Training in progress, step 3510

Information-Retrieval_evaluation_val_results.csv

@@ -0,0 +1,2 @@
+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,-1,0.908,0.9684,0.9834,0.908,0.908,0.3228,0.9684,0.19667999999999997,0.9834,0.908,0.9386633333333337,0.9400269841269848,0.9532296698470627,0.9404621256346036

README.md

@@ -5,108 +5,38 @@ tags:
 - feature-extraction
 - dense
 - generated_from_trainer
-- dataset_size:90000
+- dataset_size:100000
 - loss:MultipleNegativesRankingLoss
 base_model: prajjwal1/bert-small
 widget:
-- source_sentence: How do I cope with my depression to keep my girlfriend?
+- source_sentence: How do I calculate IQ?
   sentences:
-  - How do you cope with depression?
-  - How do I cope with my depression to keep my girlfriend?
-  - What is the significance of Nevanlinna theory?
-- source_sentence: Which is the best college for MBA in Delhi?
+  - What is the easiest way to know my IQ?
+  - How do I calculate not IQ ?
+  - What are some creative and innovative business ideas with less investment in India?
+- source_sentence: How can I learn martial arts in my home?
   sentences:
-  - Who played the character of 'Russ' in friends?
-  - What will be the picture quality if a Standard STB is Connected to a Full HD 40"
-    Led TV?
-  - Which is the best college to do an MBA in Delhi?
-- source_sentence: What is poison mailbox?
+  - How can I learn martial arts by myself?
+  - What are the advantages and disadvantages of investing in gold?
+  - Can people see that I have looked at their pictures on instagram if I am not following
+    them?
+- source_sentence: When Enterprise picks you up do you have to take them back?
   sentences:
-  - What are the differences between a concentric and eccentric movement?
-  - What is poison mailbox?
-  - What is not poison mailbox ?
-- source_sentence: What are the examples of a presence of mind?
+  - Are there any software Training institute in Tuticorin?
+  - When Enterprise picks you up do you have to take them back?
+  - When Enterprise picks you up do them have to take youback?
+- source_sentence: What are some non-capital goods?
   sentences:
-  - What are not the examples of a presence of mind ?
-  - What's the point of dressing well?
-  - What are some of the greatest examples of the presence of mind?
-- source_sentence: What are some tips on making it through the job interview process
-    at Opus Bank?
+  - What are capital goods?
+  - How is the value of [math]\pi[/math] calculated?
+  - What are some non-capital goods?
+- source_sentence: What is the QuickBooks technical support phone number in New York?
   sentences:
-  - I've got an online coupon for Domino's pizza through the freecharge app. Is it
-    necessary to use that coupon only when I order online?
-  - What are not some tips on making it through the job interview process at Opus
-    Bank ?
-  - What are some tips on making it through the job interview process at Opus Bank?
+  - What caused the Great Depression?
+  - Can I apply for PR in Canada?
+  - Which is the best QuickBooks Hosting Support Number in New York?
 pipeline_tag: sentence-similarity
 library_name: sentence-transformers
-metrics:
-- cosine_accuracy@1
-- cosine_accuracy@3
-- cosine_accuracy@5
-- cosine_precision@1
-- cosine_precision@3
-- cosine_precision@5
-- cosine_recall@1
-- cosine_recall@3
-- cosine_recall@5
-- cosine_ndcg@10
-- cosine_mrr@1
-- cosine_mrr@5
-- cosine_mrr@10
-- cosine_map@100
-model-index:
-- name: SentenceTransformer based on prajjwal1/bert-small
-  results:
-  - task:
-      type: information-retrieval
-      name: Information Retrieval
-    dataset:
-      name: val
-      type: val
-    metrics:
-    - type: cosine_accuracy@1
-      value: 0.903
-      name: Cosine Accuracy@1
-    - type: cosine_accuracy@3
-      value: 0.9652
-      name: Cosine Accuracy@3
-    - type: cosine_accuracy@5
-      value: 0.9802
-      name: Cosine Accuracy@5
-    - type: cosine_precision@1
-      value: 0.903
-      name: Cosine Precision@1
-    - type: cosine_precision@3
-      value: 0.32173333333333337
-      name: Cosine Precision@3
-    - type: cosine_precision@5
-      value: 0.19603999999999996
-      name: Cosine Precision@5
-    - type: cosine_recall@1
-      value: 0.903
-      name: Cosine Recall@1
-    - type: cosine_recall@3
-      value: 0.9652
-      name: Cosine Recall@3
-    - type: cosine_recall@5
-      value: 0.9802
-      name: Cosine Recall@5
-    - type: cosine_ndcg@10
-      value: 0.9497950442756341
-      name: Cosine Ndcg@10
-    - type: cosine_mrr@1
-      value: 0.903
-      name: Cosine Mrr@1
-    - type: cosine_mrr@5
-      value: 0.93429
-      name: Cosine Mrr@5
-    - type: cosine_mrr@10
-      value: 0.93595873015873
-      name: Cosine Mrr@10
-    - type: cosine_map@100
-      value: 0.9364845314523799
-      name: Cosine Map@100
 ---
 
