Training in progress, step 5000

1_Pooling/config.json

@@ -1,5 +1,5 @@
 {
-    "word_embedding_dimension": 768,
+    "word_embedding_dimension": 512,
     "pooling_mode_cls_token": true,
     "pooling_mode_mean_tokens": false,
     "pooling_mode_max_tokens": false,

Information-Retrieval_evaluation_val_results.csv

@@ -14,3 +14,4 @@ epoch,steps,cosine-Accuracy@1,cosine-Accuracy@3,cosine-Accuracy@5,cosine-Precisi
 -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
 -1,-1,0.831025,0.903825,0.9306,0.831025,0.831025,0.301275,0.903825,0.18612000000000004,0.9306,0.831025,0.8695604166666618,0.873754801587296,0.8949476210025439,0.8759213487912666
+-1,-1,0.828675,0.90055,0.926875,0.828675,0.828675,0.3001833333333333,0.90055,0.185375,0.926875,0.828675,0.8668858333333296,0.870941557539677,0.8917140181282133,0.873184159266725

README.md

@@ -5,124 +5,51 @@ tags:
 - feature-extraction
 - dense
 - generated_from_trainer
-- dataset_size:359997
+- dataset_size:100000
 - loss:MultipleNegativesRankingLoss
-base_model: Alibaba-NLP/gte-modernbert-base
+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 Alibaba-NLP/gte-modernbert-base
-  results:
-  - task:
-      type: information-retrieval
-      name: Information Retrieval
-    dataset:
-      name: val
-      type: val
-    metrics:
-    - type: cosine_accuracy@1
-      value: 0.828675
-      name: Cosine Accuracy@1
-    - type: cosine_accuracy@3
-      value: 0.90055
-      name: Cosine Accuracy@3
-    - type: cosine_accuracy@5
-      value: 0.926875
-      name: Cosine Accuracy@5
-    - type: cosine_precision@1
-      value: 0.828675
-      name: Cosine Precision@1
-    - type: cosine_precision@3
-      value: 0.3001833333333333
-      name: Cosine Precision@3
-    - type: cosine_precision@5
-      value: 0.185375
-      name: Cosine Precision@5
-    - type: cosine_recall@1
-      value: 0.828675
-      name: Cosine Recall@1
-    - type: cosine_recall@3
-      value: 0.90055
-      name: Cosine Recall@3
-    - type: cosine_recall@5
-      value: 0.926875
-      name: Cosine Recall@5
-    - type: cosine_ndcg@10
-      value: 0.8917140181282133
-      name: Cosine Ndcg@10
-    - type: cosine_mrr@1
-      value: 0.828675
-      name: Cosine Mrr@1
-    - type: cosine_mrr@5
-      value: 0.8668858333333296
-      name: Cosine Mrr@5
-    - type: cosine_mrr@10
-      value: 0.870941557539677
-      name: Cosine Mrr@10
-    - type: cosine_map@100
-      value: 0.873184159266725
-      name: Cosine Map@100
 ---
 
-# SentenceTransformer based on Alibaba-NLP/gte-modernbert-base
+# SentenceTransformer based on prajjwal1/bert-small
 
-This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [Alibaba-NLP/gte-modernbert-base](https://huggingface.co/Alibaba-NLP/gte-modernbert-base). It maps sentences & paragraphs to a 768-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:** [Alibaba-NLP/gte-modernbert-base](https://huggingface.co/Alibaba-NLP/gte-modernbert-base) <!-- at revision e7f32e3c00f91d699e8c43b53106206bcc72bb22 -->
+- **Base model:** [prajjwal1/bert-small](https://huggingface.co/prajjwal1/bert-small) <!-- at revision 0ec5f86f27c1a77d704439db5e01c307ea11b9d4 -->
 - **Maximum Sequence Length:** 128 tokens
-- **Output Dimensionality:** 768 dimensions
+- **Output Dimensionality:** 512 dimensions
 - **Similarity Function:** Cosine Similarity
 <!-- - **Training Dataset:** Unknown -->
 <!-- - **Language:** Unknown -->
@@ -138,8 +65,8 @@ This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [A
 
 ```
 SentenceTransformer(
-  (0): Transformer({'max_seq_length': 128, 'do_lower_case': False, 'architecture': 'PeftModelForFeatureExtraction'})
-  (1): Pooling({'word_embedding_dimension': 768, '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})
+  (0): Transformer({'max_seq_length': 128, 'do_lower_case': False, 'architecture': 'BertModel'})
+  (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-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, 768]
+# [3, 512]
 
 # Get the similarity scores for the embeddings
 similarities = model.similarity(embeddings, embeddings)
 print(similarities)
-# tensor([[1.0000, 0.9865, 0.0499],
-#         [0.9865, 1.0000, 0.0422],
-#         [0.0499, 0.0422, 1.0000]])
+# tensor([[ 1.0000,  0.7596, -0.0398],
+#         [ 0.7596,  1.0000, -0.0308],
+#         [-0.0398, -0.0308,  1.0000]])
 ```
 
