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,-1,0.83545,0.911175,0.9366,0.83545,0.83545,0.303725,0.911175,0.18732000000000001,0.9366,0.83545,0.8751591666666616,0.8790415476190412,0.8999318372974409,0.8810239994800558
 -1,-1,0.0,0.0,2.5e-05,0.0,0.0,0.0,0.0,5e-06,2.5e-05,0.0,5e-06,1.697420634920635e-05,4.0643645983386815e-05,5.219463554638405e-05
 -1,-1,0.828275,0.90535,0.930675,0.828275,0.828275,0.3017833333333333,0.90535,0.186135,0.930675,0.828275,0.8685570833333288,0.8726829662698361,0.8940991092644636,0.8748315667834753
+-1,-1,0.833175,0.90785,0.933075,0.833175,0.833175,0.3026166666666666,0.90785,0.186615,0.933075,0.833175,0.8724479166666644,0.876612886904759,0.8976448899066025,0.8786690345206932

README.md

@@ -5,123 +5,51 @@ tags:
 - feature-extraction
 - dense
 - generated_from_trainer
-- dataset_size:713743
+- dataset_size:100000
 - loss:MultipleNegativesRankingLoss
-base_model: sentence-transformers/all-MiniLM-L12-v2
+base_model: prajjwal1/bert-small
 widget:
-- source_sentence: 'Abraham Lincoln: Why is the Gettysburg Address so memorable?'
+- source_sentence: How do I calculate IQ?
   sentences:
-  - 'Abraham Lincoln: Why is the Gettysburg Address so memorable?'
-  - What does the Gettysburg Address really mean?
-  - What is eatalo.com?
-- source_sentence: Has the influence of Ancient Carthage in science, math, and society
-    been underestimated?
+  - 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:
-  - How does one earn money online without an investment from home?
-  - Has the influence of Ancient Carthage in science, math, and society been underestimated?
-  - Has the influence of the Ancient Etruscans in science and math been underestimated?
-- source_sentence: Is there any app that shares charging to others like share it how
-    we transfer files?
+  - 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:
-  - How do you think of Chinese claims that the present Private Arbitration is illegal,
-    its verdict violates the UNCLOS and is illegal?
-  - Is there any app that shares charging to others like share it how we transfer
-    files?
-  - Are there any platforms that provides end-to-end encryption for file transfer/
-    sharing?
-- source_sentence: Why AAP’s MLA Dinesh Mohaniya has been arrested?
+  - 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 your views on the latest sex scandal by AAP MLA Sandeep Kumar?
-  - What is a dc current? What are some examples?
-  - Why AAP’s MLA Dinesh Mohaniya has been arrested?
-- source_sentence: What is the difference between economic growth and economic development?
+  - 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:
-  - How cold can the Gobi Desert get, and how do its average temperatures compare
-    to the ones in the Simpson Desert?
-  - the difference between economic growth and economic development is What?
-  - What is the difference between economic growth and economic development?
+  - 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 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: 0.833175
-      name: Cosine Accuracy@1
-    - type: cosine_accuracy@3
-      value: 0.90785
-      name: Cosine Accuracy@3
-    - type: cosine_accuracy@5
-      value: 0.933075
-      name: Cosine Accuracy@5
-    - type: cosine_precision@1
-      value: 0.833175
-      name: Cosine Precision@1
-    - type: cosine_precision@3
-      value: 0.3026166666666666
-      name: Cosine Precision@3
-    - type: cosine_precision@5
-      value: 0.186615
-      name: Cosine Precision@5
-    - type: cosine_recall@1
-      value: 0.833175
-      name: Cosine Recall@1
-    - type: cosine_recall@3
-      value: 0.90785
-      name: Cosine Recall@3
-    - type: cosine_recall@5
-      value: 0.933075
-      name: Cosine Recall@5
-    - type: cosine_ndcg@10
-      value: 0.8976448899066025
-      name: Cosine Ndcg@10
-    - type: cosine_mrr@1
-      value: 0.833175
-      name: Cosine Mrr@1
-    - type: cosine_mrr@5
-      value: 0.8724479166666644
-      name: Cosine Mrr@5
-    - type: cosine_mrr@10
-      value: 0.876612886904759
-      name: Cosine Mrr@10
-    - type: cosine_map@100
-      value: 0.8786690345206932
-      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 -->
@@ -138,8 +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})
 )
 ```
 
@@ -158,23 +85,23 @@ Then you can load this model and run inference.
 from sentence_transformers import SentenceTransformer
 
 # Download from the 🤗 Hub
-model = SentenceTransformer("redis/model-b-structured")
+model = SentenceTransformer("sentence_transformers_model_id")
 # Run inference
 sentences = [
-    'What is the difference between economic growth and economic development?',
-    'What is the difference between economic growth and economic development?',
-    'the difference between economic growth and economic development is What?',
+    '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)
-# [3, 384]
+# [3, 512]
 
 # Get the similarity scores for the embeddings
 similarities = model.similarity(embeddings, embeddings)
 print(similarities)
-# tensor([[ 1.0000,  1.0000, -0.0851],
-#         [ 1.0000,  1.0000, -0.0851],
-#         [-0.0851, -0.0851,  1.0000]])
+# tensor([[1.0000, 0.8563, 0.0594],
+#         [0.8563, 1.0000, 0.1245],
+#         [0.0594, 0.1245, 1.0000]])
 ```
 
