Add new SentenceTransformer model

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+  "word_embedding_dimension": 128,
+  "pooling_mode_cls_token": false,
+  "pooling_mode_mean_tokens": true,
+  "pooling_mode_max_tokens": false,
+  "pooling_mode_mean_sqrt_len_tokens": false,
+  "pooling_mode_weightedmean_tokens": false,
+  "pooling_mode_lasttoken": false,
+  "include_prompt": true
+}

README.md

@@ -0,0 +1,472 @@
+---
+language:
+- en
+license: apache-2.0
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:8959
+- loss:CoSENTLoss
+base_model: prajjwal1/bert-tiny
+widget:
+- source_sentence: 'When this card is Normal Summoned: You can Special Summon 1 "Crashbug
+    X" from your Deck. You must control a face-up "Crashbug Z" to activate and to
+    resolve this effect.'
+  sentences:
+  - You can remove from play 1 Tuner monster in your GY to Special Summon this card
+    from your hand.
+  - This spirit emerges from the mystic lamp and obeys the wishes of its summoner.
+  - 'When your opponent activates a monster effect, while you control a "Beetrooper"
+    monster: Negate the activation, and if you do, destroy it. During your End Phase,
+    if this card is in your GY and you control an Insect monster with 3000 or more
+    ATK: You can banish 1 Insect monster from your GY; Set this card. You can only
+    use 1 "Beetrooper Fly & Sting" effect per turn, and only once that turn.'
+- source_sentence: Each time a Spell Card is activated, place 1 Spell Counter on this
+    card when that Spell Card resolves. This card's Level is increased by the number
+    of Spell Counters on this card. You can remove 3 Spell Counters from this card,
+    then target 1 Quick-Play Spell Card in your GY; Set that card to your Spell &
+    Trap Zone. You can only use this effect of "Magical Something" once per turn.
+  sentences:
+  - Activate only while "Umi" is on the field. As long as "Umi" remains face-up on
+    the field, you take no damage from attacking monsters. When "Umi" is removed from
+    the field, destroy this card.
+  - Shuffle 1 "Duoterion", 1 "Hydrogeddon", and 1 "Oxygeddon" from your hand and/or
+    GY into the Deck; Special Summon 1 "Water Dragon Cluster" from your hand or GY.
+    You can banish this card from your GY; add 1 "Water Dragon" or "Water Dragon Cluster"
+    from your Deck or GY to your hand.
+  - You can Special Summon this card (from your hand) by Tributing 1 WATER monster.
+- source_sentence: You can only activate this card when there are "Don Zaloog", "Cliff
+    the Trap Remover", "Dark Scorpion - Chick the Yellow", "Dark Scorpion - Gorg the
+    Strong", and "Dark Scorpion - Meanae the Thorn" face-up on your side of the field.
+    During this turn, any of these 5 cards can attack your opponent's Life Points
+    directly. In that case, the Battle Damage inflicted to your opponent by each of
+    those cards becomes 400 points.
+  sentences:
+  - "During either turn, except the End Phase (Quick Effect): You can discard this\
+    \ card; apply this effect this turn. You can only use this effect of \"Ghost Sister\
+    \ & Spooky Dogwood\" once per turn.\r\n● Each time your opponent Special Summons\
+    \ an Effect Monster(s) during the Main Phase or Battle Phase, you gain LP equal\
+    \ to that monster's ATK. If you did not gain LP by this effect, your LP are halved\
+    \ during the End Phase."
+  - A WIND monster equipped with this card increases its ATK by 400 and decreases
+    its DEF by 200.
+  - During your Standby Phase, inflict 300 points of damage to your opponent's Life
+    Points for each monster on your opponent's side of the field.
+- source_sentence: When this card is destroyed by battle and sent to the GY, send
+    1 Fish-type monster from your Deck to the GY. Then, you can Special Summon 1 "Nimble
+    Sunfish" from your Deck.
