Training in progress, step 5000

Information-Retrieval_evaluation_val_results.csv

@@ -5,3 +5,4 @@ epoch,steps,cosine-Accuracy@1,cosine-Accuracy@3,cosine-Accuracy@5,cosine-Precisi
 -1,-1,0.829275,0.9051,0.9329,0.829275,0.829275,0.30169999999999997,0.9051,0.18658000000000002,0.9329,0.829275,0.8692179166666618,0.8735753373015815,0.8956869608914538,0.8756452160249361
 -1,-1,0.76415,0.822175,0.84665,0.76415,0.76415,0.2740583333333333,0.822175,0.16933,0.84665,0.76415,0.7953370833333295,0.8000376587301573,0.8195085862842543,0.8034052122492592
 -1,-1,0.802275,0.8676,0.89495,0.802275,0.802275,0.28919999999999996,0.8676,0.17899,0.89495,0.802275,0.8373504166666614,0.8418555952380918,0.8626142815266079,0.8448604581747029
+-1,-1,0.76535,0.820425,0.8436,0.76535,0.76535,0.27347499999999997,0.820425,0.16872,0.8436,0.76535,0.7948791666666619,0.798946091269839,0.8168396181783457,0.8022530766472562

README.md

@@ -5,111 +5,38 @@ tags:
 - feature-extraction
 - dense
 - generated_from_trainer
-- dataset_size:359997
+- dataset_size:100000
 - loss:MultipleNegativesRankingLoss
 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 prajjwal1/bert-small
-  results:
-  - task:
-      type: information-retrieval
-      name: Information Retrieval
-    dataset:
-      name: val
-      type: val
-    metrics:
-    - type: cosine_accuracy@1
-      value: 0.76535
-      name: Cosine Accuracy@1
-    - type: cosine_accuracy@3
-      value: 0.820425
-      name: Cosine Accuracy@3
-    - type: cosine_accuracy@5
-      value: 0.8436
-      name: Cosine Accuracy@5
-    - type: cosine_precision@1
-      value: 0.76535
-      name: Cosine Precision@1
-    - type: cosine_precision@3
-      value: 0.27347499999999997
-      name: Cosine Precision@3
-    - type: cosine_precision@5
-      value: 0.16872
-      name: Cosine Precision@5
-    - type: cosine_recall@1
-      value: 0.76535
-      name: Cosine Recall@1
-    - type: cosine_recall@3
-      value: 0.820425
-      name: Cosine Recall@3
-    - type: cosine_recall@5
-      value: 0.8436
-      name: Cosine Recall@5
-    - type: cosine_ndcg@10
-      value: 0.8168396181783457
-      name: Cosine Ndcg@10
-    - type: cosine_mrr@1
-      value: 0.76535
-      name: Cosine Mrr@1
-    - type: cosine_mrr@5
-      value: 0.7948791666666619
-      name: Cosine Mrr@5
-    - type: cosine_mrr@10
-      value: 0.798946091269839
-      name: Cosine Mrr@10
-    - type: cosine_map@100
-      value: 0.8022530766472562
-      name: Cosine Map@100
 ---
 
 # SentenceTransformer based on prajjwal1/bert-small
@@ -158,12 +85,12 @@ Then you can load this model and run inference.
