Training in progress, step 14060

Information-Retrieval_evaluation_val_results.csv

@@ -1,3 +1,4 @@
 epoch,steps,cosine-Accuracy@1,cosine-Accuracy@3,cosine-Accuracy@5,cosine-Precision@1,cosine-Recall@1,cosine-Precision@3,cosine-Recall@3,cosine-Precision@5,cosine-Recall@5,cosine-MRR@1,cosine-MRR@5,cosine-MRR@10,cosine-NDCG@10,cosine-MAP@100
 -1,-1,0.9208,0.9698,0.9842,0.9208,0.9208,0.3232666666666667,0.9698,0.19684,0.9842,0.9208,0.9460899999999998,0.9476021428571432,0.9593212690041523,0.9479260307963899
 -1,-1,0.9184,0.97,0.9852,0.9184,0.9184,0.3233333333333333,0.97,0.19703999999999997,0.9852,0.9184,0.9451366666666663,0.9466038095238087,0.9586270476620361,0.946959374340519
+-1,-1,0.829575,0.9048,0.9324,0.829575,0.829575,0.3016,0.9048,0.18648000000000003,0.9324,0.829575,0.8693266666666628,0.873717658730154,0.8957411186558171,0.8757871539962314

README.md

@@ -5,114 +5,38 @@ tags:
 - feature-extraction
 - dense
 - generated_from_trainer
-- dataset_size:359997
+- dataset_size:100000
 - loss:MultipleNegativesRankingLoss
 base_model: prajjwal1/bert-small
 widget:
-- source_sentence: When do you use Ms. or Mrs.? Is one for a married woman and one
-    for one that's not married? Which one is for what?
+- source_sentence: How do I polish my English skills?
   sentences:
-  - When do you use Ms. or Mrs.? Is one for a married woman and one for one that's
-    not married? Which one is for what?
-  - Nations that do/does otherwise? Which one do I use?
-  - What is the best way to make money on Quora?
-- source_sentence: Which ointment is applied to the face of UFC fighters at the commencement
-    of a bout? What does it do?
+  - How can we polish English skills?
+  - Why should I move to Israel as a Jew?
+  - What are vitamins responsible for?
+- source_sentence: Can I use the Kozuka Gothic Pro font as a font-face on my web site?
   sentences:
-  - Why don't bikes have a gear indicator?
-  - Which ointment is applied to the face of UFC fighters at the commencement of a
-    bout? What does it do?
-  - How do I get the body of a UFC Fighter?
-- source_sentence: Do you love the life you live?
+  - Can I use the Kozuka Gothic Pro font as a font-face on my web site?
+  - Why are Google, Facebook, YouTube and other social networking sites banned in
+    China?
+  - What font is used in Bloomberg Terminal?
+- source_sentence: Is Quora the best Q&A site?
   sentences:
-  - How can I save a Snapchat video that others posted?
-  - Do you love the life you're living?
-  - What is the best way to find a person just using their phone by trying to track
-    the other persons phone and get a location from it?
-- source_sentence: Can I do shoulder and triceps workout on same day? What other combinations
-    like this can I do?
+  - What was the best Quora question ever?
+  - Is Quora the best inquiry site?
+  - Where do I buy Oway hair products online?
+- source_sentence: How can I customize my walking speed on Google Maps?
   sentences:
-  - Can gym just 3 days/week. Is it better to do full body workouts on those 3 days
-    or should I split it into Chest-triceps, Back-biceps, Legs-shoulders?
-  - How do I die and make it look like an accident?
-  - Can I do shoulder and triceps workout on same day? What other combinations like
-    this can I do?
-- source_sentence: Ordered food on Swiggy 3 days ago.After accepting my money, said
-    no more on Menu! When if ever will I atleast get refund in cr card a/c?
+  - How do I bring back Google maps icon in my home screen?
+  - How many pages are there in all the Harry Potter books combined?
+  - How can I customize my walking speed on Google Maps?
+- source_sentence: DId something exist before the Big Bang?
   sentences:
-  - What is a cheap healthy diet I can keep the same and eat every day?
-  - Is getting to the Tel Aviv airport to catch a 5:30 AM flight very expensive?
-  - 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 can I improve my memory problem?
+  - Where can I buy Fairy Tail Manga?
+  - Is there a scientific name for what existed before the Big Bang?
 pipeline_tag: sentence-similarity
 library_name: sentence-transformers
-metrics:
-- cosine_accuracy@1
-- cosine_accuracy@3
-- cosine_accuracy@5
-- cosine_precision@1
-- cosine_precision@3
-- cosine_precision@5
-- cosine_recall@1
-- cosine_recall@3
-- cosine_recall@5
-- cosine_ndcg@10
-- cosine_mrr@1
-- cosine_mrr@5
-- cosine_mrr@10
-- cosine_map@100
-model-index:
-- name: SentenceTransformer based on prajjwal1/bert-small
-  results:
-  - task:
-      type: information-retrieval
-      name: Information Retrieval
-    dataset:
-      name: val
-      type: val
-    metrics:
-    - type: cosine_accuracy@1
-      value: 0.829675
-      name: Cosine Accuracy@1
-    - type: cosine_accuracy@3
-      value: 0.9048
-      name: Cosine Accuracy@3
-    - type: cosine_accuracy@5
-      value: 0.93245
-      name: Cosine Accuracy@5
-    - type: cosine_precision@1
-      value: 0.829675
-      name: Cosine Precision@1
-    - type: cosine_precision@3
-      value: 0.3016
-      name: Cosine Precision@3
-    - type: cosine_precision@5
-      value: 0.18649000000000004
-      name: Cosine Precision@5
-    - type: cosine_recall@1
-      value: 0.829675
-      name: Cosine Recall@1
-    - type: cosine_recall@3
-      value: 0.9048
-      name: Cosine Recall@3
-    - type: cosine_recall@5
-      value: 0.93245
-      name: Cosine Recall@5
-    - type: cosine_ndcg@10
-      value: 0.8957919450437679
-      name: Cosine Ndcg@10
-    - type: cosine_mrr@1
-      value: 0.829675
-      name: Cosine Mrr@1
-    - type: cosine_mrr@5
-      value: 0.8693824999999958
-      name: Cosine Mrr@5
-    - type: cosine_mrr@10
-      value: 0.8737714285714238
-      name: Cosine Mrr@10
-    - type: cosine_map@100
-      value: 0.8758361833602419
-      name: Cosine Map@100
 ---
 
 # SentenceTransformer based on prajjwal1/bert-small
@@ -161,12 +85,12 @@ Then you can load this model and run inference.
 from sentence_transformers import SentenceTransformer
 
 # Download from the 🤗 Hub
-model = SentenceTransformer("redis/model-a-baseline")
+model = SentenceTransformer("sentence_transformers_model_id")
 # Run inference
 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?',
-    '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?',
-    'Is getting to the Tel Aviv airport to catch a 5:30 AM flight very expensive?',
+    'DId something exist before the Big Bang?',
+    'Is there a scientific name for what existed before the Big Bang?',
+    'Where can I buy Fairy Tail Manga?',
 ]
 embeddings = model.encode(sentences)
 print(embeddings.shape)
@@ -175,9 +99,9 @@ print(embeddings.shape)
 # Get the similarity scores for the embeddings
 similarities = model.similarity(embeddings, embeddings)
 print(similarities)
-# tensor([[1.0000, 1.0000, 0.1381],
-#         [1.0000, 1.0000, 0.1381],
-#         [0.1381, 0.1381, 1.0000]])
+# tensor([[ 1.0000,  0.7596, -0.0398],
+#         [ 0.7596,  1.0000, -0.0308],
+#         [-0.0398, -0.0308,  1.0000]])
 ```
 
 <!--
@@ -204,32 +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  | 0.8297     |
-| cosine_accuracy@3  | 0.9048     |
-| cosine_accuracy@5  | 0.9325     |
-| cosine_precision@1 | 0.8297     |
-| cosine_precision@3 | 0.3016     |
-| cosine_precision@5 | 0.1865     |
-| cosine_recall@1    | 0.8297     |
-| cosine_recall@3    | 0.9048     |
-| cosine_recall@5    | 0.9325     |
-| **cosine_ndcg@10** | **0.8958** |
-| cosine_mrr@1       | 0.8297     |
-| cosine_mrr@5       | 0.8694     |
-| cosine_mrr@10      | 0.8738     |
-| cosine_map@100     | 0.8758     |
-
 <!--
 ## Bias, Risks and Limitations
 
@@ -248,45 +146,19 @@ You can finetune this model on your own dataset.
