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,-1,0.9208,0.9698,0.9842,0.9208,0.9208,0.3232666666666667,0.9698,0.19684,0.9842,0.9208,0.9460899999999998,0.9476021428571432,0.9593212690041523,0.9479260307963899

README.md

@@ -5,109 +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 polish my English skills?
   sentences:
-  - How do you cope with depression?
-  - How do I cope with my depression to keep my girlfriend?
-  - What does science say about crop circles?
-- source_sentence: Which is the best college for MBA in Delhi?
+  - 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:
-  - Will time travel be possible in future?
-  - 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?
+  - 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:
-  - What are examples of homonyms with meanings and sentences?
-  - What is poison mailbox?
-  - I was born on 29 may 1994 in pakistan city lahore my name is Ali Fraz Virk what
-    is my horoscope in details plz?
-- source_sentence: What are the differences between eccentric and concentric contraction?
-    What are some examples?
+  - 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:
-  - Why is it when I pass my crush he always looks down at his phone?
-  - How widely accepted are credit cards at small businesses and restaurants in Bahrain?
-  - What are the differences between a concentric and eccentric movement?
-- source_sentence: 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?
+  - 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:
-  - Who played the character of 'Russ' in friends?
-  - How do you use Dominos India WalkIn coupon code?
-  - 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?
+  - 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: 0.9156
-      name: Cosine Accuracy@1
-    - type: cosine_accuracy@3
-      value: 0.9674
-      name: Cosine Accuracy@3
-    - type: cosine_accuracy@5
-      value: 0.9828
-      name: Cosine Accuracy@5
-    - type: cosine_precision@1
-      value: 0.9156
-      name: Cosine Precision@1
-    - type: cosine_precision@3
-      value: 0.3224666666666667
-      name: Cosine Precision@3
-    - type: cosine_precision@5
-      value: 0.19655999999999996
-      name: Cosine Precision@5
-    - type: cosine_recall@1
-      value: 0.9156
-      name: Cosine Recall@1
-    - type: cosine_recall@3
-      value: 0.9674
-      name: Cosine Recall@3
-    - type: cosine_recall@5
-      value: 0.9828
-      name: Cosine Recall@5
-    - type: cosine_ndcg@10
-      value: 0.9557389379924726
-      name: Cosine Ndcg@10
-    - type: cosine_mrr@1
-      value: 0.9156
-      name: Cosine Mrr@1
-    - type: cosine_mrr@5
-      value: 0.9418899999999998
-      name: Cosine Mrr@5
-    - type: cosine_mrr@10
-      value: 0.9433757142857143
-      name: Cosine Mrr@10
-    - type: cosine_map@100
-      value: 0.9437967311048533
-      name: Cosine Map@100
 ---
 
 # SentenceTransformer based on prajjwal1/bert-small
@@ -156,12 +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 = [
-    "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?",
-    "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?",
-    'How do you use Dominos India WalkIn coupon code?',
+    '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)
@@ -170,9 +99,9 @@ print(embeddings.shape)
 # Get the similarity scores for the embeddings
 similarities = model.similarity(embeddings, embeddings)
 print(similarities)
-# tensor([[1.0000, 1.0000, 0.4250],
-#         [1.0000, 1.0000, 0.4250],
-#         [0.4250, 0.4250, 1.0000]])
+# tensor([[ 1.0000,  0.7596, -0.0398],
+#         [ 0.7596,  1.0000, -0.0308],
+#         [-0.0398, -0.0308,  1.0000]])
 ```
 
 <!--
@@ -199,32 +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  | 0.9156     |
-| cosine_accuracy@3  | 0.9674     |
-| cosine_accuracy@5  | 0.9828     |
-| cosine_precision@1 | 0.9156     |