+  sentences:
+  - You can Special Summon this card (from your hand) to your Main Monster Zone, adjacent
+    to a "Scareclaw" monster you control or in its column. You can only Special Summon
+    "Scareclaw Belone" once per turn this way. If your "Scareclaw" monster in the
+    Extra Monster Zone attacks a Defense Position monster, inflict piercing battle
+    damage to your opponent.
+  - "2 monsters, including a Level/Rank/Link 2 monster\r\nCannot be used as Link Material\
+    \ the turn it is Link Summoned. Your opponent cannot target monsters this card\
+    \ points to with card effects. During the Main Phase (Quick Effect): You can target\
+    \ 1 Level 2 monster in your GY, or, if your opponent controls a monster, you can\
+    \ target 1 Rank/Link 2 monster instead; Special Summon it. You can only use this\
+    \ effect of \"Spright Elf\" once per turn."
+  - 'If this card is Normal/Special Summoned, or flipped face-up: You can target up
+    to 2 face-up monsters on the field; change them to face-down Defense Position,
+    and if you do, any opponent''s monsters that were flipped by this effect cannot
+    change their battle positions. If a monster on the field is flipped face-up, while
+    this monster is face-up on the field (except during the Damage Step): You can
+    target 1 card your opponent controls; destroy it. You can only use each effect
+    of "Jioh the Gravity Ninja" once per turn.'
+- source_sentence: 'If you control 3 or more face-up "Six Samurai" monsters, you can
+    activate 1 of these effects: Destroy all face-up monsters your opponent controls.
+    Destroy all face-up Spell/Trap Cards your opponent controls. Destroy all Set Spell/Trap
+    Cards your opponent controls.'
+  sentences:
+  - Target 1 Link Monster you control and 1 monster your opponent controls; destroy
+    them, then draw 1 card. You can only activate 1 "Link Burst" per turn.
+  - 'Cannot be Normal Summoned/Set. Must first be Special Summoned (from your hand)
+    by Tributing 1 Level 1 "Flower Cardian" monster, except "Flower Cardian Pine with
+    Crane". If this card is Special Summoned: Draw 1 card, and if you do, show it,
+    then you can Special Summon it if it is a "Flower Cardian" monster. Otherwise,
+    send it to the GY. At the end of the Battle Phase, if this card battled: Draw
+    1 card.'
+  - While you have 2 or less cards in your hand, all face-up "Fabled" monsters you
+    control gain 400 ATK.
+datasets:
+- Tien09/pair_similarity
+pipeline_tag: sentence-similarity
+library_name: sentence-transformers
+---
+
+# MPNet base trained on AllNLI triplets
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [prajjwal1/bert-tiny](https://huggingface.co/prajjwal1/bert-tiny) on the [pair_similarity](https://huggingface.co/datasets/Tien09/pair_similarity) dataset. It maps sentences & paragraphs to a 128-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:** [prajjwal1/bert-tiny](https://huggingface.co/prajjwal1/bert-tiny) <!-- at revision 6f75de8b60a9f8a2fdf7b69cbd86d9e64bcb3837 -->
+- **Maximum Sequence Length:** 512 tokens
+- **Output Dimensionality:** 128 dimensions
+- **Similarity Function:** Cosine Similarity
+- **Training Dataset:**
+    - [pair_similarity](https://huggingface.co/datasets/Tien09/pair_similarity)
+- **Language:** en
+- **License:** apache-2.0
+
+### Model Sources
+
+- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
+- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
+- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
+
+### Full Model Architecture
+
+```
+SentenceTransformer(
+  (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel 
+  (1): Pooling({'word_embedding_dimension': 128, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
+)
+```
+
+## Usage
+
+### Direct Usage (Sentence Transformers)
+
+First install the Sentence Transformers library:
+
+```bash
+pip install -U sentence-transformers
+```
+
+Then you can load this model and run inference.