 
 #### Unnamed Dataset
 
-* Size: 359,997 training samples
-* Columns: <code>anchor</code>, <code>positive</code>, and <code>negative</code>
-* Approximate statistics based on the first 1000 samples:
-  |         | anchor                                                                            | positive                                                                          | negative                                                                           |
-  |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|
-  | type    | string                                                                            | string                                                                            | string                                                                             |
-  | details | <ul><li>min: 4 tokens</li><li>mean: 15.46 tokens</li><li>max: 49 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 15.52 tokens</li><li>max: 49 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 17.07 tokens</li><li>max: 128 tokens</li></ul> |
-* Samples:
-  | anchor                                                                          | positive                                                                                             | negative                                                                                                                                                                |
-  |:--------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
-  | <code>Shall I upgrade my iPhone 5s to iOS 10 final version?</code>              | <code>Should I upgrade an iPhone 5s to iOS 10?</code>                                                | <code>How, if at all, is the accent, pitch and voice of gay men different than that of straight men and how accurate is voice in determining sexual orientation?</code> |
-  | <code>Is Donald Trump really going to be the president of United States?</code> | <code>Do you think Donald Trump could conceivably be the next President of the United States?</code> | <code>Can a 15-year-old boy and an 18-year-old girl have sex?</code>                                                                                                    |
-  | <code>What are real tips to improve work life balance?</code>                   | <code>What are the best ways to create a work life balance?</code>                                   | <code>How far is Miami from Fort Lauderdale?</code>                                                                                                                     |
-* Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
-  ```json
-  {
-      "scale": 20.0,
-      "similarity_fct": "cos_sim",
-      "gather_across_devices": false
-  }
-  ```
-
-### Evaluation Dataset
-
-#### Unnamed Dataset
-
-* Size: 40,000 evaluation samples
-* Columns: <code>anchor</code>, <code>positive</code>, and <code>negative</code>
+* Size: 100,000 training samples
+* Columns: <code>sentence_0</code>, <code>sentence_1</code>, and <code>sentence_2</code>
 * Approximate statistics based on the first 1000 samples:
-  |         | anchor                                                                            | positive                                                                          | negative                                                                          |
-  |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
-  | type    | string                                                                            | string                                                                            | string                                                                            |
-  | details | <ul><li>min: 6 tokens</li><li>mean: 15.71 tokens</li><li>max: 65 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 15.79 tokens</li><li>max: 65 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 16.82 tokens</li><li>max: 78 tokens</li></ul> |
+  |         | sentence_0                                                                        | sentence_1                                                                       | sentence_2                                                                         |
+  |:--------|:----------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|
+  | type    | string                                                                            | string                                                                           | string                                                                             |
+  | details | <ul><li>min: 3 tokens</li><li>mean: 15.53 tokens</li><li>max: 59 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 15.5 tokens</li><li>max: 59 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 16.87 tokens</li><li>max: 128 tokens</li></ul> |
 * Samples:
-  | anchor                                                                                                            | positive                                                                                                          | negative                                                                                                                                  |
-  |:------------------------------------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------------------------------------------------|
-  | <code>Why were feathered dinosaur fossils only found in the last 20 years?</code>                                 | <code>Why were feathered dinosaur fossils only found in the last 20 years?</code>                                 | <code>Why are only few people aware that many dinosaurs had feathers?</code>                                                              |
-  | <code>If FOX News is the conservative news station, which cable news network is for liberals/progressives?</code> | <code>If FOX News is the conservative news station, which cable news network is for liberals/progressives?</code> | <code>How much did Fox News and conservative leaning media networks stoke the anger that contributed to Donald Trump's popularity?</code> |
-  | <code>How can guys last longer during sex?</code>                                                                 | <code>How do I last longer in sex?</code>                                                                         | <code>Why does economics require calculus?</code>                                                                                         |
+  | sentence_0                                                                              | sentence_1                                                                              | sentence_2                                                             |
+  |:----------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------------|:-----------------------------------------------------------------------|
+  | <code>Is there visitor entry facility in Jaipur airport. How much is the ticket?</code> | <code>Is there visitor entry facility in Jaipur airport. How much is the ticket?</code> | <code>How much is the airport tax in bogota?</code>                    |