 <!--
@@ -201,32 +128,6 @@ You can finetune this model on your own dataset.
 *List how the model may foreseeably be misused and address what users ought not to do with the model.*
 -->
 
-## Evaluation
-
-### Metrics
-
-#### Information Retrieval
-
-* Dataset: `val`
-* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
-
-| Metric             | Value      |
-|:-------------------|:-----------|
-| cosine_accuracy@1  | 0.8332     |
-| cosine_accuracy@3  | 0.9079     |
-| cosine_accuracy@5  | 0.9331     |
-| cosine_precision@1 | 0.8332     |
-| cosine_precision@3 | 0.3026     |
-| cosine_precision@5 | 0.1866     |
-| cosine_recall@1    | 0.8332     |
-| cosine_recall@3    | 0.9079     |
-| cosine_recall@5    | 0.9331     |
-| **cosine_ndcg@10** | **0.8976** |
-| cosine_mrr@1       | 0.8332     |
-| cosine_mrr@5       | 0.8724     |
-| cosine_mrr@10      | 0.8766     |
-| cosine_map@100     | 0.8787     |
-
 <!--
 ## Bias, Risks and Limitations
 
@@ -245,49 +146,23 @@ You can finetune this model on your own dataset.
 
 #### Unnamed Dataset
 
-* Size: 713,743 training 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: 16.07 tokens</li><li>max: 53 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 16.03 tokens</li><li>max: 53 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 16.81 tokens</li><li>max: 58 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>Which one is better Linux OS? Ubuntu or Mint?</code>                     | <code>Why do you use Linux Mint?</code>                                               | <code>Which one is not better Linux OS ? Ubuntu or Mint ?</code>                                                  |
-  | <code>What is flow?</code>                                                     | <code>What is flow?</code>                                                            | <code>What are flow lines?</code>                                                                                 |
-  | <code>How is Trump planning to get Mexico to pay for his supposed wall?</code> | <code>How is it possible for Donald Trump to force Mexico to pay for the wall?</code> | <code>Why do we connect the positive terminal before the negative terminal to ground in a vehicle battery?</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
   {
-      "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>
-* Approximate statistics based on the first 1000 samples:
-  |         | anchor                                                                            | positive                                                                          | negative                                                                          |
-  |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
-  | type    | string                                                                            | string                                                                            | string                                                                            |
-  | details | <ul><li>min: 6 tokens</li><li>mean: 15.52 tokens</li><li>max: 74 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 15.51 tokens</li><li>max: 74 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 16.79 tokens</li><li>max: 69 tokens</li></ul> |
-* Samples:
-  | anchor                                                                                                                                                       | positive                                                                                                                                                     | negative                                                                                                                                                            |
-  |:-------------------------------------------------------------------------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------------------------------------------------------------------------------------|
-  | <code>Why are all my questions on Quora marked needing improvement?</code>                                                                                   | <code>Why are all my questions immediately being marked as needing improvement?</code>                                                                       | <code>For a post-graduate student in IIT, is it allowed to take an external scholarship as a top-up to his/her MHRD assistantship?</code>                           |
-  | <code>Can blue butter fly needle with vaccum tube be reused? Is it HIV risk? . Heard the needle is too small to be reused . Had blood draw at clinic?</code> | <code>Can blue butter fly needle with vaccum tube be reused? Is it HIV risk? . Heard the needle is too small to be reused . Had blood draw at clinic?</code> | <code>Can blue butter fly needle with vaccum tube be reused not ? Is it HIV risk ? . Heard the needle is too small to be reused . Had blood draw at clinic ?</code> |
-  | <code>Why do people still believe the world is flat?</code>                                                                                                  | <code>Why are there still people who believe the world is flat?</code>                                                                                       | <code>I'm not able to buy Udemy course .it is not accepting mine and my friends debit card.my card can be used for Flipkart .how to purchase now?</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
   }
@@ -296,49 +171,36 @@ You can finetune this model on your own dataset.
 ### Training Hyperparameters
 #### Non-Default Hyperparameters
 
