Training in progress, step 5000

1_Pooling/config.json

@@ -1,7 +1,7 @@
 {
-    "word_embedding_dimension": 384,
-    "pooling_mode_cls_token": false,
-    "pooling_mode_mean_tokens": true,
+    "word_embedding_dimension": 512,
+    "pooling_mode_cls_token": true,
+    "pooling_mode_mean_tokens": false,
     "pooling_mode_max_tokens": false,
     "pooling_mode_mean_sqrt_len_tokens": false,
     "pooling_mode_weightedmean_tokens": false,

Information-Retrieval_evaluation_val_results.csv

@@ -12,3 +12,4 @@ epoch,steps,cosine-Accuracy@1,cosine-Accuracy@3,cosine-Accuracy@5,cosine-Precisi
 -1,-1,0.82585,0.902175,0.930075,0.82585,0.82585,0.30072499999999996,0.902175,0.186015,0.930075,0.82585,0.8661279166666617,0.8703281448412645,0.8922105025555344,0.8724788643099791
 -1,-1,0.00065,0.7986,0.880825,0.00065,0.00065,0.26619999999999994,0.7986,0.17616500000000002,0.880825,0.00065,0.288667083333407,0.2951483234127803,0.45147470340355694,0.2980051496600344
 -1,-1,0.827675,0.9006,0.9272,0.827675,0.827675,0.3001999999999999,0.9006,0.18544000000000002,0.9272,0.827675,0.8661058333333287,0.8703261011904707,0.8916124422761306,0.8726181110807445
+-1,-1,0.82885,0.902725,0.93035,0.82885,0.82885,0.3009083333333333,0.902725,0.18607000000000004,0.93035,0.82885,0.8681187499999955,0.8721355654761855,0.8933682535781845,0.8743952711926549

README.md

@@ -5,124 +5,51 @@ tags:
 - feature-extraction
 - dense
 - generated_from_trainer
-- dataset_size:359997
+- dataset_size:100000
 - loss:MultipleNegativesRankingLoss
-base_model: sentence-transformers/all-MiniLM-L12-v2
+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 sentence-transformers/all-MiniLM-L12-v2
-  results:
-  - task:
-      type: information-retrieval
-      name: Information Retrieval
-    dataset:
-      name: val
-      type: val
-    metrics:
-    - type: cosine_accuracy@1
-      value: 0.82885
-      name: Cosine Accuracy@1
-    - type: cosine_accuracy@3
-      value: 0.902725
-      name: Cosine Accuracy@3
-    - type: cosine_accuracy@5
-      value: 0.93035
-      name: Cosine Accuracy@5
-    - type: cosine_precision@1
-      value: 0.82885
-      name: Cosine Precision@1
-    - type: cosine_precision@3
-      value: 0.3009083333333333
-      name: Cosine Precision@3
-    - type: cosine_precision@5
-      value: 0.18607000000000004
-      name: Cosine Precision@5
-    - type: cosine_recall@1
-      value: 0.82885
-      name: Cosine Recall@1
-    - type: cosine_recall@3
-      value: 0.902725
-      name: Cosine Recall@3
-    - type: cosine_recall@5
-      value: 0.93035
-      name: Cosine Recall@5
-    - type: cosine_ndcg@10
-      value: 0.8933682535781845
-      name: Cosine Ndcg@10
-    - type: cosine_mrr@1
-      value: 0.82885
-      name: Cosine Mrr@1
-    - type: cosine_mrr@5
-      value: 0.8681187499999955
-      name: Cosine Mrr@5
-    - type: cosine_mrr@10
-      value: 0.8721355654761855
-      name: Cosine Mrr@10
-    - type: cosine_map@100
-      value: 0.8743952711926549
-      name: Cosine Map@100
 ---
 
-# SentenceTransformer based on sentence-transformers/all-MiniLM-L12-v2
+# SentenceTransformer based on prajjwal1/bert-small
 
-This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [sentence-transformers/all-MiniLM-L12-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L12-v2). It maps sentences & paragraphs to a 384-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [prajjwal1/bert-small](https://huggingface.co/prajjwal1/bert-small). It maps sentences & paragraphs to a 512-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
 
