Upload model checkpoint

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+  "word_embedding_dimension": 1024,
+  "pooling_mode_cls_token": true,
+  "pooling_mode_mean_tokens": false,
+  "pooling_mode_max_tokens": false,
+  "pooling_mode_mean_sqrt_len_tokens": false,
+  "pooling_mode_weightedmean_tokens": false,
+  "pooling_mode_lasttoken": false,
+  "include_prompt": true
+}

README.md

@@ -0,0 +1,440 @@
+---
+base_model: Alibaba-NLP/gte-large-en-v1.5
+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: nokya heavy duty fog light harnesses 0708 jeep compass h10 these
+    nokya heavy duty fog light h10 wire harnesses have been designed to be plugged
+    into your jeep compasss stock wiring aftermarket bulbs or not as complete upgrades
+    a precautionary measure against harness plug burnouts which can permanently damage
+    compass housings these also help handle the increased demands of offers cheap
+    and relatively easy upgrade electrical system they work replacements for damaged
+    plugs lighting are extended periods use operation in adverse severe conditions
+    address this brand otherwise each set consists 2 harnesses identifiers is nok91052pcs
+    category of automotive
+  sentences:
+  - nokya heavy duty headlight harnesses high beam 0103 acura cl 32 9005hb3 these
+    nokya heavy duty headlight high beam 9005 wire harnesses have been designed to
+    be plugged into your acura cl 32s stock wiring aftermarket bulbs or not offers
+    these as a cheap and relatively easy upgrade 32 electrical system they work replacements
+    for damaged harness plugs complete upgrades precautionary measure against plug
+    burnouts which can permanently damage housings also help handle the increased
+    demands of operation in adverse severe conditions address this lighting are extended
+    periods use brand otherwise each set consists 2 harnesses identifiers is nok91052pcs
+    category of automotive
+  - powergard protection plan residential 2year option for gator t series and hpx
+    john deere in john deere us riding lawn mowers sale tractors castongia tractor
+    valparaiso for t series and hpx gator utility vehicles view plan detailsextends
+    manufacturers warranty 1 additional year2 years of transportationfor residential
+    owners onlynot available in all areasbuy online for machines purchased within
+    the past year identifiers is ppprtuv2y category of automotive
+  - compatible for okidata c5500n c5800ldn toner cart cyan 5k compatible 5k 43324403
+    identifiers is 43324403 category of officeproducts
+- source_sentence: zebra handheld protective boot zebra boot sgtc55boot101 scanner
+    accessories cdwcom identifiers is 43211612 category of otherelectronics
+  sentences:
+  - window regulator without motor electric front left 1996 bmw 318is base coupe panels
+    doors page 1 note includes bushings 51 33 8 163 351 and 352 produced by genuine
+    bmw identifiers is 51331977579m9 category of automotive
+  - zebra handheld protective boot zebra boot sgtc55boot101 scanner accessories cdwcom
+    identifiers is 43211612 category of otherelectronics
+  - premium screen protector film 3 pack samsung exhilarate accessoriesexhilarate
+    accessoriessave now accessorygeekscom identifiers is sfpuni3pk category of cellphonesandaccessories
+- source_sentence: samsung clp310n black genuine samsung toner cartridge cartridges
+    inkrediblecouk black approx 1500 page yield at 5 coverage identifiers is cltk4092sblack
+    category of officeproducts
+  sentences:
+  - hansgrohe 240 air singlejet showerhead 25 gpm tub shower accessories heads trim
+    plates products at efaucetscom 10 spray face solid brass airinjection technology
+    12 female inlet 180 noclog channels flow rate is 25 gpm requires shower arm and
+    flange sold separately mode rainair fullyfinished matching fast antilimescale
+    function with quickclean cupc listed identifiers is 27474001 category of toolsandhomeimprovement
+  - epson 24xl elephant black ink cartridge 24xl elephant black ink cartridge 10ml
