Hugging Face's logo

thebajajra
/
RexBERT-base-embed-pf-v0.1

Sentence Similarity
sentence-transformers
Safetensors
English
modernbert
feature-extraction
dense
Generated from Trainer
dataset_size:222490215
loss:MultipleNegativesRankingLoss
text-embeddings-inference
Model card Files
xet
Community
RexBERT-base-embed-pf-v0.1 / README.md
thebajajra's picture
thebajajra
Upload folder using huggingface_hub
30c9769 verified
preview code
|
raw
history blame contribute delete
51.7 kB
 ---
language:
- en
tags:
- sentence-transformers
- sentence-similarity
- feature-extraction
- dense
- generated_from_trainer
- dataset_size:222490215
- loss:MultipleNegativesRankingLoss
base_model: thebajajra/RexBERT-base
widget:
- source_sentence: Can I bring Katana (Samurai Sword) from Japan to Malaysia?
sentences:
- I've seen the j hook method and binder method on here, but I was looking for something
a little cheaper. I need to hang 100 empty record sleeves on a wall for a photoshoot
and couldn't think of anything other than command strips. I'd use magic tape but
I hear that it rips paper. I also need to hang them on cement
- "Hi all, \n\nWith the success of GoT, and with the upcoming QoT, LoTR and The\
\ Witcher series, I was wondering which fantasy books you thought would translate\
\ well to TV. \n\nI think The Traitor Baru Cormorant would be great, as well as\
\ Farseer. My heart also wants me to believe Malazan would be good, but the CGI\
\ budget would likely need to be ridiculous."
- Hi everyone, currently I'm at Japan and thinking of buying a Katana (Samurai Sword)
and bring it back to Malaysia. How do you guys/girls reckon? Will i pass through
japanese and malaysian customs without a problem?
- source_sentence: What one book would you recommend schools add to the list of books
to teach?
sentences:
- 'Hi everyone. I''m in the middle of teaching a college algebra course and a large
portion of my students are working toward a nursing career (this is a required
course for them).
Since my background is in math and a variety of physical/engineering sciences,
I have no problem emphasizing the utility of the course material to the few students
aiming for computer science, physics, and accounting. However, I feel really lost
as to how I can answer the classical "when am I going to use this class" for the
nursing types, and I''d really like to do everything I can to motivate them. My
general thoughts on mathematics as a whole is that the most important thing to
learn from it is the logical, systematic, and scientific thought process for problem
solving, but I also feel that this is built up over several deeper math and science
courses rather than just one introductory math course.
So I''m hoping some people can offer some insight as to the long-term reality:
does anyone here feel like they benefited from an algebra or other introductory
math course in the long run? If so, how? And if possible, are there any examples
from the actual job that can be related in some way to a basic algebra class?
Or do you feel that this is a complete waste of time and shouldn''t be required?
Any input is appreciated.'
- "Hello all, \n\nI need some serious help with a spot in my hard. \n\n\nIt's\
\ between a hundred foot tall oak tree, the shade of the carport, and sits in\
\ front of the bay windows on the front of my house. \n\n\nWe're so tired if sitting\
\ here and staring at this, \"dead zone. \" \n\n\nIt's shaded basically all\
\ the time and stays pretty damp. \n\n\nWe've planted periwinkle here, and it\
\ blooms, but won't spread. I think we spent about $700 planting it 3 years\
\ ago.. . But it hasn't done anything. \n\n\nSince the spot is in front of the\
\ windows, we can't plant anything tall. Also, the yard is sloped, so I\
\ can't put a patio there (without terracing). About 5 years ago, we tried\
\ to turn it into a rock garden.... but the oak tree drops so many leaves in the\
\ autumn that the rock garden was covered and it was a nightmare to get the leaves\
\ out of the pea gravel. \n\n\nI live in central Alabama. Any help would\
\ be greatly appreciated. Please save me."
- 'I had a conversation a while back, and we noticed that schools (specifically
high schools) don''t really teach any contemporary books. I''m curious what books,
new or old, you would add the the required high school reading.
The first books that comes to my mind are *Zen and the Art of Motorcycle maintenance*,
*Zen Flesh Zen Bones*, and maybe even *the Bible* (+ other old religious scriptures:
Tao Te Jing etc) if for nothing else the shear number of literary allusions reading
it reveals.'
- source_sentence: Ram allocation setting keeps resetting to xmx1g in vanilla launcher,
not using Curse or Twitch launcher, wtf?
sentences:
- 'Is there some way we can reward people for having a good win differential (i.e.
they''ve won a lot more games than they''ve lost). I''m not opposed to the current
degree/rank system, but maybe we could add a flair for highest win differential
in a day or in a month or something like that. I feel like we should reward people
who are winning 70+% of their games as opposed to only rewarding people with the
highest volume of wins.
Thoughts?'
- 'So every time I allocate 6gb of ram to minecraft, I can start up the game and
use 6gb just fine, but if I close the game and re-open it, the java argument is
reset back to the default ram value. I''ve researched everywhere and I can''t
find anything for the vanilla launcher as this problem seems to only effect people
using the Curse or Twitch launcher which I do not have or have ever used. Razer
Synapse seems to be a factor as well, but I don''t have Razer Synapse either.
Not a major problem, I just don''t feel like adding the argument before I launch
the game every time.
EDIT: Can''t edit post title, but I meant to type xmx2g instead of 1g.
EDIT 2: The problem fixed itself after setting the argument a few times, dunno
what was goin on.'
