Training in progress, step 5000

Information-Retrieval_evaluation_val_results.csv

@@ -3,3 +3,4 @@ epoch,steps,cosine-Accuracy@1,cosine-Accuracy@3,cosine-Accuracy@5,cosine-Precisi
 -1,-1,0.9104,0.9688,0.9842,0.9104,0.9104,0.32293333333333335,0.9688,0.19683999999999996,0.9842,0.9104,0.9402433333333332,0.9416250793650793,0.9545809774353143,0.9420576026548708
 -1,-1,0.8281,0.9026,0.93105,0.8281,0.8281,0.3008666666666666,0.9026,0.18621000000000004,0.93105,0.8281,0.8677437499999962,0.8721381249999942,0.8942437004811851,0.874246358340888
 -1,-1,0.82925,0.903025,0.931175,0.82925,0.82925,0.3010083333333333,0.903025,0.186235,0.931175,0.82925,0.8687345833333282,0.8731489384920591,0.8950131360828151,0.8752091976044037
+-1,-1,0.7614,0.82615,0.850775,0.7614,0.7614,0.2753833333333333,0.82615,0.170155,0.850775,0.7614,0.7960862499999959,0.8003843253968239,0.8201550154419872,0.8038332983359062

README.md

@@ -5,110 +5,38 @@ tags:
 - feature-extraction
 - dense
 - generated_from_trainer
-- dataset_size:359999
+- dataset_size:100000
 - loss:MultipleNegativesRankingLoss
 base_model: prajjwal1/bert-small
 widget:
-- source_sentence: Someone blocked me on Instagram. How do I unblock myself from their
-    account?
+- source_sentence: How do I calculate IQ?
   sentences:
-  - Someone blocked me on Instagram. How do I unblock myself from their account?
-  - Someone blocked me on Instagram. How do myself unblock Ifrom their account?
-  - What are some good tips for dealing with a very easily frustrated 1 year old?
-- source_sentence: Do you love the life you live?
+  - 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:
-  - What is Jakob Nowell, Bradley Nowell's son, up to and will he pursue a career
-    in music?
-  - Do you love the life you're living?
-  - Do you love not the life you live ?
-- source_sentence: I had sex on the 9th and my period started on the 11th. Could I
-    still get pregnant?
+  - 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 can I earn money easily online?
-  - If I have sex on the day of my ovulation and I get my period two weeks later,
-    can I still be pregnant?
-  - I did not have sex on the 9th and my period started on the 11th . Could I still
-    get pregnant ?
-- source_sentence: Would you read book at your office?
+  - 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:
-  - Would book read youat your office?
-  - I am a married woman and I'm in love with married man. what should I do?
-  - Would you read book at your office?
-- source_sentence: How do you earn money on Quora?
+  - 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:
-  - 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?
-  - How do you earn not money on Quora ?
-  - What is the best way to make money on Quora?
+  - 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 prajjwal1/bert-small
-  results:
-  - task:
-      type: information-retrieval
-      name: Information Retrieval
-    dataset:
-      name: val
-      type: val
-    metrics:
-    - type: cosine_accuracy@1
-      value: 0.761525
-      name: Cosine Accuracy@1
-    - type: cosine_accuracy@3
-      value: 0.826125
-      name: Cosine Accuracy@3
-    - type: cosine_accuracy@5
-      value: 0.85095
-      name: Cosine Accuracy@5
-    - type: cosine_precision@1
-      value: 0.761525
-      name: Cosine Precision@1
-    - type: cosine_precision@3
-      value: 0.275375
-      name: Cosine Precision@3
-    - type: cosine_precision@5
-      value: 0.17019000000000004
-      name: Cosine Precision@5
-    - type: cosine_recall@1
-      value: 0.761525
-      name: Cosine Recall@1
-    - type: cosine_recall@3
-      value: 0.826125
-      name: Cosine Recall@3
-    - type: cosine_recall@5
-      value: 0.85095
-      name: Cosine Recall@5
-    - type: cosine_ndcg@10
-      value: 0.8202534934281767
-      name: Cosine Ndcg@10
-    - type: cosine_mrr@1
-      value: 0.761525
-      name: Cosine Mrr@1
-    - type: cosine_mrr@5
-      value: 0.7961479166666627
-      name: Cosine Mrr@5
-    - type: cosine_mrr@10
-      value: 0.8004402281746008
-      name: Cosine Mrr@10
-    - type: cosine_map@100