-- `eval_strategy`: steps
-- `per_device_train_batch_size`: 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-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`: 0.0001
+- `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
@@ -366,14 +228,14 @@ You can finetune this model on your own dataset.
 - `tpu_num_cores`: None
 - `tpu_metrics_debug`: False
 - `debug`: []
-- `dataloader_drop_last`: True
-- `dataloader_num_workers`: 1
-- `dataloader_prefetch_factor`: 1
+- `dataloader_drop_last`: False
+- `dataloader_num_workers`: 0
+- `dataloader_prefetch_factor`: None
 - `past_index`: -1
 - `disable_tqdm`: False
 - `remove_unused_columns`: True
 - `label_names`: None
-- `load_best_model_at_end`: True
+- `load_best_model_at_end`: False
 - `ignore_data_skip`: False
 - `fsdp`: []
 - `fsdp_min_num_params`: 0
@@ -383,23 +245,23 @@ You can finetune this model on your own dataset.
 - `parallelism_config`: None
 - `deepspeed`: None
 - `label_smoothing_factor`: 0.0
-- `optim`: adamw_torch
+- `optim`: adamw_torch_fused
 - `optim_args`: None
 - `adafactor`: False
 - `group_by_length`: False
 - `length_column_name`: length
 - `project`: huggingface
 - `trackio_space_id`: trackio
-- `ddp_find_unused_parameters`: False
+- `ddp_find_unused_parameters`: None
 - `ddp_bucket_cap_mb`: None
 - `ddp_broadcast_buffers`: False
 - `dataloader_pin_memory`: True
 - `dataloader_persistent_workers`: False
 - `skip_memory_metrics`: True
 - `use_legacy_prediction_loop`: False
-- `push_to_hub`: True
+- `push_to_hub`: False
 - `resume_from_checkpoint`: None
-- `hub_model_id`: redis/model-b-structured
+- `hub_model_id`: None
 - `hub_strategy`: every_save
 - `hub_private_repo`: None
 - `hub_always_push`: False
@@ -426,73 +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         | -             | 1.0936          | 0.8581             |
-| 0.0897     | 250       | 1.0794        | 0.7047          | 0.8883             |
-| 0.1793     | 500       | 0.8384        | 0.6462          | 0.8900             |
-| 0.2690     | 750       | 0.7888        | 0.6266          | 0.8910             |
-| 0.3587     | 1000      | 0.7605        | 0.6110          | 0.8918             |
-| 0.4484     | 1250      | 0.7359        | 0.5987          | 0.8925             |
-| 0.5380     | 1500      | 0.717         | 0.5884          | 0.8930             |
-| 0.6277     | 1750      | 0.7043        | 0.5822          | 0.8940             |
-| 0.7174     | 2000      | 0.694         | 0.5765          | 0.8938             |
-| 0.8070     | 2250      | 0.685         | 0.5723          | 0.8942             |
-| 0.8967     | 2500      | 0.6786        | 0.5687          | 0.8945             |
-| 0.9864     | 2750      | 0.6745        | 0.5649          | 0.8947             |
-| 1.0760     | 3000      | 0.6652        | 0.5617          | 0.8948             |
-| 1.1657     | 3250      | 0.6596        | 0.5581          | 0.8949             |