- 'timestamp
closeup of cables
​
​
# OUTDATED, PLEASE SEE MY NEWEST POST
# OUTDATED, PLEASE SEE MY NEWEST POST
# OUTDATED, PLEASE SEE MY NEWEST POST
​
​
|ITEM|NOTE|PRICE|
|:-|:-|:-|
|SA Arcane base kit|never mounted|130 EUR **SOLD**|
|coiled LEMO cable rose|1.5m with 15cm coil on device side. USB-A to USB-C. "Rose"
paracord with white techflex double sleeving. white heatshrink|~~105 EUR~~ **SOLD**|
|coiled LEMO cable purple|1.5m with 15cm coil on device side. USB-A to USB-C.
"Neon Pink" paracord with purple techflex double sleeving. blue heatshrink. (GMK
Laser themed) - rest of cable not pictured but will be included obviously|105
EUR **SOLD**|
|Unholy Panda (linear) x70|Halo housing + Trash Panda stem (you can choose between
Halo True and Halo Clear spring)|18 EUR **SOLD**|
|Unholy Panda (tactile) x 100|Halo housing + purple Trash Panda stem (you can
choose between Halo True and Halo Clear spring)|23 EUR|
|Unholy Panda (tactile) x 100|Halo housing + purple Trash Panda stem (you can
choose between Halo True and Halo Clear spring)|23 EUR|
|\--|\--|\--|
|ADD-ON ONLY: Nutcracker V1 Pro switch opener|for Cherry style housings, silver.
will only sell bundled with other items|15 EUR|
Cables were made by PexonPCs and use genuine LEMO connectors'
- source_sentence: Struggling with BPD for a little over a year, SO just told me something
that hurt my feelings. Is this the BP clinginess talking or am I correct in my
gut instincts?
sentences:
- Since demon's souls is getting a remake i wanted to ask how strong do you guys
think the slayer of demon's from the original version is. I personally have him
at planet level
- 'My SO and I were on the couch watching TV. I reached up and softly touched his
face for a second. He smiled and rubbed my leg. I asked him, "Does me touching
you annoy you?" He thought for a moment and said, "Not all the time." I pressed
for an explanation and he said, "Sometimes during the week, when I''m exhausted
from work, I don''t want you to be so needy."
Is this a red flag or is this just my constant need for validation due to the
BPD?'
- So I'm on a trip right now and I may have found a sweet deal on a Mohawk solo
canoe. The problem of course (just my luck) is that I also have my kayak with
me. I'm ready to pull the trigger on this canoe if it's in good shape bit I don't
have a way of getting it home at the moment. There's an rei close by and I was
thinking about getting a set of the y carriers. Has anyone ever tried putting
a solo canoe in one of these? Could I fit one boat in a single y carrier and then
the other on the roof racks? Another option is to build a addition to the roof
rack but I don't have any tools on hand so I would like to avoid that if possible.
- source_sentence: Where do you guys go to find used camper shells?
sentences:
- 'Hey guys what is the most optimal tool for pulling long staples out from hardwood
flooring? I''m trying to find the most optimal way to do it because I have thousands
to pull! Fence pliers did not work too well on account the pointy tip was too
thick get in and roll them out and when i tried the gripping/cutting part it broke
the staples.
I''m thinking round nose vice grips or a car gasket puller?
Thanks'
- 'I''ve got a newly acquired 1st gen 2005 silvee Toyota tundra trd and am looking
for an used camper shell. Craigslist hasnt been very useful....where do you guys
go?
Thanks!'
- I work at a convenience store and the number of Newports I sell a day is insane.
Considering buying a couple cartons of em and maybe some parliament menthols if
the FDA goes through with this. Should be able to throw em up on craigslist or
ebay a week or two later and it'll be like steaks in a piranha pond
datasets:
- nomic-ai/nomic-embed-unsupervised-data
pipeline_tag: sentence-similarity
library_name: sentence-transformers
---
