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 estimated training cost of DeepSeek v3, and how does it
      compare to the training hours used for Llama 31?
    sentences:
      - >-
        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.
      - >-
        DeepSeek v3 is a huge 685B parameter model—one of the largest openly
        licensed models currently available, significantly bigger than the
        largest of Meta’s Llama series, Llama 3.1 405B.

        Benchmarks put it up there with Claude 3.5 Sonnet. Vibe benchmarks (aka
        the Chatbot Arena) currently rank it 7th, just behind the Gemini 2.0 and
        OpenAI 4o/o1 models. This is by far the highest ranking openly licensed
        model.

        The really impressive thing about DeepSeek v3 is the training cost. The
        model was trained on 2,788,000 H800 GPU hours at an estimated cost of
        $5,576,000. Llama 3.1 405B trained 30,840,000 GPU hours—11x that used by
        DeepSeek v3, for a model that benchmarks slightly worse.
      - >-
        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.
  - source_sentence: >-
      How does the launch of ChatGPT Pro impact access to OpenAI's most capable
      model compared to previous offerings?
    sentences:
      - >-
        These abilities are just a few weeks old at this point, and I don’t
        think their impact has been fully felt yet. If you haven’t tried them
        out yet you really should.

        Both Gemini and OpenAI offer API access to these features as well.
        OpenAI started with a WebSocket API that was quite challenging to use,
        but in December they announced a new WebRTC API which is much easier to
        get started with. Building a web app that a user can talk to via voice
        is easy now!

        Prompt driven app generation is a commodity already

        This was possible with GPT-4 in 2023, but the value it provides became
        evident in 2024.
      - >-
        OpenAI made GPT-4o free for all users in May, and Claude 3.5 Sonnet was
        freely available from its launch in June. This was a momentus change,
        because for the previous year free users had mostly been restricted to
        GPT-3.5 level models, meaning new users got a very inaccurate mental
        model of what a capable LLM could actually do.

        That era appears to have ended, likely permanently, with OpenAI’s launch
        of ChatGPT Pro. This $200/month subscription service is the only way to
        access their most capable model, o1 Pro.

        Since the trick behind the o1 series (and the future models it will
        undoubtedly inspire) is to expend more compute time to get better
        results, I don’t think those days of free access to the best available
        models are likely to return.
      - >-
        Intuitively, one would expect that systems this powerful would take
        millions of lines of complex code. Instead, it turns out a few hundred
        lines of Python is genuinely enough to train a basic version!

        What matters most is the training  data. You need a lot of data to make
        these things work, and the quantity and quality of the training data
        appears to be the most important factor in how good the resulting model
        is.

        If you can gather the right data, and afford to pay for the GPUs to
        train it, you can build an LLM.
  - source_sentence: >-
      What are the implications of having a Code Interpreter equivalent for
      fact-checking natural language?
    sentences:
      - >-
        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.
      - >-
        Except... you can run generated code to see if it’s correct. And with
        patterns like ChatGPT Code Interpreter the LLM can execute the code
        itself, process the error message, then rewrite it and keep trying until
        it works!

        So hallucination is a much lesser problem for code generation than for
        anything else. If only we had the equivalent of Code Interpreter for
        fact-checking natural language!

        How should we feel about this as software engineers?

        On the one hand, this feels like a threat: who needs a programmer if
        ChatGPT can write code for you?
      - >-
        The biggest innovation here is that it opens up a new way to scale a
        model: instead of improving model performance purely through additional
        compute at training time, models can now take on harder problems by
        spending more compute on inference.