 <!--
@@ -201,32 +128,6 @@ You can finetune this model on your own dataset.
 *List how the model may foreseeably be misused and address what users ought not to do with the model.*
 -->
 
-## Evaluation
-
-### Metrics
-
-#### Information Retrieval
-
-* Dataset: `val`
-* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
-
-| Metric             | Value      |
-|:-------------------|:-----------|
-| cosine_accuracy@1  | 0.8287     |
-| cosine_accuracy@3  | 0.9005     |
-| cosine_accuracy@5  | 0.9269     |
-| cosine_precision@1 | 0.8287     |
-| cosine_precision@3 | 0.3002     |
-| cosine_precision@5 | 0.1854     |
-| cosine_recall@1    | 0.8287     |
-| cosine_recall@3    | 0.9005     |
-| cosine_recall@5    | 0.9269     |
-| **cosine_ndcg@10** | **0.8917** |
-| cosine_mrr@1       | 0.8287     |
-| cosine_mrr@5       | 0.8669     |
-| cosine_mrr@10      | 0.8709     |
-| cosine_map@100     | 0.8732     |
-
 <!--
 ## Bias, Risks and Limitations
 
@@ -245,49 +146,23 @@ You can finetune this model on your own dataset.
 
 #### Unnamed Dataset
 
-* Size: 359,997 training samples
-* Columns: <code>anchor</code>, <code>positive</code>, and <code>negative</code>
-* Approximate statistics based on the first 1000 samples:
-  |         | anchor                                                                           | positive                                                                          | negative                                                                          |
-  |:--------|:---------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
-  | type    | string                                                                           | string                                                                            | string                                                                            |
-  | details | <ul><li>min: 4 tokens</li><li>mean: 15.4 tokens</li><li>max: 47 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 15.47 tokens</li><li>max: 47 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 16.9 tokens</li><li>max: 125 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: 15.68 tokens</li><li>max: 72 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 15.75 tokens</li><li>max: 72 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 16.95 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
   }
@@ -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`: 128
-- `per_device_eval_batch_size`: 128
-- `learning_rate`: 0.0002
-- `weight_decay`: 0.0001
-- `max_steps`: 5000
-- `warmup_ratio`: 0.1
+- `per_device_train_batch_size`: 64
+- `per_device_eval_batch_size`: 64
 - `fp16`: True
-- `dataloader_drop_last`: True
-- `dataloader_num_workers`: 1
-- `dataloader_prefetch_factor`: 1
-- `load_best_model_at_end`: True
-- `optim`: adamw_torch
-- `ddp_find_unused_parameters`: False
-- `push_to_hub`: True
-- `hub_model_id`: redis/model-a-baseline
-- `eval_on_start`: True
+- `multi_dataset_batch_sampler`: round_robin
 