# SentenceTransformer based on thebajajra/RexBERT-base
This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [thebajajra/RexBERT-base](https://huggingface.co/thebajajra/RexBERT-base) on the [nomic-embed-unsupervised-data](https://huggingface.co/datasets/nomic-ai/nomic-embed-unsupervised-data) dataset. 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:** [thebajajra/RexBERT-base](https://huggingface.co/thebajajra/RexBERT-base) <!-- at revision 4f66d2977864414371770084b681e00698b98457 -->
- **Maximum Sequence Length:** 1024 tokens
- **Output Dimensionality:** 768 dimensions
- **Similarity Function:** Cosine Similarity
- **Training Dataset:**
- [nomic-embed-unsupervised-data](https://huggingface.co/datasets/nomic-ai/nomic-embed-unsupervised-data)
- **Language:** en
<!-- - **License:** Unknown -->
### Model Sources
- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
- **Repository:** [Sentence Transformers on GitHub](https://github.com/huggingface/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': 1024, 'do_lower_case': False, 'architecture': 'ModernBertModel'})
(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})
)
```
## 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
queries = [
"Where do you guys go to find used camper shells?",
]
documents = [
"I've got a newly acquired 1st gen 2005 silvee Toyota tundra trd and am looking for an used camper shell. Craigslist hasnt been very useful....where do you guys go?\n\nThanks!",
"I work at a convenience store and the number of Newports I sell a day is insane. Considering buying a couple cartons of em and maybe some parliament menthols if the FDA goes through with this. Should be able to throw em up on craigslist or ebay a week or two later and it'll be like steaks in a piranha pond",
"Hey guys what is the most optimal tool for pulling long staples out from hardwood flooring? I'm trying to find the most optimal way to do it because I have thousands to pull! Fence pliers did not work too well on account the pointy tip was too thick get in and roll them out and when i tried the gripping/cutting part it broke the staples.\n\nI'm thinking round nose vice grips or a car gasket puller?\n\nThanks",
]
query_embeddings = model.encode_query(queries)
document_embeddings = model.encode_document(documents)
print(query_embeddings.shape, document_embeddings.shape)
# [1, 768] [3, 768]
# Get the similarity scores for the embeddings
similarities = model.similarity(query_embeddings, document_embeddings)
print(similarities)
# tensor([[0.8108, 0.2481, 0.1200]])
```
<!--
### 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
#### nomic-embed-unsupervised-data
* Dataset: [nomic-embed-unsupervised-data](https://huggingface.co/datasets/nomic-ai/nomic-embed-unsupervised-data) at [917bae6](https://huggingface.co/datasets/nomic-ai/nomic-embed-unsupervised-data/tree/917bae6ed30ebc80fc8c81ba8e3e34558205d6bb)
* Size: 222,490,215 training samples
* Columns: <code>query</code> and <code>document</code>
* Approximate statistics based on the first 1000 samples:
| | query | document |
|:--------|:----------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------|
| type | string | string |
| details | <ul><li>min: 6 tokens</li><li>mean: 16.83 tokens</li><li>max: 62 tokens</li></ul> | <ul><li>min: 12 tokens</li><li>mean: 162.25 tokens</li><li>max: 1024 tokens</li></ul> |
* Samples:
| query | document |
|:--------------------------------------------------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| <code>I became a US citizen early this year and this is going to be my first 4th of July as an American!</code> | <code>Because of the current situation, my citizen oath ceremony felt more like a pick up order... Got my certificate, and no guests allowed, so I couldn’t bring anybody to join my ceremony, also no pictures. <br><br>Anyway... I want to celebrate big time this 4th of July, and I’m already planning it! (Any ideas are super welcome!). I say big time but I just really want to do something fun at home with my family. 😊</code> |
