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 +1,451 @@
+---
+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:281342
+- loss:CachedMultipleNegativesRankingLoss
+widget:
+- source_sentence: ez buy federal 556 nato xm855 62 grain green tip fmj us bulk 223
+    ammo for sale cheap bulk ammunition in fmj and jhp depotus american eagle 223556
+    fmj rebate 400 maximum per household case upcs accepted for mailin us identifiers
+    is xm855lpc120rebate30 category of toolsandhomeimprovement
+  sentences:
+  - ez buy federal 556 nato xm855 62 grain green tip fmj us bulk 223 ammo for sale
+    cheap bulk ammunition in fmj and jhp depotus american eagle 223556 fmj rebate
+    400 maximum per household case upcs accepted for mailin us identifiers is xm855lpc120rebate30
+    category of toolsandhomeimprovement
+  - 3m cable for dlink 10gbe cx4 module demcb300cx 3m module dlink list retailers
+    identifiers is demcb300cx category of otherelectronics
+  - seat frame wiring harnessd 02082010 gb 2013 volkswagen golf china market electrics
+    harness 4doorright gb identifiers is 1k4971369f category of automotive
+- source_sentence: epson t33xl photo black inkjet cartridge ink colours photo black
+    identifiers is 8715946600598 category of officeproducts key specifications are
+    attributes ink colours photo black volume 81ml newremanufactured new single or
+    multi colour cartridge compatibility compatible brand epson printers expression
+    premium xp530xp630xp635xp830 originalcompatible original manufacturer general
+    number t33614010 c13t33614012 model name 33xl physical form factor pack quantity
+    1 pieces recycling information can i recycle it click here for details on how
+    to recycle
+  sentences:
+  - rear child seat support bolt 516x35 belts upholstery page 1 1994 bmw 325i base
+    sedan seats produced by genuine bmw identifiers is 72111922499boe category of
+    automotive
+  - epson claria 33xl ink cartridge photo black inkjet 400 page 1 blister pack c13t33614010
+    novatech inkjet 400 page 1 blister pack produced by epson identifiers is eps101979
+    category of officeproducts
+  - maglite xenon replacement lamps for 2cell aa flashlights 2packus the maglite xenon
+    replacement lamps for 2cell aa flashlights 2pack help keep your mini shining mini
+    not included are highintensity bulbs and come in a package of 2 convenience us
+    produced by maglite us identifiers is 100045339 category of toolsandhomeimprovement
+- source_sentence: control arm front right lower 1993 bmw 325i base sedan suspension
+    shocks springs page 8 produced by genuine bmw identifiers is 31122339996boe category
+    of automotive
+  sentences:
+  - vehicle jump starter jumpncarry 660 note 1700 peak amps 425 cranking clore proformer
+    battery technology 46 2 awg welding cable leads industrialgrade clamps builtin
+    charger automatic charging voltmeter provides charge status of onboard battery
+    12v dc outlet to power accessories 1991 bmw 325i base sedan charging system page
+    2 note 1700 peak amps 425 cranking clore proformer battery technology 46 2 awg
+    welding cable leads industrialgrade clamps builtin charger automatic charging
+    voltmeter provides charge status of onboard battery 12v dc outlet to power accessories
+    produced by null identifiers is jnc660m1313 category of automotive
+  - hose clamp 1628 mm range 9 width screw type 1997 bmw 318is base coupe radiators
+    page 2 produced by norma identifiers is 64218367179m249 category of automotive
+  - control arm front right lower 1998 bmw 318ti base hatchback suspension shocks
+    springs page 6 produced by delphi identifiers is 31122339996m292 category of automotive
+- source_sentence: sunvisor support bracket interior right sideus chevy parts sunvisor
+    interior this is the interior sunvisor support bracket for right side with screws
+    and a template passenger sideus identifiers is 986155r4753 category of automotive
+  sentences:
+  - chevrolet sunvisor support bracket interior right sideus chevy parts interior
+    sunvisors chevs of the 40sus this is the interior sunvisor support bracket for
+    right side with screws and a template passenger side 1947 1948 1949 1950 1951
+    1952 1953 chevrolet trucks us identifiers is 986155r4753 category of automotive
+  - abbey round 30 wall mirror in frameless 791888045671 guildhall 8quote 1 light
+    sconce dutch goldantique sale home lighting fixtures lamps more online this stylish
+    silver wall mirror will introduce a modern feel to any room its sleek design makes
+    the versatile and distinct in frameless produced by cooper classics identifiers
+    is 4567upc791888045671 category of toolsandhomeimprovement
+  - 10700 series return shell 30w x 20d 2912h henna cherry hon107270xjj home office
