0.902375,0.18589,0.92945,0.8289,0.8678683333333289,0.8720034722222172,0.893275435795285,0.8742311935731993
+4.978662873399715,7000,0.828925,0.90245,0.92885,0.828925,0.828925,0.3008166666666667,0.90245,0.18577000000000002,0.92885,0.828925,0.8676416666666624,0.8718145634920582,0.8930143027384154,0.874081632481735
+5.15647226173542,7250,0.828625,0.901875,0.92925,0.828625,0.828625,0.300625,0.901875,0.18585,0.92925,0.828625,0.8675404166666627,0.871692539682534,0.8929959274216948,0.8739423722429887
+5.334281650071124,7500,0.82945,0.902125,0.92955,0.82945,0.82945,0.3007083333333333,0.902125,0.18591000000000002,0.92955,0.82945,0.868159999999996,0.8722399503968199,0.8933571018155224,0.874499699669214
+5.512091038406828,7750,0.8291,0.9021,0.929275,0.8291,0.8291,0.3006999999999999,0.9021,0.18585500000000002,0.929275,0.8291,0.8679370833333294,0.8721387202380895,0.8934094257505741,0.874347382813781
+5.689900426742532,8000,0.828825,0.9022,0.9295,0.828825,0.828825,0.30073333333333324,0.9022,0.1859,0.9295,0.828825,0.8678212499999955,0.8718958829365024,0.8930664285193755,0.8741740890708576
+5.867709815078236,8250,0.829275,0.902725,0.9299,0.829275,0.829275,0.3009083333333333,0.902725,0.18598,0.9299,0.829275,0.8682024999999943,0.8722260019841209,0.8933331360580372,0.8745133632691464
+6.0455192034139404,8500,0.828775,0.901875,0.9297,0.828775,0.828775,0.3006249999999999,0.901875,0.18594000000000002,0.9297,0.828775,0.8677733333333275,0.8718678968253908,0.8931366407847511,0.87411588035112
+6.223328591749644,8750,0.828975,0.9021,0.929325,0.828975,0.828975,0.30069999999999997,0.9021,0.18586500000000003,0.929325,0.828975,0.8677941666666613,0.8719745932539625,0.8932472018391169,0.8742047139175374
+6.401137980085348,9000,0.829125,0.9026,0.93015,0.829125,0.829125,0.3008666666666666,0.9026,0.18603000000000006,0.93015,0.829125,0.868102499999995,0.8721592063492002,0.8934370150571285,0.8743781121824579
+6.578947368421053,9250,0.8289,0.902425,0.929925,0.8289,0.8289,0.3008083333333333,0.902425,0.185985,0.929925,0.8289,0.8679437499999944,0.8720076289682469,0.8932713634606291,0.8742460745252904
+6.756756756756757,9500,0.828925,0.902,0.9295,0.828925,0.828925,0.3006666666666666,0.902,0.1859,0.9295,0.828925,0.8678695833333282,0.8720051984126925,0.8932465278972923,0.8742575945249027
+6.934566145092461,9750,0.828975,0.902475,0.9303,0.828975,0.828975,0.30082499999999995,0.902475,0.18606000000000003,0.9303,0.828975,0.8681374999999951,0.8721719345238036,0.8934081574929793,0.8744241035730255
+7.112375533428165,10000,0.82925,0.90255,0.9299,0.82925,0.82925,0.30084999999999995,0.90255,0.18598000000000003,0.9299,0.82925,0.868111666666662,0.8721829464285649,0.8933828781325055,0.8744379732650784
+7.290184921763869,10250,0.82925,0.902775,0.9305,0.82925,0.82925,0.30092499999999994,0.902775,0.1861,0.9305,0.82925,0.8683645833333281,0.8723633035714223,0.8935592675577376,0.8746075116293569
+7.467994310099574,10500,0.8286,0.902625,0.930125,0.8286,0.8286,0.300875,0.902625,0.18602500000000005,0.930125,0.8286,0.8678754166666618,0.8719397718253904,0.893234013911161,0.8741865749917389
+7.6458036984352775,10750,0.8287,0.903,0.9303,0.8287,0.8287,0.301,0.903,0.18606,0.9303,0.8287,0.8680454166666621,0.8720796726190423,0.8933305820091977,0.8743385301196366
+7.823613086770981,11000,0.82905,0.902725,0.930125,0.82905,0.82905,0.3009083333333333,0.902725,0.18602500000000005,0.930125,0.82905,0.868142083333329,0.872236210317455,0.8935066251827831,0.8744652022358489
+8.001422475106686,11250,0.82905,0.902775,0.930375,0.82905,0.82905,0.30092499999999994,0.902775,0.18607500000000002,0.930375,0.82905,0.8682774999999954,0.8723231448412644,0.8935609899273397,0.8745617632689283
+8.17923186344239,11500,0.8291,0.902725,0.930425,0.8291,0.8291,0.3009083333333333,0.902725,0.18608500000000003,0.930425,0.8291,0.868302916666662,0.8723129365079314,0.8934984837860438,0.8745770163799339
+8.357041251778094,11750,0.829025,0.90275,0.93025,0.829025,0.829025,0.3009166666666666,0.90275,0.18605000000000002,0.93025,0.829025,0.8682012499999952,0.8722469146825345,0.8934640564205625,0.87450322519466
+8.534850640113799,12000,0.82885,0.902725,0.93035,0.82885,0.82885,0.3009083333333333,0.902725,0.18607000000000004,0.93035,0.82885,0.8681187499999955,0.8721355654761855,0.8933682535781845,0.8743952711926549