| <code>"The Kingdom of God for Jesus"; I know you guys know how to answer this overrated question.</code> | <code>Basically what we're talking about is that the "kingdom" of god according to jesus are:<br><br>* "the kingdom as good news (where the kingdom is on earth, whereas by living a beautiful, meaningful life on earth is the meaning of salvation)" <br>* "the kingdom is offered to all"<br>* etc.<br><br>and finally, the question goes like this: "The Kingdom Does Not Ask for Performance; It is a gift, an offer. We can only inherit it. So, ***what is the point of being good***?"</code> |
| <code>So I made a "size" chart to go with my weight infograph, all based off that "Relative champ weight/height" thread.</code> | <code>Here's the weight chart I did the other day<br><br><br><br>And here's the size chart I did today. <br><br><br><br>*Anivia, Skarner and Shyvanna (dragon form) are "Dimensions" instead of an actual "height", but I think you can get the jist.<br><br>The original thread this is based off of is located via the link below. I am using these numbers (and my own conversions), so I'm not always sure where they got the numbers!<br><br></code> |
* Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
```json
{
"scale": 20.0,
"similarity_fct": "cos_sim",
"gather_across_devices": false
}
```
### Evaluation Dataset
#### nomic-embed-unsupervised-data
* Dataset: [nomic-embed-unsupervised-data](https://huggingface.co/datasets/nomic-ai/nomic-embed-unsupervised-data) at [917bae6](https://huggingface.co/datasets/nomic-ai/nomic-embed-unsupervised-data/tree/917bae6ed30ebc80fc8c81ba8e3e34558205d6bb)
* Size: 222,727 evaluation samples
* Columns: <code>query</code> and <code>document</code>
* Approximate statistics based on the first 1000 samples:
| | query | document |
|:--------|:----------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------|
| type | string | string |
| details | <ul><li>min: 6 tokens</li><li>mean: 16.41 tokens</li><li>max: 66 tokens</li></ul> | <ul><li>min: 15 tokens</li><li>mean: 164.47 tokens</li><li>max: 1024 tokens</li></ul> |
* Samples:
| query | document |
|:-------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| <code>Do you subscribe to any horror magazines?</code> | <code>I get most of my horror news from blogs and websites and such, but i do subscribe to a bunch of horror mags. With everything being so digital these days, something about flipping through a magazine and reading articles about both classic and upcoming horror movies is refreshing. I get a lot of great recommendations from them, and theres a lot of interesting interviews and behind the scenes stuff that i dont see on the popular websites.</code> |
| <code>Missing PDS Laundry Card :(</code> | <code>This is an absolute long shot but I must've accidentally left my laundry card in the dryer card slot because I cant find it anywhere. If someone found a card in there, please DM me. I've already bought a card but I'd like to have my original card back :(</code> |
| <code>Talking Bad will be terrible</code> | <code>Talking Dead is horrible and this will be to. Chris Hardwick and the cast of random no name celebrities offer nothing new to the discussion. The only good thing about Breaking Bad ending is that Talking Bad will end soon as well.</code> |
* Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
```json
{
"scale": 20.0,
"similarity_fct": "cos_sim",
"gather_across_devices": false
}
```
### Training Hyperparameters
#### Non-Default Hyperparameters
- `eval_strategy`: steps
- `per_device_train_batch_size`: 256
- `per_device_eval_batch_size`: 128
- `learning_rate`: 2e-06
- `num_train_epochs`: 4
- `warmup_ratio`: 0.1
- `bf16`: 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`: 256
- `per_device_eval_batch_size`: 128
- `per_gpu_train_batch_size`: None
- `per_gpu_eval_batch_size`: None
- `gradient_accumulation_steps`: 1
- `eval_accumulation_steps`: None
- `torch_empty_cache_steps`: None
- `learning_rate`: 2e-06
- `weight_decay`: 0.0
- `adam_beta1`: 0.9
- `adam_beta2`: 0.999
- `adam_epsilon`: 1e-08
- `max_grad_norm`: 1.0
- `num_train_epochs`: 4
- `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
- `bf16`: True
- `fp16`: False
- `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`: True
- `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}
