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,-1,0.7467,0.81875,0.842275,0.7467,0.7467,0.27291666666666664,0.81875,0.16845500000000002,0.842275,0.7467,0.784354583333328,0.7884659325396792,0.8088581445720447,0.7917670616349511
 -1,-1,0.83665,0.91045,0.9361,0.83665,0.83665,0.3034833333333333,0.91045,0.18722000000000003,0.9361,0.83665,0.8753945833333286,0.8793089583333286,0.9000254411118587,0.8812821493075779
 -1,-1,0.827675,0.903,0.928425,0.827675,0.827675,0.30099999999999993,0.903,0.18568500000000004,0.928425,0.827675,0.8671804166666619,0.8711970039682481,0.8922532953454642,0.87334664003711
+-1,-1,0.83295,0.9071,0.9329,0.83295,0.83295,0.3023666666666666,0.9071,0.18658000000000005,0.9329,0.83295,0.872013749999996,0.8760916468253912,0.8970951855878305,0.8781372459990227

README.md

@@ -5,123 +5,51 @@ tags:
 - feature-extraction
 - dense
 - generated_from_trainer
-- dataset_size:713743
+- dataset_size:100000
 - loss:MultipleNegativesRankingLoss
-base_model: thenlper/gte-small
+base_model: prajjwal1/bert-small
 widget:
-- source_sentence: 'Abraham Lincoln: Why is the Gettysburg Address so memorable?'
+- source_sentence: How do I calculate IQ?
   sentences:
-  - 'Abraham Lincoln: Why is the Gettysburg Address so memorable?'
-  - What does the Gettysburg Address really mean?
-  - What is eatalo.com?
-- source_sentence: Has the influence of Ancient Carthage in science, math, and society
-    been underestimated?
+  - What is the easiest way to know my IQ?
+  - How do I calculate not IQ ?
+  - What are some creative and innovative business ideas with less investment in India?
+- source_sentence: How can I learn martial arts in my home?
   sentences:
-  - How does one earn money online without an investment from home?
-  - Has the influence of Ancient Carthage in science, math, and society been underestimated?
-  - Has the influence of the Ancient Etruscans in science and math been underestimated?
-- source_sentence: Is there any app that shares charging to others like share it how
-    we transfer files?
+  - How can I learn martial arts by myself?
+  - What are the advantages and disadvantages of investing in gold?
+  - Can people see that I have looked at their pictures on instagram if I am not following
+    them?
+- source_sentence: When Enterprise picks you up do you have to take them back?
   sentences:
-  - How do you think of Chinese claims that the present Private Arbitration is illegal,
-    its verdict violates the UNCLOS and is illegal?
-  - Is there any app that shares charging to others like share it how we transfer
-    files?
-  - Are there any platforms that provides end-to-end encryption for file transfer/
-    sharing?
-- source_sentence: Why AAP’s MLA Dinesh Mohaniya has been arrested?
+  - Are there any software Training institute in Tuticorin?
+  - When Enterprise picks you up do you have to take them back?
+  - When Enterprise picks you up do them have to take youback?
+- source_sentence: What are some non-capital goods?
   sentences:
-  - What are your views on the latest sex scandal by AAP MLA Sandeep Kumar?
-  - What is a dc current? What are some examples?
-  - Why AAP’s MLA Dinesh Mohaniya has been arrested?
-- source_sentence: What is the difference between economic growth and economic development?
+  - What are capital goods?
+  - How is the value of [math]\pi[/math] calculated?
+  - What are some non-capital goods?
+- source_sentence: What is the QuickBooks technical support phone number in New York?
   sentences:
-  - How cold can the Gobi Desert get, and how do its average temperatures compare
-    to the ones in the Simpson Desert?
-  - the difference between economic growth and economic development is What?
-  - What is the difference between economic growth and economic development?
+  - What caused the Great Depression?
+  - Can I apply for PR in Canada?
+  - Which is the best QuickBooks Hosting Support Number in New York?