+    500 pagespage yields based on isoiec 24711 and 24712for a list of compatible machines
+    see the more info tab below produced by epson identifiers is c13t24314010 category
+    of officeproducts
+  - samsung clx3175 black genuine samsung toner cartridge cartridges inkrediblecouk
+    black approx 1500 page yield at 5 coverage identifiers is cltk4092sblack category
+    of officeproducts
+- source_sentence: coolant hose gb 2004 audi a4s4avantqu canada market fuel cooling
+    auxiliary heater 6cylinder petr enginegb exhaust 30ltr gb identifiers is 8e0265357g
+    category of automotive
+  sentences:
+  - coolant hose gb 2001 audi a4s4avantquattro europe market fuel cooling auxiliary
+    heater 6cylinder petr enginegb exhaust 30ltr gb identifiers is 8e0265357g category
+    of automotive
+  - pilot bearing 15 x 32 10 1992 bmw 325i base sedan clutch flywheel page 3 produced
+    by genuine bmw identifiers is 11211720310boe category of automotive
+  - mityvac mv8020 brake bleeding kit 1992 bmw 318i base sedan wizard page 1 identifiers
+    is tolmtymv8020 category of automotive
+- source_sentence: steinel led floodlight with sensor xled home 1 silver led floodlights
+    anylamp produced by steinel identifiers is 4007841002688 category of toolsandhomeimprovement
+  sentences:
+  - steinel led floodlight with sensor xled home 1 silver led lighting anylamp produced
+    by steinel identifiers is 4007841002688 category of toolsandhomeimprovement
+  - desk organizers quillcom durable bookends with reinforced rib designheavygauge
+    steel construction9 height identifiers is 90117bebk category of officeproducts
+  - hp photosmart c4150 cartridges for ink jet printers quillcom yields up to 399
+    pagessized and priced for occasional printingoriginal hp ink a little less ink
+    at very affordable price identifiers is 901d8j33an category of officeproducts
+---
+
+# SentenceTransformer based on Alibaba-NLP/gte-large-en-v1.5
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [Alibaba-NLP/gte-large-en-v1.5](https://huggingface.co/Alibaba-NLP/gte-large-en-v1.5). It maps sentences & paragraphs to a 1024-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
+
+## Model Details
+
+### Model Description
+- **Model Type:** Sentence Transformer
+- **Base model:** [Alibaba-NLP/gte-large-en-v1.5](https://huggingface.co/Alibaba-NLP/gte-large-en-v1.5) <!-- at revision 104333d6af6f97649377c2afbde10a7704870c7b -->
+- **Maximum Sequence Length:** 8192 tokens
+- **Output Dimensionality:** 1024 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': 8192, 'do_lower_case': False}) with Transformer model: NewModel 
+  (1): Pooling({'word_embedding_dimension': 1024, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
+)
+```
+
+## 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 = [
+    'steinel led floodlight with sensor xled home 1 silver led floodlights anylamp produced by steinel identifiers is 4007841002688 category of toolsandhomeimprovement',
+    'steinel led floodlight with sensor xled home 1 silver led lighting anylamp produced by steinel identifiers is 4007841002688 category of toolsandhomeimprovement',
+    'desk organizers quillcom durable bookends with reinforced rib designheavygauge steel construction9 height identifiers is 90117bebk category of officeproducts',
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 1024]
+
+# 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: 24 tokens</li><li>mean: 81.17 tokens</li><li>max: 941 tokens</li></ul> | <ul><li>min: 23 tokens</li><li>mean: 80.26 tokens</li><li>max: 1004 tokens</li></ul> |
+* Samples:
+  | anchor                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                | positive                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                               |