+  | <code>Which concept is more important: good planning or hard work?</code>               | <code>Which concept is more important: good planning or hard work?</code>               | <code>What is important in life: luck or hard work?</code>             |
+  | <code>What is the most efficient way to make money?</code>                              | <code>How can I make my money make money?</code>                                        | <code>What can one learn about Quantum Mechanics in 10 minutes?</code> |
 * Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
   ```json
   {
@@ -299,49 +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-a-baseline
-- `eval_on_start`: True
+- `multi_dataset_batch_sampler`: round_robin
 
 #### All Hyperparameters
 <details><summary>Click to expand</summary>
 
 - `overwrite_output_dir`: False
 - `do_predict`: False
-- `eval_strategy`: steps
+- `eval_strategy`: no
 - `prediction_loss_only`: True
-- `per_device_train_batch_size`: 256
-- `per_device_eval_batch_size`: 256
+- `per_device_train_batch_size`: 64
+- `per_device_eval_batch_size`: 64
 - `per_gpu_train_batch_size`: None
 - `per_gpu_eval_batch_size`: None
 - `gradient_accumulation_steps`: 1
 - `eval_accumulation_steps`: None
 - `torch_empty_cache_steps`: None
-- `learning_rate`: 2e-05
-- `weight_decay`: 0.001
+- `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
@@ -369,14 +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
@@ -386,23 +245,23 @@ You can finetune this model on your own dataset.
 - `parallelism_config`: None
 - `deepspeed`: None
 - `label_smoothing_factor`: 0.0
-- `optim`: adamw_torch
+- `optim`: adamw_torch_fused
 - `optim_args`: None
 - `adafactor`: False
 - `group_by_length`: False
 - `length_column_name`: length
 - `project`: huggingface
 - `trackio_space_id`: trackio
-- `ddp_find_unused_parameters`: False
+- `ddp_find_unused_parameters`: None
 - `ddp_bucket_cap_mb`: None
 - `ddp_broadcast_buffers`: False
 - `dataloader_pin_memory`: True
 - `dataloader_persistent_workers`: False
 - `skip_memory_metrics`: True
 - `use_legacy_prediction_loop`: False
-- `push_to_hub`: True
+- `push_to_hub`: False
 - `resume_from_checkpoint`: None
-- `hub_model_id`: redis/model-a-baseline
+- `hub_model_id`: None
 - `hub_strategy`: every_save
 - `hub_private_repo`: None
 - `hub_always_push`: False
@@ -429,167 +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  | 0.2284        |
+| 0.6398 | 1000 | 0.0571        |
+| 0.9597 | 1500 | 0.0486        |
+| 1.2796 | 2000 | 0.0378        |
+| 1.5995 | 2500 | 0.0367        |
+| 1.9194 | 3000 | 0.0338        |
+| 2.2393 | 3500 | 0.0327        |
+| 2.5592 | 4000 | 0.0285        |
+| 2.8791 | 4500 | 0.0285        |
 
-| Epoch  | Step  | Training Loss | Validation Loss | val_cosine_ndcg@10 |
-|:------:|:-----:|:-------------:|:---------------:|:------------------:|
-| 0      | 0     | -             | 1.6256          | 0.8046             |
-| 0.0711 | 100   | 1.9658        | 0.3149          | 0.8458             |
-| 0.1422 | 200   | 0.4018        | 0.1192          | 0.8670             |
-| 0.2134 | 300   | 0.1963        | 0.0916          | 0.8733             |
-| 0.2845 | 400   | 0.163         | 0.0803          | 0.8766             |
-| 0.3556 | 500   | 0.1397        | 0.0729          | 0.8783             |
-| 0.4267 | 600   | 0.1261        | 0.0681          | 0.8798             |
-| 0.4979 | 700   | 0.1181        | 0.0640          | 0.8810             |
-| 0.5690 | 800   | 0.1166        | 0.0614          | 0.8818             |
-| 0.6401 | 900   | 0.1068        | 0.0586          | 0.8829             |
-| 0.7112 | 1000  | 0.1001        | 0.0564          | 0.8835             |
-| 0.7824 | 1100  | 0.097         | 0.0549          | 0.8842             |
-| 0.8535 | 1200  | 0.0941        | 0.0530          | 0.8844             |
-| 0.9246 | 1300  | 0.0934        | 0.0515          | 0.8854             |
-| 0.9957 | 1400  | 0.086         | 0.0499          | 0.8859             |
-| 1.0669 | 1500  | 0.081         | 0.0482          | 0.8864             |
-| 1.1380 | 1600  | 0.0778        | 0.0476          | 0.8868             |
-| 1.2091 | 1700  | 0.0734        | 0.0459          | 0.8870             |
-| 1.2802 | 1800  | 0.0744        | 0.0459          | 0.8872             |
-| 1.3514 | 1900  | 0.0734        | 0.0447          | 0.8880             |
-| 1.4225 | 2000  | 0.0695        | 0.0440          | 0.8883             |
-| 1.4936 | 2100  | 0.0671        | 0.0438          | 0.8880             |
-| 1.5647 | 2200  | 0.0703        | 0.0435          | 0.8884             |
-| 1.6358 | 2300  | 0.0658        | 0.0425          | 0.8886             |
-| 1.7070 | 2400  | 0.0695        | 0.0416          | 0.8894             |
-| 1.7781 | 2500  | 0.0665        | 0.0413          | 0.8893             |
-| 1.8492 | 2600  | 0.0648        | 0.0407          | 0.8896             |
-| 1.9203 | 2700  | 0.0668        | 0.0405          | 0.8894             |
-| 1.9915 | 2800  | 0.0636        | 0.0398          | 0.8902             |
-| 2.0626 | 2900  | 0.0583        | 0.0394          | 0.8903             |
-| 2.1337 | 3000  | 0.0583        | 0.0390          | 0.8903             |
-| 2.2048 | 3100  | 0.0563        | 0.0385          | 0.8908             |
-| 2.2760 | 3200  | 0.0588        | 0.0384          | 0.8910             |
-| 2.3471 | 3300  | 0.0586        | 0.0383          | 0.8910             |
-| 2.4182 | 3400  | 0.0557        | 0.0380          | 0.8907             |
-| 2.4893 | 3500  | 0.0561        | 0.0378          | 0.8910             |
-| 2.5605 | 3600  | 0.0557        | 0.0375          | 0.8912             |
-| 2.6316 | 3700  | 0.0553        | 0.0371          | 0.8915             |
-| 2.7027 | 3800  | 0.053         | 0.0371          | 0.8913             |
-| 2.7738 | 3900  | 0.0562        | 0.0369          | 0.8916             |
-| 2.8450 | 4000  | 0.0531        | 0.0368          | 0.8914             |
-| 2.9161 | 4100  | 0.0522        | 0.0363          | 0.8918             |
-| 2.9872 | 4200  | 0.0555        | 0.0363          | 0.8919             |
-| 3.0583 | 4300  | 0.0524        | 0.0363          | 0.8921             |
-| 3.1294 | 4400  | 0.0512        | 0.0356          | 0.8924             |
-| 3.2006 | 4500  | 0.0503        | 0.0356          | 0.8922             |
-| 3.2717 | 4600  | 0.0523        | 0.0355          | 0.8925             |
-| 3.3428 | 4700  | 0.0524        | 0.0351          | 0.8925             |
-| 3.4139 | 4800  | 0.0478        | 0.0351          | 0.8925             |
-| 3.4851 | 4900  | 0.0506        | 0.0347          | 0.8929             |
-| 3.5562 | 5000  | 0.0486        | 0.0344          | 0.8929             |
-| 3.6273 | 5100  | 0.0496        | 0.0344          | 0.8929             |
-| 3.6984 | 5200  | 0.0486        | 0.0345          | 0.8928             |
-| 3.7696 | 5300  | 0.0441        | 0.0343          | 0.8928             |
-| 3.8407 | 5400  | 0.0502        | 0.0342          | 0.8929             |
-| 3.9118 | 5500  | 0.0498        | 0.0341          | 0.8931             |
-| 3.9829 | 5600  | 0.0499        | 0.0342          | 0.8932             |
-| 4.0541 | 5700  | 0.0483        | 0.0339          | 0.8933             |
-| 4.1252 | 5800  | 0.046         | 0.0338          | 0.8933             |
-| 4.1963 | 5900  | 0.0481        | 0.0337          | 0.8933             |