-      value: 0.8038638243708912
-      name: Cosine Map@100
 ---
 
 # SentenceTransformer based on prajjwal1/bert-small
@@ -157,12 +85,12 @@ 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 = [
-    'How do you earn money on Quora?',
-    'What is the best way to make money on Quora?',
-    'How do you earn not money on Quora ?',
+    '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)
@@ -171,9 +99,9 @@ print(embeddings.shape)
 # Get the similarity scores for the embeddings
 similarities = model.similarity(embeddings, embeddings)
 print(similarities)
-# tensor([[ 1.0001,  0.9996, -0.3001],
-#         [ 0.9996,  1.0000, -0.3007],
-#         [-0.3001, -0.3007,  1.0003]])
+# tensor([[1.0000, 0.8563, 0.0594],
+#         [0.8563, 1.0000, 0.1245],
+#         [0.0594, 0.1245, 1.0000]])
 ```
 
 <!--
@@ -200,32 +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  | 0.7615     |
-| cosine_accuracy@3  | 0.8261     |
-| cosine_accuracy@5  | 0.8509     |
-| cosine_precision@1 | 0.7615     |
-| cosine_precision@3 | 0.2754     |
-| cosine_precision@5 | 0.1702     |
-| cosine_recall@1    | 0.7615     |
-| cosine_recall@3    | 0.8261     |
-| cosine_recall@5    | 0.8509     |
-| **cosine_ndcg@10** | **0.8203** |
-| cosine_mrr@1       | 0.7615     |
-| cosine_mrr@5       | 0.7961     |
-| cosine_mrr@10      | 0.8004     |
-| cosine_map@100     | 0.8039     |
-
 <!--
 ## Bias, Risks and Limitations
 
@@ -244,49 +146,23 @@ You can finetune this model on your own dataset.
 
 #### Unnamed Dataset
 
-* Size: 359,999 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                                                                          |
-  |:--------|:---------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
-  | type    | string                                                                           | string                                                                            | string                                                                            |
-  | details | <ul><li>min: 6 tokens</li><li>mean: 15.4 tokens</li><li>max: 60 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 15.45 tokens</li><li>max: 78 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 16.07 tokens</li><li>max: 62 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>Shall I upgrade not my iPhone 5s to iOS 10 final version ?</code>                                             |
-  | <code>Do Census Bureau income figures count sources of unearned income, or do they just count earned income?</code> | <code>Do Census Bureau income figures count sources of unearned income, or do they just count earned income?</code> | <code>Do Census Bureau income figures count sources of unearned income, or do income just count earned they?</code> |
-  | <code>Who has the highest IQ?</code>                                                                                | <code>Who has the highest IQ?</code>                                                                                | <code>the highest IQ has Who?</code>                                                                                |
-* Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
-  ```json
-  {
-      "scale": 1.0,
-      "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                                                                          |
+  |         | sentence_0                                                                        | sentence_1                                                                        | sentence_2                                                                        |
   |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
   | type    | string                                                                            | string                                                                            | string                                                                            |