 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: 0.83295
-      name: Cosine Accuracy@1
-    - type: cosine_accuracy@3
-      value: 0.9071
-      name: Cosine Accuracy@3
-    - type: cosine_accuracy@5
-      value: 0.9329
-      name: Cosine Accuracy@5
-    - type: cosine_precision@1
-      value: 0.83295
-      name: Cosine Precision@1
-    - type: cosine_precision@3
-      value: 0.3023666666666666
-      name: Cosine Precision@3
-    - type: cosine_precision@5
-      value: 0.18658000000000005
-      name: Cosine Precision@5
-    - type: cosine_recall@1
-      value: 0.83295
-      name: Cosine Recall@1
-    - type: cosine_recall@3
-      value: 0.9071
-      name: Cosine Recall@3
-    - type: cosine_recall@5
-      value: 0.9329
-      name: Cosine Recall@5
-    - type: cosine_ndcg@10
-      value: 0.8970951855878305
-      name: Cosine Ndcg@10
-    - type: cosine_mrr@1
-      value: 0.83295
-      name: Cosine Mrr@1
-    - type: cosine_mrr@5
-      value: 0.872013749999996
-      name: Cosine Mrr@5
-    - type: cosine_mrr@10
-      value: 0.8760916468253912
-      name: Cosine Mrr@10
-    - type: cosine_map@100
-      value: 0.8781372459990227
-      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 -->
@@ -138,8 +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})
 )
 ```
 
@@ -158,23 +85,23 @@ Then you can load this model and run inference.
 from sentence_transformers import SentenceTransformer
 
 # Download from the 🤗 Hub
-model = SentenceTransformer("redis/model-b-structured")
+model = SentenceTransformer("sentence_transformers_model_id")
 # Run inference
 sentences = [
-    'What is the difference between economic growth and economic development?',
-    'What is the difference between economic growth and economic development?',
-    'the difference between economic growth and economic development is What?',
+    'What is the QuickBooks technical support phone number in New York?',
+    'Which is the best QuickBooks Hosting Support Number in New York?',
+    'Can I apply for PR in Canada?',
 ]
 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,  1.0000, -0.0559],
-#         [ 1.0000,  1.0000, -0.0559],
-#         [-0.0559, -0.0559,  1.0000]])
+# tensor([[1.0000, 0.8563, 0.0594],
+#         [0.8563, 1.0000, 0.1245],
+#         [0.0594, 0.1245, 1.0000]])
 ```
 
 <!--
@@ -201,32 +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  | 0.8329     |
-| cosine_accuracy@3  | 0.9071     |
-| cosine_accuracy@5  | 0.9329     |
-| cosine_precision@1 | 0.8329     |
-| cosine_precision@3 | 0.3024     |
-| cosine_precision@5 | 0.1866     |
-| cosine_recall@1    | 0.8329     |
-| cosine_recall@3    | 0.9071     |
-| cosine_recall@5    | 0.9329     |
-| **cosine_ndcg@10** | **0.8971** |
-| cosine_mrr@1       | 0.8329     |
-| cosine_mrr@5       | 0.872      |
-| cosine_mrr@10      | 0.8761     |
-| cosine_map@100     | 0.8781     |
-
 <!--
 ## Bias, Risks and Limitations
 
@@ -245,49 +146,23 @@ You can finetune this model on your own dataset.