-| 4.2674 | 6000  | 0.0435        | 0.0335          | 0.8936             |
-| 4.3385 | 6100  | 0.0459        | 0.0335          | 0.8935             |
-| 4.4097 | 6200  | 0.0467        | 0.0335          | 0.8933             |
-| 4.4808 | 6300  | 0.0452        | 0.0334          | 0.8937             |
-| 4.5519 | 6400  | 0.0436        | 0.0330          | 0.8940             |
-| 4.6230 | 6500  | 0.0447        | 0.0329          | 0.8940             |
-| 4.6942 | 6600  | 0.0474        | 0.0328          | 0.8940             |
-| 4.7653 | 6700  | 0.0419        | 0.0328          | 0.8940             |
-| 4.8364 | 6800  | 0.0456        | 0.0327          | 0.8939             |
-| 4.9075 | 6900  | 0.0464        | 0.0328          | 0.8940             |
-| 4.9787 | 7000  | 0.0432        | 0.0326          | 0.8940             |
-| 5.0498 | 7100  | 0.0409        | 0.0326          | 0.8939             |
-| 5.1209 | 7200  | 0.0411        | 0.0324          | 0.8941             |
-| 5.1920 | 7300  | 0.0415        | 0.0326          | 0.8940             |
-| 5.2632 | 7400  | 0.0424        | 0.0324          | 0.8943             |
-| 5.3343 | 7500  | 0.0436        | 0.0324          | 0.8942             |
-| 5.4054 | 7600  | 0.0431        | 0.0325          | 0.8942             |
-| 5.4765 | 7700  | 0.0433        | 0.0324          | 0.8941             |
-| 5.5477 | 7800  | 0.0421        | 0.0323          | 0.8943             |
-| 5.6188 | 7900  | 0.0423        | 0.0321          | 0.8944             |
-| 5.6899 | 8000  | 0.0427        | 0.0322          | 0.8947             |
-| 5.7610 | 8100  | 0.0426        | 0.0321          | 0.8946             |
-| 5.8321 | 8200  | 0.0415        | 0.0323          | 0.8944             |
-| 5.9033 | 8300  | 0.0415        | 0.0320          | 0.8946             |
-| 5.9744 | 8400  | 0.0403        | 0.0321          | 0.8947             |
-| 6.0455 | 8500  | 0.0416        | 0.0318          | 0.8949             |
-| 6.1166 | 8600  | 0.0391        | 0.0317          | 0.8949             |
-| 6.1878 | 8700  | 0.0408        | 0.0316          | 0.8949             |
-| 6.2589 | 8800  | 0.0405        | 0.0316          | 0.8950             |
-| 6.3300 | 8900  | 0.041         | 0.0316          | 0.8950             |
-| 6.4011 | 9000  | 0.041         | 0.0316          | 0.8947             |
-| 6.4723 | 9100  | 0.0396        | 0.0315          | 0.8949             |
-| 6.5434 | 9200  | 0.0416        | 0.0315          | 0.8949             |
-| 6.6145 | 9300  | 0.0411        | 0.0315          | 0.8947             |
-| 6.6856 | 9400  | 0.0387        | 0.0315          | 0.8948             |
-| 6.7568 | 9500  | 0.0393        | 0.0315          | 0.8951             |
-| 6.8279 | 9600  | 0.0379        | 0.0314          | 0.8951             |
-| 6.8990 | 9700  | 0.0409        | 0.0313          | 0.8952             |
-| 6.9701 | 9800  | 0.0417        | 0.0312          | 0.8952             |
-| 7.0413 | 9900  | 0.0412        | 0.0312          | 0.8950             |
-| 7.1124 | 10000 | 0.0386        | 0.0312          | 0.8951             |
-| 7.1835 | 10100 | 0.0397        | 0.0312          | 0.8952             |
-| 7.2546 | 10200 | 0.0396        | 0.0311          | 0.8953             |
-| 7.3257 | 10300 | 0.0385        | 0.0312          | 0.8952             |
-| 7.3969 | 10400 | 0.0364        | 0.0310          | 0.8952             |
-| 7.4680 | 10500 | 0.0387        | 0.0310          | 0.8952             |
-| 7.5391 | 10600 | 0.0356        | 0.0309          | 0.8953             |
-| 7.6102 | 10700 | 0.0384        | 0.0310          | 0.8951             |
-| 7.6814 | 10800 | 0.0381        | 0.0308          | 0.8953             |
-| 7.7525 | 10900 | 0.0407        | 0.0309          | 0.8954             |
-| 7.8236 | 11000 | 0.0398        | 0.0308          | 0.8955             |
-| 7.8947 | 11100 | 0.0396        | 0.0307          | 0.8955             |
-| 7.9659 | 11200 | 0.0381        | 0.0307          | 0.8957             |
-| 8.0370 | 11300 | 0.0411        | 0.0308          | 0.8955             |
-| 8.1081 | 11400 | 0.0377        | 0.0307          | 0.8955             |
-| 8.1792 | 11500 | 0.0369        | 0.0307          | 0.8954             |
-| 8.2504 | 11600 | 0.0355        | 0.0307          | 0.8956             |
-| 8.3215 | 11700 | 0.0395        | 0.0307          | 0.8954             |
-| 8.3926 | 11800 | 0.0376        | 0.0306          | 0.8956             |
-| 8.4637 | 11900 | 0.0384        | 0.0307          | 0.8957             |
-| 8.5349 | 12000 | 0.0369        | 0.0306          | 0.8957             |
-| 8.6060 | 12100 | 0.0371        | 0.0306          | 0.8957             |
-| 8.6771 | 12200 | 0.0343        | 0.0306          | 0.8957             |
-| 8.7482 | 12300 | 0.0374        | 0.0305          | 0.8957             |
-| 8.8193 | 12400 | 0.0376        | 0.0305          | 0.8957             |
-| 8.8905 | 12500 | 0.0365        | 0.0305          | 0.8957             |
-| 8.9616 | 12600 | 0.0373        | 0.0304          | 0.8957             |
-| 9.0327 | 12700 | 0.0381        | 0.0305          | 0.8957             |
-| 9.1038 | 12800 | 0.0356        | 0.0305          | 0.8956             |
-| 9.1750 | 12900 | 0.0384        | 0.0305          | 0.8955             |
-| 9.2461 | 13000 | 0.0369        | 0.0304          | 0.8956             |
-| 9.3172 | 13100 | 0.0399        | 0.0304          | 0.8956             |
-| 9.3883 | 13200 | 0.0382        | 0.0304          | 0.8957             |
-| 9.4595 | 13300 | 0.0357        | 0.0304          | 0.8956             |
-| 9.5306 | 13400 | 0.0375        | 0.0304          | 0.8957             |
-| 9.6017 | 13500 | 0.0362        | 0.0304          | 0.8956             |
-| 9.6728 | 13600 | 0.0374        | 0.0304          | 0.8957             |
-| 9.7440 | 13700 | 0.0397        | 0.0304          | 0.8957             |
-| 9.8151 | 13800 | 0.0385        | 0.0304          | 0.8957             |
-| 9.8862 | 13900 | 0.0383        | 0.0304          | 0.8957             |
-| 9.9573 | 14000 | 0.0384        | 0.0304          | 0.8958             |
-
-</details>
 
 ### Framework Versions
 - Python: 3.10.18

eval/Information-Retrieval_evaluation_val_results.csv

@@ -180,3 +180,144 @@ epoch,steps,cosine-Accuracy@1,cosine-Accuracy@3,cosine-Accuracy@5,cosine-Precisi
 9.815078236130867,13800,0.8296,0.904725,0.932475,0.8296,0.8296,0.301575,0.904725,0.18649500000000002,0.932475,0.8296,0.8693120833333294,0.8736897916666616,0.8957134946126672,0.8757585053341062
 9.88620199146515,13900,0.829475,0.904825,0.932425,0.829475,0.829475,0.3016083333333333,0.904825,0.186485,0.932425,0.829475,0.8692816666666627,0.8736694444444394,0.8957054405004242,0.875738183071688
 9.95732574679943,14000,0.829675,0.9048,0.93245,0.829675,0.829675,0.3016,0.9048,0.18649000000000004,0.93245,0.829675,0.8693824999999958,0.8737714285714238,0.8957919450437679,0.8758361833602419
+0,0,0.754525,0.807575,0.830125,0.754525,0.754525,0.26919166666666666,0.807575,0.166025,0.830125,0.754525,0.7830570833333289,0.787073373015871,0.8044871056225573,0.7902066872230316
+0.07112375533428165,100,0.788175,0.8515,0.8754,0.788175,0.788175,0.2838333333333333,0.8515,0.17507999999999999,0.8754,0.788175,0.8216874999999941,0.8261519940476153,0.8459150549027301,0.829169181087181