-  | details | <ul><li>min: 6 tokens</li><li>mean: 15.86 tokens</li><li>max: 65 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 15.94 tokens</li><li>max: 65 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 16.46 tokens</li><li>max: 66 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>What are some mind-blowing Iphone gadgets and tools that most people don't know about?</code>               | <code>What are some mind-blowing iphone tools that most people don't know about?</code>                           | <code>most people are some mind-blowing Iphone gadgets and tools that Whatdon't know about?</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>If FOX News is not the conservative news station , which cable news network is for liberals / progressives ?</code> |
-  | <code>How can guys last longer during sex?</code>                                                                 | <code>How do I last longer in sex?</code>                                                                         | <code>How can guys last not longer during sex ?</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": 1.0,
+      "scale": 20.0,
       "similarity_fct": "cos_sim",
       "gather_across_devices": false
   }
@@ -295,49 +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`: 0.001
-- `max_steps`: 14060
-- `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`: 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`: 0.001
+- `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`: 14060
+- `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
@@ -365,14 +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
@@ -382,23 +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
@@ -425,167 +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
-<details><summary>Click to expand</summary>
+| 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        |
 
-| Epoch  | Step  | Training Loss | Validation Loss | val_cosine_ndcg@10 |
-|:------:|:-----:|:-------------:|:---------------:|:------------------:|
-| 0      | 0     | -             | 5.9531          | 0.7603             |
-| 0.0711 | 100   | 5.9694        | 5.7072          | 0.7792             |
-| 0.1422 | 200   | 5.7181        | 5.4263          | 0.7865             |
-| 0.2134 | 300   | 5.5628        | 5.3443          | 0.7829             |
-| 0.2845 | 400   | 5.4947        | 5.3221          | 0.7774             |
-| 0.3556 | 500   | 5.4597        | 5.3180          | 0.7741             |
-| 0.4267 | 600   | 5.4387        | 5.3158          | 0.7737             |
-| 0.4979 | 700   | 5.423         | 5.3141          | 0.7751             |
-| 0.5690 | 800   | 5.4108        | 5.3109          | 0.7848             |
-| 0.6401 | 900   | 5.397         | 5.2923          | 0.8008             |
-| 0.7112 | 1000  | 5.3724        | 5.2839          | 0.8004             |
-| 0.7824 | 1100  | 5.3625        | 5.2804          | 0.8007             |
-| 0.8535 | 1200  | 5.355         | 5.2777          | 0.8013             |
-| 0.9246 | 1300  | 5.3499        | 5.2748          | 0.8030             |
-| 0.9957 | 1400  | 5.3442        | 5.2729          | 0.8067             |
-| 1.0669 | 1500  | 5.3382        | 5.2624          | 0.8103             |
-| 1.1380 | 1600  | 5.3254        | 5.2557          | 0.8138             |
-| 1.2091 | 1700  | 5.3159        | 5.2441          | 0.8163             |
-| 1.2802 | 1800  | 5.3035        | 5.2350          | 0.8180             |
-| 1.3514 | 1900  | 5.295         | 5.2303          | 0.8179             |
-| 1.4225 | 2000  | 5.2925        | 5.2292          | 0.8182             |
-| 1.4936 | 2100  | 5.2881        | 5.2271          | 0.8187             |
-| 1.5647 | 2200  | 5.2854        | 5.2258          | 0.8187             |
-| 1.6358 | 2300  | 5.2831        | 5.2258          | 0.8189             |
-| 1.7070 | 2400  | 5.2805        | 5.2247          | 0.8192             |
-| 1.7781 | 2500  | 5.278         | 5.2247          | 0.8186             |
-| 1.8492 | 2600  | 5.2761        | 5.2230          | 0.8184             |
-| 1.9203 | 2700  | 5.2754        | 5.2221          | 0.8185             |
-| 1.9915 | 2800  | 5.274         | 5.2228          | 0.8185             |
-| 2.0626 | 2900  | 5.2722        | 5.2209          | 0.8175             |
