Upload model checkpoint

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+  "word_embedding_dimension": 768,
+  "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 +1,466 @@
+---
+base_model: sentence-transformers/all-mpnet-base-v2
+datasets: []
+language: []
+library_name: sentence-transformers
+pipeline_tag: sentence-similarity
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:281362
+- loss:CachedMultipleNegativesRankingLoss
+widget:
+- source_sentence: steel lock washer 8 x 144 2 mm zinc plated split 2004 bmw 325ci
+    base convertible miscellaneous hardware page 3 auveco 17397m769 automotive
+  sentences:
+  - steel lock washer 8 x 144 2 mm zinc plated split 1993 bmw 318i base sedan miscellaneous
+    hardware page 3 auveco 17397m769 automotive
+  - generac protector rg03624ansx standby generators liquidcooled reviews ratings
+    product discontinued discontinued electric directcom 696471617450 toolsandhomeimprovement
+  - drive belt tensioner water pumpalternator 1994 bmw 325i base convertible charging
+    system battery page 6 note shock type hydraulic ina 11281717188m40 automotive
+- source_sentence: nokya hyper white front turn signal light bulbs 2010 toyota camry
+    please double check your bulbs to make sure we have the right replacement bulb
+    listed so there is arguably even an added benefit of increased safety tooplease
+    note then you almost have change corner lights too avoid ruining benefits new
+    headlights give look car also signal in style with these nokya hyper white front
+    turn signal bulbs instead ugly stock orange 1010 camry came while try be as accurate
+    possible our listings custom front definitely stand out more compared other could
+    whole assembly a set in case where are already changing headlight color nok52022pcs
+    automotive
+  sentences:
+  - datalogic accessories for readers codbc9180433 datalogic codstdp090 datalogic
+    base stationcharger ethernet datalogic bc9180433 computersandaccessories
+  - nokya hyper white front turn signal light bulbs 2010 toyota camry please double
+    check your bulbs to make sure we have the right replacement bulb listed so there
+    is arguably even an added benefit of increased safety tooplease note then you
+    almost have change corner lights too avoid ruining benefits new headlights give
+    look car also signal in style with these nokya hyper white front turn signal bulbs
+    instead ugly stock orange 1010 camry came while try be as accurate possible our
+    listings custom front definitely stand out more compared other could whole assembly
+    a set in case where are already changing headlight color nok52022pcs automotive
+  - 39400001 axor citterio wall mounted bath tub filler faucetnohtin 39034821 bathroom
+    faucet tall and handle brushed sale appliance specials and replacement parts axor
+    citterio revives the opulence of water and redefines the purity of space each
+    arch angle and line weds clarity and harmony evoking timeless classics that are
+    mysterious yet somehow familiar discover a new form of luxury with axor citterio
+    axor 232848id39400001 toolsandhomeimprovement
+- source_sentence: canon pixus 865r cartridges for ink jet printers quillcom null
+    901tgbci6bkclo officeproducts
+  sentences:
+  - smart racing products smartcamber digital camber gauge 2003 bmw 325ci base convertible
+    suspension upgrades performance page 7 pel1850070smrt automotive valving option
+    street comfort front spring 180mm 8kg rear spring 135mm 10kg front pillowball
+    pillowball w camber plates rear pillowball n1 basic w top plates no camber plates
+    valving option street sport front spring 180mm 8kg rear spring 135mm 10kg front
+    pillowball pillowball w camber plates rear pillowball basic w top plates no camber
+    plates valving option track race front spring 180mm 10kg rear spring 140mm 10kg
+    front pillowball pillowball w camber plates rear pillowball basic w top plates
+    no camber plates
+  - datalogic cable for readers cod90a051903 datalogic cod90a051330 datalogic cable
+    cab413 usb straight ibm pos mode datalogic 90a051903 computersandaccessories
+  - canon pixus 865r cartridges for ink jet printers quillcom null 901tgbci6bkclo