 ## Model Details
 
 ### Model Description
 - **Model Type:** Sentence Transformer
-- **Base model:** [sentence-transformers/all-MiniLM-L12-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L12-v2) <!-- at revision 936af83a2ecce5fe87a09109ff5cbcefe073173a -->
+- **Base model:** [prajjwal1/bert-small](https://huggingface.co/prajjwal1/bert-small) <!-- at revision 0ec5f86f27c1a77d704439db5e01c307ea11b9d4 -->
 - **Maximum Sequence Length:** 128 tokens
-- **Output Dimensionality:** 384 dimensions
+- **Output Dimensionality:** 512 dimensions
 - **Similarity Function:** Cosine Similarity
 <!-- - **Training Dataset:** Unknown -->
 <!-- - **Language:** Unknown -->
@@ -139,8 +66,7 @@ This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [s
 ```
 SentenceTransformer(
   (0): Transformer({'max_seq_length': 128, 'do_lower_case': False, 'architecture': 'BertModel'})
-  (1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
-  (2): Normalize()
+  (1): Pooling({'word_embedding_dimension': 512, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
 )
 ```
 
@@ -159,23 +85,23 @@ 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)
-# [3, 384]
+# [3, 512]
 
 # Get the similarity scores for the embeddings
 similarities = model.similarity(embeddings, embeddings)
 print(similarities)
-# tensor([[ 0.9999,  0.9973, -0.0139],
-#         [ 0.9973,  1.0000, -0.0092],
-#         [-0.0139, -0.0092,  1.0000]])
+# tensor([[ 1.0000,  0.7596, -0.0398],
+#         [ 0.7596,  1.0000, -0.0308],
+#         [-0.0398, -0.0308,  1.0000]])
 ```
 
 <!--
@@ -202,32 +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  | 0.8288     |
-| cosine_accuracy@3  | 0.9027     |
-| cosine_accuracy@5  | 0.9304     |
-| cosine_precision@1 | 0.8288     |
-| cosine_precision@3 | 0.3009     |
-| cosine_precision@5 | 0.1861     |
-| cosine_recall@1    | 0.8288     |
-| cosine_recall@3    | 0.9027     |
-| cosine_recall@5    | 0.9304     |
-| **cosine_ndcg@10** | **0.8934** |
-| cosine_mrr@1       | 0.8288     |
-| cosine_mrr@5       | 0.8681     |
-| cosine_mrr@10      | 0.8721     |
-| cosine_map@100     | 0.8744     |
-
 <!--
 ## Bias, Risks and Limitations
 
@@ -246,49 +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": 7.0,
-      "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": 7.0,
+      "scale": 20.0,
       "similarity_fct": "cos_sim",
       "gather_across_devices": false
   }
@@ -297,49 +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`: 0.0001
-- `max_steps`: 12000
-- `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`: 0.0001
+- `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`: 12000
+- `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
@@ -367,14 +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
@@ -384,23 +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
@@ -427,71 +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     | -             | 0.9225          | 0.8948             |
-| 0.1778 | 250   | 0.9562        | 0.6672          | 0.8930             |
-| 0.3556 | 500   | 0.8212        | 0.6496          | 0.8921             |
-| 0.5334 | 750   | 0.7906        | 0.6376          | 0.8921             |
-| 0.7112 | 1000  | 0.7719        | 0.6282          | 0.8919             |
-| 0.8890 | 1250  | 0.7542        | 0.6206          | 0.8919             |
-| 1.0669 | 1500  | 0.7378        | 0.6131          | 0.8913             |
-| 1.2447 | 1750  | 0.7249        | 0.6089          | 0.8921             |
-| 1.4225 | 2000  | 0.7152        | 0.6057          | 0.8918             |
-| 1.6003 | 2250  | 0.7095        | 0.6031          | 0.8924             |