+    desks page 601 furniture town 10700 series return shell 30w x 20d 29 12h henna
+    cherry produced by mydirectadvantage identifiers is hon107270xjj107270xjj category
+    of officeproducts
+- source_sentence: paint sealant sonax profiline polymer net shield 75 ml aerosol
+    can 1994 bmw 318is base coupe miscellaneous page 24 note innovative surface protection
+    based on hybrid polymers protects the paintwork by means of a resistant network
+    made from organic and inorganic components can be applied quickly easily intensively
+    freshens up paint color produces silky smooth with an outstanding drip off effect
+    one 75 ml should complete average size car produced by sonax identifiers is 223000m941
+    category of automotive
+  sentences:
+  - paint sealant sonax profiline polymer net shield 75 ml aerosol can 1991 bmw 325i
+    base convertible miscellaneous page 23 note innovative surface protection based
+    on hybrid polymers protects the paintwork by means of a resistant network made
+    from organic and inorganic components can be applied quickly easily intensively
+    freshens up paint color produces silky smooth with an outstanding drip off effect
+    one 75 ml should complete average size car produced by sonax identifiers is 223000m941
+    category of automotive
+  - honeywell accessories for terminal cod99exmb12 honeywell cod871238012 honeywell
+    dolphin 99ex mobile base vehicle kit charging cradle rs232 universal mounting
+    bracket and 12v cigarette lighter power adapter produced by honeywell metrologic
+    identifiers is 99exmb12 category of computersandaccessories
+  - usb flash drives hard quillcom null identifiers is 901507043 category of computersandaccessories
+---
+
+# 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 = [
+    'paint sealant sonax profiline polymer net shield 75 ml aerosol can 1994 bmw 318is base coupe miscellaneous page 24 note innovative surface protection based on hybrid polymers protects the paintwork by means of a resistant network made from organic and inorganic components can be applied quickly easily intensively freshens up paint color produces silky smooth with an outstanding drip off effect one 75 ml should complete average size car produced by sonax identifiers is 223000m941 category of automotive',
+    'paint sealant sonax profiline polymer net shield 75 ml aerosol can 1991 bmw 325i base convertible miscellaneous page 23 note innovative surface protection based on hybrid polymers protects the paintwork by means of a resistant network made from organic and inorganic components can be applied quickly easily intensively freshens up paint color produces silky smooth with an outstanding drip off effect one 75 ml should complete average size car produced by sonax identifiers is 223000m941 category of automotive',
+    'honeywell accessories for terminal cod99exmb12 honeywell cod871238012 honeywell dolphin 99ex mobile base vehicle kit charging cradle rs232 universal mounting bracket and 12v cigarette lighter power adapter produced by honeywell metrologic identifiers is 99exmb12 category of computersandaccessories',
+]
+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: 281,342 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: 25 tokens</li><li>mean: 74.69 tokens</li><li>max: 384 tokens</li></ul> | <ul><li>min: 25 tokens</li><li>mean: 75.63 tokens</li><li>max: 384 tokens</li></ul> |
+* Samples:
+  | anchor                                                                                                                                                                                                                  | positive                                                                                                                                                                                                                                                                                                                                                                                                                                            |
+  |:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+  | <code>honeywell hand held products dolphin 99509951 series mobile computer usb cable 6 ft 18m 80000355e usb cable 6 ft 18m identifiers is 80000355e category of computersandaccessories</code>                          | <code>hand held usb cable 6 ft hand ft 80000355e scanner accessories cdwcom hand held products is the leading provider of imagebased data collection solutions for mobile wireless and transaction processing applications to end users throughout world by investing in hhp products its customers are able reduce costs improve service position their companies future growth identifiers is 26121604 category of computersandaccessories</code> |
