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

@@ -6,3 +6,4 @@ epoch,steps,cosine-Accuracy@1,cosine-Accuracy@3,cosine-Accuracy@5,cosine-Precisi
 -1,-1,0.7614,0.82615,0.850775,0.7614,0.7614,0.2753833333333333,0.82615,0.170155,0.850775,0.7614,0.7960862499999959,0.8003843253968239,0.8201550154419872,0.8038332983359062
 -1,-1,0.7966,0.87425,0.900575,0.7966,0.7966,0.2914166666666666,0.87425,0.180115,0.900575,0.7966,0.8372962499999956,0.8416481150793601,0.8637140791780538,0.8444611118975183
 -1,-1,0.7467,0.81875,0.842275,0.7467,0.7467,0.27291666666666664,0.81875,0.16845500000000002,0.842275,0.7467,0.784354583333328,0.7884659325396792,0.8088581445720447,0.7917670616349511
+-1,-1,0.83665,0.91045,0.9361,0.83665,0.83665,0.3034833333333333,0.91045,0.18722000000000003,0.9361,0.83665,0.8753945833333286,0.8793089583333286,0.9000254411118587,0.8812821493075779

README.md

@@ -5,123 +5,51 @@ tags:
 - feature-extraction
 - dense
 - generated_from_trainer
-- dataset_size:713743
+- dataset_size:100000
 - loss:MultipleNegativesRankingLoss
-base_model: Alibaba-NLP/gte-modernbert-base
+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 Alibaba-NLP/gte-modernbert-base
-  results:
-  - task:
-      type: information-retrieval
-      name: Information Retrieval
-    dataset:
-      name: val
-      type: val
-    metrics:
-    - type: cosine_accuracy@1
-      value: 0.83665
-      name: Cosine Accuracy@1
-    - type: cosine_accuracy@3
-      value: 0.91045
-      name: Cosine Accuracy@3
-    - type: cosine_accuracy@5
-      value: 0.9361
-      name: Cosine Accuracy@5
-    - type: cosine_precision@1
-      value: 0.83665
-      name: Cosine Precision@1
-    - type: cosine_precision@3
-      value: 0.3034833333333333
-      name: Cosine Precision@3
-    - type: cosine_precision@5
-      value: 0.18722000000000003
-      name: Cosine Precision@5
-    - type: cosine_recall@1
-      value: 0.83665
-      name: Cosine Recall@1
-    - type: cosine_recall@3
-      value: 0.91045
-      name: Cosine Recall@3
-    - type: cosine_recall@5
-      value: 0.9361
-      name: Cosine Recall@5
-    - type: cosine_ndcg@10
-      value: 0.9000254411118587
-      name: Cosine Ndcg@10
-    - type: cosine_mrr@1
-      value: 0.83665
-      name: Cosine Mrr@1
-    - type: cosine_mrr@5
-      value: 0.8753945833333286
-      name: Cosine Mrr@5
-    - type: cosine_mrr@10
-      value: 0.8793089583333286
-      name: Cosine Mrr@10
-    - type: cosine_map@100
-      value: 0.8812821493075779
-      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 -->
@@ -137,8 +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': 'ModernBertModel'})
-  (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})
 )
 ```
 
@@ -157,23 +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, 768]
+# [3, 512]
 
 # Get the similarity scores for the embeddings
 similarities = model.similarity(embeddings, embeddings)
 print(similarities)
-# tensor([[ 1.0000,  1.0000, -0.0640],
-#         [ 1.0000,  1.0000, -0.0640],
-#         [-0.0640, -0.0640,  1.0000]])
+# tensor([[1.0000, 0.8563, 0.0594],
+#         [0.8563, 1.0000, 0.1245],
+#         [0.0594, 0.1245, 1.0000]])
 ```
 
 <!--
@@ -200,32 +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  | 0.8367  |
-| cosine_accuracy@3  | 0.9104  |
-| cosine_accuracy@5  | 0.9361  |
-| cosine_precision@1 | 0.8367  |
-| cosine_precision@3 | 0.3035  |
-| cosine_precision@5 | 0.1872  |
-| cosine_recall@1    | 0.8367  |
-| cosine_recall@3    | 0.9104  |
-| cosine_recall@5    | 0.9361  |
-| **cosine_ndcg@10** | **0.9** |
-| cosine_mrr@1       | 0.8367  |
-| cosine_mrr@5       | 0.8754  |
-| cosine_mrr@10      | 0.8793  |
-| cosine_map@100     | 0.8813  |
-
 <!--
 ## Bias, Risks and Limitations
 