-| 1.7781 | 2500  | 0.7041        | 0.5983          | 0.8925             |
-| 1.9559 | 2750  | 0.6991        | 0.5965          | 0.8925             |
-| 2.1337 | 3000  | 0.6895        | 0.5947          | 0.8920             |
-| 2.3115 | 3250  | 0.686         | 0.5920          | 0.8926             |
-| 2.4893 | 3500  | 0.6838        | 0.5907          | 0.8923             |
-| 2.6671 | 3750  | 0.6778        | 0.5888          | 0.8926             |
-| 2.8450 | 4000  | 0.6768        | 0.5872          | 0.8926             |
-| 3.0228 | 4250  | 0.675         | 0.5855          | 0.8927             |
-| 3.2006 | 4500  | 0.6672        | 0.5842          | 0.8928             |
-| 3.3784 | 4750  | 0.6667        | 0.5830          | 0.8930             |
-| 3.5562 | 5000  | 0.6651        | 0.5827          | 0.8931             |
-| 3.7340 | 5250  | 0.6626        | 0.5808          | 0.8930             |
-| 3.9118 | 5500  | 0.6605        | 0.5801          | 0.8929             |
-| 4.0896 | 5750  | 0.6585        | 0.5788          | 0.8932             |
-| 4.2674 | 6000  | 0.6539        | 0.5779          | 0.8928             |
-| 4.4452 | 6250  | 0.6534        | 0.5774          | 0.8931             |
-| 4.6230 | 6500  | 0.6517        | 0.5764          | 0.8931             |
-| 4.8009 | 6750  | 0.6507        | 0.5757          | 0.8933             |
-| 4.9787 | 7000  | 0.6504        | 0.5753          | 0.8930             |
-| 5.1565 | 7250  | 0.6449        | 0.5747          | 0.8930             |
-| 5.3343 | 7500  | 0.6461        | 0.5743          | 0.8934             |
-| 5.5121 | 7750  | 0.645         | 0.5735          | 0.8934             |
-| 5.6899 | 8000  | 0.6435        | 0.5732          | 0.8931             |
-| 5.8677 | 8250  | 0.6442        | 0.5727          | 0.8933             |
-| 6.0455 | 8500  | 0.6406        | 0.5722          | 0.8931             |
-| 6.2233 | 8750  | 0.6382        | 0.5719          | 0.8932             |
-| 6.4011 | 9000  | 0.6389        | 0.5713          | 0.8934             |
-| 6.5789 | 9250  | 0.64          | 0.5710          | 0.8933             |
-| 6.7568 | 9500  | 0.6382        | 0.5708          | 0.8932             |
-| 6.9346 | 9750  | 0.6381        | 0.5705          | 0.8934             |
-| 7.1124 | 10000 | 0.6358        | 0.5704          | 0.8934             |
-| 7.2902 | 10250 | 0.635         | 0.5700          | 0.8936             |
-| 7.4680 | 10500 | 0.6348        | 0.5699          | 0.8932             |
-| 7.6458 | 10750 | 0.6326        | 0.5697          | 0.8933             |
-| 7.8236 | 11000 | 0.6353        | 0.5695          | 0.8935             |
-| 8.0014 | 11250 | 0.6364        | 0.5694          | 0.8936             |
-| 8.1792 | 11500 | 0.6325        | 0.5692          | 0.8935             |
-| 8.3570 | 11750 | 0.6335        | 0.5692          | 0.8935             |
-| 8.5349 | 12000 | 0.633         | 0.5691          | 0.8934             |
+| 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

config.json

@@ -1,25 +1,23 @@
 {
   "architectures": [
-    "BertModel"
+    "MPNetModel"
   ],
   "attention_probs_dropout_prob": 0.1,
-  "classifier_dropout": null,
+  "bos_token_id": 0,
   "dtype": "float32",
-  "gradient_checkpointing": false,
+  "eos_token_id": 2,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
-  "hidden_size": 384,
+  "hidden_size": 768,
   "initializer_range": 0.02,
-  "intermediate_size": 1536,
-  "layer_norm_eps": 1e-12,
-  "max_position_embeddings": 512,
-  "model_type": "bert",
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "mpnet",
   "num_attention_heads": 12,
   "num_hidden_layers": 12,