-| 1.2554     | 3500      | 0.6544        | 0.5566          | 0.8955             |
-| 1.3451     | 3750      | 0.6523        | 0.5556          | 0.8952             |
-| 1.4347     | 4000      | 0.6492        | 0.5533          | 0.8955             |
-| 1.5244     | 4250      | 0.6446        | 0.5513          | 0.8957             |
-| 1.6141     | 4500      | 0.6408        | 0.5477          | 0.8961             |
-| 1.7037     | 4750      | 0.6391        | 0.5477          | 0.8963             |
-| 1.7934     | 5000      | 0.6374        | 0.5468          | 0.8960             |
-| 1.8831     | 5250      | 0.6348        | 0.5446          | 0.8962             |
-| 1.9727     | 5500      | 0.6318        | 0.5431          | 0.8966             |
-| 2.0624     | 5750      | 0.627         | 0.5423          | 0.8967             |
-| 2.1521     | 6000      | 0.6249        | 0.5404          | 0.8966             |
-| 2.2418     | 6250      | 0.6264        | 0.5397          | 0.8965             |
-| 2.3314     | 6500      | 0.6225        | 0.5399          | 0.8967             |
-| 2.4211     | 6750      | 0.6212        | 0.5397          | 0.8966             |
-| 2.5108     | 7000      | 0.6196        | 0.5371          | 0.8971             |
-| 2.6004     | 7250      | 0.6156        | 0.5366          | 0.8967             |
-| 2.6901     | 7500      | 0.6171        | 0.5358          | 0.8971             |
-| 2.7798     | 7750      | 0.6158        | 0.5353          | 0.8972             |
-| 2.8694     | 8000      | 0.6162        | 0.5350          | 0.8974             |
-| 2.9591     | 8250      | 0.6135        | 0.5342          | 0.8972             |
-| 3.0488     | 8500      | 0.6107        | 0.5330          | 0.8973             |
-| 3.1385     | 8750      | 0.6094        | 0.5331          | 0.8974             |
-| 3.2281     | 9000      | 0.6104        | 0.5323          | 0.8974             |
-| 3.3178     | 9250      | 0.6092        | 0.5324          | 0.8973             |
-| 3.4075     | 9500      | 0.6078        | 0.5312          | 0.8975             |
-| 3.4971     | 9750      | 0.6094        | 0.5310          | 0.8975             |
-| 3.5868     | 10000     | 0.6061        | 0.5307          | 0.8973             |
-| 3.6765     | 10250     | 0.6052        | 0.5299          | 0.8974             |
-| 3.7661     | 10500     | 0.6057        | 0.5302          | 0.8975             |
-| 3.8558     | 10750     | 0.6057        | 0.5300          | 0.8975             |
-| 3.9455     | 11000     | 0.6054        | 0.5298          | 0.8976             |
-| 4.0352     | 11250     | 0.6043        | 0.5297          | 0.8975             |
-| 4.1248     | 11500     | 0.6019        | 0.5294          | 0.8976             |
-| 4.2145     | 11750     | 0.6033        | 0.5294          | 0.8977             |
-| **4.3042** | **12000** | **0.6045**    | **0.5294**      | **0.8976**         |
-
-* 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

