Training in progress, step 2000

Information-Retrieval_evaluation_val_results.csv

@@ -4,3 +4,4 @@ epoch,steps,cosine-Accuracy@1,cosine-Accuracy@3,cosine-Accuracy@5,cosine-Precisi
 -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
 -1,-1,0.829275,0.9051,0.9329,0.829275,0.829275,0.30169999999999997,0.9051,0.18658000000000002,0.9329,0.829275,0.8692179166666618,0.8735753373015815,0.8956869608914538,0.8756452160249361
 -1,-1,0.76415,0.822175,0.84665,0.76415,0.76415,0.2740583333333333,0.822175,0.16933,0.84665,0.76415,0.7953370833333295,0.8000376587301573,0.8195085862842543,0.8034052122492592
+-1,-1,0.802275,0.8676,0.89495,0.802275,0.802275,0.28919999999999996,0.8676,0.17899,0.89495,0.802275,0.8373504166666614,0.8418555952380918,0.8626142815266079,0.8448604581747029

README.md

@@ -5,111 +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?
-  - Why don't bikes have a gear indicator?
-- source_sentence: Which ointment is applied to the face of UFC fighters at the commencement
-    of a bout? What does it do?
+  - How can we polish English skills?
+  - Why should I move to Israel as a Jew?
+  - What are vitamins responsible for?
+- source_sentence: Can I use the Kozuka Gothic Pro font as a font-face on my web site?
   sentences:
-  - How can I save a Snapchat video that others posted?
-  - Which ointment is applied to the face of UFC fighters at the commencement of a
-    bout? What does it do?
-  - How do I get the body of a UFC Fighter?
-- source_sentence: Do you love the life you live?
+  - Can I use the Kozuka Gothic Pro font as a font-face on my web site?
+  - Why are Google, Facebook, YouTube and other social networking sites banned in
+    China?
+  - What font is used in Bloomberg Terminal?
+- source_sentence: Is Quora the best Q&A site?
   sentences:
-  - Can I do shoulder and triceps workout on same day? What other combinations like
-    this can I do?
-  - Do you love the life you're living?
-  - Where can you find an online TI-84 calculator?
-- source_sentence: Ordered food on Swiggy 3 days ago.After accepting my money, said
-    no more on Menu! When if ever will I atleast get refund in cr card a/c?
+  - What was the best Quora question ever?
+  - Is Quora the best inquiry site?
+  - Where do I buy Oway hair products online?
+- source_sentence: How can I customize my walking speed on Google Maps?
   sentences:
-  - Is getting to the Tel Aviv airport to catch a 5:30 AM flight very expensive?
-  - How do I die and make it look like an accident?
-  - Ordered food on Swiggy 3 days ago.After accepting my money, said no more on Menu!
-    When if ever will I atleast get refund in cr card a/c?
-- source_sentence: How do you earn money on Quora?
+  - How do I bring back Google maps icon in my home screen?
+  - How many pages are there in all the Harry Potter books combined?
+  - How can I customize my walking speed on Google Maps?
+- source_sentence: DId something exist before the Big Bang?
   sentences:
-  - What is a cheap healthy diet I can keep the same and eat every day?
-  - What are some things new employees should know going into their first day at Maximus?
-  - What is the best way to make money on Quora?
+  - How can I improve my memory problem?
+  - Where can I buy Fairy Tail Manga?
+  - Is there a scientific name for what existed before the Big Bang?