@@ -244,49 +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>
-* Approximate statistics based on the first 1000 samples:
-  |         | anchor                                                                            | positive                                                                          | negative                                                                          |
-  |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
-  | type    | string                                                                            | string                                                                            | string                                                                            |
-  | details | <ul><li>min: 6 tokens</li><li>mean: 15.96 tokens</li><li>max: 53 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 15.93 tokens</li><li>max: 53 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 16.72 tokens</li><li>max: 59 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> |
-* 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                                                                          |
+  |         | sentence_0                                                                        | sentence_1                                                                        | sentence_2                                                                        |
   |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
   | type    | string                                                                            | string                                                                            | string                                                                            |
-  | details | <ul><li>min: 7 tokens</li><li>mean: 15.47 tokens</li><li>max: 70 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 15.48 tokens</li><li>max: 70 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 16.76 tokens</li><li>max: 67 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>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>            |
+  | 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,
+      "scale": 20.0,
       "similarity_fct": "cos_sim",
       "gather_across_devices": false
   }
@@ -295,49 +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`: 2e-05
-- `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-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`: 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`: 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`: 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
@@ -365,14 +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
@@ -382,23 +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
@@ -425,43 +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    | -             | 2.2389          | 0.8638             |
-| 0.0448 | 250  | 1.0018        | 0.4153          | 0.8910             |
-| 0.0897 | 500  | 0.3879        | 0.3664          | 0.8940             |
-| 0.1345 | 750  | 0.3583        | 0.3532          | 0.8937             |
-| 0.1793 | 1000 | 0.3453        | 0.3371          | 0.8962             |
-| 0.2242 | 1250 | 0.3371        | 0.3299          | 0.8956             |
-| 0.2690 | 1500 | 0.3283        | 0.3230          | 0.8967             |
-| 0.3138 | 1750 | 0.323         | 0.3185          | 0.8974             |
-| 0.3587 | 2000 | 0.3205        | 0.3139          | 0.8978             |
-| 0.4035 | 2250 | 0.315         | 0.3123          | 0.8985             |
-| 0.4484 | 2500 | 0.3132        | 0.3095          | 0.8987             |
-| 0.4932 | 2750 | 0.3082        | 0.3071          | 0.8991             |
-| 0.5380 | 3000 | 0.3065        | 0.3045          | 0.8985             |
-| 0.5829 | 3250 | 0.3041        | 0.3029          | 0.8988             |
-| 0.6277 | 3500 | 0.3046        | 0.3015          | 0.8996             |
-| 0.6725 | 3750 | 0.3023        | 0.3002          | 0.8995             |
-| 0.7174 | 4000 | 0.3017        | 0.2991          | 0.9000             |
-| 0.7622 | 4250 | 0.3001        | 0.2985          | 0.8996             |
-| 0.8070 | 4500 | 0.3006        | 0.2975          | 0.8999             |
-| 0.8519 | 4750 | 0.2983        | 0.2970          | 0.8998             |
-| 0.8967 | 5000 | 0.2991        | 0.2966          | 0.9000             |
+| 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

config.json

@@ -1,45 +1,24 @@
 {
   "architectures": [
-    "ModernBertModel"
+    "BertModel"
   ],
-  "attention_bias": false,
-  "attention_dropout": 0.0,
-  "bos_token_id": 50281,
-  "classifier_activation": "gelu",
-  "classifier_bias": false,
-  "classifier_dropout": 0.0,
-  "classifier_pooling": "mean",
-  "cls_token_id": 50281,
-  "decoder_bias": true,
-  "deterministic_flash_attn": false,
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
   "dtype": "float32",
-  "embedding_dropout": 0.0,
-  "eos_token_id": 50282,
-  "global_attn_every_n_layers": 3,
-  "global_rope_theta": 160000.0,
-  "gradient_checkpointing": false,
-  "hidden_activation": "gelu",
-  "hidden_size": 768,
-  "initializer_cutoff_factor": 2.0,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 384,
   "initializer_range": 0.02,
-  "intermediate_size": 1152,
-  "layer_norm_eps": 1e-05,
-  "local_attention": 128,
-  "local_rope_theta": 10000.0,
-  "max_position_embeddings": 8192,
-  "mlp_bias": false,
-  "mlp_dropout": 0.0,
-  "model_type": "modernbert",
-  "norm_bias": false,
-  "norm_eps": 1e-05,
+  "intermediate_size": 1536,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
   "num_attention_heads": 12,
-  "num_hidden_layers": 22,
-  "pad_token_id": 50283,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
   "position_embedding_type": "absolute",
-  "repad_logits_with_grad": false,
-  "sep_token_id": 50282,
-  "sparse_pred_ignore_index": -100,
-  "sparse_prediction": false,
   "transformers_version": "4.57.3",
-  "vocab_size": 50368
+  "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_val_results.csv