 
 #### Unnamed Dataset
 
-* Size: 713,743 training 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                                                                          |
+  |         | sentence_0                                                                        | sentence_1                                                                        | sentence_2                                                                        |
   |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
   | type    | string                                                                            | string                                                                            | string                                                                            |
-  | details | <ul><li>min: 6 tokens</li><li>mean: 16.07 tokens</li><li>max: 53 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 16.03 tokens</li><li>max: 53 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 16.81 tokens</li><li>max: 58 tokens</li></ul> |
+  | details | <ul><li>min: 6 tokens</li><li>mean: 15.79 tokens</li><li>max: 66 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 15.68 tokens</li><li>max: 66 tokens</li></ul> | <ul><li>min: 7 tokens</li><li>mean: 16.37 tokens</li><li>max: 67 tokens</li></ul> |
 * Samples:
-  | anchor                                                                         | positive                                                                              | negative                                                                                                          |
-  |:-------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------------------------|
-  | <code>Which one is better Linux OS? Ubuntu or Mint?</code>                     | <code>Why do you use Linux Mint?</code>                                               | <code>Which one is not better Linux OS ? Ubuntu or Mint ?</code>                                                  |
-  | <code>What is flow?</code>                                                     | <code>What is flow?</code>                                                            | <code>What are flow lines?</code>                                                                                 |
-  | <code>How is Trump planning to get Mexico to pay for his supposed wall?</code> | <code>How is it possible for Donald Trump to force Mexico to pay for the wall?</code> | <code>Why do we connect the positive terminal before the negative terminal to ground in a vehicle battery?</code> |
+  | sentence_0                                                       | sentence_1                                                       | sentence_2                                                                        |
+  |:-----------------------------------------------------------------|:-----------------------------------------------------------------|:----------------------------------------------------------------------------------|
+  | <code>Is masturbating bad for boys?</code>                       | <code>Is masturbating bad for boys?</code>                       | <code>How harmful or unhealthy is masturbation?</code>                            |
+  | <code>Does a train engine move in reverse?</code>                | <code>Does a train engine move in reverse?</code>                | <code>Time moves forward, not in reverse. Doesn't that make time a vector?</code> |
+  | <code>What is the most badass thing anyone has ever done?</code> | <code>What is the most badass thing anyone has ever done?</code> | <code>anyone is the most badass thing Whathas ever done?</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>
-* Approximate statistics based on the first 1000 samples:
-  |         | anchor                                                                            | positive                                                                          | negative                                                                          |