+  | <code>intake boot air mass sensor to throttle housing 1995 bmw 318i base convertible intake system page 2 note from 0994 produced by oem identifiers is 13711247829m58 category of automotive</code>                    | <code>intake boot air mass sensor to throttle housing 1995 bmw 318i base convertible intake system page 2 produced by crp identifiers is 13711247829int category of automotive</code>                                                                                                                                                                                                                                                               |
+  | <code>blue sky panorama with transparent clouds vector image sky images over 150 000 vector blue sky panorama with transparent clouds vector background image identifiers is 15266707 category of officeproducts</code> | <code>blue sky panorama with transparent clouds vector image images within landscapes nature over 55 000 vector blue sky panorama with transparent clouds vector background image identifiers is 15266707 category of 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"
+  }
+  ```
+
+### Evaluation Dataset
+
+#### Unnamed Dataset
+
+
+* Size: 70,336 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: 25 tokens</li><li>mean: 78.58 tokens</li><li>max: 384 tokens</li></ul> | <ul><li>min: 22 tokens</li><li>mean: 81.44 tokens</li><li>max: 384 tokens</li></ul> |
+* Samples:
+  | anchor                                                                                                                                                                                                                                                                                                                                                                                                                                        | positive                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                            |
+  |:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+  | <code>heater hose inlet from cylinder head to water valve 1997 bmw 318i base sedan heater system page 3 produced by genuine bmw identifiers is 64211394295boe category of automotive</code>                                                                                                                                                                                                                                                   | <code>heater hose inlet from cylinder head to water valve 1996 bmw 318i base convertible heater system page 3 produced by genuine bmw identifiers is 64211394295boe category of automotive</code>                                                                                                                                                                                                                                                                                                                                   |
+  | <code>harris harris group inc group 1 full quote netdaniacom produced by source nasdaq identifiers is isinus4138331040 category of toolsandhomeimprovement</code>                                                                                                                                                                                                                                                                             | <code>harris harris group inc 1 statistics netdaniacom group produced by source nasdaq identifiers is isinus4138331040 category of toolsandhomeimprovement</code>                                                                                                                                                                                                                                                                                                                                                                   |
+  | <code>swiffer dusters with extendable handledusters plastic handle extends to 3 ft 1 per kit handledusters ft kitpag82074 buy online at janeice products identifiers is pag82074 category of toolsandhomeimprovement key specifications are weight per case std pkg quantity package one handle and three dusters description includes item cube 008276 upc code 037000447504 pack 00037000820741 length 092 width 022 height 042 0476</code> | <code>6 pack value bundle pag82074 dusters plastic handle extends to 3 ft 1 dusters per kitus feather page 5 the janitorial marketus now its easier than ever to get those hardtoreach places pivoting head can be adjusted and locked into place for cleaning angled surfaces such as ceiling fans cabinet corners baseboards refill dusters sold separately one handle three per box bristle material fiber color white plastic greenus produced by pag82074us identifiers is pag82074 category of toolsandhomeimprovement</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  | 0.0083        | 0.0029 |