- `parallelism_config`: None
- `deepspeed`: None
- `label_smoothing_factor`: 0.0
- `optim`: adamw_torch
- `optim_args`: None
- `adafactor`: False
- `group_by_length`: False
- `length_column_name`: length
- `project`: huggingface
- `trackio_space_id`: trackio
- `ddp_find_unused_parameters`: None
- `ddp_bucket_cap_mb`: None
- `ddp_broadcast_buffers`: False
- `dataloader_pin_memory`: True
- `dataloader_persistent_workers`: False
- `skip_memory_metrics`: True
- `use_legacy_prediction_loop`: False
- `push_to_hub`: False
- `resume_from_checkpoint`: None
- `hub_model_id`: None
- `hub_strategy`: every_save
- `hub_private_repo`: None
- `hub_always_push`: False
- `hub_revision`: None
- `gradient_checkpointing`: False
- `gradient_checkpointing_kwargs`: None
- `include_inputs_for_metrics`: False
- `include_for_metrics`: []
- `eval_do_concat_batches`: True
- `fp16_backend`: auto
- `push_to_hub_model_id`: None
- `push_to_hub_organization`: None
- `mp_parameters`:
- `auto_find_batch_size`: False
- `full_determinism`: False
- `torchdynamo`: None
- `ray_scope`: last
- `ddp_timeout`: 1800
- `torch_compile`: False
- `torch_compile_backend`: None
- `torch_compile_mode`: None
- `include_tokens_per_second`: False
- `include_num_input_tokens_seen`: no
- `neftune_noise_alpha`: None
- `optim_target_modules`: None
- `batch_eval_metrics`: False
- `eval_on_start`: False
- `use_liger_kernel`: False
- `liger_kernel_config`: None
- `eval_use_gather_object`: False
- `average_tokens_across_devices`: True
- `prompts`: None
- `batch_sampler`: no_duplicates
- `multi_dataset_batch_sampler`: proportional
- `router_mapping`: {}
- `learning_rate_mapping`: {}
</details>
### Training Logs
<details><summary>Click to expand</summary>
| Epoch | Step | Training Loss | Validation Loss |
|:------:|:-----:|:-------------:|:---------------:|
| 0.0009 | 100 | 4.4714 | - |
| 0.0018 | 200 | 4.4457 | - |
| 0.0028 | 300 | 4.4007 | - |
| 0.0037 | 400 | 4.336 | - |
| 0.0046 | 500 | 4.2476 | - |
| 0.0055 | 600 | 4.1406 | - |
| 0.0064 | 700 | 4.0049 | - |
| 0.0074 | 800 | 3.8434 | - |
| 0.0083 | 900 | 3.6393 | - |
| 0.0092 | 1000 | 3.3763 | - |
| 0.0101 | 1100 | 3.0541 | - |
| 0.0110 | 1200 | 2.6362 | - |
| 0.0120 | 1300 | 2.1226 | - |
| 0.0129 | 1400 | 1.6113 | - |
| 0.0138 | 1500 | 1.2565 | - |
| 0.0147 | 1600 | 1.029 | - |
| 0.0156 | 1700 | 0.846 | - |
| 0.0166 | 1800 | 0.7111 | - |
| 0.0175 | 1900 | 0.5967 | - |
| 0.0184 | 2000 | 0.488 | - |
| 0.0193 | 2100 | 0.4138 | - |
| 0.0203 | 2200 | 0.3565 | - |
| 0.0212 | 2300 | 0.3129 | - |
| 0.0221 | 2400 | 0.2827 | - |
| 0.0230 | 2500 | 0.2557 | - |
| 0.0239 | 2600 | 0.2379 | - |
| 0.0249 | 2700 | 0.2234 | - |
| 0.0258 | 2800 | 0.2055 | - |
| 0.0267 | 2900 | 0.1926 | - |
| 0.0276 | 3000 | 0.1843 | - |
| 0.0285 | 3100 | 0.175 | - |
| 0.0295 | 3200 | 0.1647 | - |
| 0.0304 | 3300 | 0.157 | - |
| 0.0313 | 3400 | 0.1512 | - |
| 0.0322 | 3500 | 0.146 | - |
| 0.0331 | 3600 | 0.1412 | - |
| 0.0341 | 3700 | 0.1352 | - |
| 0.0350 | 3800 | 0.1295 | - |
| 0.0359 | 3900 | 0.1261 | - |
| 0.0368 | 4000 | 0.122 | - |
| 0.0377 | 4100 | 0.1171 | - |
| 0.0387 | 4200 | 0.1147 | - |
| 0.0396 | 4300 | 0.1103 | - |
| 0.0405 | 4400 | 0.1073 | - |
| 0.0414 | 4500 | 0.1053 | - |
| 0.0423 | 4600 | 0.1016 | - |
| 0.0433 | 4700 | 0.0991 | - |
| 0.0442 | 4800 | 0.0981 | - |
| 0.0451 | 4900 | 0.0935 | - |
| 0.0460 | 5000 | 0.0928 | - |
| 0.0469 | 5100 | 0.0895 | - |
| 0.0479 | 5200 | 0.0877 | - |
| 0.0488 | 5300 | 0.0853 | - |
| 0.0497 | 5400 | 0.0829 | - |
| 0.0506 | 5500 | 0.0818 | - |
| 0.0515 | 5600 | 0.0805 | - |
| 0.0525 | 5700 | 0.0785 | - |
| 0.0534 | 5800 | 0.0769 | - |
| 0.0543 | 5900 | 0.0746 | - |
| 0.0552 | 6000 | 0.0754 | - |
| 0.0562 | 6100 | 0.0715 | - |
| 0.0571 | 6200 | 0.0707 | - |
| 0.0580 | 6300 | 0.0699 | - |
| 0.0589 | 6400 | 0.0678 | - |
| 0.0598 | 6500 | 0.0659 | - |
| 0.0608 | 6600 | 0.0659 | - |
| 0.0617 | 6700 | 0.0646 | - |
| 0.0626 | 6800 | 0.0627 | - |
| 0.0635 | 6900 | 0.0627 | - |
| 0.0644 | 7000 | 0.0604 | - |
| 0.0654 | 7100 | 0.0592 | - |
| 0.0663 | 7200 | 0.059 | - |