-  |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
-  | type    | string                                                                            | string                                                                            | string                                                                            |
-  | details | <ul><li>min: 6 tokens</li><li>mean: 15.52 tokens</li><li>max: 74 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 15.51 tokens</li><li>max: 74 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 16.79 tokens</li><li>max: 69 tokens</li></ul> |
-* Samples:
-  | anchor                                                                                                                                                       | positive                                                                                                                                                     | negative                                                                                                                                                            |
-  |:-------------------------------------------------------------------------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------------------------------------------------------------------------------------|
-  | <code>Why are all my questions on Quora marked needing improvement?</code>                                                                                   | <code>Why are all my questions immediately being marked as needing improvement?</code>                                                                       | <code>For a post-graduate student in IIT, is it allowed to take an external scholarship as a top-up to his/her MHRD assistantship?</code>                           |
-  | <code>Can blue butter fly needle with vaccum tube be reused? Is it HIV risk? . Heard the needle is too small to be reused . Had blood draw at clinic?</code> | <code>Can blue butter fly needle with vaccum tube be reused? Is it HIV risk? . Heard the needle is too small to be reused . Had blood draw at clinic?</code> | <code>Can blue butter fly needle with vaccum tube be reused not ? Is it HIV risk ? . Heard the needle is too small to be reused . Had blood draw at clinic ?</code> |
-  | <code>Why do people still believe the world is flat?</code>                                                                                                  | <code>Why are there still people who believe the world is flat?</code>                                                                                       | <code>I'm not able to buy Udemy course .it is not accepting mine and my friends debit card.my card can be used for Flipkart .how to purchase now?</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
   }
@@ -296,49 +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-b-structured
-- `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
@@ -366,14 +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
@@ -383,23 +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-b-structured
+- `hub_model_id`: None
 - `hub_strategy`: every_save
 - `hub_private_repo`: None
 - `hub_always_push`: False
@@ -426,45 +288,32 @@ 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        | -             | 3.6810          | 0.8566             |
-| 0.0448     | 250      | 1.3118        | 0.4250          | 0.8876             |
-| 0.0897     | 500      | 0.5175        | 0.4063          | 0.8888             |
-| 0.1345     | 750      | 0.481         | 0.3818          | 0.8886             |
-| 0.1793     | 1000     | 0.4592        | 0.3774          | 0.8894             |
-| 0.2242     | 1250     | 0.4498        | 0.3676          | 0.8899             |
-| 0.2690     | 1500     | 0.4358        | 0.3602          | 0.8899             |
-| 0.3138     | 1750     | 0.4258        | 0.3543          | 0.8911             |
-| 0.3587     | 2000     | 0.4181        | 0.3472          | 0.8915             |