-| 2.1337 | 3000  | 5.2708        | 5.2206          | 0.8182             |
-| 2.2048 | 3100  | 5.2686        | 5.2211          | 0.8194             |
-| 2.2760 | 3200  | 5.2666        | 5.2204          | 0.8186             |
-| 2.3471 | 3300  | 5.2671        | 5.2192          | 0.8191             |
-| 2.4182 | 3400  | 5.2657        | 5.2200          | 0.8188             |
-| 2.4893 | 3500  | 5.2638        | 5.2188          | 0.8184             |
-| 2.5605 | 3600  | 5.2635        | 5.2189          | 0.8188             |
-| 2.6316 | 3700  | 5.2624        | 5.2187          | 0.8192             |
-| 2.7027 | 3800  | 5.262         | 5.2178          | 0.8182             |
-| 2.7738 | 3900  | 5.2608        | 5.2175          | 0.8188             |
-| 2.8450 | 4000  | 5.2595        | 5.2179          | 0.8189             |
-| 2.9161 | 4100  | 5.2599        | 5.2163          | 0.8191             |
-| 2.9872 | 4200  | 5.2587        | 5.2162          | 0.8184             |
-| 3.0583 | 4300  | 5.2574        | 5.2168          | 0.8193             |
-| 3.1294 | 4400  | 5.256         | 5.2165          | 0.8197             |
-| 3.2006 | 4500  | 5.2551        | 5.2158          | 0.8188             |
-| 3.2717 | 4600  | 5.2552        | 5.2159          | 0.8188             |
-| 3.3428 | 4700  | 5.2549        | 5.2157          | 0.8192             |
-| 3.4139 | 4800  | 5.2531        | 5.2154          | 0.8192             |
-| 3.4851 | 4900  | 5.2534        | 5.2152          | 0.8191             |
-| 3.5562 | 5000  | 5.2528        | 5.2146          | 0.8197             |
-| 3.6273 | 5100  | 5.2521        | 5.2149          | 0.8193             |
-| 3.6984 | 5200  | 5.2509        | 5.2145          | 0.8199             |
-| 3.7696 | 5300  | 5.2509        | 5.2144          | 0.8189             |
-| 3.8407 | 5400  | 5.2495        | 5.2139          | 0.8195             |
-| 3.9118 | 5500  | 5.2496        | 5.2140          | 0.8195             |
-| 3.9829 | 5600  | 5.2505        | 5.2135          | 0.8193             |
-| 4.0541 | 5700  | 5.2478        | 5.2140          | 0.8197             |
-| 4.1252 | 5800  | 5.2476        | 5.2136          | 0.8196             |
-| 4.1963 | 5900  | 5.248         | 5.2130          | 0.8199             |
-| 4.2674 | 6000  | 5.2482        | 5.2129          | 0.8196             |
-| 4.3385 | 6100  | 5.2466        | 5.2135          | 0.8196             |
-| 4.4097 | 6200  | 5.2461        | 5.2126          | 0.8196             |
-| 4.4808 | 6300  | 5.2453        | 5.2124          | 0.8196             |
-| 4.5519 | 6400  | 5.2448        | 5.2128          | 0.8197             |
-| 4.6230 | 6500  | 5.2439        | 5.2124          | 0.8193             |
-| 4.6942 | 6600  | 5.244         | 5.2123          | 0.8192             |
-| 4.7653 | 6700  | 5.2428        | 5.2114          | 0.8192             |
-| 4.8364 | 6800  | 5.2433        | 5.2112          | 0.8197             |
-| 4.9075 | 6900  | 5.2439        | 5.2117          | 0.8194             |
-| 4.9787 | 7000  | 5.2422        | 5.2121          | 0.8204             |
-| 5.0498 | 7100  | 5.2425        | 5.2114          | 0.8198             |
-| 5.1209 | 7200  | 5.2418        | 5.2113          | 0.8201             |
-| 5.1920 | 7300  | 5.2416        | 5.2113          | 0.8200             |
-| 5.2632 | 7400  | 5.2405        | 5.2109          | 0.8199             |
-| 5.3343 | 7500  | 5.242         | 5.2106          | 0.8197             |
-| 5.4054 | 7600  | 5.2402        | 5.2105          | 0.8199             |
-| 5.4765 | 7700  | 5.2393        | 5.2108          | 0.8203             |
-| 5.5477 | 7800  | 5.24          | 5.2104          | 0.8198             |
-| 5.6188 | 7900  | 5.2395        | 5.2103          | 0.8201             |
-| 5.6899 | 8000  | 5.2381        | 5.2102          | 0.8198             |
-| 5.7610 | 8100  | 5.2399        | 5.2102          | 0.8195             |
-| 5.8321 | 8200  | 5.2395        | 5.2100          | 0.8195             |
-| 5.9033 | 8300  | 5.2377        | 5.2100          | 0.8197             |
-| 5.9744 | 8400  | 5.238         | 5.2097          | 0.8198             |