| 0.0672 | 7300 | 0.0577 | - |
| 0.0681 | 7400 | 0.0568 | - |
| 0.0690 | 7500 | 0.0558 | - |
| 0.0700 | 7600 | 0.0552 | - |
| 0.0709 | 7700 | 0.0542 | - |
| 0.0718 | 7800 | 0.0531 | - |
| 0.0727 | 7900 | 0.0528 | - |
| 0.0736 | 8000 | 0.0526 | - |
| 0.0746 | 8100 | 0.0509 | - |
| 0.0755 | 8200 | 0.05 | - |
| 0.0764 | 8300 | 0.0495 | - |
| 0.0773 | 8400 | 0.0486 | - |
| 0.0782 | 8500 | 0.0482 | - |
| 0.0792 | 8600 | 0.048 | - |
| 0.0801 | 8700 | 0.0468 | - |
| 0.0810 | 8800 | 0.0461 | - |
| 0.0819 | 8900 | 0.0459 | - |
| 0.0828 | 9000 | 0.0453 | - |
| 0.0838 | 9100 | 0.0442 | - |
| 0.0847 | 9200 | 0.0443 | - |
| 0.0856 | 9300 | 0.0437 | - |
| 0.0865 | 9400 | 0.0435 | - |
| 0.0874 | 9500 | 0.0426 | - |
| 0.0884 | 9600 | 0.042 | - |
| 0.0893 | 9700 | 0.0423 | - |
| 0.0902 | 9800 | 0.0406 | - |
| 0.0911 | 9900 | 0.0405 | - |
| 0.0920 | 10000 | 0.0397 | - |
| 0.0930 | 10100 | 0.0401 | - |
| 0.0939 | 10200 | 0.0392 | - |
| 0.0948 | 10300 | 0.0396 | - |
| 0.0957 | 10400 | 0.0391 | - |
| 0.0967 | 10500 | 0.0384 | - |
| 0.0976 | 10600 | 0.0377 | - |
| 0.0985 | 10700 | 0.0379 | - |
| 0.0994 | 10800 | 0.0372 | - |
| 0.1003 | 10900 | 0.0364 | - |
| 0.1013 | 11000 | 0.0367 | - |
| 0.1022 | 11100 | 0.0359 | - |
| 0.1031 | 11200 | 0.0355 | - |
| 0.1040 | 11300 | 0.0358 | - |
| 0.1049 | 11400 | 0.035 | - |
| 0.1059 | 11500 | 0.0353 | - |
| 0.1068 | 11600 | 0.0341 | - |
| 0.1077 | 11700 | 0.0343 | - |
| 0.1086 | 11800 | 0.034 | - |
| 0.1095 | 11900 | 0.0334 | - |
| 0.1105 | 12000 | 0.0337 | - |
| 0.1114 | 12100 | 0.0332 | - |
| 0.1123 | 12200 | 0.0323 | - |
| 0.1132 | 12300 | 0.0323 | - |
| 0.1141 | 12400 | 0.0322 | - |
| 0.1151 | 12500 | 0.0312 | - |
| 0.1160 | 12600 | 0.0307 | - |
| 0.1169 | 12700 | 0.0314 | - |
| 0.1178 | 12800 | 0.0309 | - |
| 0.1187 | 12900 | 0.0313 | - |
| 0.1197 | 13000 | 0.0306 | - |
| 0.1206 | 13100 | 0.0303 | - |
| 0.1215 | 13200 | 0.0301 | - |
| 0.1224 | 13300 | 0.0302 | - |
| 0.1233 | 13400 | 0.0296 | - |
| 0.1243 | 13500 | 0.029 | - |
| 0.1252 | 13600 | 0.0288 | - |
| 0.1261 | 13700 | 0.0286 | - |
| 0.1270 | 13800 | 0.0291 | - |
| 0.1279 | 13900 | 0.0287 | - |
| 0.1289 | 14000 | 0.0284 | - |
| 0.1298 | 14100 | 0.0276 | - |
| 0.1307 | 14200 | 0.028 | - |
| 0.1316 | 14300 | 0.0275 | - |
| 0.1326 | 14400 | 0.0269 | - |
| 0.1335 | 14500 | 0.027 | - |
| 0.1344 | 14600 | 0.0273 | - |
| 0.1353 | 14700 | 0.0267 | - |
| 0.1362 | 14800 | 0.0263 | - |
| 0.1372 | 14900 | 0.0264 | - |
| 0.1381 | 15000 | 0.0263 | - |
| 0.1390 | 15100 | 0.0262 | - |
| 0.1399 | 15200 | 0.0256 | - |
| 0.1408 | 15300 | 0.0254 | - |
| 0.1418 | 15400 | 0.0257 | - |
| 0.1427 | 15500 | 0.0251 | - |
| 0.1436 | 15600 | 0.0253 | - |
| 0.1445 | 15700 | 0.0247 | - |
| 0.1454 | 15800 | 0.0251 | - |
| 0.1464 | 15900 | 0.0245 | - |
| 0.1473 | 16000 | 0.0246 | - |
| 0.1482 | 16100 | 0.024 | - |
| 0.1491 | 16200 | 0.0241 | - |
| 0.1500 | 16300 | 0.0243 | - |
| 0.1510 | 16400 | 0.0235 | - |
| 0.1519 | 16500 | 0.024 | - |
| 0.1528 | 16600 | 0.0236 | - |
| 0.1537 | 16700 | 0.0233 | - |
| 0.1546 | 16800 | 0.0237 | - |
| 0.1556 | 16900 | 0.023 | - |
| 0.1565 | 17000 | 0.0233 | - |
| 0.1574 | 17100 | 0.0229 | - |
| 0.1583 | 17200 | 0.0227 | - |
| 0.1592 | 17300 | 0.023 | - |
| 0.1602 | 17400 | 0.0232 | - |
| 0.1611 | 17500 | 0.0221 | - |
| 0.1620 | 17600 | 0.0217 | - |
| 0.1629 | 17700 | 0.0224 | - |
| 0.1638 | 17800 | 0.0217 | - |
| 0.1648 | 17900 | 0.0219 | - |
| 0.1657 | 18000 | 0.0216 | - |
| 0.1666 | 18100 | 0.0214 | - |
| 0.1675 | 18200 | 0.0213 | - |
| 0.1685 | 18300 | 0.0215 | - |
| 0.1694 | 18400 | 0.0211 | - |
| 0.1703 | 18500 | 0.0213 | - |
| 0.1712 | 18600 | 0.0211 | - |
| 0.1721 | 18700 | 0.0212 | - |
| 0.1731 | 18800 | 0.0204 | - |
| 0.1740 | 18900 | 0.0206 | - |
| 0.1749 | 19000 | 0.021 | - |
| 0.1758 | 19100 | 0.0208 | - |
| 0.1767 | 19200 | 0.0202 | - |
| 0.1777 | 19300 | 0.0199 | - |
| 0.1786 | 19400 | 0.0204 | - |
| 0.1795 | 19500 | 0.0199 | - |
| 0.1804 | 19600 | 0.0196 | - |
| 0.1813 | 19700 | 0.0198 | - |
| 0.1823 | 19800 | 0.0199 | - |
| 0.1832 | 19900 | 0.0194 | - |
| 0.1841 | 20000 | 0.0191 | - |
| 0.1850 | 20100 | 0.0193 | - |