 from sentence_transformers import SentenceTransformer
 
 # Download from the 🤗 Hub
-model = SentenceTransformer("redis/model-a-baseline")
+model = SentenceTransformer("sentence_transformers_model_id")
 # Run inference
 sentences = [
-    '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)
@@ -172,9 +99,9 @@ print(embeddings.shape)
 # Get the similarity scores for the embeddings
 similarities = model.similarity(embeddings, embeddings)
 print(similarities)
-# tensor([[ 1.0000,  0.9991, -0.0375],
-#         [ 0.9991,  1.0000, -0.0345],
-#         [-0.0375, -0.0345,  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  | 0.7653     |
-| cosine_accuracy@3  | 0.8204     |
-| cosine_accuracy@5  | 0.8436     |
-| cosine_precision@1 | 0.7653     |
-| cosine_precision@3 | 0.2735     |
-| cosine_precision@5 | 0.1687     |
-| cosine_recall@1    | 0.7653     |
-| cosine_recall@3    | 0.8204     |
-| cosine_recall@5    | 0.8436     |
-| **cosine_ndcg@10** | **0.8168** |
-| cosine_mrr@1       | 0.7653     |
-| cosine_mrr@5       | 0.7949     |
-| cosine_mrr@10      | 0.7989     |
-| cosine_map@100     | 0.8023     |
-
 <!--
 ## 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: 15.46 tokens</li><li>max: 49 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 15.52 tokens</li><li>max: 49 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 16.99 tokens</li><li>max: 128 tokens</li></ul> |
-* Samples:
-  | anchor                                                                          | positive                                                                                             | negative                                                                                                                 |
-  |:--------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------------------------|
-  | <code>Shall I upgrade my iPhone 5s to iOS 10 final version?</code>              | <code>Should I upgrade an iPhone 5s to iOS 10?</code>                                                | <code>Whether extension of CA-articleship is to be served at same firm/company?</code>                                   |
-  | <code>Is Donald Trump really going to be the president of United States?</code> | <code>Do you think Donald Trump could conceivably be the next President of the United States?</code> | <code>Since solid carbon dioxide is dry ice and incredibly cold, why doesn't it have an effect on global warming?</code> |
-  | <code>What are real tips to improve work life balance?</code>                   | <code>What are the best ways to create a work life balance?</code>                                   | <code>How do you open a briefcase combination lock without the combination?</code>                                       |
-* Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
-  ```json
-  {
-      "scale": 1.0,
-      "similarity_fct": "cos_sim",
-      "gather_across_devices": false
-  }
-  ```
-
-### Evaluation Dataset
-
-#### Unnamed Dataset
-
-* Size: 40,000 evaluation samples
-* Columns: <code>anchor</code>, <code>positive</code>, and <code>negative</code>
+* Size: 100,000 training samples
+* Columns: <code>sentence_0</code>, <code>sentence_1</code>, and <code>sentence_2</code>
 * Approximate statistics based on the first 1000 samples:
-  |         | anchor                                                                            | positive                                                                          | negative                                                                          |
-  |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
-  | type    | string                                                                            | string                                                                            | string                                                                            |