-| 6.0455 | 8500  | 5.2372        | 5.2097          | 0.8200             |
-| 6.1166 | 8600  | 5.2368        | 5.2095          | 0.8200             |
-| 6.1878 | 8700  | 5.2378        | 5.2096          | 0.8201             |
-| 6.2589 | 8800  | 5.2372        | 5.2097          | 0.8197             |
-| 6.3300 | 8900  | 5.2365        | 5.2098          | 0.8197             |
-| 6.4011 | 9000  | 5.2367        | 5.2092          | 0.8199             |
-| 6.4723 | 9100  | 5.2364        | 5.2093          | 0.8197             |
-| 6.5434 | 9200  | 5.2362        | 5.2095          | 0.8202             |
-| 6.6145 | 9300  | 5.2359        | 5.2096          | 0.8199             |
-| 6.6856 | 9400  | 5.2345        | 5.2095          | 0.8203             |
-| 6.7568 | 9500  | 5.2362        | 5.2090          | 0.8202             |
-| 6.8279 | 9600  | 5.2353        | 5.2089          | 0.8201             |
-| 6.8990 | 9700  | 5.2346        | 5.2090          | 0.8203             |
-| 6.9701 | 9800  | 5.2354        | 5.2090          | 0.8202             |
-| 7.0413 | 9900  | 5.234         | 5.2089          | 0.8202             |
-| 7.1124 | 10000 | 5.2334        | 5.2087          | 0.8202             |
-| 7.1835 | 10100 | 5.2342        | 5.2089          | 0.8204             |
-| 7.2546 | 10200 | 5.2342        | 5.2089          | 0.8204             |
-| 7.3257 | 10300 | 5.2336        | 5.2085          | 0.8203             |
-| 7.3969 | 10400 | 5.2347        | 5.2086          | 0.8206             |
-| 7.4680 | 10500 | 5.2326        | 5.2086          | 0.8203             |
-| 7.5391 | 10600 | 5.2336        | 5.2082          | 0.8201             |
-| 7.6102 | 10700 | 5.2328        | 5.2084          | 0.8202             |
-| 7.6814 | 10800 | 5.2328        | 5.2085          | 0.8203             |
-| 7.7525 | 10900 | 5.2321        | 5.2083          | 0.8201             |
-| 7.8236 | 11000 | 5.2332        | 5.2082          | 0.8202             |
-| 7.8947 | 11100 | 5.2325        | 5.2082          | 0.8202             |
-| 7.9659 | 11200 | 5.2331        | 5.2082          | 0.8200             |
-| 8.0370 | 11300 | 5.2322        | 5.2081          | 0.8202             |
-| 8.1081 | 11400 | 5.2324        | 5.2082          | 0.8206             |
-| 8.1792 | 11500 | 5.2318        | 5.2080          | 0.8200             |
-| 8.2504 | 11600 | 5.2314        | 5.2082          | 0.8202             |
-| 8.3215 | 11700 | 5.2318        | 5.2082          | 0.8202             |
-| 8.3926 | 11800 | 5.2317        | 5.2078          | 0.8203             |
-| 8.4637 | 11900 | 5.2312        | 5.2078          | 0.8202             |
-| 8.5349 | 12000 | 5.2327        | 5.2079          | 0.8201             |
-| 8.6060 | 12100 | 5.2316        | 5.2077          | 0.8203             |
-| 8.6771 | 12200 | 5.2317        | 5.2078          | 0.8204             |
-| 8.7482 | 12300 | 5.2301        | 5.2079          | 0.8202             |
-| 8.8193 | 12400 | 5.2308        | 5.2077          | 0.8201             |
-| 8.8905 | 12500 | 5.2306        | 5.2078          | 0.8200             |
-| 8.9616 | 12600 | 5.231         | 5.2077          | 0.8200             |
-| 9.0327 | 12700 | 5.2307        | 5.2076          | 0.8199             |
-| 9.1038 | 12800 | 5.2309        | 5.2076          | 0.8201             |
-| 9.1750 | 12900 | 5.2301        | 5.2076          | 0.8200             |
-| 9.2461 | 13000 | 5.231         | 5.2076          | 0.8202             |
-| 9.3172 | 13100 | 5.2312        | 5.2075          | 0.8201             |
-| 9.3883 | 13200 | 5.2304        | 5.2077          | 0.8204             |
-| 9.4595 | 13300 | 5.2304        | 5.2075          | 0.8202             |
-| 9.5306 | 13400 | 5.2312        | 5.2076          | 0.8203             |
-| 9.6017 | 13500 | 5.2304        | 5.2076          | 0.8204             |
-| 9.6728 | 13600 | 5.2309        | 5.2076          | 0.8203             |
-| 9.7440 | 13700 | 5.23          | 5.2075          | 0.8202             |
-| 9.8151 | 13800 | 5.2301        | 5.2075          | 0.8201             |
-| 9.8862 | 13900 | 5.231         | 5.2075          | 0.8203             |
-| 9.9573 | 14000 | 5.2303        | 5.2075          | 0.8203             |