+```python
+from sentence_transformers import SentenceTransformer
+
+# Download from the 🤗 Hub
+model = SentenceTransformer("Tien09/tiny_bert_ft_sim_score")
+# Run inference
+sentences = [
+    'If you control 3 or more face-up "Six Samurai" monsters, you can activate 1 of these effects: Destroy all face-up monsters your opponent controls. Destroy all face-up Spell/Trap Cards your opponent controls. Destroy all Set Spell/Trap Cards your opponent controls.',
+    'Target 1 Link Monster you control and 1 monster your opponent controls; destroy them, then draw 1 card. You can only activate 1 "Link Burst" per turn.',
+    'While you have 2 or less cards in your hand, all face-up "Fabled" monsters you control gain 400 ATK.',
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 128]
+
+# Get the similarity scores for the embeddings
+similarities = model.similarity(embeddings, embeddings)
+print(similarities.shape)
+# [3, 3]
+```
+
+<!--
+### Direct Usage (Transformers)
+
+<details><summary>Click to see the direct usage in Transformers</summary>
+
+</details>
+-->
+
+<!--
+### Downstream Usage (Sentence Transformers)
+
+You can finetune this model on your own dataset.
+
+<details><summary>Click to expand</summary>
+
+</details>
+-->
+
+<!--
+### Out-of-Scope Use
+
+*List how the model may foreseeably be misused and address what users ought not to do with the model.*
+-->
+
+<!--
+## Bias, Risks and Limitations
+
+*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
+-->
+
+<!--
+### Recommendations
+
+*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
+-->
+
+## Training Details
+
+### Training Dataset
+
+#### pair_similarity
+
+* Dataset: [pair_similarity](https://huggingface.co/datasets/Tien09/pair_similarity) at [a933de4](https://huggingface.co/datasets/Tien09/pair_similarity/tree/a933de4485aee2deeb50b77b0b27e4654094d56f)
+* Size: 8,959 training samples
+* Columns: <code>effect_text</code>, <code>score</code>, and <code>effect_text2</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | effect_text                                                                        | score                                                          | effect_text2                                                                      |
+  |:--------|:-----------------------------------------------------------------------------------|:---------------------------------------------------------------|:----------------------------------------------------------------------------------|
+  | type    | string                                                                             | float                                                          | string                                                                            |
+  | details | <ul><li>min: 6 tokens</li><li>mean: 72.39 tokens</li><li>max: 191 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 0.09</li><li>max: 1.0</li></ul> | <ul><li>min: 8 tokens</li><li>mean: 72.1 tokens</li><li>max: 198 tokens</li></ul> |
+* Samples:
+  | effect_text                                                                                                                                                                                                                                                                                                                                                                                                                                                                                   | score            | effect_text2                                                                                                                                                                                                                                                                                                                                                                                                                                                                                 |
+  |:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-----------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+  | <code>Once per turn, if you Special Summon a DARK Synchro Monster(s) from the Extra Deck: You can target 1 of your "Blackwing" monsters, or "Black-Winged Dragon", with lower ATK that is banished or in your GY; Special Summon it. Once per turn, if a DARK monster(s) you control would be destroyed by battle or card effect, you can remove 1 Black Feather Counter from your field instead.</code>                                                                                      | <code>0.0</code> | <code>A Millennium item, it's rumored to block any strong attack.</code>                                                                                                                                                                                                                                                                                                                                                                                                                     |