@@ -554,3 +554,24 @@ epoch,steps,cosine-Accuracy@1,cosine-Accuracy@3,cosine-Accuracy@5,cosine-Precisi
 0.8070301291248206,4500,0.836575,0.91035,0.936225,0.836575,0.836575,0.3034499999999999,0.91035,0.18724500000000002,0.936225,0.836575,0.8753933333333296,0.8792632638888849,0.8999479246388732,0.8812381232525891
 0.8518651362984218,4750,0.8364,0.910025,0.93625,0.8364,0.8364,0.3033416666666667,0.910025,0.18725000000000003,0.93625,0.8364,0.875251249999996,0.879122916666663,0.8998371123346441,0.8811114899752792
 0.896700143472023,5000,0.83665,0.91045,0.9361,0.83665,0.83665,0.3034833333333333,0.91045,0.18722000000000003,0.9361,0.83665,0.8753945833333286,0.8793089583333286,0.9000254411118587,0.8812821493075779
+0,0,0.756925,0.886,0.915975,0.756925,0.756925,0.2953333333333333,0.886,0.183195,0.915975,0.756925,0.823237499999992,0.8273541269841215,0.8566105435301875,0.8297538154910199
+0.04483500717360115,250,0.797525,0.890075,0.916275,0.797525,0.797525,0.2966916666666667,0.890075,0.18325500000000003,0.916275,0.797525,0.8455487499999935,0.8495717063492002,0.8730393801633339,0.8519482052146723
+0.0896700143472023,500,0.82065,0.899625,0.92225,0.82065,0.82065,0.299875,0.899625,0.18445000000000006,0.92225,0.82065,0.8612837499999955,0.8653779265872968,0.8864626207459981,0.8676268538103573
+0.13450502152080343,750,0.82245,0.90005,0.925075,0.82245,0.82245,0.3000166666666666,0.90005,0.18501500000000007,0.925075,0.82245,0.8630183333333307,0.8668782837301547,0.8879172543461453,0.8691401302878512
+0.1793400286944046,1000,0.824,0.90095,0.926075,0.824,0.824,0.3003166666666666,0.90095,0.18521500000000002,0.926075,0.824,0.864193333333329,0.8680340873015829,0.8890159154358417,0.8702850493416893
+0.22417503586800575,1250,0.8251,0.900975,0.92625,0.8251,0.8251,0.30032499999999995,0.900975,0.18525000000000003,0.92625,0.8251,0.8648804166666639,0.8687764880952341,0.8897092729977382,0.8709977164602416
+0.26901004304160686,1500,0.825625,0.9012,0.9268,0.825625,0.825625,0.30039999999999994,0.9012,0.18536000000000002,0.9268,0.825625,0.865259166666663,0.8691541369047578,0.8900874550807586,0.8713935357378468
+0.31384505021520803,1750,0.826125,0.9013,0.927225,0.826125,0.826125,0.3004333333333333,0.9013,0.18544500000000003,0.927225,0.826125,0.865661249999996,0.8695618253968221,0.8905357737452925,0.8717678342233259
+0.3586800573888092,2000,0.826175,0.901025,0.926975,0.826175,0.826175,0.3003416666666666,0.901025,0.18539500000000003,0.926975,0.826175,0.8655199999999963,0.8694849007936466,0.8904921468586298,0.8716916370424884
+0.4035150645624103,2250,0.8267,0.901925,0.9278,0.8267,0.8267,0.3006416666666666,0.901925,0.18556000000000003,0.9278,0.8267,0.86619708333333,0.8700837400793613,0.8910357094734063,0.8722924784004461
+0.4483500717360115,2500,0.826325,0.9016,0.9274,0.826325,0.826325,0.3005333333333333,0.9016,0.18548,0.9274,0.826325,0.8658512499999957,0.8698226884920585,0.8908745638086586,0.8720233519109022
+0.4931850789096126,2750,0.8261,0.901675,0.9275,0.8261,0.8261,0.3005583333333333,0.901675,0.1855,0.9275,0.8261,0.8657958333333294,0.869753412698409,0.8908133360196127,0.871955705362073
+0.5380200860832137,3000,0.82665,0.901875,0.927675,0.82665,0.82665,0.300625,0.901875,0.185535,0.927675,0.82665,0.8662349999999955,0.8701861805555516,0.8911847325189749,0.8723919812776054
+0.582855093256815,3250,0.826975,0.9024,0.9278,0.826975,0.826975,0.30079999999999996,0.9024,0.18556000000000003,0.9278,0.826975,0.8663795833333295,0.8703611408730112,0.8914074480899707,0.8725399895706075
+0.6276901004304161,3500,0.8276,0.903025,0.928675,0.8276,0.8276,0.3010083333333333,0.903025,0.18573500000000004,0.928675,0.8276,0.8671770833333294,0.8711155456349156,0.8921604046034279,0.8732633623176634
+0.6725251076040172,3750,0.827375,0.90265,0.928025,0.827375,0.827375,0.3008833333333333,0.90265,0.18560500000000002,0.928025,0.827375,0.8668445833333284,0.8708662202380896,0.8919061132291579,0.8730258603104377
+0.7173601147776184,4000,0.827575,0.9031,0.9284,0.827575,0.827575,0.30103333333333326,0.9031,0.18567999999999998,0.9284,0.827575,0.8670654166666621,0.8710379265872962,0.892045030666255,0.8732157548668783
+0.7621951219512195,4250,0.8276,0.90295,0.92845,0.8276,0.8276,0.3009833333333333,0.90295,0.18569000000000002,0.92845,0.8276,0.8671320833333284,0.8711172519841215,0.8921526664242764,0.8732736127760576
+0.8070301291248206,4500,0.82765,0.902975,0.928525,0.82765,0.82765,0.3009916666666666,0.902975,0.185705,0.928525,0.82765,0.8670999999999953,0.871106845238089,0.8922032735564264,0.8732435780606005
+0.8518651362984218,4750,0.827625,0.902975,0.9284,0.827625,0.827625,0.3009916666666666,0.902975,0.18568,0.9284,0.827625,0.8671220833333285,0.8711407440476129,0.8921952489654028,0.8732955747232074
+0.896700143472023,5000,0.827675,0.903,0.928425,0.827675,0.827675,0.30099999999999993,0.903,0.18568500000000004,0.928425,0.827675,0.8671804166666619,0.8711970039682481,0.8922532953454642,0.87334664003711