 # SentenceTransformer based on prajjwal1/bert-small
@@ -155,12 +85,12 @@ Then you can load this model and run inference.
 from sentence_transformers import SentenceTransformer
 
 # Download from the 🤗 Hub
-model = SentenceTransformer("redis/model-b-structured")
+model = SentenceTransformer("sentence_transformers_model_id")
 # Run inference
 sentences = [
-    'What are some tips on making it through the job interview process at Opus Bank?',
-    'What are some tips on making it through the job interview process at Opus Bank?',
-    'What are not some tips on making it through the job interview process at Opus Bank ?',
+    'What is the QuickBooks technical support phone number in New York?',
+    'Which is the best QuickBooks Hosting Support Number in New York?',
+    'Can I apply for PR in Canada?',
 ]
 embeddings = model.encode(sentences)
 print(embeddings.shape)
@@ -169,9 +99,9 @@ print(embeddings.shape)
 # Get the similarity scores for the embeddings
 similarities = model.similarity(embeddings, embeddings)
 print(similarities)
-# tensor([[1.0000, 1.0000, 0.1451],
-#         [1.0000, 1.0000, 0.1451],
-#         [0.1451, 0.1451, 1.0000]])
+# tensor([[1.0000, 0.8563, 0.0594],
+#         [0.8563, 1.0000, 0.1245],
+#         [0.0594, 0.1245, 1.0000]])
 ```
 
 <!--
@@ -198,32 +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  | 0.903      |
-| cosine_accuracy@3  | 0.9652     |
-| cosine_accuracy@5  | 0.9802     |
-| cosine_precision@1 | 0.903      |
-| cosine_precision@3 | 0.3217     |
-| cosine_precision@5 | 0.196      |
-| cosine_recall@1    | 0.903      |
-| cosine_recall@3    | 0.9652     |
-| cosine_recall@5    | 0.9802     |
-| **cosine_ndcg@10** | **0.9498** |
-| cosine_mrr@1       | 0.903      |
-| cosine_mrr@5       | 0.9343     |
-| cosine_mrr@10      | 0.936      |
-| cosine_map@100     | 0.9365     |
-
 <!--
 ## Bias, Risks and Limitations
 
@@ -242,45 +146,19 @@ You can finetune this model on your own dataset.
 
 #### Unnamed Dataset
 
-* Size: 90,000 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: 6 tokens</li><li>mean: 15.63 tokens</li><li>max: 75 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 15.77 tokens</li><li>max: 75 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 16.2 tokens</li><li>max: 75 tokens</li></ul> |
-* Samples:
-  | anchor                                                   | positive                                                 | negative                                                                    |
-  |:---------------------------------------------------------|:---------------------------------------------------------|:----------------------------------------------------------------------------|
-  | <code>How long did it take to develop Pokémon GO?</code> | <code>How long did it take to develop Pokémon GO?</code> | <code>Can I take more than one gym in Pokémon GO?</code>                    |
-  | <code>How bad is 6/18 eyesight?</code>                   | <code>How bad is 6/18 eyesight?</code>                   | <code>How was bad eyesight dealt with in ancient and medieval times?</code> |
-  | <code>How can I do learn speaking English easily?</code> | <code>How can I learn speaking English easily?</code>    | <code>How can English do learn speaking Ieasily?</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: 5,000 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                                                                          |
+  |         | sentence_0                                                                        | sentence_1                                                                        | sentence_2                                                                        |
   |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
   | type    | string                                                                            | string                                                                            | string                                                                            |
-  | details | <ul><li>min: 6 tokens</li><li>mean: 15.65 tokens</li><li>max: 49 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 15.69 tokens</li><li>max: 49 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 16.66 tokens</li><li>max: 55 tokens</li></ul> |