+0.1422475106685633,200,0.8078,0.875,0.898975,0.8078,0.8078,0.29166666666666663,0.875,0.17979500000000004,0.898975,0.8078,0.8431537499999955,0.847442658730155,0.8675041742945899,0.85001676579445
+0.21337126600284495,300,0.8139,0.882075,0.9063,0.8139,0.8139,0.294025,0.882075,0.18126,0.9063,0.8139,0.8497174999999954,0.8537709821428534,0.8737150227497443,0.8563985748208767
+0.2844950213371266,400,0.816375,0.884475,0.9097,0.816375,0.816375,0.294825,0.884475,0.18194000000000002,0.9097,0.816375,0.8523545833333286,0.85645184523809,0.8766246185595526,0.8589986601030838
+0.35561877667140823,500,0.817925,0.8864,0.911825,0.817925,0.817925,0.2954666666666666,0.8864,0.18236500000000005,0.911825,0.817925,0.8540712499999951,0.8581809722222173,0.8784583584690699,0.8607180206672261
+0.4267425320056899,600,0.81905,0.887875,0.9133,0.81905,0.81905,0.29595833333333327,0.887875,0.18266000000000004,0.9133,0.81905,0.8553095833333285,0.859498859126979,0.8799370224897283,0.861996070829766
+0.49786628733997157,700,0.820825,0.8887,0.91495,0.820825,0.820825,0.29623333333333335,0.8887,0.18299000000000004,0.91495,0.820825,0.8568612499999957,0.8609963591269792,0.8813434328983816,0.8635262113099532
+0.5689900426742532,800,0.8212,0.889525,0.9163,0.8212,0.8212,0.2965083333333333,0.889525,0.18325999999999998,0.9163,0.8212,0.8576537499999951,0.8617598908730091,0.882234040479893,0.8642600344938268
+0.6401137980085349,900,0.821825,0.890425,0.91765,0.821825,0.821825,0.2968083333333333,0.890425,0.18353,0.91765,0.821825,0.8585424999999958,0.8626341865079316,0.8831597899495076,0.8651357816461163
+0.7112375533428165,1000,0.821875,0.891225,0.917725,0.821875,0.821875,0.297075,0.891225,0.183545,0.917725,0.821875,0.8586737499999942,0.8628899305555491,0.8836079830828143,0.8653478838731942
+0.7823613086770982,1100,0.8221,0.891925,0.91895,0.8221,0.8221,0.2973083333333333,0.891925,0.18379000000000004,0.91895,0.8221,0.8592887499999946,0.8633686904761843,0.8840734765399635,0.8658691525588665
+0.8534850640113798,1200,0.822925,0.892725,0.919175,0.822925,0.822925,0.297575,0.892725,0.18383500000000003,0.919175,0.822925,0.8599345833333281,0.8640485912698367,0.8846586524909154,0.8665777843003274
+0.9246088193456614,1300,0.82345,0.8935,0.92055,0.82345,0.82345,0.2978333333333333,0.8935,0.18411,0.92055,0.82345,0.8607987499999945,0.8649032638888835,0.8856106027310329,0.867403577329114
+0.9957325746799431,1400,0.82325,0.8933,0.921125,0.82325,0.82325,0.2977666666666666,0.8933,0.18422500000000003,0.921125,0.82325,0.8608366666666618,0.8649197718253918,0.885785240388492,0.8673886311195982
+1.0668563300142249,1500,0.8239,0.894675,0.9212,0.8239,0.8239,0.298225,0.894675,0.18424000000000004,0.9212,0.8239,0.861378749999995,0.8656084027777738,0.886533866338354,0.868050543099101
+1.1379800853485065,1600,0.8239,0.89485,0.9205,0.8239,0.8239,0.2982833333333333,0.89485,0.18409999999999999,0.9205,0.8239,0.8612483333333286,0.8656391964285669,0.8866256611000325,0.8680736081907602
+1.209103840682788,1700,0.82405,0.89515,0.92115,0.82405,0.82405,0.2983833333333333,0.89515,0.18423,0.92115,0.82405,0.8615316666666606,0.8659026388888836,0.8869176027034992,0.8683301973092413
+1.2802275960170697,1800,0.824175,0.896225,0.922375,0.824175,0.824175,0.2987416666666666,0.896225,0.18447500000000003,0.922375,0.824175,0.8621304166666607,0.8663353273809463,0.8873448262106999,0.8687668641747599
+1.3513513513513513,1900,0.825525,0.896575,0.92315,0.825525,0.825525,0.2988583333333333,0.896575,0.18463000000000002,0.92315,0.825525,0.8630337499999942,0.8672058829365027,0.8881349504555975,0.8696378148874042
+1.422475106685633,2000,0.824875,0.89615,0.922225,0.824875,0.824875,0.29871666666666663,0.89615,0.184445,0.922225,0.824875,0.8624995833333283,0.8668498412698372,0.8879244763281516,0.8692683038849478
+1.4935988620199145,2100,0.8251,0.89675,0.922925,0.8251,0.8251,0.29891666666666666,0.89675,0.18458500000000003,0.922925,0.8251,0.8628412499999946,0.8671035813492023,0.8881754016915514,0.8695244951133804
+1.5647226173541964,2200,0.824925,0.8969,0.92355,0.824925,0.824925,0.2989666666666666,0.8969,0.18470999999999999,0.92355,0.824925,0.8630016666666616,0.8671947222222179,0.8882835417851939,0.8696206929447456
+1.635846372688478,2300,0.82495,0.89735,0.923825,0.82495,0.82495,0.29911666666666664,0.89735,0.18476500000000004,0.923825,0.82495,0.8631245833333274,0.8673548611111046,0.888537638953492,0.8697591451729704
+1.7069701280227596,2400,0.826225,0.8979,0.924375,0.826225,0.826225,0.2992999999999999,0.8979,0.184875,0.924375,0.826225,0.8640779166666614,0.868321726190472,0.8894215247719068,0.8707139327932544
+1.7780938833570412,2500,0.82545,0.898275,0.924175,0.82545,0.82545,0.29942499999999994,0.898275,0.18483500000000003,0.924175,0.82545,0.8636241666666614,0.8679304464285673,0.8891594573590612,0.8703335724958975
+1.8492176386913228,2600,0.826175,0.898175,0.9247,0.826175,0.826175,0.29939166666666667,0.898175,0.18494000000000002,0.9247,0.826175,0.8641804166666623,0.8684414682539631,0.8896458867227734,0.870847238427157
+1.9203413940256047,2700,0.825875,0.897825,0.924175,0.825875,0.825875,0.299275,0.897825,0.18483500000000003,0.924175,0.825875,0.8638574999999944,0.868217509920631,0.8894948799781416,0.8706327376670759
+1.991465149359886,2800,0.826225,0.8983,0.924475,0.826225,0.826225,0.29943333333333333,0.8983,0.18489500000000003,0.924475,0.826225,0.8641595833333282,0.8685288888888845,0.889811094671074,0.8709200811674378
+2.062588904694168,2900,0.826575,0.89885,0.92485,0.826575,0.826575,0.2996166666666666,0.89885,0.18497000000000002,0.92485,0.826575,0.8645774999999943,0.8689782341269785,0.8903225599754984,0.8713206279473252
+2.1337126600284497,3000,0.8266,0.89905,0.925175,0.8266,0.8266,0.2996833333333333,0.89905,0.18503500000000003,0.925175,0.8266,0.8647558333333282,0.869107787698408,0.8904131932586173,0.8714774361878306
+2.204836415362731,3100,0.826675,0.8997,0.925225,0.826675,0.826675,0.2999,0.8997,0.18504500000000002,0.925225,0.826675,0.8648191666666607,0.8691860912698357,0.8904989946578933,0.871553217284866
+2.275960170697013,3200,0.826725,0.89955,0.9256,0.826725,0.826725,0.2998499999999999,0.89955,0.18511999999999998,0.9256,0.826725,0.8649791666666601,0.8693465277777699,0.8907582295982882,0.8716640608002595
+2.3470839260312943,3300,0.826575,0.89985,0.925625,0.826575,0.826575,0.29994999999999994,0.89985,0.185125,0.925625,0.826575,0.8650091666666611,0.869368204365073,0.8907657483756646,0.8717004467651088
+2.418207681365576,3400,0.826575,0.8997,0.925775,0.826575,0.826575,0.2998999999999999,0.8997,0.18515500000000001,0.925775,0.826575,0.8649995833333284,0.8693408432539614,0.8907417130181404,0.8716965684052127
+2.4893314366998576,3500,0.82665,0.899475,0.9261,0.82665,0.82665,0.29982499999999995,0.899475,0.18522000000000002,0.9261,0.82665,0.8649920833333282,0.8692922817460256,0.8907358632847491,0.871649860200826
+2.5604551920341394,3600,0.826875,0.9003,0.92605,0.826875,0.826875,0.3001,0.9003,0.18521000000000004,0.92605,0.826875,0.8652491666666605,0.8695896031745965,0.8909979289659293,0.8719302926120457
+2.6315789473684212,3700,0.827025,0.900275,0.926075,0.827025,0.827025,0.30009166666666665,0.900275,0.18521500000000002,0.926075,0.827025,0.865409583333329,0.8697828075396781,0.8911913854619483,0.8721236055235071
