metadata

tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - dataset_size:156
  - loss:MatryoshkaLoss
  - loss:MultipleNegativesRankingLoss
base_model: Snowflake/snowflake-arctic-embed-l
widget:
  - source_sentence: >-
      What is the author's perspective on the environmental impact of plagiarism
      machines in the field discussed?
    sentences:
      - >-
        Prince Canuma’s excellent, fast moving mlx-vlm project brings vision
        LLMs to Apple Silicon as well. I used that recently to run Qwen’s QvQ.

        While MLX is a game changer, Apple’s own “Apple Intelligence” features
        have mostly been a disappointment. I wrote about their initial
        announcement in June, and I was optimistic that Apple had focused hard
        on the subset of LLM applications that preserve user privacy and
        minimize the chance of users getting mislead by confusing features.
      - >-
        I think telling people that this whole field is environmentally
        catastrophic plagiarism machines that constantly make things up is doing
        those people a disservice, no matter how much truth that represents.
        There is genuine value to be had here, but getting to that value is
        unintuitive and needs guidance.

        Those of us who understand this stuff have a duty to help everyone else
        figure it out.

        Everything tagged “llms” on my blog in 2024

        Because I undoubtedly missed a whole bunch of things, here’s every
        long-form post I wrote in 2024 that I tagged with llms:
      - >-
        Meanwhile, it’s increasingly common for end users to develop wildly
        inaccurate mental models of how these things work and what they are
        capable of. I’ve seen so many examples of people trying to win an
        argument with a screenshot from ChatGPT—an inherently ludicrous
        proposition, given the inherent unreliability of these models crossed
        with the fact that you can get them to say anything if you prompt them
        right.
  - source_sentence: What is the license under which Alibaba's QwQ model was released?
    sentences:
      - >-
        Those US export regulations on GPUs to China seem to have inspired some
        very effective training optimizations!

        The environmental impact got better

        A welcome result of the increased efficiency of the models—both the
        hosted ones and the ones I can run locally—is that the energy usage and
        environmental impact of running a prompt has dropped enormously over the
        past couple of years.

        OpenAI themselves are charging 100x less for a prompt compared to the
        GPT-3 days. I have it on good authority that neither Google Gemini nor
        Amazon Nova (two of the least expensive model providers) are running
        prompts at a loss.
      - >-
        OpenAI are not the only game in town here. Google released their first
        entrant in the category, gemini-2.0-flash-thinking-exp, on December
        19th.

        Alibaba’s Qwen team released their QwQ model on November 28th—under an
        Apache 2.0 license, and that one I could run on my own machine. They
        followed that up with a vision reasoning model called QvQ on December
        24th, which I also ran locally.

        DeepSeek made their DeepSeek-R1-Lite-Preview model available to try out
        through their chat interface on November 20th.

        To understand more about inference scaling I recommend Is AI progress
        slowing down? by Arvind Narayanan and Sayash Kapoor.
      - >-
        The boring yet crucial secret behind good system prompts is test-driven
        development. You don’t write down a system prompt and find ways to test
        it. You write down tests and find a system prompt that passes them.


        It’s become abundantly clear over the course of 2024 that writing good
        automated evals for LLM-powered systems is the skill that’s most needed
        to build useful applications on top of these models. If you have a
        strong eval suite you can adopt new models faster, iterate better and
        build more reliable and useful product features than your competition.

        Vercel’s Malte Ubl:
  - source_sentence: >-
      How do longer inputs enhance the problem-solving capabilities of an LLM
      compared to shorter prompts?
    sentences:
      - >-
        19th: Weeknotes: GPT-4o mini, LLM 0.15, sqlite-utils 3.37 and building a
        staging environment




        August


        6th: Weeknotes: a staging environment, a Datasette alpha and a bunch of
        new LLMs


        8th: django-http-debug, a new Django app mostly written by Claude


        23rd: Claude’s API now supports CORS requests, enabling client-side
        applications


        26th: Building a tool showing how Gemini Pro can return bounding boxes
        for objects in images




        September


        6th: Calling LLMs from client-side JavaScript, converting PDFs to HTML +
        weeknotes