-  | details | <ul><li>min: 6 tokens</li><li>mean: 15.71 tokens</li><li>max: 65 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 15.79 tokens</li><li>max: 65 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 16.97 tokens</li><li>max: 78 tokens</li></ul> |
+  |         | sentence_0                                                                        | sentence_1                                                                       | sentence_2                                                                         |
+  |:--------|:----------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|
+  | type    | string                                                                            | string                                                                           | string                                                                             |
+  | details | <ul><li>min: 3 tokens</li><li>mean: 15.53 tokens</li><li>max: 59 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 15.5 tokens</li><li>max: 59 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 16.87 tokens</li><li>max: 128 tokens</li></ul> |
 * Samples:
-  | anchor                                                                                                            | positive                                                                                                          | negative                                                                                                                                  |
-  |:------------------------------------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------------------------------------------------|
-  | <code>Why were feathered dinosaur fossils only found in the last 20 years?</code>                                 | <code>Why were feathered dinosaur fossils only found in the last 20 years?</code>                                 | <code>Why are only few people aware that many dinosaurs had feathers?</code>                                                              |
-  | <code>If FOX News is the conservative news station, which cable news network is for liberals/progressives?</code> | <code>If FOX News is the conservative news station, which cable news network is for liberals/progressives?</code> | <code>How much did Fox News and conservative leaning media networks stoke the anger that contributed to Donald Trump's popularity?</code> |
-  | <code>How can guys last longer during sex?</code>                                                                 | <code>How do I last longer in sex?</code>                                                                         | <code>What is a permanent solution for rough and puffy hair?</code>                                                                       |
+  | sentence_0                                                                              | sentence_1                                                                              | sentence_2                                                             |
+  |:----------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------------|:-----------------------------------------------------------------------|
+  | <code>Is there visitor entry facility in Jaipur airport. How much is the ticket?</code> | <code>Is there visitor entry facility in Jaipur airport. How much is the ticket?</code> | <code>How much is the airport tax in bogota?</code>                    |
+  | <code>Which concept is more important: good planning or hard work?</code>               | <code>Which concept is more important: good planning or hard work?</code>               | <code>What is important in life: luck or hard work?</code>             |
+  | <code>What is the most efficient way to make money?</code>                              | <code>How can I make my money make money?</code>                                        | <code>What can one learn about Quantum Mechanics in 10 minutes?</code> |
 * Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
   ```json
   {
-      "scale": 1.0,
+      "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`: 1024
-- `per_device_eval_batch_size`: 1024
-- `learning_rate`: 2e-05
-- `weight_decay`: 0.0001
-- `max_steps`: 2000
-- `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`: 1024
-- `per_device_eval_batch_size`: 1024
+- `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`: 2000
+- `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    | -             | 7.3375          | 0.8046             |
-| 0.2849 | 100  | 7.1679        | 6.7507          | 0.8521             |
-| 0.5698 | 200  | 6.8558        | 6.6963          | 0.8296             |
-| 0.8547 | 300  | 6.7955        | 6.6900          | 0.8213             |
-| 1.1396 | 400  | 6.7751        | 6.6859          | 0.8183             |
-| 1.4245 | 500  | 6.7644        | 6.6827          | 0.8173             |
-| 1.7094 | 600  | 6.7572        | 6.6802          | 0.8170             |
-| 1.9943 | 700  | 6.7521        | 6.6785          | 0.8168             |
-| 2.2792 | 800  | 6.7472        | 6.6772          | 0.8166             |
-| 2.5641 | 900  | 6.7442        | 6.6761          | 0.8168             |
-| 2.8490 | 1000 | 6.741         | 6.6747          | 0.8172             |
-| 3.1339 | 1100 | 6.7384        | 6.6740          | 0.8171             |
-| 3.4188 | 1200 | 6.7363        | 6.6735          | 0.8169             |
-| 3.7037 | 1300 | 6.7348        | 6.6729          | 0.8169             |
-| 3.9886 | 1400 | 6.7332        | 6.6724          | 0.8170             |
-| 4.2735 | 1500 | 6.732         | 6.6720          | 0.8168             |
-| 4.5584 | 1600 | 6.7307        | 6.6719          | 0.8171             |
-| 4.8433 | 1700 | 6.7301        | 6.6715          | 0.8170             |
-| 5.1282 | 1800 | 6.7293        | 6.6712          | 0.8169             |
-| 5.4131 | 1900 | 6.7288        | 6.6711          | 0.8169             |
-| 5.6980 | 2000 | 6.7288        | 6.6711          | 0.8168             |
+| 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

@@ -1,24 +1,45 @@
 {
   "architectures": [
-    "BertModel"
+    "ModernBertModel"
   ],
-  "attention_probs_dropout_prob": 0.1,
-  "classifier_dropout": null,
+  "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,
   "dtype": "float32",
-  "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.1,
-  "hidden_size": 512,
+  "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,
   "initializer_range": 0.02,
-  "intermediate_size": 2048,
-  "layer_norm_eps": 1e-12,
-  "max_position_embeddings": 512,
-  "model_type": "bert",
-  "num_attention_heads": 8,
-  "num_hidden_layers": 4,
-  "pad_token_id": 0,
+  "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,
+  "num_attention_heads": 12,
+  "num_hidden_layers": 22,
+  "pad_token_id": 50283,
   "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",
-  "type_vocab_size": 2,
-  "use_cache": true,
-  "vocab_size": 30522
+  "vocab_size": 50368
 }

eval/Information-Retrieval_evaluation_val_results.csv

@@ -650,3 +650,66 @@ epoch,steps,cosine-Accuracy@1,cosine-Accuracy@3,cosine-Accuracy@5,cosine-Precisi
 5.128205128205128,1800,0.765475,0.8205,0.8436,0.765475,0.765475,0.2735,0.8205,0.16872,0.8436,0.765475,0.7949895833333285,0.799029236111109,0.8168726961066123,0.8023392613357988
 5.413105413105413,1900,0.7654,0.820525,0.84375,0.7654,0.7654,0.2735083333333333,0.820525,0.16875,0.84375,0.7654,0.7949549999999953,0.7989879960317439,0.8168550640005641,0.8022952787722268
 5.698005698005698,2000,0.76535,0.820425,0.8436,0.76535,0.76535,0.27347499999999997,0.820425,0.16872,0.8436,0.76535,0.7948791666666619,0.798946091269839,0.8168396181783457,0.8022530766472562
+0,0,0.832625,0.9037,0.927875,0.832625,0.832625,0.3012333333333333,0.9037,0.185575,0.927875,0.832625,0.8697074999999955,0.8736777876984081,0.893863012669616,0.8757996960238914