 pipeline_tag: sentence-similarity
 library_name: sentence-transformers
-metrics:
-- cosine_accuracy@1
-- cosine_accuracy@3
-- cosine_accuracy@5
-- cosine_precision@1
-- cosine_precision@3
-- cosine_precision@5
-- cosine_recall@1
-- cosine_recall@3
-- cosine_recall@5
-- cosine_ndcg@10
-- cosine_mrr@1
-- cosine_mrr@5
-- cosine_mrr@10
-- cosine_map@100
-model-index:
-- name: SentenceTransformer based on prajjwal1/bert-small
-  results:
-  - task:
-      type: information-retrieval
-      name: Information Retrieval
-    dataset:
-      name: val
-      type: val
-    metrics:
-    - type: cosine_accuracy@1
-      value: 0.802275
-      name: Cosine Accuracy@1
-    - type: cosine_accuracy@3
-      value: 0.8676
-      name: Cosine Accuracy@3
-    - type: cosine_accuracy@5
-      value: 0.89495
-      name: Cosine Accuracy@5
-    - type: cosine_precision@1
-      value: 0.802275
-      name: Cosine Precision@1
-    - type: cosine_precision@3
-      value: 0.28919999999999996
-      name: Cosine Precision@3
-    - type: cosine_precision@5
-      value: 0.17899
-      name: Cosine Precision@5
-    - type: cosine_recall@1
-      value: 0.802275
-      name: Cosine Recall@1
-    - type: cosine_recall@3
-      value: 0.8676
-      name: Cosine Recall@3
-    - type: cosine_recall@5
-      value: 0.89495
-      name: Cosine Recall@5
-    - type: cosine_ndcg@10
-      value: 0.8626142815266079
-      name: Cosine Ndcg@10
-    - type: cosine_mrr@1
-      value: 0.802275
-      name: Cosine Mrr@1
-    - type: cosine_mrr@5
-      value: 0.8373504166666614
-      name: Cosine Mrr@5
-    - type: cosine_mrr@10
-      value: 0.8418555952380918
-      name: Cosine Mrr@10
-    - type: cosine_map@100
-      value: 0.8448604581747029
-      name: Cosine Map@100
 ---
 
 # SentenceTransformer based on prajjwal1/bert-small
@@ -158,12 +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 = [
-    'How do you earn money on Quora?',
-    'What is the best way to make money on Quora?',
-    'What are some things new employees should know going into their first day at Maximus?',
+    'DId something exist before the Big Bang?',
+    'Is there a scientific name for what existed before the Big Bang?',
+    'Where can I buy Fairy Tail Manga?',
 ]
 embeddings = model.encode(sentences)
 print(embeddings.shape)
@@ -172,9 +99,9 @@ print(embeddings.shape)
 # Get the similarity scores for the embeddings
 similarities = model.similarity(embeddings, embeddings)
 print(similarities)
-# tensor([[ 1.0001,  0.9960, -0.0211],
-#         [ 0.9960,  1.0000, -0.0245],
-#         [-0.0211, -0.0245,  1.0000]])
+# tensor([[ 1.0000,  0.7596, -0.0398],
+#         [ 0.7596,  1.0000, -0.0308],
+#         [-0.0398, -0.0308,  1.0000]])
 ```
 
 <!--
@@ -201,32 +128,6 @@ You can finetune this model on your own dataset.
 *List how the model may foreseeably be misused and address what users ought not to do with the model.*
 -->
 
-## Evaluation
-
-### Metrics
-
-#### Information Retrieval
-
-* Dataset: `val`
-* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
-
-| Metric             | Value      |
-|:-------------------|:-----------|
-| cosine_accuracy@1  | 0.8023     |
-| cosine_accuracy@3  | 0.8676     |
-| cosine_accuracy@5  | 0.895      |
-| cosine_precision@1 | 0.8023     |
-| cosine_precision@3 | 0.2892     |
-| cosine_precision@5 | 0.179      |
-| cosine_recall@1    | 0.8023     |
-| cosine_recall@3    | 0.8676     |
-| cosine_recall@5    | 0.895      |
-| **cosine_ndcg@10** | **0.8626** |
-| cosine_mrr@1       | 0.8023     |
-| cosine_mrr@5       | 0.8374     |
-| cosine_mrr@10      | 0.8419     |
-| cosine_map@100     | 0.8449     |
-
 <!--
 ## Bias, Risks and Limitations
 
@@ -245,49 +146,23 @@ You can finetune this model on your own dataset.