-  "pad_token_id": 0,
-  "position_embedding_type": "absolute",
+  "pad_token_id": 1,
+  "relative_attention_num_buckets": 32,
   "transformers_version": "4.57.3",
-  "type_vocab_size": 2,
-  "use_cache": true,
-  "vocab_size": 30522
+  "vocab_size": 30527
 }

config_sentence_transformers.json

@@ -1,10 +1,10 @@
 {
+  "model_type": "SentenceTransformer",
   "__version__": {
     "sentence_transformers": "5.2.0",
     "transformers": "4.57.3",
     "pytorch": "2.9.1+cu128"
   },
-  "model_type": "SentenceTransformer",
   "prompts": {
     "query": "",
     "document": ""

eval/Information-Retrieval_evaluation_val_results.csv

@@ -916,3 +916,29 @@ epoch,steps,cosine-Accuracy@1,cosine-Accuracy@3,cosine-Accuracy@5,cosine-Precisi
 8.17923186344239,11500,0.8291,0.902725,0.930425,0.8291,0.8291,0.3009083333333333,0.902725,0.18608500000000003,0.930425,0.8291,0.868302916666662,0.8723129365079314,0.8934984837860438,0.8745770163799339
 8.357041251778094,11750,0.829025,0.90275,0.93025,0.829025,0.829025,0.3009166666666666,0.90275,0.18605000000000002,0.93025,0.829025,0.8682012499999952,0.8722469146825345,0.8934640564205625,0.87450322519466
 8.534850640113799,12000,0.82885,0.902725,0.93035,0.82885,0.82885,0.3009083333333333,0.902725,0.18607000000000004,0.93035,0.82885,0.8681187499999955,0.8721355654761855,0.8933682535781845,0.8743952711926549
+0,0,0.83325,0.905425,0.931,0.83325,0.83325,0.3018083333333333,0.905425,0.1862,0.931,0.83325,0.8712562499999954,0.8753886309523757,0.8962091395123962,0.8775492913588381
+0.17780938833570412,250,0.832375,0.90375,0.929875,0.832375,0.832375,0.30124999999999996,0.90375,0.18597500000000003,0.929875,0.832375,0.8701812499999957,0.8742124404761842,0.8948797132152311,0.8764104238925767
+0.35561877667140823,500,0.83225,0.9037,0.92935,0.83225,0.83225,0.3012333333333333,0.9037,0.18587000000000004,0.92935,0.83225,0.8698916666666621,0.873931021825391,0.8945232371748519,0.8761366578230303
+0.5334281650071123,750,0.831475,0.903525,0.929875,0.831475,0.831475,0.301175,0.903525,0.185975,0.929875,0.831475,0.8696999999999955,0.8736485714285654,0.8943132754963641,0.8758803021872879
+0.7112375533428165,1000,0.8312,0.90375,0.929625,0.8312,0.8312,0.30125,0.90375,0.185925,0.929625,0.8312,0.8694345833333297,0.8735466865079321,0.8944274218598192,0.8757309084630673
+0,0,0.83325,0.9054,0.931025,0.83325,0.83325,0.30179999999999996,0.9054,0.186205,0.931025,0.83325,0.8712620833333289,0.8753898115079312,0.8962099299176288,0.8775504617043945
+0.08890469416785206,250,0.832675,0.904675,0.93015,0.832675,0.832675,0.3015583333333333,0.904675,0.18603000000000003,0.93015,0.832675,0.8705983333333279,0.8746623015872936,0.8953542914520892,0.8768410276130258
+0.17780938833570412,500,0.8317,0.9038,0.92965,0.8317,0.8317,0.3012666666666666,0.9038,0.18593,0.92965,0.8317,0.8697616666666627,0.873868303571423,0.8946802521926287,0.8760491474379832
+0.26671408250355616,750,0.83145,0.903325,0.929625,0.83145,0.83145,0.3011083333333333,0.903325,0.18592500000000003,0.929625,0.83145,0.8694987499999955,0.8734923611111044,0.8941825619521252,0.8757099318021792
+0.35561877667140823,1000,0.83145,0.90435,0.930325,0.83145,0.83145,0.30144999999999994,0.90435,0.18606500000000004,0.930325,0.83145,0.8698029166666614,0.8738157638888823,0.8946742009603459,0.8759753021929175
+0.4445234708392603,1250,0.830725,0.903175,0.930425,0.830725,0.830725,0.30105833333333337,0.903175,0.186085,0.930425,0.830725,0.8692774999999965,0.873290496031741,0.8943062820490432,0.8754489530139679
+0.5334281650071123,1500,0.831025,0.90325,0.93005,0.831025,0.831025,0.3010833333333333,0.90325,0.18601000000000004,0.93005,0.831025,0.8693866666666634,0.8734269543650749,0.8943395716954996,0.8756240564541158