+  |:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+  | <code>ironwood pharmaceuticals inc class a a 1 full quote netdaniacom pharmaceuticals produced by source nasdaq identifiers is isinus46333x1081 category of automotive</code>                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                         | <code>ironwood pharmaceuticals inc class a pharmaceuticals a 1 news netdaniacom produced by source nasdaq identifiers is isinus46333x1081 category of automotive</code>                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                |
+  | <code>873010s21 hp 600gb 12g 10k 25 dp sas hdd null price 873010s2110pack new 873010s21 600gb hdd 10 pack wholesale description10 x 600gb 25inch serial attached scsi sassff digitally signed ds 12g dual portenterprise hotplug 512n 10k hard drivein hpe drive tray as picturedfor g1g7 proliant sas serversgenuine number and firmwaregenuine certified drivepart numbers option part 873010b21 smartbuy 873010s21 produced by hp enterprise identifiers is 873010s2110pack category of computersandaccessories key specifications are specifications category proliant harddrive subcategory 10k generation sas part number 873010s2110pack products id 489761 type hard drive hotswap capacity 600gb interface serial attached scsi spindle speed 10000rpm ports dual port data transfer rate 12gbs bytes per sector 512n</code> | <code>873010s21 hp 600gb 12g 10k 25 dp sas hdd null price 873010s21 new 873010s21 600gb hdd wholesale description600gb 25inch serial attached scsi sassff digitally signed ds 12g dual portenterprise hotplug 512n 10k hard drivein hpe drive tray as picturedfor g1g7 proliant sas serversgenuine number and firmwaregenuine certified drivepart numbers option part 873010b21 smartbuy 873010s21 produced by hp enterprise identifiers is 873010s21 category of computersandaccessories key specifications are specifications category proliant harddrive subcategory 10k generation sas part number 873010s21 products id 489758 type hard drive hotswap capacity 600gb interface serial attached scsi spindle speed 10000rpm ports dual port data transfer rate 12gbs bytes per sector 512n</code> |
+  | <code>armrest fabric gb 2010 audi a4avant argentina market body middle front pr6e3gb model data prn0ln5fn2en2m gb identifiers is 8k0864207a category of automotive</code>                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                             | <code>armrest fabric gb 2009 audi a5s5 coupesportback south africa market body middle front pr6e3gb model data coupeprn2e gb identifiers is 8k0864207a category of automotive</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: 80.88 tokens</li><li>max: 542 tokens</li></ul> | <ul><li>min: 24 tokens</li><li>mean: 79.18 tokens</li><li>max: 1004 tokens</li></ul> |
+* Samples:
+  | anchor                                                                                                                                                                                                                                                                                                 | positive                                                                                                                                                                                                                                                                                                                                                       |
+  |:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+  | <code>rennline race hook front universal 8 in red each 2000 bmw 323i base wagon chassis panels sheet metal page 3 identifiers is rene01r8 category of automotive</code>                                                                                                                                | <code>rennline race hook front universal 8 in red each 2000 bmw 323i base wagon chassis panels sheet metal page 3 identifiers is rene01r8 category of automotive</code>                                                                                                                                                                                        |