+  | details | <ul><li>min: 6 tokens</li><li>mean: 15.79 tokens</li><li>max: 66 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 15.68 tokens</li><li>max: 66 tokens</li></ul> | <ul><li>min: 7 tokens</li><li>mean: 16.37 tokens</li><li>max: 67 tokens</li></ul> |
 * Samples:
-  | anchor                                                                                                                                                             | positive                                                                                                                                                           | negative                                                                                                                                                               |
-  |:-------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------|
-  | <code>What's it like working in IT for Goldman Sachs?</code>                                                                                                       | <code>What's it like working in IT for Goldman Sachs?</code>                                                                                                       | <code>it 's Whatlike working in IT for Goldman Sachs?</code>                                                                                                           |
-  | <code>Will time travel be possible in future?</code>                                                                                                               | <code>Is time travel still theorized as being possible?</code>                                                                                                     | <code>Will time travel be not possible in future ?</code>                                                                                                              |
-  | <code>For creating a software based service for SME’s, we need to tie up with a bank. Need the best way to contact the right person in big banks like HDFC.</code> | <code>For creating a software based service for SME’s, we need to tie up with a bank. Need the best way to contact the right person in big banks like HDFC.</code> | <code>For creating a software based service for SME ’s , we need to tie up with a bank . Need the right way to contact the best person in big banks like HDFC .</code> |
+  | sentence_0                                                       | sentence_1                                                       | sentence_2                                                                        |
+  |:-----------------------------------------------------------------|:-----------------------------------------------------------------|:----------------------------------------------------------------------------------|
+  | <code>Is masturbating bad for boys?</code>                       | <code>Is masturbating bad for boys?</code>                       | <code>How harmful or unhealthy is masturbation?</code>                            |
+  | <code>Does a train engine move in reverse?</code>                | <code>Does a train engine move in reverse?</code>                | <code>Time moves forward, not in reverse. Doesn't that make time a vector?</code> |
+  | <code>What is the most badass thing anyone has ever done?</code> | <code>What is the most badass thing anyone has ever done?</code> | <code>anyone is the most badass thing Whathas ever done?</code>                   |
 * Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
   ```json
   {
@@ -293,49 +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`: 1053
-- `warmup_ratio`: 0.1
+- `per_device_train_batch_size`: 64
+- `per_device_eval_batch_size`: 64
 - `fp16`: True
-- `dataloader_drop_last`: True
-- `dataloader_num_workers`: 1
-- `dataloader_prefetch_factor`: 1
-- `load_best_model_at_end`: True
-- `optim`: adamw_torch
-- `ddp_find_unused_parameters`: False
-- `push_to_hub`: True
-- `hub_model_id`: redis/model-b-structured
-- `eval_on_start`: True
+- `multi_dataset_batch_sampler`: round_robin
 