+0,0,0.832625,0.9037,0.927875,0.832625,0.832625,0.3012333333333333,0.9037,0.185575,0.927875,0.832625,0.8697074999999955,0.8736777876984081,0.893863012669616,0.8757996960238914
+0.03556187766714083,100,0.832925,0.90395,0.9277,0.832925,0.832925,0.3013166666666666,0.90395,0.18554,0.9277,0.832925,0.8699662499999958,0.874077916666662,0.8943333113008198,0.8761709771231264
+0.07112375533428165,200,0.83325,0.903,0.928425,0.83325,0.83325,0.30099999999999993,0.903,0.18568500000000002,0.928425,0.83325,0.870140833333328,0.8740390674603108,0.8941570421452587,0.8761671378889205
+0.10668563300142248,300,0.83165,0.9024,0.92705,0.83165,0.83165,0.30079999999999996,0.9024,0.18541000000000002,0.92705,0.83165,0.8688354166666612,0.8727133333333262,0.8928029213677173,0.8749157698545005
+0.1422475106685633,400,0.830875,0.9017,0.926225,0.830875,0.830875,0.30056666666666665,0.9017,0.18524500000000002,0.926225,0.830875,0.8681287499999957,0.8721681646825343,0.8924133030851868,0.8743539540988015
+0.17780938833570412,500,0.83135,0.9023,0.9272,0.83135,0.83135,0.3007666666666666,0.9023,0.18544000000000002,0.9272,0.83135,0.8687166666666628,0.8726778373015832,0.8929147595312202,0.8748811786899351
+0.21337126600284495,600,0.83075,0.902125,0.92765,0.83075,0.83075,0.3007083333333333,0.902125,0.18553000000000003,0.92765,0.83075,0.8684141666666617,0.8723654464285672,0.8927343444945626,0.8745976340487334
+0.24893314366998578,700,0.82985,0.90045,0.9267,0.82985,0.82985,0.30015,0.90045,0.18534000000000003,0.9267,0.82985,0.8672554166666622,0.8713160416666622,0.8918895520448211,0.8735354083360136
+0.2844950213371266,800,0.829875,0.9011,0.927,0.829875,0.829875,0.3003666666666666,0.9011,0.1854,0.927,0.829875,0.8673366666666631,0.8713351091269796,0.8918986227268613,0.8735676898307083
+0.3200568990042674,900,0.8309,0.902025,0.927825,0.8309,0.8309,0.30067499999999997,0.902025,0.18556500000000004,0.927825,0.8309,0.8685441666666635,0.8725259424603131,0.892999942707733,0.8747680598600799
+0.35561877667140823,1000,0.83085,0.9022,0.92795,0.83085,0.83085,0.3007333333333333,0.9022,0.18558999999999998,0.92795,0.83085,0.8683162499999971,0.8723555753968225,0.8929946609827079,0.8745458347710598
+0.3911806543385491,1100,0.8307,0.901675,0.92765,0.8307,0.8307,0.3005583333333333,0.901675,0.18553000000000003,0.92765,0.8307,0.8681566666666632,0.8722391468253924,0.8928941640418292,0.8744500833260017
+0.4267425320056899,1200,0.829825,0.90125,0.9275,0.829825,0.829825,0.3004166666666666,0.90125,0.1855,0.9275,0.829825,0.8675895833333296,0.8716157242063449,0.8923141757334097,0.8738566372646849
+0.4623044096728307,1300,0.82995,0.901725,0.927825,0.82995,0.82995,0.300575,0.901725,0.185565,0.927825,0.82995,0.8679533333333292,0.8719994742063455,0.8927112778349865,0.8742416065747686
+0.49786628733997157,1400,0.8296,0.90295,0.92805,0.8296,0.8296,0.3009833333333333,0.90295,0.18561000000000002,0.92805,0.8296,0.8679712499999958,0.8719978968253923,0.8927463124311938,0.8742195201642923
+0.5334281650071123,1500,0.83105,0.9024,0.928425,0.83105,0.83105,0.3008,0.9024,0.18568500000000002,0.928425,0.83105,0.868730833333329,0.8727939583333273,0.8934538469220659,0.8750062764665736
+0.5689900426742532,1600,0.829075,0.900875,0.92685,0.829075,0.829075,0.3002916666666666,0.900875,0.18537,0.92685,0.829075,0.8669449999999947,0.8711008134920585,0.891963020364319,0.8733491002689323
+0.604551920341394,1700,0.82975,0.902675,0.9284,0.82975,0.82975,0.3008916666666666,0.902675,0.18568,0.9284,0.82975,0.8681924999999951,0.8722971230158688,0.8931424256728316,0.874526282900399
+0.6401137980085349,1800,0.8306,0.903,0.928575,0.8306,0.8306,0.30099999999999993,0.903,0.18571500000000002,0.928575,0.8306,0.8687458333333284,0.8728111706349173,0.8935364897977308,0.8750531916876738
+0.6756756756756757,1900,0.830725,0.9029,0.92915,0.830725,0.830725,0.30096666666666666,0.9029,0.18583000000000005,0.92915,0.830725,0.8690216666666624,0.8730539880952334,0.8938192061570964,0.8752834446685221