+0.6223328591749644,1750,0.83085,0.903625,0.93085,0.83085,0.83085,0.3012083333333333,0.903625,0.18617,0.93085,0.83085,0.869452499999996,0.8734516071428523,0.8944864600455292,0.8756336527083175
+0.7112375533428165,2000,0.831225,0.903225,0.931325,0.831225,0.831225,0.301075,0.903225,0.18626500000000004,0.931325,0.831225,0.8697695833333295,0.8737897519841222,0.8949105445330948,0.8759275133936261
+0.8001422475106685,2250,0.83075,0.9036,0.93125,0.83075,0.83075,0.3012,0.9036,0.18625,0.93125,0.83075,0.8696012499999961,0.8736466468253915,0.8948335206619568,0.8757729145090132
+0.8890469416785206,2500,0.831775,0.903725,0.93095,0.831775,0.831775,0.30124166666666663,0.903725,0.18619000000000002,0.93095,0.831775,0.870115416666663,0.874198214285711,0.8952109407450953,0.876351198859034
+0.9779516358463727,2750,0.831475,0.90365,0.931125,0.831475,0.831475,0.30121666666666663,0.90365,0.18622500000000003,0.931125,0.831475,0.8699791666666632,0.8740791666666621,0.8952096516523103,0.8762060286560743
+1.0668563300142249,3000,0.830625,0.9034,0.931025,0.830625,0.830625,0.3011333333333333,0.9034,0.186205,0.931025,0.830625,0.8694312499999962,0.8735366369047579,0.894772420113057,0.8756702778689754
+1.1557610241820768,3250,0.83085,0.903325,0.930625,0.83085,0.83085,0.30110833333333326,0.903325,0.18612500000000004,0.930625,0.83085,0.8694258333333299,0.8735892658730121,0.894807300652629,0.8757268250673087
+1.2446657183499288,3500,0.83045,0.903275,0.930425,0.83045,0.83045,0.3010916666666666,0.903275,0.18608500000000003,0.930425,0.83045,0.869105833333329,0.8733233234126934,0.8946213045339133,0.8754562971349984
+1.333570412517781,3750,0.8307,0.903775,0.930775,0.8307,0.8307,0.30125833333333324,0.903775,0.18615500000000001,0.930775,0.8307,0.8694320833333299,0.8735935119047575,0.8948420250169551,0.8757323145770602
+1.422475106685633,4000,0.83075,0.903175,0.930425,0.83075,0.83075,0.3010583333333333,0.903175,0.186085,0.930425,0.83075,0.8693033333333294,0.8735262797619,0.8948013471628159,0.8756675683920364
+1.5113798008534851,4250,0.830825,0.903675,0.931025,0.830825,0.830825,0.3012249999999999,0.903675,0.186205,0.931025,0.830825,0.8696312499999967,0.8737555456349175,0.8949400275891605,0.8759271983666178
+1.600284495021337,4500,0.8308,0.90395,0.931075,0.8308,0.8308,0.3013166666666666,0.90395,0.18621500000000002,0.931075,0.8308,0.869544999999996,0.8736585218253924,0.8948904344639832,0.8758201197543449
+1.689189189189189,4750,0.83075,0.903675,0.930725,0.83075,0.83075,0.30122499999999997,0.903675,0.18614500000000003,0.930725,0.83075,0.8694362499999956,0.8736176289682489,0.8948575707495342,0.8757800204606908
+1.7780938833570412,5000,0.831025,0.903825,0.9306,0.831025,0.831025,0.301275,0.903825,0.18612000000000004,0.9306,0.831025,0.8695604166666618,0.873754801587296,0.8949476210025439,0.8759213487912666

final_metrics.json

@@ -1,16 +1,16 @@
 {
-  "val_cosine_accuracy@1": 0.827675,
-  "val_cosine_accuracy@3": 0.9006,
-  "val_cosine_accuracy@5": 0.9272,
-  "val_cosine_precision@1": 0.827675,
-  "val_cosine_precision@3": 0.3001999999999999,
-  "val_cosine_precision@5": 0.18544000000000002,
-  "val_cosine_recall@1": 0.827675,
-  "val_cosine_recall@3": 0.9006,
-  "val_cosine_recall@5": 0.9272,
-  "val_cosine_ndcg@10": 0.8916124422761306,
-  "val_cosine_mrr@1": 0.827675,
-  "val_cosine_mrr@5": 0.8661058333333287,
-  "val_cosine_mrr@10": 0.8703261011904707,
-  "val_cosine_map@100": 0.8726181110807445
+  "val_cosine_accuracy@1": 0.82885,
+  "val_cosine_accuracy@3": 0.902725,
+  "val_cosine_accuracy@5": 0.93035,
+  "val_cosine_precision@1": 0.82885,