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

@@ -777,3 +777,24 @@ epoch,steps,cosine-Accuracy@1,cosine-Accuracy@3,cosine-Accuracy@5,cosine-Precisi
 4.124820659971306,11500,0.832975,0.907825,0.9333,0.832975,0.832975,0.3026083333333333,0.907825,0.18666000000000005,0.9333,0.832975,0.8723804166666645,0.8765045734126956,0.8975652123999085,0.8785589645807509
 4.214490674318508,11750,0.83315,0.90785,0.9332,0.83315,0.83315,0.3026166666666666,0.90785,0.18664000000000003,0.9332,0.83315,0.8724679166666641,0.8766142063492031,0.897652921263943,0.878664477670976
 4.30416068866571,12000,0.833175,0.90785,0.933075,0.833175,0.833175,0.3026166666666666,0.90785,0.186615,0.933075,0.833175,0.8724479166666644,0.876612886904759,0.8976448899066025,0.8786690345206932
+0,0,0.768175,0.893425,0.9225,0.768175,0.768175,0.2978083333333333,0.893425,0.1845,0.9225,0.768175,0.8321754166666571,0.8363847519841202,0.8651787436112898,0.838709715053733
+0.04483500717360115,250,0.82765,0.906025,0.930875,0.82765,0.82765,0.3020083333333333,0.906025,0.186175,0.930875,0.82765,0.868539583333329,0.8725805357142814,0.8939423025222802,0.8746545651393303
+0.0896700143472023,500,0.830375,0.90615,0.9312,0.830375,0.830375,0.30204999999999993,0.90615,0.18624000000000004,0.9312,0.830375,0.8702320833333288,0.8742685515872952,0.8952934091476702,0.8763542898942245
+0.13450502152080343,750,0.8322,0.906825,0.932,0.8322,0.8322,0.30227499999999996,0.906825,0.1864,0.932,0.8322,0.8713941666666611,0.8753614583333267,0.8961670177914439,0.8774394226578622
+0.1793400286944046,1000,0.832375,0.906675,0.931925,0.832375,0.832375,0.302225,0.906675,0.18638500000000002,0.931925,0.832375,0.8715633333333297,0.875588214285709,0.8963968912239774,0.8776610751701158
+0.22417503586800575,1250,0.833325,0.907625,0.932275,0.833325,0.833325,0.30254166666666665,0.907625,0.186455,0.932275,0.833325,0.8722958333333292,0.876324503968247,0.8970919023728408,0.8783771474769665
+0.26901004304160686,1500,0.83315,0.90785,0.931825,0.83315,0.83315,0.30261666666666664,0.90785,0.186365,0.931825,0.83315,0.8720741666666627,0.8761482837301535,0.8968831136302299,0.8782338065235146
+0.31384505021520803,1750,0.833125,0.9077,0.931975,0.833125,0.833125,0.3025666666666666,0.9077,0.18639500000000003,0.931975,0.833125,0.8721212499999962,0.8761967063492008,0.8969507516136757,0.8782797193644479
+0.3586800573888092,2000,0.833525,0.907475,0.93225,0.833525,0.833525,0.3024916666666666,0.907475,0.18645,0.93225,0.833525,0.8721949999999957,0.8761980357142802,0.8968619878925894,0.8783116796035642
+0.4035150645624103,2250,0.83365,0.908275,0.932775,0.83365,0.83365,0.3027583333333333,0.908275,0.18655500000000005,0.932775,0.83365,0.872574583333329,0.8765678571428527,0.8972629315606638,0.8786637044220084
+0.4483500717360115,2500,0.833325,0.90865,0.933375,0.833325,0.833325,0.3028833333333333,0.90865,0.18667500000000004,0.933375,0.833325,0.8726774999999954,0.8766294444444397,0.8974063058927897,0.8787165668942624
+0.4931850789096126,2750,0.83395,0.909225,0.9332,0.83395,0.83395,0.30307499999999993,0.909225,0.18664,0.9332,0.83395,0.8730345833333287,0.8771071130952327,0.8979532226371164,0.8791389959975546
+0.5380200860832137,3000,0.8343,0.9085,0.9334,0.8343,0.8343,0.3028333333333333,0.9085,0.18668,0.9334,0.8343,0.8731358333333282,0.877109394841263,0.8978122253619178,0.8791909138926036
+0.582855093256815,3250,0.834475,0.908725,0.933425,0.834475,0.834475,0.3029083333333333,0.908725,0.18668500000000005,0.933425,0.834475,0.8733483333333294,0.8773927380952328,0.898185746255296,0.8794071055747712
+0.6276901004304161,3500,0.8348,0.90915,0.934575,0.8348,0.8348,0.30305,0.90915,0.186915,0.934575,0.8348,0.8738066666666622,0.8777039186507886,0.8984432454522335,0.8797468845226724
+0.6725251076040172,3750,0.834775,0.90955,0.93425,0.834775,0.834775,0.3031833333333333,0.90955,0.18685000000000004,0.93425,0.834775,0.8738545833333288,0.8778242658730111,0.898575343427753,0.8798489932766923
+0.7173601147776184,4000,0.834375,0.909025,0.93465,0.834375,0.834375,0.3030083333333333,0.909025,0.18693,0.93465,0.834375,0.8736395833333293,0.877541329365075,0.8983462327484772,0.8795742165685977
+0.7621951219512195,4250,0.834675,0.9089,0.934275,0.834675,0.834675,0.3029666666666666,0.9089,0.18685500000000008,0.934275,0.834675,0.8736633333333291,0.8776365476190431,0.8984431232955234,0.8796638302611205
+0.8070301291248206,4500,0.8346,0.90935,0.9345,0.8346,0.8346,0.3031166666666666,0.90935,0.1869,0.9345,0.8346,0.8737774999999952,0.8777162400793597,0.8985258842614039,0.8797375973269139
+0.8518651362984218,4750,0.83475,0.90905,0.93435,0.83475,0.83475,0.3030166666666666,0.90905,0.18687000000000004,0.93435,0.83475,0.873825833333329,0.8777601190476148,0.8984916815211705,0.8798133316506274
+0.896700143472023,5000,0.835025,0.909175,0.9345,0.835025,0.835025,0.30305833333333326,0.909175,0.1869,0.9345,0.835025,0.8739791666666628,0.8779108432539642,0.898643365395631,0.8799559806850633