 #### All Hyperparameters
 <details><summary>Click to expand</summary>
 
 - `overwrite_output_dir`: False
 - `do_predict`: False
-- `eval_strategy`: steps
+- `eval_strategy`: no
 - `prediction_loss_only`: True
-- `per_device_train_batch_size`: 128
-- `per_device_eval_batch_size`: 128
+- `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`: 0.0002
-- `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`: 5000
+- `max_grad_norm`: 1
+- `num_train_epochs`: 3
+- `max_steps`: -1
 - `lr_scheduler_type`: linear
 - `lr_scheduler_kwargs`: {}
-- `warmup_ratio`: 0.1
+- `warmup_ratio`: 0.0
 - `warmup_steps`: 0
 - `log_level`: passive
 - `log_level_replica`: warning
@@ -366,14 +228,14 @@ You can finetune this model on your own dataset.
 - `tpu_num_cores`: None
 - `tpu_metrics_debug`: False
 - `debug`: []
-- `dataloader_drop_last`: True
-- `dataloader_num_workers`: 1
-- `dataloader_prefetch_factor`: 1
+- `dataloader_drop_last`: False
+- `dataloader_num_workers`: 0
+- `dataloader_prefetch_factor`: None
 - `past_index`: -1
 - `disable_tqdm`: False
 - `remove_unused_columns`: True
 - `label_names`: None
-- `load_best_model_at_end`: True
+- `load_best_model_at_end`: False
 - `ignore_data_skip`: False
 - `fsdp`: []
 - `fsdp_min_num_params`: 0
@@ -383,23 +245,23 @@ You can finetune this model on your own dataset.
 - `parallelism_config`: None
 - `deepspeed`: None
 - `label_smoothing_factor`: 0.0
-- `optim`: adamw_torch
+- `optim`: adamw_torch_fused
 - `optim_args`: None
 - `adafactor`: False
 - `group_by_length`: False
 - `length_column_name`: length
 - `project`: huggingface
 - `trackio_space_id`: trackio
-- `ddp_find_unused_parameters`: False
+- `ddp_find_unused_parameters`: None
 - `ddp_bucket_cap_mb`: None
 - `ddp_broadcast_buffers`: False
 - `dataloader_pin_memory`: True
 - `dataloader_persistent_workers`: False
 - `skip_memory_metrics`: True
 - `use_legacy_prediction_loop`: False
-- `push_to_hub`: True
+- `push_to_hub`: False
 - `resume_from_checkpoint`: None
-- `hub_model_id`: redis/model-a-baseline
+- `hub_model_id`: None
 - `hub_strategy`: every_save
 - `hub_private_repo`: None
 - `hub_always_push`: False
@@ -426,43 +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    | -             | 2.1886          | 0.8939             |
-| 0.0889 | 250  | 1.1449        | 0.4401          | 0.8927             |
-| 0.1778 | 500  | 0.4237        | 0.4117          | 0.8926             |
-| 0.2667 | 750  | 0.4067        | 0.3998          | 0.8924             |
-| 0.3556 | 1000 | 0.3971        | 0.3923          | 0.8918             |
-| 0.4445 | 1250 | 0.3875        | 0.3860          | 0.8915             |
-| 0.5334 | 1500 | 0.387         | 0.3827          | 0.8926             |
-| 0.6223 | 1750 | 0.3828        | 0.3792          | 0.8916             |
-| 0.7112 | 2000 | 0.3782        | 0.3766          | 0.8924             |
-| 0.8001 | 2250 | 0.3766        | 0.3736          | 0.8919             |
-| 0.8890 | 2500 | 0.3761        | 0.3715          | 0.8925             |
-| 0.9780 | 2750 | 0.3736        | 0.3700          | 0.8925             |
-| 1.0669 | 3000 | 0.3669        | 0.3690          | 0.8915             |
-| 1.1558 | 3250 | 0.3668        | 0.3670          | 0.8918             |
-| 1.2447 | 3500 | 0.3657        | 0.3661          | 0.8919             |
-| 1.3336 | 3750 | 0.3654        | 0.3656          | 0.8923             |
-| 1.4225 | 4000 | 0.3623        | 0.3646          | 0.8918             |
-| 1.5114 | 4250 | 0.3621        | 0.3641          | 0.8920             |
-| 1.6003 | 4500 | 0.3629        | 0.3636          | 0.8920             |
-| 1.6892 | 4750 | 0.3615        | 0.3633          | 0.8918             |
-| 1.7781 | 5000 | 0.3633        | 0.3632          | 0.8917             |
+| 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

@@ -1,23 +1,25 @@
 {
   "architectures": [
-    "MPNetModel"
+    "BertModel"
   ],
   "attention_probs_dropout_prob": 0.1,
-  "bos_token_id": 0,
+  "classifier_dropout": null,
   "dtype": "float32",
-  "eos_token_id": 2,
+  "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
+  "hidden_size": 384,
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
-  "layer_norm_eps": 1e-05,
-  "max_position_embeddings": 514,
-  "model_type": "mpnet",
+  "intermediate_size": 1536,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
   "num_attention_heads": 12,
-  "num_hidden_layers": 12,
-  "pad_token_id": 1,
-  "relative_attention_num_buckets": 32,
+  "num_hidden_layers": 6,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
   "transformers_version": "4.57.3",
-  "vocab_size": 30527
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
 }

config_sentence_transformers.json

@@ -1,4 +1,5 @@
 {
+  "model_type": "SentenceTransformer",
   "__version__": {
     "sentence_transformers": "5.2.0",
     "transformers": "4.57.3",
@@ -9,6 +10,5 @@
     "document": ""
   },
   "default_prompt_name": null,
-  "similarity_fn_name": "cosine",
-  "model_type": "SentenceTransformer"
+  "similarity_fn_name": "cosine"
 }