+    officeproducts
+- source_sentence: headlamp restoration kit sonax 2002 bmw 325i base wagon lights
+    and lenses page 7 note removes yellowing and haze of plastic headlight lenses
+    restoring likenew clarity one kit restores four headlights simple three step process
+    requires no polishing machine step one use the circular sanding pad to gently
+    remove stubborn headlight hazing step two use the abrasive polish and application
+    pad to gently remove sanding marks step three use the towelette to apply a uv
+    protective coating to maintain headlight clarity contains qty 1 75 ml polish 4
+    sanding discs 5000 grit 2 application sponges 4 polishing cloths 2 moist cloths
+    with sealant sonax 405941m941 automotive
+  sentences:
+  - headlamp restoration kit sonax 1976 bmw 30si base sedan lights and lenses page
+    2 note removes yellowing and haze of plastic headlight lenses restoring likenew
+    clarity one kit restores four headlights simple three step process requires no
+    polishing machine step one use the circular sanding pad to gently remove stubborn
+    headlight hazing step two use the abrasive polish and application pad to gently
+    remove sanding marks step three use the towelette to apply a uv protective coating
+    to maintain headlight clarity contains qty 1 75 ml polish 4 sanding discs 5000
+    grit 2 application sponges 4 polishing cloths 2 moist cloths with sealant sonax
+    405941m941 automotive
+  - philips ultinon led lighting 2122w 43mm festoon white 1 piece 1996 bmw 318i base
+    convertible lights and lenses page 3 phi2122ulwx11 automotive
+  - canon pixma mx850 cartridges for ink jet printers quillcom trust genuine canon
+    cli8bk ink cartridges to provide outstanding print quality for all your important
+    photos and documentsunlike bargain replacement inks original canon cli8bk ink
+    cartridges are designed specifically to work with canon printers for exceptional
+    reliability and performancehave full photolithography inkjet nozzle engineering
+    901cli8bk officeproducts
+- source_sentence: phone cable flat 4 wire solid silver 1000ft 26awg wire solid 1000ft
+    phone cable flat 4 wire solid silver 1000ft 26awg allows you to connect your telephones
+    faxes answering machines and most modems perfect for all your custom installation
+    projects 1000ft roll bulk phone cable flat cable silver color 4 conductor 26 awg
+    solid copper ul listed 815239013642 otherelectronics
+  sentences:
+  - phone cable flat 4 wire solid silver 1000ft 26awg wire solid 1000ft phone cable
+    flat 4 wire solid silver 1000ft 26awg allows you to connect your telephones faxes
+    answering machines and most modems perfect for all your custom installation projects
+    1000ft roll bulk phone cable flat cable silver color 4 conductor 26 awg solid
+    copper ul listed 815239013642 otherelectronics
+  - soul black gb 2013 audi a4 allroad quattro canada market body middle armrest front
+    pr6e3gb fz period 1111 gb 8k0864207jtq8 automotive
+  - flashlight streamlight stinger led 1970 bmw 1602 base coupe tools page 8 note
+    compact and extremely powerful with 3 microprocessor controlled intensity modes
+    strobe mode and the latest in power led technology 6000 series machined aircraft
+    aluminum with nonslip rubberized comfort grip with antiroll rubber ring unbreakable
+    polycarbonate lens with scratchresistant coating oring sealed c4 led technology
+    impervious to shock with a 50000 hour lifetime includes qty 2 3cell 36 volt nicd
+    subc battery rechargeable upto 1000 times 1 piggy back chargerholder 1 120v ac
+    charge cord 1 12v dc charge cord 841 inch length 162 inch major diameter 117 inch
+    body diameter light output 350 lumens on high 175 lumens on medium 85 lumens on
+    low streamlight blue 552480010m1272 toolsandhomeimprovement
+---
+
+# SentenceTransformer based on sentence-transformers/all-mpnet-base-v2
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [sentence-transformers/all-mpnet-base-v2](https://huggingface.co/sentence-transformers/all-mpnet-base-v2). It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
+
+## Model Details
+
+### Model Description
+- **Model Type:** Sentence Transformer