+0.7112375533428165,2000,0.8303,0.9039,0.9298,0.8303,0.8303,0.3013,0.9039,0.18596000000000004,0.9298,0.8303,0.8692183333333283,0.873315158730154,0.8942898386786119,0.875475843678592
+0.7467994310099573,2100,0.82975,0.9035,0.929425,0.82975,0.82975,0.3011666666666666,0.9035,0.18588500000000005,0.929425,0.82975,0.8686962499999954,0.8727533928571384,0.8936936270466121,0.8749909719089175
+0.7823613086770982,2200,0.830325,0.903525,0.929575,0.830325,0.830325,0.30117499999999997,0.903525,0.18591500000000005,0.929575,0.830325,0.8689591666666627,0.873092916666663,0.8941095337315879,0.8752809709636676
+0.817923186344239,2300,0.829525,0.90315,0.929675,0.829525,0.829525,0.30104999999999993,0.90315,0.18593500000000002,0.929675,0.829525,0.8684033333333289,0.8724714880952346,0.893571678665366,0.8746840849142583
+0.8534850640113798,2400,0.829225,0.903825,0.929875,0.829225,0.829225,0.30127499999999996,0.903825,0.185975,0.929875,0.829225,0.8683666666666617,0.8724318055555502,0.8935847229714423,0.8746450514266271
+0.8890469416785206,2500,0.8309,0.9032,0.930475,0.8309,0.8309,0.3010666666666666,0.9032,0.18609500000000004,0.930475,0.8309,0.8693729166666624,0.8733628670634884,0.8943213269445812,0.8755665603259773
+0.9246088193456614,2600,0.830625,0.903875,0.930225,0.830625,0.830625,0.3012916666666666,0.903875,0.18604500000000002,0.930225,0.830625,0.8693083333333299,0.8733412003968207,0.8942923318132081,0.8755548146147967
+0.9601706970128022,2700,0.8316,0.9038,0.930925,0.8316,0.8316,0.3012666666666666,0.9038,0.18618500000000002,0.930925,0.8316,0.8700662499999967,0.8741053571428529,0.8950461463489657,0.8762769151988284
+0.9957325746799431,2800,0.83145,0.9038,0.930325,0.83145,0.83145,0.3012666666666666,0.9038,0.186065,0.930325,0.83145,0.869842499999996,0.8739921626984085,0.8949688246090962,0.8761549893103089
+1.031294452347084,2900,0.82985,0.90225,0.930325,0.82985,0.82985,0.3007499999999999,0.90225,0.18606500000000004,0.930325,0.82985,0.8684687499999969,0.8725344444444416,0.8937356931451748,0.8747342369421204
+1.0668563300142249,3000,0.829475,0.90225,0.92985,0.829475,0.829475,0.30075,0.90225,0.18597000000000002,0.92985,0.829475,0.8682062499999978,0.872291061507934,0.8934799761476059,0.8745063477437907
+1.1024182076813656,3100,0.829175,0.9018,0.930425,0.829175,0.829175,0.3005999999999999,0.9018,0.18608500000000003,0.930425,0.829175,0.8681274999999967,0.8721630158730126,0.8934438983308882,0.8743702134112785
+1.1379800853485065,3200,0.829875,0.902925,0.93135,0.829875,0.829875,0.30097499999999994,0.902925,0.18627000000000002,0.93135,0.829875,0.8690058333333305,0.8729861210317437,0.8941614499287278,0.8752036601464024
+1.1735419630156472,3300,0.8295,0.902525,0.9298,0.8295,0.8295,0.3008416666666666,0.902525,0.18596000000000004,0.9298,0.8295,0.8683370833333302,0.8724927876984094,0.893695141462053,0.8747170126613444
+1.209103840682788,3400,0.830025,0.903125,0.930325,0.830025,0.830025,0.3010416666666666,0.903125,0.186065,0.930325,0.830025,0.8687120833333296,0.8727945535714241,0.8939594120219082,0.8749889145998196
+1.2446657183499288,3500,0.829225,0.9031,0.931075,0.829225,0.829225,0.3010333333333333,0.9031,0.18621500000000005,0.931075,0.829225,0.8685908333333308,0.8725394345238062,0.8937560424907722,0.8747570755925975
+1.2802275960170697,3600,0.8297,0.90285,0.93115,0.8297,0.8297,0.30094999999999994,0.90285,0.18623000000000003,0.93115,0.8297,0.8688995833333305,0.8729053472222197,0.894091838383591,0.875114419750474
+1.3157894736842106,3700,0.830825,0.903325,0.93085,0.830825,0.830825,0.30110833333333326,0.903325,0.18617000000000003,0.93085,0.830825,0.86946833333333,0.8736243948412664,0.8948236888865062,0.8757964603773258
+1.3513513513513513,3800,0.830475,0.903375,0.93115,0.830475,0.830475,0.3011249999999999,0.903375,0.18623,0.93115,0.830475,0.8693324999999966,0.8734189186507912,0.8946253675585429,0.875607289307083