        The sequel to o1, o3 (they skipped “o2” for European trademark reasons)
        was announced on 20th December with an impressive result against the
        ARC-AGI benchmark, albeit one that likely involved more than $1,000,000
        of compute time expense!

        o3 is expected to ship in January. I doubt many people have real-world
        problems that would benefit from that level of compute expenditure—I
        certainly don’t!—but it appears to be a genuine next step in LLM
        architecture for taking on much harder problems.
  - source_sentence: >-
      What advantages does a 64GB Mac have for running models compared to other
      machines?
    sentences:
      - >-
        My personal laptop is a 64GB M2 MacBook Pro from 2023. It’s a powerful
        machine, but it’s also nearly two years old now—and crucially it’s the
        same laptop I’ve been using ever since I first ran an LLM on my computer
        back in March 2023 (see Large language models are having their Stable
        Diffusion moment).

        That same laptop that could just about run a GPT-3-class model in March
        last year has now run multiple GPT-4 class models! Some of my notes on
        that:
      - >-
        This prompt-driven custom interface feature is so powerful and easy to
        build (once you’ve figured out the gnarly details of browser sandboxing)
        that I expect it to show up as a feature in a wide range of products in
        2025.

        Universal access to the best models lasted for just a few short months

        For a few short months this year all three of the best available
        models—GPT-4o, Claude 3.5 Sonnet and Gemini 1.5 Pro—were freely
        available to most of the world.
      - >-
        On paper, a 64GB Mac should be a great machine for running models due to
        the way the CPU and GPU can share the same memory. In practice, many
        models are released as model weights and libraries that reward NVIDIA’s
        CUDA over other platforms.

        The llama.cpp ecosystem helped a lot here, but the real breakthrough has
        been Apple’s MLX library, “an array framework for Apple Silicon”. It’s
        fantastic.

        Apple’s mlx-lm Python library supports running a wide range of
        MLX-compatible models on my Mac, with excellent performance.
        mlx-community on Hugging Face offers more than 1,000 models that have
        been converted to the necessary format.
  - source_sentence: >-
      How does Claude enable users to interact with applications generated by
      its system?
    sentences:
      - >-
        We already knew LLMs were spookily good at writing code. If you prompt
        them right, it turns out they can build you a full interactive
        application using HTML, CSS and JavaScript (and tools like React if you
        wire up some extra supporting build mechanisms)—often in a single
        prompt.

        Anthropic kicked this idea into high gear when they released Claude
        Artifacts, a groundbreaking new feature that was initially slightly lost
        in the noise due to being described half way through their announcement
        of the incredible Claude 3.5 Sonnet.

        With Artifacts, Claude can write you an on-demand interactive
        application and then let you use it directly inside the Claude
        interface.

        Here’s my Extract URLs app, entirely generated by Claude:
      - >-
        An interesting point of comparison here could be the way railways rolled
        out around the world in the 1800s. Constructing these required enormous
        investments and had a massive environmental impact, and many of the
        lines that were built turned out to be unnecessary—sometimes multiple
        lines from different companies serving the exact same routes!

        The resulting bubbles contributed to several financial crashes, see
        Wikipedia for Panic of 1873, Panic of 1893, Panic of 1901 and the UK’s
        Railway Mania. They left us with a lot of useful infrastructure and a
        great deal of bankruptcies and environmental damage.

        The year of slop
      - >-
        We don’t yet know how to build GPT-4

        Frustratingly, despite the enormous leaps ahead we’ve had this year, we
        are yet to see an alternative model that’s better than GPT-4.

        OpenAI released GPT-4 in March, though it later turned out we had a
        sneak peak of it in February when Microsoft used it as part of the new
        Bing.

        This may well change in the next few weeks: Google’s Gemini Ultra has
        big claims, but isn’t yet available for us to try out.