 #### All Hyperparameters
 <details><summary>Click to expand</summary>
 
 - `overwrite_output_dir`: False
 - `do_predict`: False
-- `eval_strategy`: steps
+- `eval_strategy`: no
 - `prediction_loss_only`: True
-- `per_device_train_batch_size`: 256
-- `per_device_eval_batch_size`: 256
+- `per_device_train_batch_size`: 64
+- `per_device_eval_batch_size`: 64
 - `per_gpu_train_batch_size`: None
 - `per_gpu_eval_batch_size`: None
 - `gradient_accumulation_steps`: 1
 - `eval_accumulation_steps`: None
 - `torch_empty_cache_steps`: None
-- `learning_rate`: 2e-05
-- `weight_decay`: 0.001
+- `learning_rate`: 5e-05
+- `weight_decay`: 0.0
 - `adam_beta1`: 0.9
 - `adam_beta2`: 0.999
 - `adam_epsilon`: 1e-08
-- `max_grad_norm`: 1.0
-- `num_train_epochs`: 3.0
-- `max_steps`: 1053
+- `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
@@ -363,14 +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
@@ -380,23 +245,23 @@ You can finetune this model on your own dataset.
 - `parallelism_config`: None
 - `deepspeed`: None
 - `label_smoothing_factor`: 0.0
-- `optim`: adamw_torch
+- `optim`: adamw_torch_fused
 - `optim_args`: None
 - `adafactor`: False
 - `group_by_length`: False
 - `length_column_name`: length
 - `project`: huggingface
 - `trackio_space_id`: trackio
-- `ddp_find_unused_parameters`: False
+- `ddp_find_unused_parameters`: None
 - `ddp_bucket_cap_mb`: None
 - `ddp_broadcast_buffers`: False
 - `dataloader_pin_memory`: True
 - `dataloader_persistent_workers`: False
 - `skip_memory_metrics`: True
 - `use_legacy_prediction_loop`: False
-- `push_to_hub`: True
+- `push_to_hub`: False
 - `resume_from_checkpoint`: None
-- `hub_model_id`: redis/model-b-structured
+- `hub_model_id`: None
 - `hub_strategy`: every_save
 - `hub_private_repo`: None
 - `hub_always_push`: False
@@ -423,35 +288,32 @@ You can finetune this model on your own dataset.
 - `neftune_noise_alpha`: None
 - `optim_target_modules`: None
 - `batch_eval_metrics`: False
-- `eval_on_start`: True
+- `eval_on_start`: False
 - `use_liger_kernel`: False
 - `liger_kernel_config`: None
 - `eval_use_gather_object`: False
 - `average_tokens_across_devices`: True
 - `prompts`: None
 - `batch_sampler`: batch_sampler
-- `multi_dataset_batch_sampler`: proportional
+- `multi_dataset_batch_sampler`: round_robin
 - `router_mapping`: {}
 - `learning_rate_mapping`: {}
 
 </details>
 
 ### Training Logs
-| Epoch     | Step     | Training Loss | Validation Loss | val_cosine_ndcg@10 |
-|:---------:|:--------:|:-------------:|:---------------:|:------------------:|
-| 0         | 0        | -             | 1.7213          | 0.8444             |
-| 0.2849    | 100      | 1.0498        | -               | -                  |
-| 0.5698    | 200      | 0.2458        | -               | -                  |
-| 0.8547    | 300      | 0.1967        | -               | -                  |
-| 1.1396    | 400      | 0.1731        | -               | -                  |
-| 1.4245    | 500      | 0.158         | 0.1040          | 0.9472             |
-| 1.7094    | 600      | 0.1503        | -               | -                  |
-| 1.9943    | 700      | 0.14          | -               | -                  |
-| 2.2792    | 800      | 0.1375        | -               | -                  |
-| 2.5641    | 900      | 0.1301        | -               | -                  |
-| **2.849** | **1000** | **0.1234**    | **0.0925**      | **0.9498**         |
-
-* The bold row denotes the saved checkpoint.
+| Epoch  | Step | Training Loss |
+|:------:|:----:|:-------------:|
+| 0.3199 | 500  | 0.4294        |
+| 0.6398 | 1000 | 0.1268        |
+| 0.9597 | 1500 | 0.1           |
+| 1.2796 | 2000 | 0.0792        |
+| 1.5995 | 2500 | 0.0706        |
+| 1.9194 | 3000 | 0.0687        |
+| 2.2393 | 3500 | 0.0584        |
+| 2.5592 | 4000 | 0.057         |
+| 2.8791 | 4500 | 0.0581        |
+
 