+1.3869132290184922,3900,0.830725,0.904325,0.9317,0.830725,0.830725,0.3014416666666666,0.904325,0.18634,0.9317,0.830725,0.8697354166666631,0.873812053571425,0.8950651983408352,0.8759590768585738
+1.422475106685633,4000,0.830075,0.9036,0.9315,0.830075,0.830075,0.3012,0.9036,0.1863,0.9315,0.830075,0.8692433333333293,0.8733086904761863,0.8946492725845665,0.8754630887584479
+0,0,0.832625,0.9037,0.927875,0.832625,0.832625,0.3012333333333333,0.9037,0.185575,0.927875,0.832625,0.8697116666666621,0.8736819543650747,0.8938662859134554,0.8758038626905582
+0.08890469416785206,250,0.832025,0.90245,0.927025,0.832025,0.832025,0.3008166666666666,0.90245,0.18540500000000001,0.927025,0.832025,0.8691454166666625,0.8731636011904708,0.8933287818830064,0.8753340507428459
+0.17780938833570412,500,0.8313,0.9025,0.928175,0.8313,0.8313,0.3008333333333333,0.9025,0.18563500000000002,0.928175,0.8313,0.8687954166666632,0.872793283730154,0.8933126327822276,0.8749867339241133
+0.26671408250355616,750,0.831325,0.90285,0.928975,0.831325,0.831325,0.30094999999999994,0.90285,0.18579500000000002,0.928975,0.831325,0.8691287499999965,0.8730648313492023,0.8936161295093737,0.8752900406738882
+0.35561877667140823,1000,0.830975,0.902925,0.928525,0.830975,0.830975,0.3009749999999999,0.902925,0.185705,0.928525,0.830975,0.8687512499999959,0.8727652380952342,0.8933548981362803,0.8750275536756009
+0.4445234708392603,1250,0.830325,0.90235,0.9285,0.830325,0.830325,0.3007833333333333,0.90235,0.18570000000000003,0.9285,0.830325,0.8683841666666611,0.8724430952380884,0.8932124129848924,0.8746787415896043
+0.5334281650071123,1500,0.830225,0.90415,0.9288,0.830225,0.830225,0.3013833333333333,0.90415,0.18576000000000004,0.9288,0.830225,0.8686012499999951,0.8727332043650744,0.8936331337170464,0.8749186222812468
+0.6223328591749644,1750,0.8306,0.903625,0.929025,0.8306,0.8306,0.3012083333333333,0.903625,0.18580500000000003,0.929025,0.8306,0.8689979166666619,0.8730833432539643,0.8938783743451566,0.8753002240025347
+0.7112375533428165,2000,0.830675,0.904575,0.930575,0.830675,0.830675,0.30152499999999993,0.904575,0.186115,0.930575,0.830675,0.8695724999999948,0.873543511904757,0.8944309414226286,0.8757572098331393
+0.8001422475106685,2250,0.8301,0.903775,0.929925,0.8301,0.8301,0.3012583333333333,0.903775,0.18598500000000007,0.929925,0.8301,0.8689666666666628,0.873080525793647,0.8941511074013463,0.8752729359535794
+0.8890469416785206,2500,0.8309,0.904575,0.9311,0.8309,0.8309,0.30152499999999993,0.904575,0.18622000000000002,0.9311,0.8309,0.8697645833333285,0.8737814384920582,0.8948209749670885,0.8759463324960738
+0.9779516358463727,2750,0.83125,0.90425,0.93085,0.83125,0.83125,0.3014166666666667,0.90425,0.18617000000000003,0.93085,0.83125,0.8699745833333292,0.8740142361111078,0.8949559350348373,0.8762157798774689
+1.0668563300142249,3000,0.829225,0.903125,0.930625,0.829225,0.829225,0.3010416666666666,0.903125,0.186125,0.930625,0.829225,0.868449166666663,0.8724306448412661,0.8936258778172876,0.8746566089604821
+1.1557610241820768,3250,0.8291,0.902925,0.930625,0.8291,0.8291,0.30097499999999994,0.902925,0.186125,0.930625,0.8291,0.868384999999997,0.872421170634917,0.8936615661185424,0.8746388042879188
+1.2446657183499288,3500,0.829025,0.90325,0.930475,0.829025,0.829025,0.3010833333333333,0.90325,0.18609500000000004,0.930475,0.829025,0.8683124999999969,0.8723796626984098,0.8936560300871732,0.8745876596558771
+1.333570412517781,3750,0.829275,0.90355,0.930525,0.829275,0.829275,0.3011833333333333,0.90355,0.18610500000000005,0.930525,0.829275,0.8684841666666634,0.872600109126981,0.8938789272266782,0.8748097941197565
+1.422475106685633,4000,0.829075,0.9032,0.930475,0.829075,0.829075,0.30106666666666665,0.9032,0.186095,0.930475,0.829075,0.8683133333333308,0.8724658432539669,0.8938266258167138,0.8746658630174021
+1.5113798008534851,4250,0.8295,0.9034,0.93085,0.8295,0.8295,0.3011333333333333,0.9034,0.18617000000000003,0.93085,0.8295,0.8686858333333305,0.8728145833333306,0.8941773667085674,0.8749931279150198