        The team behind Mistral are working to beat GPT-4 as well, and their
        track record is already extremely strong considering their first public
        model only came out in September, and they’ve released two significant
        improvements since then.
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: 1
            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: 1
            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: 1
            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: 1
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 1
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 1
            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("llm-wizard/legal-ft-2")
# Run inference
sentences = [
    'How does Claude enable users to interact with applications generated by its system?',
    'We already knew LLMs were spookily good at writing code. If you prompt them right, it turns out they can build you a full interactive application using HTML, CSS and JavaScript (and tools like React if you wire up some extra supporting build mechanisms)—often in a single prompt.\nAnthropic kicked this idea into high gear when they released Claude Artifacts, a groundbreaking new feature that was initially slightly lost in the noise due to being described half way through their announcement of the incredible Claude 3.5 Sonnet.\nWith Artifacts, Claude can write you an on-demand interactive application and then let you use it directly inside the Claude interface.\nHere’s my Extract URLs app, entirely generated by Claude:',
    'We don’t yet know how to build GPT-4\nFrustratingly, despite the enormous leaps ahead we’ve had this year, we are yet to see an alternative model that’s better than GPT-4.\nOpenAI released GPT-4 in March, though it later turned out we had a sneak peak of it in February when Microsoft used it as part of the new Bing.\nThis may well change in the next few weeks: Google’s Gemini Ultra has big claims, but isn’t yet available for us to try out.\nThe team behind Mistral are working to beat GPT-4 as well, and their track record is already extremely strong considering their first public model only came out in September, and they’ve released two significant improvements since then.',
]
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	1.0
cosine_accuracy@3	1.0
cosine_accuracy@5	1.0
cosine_accuracy@10	1.0
cosine_precision@1	1.0
cosine_precision@3	0.3333
cosine_precision@5	0.2
cosine_precision@10	0.1
cosine_recall@1	1.0
cosine_recall@3	1.0
cosine_recall@5	1.0
cosine_recall@10	1.0
cosine_ndcg@10	1.0
cosine_mrr@10	1.0
cosine_map@100	1.0

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: 12 tokens
mean: 20.22 tokens
max: 33 tokens

min: 43 tokens
mean: 134.95 tokens
max: 214 tokens

	sentence_0	sentence_1
type	string	string
details	min: 12 tokens mean: 20.22 tokens max: 33 tokens	min: 43 tokens mean: 134.95 tokens max: 214 tokens

Samples:

sentence_0	sentence_1
`What topics were covered in the annotated presentations given in 2023?`	I also gave a bunch of talks and podcast appearances. I’ve started habitually turning my talks into annotated presentations—here are my best from 2023: Prompt injection explained, with video, slides, and a transcript Catching up on the weird world of LLMs Making Large Language Models work for you Open questions for AI engineering Embeddings: What they are and why they matter Financial sustainability for open source projects at GitHub Universe And in podcasts: What AI can do for you on the Theory of Change Working in public on Path to Citus Con LLMs break the internet on the Changelog Talking Large Language Models on Rooftop Ruby Thoughts on the OpenAI board situation on Newsroom Robots
`Which podcasts featured discussions about Large Language Models?`	I also gave a bunch of talks and podcast appearances. I’ve started habitually turning my talks into annotated presentations—here are my best from 2023: Prompt injection explained, with video, slides, and a transcript Catching up on the weird world of LLMs Making Large Language Models work for you Open questions for AI engineering Embeddings: What they are and why they matter Financial sustainability for open source projects at GitHub Universe And in podcasts: What AI can do for you on the Theory of Change Working in public on Path to Citus Con LLMs break the internet on the Changelog Talking Large Language Models on Rooftop Ruby Thoughts on the OpenAI board situation on Newsroom Robots
`When did Google release their gemini-20-flash-thinking-exp model?`	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.

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	1.0
2.0	32	1.0
3.0	48	1.0
3.125	50	1.0
4.0	64	1.0
5.0	80	1.0
6.0	96	1.0
6.25	100	1.0
7.0	112	1.0
8.0	128	1.0
9.0	144	1.0
9.375	150	1.0
10.0	160	1.0

Framework Versions

Python: 3.13.1
Sentence Transformers: 3.4.1
Transformers: 4.48.3
PyTorch: 2.6.0+cu124
Accelerate: 1.3.0
Datasets: 3.2.0
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}
}