-
-</details>
 
 ### Framework Versions
 - Python: 3.10.18

eval/Information-Retrieval_evaluation_val_results.csv

@@ -461,3 +461,54 @@ epoch,steps,cosine-Accuracy@1,cosine-Accuracy@3,cosine-Accuracy@5,cosine-Precisi
 9.815078236130867,13800,0.761775,0.825825,0.85075,0.761775,0.761775,0.275275,0.825825,0.17015,0.85075,0.761775,0.7961812499999961,0.8004442063492047,0.8201302361968327,0.8038924254433807
 9.88620199146515,13900,0.76165,0.8262,0.8508,0.76165,0.76165,0.2754,0.8262,0.17016,0.8508,0.76165,0.7961833333333295,0.8005036607142841,0.8202859573683243,0.8039239466787359
 9.95732574679943,14000,0.761525,0.826125,0.85095,0.761525,0.761525,0.275375,0.826125,0.17019000000000004,0.85095,0.761525,0.7961479166666627,0.8004402281746008,0.8202534934281767,0.8038638243708912
+0,0,0.70285,0.79605,0.8218,0.70285,0.70285,0.26535,0.79605,0.16436,0.8218,0.70285,0.7512891666666622,0.7555783333333311,0.7794223255349312,0.7588558044000856
+0.14347202295552366,100,0.719,0.84285,0.872675,0.719,0.719,0.28095,0.84285,0.174535,0.872675,0.719,0.7830449999999936,0.7875145634920601,0.8164610131170594,0.7906443623737947
+0.28694404591104733,200,0.720475,0.8441,0.8731,0.720475,0.720475,0.2813666666666666,0.8441,0.17462000000000003,0.8731,0.720475,0.7841733333333266,0.7884872916666616,0.8171180249207256,0.7915054648946475
+0.430416068866571,300,0.734225,0.847,0.87485,0.734225,0.734225,0.2823333333333333,0.847,0.17497000000000001,0.87485,0.734225,0.792364583333327,0.7966418452380913,0.823543683794261,0.7997161682861882
+0.5738880918220947,400,0.767825,0.85415,0.879475,0.767825,0.767825,0.2847166666666667,0.85415,0.17589500000000002,0.879475,0.767825,0.8127879166666606,0.8170799999999967,0.8399432792184387,0.8200855451322794
+0.7173601147776184,500,0.7684,0.85535,0.881075,0.7684,0.7684,0.28511666666666663,0.85535,0.176215,0.881075,0.7684,0.813672499999994,0.8180551190476166,0.8411684249227638,0.8211524512569452
+0.860832137733142,600,0.770075,0.856575,0.883375,0.770075,0.770075,0.285525,0.856575,0.176675,0.883375,0.770075,0.8152941666666604,0.8196073908730117,0.8428450304728525,0.8226640279051873
+1.0043041606886658,700,0.77065,0.8581,0.884225,0.77065,0.77065,0.2860333333333333,0.8581,0.176845,0.884225,0.77065,0.8159979166666597,0.8204329067460283,0.8438585312774513,0.8234774368034475
+1.1477761836441893,800,0.772,0.8595,0.885475,0.772,0.772,0.2864999999999999,0.8595,0.177095,0.885475,0.772,0.8172545833333261,0.8216476984126937,0.8450234064355687,0.8246727126545477
+1.291248206599713,900,0.772025,0.859125,0.8859,0.772025,0.772025,0.28637499999999994,0.859125,0.17718000000000003,0.8859,0.772025,0.8173566666666607,0.8217971825396798,0.8453118351395867,0.8248254459650096
+1.4347202295552366,1000,0.7729,0.859775,0.886875,0.7729,0.7729,0.28659166666666663,0.859775,0.17737500000000003,0.886875,0.7729,0.8180929166666607,0.8224405753968238,0.8458532846321035,0.825523835584324
+1.5781922525107603,1100,0.773575,0.860275,0.88775,0.773575,0.773575,0.2867583333333333,0.860275,0.17755,0.88775,0.773575,0.8187566666666616,0.823100605158728,0.8465896111780518,0.826152915497014
+1.721664275466284,1200,0.77435,0.8607,0.88835,0.77435,0.77435,0.28689999999999993,0.8607,0.17767,0.88835,0.77435,0.819414999999994,0.8237554067460292,0.8471635033699103,0.8268239553737456
+1.8651362984218078,1300,0.774725,0.8618,0.8893,0.774725,0.774725,0.2872666666666666,0.8618,0.17786000000000002,0.8893,0.774725,0.8200458333333279,0.8243714087301552,0.8478746522446807,0.8274045280642844
+2.0086083213773316,1400,0.77535,0.862225,0.88985,0.77535,0.77535,0.2874083333333333,0.862225,0.17797000000000002,0.88985,0.77535,0.8206862499999943,0.8250188888888853,0.8485109476637894,0.8280391911329523
+2.152080344332855,1500,0.77595,0.862725,0.89,0.77595,0.77595,0.287575,0.862725,0.17800000000000002,0.89,0.77595,0.8211174999999945,0.8255692956349164,0.8491781941787744,0.8285374285017794
+2.2955523672883786,1600,0.7767,0.863225,0.8902,0.7767,0.7767,0.2877416666666667,0.863225,0.17804000000000003,0.8902,0.7767,0.8216608333333275,0.8260917757936465,0.8496076724497309,0.8290711273746223