final_metrics.json

@@ -1,16 +1,16 @@
 {
-  "val_cosine_accuracy@1": 0.828275,
-  "val_cosine_accuracy@3": 0.90535,
-  "val_cosine_accuracy@5": 0.930675,
-  "val_cosine_precision@1": 0.828275,
-  "val_cosine_precision@3": 0.3017833333333333,
-  "val_cosine_precision@5": 0.186135,
-  "val_cosine_recall@1": 0.828275,
-  "val_cosine_recall@3": 0.90535,
-  "val_cosine_recall@5": 0.930675,
-  "val_cosine_ndcg@10": 0.8940991092644636,
-  "val_cosine_mrr@1": 0.828275,
-  "val_cosine_mrr@5": 0.8685570833333288,
-  "val_cosine_mrr@10": 0.8726829662698361,
-  "val_cosine_map@100": 0.8748315667834753
+  "val_cosine_accuracy@1": 0.833175,
+  "val_cosine_accuracy@3": 0.90785,
+  "val_cosine_accuracy@5": 0.933075,
+  "val_cosine_precision@1": 0.833175,
+  "val_cosine_precision@3": 0.3026166666666666,
+  "val_cosine_precision@5": 0.186615,
+  "val_cosine_recall@1": 0.833175,
+  "val_cosine_recall@3": 0.90785,
+  "val_cosine_recall@5": 0.933075,
+  "val_cosine_ndcg@10": 0.8976448899066025,
+  "val_cosine_mrr@1": 0.833175,
+  "val_cosine_mrr@5": 0.8724479166666644,
+  "val_cosine_mrr@10": 0.876612886904759,
+  "val_cosine_map@100": 0.8786690345206932
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a1047f90ead99257dfe6d228a4901cfc9a8961a56b175574ee550bdf183c5337
-size 133462128
+oid sha256:d32578e43f741d79db0ddf8f897632635b4ee097c25a40ab477a811806ba90ca
+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 sha256:9b00bfe28f1f5c19078fccb765b6539914861c7d57b38fb16b169199ec0cec5c
+oid sha256:fcb37e6b968d556eedfc831d961ab7fcaa49504d2631242a44ef780da21af2c5
 size 6161

vocab.txt

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