+- **Base model:** [sentence-transformers/all-mpnet-base-v2](https://huggingface.co/sentence-transformers/all-mpnet-base-v2) <!-- at revision 84f2bcc00d77236f9e89c8a360a00fb1139bf47d -->
+- **Maximum Sequence Length:** 384 tokens
+- **Output Dimensionality:** 768 tokens
+- **Similarity Function:** Cosine Similarity
+<!-- - **Training Dataset:** Unknown -->
+<!-- - **Language:** Unknown -->
+<!-- - **License:** Unknown -->
+
+### 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': 384, 'do_lower_case': False}) with Transformer model: MPNetModel 
+  (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
+  (2): Normalize()
+)
+```
+
+## 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("sentence_transformers_model_id")
+# Run inference
+sentences = [
+    'phone cable flat 4 wire solid silver 1000ft 26awg wire solid 1000ft phone cable flat 4 wire solid silver 1000ft 26awg allows you to connect your telephones faxes answering machines and most modems perfect for all your custom installation projects 1000ft roll bulk phone cable flat cable silver color 4 conductor 26 awg solid copper ul listed 815239013642 otherelectronics',
+    'phone cable flat 4 wire solid silver 1000ft 26awg wire solid 1000ft phone cable flat 4 wire solid silver 1000ft 26awg allows you to connect your telephones faxes answering machines and most modems perfect for all your custom installation projects 1000ft roll bulk phone cable flat cable silver color 4 conductor 26 awg solid copper ul listed 815239013642 otherelectronics',
+    'soul black gb 2013 audi a4 allroad quattro canada market body middle armrest front pr6e3gb fz period 1111 gb 8k0864207jtq8 automotive',
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 768]
+
+# 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
+
+#### Unnamed Dataset
+
+
+* Size: 281,362 training samples
+* Columns: <code>anchor</code> and <code>positive</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | anchor                                                                              | positive                                                                            |
+  |:--------|:------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|
+  | type    | string                                                                              | string                                                                              |
+  | details | <ul><li>min: 14 tokens</li><li>mean: 77.68 tokens</li><li>max: 384 tokens</li></ul> | <ul><li>min: 20 tokens</li><li>mean: 79.97 tokens</li><li>max: 384 tokens</li></ul> |
+* Samples:
+  | anchor                                                                                                                                                                                                                                                                                                                                            | positive                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                          |
+  |:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+  | <code>glue tamiya cement 40ml 12 johnn johnny herbert gb shunko models marking livery 120 scale lotus ford type 102d camel 11 tam20033 and tam20034 ref shkd310 decals markings f1 cars 90 years spotmodel derek warwick japan grand prix 1992 water slide decals assembly instructions for references tam20030 tamiya tam87003 automotive</code> | <code>glue tamiya cement 40ml shunko models marking livery 120 scale benetton ford b192 camel 19 20 michael schumacher de martin brundle gb fia formula 1 world championship 1992 water slide decals and assembly instructions for reference tam20036 ref shkd281 decals markings f1 cars 90 years spotmodel tamiya tam87003 automotive</code>                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                    |