+2.7027027027027026,3800,0.827025,0.90095,0.92645,0.827025,0.827025,0.3003166666666666,0.90095,0.18529000000000004,0.92645,0.827025,0.8655795833333275,0.8698699603174542,0.8912290647496708,0.8722296272752561
+2.7738264580369845,3900,0.826775,0.900975,0.926525,0.826775,0.826775,0.3003249999999999,0.900975,0.18530500000000003,0.926525,0.826775,0.8655420833333285,0.8699055654761841,0.8914045716439474,0.8722080443535084
+2.844950213371266,4000,0.8272,0.90065,0.926825,0.8272,0.8272,0.30021666666666663,0.90065,0.18536500000000003,0.926825,0.8272,0.8658591666666623,0.8701858333333292,0.8916375973389772,0.8724953320587089
+2.9160739687055477,4100,0.8273,0.90065,0.92755,0.8273,0.8273,0.30021666666666663,0.90065,0.18551,0.92755,0.8273,0.8660504166666627,0.8703939980158677,0.8919791384990317,0.8726592726636881
+2.987197724039829,4200,0.827725,0.90045,0.92775,0.827725,0.827725,0.30015,0.90045,0.18555,0.92775,0.827725,0.8662579166666624,0.8705597023809468,0.892066241132213,0.8728541618998119
+3.058321479374111,4300,0.827475,0.901175,0.928025,0.827475,0.827475,0.3003916666666666,0.901175,0.18560500000000002,0.928025,0.827475,0.866314583333329,0.8705805654761841,0.8921197780063829,0.8728613054421528
+3.1294452347083928,4400,0.8277,0.901175,0.92825,0.8277,0.8277,0.3003916666666666,0.901175,0.18565,0.92825,0.8277,0.8665124999999955,0.8708128670634864,0.8924373846941944,0.8730523461044413
+3.200568990042674,4500,0.827575,0.901225,0.928375,0.827575,0.827575,0.3004083333333333,0.901225,0.18567500000000003,0.928375,0.827575,0.8664383333333281,0.8708214682539619,0.8925953907373283,0.8730156219725579
+3.271692745376956,4600,0.8279,0.901575,0.928375,0.8279,0.8279,0.300525,0.901575,0.185675,0.928375,0.8279,0.866585833333329,0.8709510019841202,0.8926942737918313,0.8731458638145055
+3.3428165007112374,4700,0.827575,0.9014,0.92795,0.827575,0.827575,0.3004666666666666,0.9014,0.18559000000000006,0.92795,0.827575,0.8664058333333281,0.8708573710317392,0.8926411564059361,0.8730650536407063
+3.413940256045519,4800,0.8276,0.901575,0.92875,0.8276,0.8276,0.300525,0.901575,0.18575,0.92875,0.8276,0.8665841666666624,0.8708900198412636,0.8926305600650463,0.873122633964442
+3.485064011379801,4900,0.82815,0.9011,0.92885,0.82815,0.82815,0.3003666666666666,0.9011,0.18577,0.92885,0.82815,0.8668041666666617,0.8711553373015805,0.8929320907320707,0.8733508626597645
+3.5561877667140824,5000,0.827675,0.901125,0.92895,0.827675,0.827675,0.300375,0.901125,0.18579,0.92895,0.827675,0.8665837499999955,0.8708607738095179,0.8925810943314898,0.8731088176524069
+3.6273115220483643,5100,0.8279,0.9018,0.9286,0.8279,0.8279,0.3006,0.9018,0.18572000000000002,0.9286,0.8279,0.8668145833333285,0.8711948015872957,0.8929008508637697,0.8734305622412212
+3.6984352773826457,5200,0.8277,0.90215,0.9287,0.8277,0.8277,0.30071666666666663,0.90215,0.18574000000000004,0.9287,0.8277,0.8667604166666624,0.8711313293650733,0.8928740678326429,0.8733567486761654
+3.7695590327169275,5300,0.82845,0.9025,0.929125,0.82845,0.82845,0.3008333333333333,0.9025,0.18582500000000002,0.929125,0.82845,0.8674124999999964,0.8718316964285665,0.8935972664353634,0.8740016594916253
+3.8406827880512093,5400,0.827975,0.90155,0.92865,0.827975,0.827975,0.3005166666666666,0.90155,0.18573000000000003,0.92865,0.827975,0.8668745833333286,0.8712864880952323,0.8930123747026218,0.8735193873832935
+3.9118065433854907,5500,0.8277,0.90215,0.9289,0.8277,0.8277,0.30071666666666663,0.90215,0.18578,0.9289,0.8277,0.8668504166666622,0.8712548115079313,0.8930900566464374,0.873443092121
+3.9829302987197726,5600,0.8274,0.90235,0.928875,0.8274,0.8274,0.3007833333333333,0.90235,0.18577500000000005,0.928875,0.8274,0.8667458333333284,0.8712413492063439,0.8932113985600477,0.8733958591837214
+4.054054054054054,5700,0.8284,0.902525,0.92915,0.8284,0.8284,0.3008416666666666,0.902525,0.18583000000000002,0.92915,0.8284,0.8673966666666616,0.8718133630952317,0.8935767431048043,0.8740015491385773
+4.125177809388336,5800,0.828425,0.902825,0.9296,0.828425,0.828425,0.3009416666666666,0.902825,0.18592000000000003,0.9296,0.828425,0.8675812499999948,0.871918124999994,0.893666432010205,0.8741087426233196
+4.196301564722617,5900,0.828525,0.9022,0.92915,0.828525,0.828525,0.3007333333333333,0.9022,0.18583000000000002,0.92915,0.828525,0.8673833333333288,0.8718712202380895,0.8937141847404675,0.8740192110160396
+4.2674253200568995,6000,0.828875,0.90235,0.92975,0.828875,0.828875,0.30078333333333324,0.90235,0.18595000000000003,0.92975,0.828875,0.8678129166666622,0.8721811706349157,0.8938989321601007,0.8743745063266631
+4.338549075391181,6100,0.82845,0.9026,0.9291,0.82845,0.82845,0.3008666666666666,0.9026,0.18582,0.9291,0.82845,0.8673166666666617,0.8717749999999929,0.8936243154363203,0.8739455546849367
+4.409672830725462,6200,0.8284,0.903075,0.9296,0.8284,0.8284,0.30102499999999993,0.903075,0.18592000000000003,0.9296,0.8284,0.8676320833333286,0.8720804365079297,0.8939257947166456,0.8742395675408973
+4.480796586059744,6300,0.828225,0.90275,0.929325,0.828225,0.828225,0.3009166666666666,0.90275,0.18586500000000003,0.929325,0.828225,0.8674999999999947,0.8719905158730092,0.8938322598813815,0.8741705169023509
+4.551920341394026,6400,0.8285,0.90335,0.92975,0.8285,0.8285,0.3011166666666666,0.90335,0.18595000000000003,0.92975,0.8285,0.8678516666666617,0.8723455853174541,0.8942491439779721,0.874474011966291
+4.623044096728307,6500,0.829175,0.902875,0.929875,0.829175,0.829175,0.30095833333333327,0.902875,0.18597500000000006,0.929875,0.829175,0.8680937499999958,0.8725534623015822,0.894368923703291,0.8746872189322042
+4.694167852062589,6600,0.82905,0.903075,0.93015,0.82905,0.82905,0.301025,0.903075,0.18603000000000003,0.93015,0.82905,0.8681745833333278,0.8725917361111044,0.8944163915781091,0.8747310389447597
+4.76529160739687,6700,0.828925,0.90325,0.929775,0.828925,0.828925,0.3010833333333333,0.90325,0.185955,0.929775,0.828925,0.8679954166666616,0.8724790773809465,0.8943439212494719,0.8746128881249259
+4.836415362731152,6800,0.828575,0.9031,0.9304,0.828575,0.828575,0.3010333333333333,0.9031,0.18608000000000002,0.9304,0.828575,0.8679383333333275,0.8723482936507868,0.8942892449456445,0.8744742271170953
+4.907539118065434,6900,0.82885,0.9029,0.9307,0.82885,0.82885,0.3009666666666666,0.9029,0.18614,0.9307,0.82885,0.8680495833333282,0.8724709027777715,0.8944710513562503,0.8745647676257946
+4.978662873399715,7000,0.8283,0.9031,0.93085,0.8283,0.8283,0.3010333333333333,0.9031,0.18617,0.93085,0.8283,0.8678516666666619,0.8722358730158676,0.8943000182461698,0.8743369199623621
+5.049786628733997,7100,0.8279,0.903125,0.9307,0.8279,0.8279,0.3010416666666666,0.903125,0.18614000000000003,0.9307,0.8279,0.8676270833333279,0.8719915376984065,0.8940120699532174,0.8741380897523008
+5.120910384068279,7200,0.828275,0.90295,0.930025,0.828275,0.828275,0.3009833333333333,0.90295,0.18600500000000003,0.930025,0.828275,0.8676429166666617,0.8721463293650742,0.8941977596786901,0.8742604553436768
+5.19203413940256,7300,0.828425,0.903025,0.930275,0.828425,0.828425,0.3010083333333333,0.903025,0.18605500000000003,0.930275,0.828425,0.8678812499999949,0.872354652777772,0.8943000793022067,0.8745114126364067
+5.2631578947368425,7400,0.828225,0.9028,0.9301,0.828225,0.828225,0.30093333333333333,0.9028,0.18602000000000002,0.9301,0.828225,0.8675679166666612,0.872012182539677,0.8939575105681979,0.8741988719154433