| 0.1859 | 20200 | 0.0193 | - |
| 0.1869 | 20300 | 0.0192 | - |
| 0.1878 | 20400 | 0.0192 | - |
| 0.1887 | 20500 | 0.0188 | - |
| 0.1896 | 20600 | 0.0183 | - |
| 0.1905 | 20700 | 0.0186 | - |
| 0.1915 | 20800 | 0.0182 | - |
| 0.1924 | 20900 | 0.0184 | - |
| 0.1933 | 21000 | 0.0187 | - |
| 0.1942 | 21100 | 0.0184 | - |
| 0.1951 | 21200 | 0.0183 | - |
| 0.1961 | 21300 | 0.0181 | - |
| 0.1970 | 21400 | 0.0178 | - |
| 0.1979 | 21500 | 0.0179 | - |
| 0.1988 | 21600 | 0.018 | - |
| 0.1997 | 21700 | 0.0185 | - |
| 0.2000 | 21728 | - | 0.0098 |
| 0.2007 | 21800 | 0.0176 | - |
| 0.2016 | 21900 | 0.0183 | - |
| 0.2025 | 22000 | 0.0174 | - |
| 0.2034 | 22100 | 0.0179 | - |
| 0.2044 | 22200 | 0.0175 | - |
| 0.2053 | 22300 | 0.0175 | - |
| 0.2062 | 22400 | 0.0172 | - |
| 0.2071 | 22500 | 0.0173 | - |
| 0.2080 | 22600 | 0.017 | - |
| 0.2090 | 22700 | 0.0167 | - |
| 0.2099 | 22800 | 0.0164 | - |
| 0.2108 | 22900 | 0.0167 | - |
| 0.2117 | 23000 | 0.0165 | - |
| 0.2126 | 23100 | 0.0171 | - |
| 0.2136 | 23200 | 0.0169 | - |
| 0.2145 | 23300 | 0.0164 | - |
| 0.2154 | 23400 | 0.0162 | - |
| 0.2163 | 23500 | 0.0164 | - |
| 0.2172 | 23600 | 0.0164 | - |
| 0.2182 | 23700 | 0.0166 | - |
| 0.2191 | 23800 | 0.0163 | - |
| 0.2200 | 23900 | 0.0164 | - |
| 0.2209 | 24000 | 0.0165 | - |
| 0.2218 | 24100 | 0.0163 | - |
| 0.2228 | 24200 | 0.0162 | - |
| 0.2237 | 24300 | 0.0163 | - |
| 0.2246 | 24400 | 0.0157 | - |
| 0.2255 | 24500 | 0.0157 | - |
| 0.2264 | 24600 | 0.0158 | - |
| 0.2274 | 24700 | 0.0153 | - |
| 0.2283 | 24800 | 0.0156 | - |
| 0.2292 | 24900 | 0.0155 | - |
| 0.2301 | 25000 | 0.0156 | - |
| 0.2310 | 25100 | 0.0154 | - |
| 0.2320 | 25200 | 0.0151 | - |
| 0.2329 | 25300 | 0.0153 | - |
| 0.2338 | 25400 | 0.015 | - |
| 0.2347 | 25500 | 0.0153 | - |
| 0.2356 | 25600 | 0.015 | - |
| 0.2366 | 25700 | 0.0152 | - |
| 0.2375 | 25800 | 0.0147 | - |
| 0.2384 | 25900 | 0.0148 | - |
| 0.2393 | 26000 | 0.0148 | - |
| 0.2402 | 26100 | 0.0144 | - |
| 0.2412 | 26200 | 0.0146 | - |
| 0.2421 | 26300 | 0.0143 | - |
| 0.2430 | 26400 | 0.0143 | - |
| 0.2439 | 26500 | 0.0145 | - |
| 0.2449 | 26600 | 0.0142 | - |
| 0.2458 | 26700 | 0.0142 | - |
| 0.2467 | 26800 | 0.0143 | - |
| 0.2476 | 26900 | 0.0139 | - |
| 0.2485 | 27000 | 0.0141 | - |
| 0.2495 | 27100 | 0.0141 | - |
| 0.2504 | 27200 | 0.0143 | - |
| 0.2513 | 27300 | 0.0141 | - |
| 0.2522 | 27400 | 0.014 | - |
| 0.2531 | 27500 | 0.0137 | - |
| 0.2541 | 27600 | 0.014 | - |
| 0.2550 | 27700 | 0.0139 | - |
| 0.2559 | 27800 | 0.0138 | - |
| 0.2568 | 27900 | 0.0141 | - |
| 0.2577 | 28000 | 0.0138 | - |
| 0.2587 | 28100 | 0.0138 | - |
| 0.2596 | 28200 | 0.0134 | - |
| 0.2605 | 28300 | 0.0135 | - |
| 0.2614 | 28400 | 0.0131 | - |
| 0.2623 | 28500 | 0.0133 | - |
| 0.2633 | 28600 | 0.0132 | - |
| 0.2642 | 28700 | 0.0133 | - |
| 0.2651 | 28800 | 0.0131 | - |
| 0.2660 | 28900 | 0.013 | - |
| 0.2669 | 29000 | 0.0131 | - |
| 0.2679 | 29100 | 0.013 | - |
| 0.2688 | 29200 | 0.0135 | - |
| 0.2697 | 29300 | 0.0131 | - |
| 0.2706 | 29400 | 0.0134 | - |
| 0.2715 | 29500 | 0.0131 | - |
| 0.2725 | 29600 | 0.0129 | - |
| 0.2734 | 29700 | 0.0127 | - |
| 0.2743 | 29800 | 0.0128 | - |
| 0.2752 | 29900 | 0.0125 | - |
| 0.2761 | 30000 | 0.0127 | - |
| 0.2771 | 30100 | 0.0126 | - |
| 0.2780 | 30200 | 0.0124 | - |
| 0.2789 | 30300 | 0.0126 | - |
| 0.2798 | 30400 | 0.0126 | - |
| 0.2808 | 30500 | 0.0122 | - |
| 0.2817 | 30600 | 0.0124 | - |
| 0.2826 | 30700 | 0.0123 | - |
| 0.2835 | 30800 | 0.0126 | - |
| 0.2844 | 30900 | 0.0123 | - |
| 0.2854 | 31000 | 0.012 | - |
| 0.2863 | 31100 | 0.012 | - |
| 0.2872 | 31200 | 0.0123 | - |
| 0.2881 | 31300 | 0.0122 | - |
| 0.2890 | 31400 | 0.0121 | - |
| 0.2900 | 31500 | 0.0124 | - |
| 0.2909 | 31600 | 0.0117 | - |
| 0.2918 | 31700 | 0.0118 | - |
| 0.2927 | 31800 | 0.0121 | - |
| 0.2936 | 31900 | 0.0119 | - |
| 0.2946 | 32000 | 0.0115 | - |
| 0.2955 | 32100 | 0.0117 | - |
| 0.2964 | 32200 | 0.012 | - |
| 0.2973 | 32300 | 0.0118 | - |
| 0.2982 | 32400 | 0.0117 | - |
| 0.2992 | 32500 | 0.0119 | - |
| 0.3001 | 32600 | 0.0118 | - |
| 0.3010 | 32700 | 0.0115 | - |