-| 0.4035     | 2250     | 0.4077        | 0.3439          | 0.8924             |
-| 0.4484     | 2500     | 0.4032        | 0.3411          | 0.8930             |
-| 0.4932     | 2750     | 0.3987        | 0.3375          | 0.8940             |
-| 0.5380     | 3000     | 0.3943        | 0.3327          | 0.8942             |
-| 0.5829     | 3250     | 0.3897        | 0.3321          | 0.8952             |
-| 0.6277     | 3500     | 0.3863        | 0.3280          | 0.8957             |
-| 0.6725     | 3750     | 0.3819        | 0.3251          | 0.8959             |
-| 0.7174     | 4000     | 0.3786        | 0.3229          | 0.8959             |
-| 0.7622     | 4250     | 0.3753        | 0.3218          | 0.8967             |
-| 0.8070     | 4500     | 0.3723        | 0.3202          | 0.8967             |
-| 0.8519     | 4750     | 0.3731        | 0.3184          | 0.8970             |
-| **0.8967** | **5000** | **0.3715**    | **0.3179**      | **0.8971**         |
-
-* The bold row denotes the saved checkpoint.
+| Epoch  | Step | Training Loss |
+|:------:|:----:|:-------------:|
+| 0.3199 | 500  | 0.4294        |
+| 0.6398 | 1000 | 0.1268        |
+| 0.9597 | 1500 | 0.1           |
+| 1.2796 | 2000 | 0.0792        |
+| 1.5995 | 2500 | 0.0706        |
+| 1.9194 | 3000 | 0.0687        |
+| 2.2393 | 3500 | 0.0584        |
+| 2.5592 | 4000 | 0.057         |
+| 2.8791 | 4500 | 0.0581        |
+
 
 ### Framework Versions
 - Python: 3.10.18

eval/Information-Retrieval_evaluation_val_results.csv

@@ -596,3 +596,44 @@ epoch,steps,cosine-Accuracy@1,cosine-Accuracy@3,cosine-Accuracy@5,cosine-Precisi
 0.8070301291248206,4500,0.832425,0.907,0.9329,0.832425,0.832425,0.30233333333333323,0.907,0.18658000000000002,0.9329,0.832425,0.8716549999999955,0.8756687400793598,0.8966595486024471,0.8777365690203913
 0.8518651362984218,4750,0.832725,0.906625,0.9325,0.832725,0.832725,0.3022083333333333,0.906625,0.18650000000000003,0.9325,0.832725,0.8717712499999956,0.875926736111106,0.8969831290691738,0.8779553498165824
 0.896700143472023,5000,0.83295,0.9071,0.9329,0.83295,0.83295,0.3023666666666666,0.9071,0.18658000000000005,0.9329,0.83295,0.872013749999996,0.8760916468253912,0.8970951855878305,0.8781372459990227
+0,0,0.756875,0.885975,0.915975,0.756875,0.756875,0.29532499999999995,0.885975,0.183195,0.915975,0.756875,0.8232162499999922,0.8273359722222166,0.856602510698957,0.8297335360187499
+0.04483500717360115,250,0.82035,0.898775,0.92285,0.82035,0.82035,0.2995916666666666,0.898775,0.18457000000000004,0.92285,0.82035,0.86118333333333,0.8652290178571391,0.8863952063258179,0.8674982896312767
+0.0896700143472023,500,0.82575,0.901225,0.926425,0.82575,0.82575,0.3004083333333333,0.901225,0.18528500000000003,0.926425,0.82575,0.8653429166666632,0.869252619047615,0.8901201170724944,0.871476202470505
+0.13450502152080343,750,0.82445,0.899725,0.9245,0.82445,0.82445,0.2999083333333333,0.899725,0.18490000000000004,0.9245,0.82445,0.8637154166666616,0.8677438293650747,0.8887072695847659,0.8700066362403331
+0.1793400286944046,1000,0.823725,0.8996,0.9254,0.823725,0.823725,0.2998666666666666,0.8996,0.18508000000000005,0.9254,0.823725,0.8636041666666624,0.8676212003968201,0.8888184696948367,0.8698389104387599
+0.22417503586800575,1250,0.82575,0.900475,0.925925,0.82575,0.82575,0.3001583333333333,0.900475,0.18518500000000004,0.925925,0.82575,0.8650262499999968,0.8690059325396793,0.8898745986756869,0.8713005062855422
+0.26901004304160686,1500,0.8258,0.89895,0.9255,0.8258,0.8258,0.29964999999999997,0.89895,0.1851,0.9255,0.8258,0.8646383333333307,0.8686647321428549,0.8896124993180665,0.8709116156766271
+0.31384505021520803,1750,0.825775,0.89995,0.926175,0.825775,0.825775,0.2999833333333333,0.89995,0.18523500000000004,0.926175,0.825775,0.8647587499999958,0.8688205654761856,0.8899081515731087,0.8710784885214251
+0.3586800573888092,2000,0.825425,0.8996,0.92655,0.825425,0.825425,0.29986666666666667,0.8996,0.18531,0.92655,0.825425,0.8647316666666629,0.8689200595238069,0.8902407189043086,0.8711187710568107