+  "val_cosine_precision@3": 0.3009083333333333,
+  "val_cosine_precision@5": 0.18607000000000004,
+  "val_cosine_recall@1": 0.82885,
+  "val_cosine_recall@3": 0.902725,
+  "val_cosine_recall@5": 0.93035,
+  "val_cosine_ndcg@10": 0.8933682535781845,
+  "val_cosine_mrr@1": 0.82885,
+  "val_cosine_mrr@5": 0.8681187499999955,
+  "val_cosine_mrr@10": 0.8721355654761855,
+  "val_cosine_map@100": 0.8743952711926549
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7c7afc06dad67124b52482ffca5970ca799969e342466f6e3c5f74a85a05d03
-size 133462128
+oid sha256:39ff98dbc91d0bddccd1ed85f5a47442723db4eb361d5877900472c83ac56263
+size 437967672

modules.json

@@ -10,11 +10,5 @@
     "name": "1",
     "path": "1_Pooling",
     "type": "sentence_transformers.models.Pooling"
-  },
-  {
-    "idx": 2,
-    "name": "2",
-    "path": "2_Normalize",
-    "type": "sentence_transformers.models.Normalize"
   }
 ]

special_tokens_map.json

@@ -1,27 +1,41 @@
 {
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
   "cls_token": {
-    "content": "[CLS]",
+    "content": "<s>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
-  "mask_token": {
-    "content": "[MASK]",
+  "eos_token": {
+    "content": "</s>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
   "pad_token": {
-    "content": "[PAD]",
+    "content": "<pad>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "sep_token": {
-    "content": "[SEP]",
+    "content": "</s>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2fc687b11de0bc1b3d8348f92e3b49ef1089a621506c7661fbf3248fcd54947e
-size 711649
+oid sha256:faaa392e91b132ea18a5c356477832565e05553acb30458841dd9710753a3dba
+size 710932

tokenizer_config.json

@@ -1,64 +1,72 @@
 {
   "added_tokens_decoder": {
     "0": {
-      "content": "[PAD]",
+      "content": "<s>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "100": {
-      "content": "[UNK]",
+    "1": {
+      "content": "<pad>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "101": {
-      "content": "[CLS]",
+    "2": {
+      "content": "</s>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "102": {
-      "content": "[SEP]",
+    "3": {
+      "content": "<unk>",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "103": {
-      "content": "[MASK]",
+    "104": {
+      "content": "[UNK]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
+    },
+    "30526": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
     }
   },
+  "bos_token": "<s>",
   "clean_up_tokenization_spaces": false,
-  "cls_token": "[CLS]",
-  "do_basic_tokenize": true,
+  "cls_token": "<s>",
   "do_lower_case": true,
+  "eos_token": "</s>",
   "extra_special_tokens": {},
-  "mask_token": "[MASK]",
+  "mask_token": "<mask>",
   "max_length": 128,
-  "model_max_length": 128,
-  "never_split": null,
+  "model_max_length": 384,
   "pad_to_multiple_of": null,
-  "pad_token": "[PAD]",
+  "pad_token": "<pad>",
   "pad_token_type_id": 0,
   "padding_side": "right",
-  "sep_token": "[SEP]",
+  "sep_token": "</s>",
   "stride": 0,
   "strip_accents": null,
   "tokenize_chinese_chars": true,
-  "tokenizer_class": "BertTokenizer",
+  "tokenizer_class": "MPNetTokenizer",
   "truncation_side": "right",
   "truncation_strategy": "longest_first",
   "unk_token": "[UNK]"

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c95d57155864ceb9f17b5db3a6c9a6215d12f49d260b60a68d720a3bc86ddd0
+oid sha256:3726ece5e3c076eec5b76be95311c502c97d1d84d6588af421499557cb47e84d
 size 6161

vocab.txt

@@ -1,3 +1,7 @@
+<s>
+<pad>
+</s>
+<unk>
 [PAD]
 [unused0]
 [unused1]
@@ -30520,3 +30524,4 @@ necessitated
 ##：
 ##？
 ##～
+<mask>