| 0.3019 | 32800 | 0.012 | - |
| 0.3028 | 32900 | 0.0119 | - |
| 0.3038 | 33000 | 0.0113 | - |
| 0.3047 | 33100 | 0.0117 | - |
| 0.3056 | 33200 | 0.0117 | - |
| 0.3065 | 33300 | 0.0113 | - |
| 0.3074 | 33400 | 0.0113 | - |
| 0.3084 | 33500 | 0.0113 | - |
| 0.3093 | 33600 | 0.0117 | - |
| 0.3102 | 33700 | 0.0111 | - |
| 0.3111 | 33800 | 0.0112 | - |
| 0.3120 | 33900 | 0.0113 | - |
| 0.3130 | 34000 | 0.0111 | - |
| 0.3139 | 34100 | 0.0113 | - |
| 0.3148 | 34200 | 0.0115 | - |
| 0.3157 | 34300 | 0.0114 | - |
| 0.3167 | 34400 | 0.0109 | - |
| 0.3176 | 34500 | 0.0112 | - |
| 0.3185 | 34600 | 0.0109 | - |
| 0.3194 | 34700 | 0.011 | - |
| 0.3203 | 34800 | 0.0108 | - |
| 0.3213 | 34900 | 0.0108 | - |
| 0.3222 | 35000 | 0.0107 | - |
| 0.3231 | 35100 | 0.0109 | - |
| 0.3240 | 35200 | 0.0108 | - |
| 0.3249 | 35300 | 0.0108 | - |
| 0.3259 | 35400 | 0.0108 | - |
| 0.3268 | 35500 | 0.0105 | - |
| 0.3277 | 35600 | 0.0106 | - |
| 0.3286 | 35700 | 0.0105 | - |
| 0.3295 | 35800 | 0.0104 | - |
| 0.3305 | 35900 | 0.0107 | - |
| 0.3314 | 36000 | 0.0105 | - |
| 0.3323 | 36100 | 0.0103 | - |
| 0.3332 | 36200 | 0.0105 | - |
| 0.3341 | 36300 | 0.0103 | - |
| 0.3351 | 36400 | 0.0107 | - |
| 0.3360 | 36500 | 0.0101 | - |
| 0.3369 | 36600 | 0.0102 | - |
| 0.3378 | 36700 | 0.0102 | - |
| 0.3387 | 36800 | 0.0102 | - |
| 0.3397 | 36900 | 0.01 | - |
| 0.3406 | 37000 | 0.0103 | - |
| 0.3415 | 37100 | 0.0103 | - |
| 0.3424 | 37200 | 0.01 | - |
| 0.3433 | 37300 | 0.0103 | - |
| 0.3443 | 37400 | 0.0103 | - |
| 0.3452 | 37500 | 0.0104 | - |
| 0.3461 | 37600 | 0.0098 | - |
| 0.3470 | 37700 | 0.0099 | - |
| 0.3479 | 37800 | 0.0102 | - |
| 0.3489 | 37900 | 0.0102 | - |
| 0.3498 | 38000 | 0.01 | - |
| 0.3507 | 38100 | 0.0101 | - |
| 0.3516 | 38200 | 0.01 | - |
| 0.3526 | 38300 | 0.0098 | - |
| 0.3535 | 38400 | 0.0097 | - |
| 0.3544 | 38500 | 0.0096 | - |
| 0.3553 | 38600 | 0.01 | - |
| 0.3562 | 38700 | 0.0097 | - |
| 0.3572 | 38800 | 0.0101 | - |
| 0.3581 | 38900 | 0.0099 | - |
| 0.3590 | 39000 | 0.0099 | - |
| 0.3599 | 39100 | 0.01 | - |
| 0.3608 | 39200 | 0.0094 | - |
| 0.3618 | 39300 | 0.0096 | - |
| 0.3627 | 39400 | 0.0095 | - |
| 0.3636 | 39500 | 0.0094 | - |
| 0.3645 | 39600 | 0.0094 | - |
| 0.3654 | 39700 | 0.0094 | - |
| 0.3664 | 39800 | 0.0096 | - |
| 0.3673 | 39900 | 0.0095 | - |
| 0.3682 | 40000 | 0.0096 | - |
| 0.3691 | 40100 | 0.0096 | - |
| 0.3700 | 40200 | 0.0094 | - |
| 0.3710 | 40300 | 0.0093 | - |
| 0.3719 | 40400 | 0.0092 | - |
| 0.3728 | 40500 | 0.0095 | - |
| 0.3737 | 40600 | 0.0091 | - |
| 0.3746 | 40700 | 0.0098 | - |
| 0.3756 | 40800 | 0.0094 | - |
| 0.3765 | 40900 | 0.0092 | - |
| 0.3774 | 41000 | 0.0094 | - |
| 0.3783 | 41100 | 0.0092 | - |
| 0.3792 | 41200 | 0.0093 | - |
| 0.3802 | 41300 | 0.0092 | - |
| 0.3811 | 41400 | 0.0095 | - |
| 0.3820 | 41500 | 0.0094 | - |
| 0.3829 | 41600 | 0.0089 | - |
| 0.3838 | 41700 | 0.009 | - |
| 0.3848 | 41800 | 0.0092 | - |
| 0.3857 | 41900 | 0.009 | - |
| 0.3866 | 42000 | 0.0089 | - |
| 0.3875 | 42100 | 0.0091 | - |
| 0.3884 | 42200 | 0.0087 | - |
| 0.3894 | 42300 | 0.0091 | - |
| 0.3903 | 42400 | 0.0089 | - |
| 0.3912 | 42500 | 0.0089 | - |
| 0.3921 | 42600 | 0.0089 | - |
| 0.3931 | 42700 | 0.0087 | - |
| 0.3940 | 42800 | 0.009 | - |
| 0.3949 | 42900 | 0.0087 | - |
| 0.3958 | 43000 | 0.0089 | - |
| 0.3967 | 43100 | 0.0088 | - |
| 0.3977 | 43200 | 0.0088 | - |
| 0.3986 | 43300 | 0.0089 | - |
| 0.3995 | 43400 | 0.0088 | - |
| 0.4000 | 43456 | - | 0.0047 |
</details>
### Framework Versions
- Python: 3.11.10
- Sentence Transformers: 5.1.2
- Transformers: 4.57.1
- PyTorch: 2.4.1+cu121
- Accelerate: 1.11.0
- Datasets: 4.3.0
- Tokenizers: 0.22.1
## 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",
}
```
#### MultipleNegativesRankingLoss
```bibtex
@misc{henderson2017efficient,
title={Efficient Natural Language Response Suggestion for Smart Reply},
author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil},
year={2017},
eprint={1705.00652},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
```
<!--
## 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.*
-->