 
 #### Unnamed Dataset
 
-* Size: 359,997 training samples
-* Columns: <code>anchor</code>, <code>positive</code>, and <code>negative</code>
-* Approximate statistics based on the first 1000 samples:
-  |         | anchor                                                                            | positive                                                                          | negative                                                                           |
-  |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|
-  | type    | string                                                                            | string                                                                            | string                                                                             |
-  | details | <ul><li>min: 4 tokens</li><li>mean: 15.46 tokens</li><li>max: 49 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 15.52 tokens</li><li>max: 49 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 16.99 tokens</li><li>max: 128 tokens</li></ul> |
-* Samples:
-  | anchor                                                                          | positive                                                                                             | negative                                                                                                                 |
-  |:--------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------------------------|
-  | <code>Shall I upgrade my iPhone 5s to iOS 10 final version?</code>              | <code>Should I upgrade an iPhone 5s to iOS 10?</code>                                                | <code>Whether extension of CA-articleship is to be served at same firm/company?</code>                                   |
-  | <code>Is Donald Trump really going to be the president of United States?</code> | <code>Do you think Donald Trump could conceivably be the next President of the United States?</code> | <code>Since solid carbon dioxide is dry ice and incredibly cold, why doesn't it have an effect on global warming?</code> |
-  | <code>What are real tips to improve work life balance?</code>                   | <code>What are the best ways to create a work life balance?</code>                                   | <code>How do you open a briefcase combination lock without the combination?</code>                                       |
-* Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
-  ```json
-  {
-      "scale": 5.0,
-      "similarity_fct": "cos_sim",
-      "gather_across_devices": false
-  }
-  ```
-
-### Evaluation Dataset
-
-#### Unnamed Dataset
-
-* Size: 40,000 evaluation samples
-* Columns: <code>anchor</code>, <code>positive</code>, and <code>negative</code>
+* Size: 100,000 training samples
+* Columns: <code>sentence_0</code>, <code>sentence_1</code>, and <code>sentence_2</code>
 * Approximate statistics based on the first 1000 samples:
-  |         | anchor                                                                            | positive                                                                          | negative                                                                          |
-  |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
-  | type    | string                                                                            | string                                                                            | string                                                                            |
-  | details | <ul><li>min: 6 tokens</li><li>mean: 15.71 tokens</li><li>max: 65 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 15.79 tokens</li><li>max: 65 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 16.97 tokens</li><li>max: 78 tokens</li></ul> |
+  |         | sentence_0                                                                        | sentence_1                                                                       | sentence_2                                                                         |
+  |:--------|:----------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|
+  | type    | string                                                                            | string                                                                           | string                                                                             |
+  | details | <ul><li>min: 3 tokens</li><li>mean: 15.53 tokens</li><li>max: 59 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 15.5 tokens</li><li>max: 59 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 16.87 tokens</li><li>max: 128 tokens</li></ul> |
 * Samples:
-  | anchor                                                                                                            | positive                                                                                                          | negative                                                                                                                                  |
-  |:------------------------------------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------------------------------------------------|
-  | <code>Why were feathered dinosaur fossils only found in the last 20 years?</code>                                 | <code>Why were feathered dinosaur fossils only found in the last 20 years?</code>                                 | <code>Why are only few people aware that many dinosaurs had feathers?</code>                                                              |
-  | <code>If FOX News is the conservative news station, which cable news network is for liberals/progressives?</code> | <code>If FOX News is the conservative news station, which cable news network is for liberals/progressives?</code> | <code>How much did Fox News and conservative leaning media networks stoke the anger that contributed to Donald Trump's popularity?</code> |
-  | <code>How can guys last longer during sex?</code>                                                                 | <code>How do I last longer in sex?</code>                                                                         | <code>What is a permanent solution for rough and puffy hair?</code>                                                                       |
+  | sentence_0                                                                              | sentence_1                                                                              | sentence_2                                                             |
+  |:----------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------------|:-----------------------------------------------------------------------|
+  | <code>Is there visitor entry facility in Jaipur airport. How much is the ticket?</code> | <code>Is there visitor entry facility in Jaipur airport. How much is the ticket?</code> | <code>How much is the airport tax in bogota?</code>                    |
+  | <code>Which concept is more important: good planning or hard work?</code>               | <code>Which concept is more important: good planning or hard work?</code>               | <code>What is important in life: luck or hard work?</code>             |
+  | <code>What is the most efficient way to make money?</code>                              | <code>How can I make my money make money?</code>                                        | <code>What can one learn about Quantum Mechanics in 10 minutes?</code> |
 * Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
   ```json
   {
-      "scale": 5.0,
+      "scale": 20.0,
       "similarity_fct": "cos_sim",
       "gather_across_devices": false
   }
@@ -296,49 +171,36 @@ You can finetune this model on your own dataset.
 ### Training Hyperparameters
 #### Non-Default Hyperparameters
 
-- `eval_strategy`: steps
-- `per_device_train_batch_size`: 1024
-- `per_device_eval_batch_size`: 1024
-- `learning_rate`: 2e-05
-- `weight_decay`: 0.001
-- `max_steps`: 5000
-- `warmup_ratio`: 0.1
+- `per_device_train_batch_size`: 64
+- `per_device_eval_batch_size`: 64
 - `fp16`: True
-- `dataloader_drop_last`: True
-- `dataloader_num_workers`: 1
-- `dataloader_prefetch_factor`: 1
-- `load_best_model_at_end`: True
-- `optim`: adamw_torch
-- `ddp_find_unused_parameters`: False
-- `push_to_hub`: True
-- `hub_model_id`: redis/model-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`: 1024
-- `per_device_eval_batch_size`: 1024
+- `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`: 5000
+- `max_grad_norm`: 1
+- `num_train_epochs`: 3
+- `max_steps`: -1
 - `lr_scheduler_type`: linear
 - `lr_scheduler_kwargs`: {}
-- `warmup_ratio`: 0.1
+- `warmup_ratio`: 0.0
 - `warmup_steps`: 0
 - `log_level`: passive
 - `log_level_replica`: warning
@@ -366,14 +228,14 @@ You can finetune this model on your own dataset.