+| 0.3981 | 14000 | 0.0026        | 0.0019 |
+| 0.5971 | 21000 | 0.0015        | 0.0014 |
+| 0.7962 | 28000 | 0.0013        | 0.0011 |
+| 0.9952 | 35000 | 0.0013        | 0.0010 |
+| 1.1943 | 42000 | 0.0008        | 0.0010 |
+| 1.3933 | 49000 | 0.0005        | 0.0009 |
+| 1.5924 | 56000 | 0.0003        | 0.0009 |
+
+
+### 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 sha256:87e266683916753caf604b1813d347ffac0dc8a34244ee6c1295f3e0b45ce284
+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"
+  }
+]

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b69efe25866431df1b62d40fbe38c1105576e656362fc7f5dce862455dfa03e7
+size 871331770

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2cd293246b360c89a52808a6915adce6376258887785b1c284bf376ba6238405
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:801539f0e554cac782b1d9195dfe01948924cc3e8dad48d60f1f1dd6dc515001
+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 +1,153 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.5923566878980893,
+  "eval_steps": 7000,
+  "global_step": 56000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.19904458598726116,
+      "grad_norm": 0.2248842865228653,
+      "learning_rate": 9.947398350867217e-06,
+      "loss": 0.0083,
+      "step": 7000
+    },
+    {
+      "epoch": 0.19904458598726116,
+      "eval_loss": 0.002906730631366372,
+      "eval_runtime": 281.988,
+      "eval_samples_per_second": 249.429,
+      "eval_steps_per_second": 31.179,
+      "step": 7000
+    },
+    {
+      "epoch": 0.3980891719745223,
+      "grad_norm": 0.0002081295824609697,
+      "learning_rate": 8.900350699819912e-06,
+      "loss": 0.0026,
+      "step": 14000
+    },
+    {
+      "epoch": 0.3980891719745223,
+      "eval_loss": 0.0018650980200618505,
+      "eval_runtime": 284.0569,
+      "eval_samples_per_second": 247.612,
+      "eval_steps_per_second": 30.952,
+      "step": 14000
+    },
+    {
+      "epoch": 0.5971337579617835,
+      "grad_norm": 0.010839835740625858,
+      "learning_rate": 7.795014375533159e-06,
+      "loss": 0.0015,
+      "step": 21000
+    },
+    {
+      "epoch": 0.5971337579617835,
+      "eval_loss": 0.001360387192107737,
+      "eval_runtime": 285.5315,
+      "eval_samples_per_second": 246.334,
+      "eval_steps_per_second": 30.792,
+      "step": 21000
+    },
+    {
+      "epoch": 0.7961783439490446,
+      "grad_norm": 0.00013278079859446734,
+      "learning_rate": 6.689836024138259e-06,
+      "loss": 0.0013,
+      "step": 28000
+    },
+    {
+      "epoch": 0.7961783439490446,
+      "eval_loss": 0.0011233221739530563,
+      "eval_runtime": 285.4742,
+      "eval_samples_per_second": 246.383,
+      "eval_steps_per_second": 30.798,
+      "step": 28000
+    },
+    {
+      "epoch": 0.9952229299363057,
+      "grad_norm": 0.00014249606465455145,
+      "learning_rate": 5.5841837540678024e-06,
+      "loss": 0.0013,
+      "step": 35000
+    },
+    {
+      "epoch": 0.9952229299363057,
+      "eval_loss": 0.0010357595747336745,
+      "eval_runtime": 286.0827,
+      "eval_samples_per_second": 245.859,
+      "eval_steps_per_second": 30.732,
+      "step": 35000
+    },
+    {
+      "epoch": 1.194267515923567,
+      "grad_norm": 0.0002924288564827293,
+      "learning_rate": 4.478689456889198e-06,
+      "loss": 0.0008,
+      "step": 42000
+    },
+    {
+      "epoch": 1.194267515923567,
+      "eval_loss": 0.0010089210700243711,
+      "eval_runtime": 282.9155,
+      "eval_samples_per_second": 248.611,
+      "eval_steps_per_second": 31.076,
+      "step": 42000
+    },
+    {
+      "epoch": 1.393312101910828,
+      "grad_norm": 0.00017198333807755262,
+      "learning_rate": 3.3733531326024454e-06,
+      "loss": 0.0005,
+      "step": 49000
+    },
+    {
+      "epoch": 1.393312101910828,
+      "eval_loss": 0.0009262111852876842,
+      "eval_runtime": 285.6294,
+      "eval_samples_per_second": 246.249,
+      "eval_steps_per_second": 30.781,
+      "step": 49000
+    },
+    {
+      "epoch": 1.5923566878980893,
+      "grad_norm": 2.850917553587351e-05,
+      "learning_rate": 2.2678588354238415e-06,
+      "loss": 0.0003,
+      "step": 56000
+    },
+    {
+      "epoch": 1.5923566878980893,
+      "eval_loss": 0.0008692654664628208,
+      "eval_runtime": 281.4473,
+      "eval_samples_per_second": 249.908,
+      "eval_steps_per_second": 31.239,
+      "step": 56000
+    }
+  ],
+  "logging_steps": 7000,
+  "max_steps": 70336,
+  "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:ebd26e3916d1afe3a7febaec075216749fc2d7d7b776a249951c32c8b626f07c
+size 5368