+2.4390243902439024,1700,0.777225,0.863475,0.891225,0.777225,0.777225,0.28782499999999994,0.863475,0.17824500000000001,0.891225,0.777225,0.8222145833333278,0.8265672817460276,0.8500954337191586,0.8295570818284077
+2.582496413199426,1800,0.77805,0.8639,0.8913,0.77805,0.77805,0.2879666666666666,0.8639,0.17826,0.8913,0.77805,0.8227304166666612,0.827145585317457,0.850644080505664,0.8301130910406217
+2.72596843615495,1900,0.778275,0.86375,0.89145,0.778275,0.778275,0.28791666666666665,0.86375,0.17829000000000003,0.89145,0.778275,0.8229012499999945,0.8273325496031723,0.8508192713538839,0.8302895273161849
+2.869440459110473,2000,0.77855,0.864725,0.892125,0.77855,0.77855,0.2882416666666666,0.864725,0.17842500000000003,0.892125,0.77855,0.8233962499999948,0.8278009722222194,0.8512696523745088,0.8307845745575778
+3.012912482065997,2100,0.779125,0.8652,0.892625,0.779125,0.779125,0.2884,0.8652,0.17852500000000004,0.892625,0.779125,0.8240054166666613,0.8283730357142838,0.8517705008752033,0.8313728112076162
+3.1563845050215207,2200,0.78015,0.865575,0.8929,0.78015,0.78015,0.288525,0.865575,0.17858000000000002,0.8929,0.78015,0.824600833333328,0.8290193452380925,0.8524261174442127,0.8319848134194368
+3.2998565279770444,2300,0.78065,0.86615,0.892975,0.78065,0.78065,0.2887166666666667,0.86615,0.178595,0.892975,0.78065,0.8250170833333279,0.8294674404761879,0.8528264662625589,0.8324378340650243
+3.443328550932568,2400,0.78115,0.8657,0.89325,0.78115,0.78115,0.2885666666666666,0.8657,0.17865000000000006,0.89325,0.78115,0.8253199999999944,0.829710376984124,0.8529684135498555,0.8327162907465414
+3.586800573888092,2500,0.782425,0.867,0.893425,0.782425,0.782425,0.2889999999999999,0.867,0.17868499999999998,0.893425,0.782425,0.8262479166666608,0.8307461111111079,0.8539413492468615,0.833704350343306
+3.7302725968436157,2600,0.785025,0.86815,0.8947,0.785025,0.785025,0.2893833333333333,0.86815,0.17894000000000002,0.8947,0.785025,0.8282516666666608,0.8326595138888846,0.8555509282711606,0.835614215395537
+3.8737446197991394,2700,0.78835,0.869425,0.8953,0.78835,0.78835,0.2898083333333333,0.869425,0.17906000000000002,0.8953,0.78835,0.8303924999999946,0.8348711805555517,0.8574317937994774,0.8378084083914124
+4.017216642754663,2800,0.789625,0.869975,0.896375,0.789625,0.789625,0.2899916666666666,0.869975,0.17927500000000002,0.896375,0.789625,0.8315524999999954,0.8359549603174564,0.8584329706633668,0.8388745159081235
+4.160688665710187,2900,0.7904,0.870225,0.8966,0.7904,0.7904,0.29007499999999997,0.870225,0.17932000000000003,0.8966,0.7904,0.8321333333333286,0.8365512301587261,0.8589791279951865,0.8394417496177948
+4.30416068866571,3000,0.791,0.87075,0.896925,0.791,0.791,0.29025,0.87075,0.17938500000000004,0.896925,0.791,0.8326162499999953,0.8370420039682492,0.8594495308982596,0.8399103794062596
+4.4476327116212335,3100,0.7909,0.8707,0.89715,0.7909,0.7909,0.2902333333333333,0.8707,0.17943,0.89715,0.7909,0.8325645833333286,0.8370284523809475,0.859566366154815,0.8398713536662339
+4.591104734576757,3200,0.791,0.8714,0.8973,0.791,0.791,0.29046666666666665,0.8714,0.17946000000000004,0.8973,0.791,0.8327691666666618,0.8372275099206298,0.8597537767314556,0.8400765245602044
+4.734576757532281,3300,0.7913,0.87155,0.89775,0.7913,0.7913,0.2905166666666666,0.87155,0.17955,0.89775,0.7913,0.8331179166666621,0.8375202876984075,0.8599949949176163,0.8403721064349383
+4.878048780487805,3400,0.791675,0.87175,0.898,0.791675,0.791675,0.2905833333333333,0.87175,0.1796,0.898,0.791675,0.8334462499999957,0.8378570833333279,0.8603339594646136,0.8406951566811449
+5.0215208034433285,3500,0.791975,0.872325,0.898175,0.791975,0.791975,0.2907749999999999,0.872325,0.17963500000000002,0.898175,0.791975,0.8337024999999952,0.8381229563492009,0.8605866702778303,0.8409624835010298
+5.164992826398852,3600,0.792875,0.872425,0.898625,0.792875,0.792875,0.2908083333333333,0.872425,0.17972500000000002,0.898625,0.792875,0.8343720833333287,0.8387630853174556,0.8611154131232631,0.8416006979310702
+5.308464849354376,3700,0.795075,0.873425,0.900075,0.795075,0.795075,0.29114166666666663,0.873425,0.18001500000000004,0.900075,0.795075,0.8360816666666618,0.8403687202380905,0.862515115440112,0.8431846364719889
