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,-1,0.7966,0.87425,0.900575,0.7966,0.7966,0.2914166666666666,0.87425,0.180115,0.900575,0.7966,0.8372962499999956,0.8416481150793601,0.8637140791780538,0.8444611118975183
 -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

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: 0.827675
-      name: Cosine Accuracy@1
-    - type: cosine_accuracy@3
-      value: 0.903
-      name: Cosine Accuracy@3
-    - type: cosine_accuracy@5
-      value: 0.928425
-      name: Cosine Accuracy@5
-    - type: cosine_precision@1
-      value: 0.827675
-      name: Cosine Precision@1
-    - type: cosine_precision@3
-      value: 0.30099999999999993
-      name: Cosine Precision@3
-    - type: cosine_precision@5
-      value: 0.18568500000000004
-      name: Cosine Precision@5
-    - type: cosine_recall@1
-      value: 0.827675
-      name: Cosine Recall@1
-    - type: cosine_recall@3
-      value: 0.903
-      name: Cosine Recall@3
-    - type: cosine_recall@5
-      value: 0.928425
-      name: Cosine Recall@5
-    - type: cosine_ndcg@10
-      value: 0.8922532953454642
-      name: Cosine Ndcg@10
-    - type: cosine_mrr@1
-      value: 0.827675
-      name: Cosine Mrr@1
-    - type: cosine_mrr@5
-      value: 0.8671804166666619
-      name: Cosine Mrr@5
-    - type: cosine_mrr@10
-      value: 0.8711970039682481
-      name: Cosine Mrr@10
-    - type: cosine_map@100
-      value: 0.87334664003711
-      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([[ 1.0001,  1.0001, -0.0307],
-#         [ 1.0001,  1.0001, -0.0307],
-#         [-0.0307, -0.0307,  1.0001]])
+# 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  | 0.8277     |
-| cosine_accuracy@3  | 0.903      |
-| cosine_accuracy@5  | 0.9284     |
-| cosine_precision@1 | 0.8277     |
-| cosine_precision@3 | 0.301      |
-| cosine_precision@5 | 0.1857     |
-| cosine_recall@1    | 0.8277     |
-| cosine_recall@3    | 0.903      |
-| cosine_recall@5    | 0.9284     |
-| **cosine_ndcg@10** | **0.8923** |
-| cosine_mrr@1       | 0.8277     |
-| cosine_mrr@5       | 0.8672     |
-| cosine_mrr@10      | 0.8712     |
-| cosine_map@100     | 0.8733     |
-
 <!--
 ## 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`: 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-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`: 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
@@ -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      | 2.585         | 0.6156          | 0.8730             |
-| 0.0897     | 500      | 0.6653        | 0.4478          | 0.8865             |
-| 0.1345     | 750      | 0.5594        | 0.4191          | 0.8879             |
-| 0.1793     | 1000     | 0.5315        | 0.4058          | 0.8890             |
-| 0.2242     | 1250     | 0.5141        | 0.3980          | 0.8897             |
-| 0.2690     | 1500     | 0.4986        | 0.3916          | 0.8901             |
-| 0.3138     | 1750     | 0.4909        | 0.3857          | 0.8905             |
-| 0.3587     | 2000     | 0.4831        | 0.3818          | 0.8905             |
-| 0.4035     | 2250     | 0.4752        | 0.3785          | 0.8910             |
-| 0.4484     | 2500     | 0.4707        | 0.3758          | 0.8909             |
-| 0.4932     | 2750     | 0.4646        | 0.3733          | 0.8908             |
-| 0.5380     | 3000     | 0.4636        | 0.3713          | 0.8912             |
-| 0.5829     | 3250     | 0.4602        | 0.3693          | 0.8914             |
-| 0.6277     | 3500     | 0.4597        | 0.3678          | 0.8922             |
-| 0.6725     | 3750     | 0.4555        | 0.3665          | 0.8919             |
-| 0.7174     | 4000     | 0.4541        | 0.3661          | 0.8920             |
-| 0.7622     | 4250     | 0.4528        | 0.3649          | 0.8922             |
-| 0.8070     | 4500     | 0.4495        | 0.3643          | 0.8922             |
-| 0.8519     | 4750     | 0.4524        | 0.3640          | 0.8922             |
-| **0.8967** | **5000** | **0.4516**    | **0.3637**      | **0.8923**         |
-
-* 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