 - `tpu_num_cores`: None
 - `tpu_metrics_debug`: False
 - `debug`: []
-- `dataloader_drop_last`: True
-- `dataloader_num_workers`: 1
-- `dataloader_prefetch_factor`: 1
+- `dataloader_drop_last`: False
+- `dataloader_num_workers`: 0
+- `dataloader_prefetch_factor`: None
 - `past_index`: -1
 - `disable_tqdm`: False
 - `remove_unused_columns`: True
 - `label_names`: None
-- `load_best_model_at_end`: True
+- `load_best_model_at_end`: False
 - `ignore_data_skip`: False
 - `fsdp`: []
 - `fsdp_min_num_params`: 0
@@ -383,23 +245,23 @@ You can finetune this model on your own dataset.
 - `parallelism_config`: None
 - `deepspeed`: None
 - `label_smoothing_factor`: 0.0
-- `optim`: adamw_torch
+- `optim`: adamw_torch_fused
 - `optim_args`: None
 - `adafactor`: False
 - `group_by_length`: False
 - `length_column_name`: length
 - `project`: huggingface
 - `trackio_space_id`: trackio
-- `ddp_find_unused_parameters`: False
+- `ddp_find_unused_parameters`: None
 - `ddp_bucket_cap_mb`: None
 - `ddp_broadcast_buffers`: False
 - `dataloader_pin_memory`: True
 - `dataloader_persistent_workers`: False
 - `skip_memory_metrics`: True
 - `use_legacy_prediction_loop`: False
-- `push_to_hub`: True
+- `push_to_hub`: False
 - `resume_from_checkpoint`: None
-- `hub_model_id`: redis/model-a-baseline
+- `hub_model_id`: None
 - `hub_strategy`: every_save
 - `hub_private_repo`: None
 - `hub_always_push`: False
@@ -426,73 +288,31 @@ You can finetune this model on your own dataset.
 - `neftune_noise_alpha`: None
 - `optim_target_modules`: None
 - `batch_eval_metrics`: False
-- `eval_on_start`: True
+- `eval_on_start`: False
 - `use_liger_kernel`: False
 - `liger_kernel_config`: None
 - `eval_use_gather_object`: False
 - `average_tokens_across_devices`: True
 - `prompts`: None
 - `batch_sampler`: batch_sampler
-- `multi_dataset_batch_sampler`: proportional
+- `multi_dataset_batch_sampler`: round_robin
 - `router_mapping`: {}
 - `learning_rate_mapping`: {}
 
 </details>
 
 ### Training Logs
-| Epoch   | Step | Training Loss | Validation Loss | val_cosine_ndcg@10 |
-|:-------:|:----:|:-------------:|:---------------:|:------------------:|
-| 0       | 0    | -             | 6.2276          | 0.8046             |
-| 0.2849  | 100  | 5.882         | 3.9651          | 0.8557             |
-| 0.5698  | 200  | 4.3197        | 3.2712          | 0.8551             |
-| 0.8547  | 300  | 3.93          | 3.2258          | 0.8543             |
-| 1.1396  | 400  | 3.7914        | 3.1976          | 0.8544             |
-| 1.4245  | 500  | 3.7016        | 3.1692          | 0.8550             |
-| 1.7094  | 600  | 3.6345        | 3.1525          | 0.8556             |
-| 1.9943  | 700  | 3.5897        | 3.1350          | 0.8563             |
-| 2.2792  | 800  | 3.5494        | 3.1225          | 0.8566             |
-| 2.5641  | 900  | 3.5241        | 3.1107          | 0.8570             |
-| 2.8490  | 1000 | 3.4975        | 3.1020          | 0.8572             |
-| 3.1339  | 1100 | 3.4786        | 3.0944          | 0.8574             |
-| 3.4188  | 1200 | 3.4606        | 3.0875          | 0.8579             |
-| 3.7037  | 1300 | 3.4466        | 3.0821          | 0.8582             |
-| 3.9886  | 1400 | 3.4327        | 3.0765          | 0.8586             |
-| 4.2735  | 1500 | 3.4196        | 3.0725          | 0.8589             |
-| 4.5584  | 1600 | 3.4075        | 3.0682          | 0.8592             |