+5.4519368723099,3800,0.795475,0.8736,0.9,0.795475,0.795475,0.2912,0.8736,0.18,0.9,0.795475,0.8363358333333288,0.8406914682539638,0.8628528597721815,0.8434900769937785
+5.5954088952654235,3900,0.79585,0.873925,0.9002,0.79585,0.79585,0.2913083333333333,0.873925,0.18004000000000003,0.9002,0.79585,0.8367083333333285,0.8410683035714231,0.8632126094245476,0.843847672580781
+5.738880918220947,4000,0.795925,0.87395,0.9003,0.795925,0.795925,0.2913166666666666,0.87395,0.18006,0.9003,0.795925,0.8368241666666619,0.8411607341269797,0.8632362511657556,0.8439728103363221
+5.882352941176471,4100,0.796225,0.873875,0.900375,0.796225,0.796225,0.2912916666666666,0.873875,0.180075,0.900375,0.796225,0.836939999999995,0.8412853472222173,0.8633881265956905,0.8440847141806891
+6.025824964131994,4200,0.7963,0.87395,0.900275,0.7963,0.7963,0.29131666666666667,0.87395,0.180055,0.900275,0.7963,0.8370295833333288,0.8413968650793606,0.8634661920710485,0.8442117176658458
+6.169296987087518,4300,0.796625,0.874375,0.9004,0.796625,0.796625,0.2914583333333333,0.874375,0.18008000000000002,0.9004,0.796625,0.8372995833333283,0.8416971329365032,0.863770166922786,0.8444891316790374
+6.312769010043041,4400,0.7964,0.874075,0.90055,0.7964,0.7964,0.29135833333333333,0.874075,0.18011000000000002,0.90055,0.7964,0.8371683333333285,0.8415165575396771,0.8636091649093294,0.8443133788931692
+6.456241032998565,4500,0.796425,0.8742,0.900575,0.796425,0.796425,0.29139999999999994,0.8742,0.18011500000000003,0.900575,0.796425,0.8372233333333284,0.8415766964285661,0.8636591002412395,0.8443833078274336
+6.599713055954089,4600,0.796725,0.874275,0.900675,0.796725,0.796725,0.291425,0.874275,0.18013500000000002,0.900675,0.796725,0.8373820833333288,0.8417151587301536,0.8637637204512882,0.844523830924215
+6.743185078909613,4700,0.796575,0.8743,0.90045,0.796575,0.796575,0.2914333333333333,0.8743,0.18009,0.90045,0.796575,0.8372449999999956,0.8416117361111064,0.8636712529829847,0.8444289062161769
+6.886657101865136,4800,0.79665,0.8745,0.900525,0.79665,0.79665,0.2915,0.8745,0.18010500000000002,0.900525,0.79665,0.8373320833333286,0.8416871428571374,0.863729044462657,0.8445069828327856
+7.03012912482066,4900,0.79655,0.87425,0.9004,0.79655,0.79655,0.2914166666666666,0.87425,0.18008000000000002,0.9004,0.79655,0.8372299999999956,0.8416038690476145,0.8636646643385855,0.844421583046012
+7.173601147776184,5000,0.7966,0.87425,0.900575,0.7966,0.7966,0.2914166666666666,0.87425,0.180115,0.900575,0.7966,0.8372962499999956,0.8416481150793601,0.8637140791780538,0.8444611118975183

final_metrics.json

@@ -1,16 +1,16 @@
 {
-  "val_cosine_accuracy@1": 0.82925,
-  "val_cosine_accuracy@3": 0.903025,
-  "val_cosine_accuracy@5": 0.931175,
-  "val_cosine_precision@1": 0.82925,
-  "val_cosine_precision@3": 0.3010083333333333,
-  "val_cosine_precision@5": 0.186235,
-  "val_cosine_recall@1": 0.82925,
-  "val_cosine_recall@3": 0.903025,
-  "val_cosine_recall@5": 0.931175,
-  "val_cosine_ndcg@10": 0.8950131360828151,
-  "val_cosine_mrr@1": 0.82925,
-  "val_cosine_mrr@5": 0.8687345833333282,
-  "val_cosine_mrr@10": 0.8731489384920591,
-  "val_cosine_map@100": 0.8752091976044037
+  "val_cosine_accuracy@1": 0.7614,
+  "val_cosine_accuracy@3": 0.82615,
+  "val_cosine_accuracy@5": 0.850775,
+  "val_cosine_precision@1": 0.7614,
+  "val_cosine_precision@3": 0.2753833333333333,
+  "val_cosine_precision@5": 0.170155,
+  "val_cosine_recall@1": 0.7614,
+  "val_cosine_recall@3": 0.82615,
+  "val_cosine_recall@5": 0.850775,
+  "val_cosine_ndcg@10": 0.8201550154419872,
+  "val_cosine_mrr@1": 0.7614,
+  "val_cosine_mrr@5": 0.7960862499999959,
+  "val_cosine_mrr@10": 0.8003843253968239,
+  "val_cosine_map@100": 0.8038332983359062
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92f71bc07a682285115d27c1ff96626310f991575725ca37984cfd4651023a66
+oid sha256:5db1674c675ac3fecdc903e40be0f70444de31052681e25137b3a8818fa28d06
 size 114011616

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97dfabb4d1b0f4e7472f63fe7d96632afc7ca09080738d20201c498fcf74eb45
+oid sha256:9d4c139a71ec4d4b0dfbafa31c4950656cd8f9c5e2ab0d688a8a2c2fdc8272c3
 size 6161