-| cosine_precision@3 | 0.3225     |
-| cosine_precision@5 | 0.1966     |
-| cosine_recall@1    | 0.9156     |
-| cosine_recall@3    | 0.9674     |
-| cosine_recall@5    | 0.9828     |
-| **cosine_ndcg@10** | **0.9557** |
-| cosine_mrr@1       | 0.9156     |
-| cosine_mrr@5       | 0.9419     |
-| cosine_mrr@10      | 0.9434     |
-| cosine_map@100     | 0.9438     |
-
 <!--
 ## Bias, Risks and Limitations
 
@@ -243,45 +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: 16.5 tokens</li><li>max: 67 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 do you hack an Instagram account?</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                                                                          |
-  |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
-  | 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: 16.77 tokens</li><li>max: 67 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>What's it like working in IT for Goldman Sachs?</code>                                                                                                       | <code>What's it like working in IT for Goldman Sachs?</code>                                                                                                       | <code>What is the work done at Goldman Sachs?</code>                                           |
-  | <code>Will time travel be possible in future?</code>                                                                                                               | <code>Is time travel still theorized as being possible?</code>                                                                                                     | <code>What are the things that would make you fail a Canadian immigration medical exam?</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>What does it feel like to be eaten alive by a Pachycephalosaurus?</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
   {
@@ -294,49 +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-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`: 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
@@ -364,14 +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
@@ -381,23 +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
@@ -424,35 +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        | -             | 1.6082          | 0.8775             |
-| 0.2849    | 100      | 0.7901        | -               | -                  |
-| 0.5698    | 200      | 0.1342        | -               | -                  |
-| 0.8547    | 300      | 0.1166        | -               | -                  |
-| 1.1396    | 400      | 0.1036        | -               | -                  |
-| 1.4245    | 500      | 0.0934        | 0.0503          | 0.9550             |
-| 1.7094    | 600      | 0.0981        | -               | -                  |
-| 1.9943    | 700      | 0.0867        | -               | -                  |
-| 2.2792    | 800      | 0.0859        | -               | -                  |
-| 2.5641    | 900      | 0.0817        | -               | -                  |
-| **2.849** | **1000** | **0.0792**    | **0.046**       | **0.9557**         |
-
-* The bold row denotes the saved checkpoint.
+| 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
 - 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
 0,0,0.8306,0.8812,0.903,0.8306,0.8306,0.29373333333333335,0.8812,0.1806,0.903,0.8306,0.8580933333333336,0.8615153968253979,0.8775189066928426,0.8635987322727473
 1.4245014245014245,500,0.915,0.9666,0.9802,0.915,0.915,0.3222,0.9666,0.19603999999999996,0.9802,0.915,0.9408566666666663,0.9426431746031747,0.9549755895413731,0.9431098688909989
 2.849002849002849,1000,0.9156,0.9674,0.9828,0.9156,0.9156,0.3224666666666667,0.9674,0.19655999999999996,0.9828,0.9156,0.9418899999999998,0.9433757142857143,0.9557389379924726,0.9437967311048533