eval/Information-Retrieval_evaluation_NanoMSMARCO_results.csv

@@ -0,0 +1,22 @@
+epoch,steps,cosine-Accuracy@1,cosine-Accuracy@3,cosine-Accuracy@5,cosine-Accuracy@10,cosine-Precision@1,cosine-Recall@1,cosine-Precision@3,cosine-Recall@3,cosine-Precision@5,cosine-Recall@5,cosine-Precision@10,cosine-Recall@10,cosine-MRR@10,cosine-NDCG@10,cosine-MAP@100
+0,0,0.36,0.52,0.58,0.8,0.36,0.36,0.1733333333333333,0.52,0.11599999999999999,0.58,0.08,0.8,0.47960317460317464,0.5539831330912274,0.49062451473627944
+0.08890469416785206,250,0.36,0.54,0.6,0.78,0.36,0.36,0.18,0.54,0.12000000000000002,0.6,0.07800000000000001,0.78,0.4796904761904762,0.5499073299106572,0.49209218836063345
+0.17780938833570412,500,0.32,0.56,0.6,0.78,0.32,0.32,0.18666666666666668,0.56,0.12000000000000002,0.6,0.07800000000000001,0.78,0.4677222222222222,0.5413577108177489,0.4802720875316783
+0.26671408250355616,750,0.28,0.56,0.62,0.76,0.28,0.28,0.18666666666666668,0.56,0.124,0.62,0.07600000000000001,0.76,0.4429920634920635,0.518757208056322,0.4576362150920974
+0.35561877667140823,1000,0.26,0.54,0.62,0.74,0.26,0.26,0.18,0.54,0.124,0.62,0.07400000000000001,0.74,0.42354761904761906,0.4998350880619619,0.44002758203717285
+0.4445234708392603,1250,0.26,0.52,0.62,0.76,0.26,0.26,0.1733333333333333,0.52,0.124,0.62,0.07600000000000001,0.76,0.42177777777777775,0.5021229360365677,0.4367610701991507
+0.5334281650071123,1500,0.28,0.56,0.6,0.74,0.28,0.28,0.18666666666666668,0.56,0.12,0.6,0.07400000000000001,0.74,0.4298253968253969,0.5039792129037896,0.44583465499641967
+0.6223328591749644,1750,0.26,0.54,0.62,0.74,0.26,0.26,0.18,0.54,0.124,0.62,0.07400000000000001,0.74,0.41935714285714276,0.49633112285022385,0.4356450930963314
+0.7112375533428165,2000,0.26,0.56,0.6,0.76,0.26,0.26,0.18666666666666668,0.56,0.12000000000000002,0.6,0.07600000000000001,0.76,0.4227460317460318,0.503315188350914,0.4378963655081302
+0.8001422475106685,2250,0.26,0.56,0.62,0.76,0.26,0.26,0.18666666666666668,0.56,0.124,0.62,0.07600000000000001,0.76,0.42791269841269836,0.5076996338892674,0.44289572267461663
+0.8890469416785206,2500,0.26,0.52,0.6,0.74,0.26,0.26,0.1733333333333333,0.52,0.12,0.6,0.07400000000000001,0.74,0.4163333333333333,0.4938511148575469,0.43266654452396147
+0.9779516358463727,2750,0.24,0.52,0.64,0.76,0.24,0.24,0.1733333333333333,0.52,0.128,0.64,0.07600000000000001,0.76,0.4116587301587301,0.49532143492616165,0.42613080702668804
+1.0668563300142249,3000,0.24,0.52,0.58,0.74,0.24,0.24,0.1733333333333333,0.52,0.11599999999999999,0.58,0.07400000000000001,0.74,0.40285714285714286,0.48383672739823635,0.4186186112614183
+1.1557610241820768,3250,0.24,0.52,0.62,0.74,0.24,0.24,0.1733333333333333,0.52,0.124,0.62,0.07400000000000001,0.74,0.41002380952380946,0.4899620983176372,0.4249682250117033
+1.2446657183499288,3500,0.24,0.52,0.64,0.74,0.24,0.24,0.1733333333333333,0.52,0.128,0.64,0.07400000000000001,0.74,0.40835714285714286,0.4888328906655155,0.4232555567129404
+1.333570412517781,3750,0.22,0.5,0.64,0.74,0.22,0.22,0.16666666666666669,0.5,0.128,0.64,0.07400000000000001,0.74,0.3940714285714286,0.4781611600888875,0.4092852112328826
+1.422475106685633,4000,0.24,0.52,0.64,0.74,0.24,0.24,0.1733333333333333,0.52,0.128,0.64,0.07400000000000001,0.74,0.40659523809523807,0.48733720181837187,0.4212405538905539
+1.5113798008534851,4250,0.24,0.5,0.62,0.74,0.24,0.24,0.16666666666666663,0.5,0.124,0.62,0.07400000000000001,0.74,0.4034047619047619,0.484929652614928,0.4181722753854333
+1.600284495021337,4500,0.22,0.5,0.62,0.74,0.22,0.22,0.16666666666666663,0.5,0.124,0.62,0.07400000000000001,0.74,0.39304761904761903,0.477190878555405,0.4074930244047891
+1.689189189189189,4750,0.22,0.5,0.62,0.74,0.22,0.22,0.16666666666666663,0.5,0.124,0.62,0.07400000000000001,0.74,0.3977380952380953,0.4810433177745632,0.41242013542013545
+1.7780938833570412,5000,0.22,0.5,0.62,0.74,0.22,0.22,0.16666666666666663,0.5,0.124,0.62,0.07400000000000001,0.74,0.39240476190476187,0.47667177266958005,0.406991563991564