@@ -575,3 +575,24 @@ epoch,steps,cosine-Accuracy@1,cosine-Accuracy@3,cosine-Accuracy@5,cosine-Precisi
 0.8070301291248206,4500,0.82765,0.902975,0.928525,0.82765,0.82765,0.3009916666666666,0.902975,0.185705,0.928525,0.82765,0.8670999999999953,0.871106845238089,0.8922032735564264,0.8732435780606005
 0.8518651362984218,4750,0.827625,0.902975,0.9284,0.827625,0.827625,0.3009916666666666,0.902975,0.18568,0.9284,0.827625,0.8671220833333285,0.8711407440476129,0.8921952489654028,0.8732955747232074
 0.896700143472023,5000,0.827675,0.903,0.928425,0.827675,0.827675,0.30099999999999993,0.903,0.18568500000000004,0.928425,0.827675,0.8671804166666619,0.8711970039682481,0.8922532953454642,0.87334664003711
+0,0,0.75685,0.885925,0.91595,0.75685,0.75685,0.2953083333333333,0.885925,0.18319000000000002,0.91595,0.75685,0.823201666666659,0.8273264583333279,0.8565954616545997,0.8297244779466222
+0.04483500717360115,250,0.822125,0.89955,0.924375,0.822125,0.822125,0.29984999999999995,0.89955,0.184875,0.924375,0.822125,0.862629999999997,0.8665409226190439,0.8876046915904008,0.8688213503021354
+0.0896700143472023,500,0.824775,0.898875,0.92425,0.824775,0.824775,0.299625,0.898875,0.18485000000000001,0.92425,0.824775,0.8636979166666618,0.8678174107142824,0.8887680480965763,0.8700790325108972
+0.13450502152080343,750,0.824175,0.8997,0.923875,0.824175,0.824175,0.29989999999999994,0.8997,0.18477500000000002,0.923875,0.824175,0.8634162499999953,0.8675796825396781,0.888606329211206,0.8698678789352505
+0.1793400286944046,1000,0.824475,0.899275,0.92585,0.824475,0.824475,0.2997583333333333,0.899275,0.18517,0.92585,0.824475,0.8640241666666622,0.868102837301583,0.8893879787695432,0.8702731364710155
+0.22417503586800575,1250,0.825675,0.900325,0.92595,0.825675,0.825675,0.3001083333333333,0.900325,0.18519000000000002,0.92595,0.825675,0.8647379166666619,0.868834970238092,0.8899189356969136,0.871083038290237
+0.26901004304160686,1500,0.825825,0.900125,0.925225,0.825825,0.825825,0.30004166666666665,0.900125,0.18504500000000002,0.925225,0.825825,0.8648429166666638,0.8689799107142828,0.8899448493850681,0.8712444453030701
+0.31384505021520803,1750,0.82645,0.901925,0.92795,0.82645,0.82645,0.3006416666666666,0.901925,0.18559,0.92795,0.82645,0.8661770833333292,0.8700933035714242,0.8911201936613601,0.8723261528734203
+0.3586800573888092,2000,0.8267,0.9025,0.928275,0.8267,0.8267,0.30083333333333323,0.9025,0.18565500000000001,0.928275,0.8267,0.8664262499999963,0.8703956051587262,0.8914690049128164,0.8726518583826198
+0.4035150645624103,2250,0.82765,0.902925,0.92875,0.82765,0.82765,0.30097499999999994,0.902925,0.18575000000000003,0.92875,0.82765,0.8671887499999963,0.871212261904757,0.8923650658200335,0.8733732468112121
+0.4483500717360115,2500,0.82865,0.9031,0.9294,0.82865,0.82865,0.3010333333333333,0.9031,0.18588000000000002,0.9294,0.82865,0.8679258333333292,0.871922837301583,0.892966730106002,0.8740831068135856
+0.4931850789096126,2750,0.829775,0.9044,0.9298,0.829775,0.829775,0.3014666666666666,0.9044,0.18596000000000004,0.9298,0.829775,0.8690379166666624,0.8730757738095192,0.893995794179853,0.8752350921259622
+0.5380200860832137,3000,0.8294,0.904475,0.9311,0.8294,0.8294,0.30149166666666666,0.904475,0.18622000000000002,0.9311,0.8294,0.8691224999999955,0.8730955654761859,0.8942270317225469,0.8752400423522199
+0.582855093256815,3250,0.8306,0.90575,0.9313,0.8306,0.8306,0.30191666666666667,0.90575,0.18626,0.9313,0.8306,0.8701383333333306,0.8741678075396787,0.8951792017997346,0.8762915235673985
+0.6276901004304161,3500,0.8309,0.9068,0.93265,0.8309,0.8309,0.30226666666666663,0.9068,0.18653000000000003,0.93265,0.8309,0.8707449999999953,0.8746839980158684,0.8957320012187149,0.8767845184577676
+0.6725251076040172,3750,0.831575,0.906575,0.932675,0.831575,0.831575,0.3021916666666666,0.906575,0.18653500000000003,0.932675,0.831575,0.871057083333329,0.8749730158730102,0.8959495111159976,0.8770786953949046
+0.7173601147776184,4000,0.831475,0.905675,0.932025,0.831475,0.831475,0.30189166666666667,0.905675,0.18640500000000004,0.932025,0.831475,0.8707333333333294,0.8747961210317415,0.895889729995354,0.8768829301874099
+0.7621951219512195,4250,0.832325,0.90685,0.93265,0.832325,0.832325,0.30228333333333324,0.90685,0.18653000000000003,0.93265,0.832325,0.8716041666666615,0.8756558531745968,0.8966707694151853,0.8777083323443566
+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

final_metrics.json

@@ -1,16 +1,16 @@
 {
-  "val_cosine_accuracy@1": 0.83665,
-  "val_cosine_accuracy@3": 0.91045,
-  "val_cosine_accuracy@5": 0.9361,
-  "val_cosine_precision@1": 0.83665,
-  "val_cosine_precision@3": 0.3034833333333333,
-  "val_cosine_precision@5": 0.18722000000000003,
-  "val_cosine_recall@1": 0.83665,
-  "val_cosine_recall@3": 0.91045,
-  "val_cosine_recall@5": 0.9361,
-  "val_cosine_ndcg@10": 0.9000254411118587,
-  "val_cosine_mrr@1": 0.83665,
-  "val_cosine_mrr@5": 0.8753945833333286,
-  "val_cosine_mrr@10": 0.8793089583333286,
-  "val_cosine_map@100": 0.8812821493075779
+  "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
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:325ea67b4c6fb434aa13d441e188dab3f657079050a07c5c0072112cfb0cb217
+oid sha256:92f9d987ad61bc598c66c3bd158c610d72bf02bcb3ca1e5e07dcc754b55681c1
 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:fcb37e6b968d556eedfc831d961ab7fcaa49504d2631242a44ef780da21af2c5
+oid sha256:509dc84fab2c36ed6d2ec320a321343e5561e26e230aa0243f3e61d187261c66
 size 6161