+0,0,0.8306,0.8812,0.903,0.8306,0.8306,0.29373333333333335,0.8812,0.1806,0.903,0.8306,0.8580933333333336,0.8615153968253979,0.8775189066928426,0.8635987322727473
+0.2849002849002849,100,0.894,0.948,0.9668,0.894,0.894,0.316,0.948,0.19336,0.9668,0.894,0.9223233333333335,0.9244372222222224,0.938479280073602,0.9252923238377365
+0.5698005698005698,200,0.908,0.9566,0.9762,0.908,0.908,0.31886666666666663,0.9566,0.19523999999999997,0.9762,0.908,0.934316666666666,0.9358780158730157,0.9484495917361974,0.9365908719441163
+0.8547008547008547,300,0.9136,0.9616,0.9776,0.9136,0.9136,0.3205333333333333,0.9616,0.19551999999999997,0.9776,0.9136,0.9383066666666664,0.939995555555555,0.9521233134462401,0.9406401752452377
+1.1396011396011396,400,0.9116,0.9638,0.9788,0.9116,0.9116,0.3212666666666667,0.9638,0.19575999999999996,0.9788,0.9116,0.938166666666666,0.9399092063492062,0.9524429443175384,0.94049272884241
+1.4245014245014245,500,0.9122,0.9658,0.9802,0.9122,0.9122,0.3219333333333333,0.9658,0.19603999999999996,0.9802,0.9122,0.9391566666666665,0.9408415079365081,0.9535259441616083,0.9413274048032421
+1.7094017094017095,600,0.9138,0.9662,0.9812,0.9138,0.9138,0.32206666666666667,0.9662,0.19623999999999997,0.9812,0.9138,0.9402833333333328,0.941934841269841,0.9544617890424794,0.9423965116472999
+1.9943019943019942,700,0.9154,0.9668,0.982,0.9154,0.9154,0.3222666666666667,0.9668,0.1964,0.982,0.9154,0.9416466666666667,0.9432646031746031,0.9556113325450355,0.9437089809657148
+2.2792022792022792,800,0.9146,0.9668,0.9824,0.9146,0.9146,0.32226666666666665,0.9668,0.19647999999999996,0.9824,0.9146,0.9411900000000002,0.9427308730158733,0.955214779372602,0.9431701536455497
+2.564102564102564,900,0.916,0.9676,0.983,0.916,0.916,0.3225333333333333,0.9676,0.19659999999999994,0.983,0.916,0.9424433333333334,0.9439552380952385,0.9562008945401774,0.9443868016274295
+2.849002849002849,1000,0.918,0.968,0.984,0.918,0.918,0.32266666666666666,0.968,0.19679999999999995,0.984,0.918,0.9436899999999999,0.9451158730158733,0.9572002608088729,0.9455037809055091
+3.133903133903134,1100,0.917,0.9674,0.9842,0.917,0.917,0.3224666666666667,0.9674,0.19683999999999996,0.9842,0.917,0.943383333333333,0.9447990476190476,0.9570223245145849,0.9451840665936517
+3.4188034188034186,1200,0.9182,0.9678,0.9848,0.9182,0.9182,0.3226,0.9678,0.19696,0.9848,0.9182,0.944073333333333,0.9454951587301582,0.957716972687552,0.9458173871961372
+3.7037037037037037,1300,0.9178,0.9682,0.9846,0.9178,0.9178,0.3227333333333333,0.9682,0.19691999999999998,0.9846,0.9178,0.9438833333333326,0.9453219841269834,0.9575541769846366,0.9456632030173215
+3.9886039886039883,1400,0.9176,0.9686,0.984,0.9176,0.9176,0.3228666666666667,0.9686,0.19679999999999997,0.984,0.9176,0.9436733333333331,0.9451425396825395,0.9573274263550402,0.9455296883797789
+4.273504273504273,1500,0.9174,0.9678,0.9838,0.9174,0.9174,0.3226,0.9678,0.19676,0.9838,0.9174,0.9438066666666663,0.9454632539682536,0.9578062092205877,0.9457650288600289
+4.5584045584045585,1600,0.9166,0.9676,0.9842,0.9166,0.9166,0.3225333333333333,0.9676,0.19683999999999996,0.9842,0.9166,0.9433833333333332,0.9449851587301588,0.9574903853768568,0.945263396166527
+4.843304843304844,1700,0.9174,0.9684,0.9842,0.9174,0.9174,0.3228,0.9684,0.19683999999999996,0.9842,0.9174,0.9439733333333328,0.9455711111111106,0.9578939600876886,0.945876005430171
+5.128205128205128,1800,0.918,0.9676,0.9852,0.918,0.918,0.3225333333333333,0.9676,0.19704,0.9852,0.918,0.944713333333333,0.9461937301587295,0.9584220005497169,0.946479562211455
+5.413105413105413,1900,0.9182,0.9686,0.9854,0.9182,0.9182,0.32286666666666664,0.9686,0.19707999999999998,0.9854,0.9182,0.9450499999999996,0.9464548412698407,0.9585785976256349,0.946755635836173
+5.698005698005698,2000,0.9178,0.9698,0.985,0.9178,0.9178,0.3232666666666667,0.9698,0.19699999999999998,0.985,0.9178,0.9446599999999995,0.9462009523809518,0.9584813888059387,0.9464702858471533