-| 4.8433  | 1700 | 3.4001        | 3.0639          | 0.8593             |
-| 5.1282  | 1800 | 3.3895        | 3.0598          | 0.8597             |
-| 5.4131  | 1900 | 3.381         | 3.0564          | 0.8599             |
-| 5.6980  | 2000 | 3.3751        | 3.0531          | 0.8601             |
-| 5.9829  | 2100 | 3.3672        | 3.0507          | 0.8603             |
-| 6.2678  | 2200 | 3.3571        | 3.0486          | 0.8605             |
-| 6.5527  | 2300 | 3.3549        | 3.0447          | 0.8608             |
-| 6.8376  | 2400 | 3.3471        | 3.0432          | 0.8608             |
-| 7.1225  | 2500 | 3.3428        | 3.0411          | 0.8609             |
-| 7.4074  | 2600 | 3.3358        | 3.0390          | 0.8613             |
-| 7.6923  | 2700 | 3.3304        | 3.0377          | 0.8612             |
-| 7.9772  | 2800 | 3.3283        | 3.0358          | 0.8614             |
-| 8.2621  | 2900 | 3.3217        | 3.0334          | 0.8616             |
-| 8.5470  | 3000 | 3.319         | 3.0324          | 0.8618             |
-| 8.8319  | 3100 | 3.3166        | 3.0305          | 0.8620             |
-| 9.1168  | 3200 | 3.3115        | 3.0295          | 0.8620             |
-| 9.4017  | 3300 | 3.3077        | 3.0279          | 0.8619             |
-| 9.6866  | 3400 | 3.3044        | 3.0270          | 0.8620             |
-| 9.9715  | 3500 | 3.3031        | 3.0256          | 0.8623             |
-| 10.2564 | 3600 | 3.2988        | 3.0253          | 0.8623             |
-| 10.5413 | 3700 | 3.2968        | 3.0239          | 0.8623             |
-| 10.8262 | 3800 | 3.295         | 3.0233          | 0.8624             |
-| 11.1111 | 3900 | 3.2933        | 3.0227          | 0.8624             |
-| 11.3960 | 4000 | 3.2913        | 3.0217          | 0.8626             |
-| 11.6809 | 4100 | 3.2884        | 3.0211          | 0.8624             |
-| 11.9658 | 4200 | 3.2875        | 3.0207          | 0.8625             |
-| 12.2507 | 4300 | 3.2859        | 3.0202          | 0.8626             |
-| 12.5356 | 4400 | 3.2841        | 3.0196          | 0.8626             |
-| 12.8205 | 4500 | 3.2839        | 3.0193          | 0.8625             |
-| 13.1054 | 4600 | 3.2839        | 3.0188          | 0.8627             |
-| 13.3903 | 4700 | 3.2818        | 3.0188          | 0.8626             |
-| 13.6752 | 4800 | 3.2799        | 3.0185          | 0.8627             |
-| 13.9601 | 4900 | 3.2812        | 3.0183          | 0.8627             |
-| 14.2450 | 5000 | 3.2817        | 3.0183          | 0.8626             |
+| Epoch  | Step | Training Loss |
+|:------:|:----:|:-------------:|
+| 0.3199 | 500  | 0.2284        |
+| 0.6398 | 1000 | 0.0571        |
+| 0.9597 | 1500 | 0.0486        |
+| 1.2796 | 2000 | 0.0378        |
+| 1.5995 | 2500 | 0.0367        |
+| 1.9194 | 3000 | 0.0338        |
+| 2.2393 | 3500 | 0.0327        |
+| 2.5592 | 4000 | 0.0285        |
+| 2.8791 | 4500 | 0.0285        |
 
 
 ### Framework Versions

eval/Information-Retrieval_evaluation_val_results.csv

@@ -606,3 +606,47 @@ epoch,steps,cosine-Accuracy@1,cosine-Accuracy@3,cosine-Accuracy@5,cosine-Precisi
 13.675213675213675,4800,0.8024,0.867775,0.8947,0.8024,0.8024,0.2892583333333333,0.867775,0.17894000000000004,0.8947,0.8024,0.837397083333328,0.8419506051587267,0.8627007599790489,0.844947246350743
 13.96011396011396,4900,0.802475,0.867625,0.8947,0.802475,0.802475,0.2892083333333333,0.867625,0.17894,0.8947,0.802475,0.8374054166666614,0.8419520734126953,0.8626792917708476,0.8449600866335961