+  | <code>hose clamp 29325 mm range 12 width spring type 1995 bmw 325i base sedan radiators page 3 mubea sc2932512m219 automotive</code>                                                                                                                                                                                                              | <code>hose clamp 29325 mm range 12 width spring type bmw 7series e65 20022008 cooling system miscellaneous page 1 mubea sc2932512m219 automotive part 07129952131boe more info 760i 200406 760li 200308 part 11151726339m395 more info 745i and 745li 200205 750i and 750li 200608 760i 200406 760li 200308 alpina b7 200708 part 16121180240m395 more info 745i and 745li 200205 750i and 750li 200608 760i 200406 760li 200308 alpina b7 200708 part 16121180240boe more info 745i and 745li 200205 750i and 750li 200608 760i 200406 760li 200308 alpina b7 200708 part 16121180242boe more info 745i and 745li 200205 750i and 750li 200608 760i 200406 760li 200308 alpina b7 200708 part 32411156956m395 more info 745i and 745li 200205 750i and 750li 200608 760i 200406 760li 200308 alpina b7 200708 part 32411156956boe more info 745i and 745li 200205 750i and 750li 200608 760i 200406 760li 200308 alpina b7 200708 part 32411712735boe more info 745i and 745li 200205 760i 200406 760li 200308 alpina b7 200708 part 32416751127m9 more info 745i and 745li 200205 750i and 750li 200608 760i 200406 760li 200308 alpina b7 200708 part 64218367179boe more info 745i and 745li 200205 750i and 750li 200608 760i 200406 760li 200308 alpina b7 200708 part 07129952102boe more info 745i and 745li 200205 750i and 750li 200608 760i 200406 760li 200308 alpina b7 200708 part 07129952123boe more info 745i and 745li 200205 750i and 750li 200608 760i 200406 760li 200308 alpina b7 200708 part 12511309471boe more info 745i and 745li 200205 750i and 750li 200608 760i 200406 760li 200308 alpina b7 200708 part 16121176918boe more info 745i and 745li 200205 750i and 750li 200608 760i 200406 760li 200308 alpina b7 200708 part 11631716970boe more info 745i and 745li 200205 750i and 750li 200608 760i 200406 760li 200308</code> |
+  | <code>serial rj45 interlocking cable codak17463008 zebra europe qlrwp4t series lithium ion fast charger codat187373 zebra serial rj45 interlocking cable zebra ak17463008 computersandaccessories</code>                                                                                                                                          | <code>zebra universal accessories other by totalbarcodecom zebra ak17463008 kit mod plug to 9pin db pc cable ak17463008 computersandaccessories</code>                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                            |
+* Loss: [<code>CachedMultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cachedmultiplenegativesrankingloss) with these parameters:
+  ```json
+  {
+      "scale": 20.0,
+      "similarity_fct": "cos_sim"
+  }
+  ```
+
+### Evaluation Dataset
+
+#### Unnamed Dataset
+
+
+* Size: 70,341 evaluation samples
+* Columns: <code>anchor</code> and <code>positive</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | anchor                                                                             | positive                                                                           |
+  |:--------|:-----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|
+  | type    | string                                                                             | string                                                                             |
+  | details | <ul><li>min: 21 tokens</li><li>mean: 83.4 tokens</li><li>max: 384 tokens</li></ul> | <ul><li>min: 19 tokens</li><li>mean: 83.0 tokens</li><li>max: 384 tokens</li></ul> |
+* Samples:
+  | anchor                                                                                                                                                                                                                                                                         | positive                                                                                                                                                                                                                                                                       |