 ### Framework Versions
 - Python: 3.10.18

eval/Information-Retrieval_evaluation_val_results.csv

@@ -2,3 +2,39 @@ epoch,steps,cosine-Accuracy@1,cosine-Accuracy@3,cosine-Accuracy@5,cosine-Precisi
 0,0,0.7522,0.8716,0.8976,0.7522,0.7522,0.29053333333333337,0.8716,0.17951999999999999,0.8976,0.7522,0.8141766666666673,0.8179282539682551,0.8443897738734513,0.8201287535897707
 1.4245014245014245,500,0.8984,0.9626,0.9796,0.8984,0.8984,0.3208666666666667,0.9626,0.19591999999999998,0.9796,0.8984,0.9308266666666667,0.9325202380952388,0.9471587549365493,0.9330120361154303
 2.849002849002849,1000,0.903,0.9652,0.9802,0.903,0.903,0.32173333333333337,0.9652,0.19603999999999996,0.9802,0.903,0.93429,0.93595873015873,0.9497950442756341,0.9364845314523799
+0,0,0.752,0.8716,0.8976,0.752,0.752,0.29053333333333337,0.8716,0.17951999999999999,0.8976,0.752,0.8140766666666672,0.8178282539682551,0.8443159598241655,0.8200287780097951
+0.2849002849002849,100,0.8028,0.9336,0.9606,0.8028,0.8028,0.3112,0.9336,0.19211999999999999,0.9606,0.8028,0.8707999999999997,0.8734792063492066,0.8999628282412199,0.8744365809026206
+0.5698005698005698,200,0.8818,0.9486,0.969,0.8818,0.8818,0.3162,0.9486,0.19379999999999997,0.969,0.8818,0.9169700000000003,0.9188958730158733,0.9346227322971039,0.9197775668798819
+0.8547008547008547,300,0.8932,0.9548,0.9722,0.8932,0.8932,0.3182666666666667,0.9548,0.19443999999999997,0.9722,0.8932,0.92455,0.9262189682539682,0.9405238086421854,0.927085472401337
+1.1396011396011396,400,0.895,0.9592,0.9766,0.895,0.895,0.3197333333333333,0.9592,0.19532,0.9766,0.895,0.9275566666666664,0.9291465873015872,0.9436646680979195,0.9299204944081907
+1.4245014245014245,500,0.8976,0.9608,0.9786,0.8976,0.8976,0.3202666666666667,0.9608,0.19571999999999998,0.9786,0.8976,0.9302033333333336,0.9319340476190481,0.9464840368155372,0.93250380336534
+1.7094017094017095,600,0.9012,0.9624,0.9798,0.9012,0.9012,0.3208,0.9624,0.19596,0.9798,0.9012,0.9325766666666668,0.9341109523809528,0.9481312439186262,0.9346918726395761
+1.9943019943019942,700,0.9026,0.9642,0.9806,0.9026,0.9026,0.3214,0.9642,0.19612,0.9806,0.9026,0.9338233333333336,0.9354094444444451,0.9494016714102691,0.9358979207167986
+2.2792022792022792,800,0.9036,0.9636,0.9802,0.9036,0.9036,0.3212,0.9636,0.19603999999999996,0.9802,0.9036,0.9343600000000001,0.9360184126984125,0.9498159835882998,0.9365398459160087
+2.564102564102564,900,0.9044,0.9646,0.9818,0.9044,0.9044,0.32153333333333334,0.9646,0.19635999999999998,0.9818,0.9044,0.9354066666666666,0.9368538888888887,0.950475801688231,0.9373901118360287
+2.849002849002849,1000,0.9052,0.9666,0.9818,0.9052,0.9052,0.3222,0.9666,0.19635999999999998,0.9818,0.9052,0.9360233333333335,0.9375734920634928,0.9512084545091051,0.9380431058811802
+3.133903133903134,1100,0.9058,0.9664,0.9814,0.9058,0.9058,0.3221333333333333,0.9664,0.19627999999999998,0.9814,0.9058,0.9363133333333331,0.9379010317460321,0.9514451621024324,0.9383630230369934
+3.4188034188034186,1200,0.9074,0.9664,0.981,0.9074,0.9074,0.3221333333333333,0.9664,0.19619999999999999,0.981,0.9074,0.9370933333333331,0.9388146825396827,0.9522097571309723,0.9392568561033527
+3.7037037037037037,1300,0.9072,0.9662,0.9824,0.9072,0.9072,0.3220666666666667,0.9662,0.19647999999999996,0.9824,0.9072,0.937483333333333,0.9389458730158728,0.9522473041371328,0.939431839170165
+3.9886039886039883,1400,0.9074,0.9672,0.9814,0.9074,0.9074,0.3224,0.9672,0.19627999999999998,0.9814,0.9074,0.9374533333333331,0.939161507936508,0.9525437940729724,0.9396075466203089
+4.273504273504273,1500,0.9092,0.9672,0.9822,0.9092,0.9092,0.3224,0.9672,0.19643999999999998,0.9822,0.9092,0.9384999999999997,0.9401135714285714,0.9533003039075331,0.9405341566811126