+1.600284495021337,4500,0.829675,0.903575,0.93105,0.829675,0.829675,0.3011916666666666,0.903575,0.18621000000000004,0.93105,0.829675,0.8688749999999974,0.8729643749999976,0.8942879724859643,0.8751501004333917
+1.689189189189189,4750,0.8296,0.903,0.930825,0.8296,0.8296,0.30099999999999993,0.903,0.18616500000000002,0.930825,0.8296,0.8687112499999977,0.8728164087301565,0.8941220395714696,0.8750139496369153
+1.7780938833570412,5000,0.82975,0.903025,0.9308,0.82975,0.82975,0.3010083333333333,0.903025,0.18616000000000002,0.9308,0.82975,0.8688179166666645,0.8729221527777756,0.894185079953941,0.8751251735048098

final_metrics.json

@@ -1,16 +1,16 @@
 {
-  "val_cosine_accuracy@1": 0.802275,
-  "val_cosine_accuracy@3": 0.8676,
-  "val_cosine_accuracy@5": 0.89495,
-  "val_cosine_precision@1": 0.802275,
-  "val_cosine_precision@3": 0.28919999999999996,
-  "val_cosine_precision@5": 0.17899,
-  "val_cosine_recall@1": 0.802275,
-  "val_cosine_recall@3": 0.8676,
-  "val_cosine_recall@5": 0.89495,
-  "val_cosine_ndcg@10": 0.8626142815266079,
-  "val_cosine_mrr@1": 0.802275,
-  "val_cosine_mrr@5": 0.8373504166666614,
-  "val_cosine_mrr@10": 0.8418555952380918,
-  "val_cosine_map@100": 0.8448604581747029
+  "val_cosine_accuracy@1": 0.76535,
+  "val_cosine_accuracy@3": 0.820425,
+  "val_cosine_accuracy@5": 0.8436,
+  "val_cosine_precision@1": 0.76535,
+  "val_cosine_precision@3": 0.27347499999999997,
+  "val_cosine_precision@5": 0.16872,
+  "val_cosine_recall@1": 0.76535,
+  "val_cosine_recall@3": 0.820425,
+  "val_cosine_recall@5": 0.8436,
+  "val_cosine_ndcg@10": 0.8168396181783457,
+  "val_cosine_mrr@1": 0.76535,
+  "val_cosine_mrr@5": 0.7948791666666619,
+  "val_cosine_mrr@10": 0.798946091269839,
+  "val_cosine_map@100": 0.8022530766472562
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:403224fc6d7381f09938b5b954225a07a08307e6cebf1477857ebbf1e46bd401
-size 114011616
+oid sha256:01fedc8f8dbe66cc8e84c4aa3bd6c91cf25dedc998b2ccbc68856af6e40c20db
+size 596070136

special_tokens_map.json

@@ -1,7 +1,37 @@
 {
-  "cls_token": "[CLS]",
-  "mask_token": "[MASK]",
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
-  "unk_token": "[UNK]"
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
 }

tokenizer_config.json

@@ -1,14 +1,230 @@
 {
   "added_tokens_decoder": {
     "0": {
-      "content": "[PAD]",
+      "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
     },
-    "100": {
+    "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|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50280": {
       "content": "[UNK]",
       "lstrip": false,
       "normalized": false,
@@ -16,7 +232,7 @@
       "single_word": false,
       "special": true
     },
-    "101": {
+    "50281": {
       "content": "[CLS]",
       "lstrip": false,
       "normalized": false,
@@ -24,7 +240,7 @@
       "single_word": false,
       "special": true
     },
-    "102": {
+    "50282": {
       "content": "[SEP]",
       "lstrip": false,
       "normalized": false,
@@ -32,27 +248,698 @@
       "single_word": false,
       "special": true
     },
-    "103": {
-      "content": "[MASK]",
+    "50283": {
+      "content": "[PAD]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
+    },
+    "50284": {
+      "content": "[MASK]",
+      "lstrip": true,
+      "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_max_length": 128,
-  "never_split": null,
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 1000000000000000019884624838656,
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",
-  "strip_accents": null,
-  "tokenize_chinese_chars": true,
-  "tokenizer_class": "BertTokenizer",
+  "tokenizer_class": "PreTrainedTokenizerFast",
   "unk_token": "[UNK]"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04c37ef25164a8c1c9c22021315ab198203ee1fb4254699c7311f96e42cb894d
+oid sha256:3726ece5e3c076eec5b76be95311c502c97d1d84d6588af421499557cb47e84d
 size 6161