+5.334281650071124,7500,0.82785,0.903125,0.930575,0.82785,0.82785,0.30104166666666665,0.903125,0.186115,0.930575,0.82785,0.8676316666666626,0.8721601488095195,0.8943613633651454,0.874238288502371
+5.405405405405405,7600,0.828475,0.902975,0.93095,0.828475,0.828475,0.3009916666666666,0.902975,0.18619000000000002,0.93095,0.828475,0.8680033333333292,0.8724383134920588,0.8944984330360523,0.8745428567045579
+5.476529160739687,7700,0.82855,0.90335,0.9307,0.82855,0.82855,0.30111666666666664,0.90335,0.18614000000000003,0.9307,0.82855,0.8680608333333294,0.8725198611111069,0.8945047825331323,0.8746575985799696
+5.547652916073969,7800,0.828875,0.903275,0.93085,0.828875,0.828875,0.3010916666666666,0.903275,0.18617000000000006,0.93085,0.828875,0.8682458333333294,0.872676269841266,0.8946389217721571,0.8747955260908377
+5.61877667140825,7900,0.82905,0.903375,0.93105,0.82905,0.82905,0.301125,0.903375,0.18621,0.93105,0.82905,0.8683870833333295,0.8727912202380916,0.8947269456300353,0.8749224068854644
+5.689900426742532,8000,0.82915,0.903325,0.930675,0.82915,0.82915,0.3011083333333333,0.903325,0.18613500000000002,0.930675,0.82915,0.8684083333333289,0.8729126091269789,0.8948820398516149,0.8750130251353759
+5.761024182076814,8100,0.829075,0.904075,0.9312,0.829075,0.829075,0.3013583333333333,0.904075,0.18624000000000004,0.9312,0.829075,0.8685508333333278,0.873021924603169,0.8950310737741233,0.8751092075074616
+5.832147937411095,8200,0.828825,0.90365,0.9305,0.828825,0.828825,0.30121666666666663,0.90365,0.18610000000000002,0.9305,0.828825,0.8682554166666617,0.8728638095238044,0.8949489700564521,0.8749277099562706
+5.903271692745377,8300,0.82895,0.903725,0.931225,0.82895,0.82895,0.30124166666666663,0.903725,0.18624500000000002,0.931225,0.82895,0.8684424999999952,0.8729208234126938,0.8949867471707442,0.8749962923229312
+5.974395448079658,8400,0.82885,0.903675,0.931025,0.82885,0.82885,0.30122499999999997,0.903675,0.18620499999999998,0.931025,0.82885,0.8683604166666622,0.8728612103174557,0.8949169009398232,0.8749454784815862
+6.0455192034139404,8500,0.82895,0.903775,0.931475,0.82895,0.82895,0.3012583333333333,0.903775,0.18629500000000002,0.931475,0.82895,0.8685329166666627,0.8729780257936461,0.8950478966468592,0.8750537538993218
+6.116642958748222,8600,0.82905,0.90415,0.93205,0.82905,0.82905,0.3013833333333333,0.90415,0.18641000000000005,0.93205,0.82905,0.8687849999999957,0.8731482539682496,0.8951754441957878,0.8752259309496394
+6.187766714082503,8700,0.828825,0.9041,0.93175,0.828825,0.828825,0.30136666666666667,0.9041,0.18635,0.93175,0.828825,0.8685724999999961,0.872876924603171,0.8947828539779766,0.8750292561714247
+6.2588904694167855,8800,0.829075,0.903925,0.931425,0.829075,0.829075,0.3013083333333333,0.903925,0.186285,0.931425,0.829075,0.868536666666662,0.8729551984126942,0.8949195971526226,0.8750767734715837
+6.330014224751067,8900,0.828975,0.90415,0.931325,0.828975,0.828975,0.3013833333333333,0.90415,0.18626500000000004,0.931325,0.828975,0.8684991666666616,0.8729706845238042,0.8949951561857655,0.8750641724121062
+6.401137980085348,9000,0.829075,0.903975,0.93165,0.829075,0.829075,0.301325,0.903975,0.18633000000000005,0.93165,0.829075,0.8685995833333287,0.872990962301583,0.8949819996202747,0.8750914105522226
+6.472261735419631,9100,0.829225,0.903925,0.932075,0.829225,0.829225,0.3013083333333333,0.903925,0.18641500000000003,0.932075,0.829225,0.868800416666662,0.8731110317460269,0.895053660038409,0.8752295993536805
+6.543385490753912,9200,0.82855,0.9041,0.931375,0.82855,0.82855,0.30136666666666667,0.9041,0.18627500000000002,0.931375,0.82855,0.8682741666666616,0.8726703174603115,0.8946713862569544,0.8748099752974711
+6.614509246088193,9300,0.828775,0.904225,0.9317,0.828775,0.828775,0.3014083333333333,0.904225,0.18634,0.9317,0.828775,0.8684645833333281,0.8728734226190421,0.8949274319558564,0.8749753112232658
+6.685633001422475,9400,0.82835,0.90395,0.932025,0.82835,0.82835,0.3013166666666666,0.90395,0.18640500000000002,0.932025,0.82835,0.8683237499999945,0.8726935218253904,0.8948281974118523,0.8747854079129327
+6.756756756756757,9500,0.828475,0.904075,0.932075,0.828475,0.828475,0.3013583333333333,0.904075,0.18641500000000003,0.932075,0.828475,0.8684204166666614,0.8727985515872957,0.8949274062023101,0.8748895020570487
+6.827880512091038,9600,0.8288,0.904225,0.93185,0.8288,0.8288,0.3014083333333333,0.904225,0.18637000000000004,0.93185,0.8288,0.8685758333333276,0.873004513888882,0.8951136713393641,0.8750801043302465
+6.89900426742532,9700,0.828825,0.904375,0.9318,0.828825,0.828825,0.30145833333333333,0.904375,0.18636000000000003,0.9318,0.828825,0.8686991666666614,0.8731213591269789,0.8951596018402795,0.8752201609740874
+6.970128022759602,9800,0.829025,0.904525,0.932225,0.829025,0.829025,0.30150833333333327,0.904525,0.18644500000000003,0.932225,0.829025,0.8689174999999952,0.8732630853174554,0.8952619483692564,0.8753690315163684
+7.0412517780938835,9900,0.828875,0.904425,0.93255,0.828875,0.828875,0.301475,0.904425,0.18651000000000004,0.93255,0.828875,0.8688845833333287,0.873162787698407,0.8951766391067307,0.8752720359442444
+7.112375533428165,10000,0.828575,0.904625,0.932375,0.828575,0.828575,0.30154166666666665,0.904625,0.186475,0.932375,0.828575,0.8687079166666616,0.8730274900793593,0.8950797790185748,0.8751374732802933
+7.183499288762446,10100,0.8286,0.905075,0.932175,0.8286,0.8286,0.3016916666666666,0.905075,0.18643500000000005,0.932175,0.8286,0.8687141666666612,0.8730440476190419,0.8950594465802302,0.8751640577624185
+7.2546230440967285,10200,0.8296,0.904775,0.9323,0.8296,0.8296,0.3015916666666666,0.904775,0.18646000000000001,0.9323,0.8296,0.8691612499999947,0.873514434523804,0.8954897884983242,0.8756084914792746
+7.32574679943101,10300,0.829075,0.904875,0.93235,0.829075,0.829075,0.301625,0.904875,0.18647000000000002,0.93235,0.829075,0.868976249999995,0.8732967956349148,0.8952704782589539,0.8754151233921735
+7.396870554765291,10400,0.82915,0.905075,0.932425,0.82915,0.82915,0.3016916666666666,0.905075,0.186485,0.932425,0.82915,0.8690495833333287,0.8734093849206295,0.8954447584237889,0.8755008479404327
+7.467994310099574,10500,0.829425,0.904825,0.932525,0.829425,0.829425,0.30160833333333326,0.904825,0.18650500000000003,0.932525,0.829425,0.8691991666666623,0.8734998115079301,0.8954660672180369,0.8756100523433119
+7.539118065433855,10600,0.829125,0.905075,0.932475,0.829125,0.829125,0.3016916666666666,0.905075,0.18649500000000002,0.932475,0.829125,0.8691154166666616,0.8734564682539616,0.8954709669225793,0.8755484892898732
+7.610241820768136,10700,0.82905,0.9048,0.932375,0.82905,0.82905,0.3016,0.9048,0.18647500000000006,0.932375,0.82905,0.8689229166666611,0.8732853769841208,0.8953490062056495,0.875372576803479
+7.681365576102419,10800,0.829025,0.905325,0.932625,0.829025,0.829025,0.30177499999999996,0.905325,0.18652500000000005,0.932625,0.829025,0.869070416666661,0.8734086011904688,0.8954652430846454,0.8754917937310882
+7.7524893314367,10900,0.82875,0.904775,0.932125,0.82875,0.82875,0.3015916666666666,0.904775,0.18642500000000004,0.932125,0.82875,0.868665416666662,0.8730924007936451,0.8952425511491899,0.8751620499741801
+7.823613086770981,11000,0.8295,0.90505,0.932275,0.8295,0.8295,0.3016833333333333,0.90505,0.186455,0.932275,0.8295,0.8692354166666619,0.8736657539682472,0.8957464957352415,0.8757095548251062