+0.4035150645624103,2250,0.827075,0.90085,0.9271,0.827075,0.827075,0.3002833333333333,0.90085,0.18542000000000003,0.9271,0.827075,0.8659733333333283,0.8702365773809475,0.8915456238576418,0.8723732785050299
+0.4483500717360115,2500,0.8275,0.901625,0.92765,0.8275,0.8275,0.30054166666666665,0.901625,0.18553,0.92765,0.8275,0.8666141666666608,0.8707196626984082,0.8918015610409895,0.8728880304439672
+0.4931850789096126,2750,0.828575,0.902625,0.92825,0.828575,0.828575,0.30087499999999995,0.902625,0.18565000000000004,0.92825,0.828575,0.8676408333333288,0.8718241765872972,0.8928635447213618,0.8739834394140719
+0.5380200860832137,3000,0.82915,0.902025,0.928175,0.82915,0.82915,0.300675,0.902025,0.18563500000000002,0.928175,0.82915,0.8676249999999954,0.8718593452380899,0.8929950331333252,0.8739908509240994
+0.582855093256815,3250,0.828225,0.90375,0.928925,0.828225,0.828225,0.30124999999999996,0.90375,0.185785,0.928925,0.828225,0.8678062499999952,0.8719268551587253,0.893049558480674,0.8740948964512514
+0.6276901004304161,3500,0.8296,0.904225,0.931225,0.8296,0.8296,0.3014083333333333,0.904225,0.186245,0.931225,0.8296,0.8693174999999963,0.87333823412698,0.8945048810893365,0.8754404709174932
+0.6725251076040172,3750,0.82935,0.905225,0.931075,0.82935,0.82935,0.30174166666666663,0.905225,0.18621500000000002,0.931075,0.82935,0.8691295833333297,0.8732088690476152,0.8945292562430565,0.875260740869872
+0.7173601147776184,4000,0.828925,0.904925,0.930725,0.828925,0.828925,0.30164166666666664,0.904925,0.18614500000000003,0.930725,0.828925,0.8689124999999959,0.873018382936505,0.894289834306215,0.875117247192105
+0.7621951219512195,4250,0.8299,0.904625,0.93025,0.8299,0.8299,0.3015416666666666,0.904625,0.18605000000000005,0.93025,0.8299,0.869239999999996,0.8733222718253933,0.8943590572888094,0.8754711827708299
+0.8070301291248206,4500,0.830475,0.9049,0.93115,0.830475,0.830475,0.30163333333333325,0.9049,0.18623000000000003,0.93115,0.830475,0.869884583333329,0.8740106349206304,0.8951880089621758,0.87607963096906
+0.8518651362984218,4750,0.8312,0.9053,0.931825,0.8312,0.8312,0.3017666666666666,0.9053,0.18636500000000003,0.931825,0.8312,0.8704595833333298,0.8746264583333299,0.8958245861242036,0.8766855238331431
+0.896700143472023,5000,0.831625,0.906375,0.932,0.831625,0.831625,0.302125,0.906375,0.1864,0.932,0.831625,0.8710616666666623,0.8751397519841212,0.8961952659834816,0.8772085890152465
+0.9415351506456241,5250,0.83225,0.9068,0.932275,0.83225,0.83225,0.30226666666666663,0.9068,0.186455,0.932275,0.83225,0.871472499999994,0.8755726091269779,0.8966047502020141,0.8776146545196168
+0.9863701578192252,5500,0.831525,0.9069,0.9324,0.831525,0.831525,0.3023,0.9069,0.18648000000000003,0.9324,0.831525,0.8711249999999958,0.8751543452380911,0.8961598314124593,0.8772640118801482
+1.0312051649928264,5750,0.831875,0.906425,0.933225,0.831875,0.831875,0.3021416666666666,0.906425,0.18664500000000003,0.933225,0.831875,0.8712795833333296,0.8752809821428542,0.89640562784357,0.8773572006292477
+1.0760401721664274,6000,0.832025,0.907525,0.933475,0.832025,0.832025,0.3025083333333333,0.907525,0.18669500000000003,0.933475,0.832025,0.8717258333333296,0.8757985714285683,0.8970077641437881,0.8778108799577121
+1.1208751793400287,6250,0.83195,0.907875,0.9335,0.83195,0.83195,0.3026249999999999,0.907875,0.1867,0.9335,0.83195,0.871782083333329,0.8757739980158697,0.8968492872184194,0.8778653232261262
+1.16571018651363,6500,0.832525,0.907625,0.9337,0.832525,0.832525,0.3025416666666666,0.907625,0.18674000000000002,0.9337,0.832525,0.8721158333333285,0.8761973015872967,0.897385051653763,0.8782121820843096
+1.210545193687231,6750,0.832475,0.90785,0.93405,0.832475,0.832475,0.3026166666666666,0.90785,0.18681000000000003,0.93405,0.832475,0.8722049999999953,0.8761733333333286,0.8973375487467027,0.8782016320221021
+1.2553802008608321,7000,0.832925,0.908325,0.934025,0.832925,0.832925,0.30277499999999996,0.908325,0.18680500000000003,0.934025,0.832925,0.8725808333333307,0.876548551587298,0.8975460346295855,0.8786242517331792