 14.245014245014245,5000,0.802275,0.8676,0.89495,0.802275,0.802275,0.28919999999999996,0.8676,0.17899,0.89495,0.802275,0.8373504166666614,0.8418555952380918,0.8626142815266079,0.8448604581747029
+0,0,0.75475,0.807325,0.8301,0.75475,0.75475,0.26910833333333334,0.807325,0.16602000000000003,0.8301,0.75475,0.7832029166666623,0.7872338690476164,0.8046173386770612,0.7903520425688696
+0.2849002849002849,100,0.796175,0.8577,0.88265,0.796175,0.796175,0.28589999999999993,0.8577,0.17653,0.88265,0.796175,0.8290354166666617,0.8330638888888834,0.8521677642570125,0.8358178320575996
+0.5698005698005698,200,0.784475,0.84315,0.8672,0.784475,0.784475,0.28105,0.84315,0.17344,0.8672,0.784475,0.8159962499999954,0.8200031150793633,0.8384791712488908,0.8228448570308199
+0.8547008547008547,300,0.78025,0.839175,0.861825,0.78025,0.78025,0.279725,0.839175,0.17236500000000002,0.861825,0.78025,0.8115912499999965,0.8155929365079354,0.8338634063734118,0.81858663664552
+1.1396011396011396,400,0.7796,0.836375,0.859475,0.7796,0.7796,0.27879166666666666,0.836375,0.171895,0.859475,0.7796,0.8101866666666637,0.814323025793652,0.832474966301733,0.8173731509898491
+1.4245014245014245,500,0.77835,0.835975,0.85845,0.77835,0.77835,0.27865833333333323,0.835975,0.17169,0.85845,0.77835,0.8091520833333294,0.8134048611111101,0.8317308073898206,0.8165040167734905
+1.7094017094017095,600,0.778275,0.835575,0.8581,0.778275,0.778275,0.278525,0.835575,0.17162,0.8581,0.778275,0.8088762499999957,0.8130983531746014,0.8314025148001128,0.816217690621124
+0,0,0.754725,0.807325,0.8301,0.754725,0.754725,0.26910833333333334,0.807325,0.16602000000000003,0.8301,0.754725,0.7831958333333291,0.7872266369047594,0.8046123556235801,0.7903445712026085
+0.2849002849002849,100,0.797375,0.859575,0.8844,0.797375,0.797375,0.2865249999999999,0.859575,0.17688,0.8844,0.797375,0.8305149999999952,0.8345059424603127,0.8536210926508915,0.8372804579624533
+0.5698005698005698,200,0.789725,0.84965,0.87305,0.789725,0.789725,0.2832166666666666,0.84965,0.17461000000000002,0.87305,0.789725,0.8217358333333288,0.8259563690476173,0.8447889773563888,0.828774953291485
+0.8547008547008547,300,0.787275,0.847325,0.8709,0.787275,0.787275,0.28244166666666665,0.847325,0.17418000000000003,0.8709,0.787275,0.8193041666666621,0.82350532738095,0.8423637151196415,0.826429578942636
+1.1396011396011396,400,0.7867,0.8458,0.86945,0.7867,0.7867,0.2819333333333333,0.8458,0.17389000000000002,0.86945,0.7867,0.818467916666663,0.8228496329365084,0.8417510820603067,0.8258477335449915
+1.4245014245014245,500,0.7868,0.846,0.869425,0.7868,0.7868,0.282,0.846,0.173885,0.869425,0.7868,0.8184445833333286,0.8228658829365068,0.8418328180715564,0.8259027097981183
+1.7094017094017095,600,0.78605,0.84515,0.870025,0.78605,0.78605,0.28171666666666667,0.84515,0.17400500000000002,0.870025,0.78605,0.8181533333333294,0.8224353273809507,0.8414338910563253,0.825517420839985
+1.9943019943019942,700,0.78635,0.846525,0.87135,0.78635,0.78635,0.282175,0.846525,0.17427000000000004,0.87135,0.78635,0.818742083333329,0.8230201091269808,0.8421871242144556,0.8260574799200178
+0,0,0.754825,0.807325,0.8301,0.754825,0.754825,0.26910833333333334,0.807325,0.16602000000000003,0.8301,0.754825,0.7832374999999957,0.787268303571426,0.8046427161605445,0.7903864322163667
+0.2849002849002849,100,0.79885,0.86135,0.886225,0.79885,0.79885,0.28711666666666663,0.86135,0.177245,0.886225,0.79885,0.8321983333333277,0.8361825793650747,0.8553282215326108,0.8389776907963354