eval/Information-Retrieval_evaluation_NanoNQ_results.csv

@@ -0,0 +1,22 @@
+epoch,steps,cosine-Accuracy@1,cosine-Accuracy@3,cosine-Accuracy@5,cosine-Accuracy@10,cosine-Precision@1,cosine-Recall@1,cosine-Precision@3,cosine-Recall@3,cosine-Precision@5,cosine-Recall@5,cosine-Precision@10,cosine-Recall@10,cosine-MRR@10,cosine-NDCG@10,cosine-MAP@100
+0,0,0.48,0.62,0.66,0.72,0.48,0.47,0.21333333333333332,0.6,0.14,0.64,0.07600000000000001,0.7,0.5643571428571428,0.5930818641709092,0.5653172420421086
+0.08890469416785206,250,0.48,0.58,0.64,0.7,0.48,0.45,0.2,0.56,0.136,0.63,0.07600000000000001,0.69,0.5460238095238095,0.5724533305174622,0.5389600328534404
+0.17780938833570412,500,0.38,0.52,0.62,0.7,0.38,0.35,0.18,0.5,0.132,0.61,0.076,0.69,0.4826349206349206,0.5238768179719329,0.4745578080189774
+0.26671408250355616,750,0.4,0.52,0.6,0.66,0.4,0.38,0.18,0.5,0.128,0.59,0.07200000000000001,0.65,0.4843571428571428,0.5189026616282685,0.48412833492656937
+0.35561877667140823,1000,0.36,0.52,0.64,0.7,0.36,0.34,0.18,0.5,0.14,0.63,0.076,0.69,0.4633571428571429,0.5138465693710441,0.46313936723622007
+0.4445234708392603,1250,0.34,0.5,0.6,0.68,0.34,0.33,0.1733333333333333,0.48,0.124,0.58,0.07400000000000001,0.67,0.44752380952380943,0.4987798321488323,0.45062469816817646
+0.5334281650071123,1500,0.32,0.46,0.62,0.7,0.32,0.31,0.15999999999999998,0.45,0.132,0.6,0.076,0.69,0.4369126984126983,0.49702940684789093,0.4409254924835626
+0.6223328591749644,1750,0.34,0.48,0.6,0.68,0.34,0.33,0.16666666666666663,0.47,0.128,0.58,0.07400000000000001,0.67,0.44704761904761897,0.49972097764614104,0.45107525976111273
+0.7112375533428165,2000,0.32,0.52,0.58,0.68,0.32,0.31,0.18,0.51,0.12400000000000003,0.57,0.07200000000000001,0.66,0.43690476190476185,0.4879691187930975,0.4384783953201125
+0.8001422475106685,2250,0.32,0.5,0.6,0.68,0.32,0.31,0.1733333333333333,0.49,0.12400000000000003,0.58,0.07200000000000001,0.66,0.43554761904761896,0.4880679719241573,0.44019636647057736
+0.8890469416785206,2500,0.32,0.48,0.6,0.66,0.32,0.31,0.16666666666666663,0.47,0.124,0.57,0.07,0.64,0.4351904761904761,0.4825916032080211,0.4397672799380328
+0.9779516358463727,2750,0.32,0.48,0.58,0.66,0.32,0.31,0.16666666666666663,0.47,0.12,0.56,0.07,0.64,0.43083333333333335,0.4777541962108678,0.4323231266915096
+1.0668563300142249,3000,0.3,0.48,0.6,0.66,0.3,0.29,0.16666666666666663,0.47,0.124,0.57,0.07,0.64,0.42133333333333334,0.47229255220802463,0.42517218529648076
+1.1557610241820768,3250,0.3,0.46,0.56,0.64,0.3,0.29,0.15999999999999998,0.45,0.11600000000000002,0.54,0.068,0.62,0.41035714285714286,0.4587252892156562,0.41623585904278976
+1.2446657183499288,3500,0.3,0.44,0.56,0.64,0.3,0.29,0.15333333333333332,0.43,0.11600000000000002,0.54,0.068,0.62,0.40619047619047616,0.455712047803041,0.4120503380495542
+1.333570412517781,3750,0.28,0.48,0.56,0.64,0.28,0.27,0.16666666666666663,0.47,0.11600000000000002,0.54,0.068,0.62,0.4,0.4512373531362176,0.40502612367813556
+1.422475106685633,4000,0.28,0.46,0.58,0.64,0.28,0.27,0.15999999999999998,0.45,0.12,0.55,0.068,0.62,0.40185714285714286,0.4507822235956072,0.40304792384509147
+1.5113798008534851,4250,0.28,0.46,0.56,0.64,0.28,0.27,0.15999999999999998,0.45,0.11600000000000002,0.54,0.066,0.61,0.4007142857142857,0.4464041552654098,0.40196506995653586
+1.600284495021337,4500,0.28,0.46,0.56,0.64,0.28,0.27,0.15999999999999998,0.45,0.11600000000000002,0.54,0.066,0.61,0.4007142857142857,0.4481867157733463,0.4052506909192797
+1.689189189189189,4750,0.28,0.46,0.56,0.64,0.28,0.27,0.15999999999999998,0.45,0.11600000000000002,0.54,0.066,0.61,0.39452380952380955,0.4432300264150815,0.3986881566666595
+1.7780938833570412,5000,0.28,0.46,0.56,0.64,0.28,0.27,0.15999999999999998,0.45,0.11600000000000002,0.54,0.066,0.61,0.39785714285714285,0.4442430372694745,0.39869586832265574