+4.5584045584045585,1600,0.9096,0.9672,0.9822,0.9096,0.9096,0.3224,0.9672,0.19643999999999998,0.9822,0.9096,0.93891,0.9404971428571433,0.9535876607555805,0.9409278641122062
+4.843304843304844,1700,0.9082,0.969,0.982,0.9082,0.9082,0.323,0.969,0.19639999999999996,0.982,0.9082,0.9384000000000002,0.9400878571428579,0.953392717309442,0.9404840470265015
+5.128205128205128,1800,0.9094,0.968,0.9832,0.9094,0.9094,0.3226666666666667,0.968,0.19663999999999995,0.9832,0.9094,0.9391966666666669,0.9406966666666673,0.9539258798148182,0.9410781176707947
+5.413105413105413,1900,0.911,0.9686,0.9826,0.911,0.911,0.3228666666666667,0.9686,0.19651999999999997,0.9826,0.911,0.939926666666667,0.9414888888888896,0.9544263660055258,0.9418952414141466
+5.698005698005698,2000,0.9092,0.9686,0.9836,0.9092,0.9092,0.3228666666666667,0.9686,0.19671999999999998,0.9836,0.9092,0.9393733333333337,0.9407995238095244,0.9539831254763356,0.9411852477617797
+5.982905982905983,2100,0.9094,0.969,0.9842,0.9094,0.9094,0.323,0.969,0.19684,0.9842,0.9094,0.93955,0.9408544444444449,0.9539826116358073,0.9412627373593819
+6.267806267806268,2200,0.9106,0.969,0.9842,0.9106,0.9106,0.323,0.969,0.19683999999999996,0.9842,0.9106,0.9402733333333337,0.9415598412698417,0.9543896052297114,0.9420296751078869
+6.552706552706553,2300,0.9108,0.9694,0.9836,0.9108,0.9108,0.32313333333333333,0.9694,0.19671999999999998,0.9836,0.9108,0.9403300000000001,0.9417396825396829,0.9545687842767867,0.942182426313767
+6.837606837606837,2400,0.9112,0.9688,0.9838,0.9112,0.9112,0.32293333333333335,0.9688,0.19676,0.9838,0.9112,0.9404233333333335,0.9418663492063495,0.9547447641571389,0.9422939942002442
+7.122507122507122,2500,0.9106,0.9696,0.9836,0.9106,0.9106,0.3232,0.9696,0.19671999999999998,0.9836,0.9106,0.9403600000000001,0.9417945238095239,0.9546595330687436,0.9422427863667379
+7.407407407407407,2600,0.9106,0.9688,0.9846,0.9106,0.9106,0.32293333333333335,0.9688,0.19691999999999998,0.9846,0.9106,0.9403466666666666,0.9416591269841272,0.9546413408053799,0.9420736822388138
+7.6923076923076925,2700,0.9106,0.9698,0.984,0.9106,0.9106,0.3232666666666667,0.9698,0.1968,0.984,0.9106,0.9403766666666669,0.9418299206349211,0.9548614738888802,0.942199023046597
+7.977207977207978,2800,0.911,0.9692,0.984,0.911,0.911,0.3230666666666667,0.9692,0.1968,0.984,0.911,0.9405033333333332,0.9418522222222224,0.9546181138998727,0.9423265801462183
+8.262108262108262,2900,0.9096,0.9696,0.9838,0.9096,0.9096,0.3232,0.9696,0.19675999999999996,0.9838,0.9096,0.9398633333333333,0.9413222222222224,0.9544037711181301,0.9417392466654881
+8.547008547008547,3000,0.912,0.969,0.9844,0.912,0.912,0.323,0.969,0.19687999999999997,0.9844,0.912,0.9409866666666666,0.9423544444444447,0.9551243697761646,0.9427933736314108
+8.831908831908832,3100,0.911,0.9688,0.984,0.911,0.911,0.32293333333333335,0.9688,0.19679999999999997,0.984,0.911,0.94048,0.9418774603174607,0.9547236289052001,0.9423332612869388
+9.116809116809117,3200,0.9106,0.969,0.9838,0.9106,0.9106,0.323,0.969,0.19676,0.9838,0.9106,0.9404333333333332,0.9418641269841271,0.954723430874728,0.9423151289033547
+9.401709401709402,3300,0.9106,0.969,0.984,0.9106,0.9106,0.323,0.969,0.19679999999999995,0.984,0.9106,0.9403533333333333,0.9417519841269842,0.9546344737257203,0.9422058505967718
+9.686609686609687,3400,0.9106,0.969,0.9838,0.9106,0.9106,0.323,0.969,0.19675999999999996,0.9838,0.9106,0.94029,0.9417384126984129,0.9546651626751027,0.9421697455120135
+9.971509971509972,3500,0.9104,0.9688,0.9842,0.9104,0.9104,0.32293333333333335,0.9688,0.19683999999999996,0.9842,0.9104,0.9402533333333333,0.9416303174603176,0.954585167414727,0.9420641228013908