+  |:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+  | <code>coolant antifreeze blue 1 liter 1996 bmw 318is base coupe radiators page 1 note approved for all bmw and mini engines concentrate for distilled water see part 55 7864 010 fuchs maintain fricofin 82142209769m865 automotive</code>                                     | <code>coolant antifreeze blue 1 liter 1996 bmw 318is base coupe radiators page 1 note approved for all bmw and mini engines concentrate for distilled water see part 55 7864 010 genuine bmw 82142209769m9 automotive</code>                                                   |
+  | <code>sealing compound loctite rtv 5699 gray silicone gasket maker 80 ml tube and supplies page 2 1991 bmw 318i base convertible engine rebuilding kits tools note high performance and noncorrosive designed for high torque applications loctite 37464m258 automotive</code> | <code>sealing compound loctite rtv 5699 gray silicone gasket maker 80 ml tube and supplies page 2 1991 bmw 318i base convertible engine rebuilding kits tools note high performance and noncorrosive designed for high torque applications loctite 37464m258 automotive</code> |
+  | <code>lexmark remanufactured 18c2090 14 black ink cartridge lexmark x2630 cartridges 4inkjets remanlx14 officeproducts</code>                                                                                                                                                  | <code>remanufactured lexmark inkjet cartridge 18c2090 14 black ink lexmark z2320 ink cartridges and printer supplies inkcartridges remanlx14 officeproducts</code>                                                                                                             |
+* Loss: [<code>CachedMultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cachedmultiplenegativesrankingloss) with these parameters:
+  ```json
+  {
+      "scale": 20.0,
+      "similarity_fct": "cos_sim"
+  }
+  ```
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `eval_strategy`: steps
+- `learning_rate`: 1e-05
+- `num_train_epochs`: 2
+- `warmup_ratio`: 0.1
+- `fp16`: True
+- `auto_find_batch_size`: 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`: 8
+- `per_device_eval_batch_size`: 8
+- `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`: 1e-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`: 2
+- `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`: False
+- `hub_always_push`: False
+- `gradient_checkpointing`: False
+- `gradient_checkpointing_kwargs`: None
+- `include_inputs_for_metrics`: False
+- `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`: True
+- `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
+- `eval_use_gather_object`: False
+- `batch_sampler`: no_duplicates
+- `multi_dataset_batch_sampler`: proportional
+
+</details>
+
+### Training Logs
+| Epoch  | Step  | Training Loss | loss   |
+|:------:|:-----:|:-------------:|:------:|
+| 0.1990 | 7000  | 0.0113        | 0.0031 |
+| 0.3981 | 14000 | 0.0022        | 0.0019 |
+| 0.5971 | 21000 | 0.0019        | 0.0012 |
+| 0.7961 | 28000 | 0.0017        | 0.0012 |
+| 0.9951 | 35000 | 0.0013        | 0.0011 |
+| 1.1942 | 42000 | 0.0012        | 0.0008 |
+| 1.3932 | 49000 | 0.0005        | 0.0008 |
+
+
+### Framework Versions
+- Python: 3.10.13
+- Sentence Transformers: 3.0.1
+- Transformers: 4.44.0
+- PyTorch: 2.2.1
+- Accelerate: 0.33.0
+- Datasets: 2.21.0
+- Tokenizers: 0.19.1
+
+## 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",
+}
+```
+
+#### CachedMultipleNegativesRankingLoss
+```bibtex
+@misc{gao2021scaling,
+    title={Scaling Deep Contrastive Learning Batch Size under Memory Limited Setup}, 
+    author={Luyu Gao and Yunyi Zhang and Jiawei Han and Jamie Callan},
+    year={2021},
+    eprint={2101.06983},
+    archivePrefix={arXiv},
+    primaryClass={cs.LG}
+}
+```
+
+<!--
+## 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 +1,24 @@
+{
+  "_name_or_path": "sentence-transformers/all-mpnet-base-v2",
+  "architectures": [
+    "MPNetModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "mpnet",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "relative_attention_num_buckets": 32,
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.0",
+  "vocab_size": 30527
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.0.1",
+    "transformers": "4.44.0",
+    "pytorch": "2.2.1"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": null
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f1dccd7a17ecfffe603c6bb81740ddddb65a5afb248339b56e2e32445894074
+size 437967672