+5.982905982905983,2100,0.9178,0.968,0.9852,0.9178,0.9178,0.3226666666666667,0.968,0.19703999999999997,0.9852,0.9178,0.9446466666666662,0.9461438095238088,0.9583932509292831,0.9464317040482961
+6.267806267806268,2200,0.9178,0.9682,0.9848,0.9178,0.9178,0.32273333333333337,0.9682,0.19695999999999997,0.9848,0.9178,0.9443633333333328,0.9459359523809515,0.9582664640306275,0.9462111969736714
+6.552706552706553,2300,0.9174,0.9684,0.9854,0.9174,0.9174,0.3228,0.9684,0.19707999999999998,0.9854,0.9174,0.9443666666666665,0.945789444444444,0.9580402481297285,0.9461211373400121
+6.837606837606837,2400,0.9178,0.9688,0.985,0.9178,0.9178,0.32293333333333335,0.9688,0.19699999999999998,0.985,0.9178,0.9447166666666662,0.9462247619047613,0.9583790685463628,0.9465534299939993
+7.122507122507122,2500,0.9178,0.9686,0.9856,0.9178,0.9178,0.3228666666666667,0.9686,0.19712,0.9856,0.9178,0.9448433333333329,0.9462237301587298,0.9583360706069709,0.9465760314467667
+7.407407407407407,2600,0.9184,0.9694,0.9856,0.9184,0.9184,0.32313333333333333,0.9694,0.19712,0.9856,0.9184,0.9453399999999996,0.9467295238095232,0.9587266587881651,0.9470744407226759
+7.6923076923076925,2700,0.9184,0.9696,0.9854,0.9184,0.9184,0.3232,0.9696,0.19707999999999998,0.9854,0.9184,0.9452299999999996,0.9466565873015865,0.9587063233562559,0.9469863530316026
+7.977207977207978,2800,0.9178,0.9694,0.9858,0.9178,0.9178,0.32313333333333333,0.9694,0.19716,0.9858,0.9178,0.9450566666666662,0.9463881746031738,0.9584692678806099,0.9467396474480428
+8.262108262108262,2900,0.9184,0.9692,0.9858,0.9184,0.9184,0.3230666666666667,0.9692,0.19716,0.9858,0.9184,0.9451566666666662,0.9465150793650786,0.9585553275034318,0.9468657961140838
+8.547008547008547,3000,0.9178,0.9692,0.9852,0.9178,0.9178,0.32306666666666667,0.9692,0.19703999999999997,0.9852,0.9178,0.9447699999999996,0.9462491269841264,0.9584001704198265,0.9465882311515644
+8.831908831908832,3100,0.9182,0.9694,0.9854,0.9182,0.9182,0.32313333333333333,0.9694,0.19707999999999998,0.9854,0.9182,0.9449499999999996,0.9464100793650785,0.9585203799914772,0.9467427222866738
+9.116809116809117,3200,0.9186,0.97,0.9854,0.9186,0.9186,0.3233333333333333,0.97,0.19707999999999998,0.9854,0.9186,0.9452433333333329,0.9466879365079358,0.958729257011403,0.947022835299621
+9.401709401709402,3300,0.918,0.9702,0.9854,0.918,0.918,0.3234,0.9702,0.19707999999999998,0.9854,0.918,0.9449833333333331,0.9464248412698404,0.9585364250732368,0.9467604500159339
+9.686609686609687,3400,0.9184,0.9702,0.9852,0.9184,0.9184,0.3234,0.9702,0.19703999999999997,0.9852,0.9184,0.9451433333333329,0.946628888888888,0.9586880746687382,0.9469662432012432
+9.971509971509972,3500,0.9184,0.97,0.9852,0.9184,0.9184,0.3233333333333333,0.97,0.19703999999999997,0.9852,0.9184,0.9451033333333331,0.9465657142857136,0.9585962869405669,0.9469212791024237

final_metrics.json

@@ -0,0 +1,16 @@
+{
+  "val_cosine_accuracy@1": 0.9208,
+  "val_cosine_accuracy@3": 0.9698,
+  "val_cosine_accuracy@5": 0.9842,
+  "val_cosine_precision@1": 0.9208,
+  "val_cosine_precision@3": 0.3232666666666667,
+  "val_cosine_precision@5": 0.19684,
+  "val_cosine_recall@1": 0.9208,
+  "val_cosine_recall@3": 0.9698,
+  "val_cosine_recall@5": 0.9842,
+  "val_cosine_ndcg@10": 0.9593212690041523,
+  "val_cosine_mrr@1": 0.9208,
+  "val_cosine_mrr@5": 0.9460899999999998,
+  "val_cosine_mrr@10": 0.9476021428571432,
+  "val_cosine_map@100": 0.9479260307963899
+}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee7d9d9fee7497fde92d793ffc6328304766fa9a334e915960c5bc256741c07a
+oid sha256:3c69983267a6db5ae9801964f057ecf353f9ae2741d24a0d28d157e7ee25803a
 size 114011616

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e262ca922da3c62d4668d20589d461720a24a67b410afffa0ff380d6ccee45d
+oid sha256:ddb13b4a71cfc0f5a0deb789459db15cf201f8e30be7b6d481e4467797f714fa
 size 6161