final_metrics.json

@@ -0,0 +1,16 @@
+{
+  "val_cosine_accuracy@1": 0.908,
+  "val_cosine_accuracy@3": 0.9684,
+  "val_cosine_accuracy@5": 0.9834,
+  "val_cosine_precision@1": 0.908,
+  "val_cosine_precision@3": 0.3228,
+  "val_cosine_precision@5": 0.19667999999999997,
+  "val_cosine_recall@1": 0.908,
+  "val_cosine_recall@3": 0.9684,
+  "val_cosine_recall@5": 0.9834,
+  "val_cosine_ndcg@10": 0.9532296698470627,
+  "val_cosine_mrr@1": 0.908,
+  "val_cosine_mrr@5": 0.9386633333333337,
+  "val_cosine_mrr@10": 0.9400269841269848,
+  "val_cosine_map@100": 0.9404621256346036
+}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9165bec07d721d490566906032416157feb6461c69983b2c810cd24685e50198
+oid sha256:45b4ce06b2a2d061461c9871a66396c951f2af0a1f2815786891af9f01b422cc
 size 114011616

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7eb099fd92e0bda303c54813aea8d9078b59fb57bebde2e5cbe081c0de10f11
+oid sha256:b6f4887f5ef478963a7e033106fee2bacd4dadbcb37a8042cfd307bbace16506
 size 6161