        10th: Notes from my appearance on the Software Misadventures Podcast


        12th: Notes on OpenAI’s new o1 chain-of-thought models


        20th: Notes on using LLMs for code
      - >-
        Longer inputs dramatically increase the scope of problems that can be
        solved with an LLM: you can now throw in an entire book and ask
        questions about its contents, but more importantly you can feed in a lot
        of example code to help the model correctly solve a coding problem. LLM
        use-cases that involve long inputs are far more interesting to me than
        short prompts that rely purely on the information already baked into the
        model weights. Many of my tools were built using this pattern.
      - >-
        The most recent twist, again from December (December was a lot) is live
        video. ChatGPT voice mode now provides the option to share your camera
        feed with the model and talk about what you can see in real time. Google
        Gemini have a preview of the same feature, which they managed to ship
        the day before ChatGPT did.
  - source_sentence: >-
      What capabilities does Google’s Gemini have regarding audio input and
      output?
    sentences:
      - >-
        Terminology aside, I remain skeptical as to their utility based, once
        again, on the challenge of gullibility. LLMs believe anything you tell
        them. Any systems that attempts to make meaningful decisions on your
        behalf will run into the same roadblock: how good is a travel agent, or
        a digital assistant, or even a research tool if it can’t distinguish
        truth from fiction?

        Just the other day Google Search was caught serving up an entirely fake
        description of the non-existant movie “Encanto 2”. It turned out to be
        summarizing an imagined movie listing from a fan fiction wiki.
      - >-
        Watching in real time as “slop” becomes a term of art. the way that
        “spam” became the term for unwanted emails, “slop” is going in the
        dictionary as the term for unwanted AI generated content


        I expanded that definition a tiny bit to this:


        Slop describes AI-generated content that is both unrequested and
        unreviewed.


        I ended up getting quoted talking about slop in both the Guardian and
        the NY Times. Here’s what I said in the NY TImes:


        Society needs concise ways to talk about modern A.I. — both the
        positives and the negatives. ‘Ignore that email, it’s spam,’ and ‘Ignore
        that article, it’s slop,’ are both useful lessons.
      - >-
        Your browser does not support the audio element.


        OpenAI aren’t the only group with a multi-modal audio model. Google’s
        Gemini also accepts audio input, and the Google Gemini apps can speak in
        a similar way to ChatGPT now. Amazon also pre-announced voice mode for
        Amazon Nova, but that’s meant to roll out in Q1 of 2025.

        Google’s NotebookLM, released in September, took audio output to a new
        level by producing spookily realistic conversations between two “podcast
        hosts” about anything you fed into their tool. They later added custom
        instructions, so naturally I turned them into pelicans:



        Your browser does not support the audio element.
  - source_sentence: >-
      How does the context compare a prompt without evals, models, and UX to an
      ASML machine?
    sentences:
      - >-
        When @v0 first came out we were paranoid about protecting the prompt
        with all kinds of pre and post processing complexity.

        We completely pivoted to let it rip. A prompt without the evals, models,
        and especially UX is like getting a broken ASML machine without a manual
      - >-
        I’m still trying to figure out the best patterns for doing this for my
        own work. Everyone knows that evals are important, but there remains a
        lack of great guidance for how to best implement them—I’m tracking this
        under my evals tag. My SVG pelican riding a bicycle benchmark is a pale
        imitation of what a real eval suite should look like.

        Apple Intelligence is bad, Apple’s MLX library is excellent

        As a Mac user I’ve been feeling a lot better about my choice of platform
        this year.

        Last year it felt like my lack of a Linux/Windows  machine with an
        NVIDIA GPU was a huge disadvantage in terms of trying out new models.
      - >-
        That’s a total cost of $1.68 to process 68,000 images. That’s so
        absurdly cheap I had to run the numbers three times to confirm I got it
        right.

        How good are those descriptions? Here’s what I got from this command:

        llm -m gemini-1.5-flash-8b-latest describe -a IMG_1825.jpeg
pipeline_tag: sentence-similarity
library_name: sentence-transformers
metrics:
  - cosine_accuracy@1
  - cosine_accuracy@3
  - cosine_accuracy@5
  - cosine_accuracy@10
  - cosine_precision@1
  - cosine_precision@3
  - cosine_precision@5
  - cosine_precision@10
  - cosine_recall@1
  - cosine_recall@3
  - cosine_recall@5
  - cosine_recall@10
  - cosine_ndcg@10
  - cosine_mrr@10
  - cosine_map@100
model-index:
  - name: SentenceTransformer based on Snowflake/snowflake-arctic-embed-l
    results:
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: Unknown
          type: unknown
        metrics:
          - type: cosine_accuracy@1
            value: 0.875
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 1
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 1
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 1
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.875
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.3333333333333333
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.20000000000000004
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.10000000000000002
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.875
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 1
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 1
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 1
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.9429554063988107
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.923611111111111
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.923611111111111
            name: Cosine Map@100