+7.894736842105263,11100,0.828925,0.90485,0.932575,0.828925,0.828925,0.3016166666666666,0.90485,0.18651500000000001,0.932575,0.828925,0.8689179166666623,0.8732802380952318,0.8954065650616195,0.8753463124648857
+7.965860597439545,11200,0.829025,0.904825,0.932675,0.829025,0.829025,0.3016083333333333,0.904825,0.186535,0.932675,0.829025,0.8690079166666621,0.8733515476190415,0.8954423259492094,0.875432665821568
+8.036984352773827,11300,0.8292,0.904725,0.93255,0.8292,0.8292,0.3015749999999999,0.904725,0.18650999999999998,0.93255,0.8292,0.869073749999995,0.8734561210317406,0.8955415674350273,0.8755229302308101
+8.108108108108109,11400,0.829325,0.904975,0.93275,0.829325,0.829325,0.3016583333333333,0.904975,0.18655000000000005,0.93275,0.829325,0.8692104166666624,0.8735678571428518,0.8956531906883425,0.8756297665813315
+8.17923186344239,11500,0.82925,0.90495,0.932375,0.82925,0.82925,0.30165,0.90495,0.186475,0.932375,0.82925,0.8690454166666621,0.8734416964285652,0.8955104391817192,0.8755223363162908
+8.250355618776672,11600,0.828875,0.9047,0.93215,0.828875,0.828875,0.3015666666666666,0.9047,0.18643,0.93215,0.828875,0.8687787499999952,0.8732215476190417,0.8953592242644414,0.8752882594576469
+8.321479374110954,11700,0.828775,0.90415,0.9323,0.828775,0.828775,0.3013833333333333,0.90415,0.18646000000000001,0.9323,0.828775,0.8686216666666616,0.8730347222222162,0.8951978059378991,0.8751061946163587
+8.392603129445234,11800,0.828925,0.90455,0.932375,0.828925,0.828925,0.3015166666666666,0.90455,0.18647500000000003,0.932375,0.828925,0.8688104166666617,0.8731834126984072,0.8952621827829491,0.8752830033195543
+8.463726884779517,11900,0.82875,0.90425,0.932075,0.82875,0.82875,0.3014166666666666,0.90425,0.186415,0.932075,0.82875,0.8686170833333284,0.8730646230158685,0.8952314018142266,0.8751380575962121
+8.534850640113799,12000,0.829075,0.9047,0.932425,0.829075,0.829075,0.30156666666666665,0.9047,0.18648500000000004,0.932425,0.829075,0.8689379166666622,0.8733352777777729,0.8954426784378953,0.8754119442285108
+8.60597439544808,12100,0.8291,0.90465,0.932525,0.8291,0.8291,0.30155,0.90465,0.18650500000000003,0.932525,0.8291,0.8689716666666616,0.8733671428571368,0.8955036503963157,0.8754304331343709
+8.677098150782362,12200,0.82895,0.90485,0.932375,0.82895,0.82895,0.3016166666666666,0.90485,0.186475,0.932375,0.82895,0.868958749999995,0.873387123015867,0.8955303325344552,0.8754507768463161
+8.748221906116642,12300,0.829475,0.904725,0.93275,0.829475,0.829475,0.301575,0.904725,0.18655,0.93275,0.829475,0.8692883333333291,0.873639414682535,0.8956905693084858,0.8757137507599527
+8.819345661450924,12400,0.8292,0.9051,0.932725,0.8292,0.8292,0.30169999999999997,0.9051,0.18654500000000002,0.932725,0.8292,0.8692066666666622,0.8735561309523755,0.8956121742695453,0.8756422684505465
+8.890469416785207,12500,0.82945,0.90485,0.93265,0.82945,0.82945,0.3016166666666666,0.90485,0.18653000000000003,0.93265,0.82945,0.8692741666666625,0.8736324999999945,0.8956449964020973,0.8757278374859732
+8.961593172119487,12600,0.8295,0.904875,0.9325,0.8295,0.8295,0.301625,0.904875,0.18650000000000005,0.9325,0.8295,0.8692387499999957,0.8736341964285653,0.8956903497814453,0.8757079138167887
+9.03271692745377,12700,0.829525,0.9047,0.9324,0.829525,0.829525,0.3015666666666666,0.9047,0.18648,0.9324,0.829525,0.8692474999999956,0.8736550694444389,0.8956994527858438,0.8757306836256025
+9.103840682788052,12800,0.829375,0.904375,0.9324,0.829375,0.829375,0.3014583333333333,0.904375,0.18648,0.9324,0.829375,0.8690412499999959,0.8734550595238041,0.8955588176732403,0.875525147366692
+9.174964438122332,12900,0.829125,0.90475,0.9324,0.829125,0.829125,0.3015833333333333,0.90475,0.18648,0.9324,0.829125,0.868967916666662,0.8733762797618992,0.8954799203066371,0.8754609487406843
+9.246088193456615,13000,0.829125,0.90485,0.9324,0.829125,0.829125,0.3016166666666666,0.90485,0.18648,0.9324,0.829125,0.868992083333329,0.8734280654761849,0.8955737083799604,0.8754895469283179
+9.317211948790897,13100,0.8293,0.904775,0.9327,0.8293,0.8293,0.3015916666666666,0.904775,0.18654,0.9327,0.8293,0.8691408333333289,0.873514990079359,0.8956181445893849,0.8755874727685248
+9.388335704125177,13200,0.829325,0.905025,0.932525,0.829325,0.829325,0.301675,0.905025,0.18650500000000003,0.932525,0.829325,0.8691233333333288,0.8735301587301532,0.8956296717143643,0.8756034523955281
+9.45945945945946,13300,0.829325,0.905125,0.932525,0.829325,0.829325,0.3017083333333333,0.905125,0.186505,0.932525,0.829325,0.8691458333333285,0.8735614980158675,0.8956763840293377,0.8756260378815925
+9.530583214793742,13400,0.82915,0.90495,0.9326,0.82915,0.82915,0.30165,0.90495,0.18652000000000002,0.9326,0.82915,0.8690558333333281,0.8734571130952323,0.8955881800163638,0.8755247191912429
+9.601706970128022,13500,0.82925,0.90495,0.932525,0.82925,0.82925,0.3016499999999999,0.90495,0.18650500000000003,0.932525,0.82925,0.8690795833333285,0.8734938392857088,0.8956149222360327,0.8755655926205971
+9.672830725462305,13600,0.8292,0.904925,0.9327,0.8292,0.8292,0.30164166666666664,0.904925,0.18654,0.9327,0.8292,0.8691233333333286,0.8735162896825339,0.895645553478534,0.8755826049757932
+9.743954480796585,13700,0.829325,0.90495,0.932775,0.829325,0.829325,0.30165,0.90495,0.18655500000000003,0.932775,0.829325,0.8692137499999953,0.8735839880952322,0.8956849160109633,0.875656327707471
+9.815078236130867,13800,0.82925,0.905,0.932825,0.82925,0.82925,0.3016666666666666,0.905,0.186565,0.932825,0.82925,0.8691904166666616,0.873566468253962,0.8956952492720289,0.8756302411100991
+9.88620199146515,13900,0.829175,0.905025,0.93285,0.829175,0.829175,0.3016749999999999,0.905025,0.18657,0.93285,0.829175,0.869152916666662,0.8735199007936449,0.895645535201997,0.8755899948508465
+9.95732574679943,14000,0.8292,0.905075,0.932925,0.8292,0.8292,0.3016916666666666,0.905075,0.18658500000000003,0.932925,0.8292,0.869192916666662,0.8735491567460258,0.895673602678825,0.8756171762848609

final_metrics.json

@@ -1,16 +1,16 @@
 {
-  "val_cosine_accuracy@1": 0.9184,
-  "val_cosine_accuracy@3": 0.97,
-  "val_cosine_accuracy@5": 0.9852,
-  "val_cosine_precision@1": 0.9184,
-  "val_cosine_precision@3": 0.3233333333333333,
-  "val_cosine_precision@5": 0.19703999999999997,
-  "val_cosine_recall@1": 0.9184,
-  "val_cosine_recall@3": 0.97,
-  "val_cosine_recall@5": 0.9852,
-  "val_cosine_ndcg@10": 0.9586270476620361,
-  "val_cosine_mrr@1": 0.9184,
-  "val_cosine_mrr@5": 0.9451366666666663,
-  "val_cosine_mrr@10": 0.9466038095238087,
-  "val_cosine_map@100": 0.946959374340519
+  "val_cosine_accuracy@1": 0.829575,
+  "val_cosine_accuracy@3": 0.9048,
+  "val_cosine_accuracy@5": 0.9324,
+  "val_cosine_precision@1": 0.829575,
+  "val_cosine_precision@3": 0.3016,
+  "val_cosine_precision@5": 0.18648000000000003,
+  "val_cosine_recall@1": 0.829575,
+  "val_cosine_recall@3": 0.9048,
+  "val_cosine_recall@5": 0.9324,
+  "val_cosine_ndcg@10": 0.8957411186558171,
+  "val_cosine_mrr@1": 0.829575,
+  "val_cosine_mrr@5": 0.8693266666666628,
+  "val_cosine_mrr@10": 0.873717658730154,
+  "val_cosine_map@100": 0.8757871539962314
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ae394348a491d3e3613014bc35b25e1e57987b52b334312c28991a2034cb6a2
+oid sha256:36f07360daa85c59707827836aa470469164811479c2802fa0e2cd50f554b85f
 size 114011616