final_metrics.json

@@ -1,16 +1,16 @@
 {
-  "val_cosine_accuracy@1": 0.00065,
-  "val_cosine_accuracy@3": 0.7986,
-  "val_cosine_accuracy@5": 0.880825,
-  "val_cosine_precision@1": 0.00065,
-  "val_cosine_precision@3": 0.26619999999999994,
-  "val_cosine_precision@5": 0.17616500000000002,
-  "val_cosine_recall@1": 0.00065,
-  "val_cosine_recall@3": 0.7986,
-  "val_cosine_recall@5": 0.880825,
-  "val_cosine_ndcg@10": 0.45147470340355694,
-  "val_cosine_mrr@1": 0.00065,
-  "val_cosine_mrr@5": 0.288667083333407,
-  "val_cosine_mrr@10": 0.2951483234127803,
-  "val_cosine_map@100": 0.2980051496600344
+  "val_cosine_accuracy@1": 0.827675,
+  "val_cosine_accuracy@3": 0.9006,
+  "val_cosine_accuracy@5": 0.9272,
+  "val_cosine_precision@1": 0.827675,
+  "val_cosine_precision@3": 0.3001999999999999,
+  "val_cosine_precision@5": 0.18544000000000002,
+  "val_cosine_recall@1": 0.827675,
+  "val_cosine_recall@3": 0.9006,
+  "val_cosine_recall@5": 0.9272,
+  "val_cosine_ndcg@10": 0.8916124422761306,
+  "val_cosine_mrr@1": 0.827675,
+  "val_cosine_mrr@5": 0.8661058333333287,
+  "val_cosine_mrr@10": 0.8703261011904707,
+  "val_cosine_map@100": 0.8726181110807445
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:362192cb39fe2be97a0273cd2772690d7be8a1fb0c2c9b2d356da5acdf07ee67
-size 90864192
+oid sha256:a7c7afc06dad67124b52482ffca5970ca799969e342466f6e3c5f74a85a05d03
+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"
   }
 ]

tokenizer_config.json

@@ -48,7 +48,7 @@
   "extra_special_tokens": {},
   "mask_token": "[MASK]",
   "max_length": 128,
-  "model_max_length": 256,
+  "model_max_length": 128,
   "never_split": null,
   "pad_to_multiple_of": null,
   "pad_token": "[PAD]",