+0.5698005698005698,200,0.793875,0.854075,0.8792,0.793875,0.793875,0.2846916666666667,0.854075,0.17584,0.8792,0.793875,0.8263912499999949,0.8305786011904728,0.8497213805401139,0.833387328072171
+0.8547008547008547,300,0.793375,0.854275,0.879025,0.793375,0.793375,0.2847583333333333,0.854275,0.175805,0.879025,0.793375,0.8259491666666623,0.8301344940476162,0.8493093565470287,0.8330524953082112
+1.1396011396011396,400,0.792775,0.854,0.8791,0.792775,0.792775,0.2846666666666667,0.854,0.17582000000000003,0.8791,0.792775,0.8256333333333294,0.8299016269841244,0.8493061349466451,0.8328548504597877
+1.4245014245014245,500,0.79315,0.85445,0.8795,0.79315,0.79315,0.2848166666666666,0.85445,0.17590000000000003,0.8795,0.79315,0.8259987499999958,0.8303588194444425,0.8498565850864034,0.8333236437309594
+1.7094017094017095,600,0.79285,0.854275,0.87935,0.79285,0.79285,0.2847583333333333,0.854275,0.17587,0.87935,0.79285,0.8257824999999961,0.830204563492062,0.8497717724505139,0.8331862081137188
+1.9943019943019942,700,0.793175,0.854975,0.8805,0.793175,0.793175,0.28499166666666664,0.854975,0.17610000000000003,0.8805,0.793175,0.8263633333333295,0.830722906746029,0.8503634764229537,0.8337120756128774
+0,0,0.754775,0.807325,0.8301,0.754775,0.754775,0.26910833333333334,0.807325,0.16602000000000003,0.8301,0.754775,0.7832112499999957,0.787242053571426,0.8046231670544519,0.7903600161324507
+0.2849002849002849,100,0.79615,0.857775,0.882375,0.79615,0.79615,0.285925,0.857775,0.17647500000000002,0.882375,0.79615,0.8289549999999947,0.832990297619042,0.8520637248283474,0.8357482483347605
+0.5698005698005698,200,0.777175,0.83395,0.857125,0.777175,0.777175,0.2779833333333333,0.83395,0.171425,0.857125,0.777175,0.8076899999999956,0.8116668253968238,0.8296498244168109,0.8144450389334662
+0.8547008547008547,300,0.77035,0.82505,0.847675,0.77035,0.77035,0.27501666666666663,0.82505,0.16953500000000002,0.847675,0.77035,0.799767499999995,0.8037215178571419,0.8212718642320342,0.8068031056763888
+1.1396011396011396,400,0.7681,0.8222,0.84455,0.7681,0.7681,0.2740666666666666,0.8222,0.16891,0.84455,0.7681,0.797017499999995,0.8009361011904734,0.8183438750585047,0.8041027539289684
+1.4245014245014245,500,0.7672,0.821025,0.8429,0.7672,0.7672,0.273675,0.821025,0.16858,0.8429,0.7672,0.7958979166666613,0.79987089285714,0.8172590008552375,0.8031241593771481
+1.7094017094017095,600,0.7669,0.82115,0.84275,0.7669,0.7669,0.27371666666666666,0.82115,0.16854999999999998,0.84275,0.7669,0.7957587499999965,0.7997043948412685,0.8170424111303709,0.802964772800136
+1.9943019943019942,700,0.766425,0.8208,0.842675,0.766425,0.766425,0.27359999999999995,0.8208,0.168535,0.842675,0.766425,0.7953187499999951,0.7993151190476158,0.8167950570233485,0.8025623643950514
+2.2792022792022792,800,0.766375,0.8205,0.8422,0.766375,0.766375,0.27349999999999997,0.8205,0.16844,0.8422,0.766375,0.7951983333333292,0.7992007242063475,0.8165910983232557,0.8025051442553142
+2.564102564102564,900,0.7663,0.821,0.84225,0.7663,0.7663,0.27366666666666667,0.821,0.16845,0.84225,0.7663,0.7952154166666622,0.7993001091269828,0.8168061947707486,0.8025787941311054
+2.849002849002849,1000,0.766725,0.821325,0.843125,0.766725,0.766725,0.27377499999999994,0.821325,0.168625,0.843125,0.766725,0.7956799999999961,0.7996824801587293,0.8171977956251342,0.8029503920896344