modules.json

@@ -0,0 +1,20 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  },
+  {
+    "idx": 2,
+    "name": "2",
+    "path": "2_Normalize",
+    "type": "sentence_transformers.models.Normalize"
+  }
+]

mpnet_incl_no_struct_no_token_MP_embedded.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59e9d10d1b091f0c536d2e077760ba6d4c6165e0ebd6ec9c405b45375960e76c
+size 8268733

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f697239641a090ee5056f3d51612f13f7c0932a3d911667a0fb6042ec284b1db
+size 871331770

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:169ef975fad5dea24803b259f3001a8774668b530044c586388945fe852b3012
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf9fb216ceb2785819ed11bbc7a3c870cfcf3a2abf50744edfaf81ad676f3226
+size 1064

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 384,
+  "do_lower_case": false
+}

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "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

@@ -0,0 +1,72 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "104": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "30526": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "do_lower_case": true,
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "max_length": 128,
+  "model_max_length": 384,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "</s>",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "MPNetTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}

trainer_state.json

@@ -0,0 +1,138 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.3931932558073412,
+  "eval_steps": 7000,
+  "global_step": 49000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.19902760797247732,
+      "grad_norm": 0.001206448650918901,
+      "learning_rate": 9.945984363894813e-06,
+      "loss": 0.0113,
+      "step": 7000
+    },
+    {
+      "epoch": 0.19902760797247732,
+      "eval_loss": 0.003107509110122919,
+      "eval_runtime": 304.4798,
+      "eval_samples_per_second": 231.02,
+      "eval_steps_per_second": 28.879,
+      "step": 7000
+    },
+    {
+      "epoch": 0.39805521594495463,
+      "grad_norm": 0.26781165599823,
+      "learning_rate": 8.900753471180123e-06,
+      "loss": 0.0022,
+      "step": 14000
+    },
+    {
+      "epoch": 0.39805521594495463,
+      "eval_loss": 0.0018909029895439744,
+      "eval_runtime": 304.1801,
+      "eval_samples_per_second": 231.248,
+      "eval_steps_per_second": 28.907,
+      "step": 14000
+    },
+    {
+      "epoch": 0.597082823917432,
+      "grad_norm": 0.00027483125450089574,
+      "learning_rate": 7.795346486170566e-06,
+      "loss": 0.0019,
+      "step": 21000
+    },
+    {
+      "epoch": 0.597082823917432,
+      "eval_loss": 0.0012107242364436388,
+      "eval_runtime": 304.0636,
+      "eval_samples_per_second": 231.336,
+      "eval_steps_per_second": 28.918,
+      "step": 21000
+    },
+    {
+      "epoch": 0.7961104318899093,
+      "grad_norm": 0.21627014875411987,
+      "learning_rate": 6.6900974615761295e-06,
+      "loss": 0.0017,
+      "step": 28000
+    },
+    {
+      "epoch": 0.7961104318899093,
+      "eval_loss": 0.001225769054144621,
+      "eval_runtime": 304.172,
+      "eval_samples_per_second": 231.254,
+      "eval_steps_per_second": 28.908,
+      "step": 28000
+    },
+    {
+      "epoch": 0.9951380398623866,
+      "grad_norm": 0.003856346942484379,
+      "learning_rate": 5.584690476566573e-06,
+      "loss": 0.0013,
+      "step": 35000
+    },
+    {
+      "epoch": 0.9951380398623866,
+      "eval_loss": 0.0011495049111545086,
+      "eval_runtime": 304.9212,
+      "eval_samples_per_second": 230.686,
+      "eval_steps_per_second": 28.837,
+      "step": 35000
+    },
+    {
+      "epoch": 1.194165647834864,
+      "grad_norm": 0.00557931000366807,
+      "learning_rate": 4.479283491557016e-06,
+      "loss": 0.0012,
+      "step": 42000
+    },
+    {
+      "epoch": 1.194165647834864,
+      "eval_loss": 0.0007833261624909937,
+      "eval_runtime": 304.4978,
+      "eval_samples_per_second": 231.007,
+      "eval_steps_per_second": 28.877,
+      "step": 42000
+    },
+    {
+      "epoch": 1.3931932558073412,
+      "grad_norm": 0.0003088970552198589,
+      "learning_rate": 3.374192427377699e-06,
+      "loss": 0.0005,
+      "step": 49000
+    },
+    {
+      "epoch": 1.3931932558073412,
+      "eval_loss": 0.0007826934452168643,
+      "eval_runtime": 305.4918,
+      "eval_samples_per_second": 230.255,
+      "eval_steps_per_second": 28.783,
+      "step": 49000
+    }
+  ],
+  "logging_steps": 7000,
+  "max_steps": 70342,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 7000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45dbf1a267df37822a08c7ca8ab904b06a6a28e4cea29ecda4d798055c2b695f
+size 5368

training_checkpoint-49000_matching_scores.txt

@@ -0,0 +1,6 @@
+Matching Scores:
+Optimal Cosine Similarity Threshold: 0.35000000000000003
+F1 Score: 0.7659574468085106
+Precision: 0.6233766233766234
+Recall: 0.993103448275862
+Accuracy: 0.6351575456053068