eval/NanoBEIR_evaluation_mean_results.csv

@@ -0,0 +1,22 @@
+epoch,steps,cosine-Accuracy@1,cosine-Accuracy@3,cosine-Accuracy@5,cosine-Accuracy@10,cosine-Precision@1,cosine-Recall@1,cosine-Precision@3,cosine-Recall@3,cosine-Precision@5,cosine-Recall@5,cosine-Precision@10,cosine-Recall@10,cosine-MRR@10,cosine-NDCG@10,cosine-MAP@100
+0,0,0.42,0.5700000000000001,0.62,0.76,0.42,0.415,0.1933333333333333,0.56,0.128,0.61,0.07800000000000001,0.75,0.5219801587301587,0.5735324986310684,0.5279708783891941
+0.08890469416785206,250,0.42,0.56,0.62,0.74,0.42,0.405,0.19,0.55,0.128,0.615,0.07700000000000001,0.735,0.5128571428571429,0.5611803302140597,0.5155261106070369
+0.17780938833570412,500,0.35,0.54,0.61,0.74,0.35,0.33499999999999996,0.18333333333333335,0.53,0.126,0.605,0.07700000000000001,0.735,0.4751785714285714,0.5326172643948408,0.4774149477753279
+0.26671408250355616,750,0.34,0.54,0.61,0.71,0.34,0.33,0.18333333333333335,0.53,0.126,0.605,0.07400000000000001,0.7050000000000001,0.4636746031746032,0.5188299348422952,0.4708822750093334
+0.35561877667140823,1000,0.31,0.53,0.63,0.72,0.31,0.30000000000000004,0.18,0.52,0.132,0.625,0.07500000000000001,0.715,0.443452380952381,0.506840828716503,0.45158347463669646
+0.4445234708392603,1250,0.30000000000000004,0.51,0.61,0.72,0.30000000000000004,0.29500000000000004,0.1733333333333333,0.5,0.124,0.6,0.07500000000000001,0.7150000000000001,0.4346507936507936,0.5004513840927,0.4436928841836636
+0.5334281650071123,1500,0.30000000000000004,0.51,0.61,0.72,0.30000000000000004,0.29500000000000004,0.17333333333333334,0.505,0.126,0.6,0.07500000000000001,0.715,0.4333690476190476,0.5005043098758403,0.4433800737399911
+0.6223328591749644,1750,0.30000000000000004,0.51,0.61,0.71,0.30000000000000004,0.29500000000000004,0.1733333333333333,0.505,0.126,0.6,0.07400000000000001,0.7050000000000001,0.43320238095238084,0.4980260502481825,0.44336017642872205
+0.7112375533428165,2000,0.29000000000000004,0.54,0.59,0.72,0.29000000000000004,0.28500000000000003,0.18333333333333335,0.535,0.12200000000000003,0.585,0.07400000000000001,0.71,0.42982539682539683,0.4956421535720058,0.43818738041412136
+0.8001422475106685,2250,0.29000000000000004,0.53,0.61,0.72,0.29000000000000004,0.28500000000000003,0.18,0.525,0.12400000000000001,0.6,0.07400000000000001,0.71,0.43173015873015863,0.49788380290671236,0.441546044572597
+0.8890469416785206,2500,0.29000000000000004,0.5,0.6,0.7,0.29000000000000004,0.28500000000000003,0.16999999999999998,0.495,0.122,0.585,0.07200000000000001,0.69,0.4257619047619047,0.48822135903278396,0.4362169122309971
+0.9779516358463727,2750,0.28,0.5,0.61,0.71,0.28,0.275,0.16999999999999998,0.495,0.124,0.6000000000000001,0.07300000000000001,0.7,0.4212460317460317,0.4865378155685147,0.4292269668590988
+1.0668563300142249,3000,0.27,0.5,0.59,0.7,0.27,0.265,0.16999999999999998,0.495,0.12,0.575,0.07200000000000001,0.69,0.41209523809523807,0.4780646398031305,0.4218953982789495
+1.1557610241820768,3250,0.27,0.49,0.5900000000000001,0.69,0.27,0.265,0.16666666666666663,0.485,0.12000000000000001,0.5800000000000001,0.07100000000000001,0.6799999999999999,0.41019047619047616,0.4743436937666467,0.4206020420272465
+1.2446657183499288,3500,0.27,0.48,0.6000000000000001,0.69,0.27,0.265,0.16333333333333333,0.475,0.12200000000000001,0.5900000000000001,0.07100000000000001,0.6799999999999999,0.40727380952380954,0.47227246923427824,0.4176529473812473
+1.333570412517781,3750,0.25,0.49,0.6000000000000001,0.69,0.25,0.245,0.16666666666666666,0.485,0.12200000000000001,0.5900000000000001,0.07100000000000001,0.6799999999999999,0.39703571428571427,0.4646992566125525,0.4071556674555091
+1.422475106685633,4000,0.26,0.49,0.61,0.69,0.26,0.255,0.16666666666666663,0.485,0.124,0.595,0.07100000000000001,0.6799999999999999,0.40422619047619046,0.46905971270698954,0.4121442388678227
+1.5113798008534851,4250,0.26,0.48,0.5900000000000001,0.69,0.26,0.255,0.1633333333333333,0.475,0.12000000000000001,0.5800000000000001,0.07,0.675,0.4020595238095238,0.46566690394016885,0.41006867267098457
+1.600284495021337,4500,0.25,0.48,0.5900000000000001,0.69,0.25,0.245,0.1633333333333333,0.475,0.12000000000000001,0.5800000000000001,0.07,0.675,0.39688095238095233,0.4626887971643756,0.4063718576620344
+1.689189189189189,4750,0.25,0.48,0.5900000000000001,0.69,0.25,0.245,0.1633333333333333,0.475,0.12000000000000001,0.5800000000000001,0.07,0.675,0.3961309523809524,0.46213667209482234,0.40555414604339746
+1.7780938833570412,5000,0.25,0.48,0.5900000000000001,0.69,0.25,0.245,0.1633333333333333,0.475,0.12000000000000001,0.5800000000000001,0.07,0.675,0.39513095238095236,0.46045740496952725,0.4028437161571099