+  | <code>Target 1 face-up monster your opponent controls; the ATK of all other monsters currently on the field become equal to that monster's ATK, until the end of this turn.</code>                                                                                                                                                                                                                                                                                                            | <code>0.0</code> | <code>While you control a "Blue-Eyes" monster, you choose the attack targets for your opponent's attacks. You can only use each of the following effects of "Dictator of D." once per turn. You can send 1 "Blue-Eyes White Dragon" from your hand or Deck to the GY; Special Summon this card from your hand. You can discard 1 "Blue-Eyes White Dragon", or 1 card that mentions it, then target 1 "Blue-Eyes" monster in your GY; Special Summon it.</code>                               |
+  | <code>1 Tuner + 1+ non-Tuner monsters
  <br>If this card is Synchro Summoned using a Tuner Synchro Monster: You can target 1 Spell/Trap in your GY; add it to your hand. When your opponent activates a card or effect (Quick Effect): You can send 1 Spell/Trap from your hand or field to the GY; Special Summon 1 Level 7 or lower Tuner Synchro Monster from your Extra Deck, GY, or banishment. You can only use each effect of "Diabell, Queen of the White Forest" once per turn.</code> | <code>0.2</code> | <code>1 Aqua monster + 1 Level 10 WATER monster<br>Must first be either Fusion Summoned, or Special Summoned (from your Extra Deck) by Tributing 1 Level 10 Aqua monster with 0 ATK. This card can be treated as 3 Tributes for the Tribute Summon of a monster. Cannot be destroyed by battle. Your opponent cannot target monsters you control with card effects, except "Egyptian God Slime", also their monsters cannot target monsters for attacks, except "Egyptian God Slime".</code> |
+* Loss: [<code>CoSENTLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosentloss) with these parameters:
+  ```json
+  {
+      "scale": 20.0,
+      "similarity_fct": "pairwise_cos_sim"
+  }
+  ```
+
+### Evaluation Dataset
+
+#### pair_similarity
+
+* Dataset: [pair_similarity](https://huggingface.co/datasets/Tien09/pair_similarity) at [a933de4](https://huggingface.co/datasets/Tien09/pair_similarity/tree/a933de4485aee2deeb50b77b0b27e4654094d56f)
+* Size: 1,920 evaluation samples
+* Columns: <code>effect_text</code>, <code>score</code>, and <code>effect_text2</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | effect_text                                                                         | score                                                          | effect_text2                                                                       |
+  |:--------|:------------------------------------------------------------------------------------|:---------------------------------------------------------------|:-----------------------------------------------------------------------------------|
+  | type    | string                                                                              | float                                                          | string                                                                             |
+  | details | <ul><li>min: 10 tokens</li><li>mean: 72.56 tokens</li><li>max: 202 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 0.09</li><li>max: 1.0</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 71.33 tokens</li><li>max: 186 tokens</li></ul> |
+* Samples:
+  | effect_text                                                                                                                                                                                                                                                                                                                                                                                             | score             | effect_text2                                                                                                                                                                                                                                                                                                                                                                                                                                      |