+1.3002152080344334,7250,0.833025,0.908625,0.934675,0.833025,0.833025,0.302875,0.908625,0.18693500000000002,0.934675,0.833025,0.872798333333329,0.8766456944444402,0.8975719517121176,0.8787563728128415
+1.3450502152080344,7500,0.83395,0.909375,0.93475,0.83395,0.83395,0.3031249999999999,0.909375,0.18695000000000003,0.93475,0.83395,0.8734979166666627,0.8773938492063433,0.8982561697266986,0.8794720667088616
+1.3898852223816356,7750,0.83335,0.9092,0.934125,0.83335,0.83335,0.3030666666666666,0.9092,0.186825,0.934125,0.83335,0.8730674999999956,0.8770896329365027,0.8980455393637466,0.8791514893239717
+1.4347202295552366,8000,0.83375,0.909575,0.93465,0.83375,0.83375,0.3031916666666666,0.909575,0.18693,0.93465,0.83375,0.873410416666661,0.8774130654761843,0.8984148182049922,0.8794540757199235
+1.4795552367288378,8250,0.833925,0.910075,0.9346,0.833925,0.833925,0.3033583333333333,0.910075,0.18692,0.9346,0.833925,0.8736404166666618,0.8776727380952328,0.8986772276719297,0.8796860009095604
+1.524390243902439,8500,0.8345,0.91075,0.935325,0.8345,0.8345,0.3035833333333333,0.91075,0.18706500000000004,0.935325,0.8345,0.8743245833333277,0.8783290972222166,0.8992457344368305,0.8803256658031703
+1.5692252510760403,8750,0.83475,0.91125,0.936225,0.83475,0.83475,0.3037499999999999,0.91125,0.18724500000000002,0.936225,0.83475,0.8745749999999958,0.8784467162698358,0.8993682431844736,0.8804482510918819
+1.6140602582496413,9000,0.835125,0.91135,0.936,0.835125,0.835125,0.3037833333333333,0.91135,0.18720000000000003,0.936,0.835125,0.8748420833333277,0.878747132936502,0.899603926389485,0.8807394423415384
+1.6588952654232425,9250,0.8351,0.9114,0.936425,0.8351,0.8351,0.30379999999999996,0.9114,0.187285,0.936425,0.8351,0.8749416666666606,0.8787940376984061,0.8996487876543313,0.8807938323330003
+1.7037302725968435,9500,0.83535,0.911475,0.93655,0.83535,0.83535,0.3038249999999999,0.911475,0.18731,0.93655,0.83535,0.8751141666666615,0.878991577380946,0.899889550569265,0.8809631243794993
+1.7485652797704447,9750,0.835325,0.9112,0.936325,0.835325,0.835325,0.3037333333333333,0.9112,0.18726500000000001,0.936325,0.835325,0.8750524999999947,0.8789839384920574,0.8998852971689221,0.8809643466594432
+1.793400286944046,10000,0.83545,0.911175,0.9366,0.83545,0.83545,0.303725,0.911175,0.18732000000000001,0.9366,0.83545,0.8751591666666616,0.8790415476190412,0.8999318372974409,0.8810239994800558

final_metrics.json

@@ -1,16 +1,16 @@
 {
-  "val_cosine_accuracy@1": 0.827675,
-  "val_cosine_accuracy@3": 0.903,
-  "val_cosine_accuracy@5": 0.928425,
-  "val_cosine_precision@1": 0.827675,
-  "val_cosine_precision@3": 0.30099999999999993,
-  "val_cosine_precision@5": 0.18568500000000004,
-  "val_cosine_recall@1": 0.827675,
-  "val_cosine_recall@3": 0.903,
-  "val_cosine_recall@5": 0.928425,
-  "val_cosine_ndcg@10": 0.8922532953454642,
-  "val_cosine_mrr@1": 0.827675,
-  "val_cosine_mrr@5": 0.8671804166666619,
-  "val_cosine_mrr@10": 0.8711970039682481,
-  "val_cosine_map@100": 0.87334664003711
+  "val_cosine_accuracy@1": 0.83295,
+  "val_cosine_accuracy@3": 0.9071,
+  "val_cosine_accuracy@5": 0.9329,
+  "val_cosine_precision@1": 0.83295,
+  "val_cosine_precision@3": 0.3023666666666666,
+  "val_cosine_precision@5": 0.18658000000000005,
+  "val_cosine_recall@1": 0.83295,
+  "val_cosine_recall@3": 0.9071,
+  "val_cosine_recall@5": 0.9329,
+  "val_cosine_ndcg@10": 0.8970951855878305,
+  "val_cosine_mrr@1": 0.83295,
+  "val_cosine_mrr@5": 0.872013749999996,
+  "val_cosine_mrr@10": 0.8760916468253912,
+  "val_cosine_map@100": 0.8781372459990227
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92f9d987ad61bc598c66c3bd158c610d72bf02bcb3ca1e5e07dcc754b55681c1
+oid sha256:bb34c96d597d832aa5edd5352a2499b5d5c6df76a439f4cead08dce5b23e26ed
 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 sha256:509dc84fab2c36ed6d2ec320a321343e5561e26e230aa0243f3e61d187261c66
+oid sha256:aa697a5587cabb6e578299c46e1745cc69a0c459a2f99c151e144c2158d43a4e
 size 6161