final_metrics.json

@@ -1,16 +1,16 @@
 {
-  "val_cosine_accuracy@1": 0.831025,
-  "val_cosine_accuracy@3": 0.903825,
-  "val_cosine_accuracy@5": 0.9306,
-  "val_cosine_precision@1": 0.831025,
-  "val_cosine_precision@3": 0.301275,
-  "val_cosine_precision@5": 0.18612000000000004,
-  "val_cosine_recall@1": 0.831025,
-  "val_cosine_recall@3": 0.903825,
-  "val_cosine_recall@5": 0.9306,
-  "val_cosine_ndcg@10": 0.8949476210025439,
-  "val_cosine_mrr@1": 0.831025,
-  "val_cosine_mrr@5": 0.8695604166666618,
-  "val_cosine_mrr@10": 0.873754801587296,
-  "val_cosine_map@100": 0.8759213487912666
+  "val_cosine_accuracy@1": 0.828675,
+  "val_cosine_accuracy@3": 0.90055,
+  "val_cosine_accuracy@5": 0.926875,
+  "val_cosine_precision@1": 0.828675,
+  "val_cosine_precision@3": 0.3001833333333333,
+  "val_cosine_precision@5": 0.185375,
+  "val_cosine_recall@1": 0.828675,
+  "val_cosine_recall@3": 0.90055,
+  "val_cosine_recall@5": 0.926875,
+  "val_cosine_ndcg@10": 0.8917140181282133,
+  "val_cosine_mrr@1": 0.828675,
+  "val_cosine_mrr@5": 0.8668858333333296,
+  "val_cosine_mrr@10": 0.870941557539677,
+  "val_cosine_map@100": 0.873184159266725
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39ff98dbc91d0bddccd1ed85f5a47442723db4eb361d5877900472c83ac56263
-size 437967672
+oid sha256:5839d66e8b7021ace7a80466d3912594c41783bf568b53dc58e99744e6b48e3b
+size 90864192

special_tokens_map.json

@@ -8,7 +8,7 @@
   },
   "mask_token": {
     "content": "[MASK]",
-    "lstrip": true,
+    "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:218484396a9d08293b108b0e5ea31e0a1b7c801dcbed35a821deb392d2fe9bb4
-size 3583485
+oid sha256:2fc687b11de0bc1b3d8348f92e3b49ef1089a621506c7661fbf3248fcd54947e
+size 711649