+3.133903133903134,1100,0.7665,0.8211,0.842975,0.7665,0.7665,0.2737,0.8211,0.168595,0.842975,0.7665,0.7955254166666629,0.7995664980158718,0.817084912159011,0.8028673709051858
+3.4188034188034186,1200,0.7661,0.82055,0.843525,0.7661,0.7661,0.27351666666666663,0.82055,0.16870500000000002,0.843525,0.7661,0.795257916666662,0.7992490178571401,0.8169202179909771,0.8025264254107551
+3.7037037037037037,1300,0.76575,0.8207,0.8439,0.76575,0.76575,0.2735666666666666,0.8207,0.16878,0.8439,0.76575,0.795229166666662,0.799171448412697,0.8168601391927396,0.8024904807059976
+3.9886039886039883,1400,0.76575,0.82095,0.843525,0.76575,0.76575,0.27365,0.82095,0.16870500000000002,0.843525,0.76575,0.7952362499999959,0.7992633829365071,0.8169688778621846,0.8025662565672069
+4.273504273504273,1500,0.7655,0.820825,0.843425,0.7655,0.7655,0.2736083333333333,0.820825,0.168685,0.843425,0.7655,0.7950049999999953,0.7990424900793635,0.8168230260140891,0.8023453387923065
+4.5584045584045585,1600,0.765775,0.820725,0.843725,0.765775,0.765775,0.27357499999999996,0.820725,0.16874499999999998,0.843725,0.765775,0.7952158333333289,0.7992546726190469,0.8170621182091751,0.80254685195691
+4.843304843304844,1700,0.76565,0.820375,0.843625,0.76565,0.76565,0.27345833333333336,0.820375,0.168725,0.843625,0.76565,0.7950887499999948,0.7991350892857123,0.8169604610301645,0.8024394419752138
+5.128205128205128,1800,0.765475,0.8205,0.8436,0.765475,0.765475,0.2735,0.8205,0.16872,0.8436,0.765475,0.7949895833333285,0.799029236111109,0.8168726961066123,0.8023392613357988
+5.413105413105413,1900,0.7654,0.820525,0.84375,0.7654,0.7654,0.2735083333333333,0.820525,0.16875,0.84375,0.7654,0.7949549999999953,0.7989879960317439,0.8168550640005641,0.8022952787722268
+5.698005698005698,2000,0.76535,0.820425,0.8436,0.76535,0.76535,0.27347499999999997,0.820425,0.16872,0.8436,0.76535,0.7948791666666619,0.798946091269839,0.8168396181783457,0.8022530766472562

final_metrics.json

@@ -1,16 +1,16 @@
 {
-  "val_cosine_accuracy@1": 0.76415,
-  "val_cosine_accuracy@3": 0.822175,
-  "val_cosine_accuracy@5": 0.84665,
-  "val_cosine_precision@1": 0.76415,
-  "val_cosine_precision@3": 0.2740583333333333,
-  "val_cosine_precision@5": 0.16933,
-  "val_cosine_recall@1": 0.76415,
-  "val_cosine_recall@3": 0.822175,
-  "val_cosine_recall@5": 0.84665,
-  "val_cosine_ndcg@10": 0.8195085862842543,
-  "val_cosine_mrr@1": 0.76415,
-  "val_cosine_mrr@5": 0.7953370833333295,
-  "val_cosine_mrr@10": 0.8000376587301573,
-  "val_cosine_map@100": 0.8034052122492592
+  "val_cosine_accuracy@1": 0.802275,
+  "val_cosine_accuracy@3": 0.8676,
+  "val_cosine_accuracy@5": 0.89495,
+  "val_cosine_precision@1": 0.802275,
+  "val_cosine_precision@3": 0.28919999999999996,
+  "val_cosine_precision@5": 0.17899,
+  "val_cosine_recall@1": 0.802275,
+  "val_cosine_recall@3": 0.8676,
+  "val_cosine_recall@5": 0.89495,
+  "val_cosine_ndcg@10": 0.8626142815266079,
+  "val_cosine_mrr@1": 0.802275,
+  "val_cosine_mrr@5": 0.8373504166666614,
+  "val_cosine_mrr@10": 0.8418555952380918,
+  "val_cosine_map@100": 0.8448604581747029
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45cdb91cc553556968b278c530594e05d926d8a2c99d01838656167e2114a507
+oid sha256:403224fc6d7381f09938b5b954225a07a08307e6cebf1477857ebbf1e46bd401
 size 114011616

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7258c121488b2e4966f22215c04593a6fcbb89f836828ccbf066defc2eda8b93
+oid sha256:04c37ef25164a8c1c9c22021315ab198203ee1fb4254699c7311f96e42cb894d
 size 6161