+  |:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:------------------|:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+  | <code>A proud ruler of the jungle that some fear and others respect.</code>                                                                                                                                                                                                                                                                                                                             | <code>0.0</code>  | <code>Cannot attack the turn it is Normal Summoned. Once per turn: You can target 1 face-up monster on the field; change this card to Defense Position, and if you do, that target loses 800 ATK until the end of this turn.</code>                                                                                                                                                                                                               |
+  | <code>During your opponent's Main Phase or Battle Phase: You can Special Summon 1 non-Tuner monster from your hand, but it has its effects negated (if any), and if you do, immediately after this effect resolves, Synchro Summon 1 Machine-Type Synchro Monster using only that monster and this card (this is a Quick Effect). You can only use this effect of "Crystron Quan" once per turn.</code> | <code>0.0</code>  | <code>You can Tribute this card while "Neo Space" is on the field to Special Summon 1 "Neo-Spacian Dark Panther" from your hand or Deck.</code>                                                                                                                                                                                                                                                                                                   |
+  | <code>When your opponent Special Summons a monster(s): Destroy it, then you can banish 5 Zombie monsters from your GY, and if you do, Special Summon 1 Level 7 or higher Zombie monster from your hand or Deck.</code>                                                                                                                                                                                  | <code>0.25</code> | <code>You can target 1 Dragon monster you control; it gains ATK/DEF equal to the total Link Rating of the Link Monsters currently on the field x 100, until the end of the opponent's turn. You can only use this effect of "Guardragon Shield" once per turn. Once per turn, if exactly 1 Dragon monster you control would be destroyed by battle or card effect, you can send 1 Normal Monster from your hand or Deck to the GY instead.</code> |
+* Loss: [<code>CoSENTLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosentloss) with these parameters:
+  ```json
+  {
+      "scale": 20.0,
+      "similarity_fct": "pairwise_cos_sim"
+  }
+  ```
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `eval_strategy`: steps
+- `per_device_train_batch_size`: 16
+- `per_device_eval_batch_size`: 16
+- `num_train_epochs`: 5
+- `warmup_ratio`: 0.1
+- `fp16`: True
+- `batch_sampler`: no_duplicates
+
+#### All Hyperparameters
+<details><summary>Click to expand</summary>
+
+- `overwrite_output_dir`: False
+- `do_predict`: False
+- `eval_strategy`: steps
+- `prediction_loss_only`: True
+- `per_device_train_batch_size`: 16
+- `per_device_eval_batch_size`: 16
+- `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`: 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`: 5
+- `max_steps`: -1
+- `lr_scheduler_type`: linear
+- `lr_scheduler_kwargs`: {}
+- `warmup_ratio`: 0.1
+- `warmup_steps`: 0
+- `log_level`: passive
+- `log_level_replica`: warning
+- `log_on_each_node`: True
+- `logging_nan_inf_filter`: True
+- `save_safetensors`: True
+- `save_on_each_node`: False
+- `save_only_model`: False
+- `restore_callback_states_from_checkpoint`: False
+- `no_cuda`: False
+- `use_cpu`: False
+- `use_mps_device`: False
+- `seed`: 42
+- `data_seed`: None
+- `jit_mode_eval`: False
+- `use_ipex`: False
+- `bf16`: False
+- `fp16`: True
+- `fp16_opt_level`: O1
+- `half_precision_backend`: auto
+- `bf16_full_eval`: False
+- `fp16_full_eval`: False
+- `tf32`: None
+- `local_rank`: 0
+- `ddp_backend`: None
+- `tpu_num_cores`: None
+- `tpu_metrics_debug`: False
+- `debug`: []
+- `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`: False
+- `ignore_data_skip`: False
+- `fsdp`: []
+- `fsdp_min_num_params`: 0
+- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
+- `fsdp_transformer_layer_cls_to_wrap`: None
+- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
+- `deepspeed`: None
+- `label_smoothing_factor`: 0.0
+- `optim`: adamw_torch
+- `optim_args`: None
+- `adafactor`: False
+- `group_by_length`: False
+- `length_column_name`: length
+- `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`: False
+- `resume_from_checkpoint`: None