SentenceTransformer based on Snowflake/snowflake-arctic-embed-l

This is a sentence-transformers model finetuned from Snowflake/snowflake-arctic-embed-l. 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: Snowflake/snowflake-arctic-embed-l
Maximum Sequence Length: 512 tokens
Output Dimensionality: 1024 dimensions
Similarity Function: Cosine Similarity

Model Sources

Documentation: Sentence Transformers Documentation
Repository: Sentence Transformers on GitHub
Hugging Face: Sentence Transformers on Hugging Face

Full Model Architecture

SentenceTransformer(
  (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel 
  (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})
  (2): Normalize()
)

Usage

Direct Usage (Sentence Transformers)

First install the Sentence Transformers library:

pip install -U sentence-transformers

Then you can load this model and run inference.

from sentence_transformers import SentenceTransformer

# Download from the 🤗 Hub
model = SentenceTransformer("philocifer/legal-ft-2")
# Run inference
sentences = [
    'How does the context compare a prompt without evals, models, and UX to an ASML machine?',
    'When @v0 first came out we were paranoid about protecting the prompt with all kinds of pre and post processing complexity.\nWe completely pivoted to let it rip. A prompt without the evals, models, and especially UX is like getting a broken ASML machine without a manual',
    'That’s a total cost of $1.68 to process 68,000 images. That’s so absurdly cheap I had to run the numbers three times to confirm I got it right.\nHow good are those descriptions? Here’s what I got from this command:\nllm -m gemini-1.5-flash-8b-latest describe -a IMG_1825.jpeg',
]
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]

Evaluation

Metrics

Information Retrieval

Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.875
cosine_accuracy@3	1.0
cosine_accuracy@5	1.0
cosine_accuracy@10	1.0
cosine_precision@1	0.875
cosine_precision@3	0.3333
cosine_precision@5	0.2
cosine_precision@10	0.1
cosine_recall@1	0.875
cosine_recall@3	1.0
cosine_recall@5	1.0
cosine_recall@10	1.0
cosine_ndcg@10	0.943
cosine_mrr@10	0.9236
cosine_map@100	0.9236

Training Details

Training Dataset

Unnamed Dataset

Size: 156 training samples
Columns: sentence_0 and sentence_1
Approximate statistics based on the first 156 samples:
sentence_0 sentence_1
type string string
details
min: 13 tokens
mean: 20.07 tokens
max: 33 tokens

min: 43 tokens
mean: 130.53 tokens
max: 204 tokens

	sentence_0	sentence_1
type	string	string
details	min: 13 tokens mean: 20.07 tokens max: 33 tokens	min: 43 tokens mean: 130.53 tokens max: 204 tokens

Samples:

sentence_0	sentence_1
`What are some ways the author has used LLMs to improve productivity and entertainment?`	So far, I think they’re a net positive. I’ve used them on a personal level to improve my productivity (and entertain myself) in all sorts of different ways. I think people who learn how to use them effectively can gain a significant boost to their quality of life. A lot of people are yet to be sold on their value! Some think their negatives outweigh their positives, some think they are all hot air, and some even think they represent an existential threat to humanity. They’re actually quite easy to build The most surprising thing we’ve learned about LLMs this year is that they’re actually quite easy to build.
`What concerns do some people have regarding the value and impact of LLMs?`	So far, I think they’re a net positive. I’ve used them on a personal level to improve my productivity (and entertain myself) in all sorts of different ways. I think people who learn how to use them effectively can gain a significant boost to their quality of life. A lot of people are yet to be sold on their value! Some think their negatives outweigh their positives, some think they are all hot air, and some even think they represent an existential threat to humanity. They’re actually quite easy to build The most surprising thing we’ve learned about LLMs this year is that they’re actually quite easy to build.
`What improvements were noted in the intonation of ChatGPT Advanced Voice mode during its rollout?`	When ChatGPT Advanced Voice mode finally did roll out (a slow roll from August through September) it was spectacular. I’ve been using it extensively on walks with my dog and it’s amazing how much the improvement in intonation elevates the material. I’ve also had a lot of fun experimenting with the OpenAI audio APIs. Even more fun: Advanced Voice mode can do accents! Here’s what happened when I told it I need you to pretend to be a California brown pelican with a very thick Russian accent, but you talk to me exclusively in Spanish.