tokenizer_config.json

@@ -1,230 +1,14 @@
 {
   "added_tokens_decoder": {
     "0": {
-      "content": "|||IP_ADDRESS|||",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "1": {
-      "content": "<|padding|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "50254": {
-      "content": "                        ",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50255": {
-      "content": "                       ",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50256": {
-      "content": "                      ",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50257": {
-      "content": "                     ",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50258": {
-      "content": "                    ",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50259": {
-      "content": "                   ",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50260": {
-      "content": "                  ",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50261": {
-      "content": "                 ",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50262": {
-      "content": "                ",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50263": {
-      "content": "               ",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50264": {
-      "content": "              ",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50265": {
-      "content": "             ",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50266": {
-      "content": "            ",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50267": {
-      "content": "           ",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50268": {
-      "content": "          ",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50269": {
-      "content": "         ",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50270": {
-      "content": "        ",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50271": {
-      "content": "       ",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50272": {
-      "content": "      ",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50273": {
-      "content": "     ",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50274": {
-      "content": "    ",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50275": {
-      "content": "   ",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50276": {
-      "content": "  ",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50277": {
-      "content": "|||EMAIL_ADDRESS|||",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50278": {
-      "content": "|||PHONE_NUMBER|||",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50279": {
-      "content": "<|endoftext|>",
+      "content": "[PAD]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "50280": {
+    "100": {
       "content": "[UNK]",
       "lstrip": false,
       "normalized": false,
@@ -232,7 +16,7 @@
       "single_word": false,
       "special": true
     },
-    "50281": {
+    "101": {
       "content": "[CLS]",
       "lstrip": false,
       "normalized": false,
@@ -240,7 +24,7 @@
       "single_word": false,
       "special": true
     },
-    "50282": {
+    "102": {
       "content": "[SEP]",
       "lstrip": false,
       "normalized": false,
@@ -248,698 +32,34 @@
       "single_word": false,
       "special": true
     },
-    "50283": {
-      "content": "[PAD]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "50284": {
+    "103": {
       "content": "[MASK]",
-      "lstrip": true,
+      "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
-    },
-    "50285": {
-      "content": "[unused0]",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50286": {
-      "content": "[unused1]",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50287": {
-      "content": "[unused2]",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50288": {
-      "content": "[unused3]",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50289": {
-      "content": "[unused4]",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50290": {
-      "content": "[unused5]",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50291": {
-      "content": "[unused6]",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50292": {
-      "content": "[unused7]",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50293": {
-      "content": "[unused8]",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50294": {
-      "content": "[unused9]",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50295": {
-      "content": "[unused10]",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50296": {
-      "content": "[unused11]",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50297": {
-      "content": "[unused12]",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50298": {
-      "content": "[unused13]",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50299": {
-      "content": "[unused14]",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50300": {
-      "content": "[unused15]",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50301": {
-      "content": "[unused16]",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50302": {
-      "content": "[unused17]",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50303": {
-      "content": "[unused18]",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50304": {
-      "content": "[unused19]",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50305": {
-      "content": "[unused20]",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50306": {
-      "content": "[unused21]",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50307": {
-      "content": "[unused22]",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50308": {
-      "content": "[unused23]",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50309": {
-      "content": "[unused24]",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50310": {
-      "content": "[unused25]",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50311": {
-      "content": "[unused26]",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50312": {
-      "content": "[unused27]",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50313": {
-      "content": "[unused28]",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50314": {
-      "content": "[unused29]",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50315": {
-      "content": "[unused30]",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50316": {
-      "content": "[unused31]",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50317": {
-      "content": "[unused32]",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50318": {
-      "content": "[unused33]",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50319": {
-      "content": "[unused34]",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50320": {
-      "content": "[unused35]",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50321": {
-      "content": "[unused36]",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50322": {
-      "content": "[unused37]",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50323": {
-      "content": "[unused38]",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50324": {
-      "content": "[unused39]",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50325": {
-      "content": "[unused40]",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50326": {
-      "content": "[unused41]",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50327": {
-      "content": "[unused42]",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50328": {
-      "content": "[unused43]",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50329": {
-      "content": "[unused44]",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50330": {
-      "content": "[unused45]",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50331": {
-      "content": "[unused46]",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50332": {
-      "content": "[unused47]",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50333": {
-      "content": "[unused48]",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50334": {
-      "content": "[unused49]",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50335": {
-      "content": "[unused50]",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50336": {
-      "content": "[unused51]",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50337": {
-      "content": "[unused52]",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50338": {
-      "content": "[unused53]",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50339": {
-      "content": "[unused54]",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50340": {
-      "content": "[unused55]",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50341": {
-      "content": "[unused56]",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50342": {
-      "content": "[unused57]",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50343": {
-      "content": "[unused58]",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50344": {
-      "content": "[unused59]",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50345": {
-      "content": "[unused60]",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50346": {
-      "content": "[unused61]",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50347": {
-      "content": "[unused62]",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50348": {
-      "content": "[unused63]",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50349": {
-      "content": "[unused64]",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50350": {
-      "content": "[unused65]",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50351": {
-      "content": "[unused66]",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50352": {
-      "content": "[unused67]",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50353": {
-      "content": "[unused68]",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50354": {
-      "content": "[unused69]",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50355": {
-      "content": "[unused70]",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50356": {
-      "content": "[unused71]",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50357": {
-      "content": "[unused72]",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50358": {
-      "content": "[unused73]",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50359": {
-      "content": "[unused74]",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50360": {
-      "content": "[unused75]",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50361": {
-      "content": "[unused76]",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50362": {
-      "content": "[unused77]",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50363": {
-      "content": "[unused78]",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50364": {
-      "content": "[unused79]",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50365": {
-      "content": "[unused80]",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50366": {
-      "content": "[unused81]",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50367": {
-      "content": "[unused82]",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
     }
   },
-  "clean_up_tokenization_spaces": true,
+  "clean_up_tokenization_spaces": false,
   "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
   "extra_special_tokens": {},
   "mask_token": "[MASK]",
-  "model_input_names": [
-    "input_ids",
-    "attention_mask"
-  ],
-  "model_max_length": 1000000000000000019884624838656,
+  "max_length": 128,
+  "model_max_length": 256,
+  "never_split": null,
+  "pad_to_multiple_of": null,
   "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
   "sep_token": "[SEP]",
-  "tokenizer_class": "PreTrainedTokenizerFast",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "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:f9ea4e4ae0572c1ec6cf4f6b909ede35f27b9076fe79a8e80be98205658efeff
+oid sha256:d53650ecc1df174d57fefd7bfa1b3bea4c2aba0dc8f41c6447068d03a777a0e2
 size 6161

vocab.txt

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