+- `hub_model_id`: None
+- `hub_strategy`: every_save
+- `hub_private_repo`: None
+- `hub_always_push`: False
+- `gradient_checkpointing`: False
+- `gradient_checkpointing_kwargs`: None
+- `include_inputs_for_metrics`: False
+- `include_for_metrics`: []
+- `eval_do_concat_batches`: True
+- `fp16_backend`: auto
+- `push_to_hub_model_id`: None
+- `push_to_hub_organization`: None
+- `mp_parameters`: 
+- `auto_find_batch_size`: False
+- `full_determinism`: False
+- `torchdynamo`: None
+- `ray_scope`: last
+- `ddp_timeout`: 1800
+- `torch_compile`: False
+- `torch_compile_backend`: None
+- `torch_compile_mode`: None
+- `dispatch_batches`: None
+- `split_batches`: None
+- `include_tokens_per_second`: False
+- `include_num_input_tokens_seen`: False
+- `neftune_noise_alpha`: None
+- `optim_target_modules`: None
+- `batch_eval_metrics`: False
+- `eval_on_start`: False
+- `use_liger_kernel`: False
+- `eval_use_gather_object`: False
+- `average_tokens_across_devices`: False
+- `prompts`: None
+- `batch_sampler`: no_duplicates
+- `multi_dataset_batch_sampler`: proportional
+
+</details>
+
+### Training Logs
+| Epoch  | Step | Training Loss | Validation Loss |
+|:------:|:----:|:-------------:|:---------------:|
+| 0.1786 | 100  | 3.8917        | 3.7898          |
+| 0.3571 | 200  | 3.7289        | 3.7576          |
+| 0.5357 | 300  | 3.6719        | 3.7211          |
+| 0.7143 | 400  | 3.6294        | 3.6751          |
+| 0.8929 | 500  | 3.5188        | 3.6291          |
+| 1.0714 | 600  | 3.6794        | 3.5768          |
+| 1.25   | 700  | 3.4962        | 3.5798          |
+| 1.4286 | 800  | 3.4325        | 3.6149          |
+| 1.6071 | 900  | 3.3956        | 3.6151          |
+| 1.7857 | 1000 | 3.2907        | 3.7533          |
+| 1.9643 | 1100 | 3.3685        | 3.5106          |
+| 2.1429 | 1200 | 3.502         | 3.4844          |
+| 2.3214 | 1300 | 3.3796        | 3.6363          |
+| 2.5    | 1400 | 3.2383        | 3.5744          |
+| 2.6786 | 1500 | 3.1346        | 3.6568          |
+| 2.8571 | 1600 | 3.1808        | 3.6278          |
+| 3.0357 | 1700 | 3.3241        | 3.4786          |
+| 3.2143 | 1800 | 3.2864        | 3.4705          |
+| 3.3929 | 1900 | 3.2056        | 3.5290          |
+| 3.5714 | 2000 | 3.1519        | 3.6228          |
+| 3.75   | 2100 | 3.0889        | 3.5919          |
+| 3.9286 | 2200 | 2.9385        | 3.6148          |
+| 4.1071 | 2300 | 3.2051        | 3.5180          |
+| 4.2857 | 2400 | 3.2581        | 3.5216          |
+| 4.4643 | 2500 | 3.0765        | 3.5968          |
+| 4.6429 | 2600 | 2.9497        | 3.6496          |
+| 4.8214 | 2700 | 2.8502        | 3.6804          |
+| 5.0    | 2800 | 3.1919        | 3.6668          |
+
+
+### Framework Versions
+- Python: 3.10.12
+- Sentence Transformers: 3.3.1
+- Transformers: 4.47.1
+- PyTorch: 2.5.1+cu121
+- Accelerate: 1.2.1
+- Datasets: 3.2.0
+- Tokenizers: 0.21.0
+
+## Citation
+
+### BibTeX
+
+#### Sentence Transformers
+```bibtex
+@inproceedings{reimers-2019-sentence-bert,
+    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
+    author = "Reimers, Nils and Gurevych, Iryna",
+    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
+    month = "11",
+    year = "2019",
+    publisher = "Association for Computational Linguistics",
+    url = "https://arxiv.org/abs/1908.10084",
+}
+```
+
+#### CoSENTLoss
+```bibtex
+@online{kexuefm-8847,
+    title={CoSENT: A more efficient sentence vector scheme than Sentence-BERT},
+    author={Su Jianlin},
+    year={2022},
+    month={Jan},
+    url={https://kexue.fm/archives/8847},
+}
+```
+
+<!--
+## Glossary
+
+*Clearly define terms in order to be accessible across audiences.*
+-->
+
+<!--
+## Model Card Authors
+
+*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
+-->
+
+<!--
+## Model Card Contact
+
+*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
+-->

config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "prajjwal1/bert-tiny",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 128,
+  "initializer_range": 0.02,
+  "intermediate_size": 512,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 2,
+  "num_hidden_layers": 2,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.47.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.3.1",
+    "transformers": "4.47.1",
+    "pytorch": "2.5.1+cu121"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7524d25984f13d0abb20cfb4a54654649c8a941371d3bfbd57a2f81feedac362
+size 17547912

modules.json

@@ -0,0 +1,14 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  }
+]

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 512,
+  "do_lower_case": false
+}

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "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": 1000000000000000019884624838656,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}