+  | <code>happy new year 2017 peace patch icon card design vector image patch images over 13 000 happy new year 2017 greeting card design with varsity college typography and stitch patch peace symbol icon as number eps10 vector vector image identifiers is 14478945 category of officeproducts</code> | <code>happy new year 2017 peace patch icon card design vector image happy new year 2017 greeting card design with varsity college typography and stitch patch peace symbol icon as number eps10 vector download a free preview or high quality adobe illustrator ai eps pdf resolution jpeg versions identifiers is 14478945 category of officeproducts</code> |
+  | <code>hp deskjet d4155 cartridges for ink jet printers quillcom yields up to 399 pagessized and priced for occasional printingoriginal hp ink a little less ink at very affordable price identifiers is 901d8j33an category of officeproducts</code>                                                   | <code>hp photosmart c4150 cartridges for ink jet printers quillcom yields up to 399 pagessized and priced for occasional printingoriginal hp ink a little less ink at very affordable price identifiers is 901d8j33an 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"
+  }
+  ```
+
+### 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  | 0.0057        | 0.0026 |
+| 0.3981 | 14000 | 0.0019        | 0.0018 |
+| 0.5971 | 21000 | 0.0016        | 0.0012 |
+| 0.7962 | 28000 | 0.001         | 0.0009 |
+| 0.9952 | 35000 | 0.001         | 0.0009 |
+| 1.1943 | 42000 | 0.0007        | 0.0008 |
+| 1.3933 | 49000 | 0.0004        | 0.0009 |
+| 1.5924 | 56000 | 0.0003        | 0.0009 |
+| 1.7914 | 63000 | 0.0002        | 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 +1,44 @@
+{
+  "_name_or_path": "Alibaba-NLP/gte-large-en-v1.5",
+  "architectures": [
+    "NewModel"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "auto_map": {
+    "AutoConfig": "Alibaba-NLP/new-impl--configuration.NewConfig",
+    "AutoModel": "Alibaba-NLP/new-impl--modeling.NewModel",
+    "AutoModelForMaskedLM": "Alibaba-NLP/new-impl--modeling.NewForMaskedLM",
+    "AutoModelForMultipleChoice": "Alibaba-NLP/new-impl--modeling.NewForMultipleChoice",
+    "AutoModelForQuestionAnswering": "Alibaba-NLP/new-impl--modeling.NewForQuestionAnswering",
+    "AutoModelForSequenceClassification": "Alibaba-NLP/new-impl--modeling.NewForSequenceClassification",
+    "AutoModelForTokenClassification": "Alibaba-NLP/new-impl--modeling.NewForTokenClassification"
+  },
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-12,
+  "layer_norm_type": "layer_norm",
+  "logn_attention_clip1": false,
+  "logn_attention_scale": false,
+  "max_position_embeddings": 8192,
+  "model_type": "new",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pack_qkv": true,
+  "pad_token_id": 0,
+  "position_embedding_type": "rope",
+  "rope_scaling": {
+    "factor": 2.0,
+    "type": "ntk"
+  },
+  "rope_theta": 160000,
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.0",
+  "type_vocab_size": 2,
+  "unpad_inputs": false,
+  "use_memory_efficient_attention": false,
+  "vocab_size": 30528
+}

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 sha256:48c84c4b56f27002b3eb72ea1423f649a41c83c838b50c6cad9d1e153b01d2a2
+size 1736585680

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"
+  }
+]

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40f3b6a12c4a423fc3b883fa24730effad25a201003e4e7e0b0adf0e96a5ebf1
+size 3473337082

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98d314b4e768bf1d786b31d1da3633581006026bfc6f127c8abba9773c9c894b
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:668de5733e9f925fc49f180dc3accbe81ff028c5c16a3a507a52543ed5a4bf2c
+size 1064

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 8192,
+  "do_lower_case": false
+}

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,62 @@
+{
+  "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_lower_case": true,
+  "mask_token": "[MASK]",
+  "max_length": 8000,
+  "model_max_length": 8192,
+  "pad_to_multiple_of": null,
+  "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "[SEP]",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}