Loss: MatryoshkaLoss with these parameters:

{
    "loss": "MultipleNegativesRankingLoss",
    "matryoshka_dims": [
        768,
        512,
        256,
        128,
        64
    ],
    "matryoshka_weights": [
        1,
        1,
        1,
        1,
        1
    ],
    "n_dims_per_step": -1
}

Training Hyperparameters

Non-Default Hyperparameters

eval_strategy: steps
per_device_train_batch_size: 10
per_device_eval_batch_size: 10
num_train_epochs: 10
multi_dataset_batch_sampler: round_robin

All Hyperparameters

Click to expand

overwrite_output_dir: False
do_predict: False
eval_strategy: steps
prediction_loss_only: True
per_device_train_batch_size: 10
per_device_eval_batch_size: 10
per_gpu_train_batch_size: None
per_gpu_eval_batch_size: None
gradient_accumulation_steps: 1
eval_accumulation_steps: None
torch_empty_cache_steps: None
learning_rate: 5e-05
weight_decay: 0.0
adam_beta1: 0.9
adam_beta2: 0.999
adam_epsilon: 1e-08
max_grad_norm: 1
num_train_epochs: 10
max_steps: -1
lr_scheduler_type: linear
lr_scheduler_kwargs: {}
warmup_ratio: 0.0
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: 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: False
dataloader_num_workers: 0
dataloader_prefetch_factor: None
past_index: -1
disable_tqdm: False
remove_unused_columns: True
label_names: None
load_best_model_at_end: False
ignore_data_skip: False
fsdp: []
fsdp_min_num_params: 0
fsdp_config: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
fsdp_transformer_layer_cls_to_wrap: None
accelerator_config: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
deepspeed: None
label_smoothing_factor: 0.0
optim: adamw_torch
optim_args: None
adafactor: False
group_by_length: False
length_column_name: length
ddp_find_unused_parameters: None
ddp_bucket_cap_mb: None
ddp_broadcast_buffers: False
dataloader_pin_memory: True
dataloader_persistent_workers: False
skip_memory_metrics: True
use_legacy_prediction_loop: False
push_to_hub: False
resume_from_checkpoint: None
hub_model_id: None
hub_strategy: every_save
hub_private_repo: None
hub_always_push: False
gradient_checkpointing: False
gradient_checkpointing_kwargs: None
include_inputs_for_metrics: False
include_for_metrics: []
eval_do_concat_batches: True
fp16_backend: auto
push_to_hub_model_id: None
push_to_hub_organization: None
mp_parameters:
auto_find_batch_size: False
full_determinism: False
torchdynamo: None
ray_scope: last
ddp_timeout: 1800
torch_compile: False
torch_compile_backend: None
torch_compile_mode: None
dispatch_batches: None
split_batches: None
include_tokens_per_second: False
include_num_input_tokens_seen: False
neftune_noise_alpha: None
optim_target_modules: None
batch_eval_metrics: False
eval_on_start: False
use_liger_kernel: False
eval_use_gather_object: False
average_tokens_across_devices: False
prompts: None
batch_sampler: batch_sampler
multi_dataset_batch_sampler: round_robin

Training Logs

Epoch	Step	cosine_ndcg@10
1.0	16	0.9276
2.0	32	0.9330
3.0	48	0.9301
3.125	50	0.9301
4.0	64	0.9372
5.0	80	0.9401
6.0	96	0.9401
6.25	100	0.9401
7.0	112	0.9430
8.0	128	0.9484
9.0	144	0.9430
9.375	150	0.9430
10.0	160	0.9430

Framework Versions

Python: 3.11.11
Sentence Transformers: 3.4.1
Transformers: 4.48.3
PyTorch: 2.5.1+cu124
Accelerate: 1.3.0
Datasets: 3.3.0
Tokenizers: 0.21.0

Citation

BibTeX

Sentence Transformers

@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",
}

MatryoshkaLoss

@misc{kusupati2024matryoshka,
    title={Matryoshka Representation Learning},
    author={Aditya Kusupati and Gantavya Bhatt and Aniket Rege and Matthew Wallingford and Aditya Sinha and Vivek Ramanujan and William Howard-Snyder and Kaifeng Chen and Sham Kakade and Prateek Jain and Ali Farhadi},
    year={2024},
    eprint={2205.13147},
    archivePrefix={arXiv},
    primaryClass={cs.LG}
}

MultipleNegativesRankingLoss

@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}
}