final_metrics.json

@@ -1,16 +1,16 @@
 {
-  "val_cosine_accuracy@1": 0.7467,
-  "val_cosine_accuracy@3": 0.81875,
-  "val_cosine_accuracy@5": 0.842275,
-  "val_cosine_precision@1": 0.7467,
-  "val_cosine_precision@3": 0.27291666666666664,
-  "val_cosine_precision@5": 0.16845500000000002,
-  "val_cosine_recall@1": 0.7467,
-  "val_cosine_recall@3": 0.81875,
-  "val_cosine_recall@5": 0.842275,
-  "val_cosine_ndcg@10": 0.8088581445720447,
-  "val_cosine_mrr@1": 0.7467,
-  "val_cosine_mrr@5": 0.784354583333328,
-  "val_cosine_mrr@10": 0.7884659325396792,
-  "val_cosine_map@100": 0.7917670616349511
+  "val_cosine_accuracy@1": 0.83665,
+  "val_cosine_accuracy@3": 0.91045,
+  "val_cosine_accuracy@5": 0.9361,
+  "val_cosine_precision@1": 0.83665,
+  "val_cosine_precision@3": 0.3034833333333333,
+  "val_cosine_precision@5": 0.18722000000000003,
+  "val_cosine_recall@1": 0.83665,
+  "val_cosine_recall@3": 0.91045,
+  "val_cosine_recall@5": 0.9361,
+  "val_cosine_ndcg@10": 0.9000254411118587,
+  "val_cosine_mrr@1": 0.83665,
+  "val_cosine_mrr@5": 0.8753945833333286,
+  "val_cosine_mrr@10": 0.8793089583333286,
+  "val_cosine_map@100": 0.8812821493075779
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:618a711cb46a993dfbbd3a4d48e58bc1574588b606af9e32ce39fe451134f747
-size 596070136
+oid sha256:325ea67b4c6fb434aa13d441e188dab3f657079050a07c5c0072112cfb0cb217
+size 133462128

special_tokens_map.json

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

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,
   "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": 512,
+  "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]"
 }