trainer_state.json

@@ -0,0 +1,168 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.7914012738853504,
+  "eval_steps": 7000,
+  "global_step": 63000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.19904458598726116,
+      "grad_norm": 0.15043310821056366,
+      "learning_rate": 9.94455501848166e-06,
+      "loss": 0.0057,
+      "step": 7000
+    },
+    {
+      "epoch": 0.19904458598726116,
+      "eval_loss": 0.002587760565802455,
+      "eval_runtime": 385.9016,
+      "eval_samples_per_second": 182.264,
+      "eval_steps_per_second": 22.783,
+      "step": 7000
+    },
+    {
+      "epoch": 0.3980891719745223,
+      "grad_norm": 0.0009809082839637995,
+      "learning_rate": 8.900666645603615e-06,
+      "loss": 0.0019,
+      "step": 14000
+    },
+    {
+      "epoch": 0.3980891719745223,
+      "eval_loss": 0.0018288933206349611,
+      "eval_runtime": 386.974,
+      "eval_samples_per_second": 181.759,
+      "eval_steps_per_second": 22.72,
+      "step": 14000
+    },
+    {
+      "epoch": 0.5971337579617835,
+      "grad_norm": 0.004145281855016947,
+      "learning_rate": 7.79517234842501e-06,
+      "loss": 0.0016,
+      "step": 21000
+    },
+    {
+      "epoch": 0.5971337579617835,
+      "eval_loss": 0.0012058253632858396,
+      "eval_runtime": 385.6472,
+      "eval_samples_per_second": 182.384,
+      "eval_steps_per_second": 22.798,
+      "step": 21000
+    },
+    {
+      "epoch": 0.7961783439490446,
+      "grad_norm": 0.0015833042562007904,
+      "learning_rate": 6.689678051246407e-06,
+      "loss": 0.001,
+      "step": 28000
+    },
+    {
+      "epoch": 0.7961783439490446,
+      "eval_loss": 0.0009336507064290345,
+      "eval_runtime": 386.8698,
+      "eval_samples_per_second": 181.808,
+      "eval_steps_per_second": 22.726,
+      "step": 28000
+    },
+    {
+      "epoch": 0.9952229299363057,
+      "grad_norm": 0.0003439185384195298,
+      "learning_rate": 5.5843417269596545e-06,
+      "loss": 0.001,
+      "step": 35000
+    },
+    {
+      "epoch": 0.9952229299363057,
+      "eval_loss": 0.0008668347145430744,
+      "eval_runtime": 386.7927,
+      "eval_samples_per_second": 181.844,
+      "eval_steps_per_second": 22.731,
+      "step": 35000
+    },
+    {
+      "epoch": 1.194267515923567,
+      "grad_norm": 0.0005341056967154145,
+      "learning_rate": 4.478847429781049e-06,
+      "loss": 0.0007,
+      "step": 42000
+    },
+    {
+      "epoch": 1.194267515923567,
+      "eval_loss": 0.0008429304580204189,
+      "eval_runtime": 387.0524,
+      "eval_samples_per_second": 181.722,
+      "eval_steps_per_second": 22.715,
+      "step": 42000
+    },
+    {
+      "epoch": 1.393312101910828,
+      "grad_norm": 0.00042841769754886627,
+      "learning_rate": 3.3735111054942974e-06,
+      "loss": 0.0004,
+      "step": 49000
+    },
+    {
+      "epoch": 1.393312101910828,
+      "eval_loss": 0.0009025875478982925,
+      "eval_runtime": 390.6459,
+      "eval_samples_per_second": 180.051,
+      "eval_steps_per_second": 22.506,
+      "step": 49000
+    },
+    {
+      "epoch": 1.5923566878980893,
+      "grad_norm": 0.0007971890736371279,
+      "learning_rate": 2.2678588354238415e-06,
+      "loss": 0.0003,
+      "step": 56000
+    },
+    {
+      "epoch": 1.5923566878980893,
+      "eval_loss": 0.0009143418865278363,
+      "eval_runtime": 388.6682,
+      "eval_samples_per_second": 180.967,
+      "eval_steps_per_second": 22.621,
+      "step": 56000
+    },
+    {
+      "epoch": 1.7914012738853504,
+      "grad_norm": 0.02023099735379219,
+      "learning_rate": 1.162522511137089e-06,
+      "loss": 0.0002,
+      "step": 63000
+    },
+    {
+      "epoch": 1.7914012738853504,
+      "eval_loss": 0.0008290820405818522,
+      "eval_runtime": 389.2129,
+      "eval_samples_per_second": 180.713,
+      "eval_steps_per_second": 22.589,
+      "step": 63000
+    }
+  ],
+  "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:cb08c5d98989717c95b2c6f128c0ede37adf47aaf8ad45515a15d140c41272c0
+size 5368