README.md

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: How does the size of DeepSeek v3 compare to Meta’s Llama 31 405B model?
    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.
      - >-
        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.
      - >-
        Against this photo of butterflies at the California Academy of Sciences:



        A shallow dish, likely a hummingbird or butterfly feeder, is red. 
        Pieces of orange slices of fruit are visible inside the dish.

        Two butterflies are positioned in the feeder, one is a dark brown/black
        butterfly with white/cream-colored markings.  The other is a large,
        brown butterfly with patterns of lighter brown, beige, and black
        markings, including prominent eye spots. The larger brown butterfly
        appears to be feeding on the fruit.
  - source_sentence: >-
      How does the author compare the difficulty of training an LLM to another
      complex task?
    sentences:
      - >-
        “Agents” still haven’t really happened yet

        I find the term “agents” extremely frustrating. It lacks a single, clear
        and widely understood meaning... but the people who use the term never
        seem to acknowledge that.

        If you tell me that you are building “agents”, you’ve conveyed almost no
        information to me at all. Without reading your mind I have no way of
        telling which of the dozens of possible definitions you are talking
        about.
      - >-
        So training an LLM still isn’t something a hobbyist can afford, but it’s
        no longer the sole domain of the super-rich. I like to compare the
        difficulty of training an LLM to that of building a suspension
        bridge—not trivial, but hundreds of countries around the world have
        figured out how to do it. (Correction: Wikipedia’s Suspension bridges by
        country category lists 44 countries).

        You can run LLMs on your own devices

        In January of this year, I thought it would be years before I could run
        a useful LLM on my own computer. GPT-3 and 3.5 were pretty much the only
        games in town, and I thought that even if the model weights were
        available it would take a $10,000+ server to run them.
      - >-
        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.
  - source_sentence: What is the new approach to scaling models mentioned in the context?
    sentences:
      - >-
        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.
      - >-
        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.
      - >-
        Language Models are gullible. They “believe” what we tell them—what’s in
        their training data, then what’s in the fine-tuning data, then what’s in
        the prompt.

        In order to be useful tools for us, we need them to believe what we feed
        them!

        But it turns out a lot of the things we want to build need them not to
        be gullible.

        Everyone wants an AI personal assistant. If you hired a real-world
        personal assistant who believed everything that anyone told them, you
        would quickly find that their ability to positively impact your life was
        severely limited.
  - source_sentence: When was Anthropic’s Claude 3 series initially launched?
    sentences:
      - >-
        Prompt injection is a natural consequence of this gulibility. I’ve seen
        precious little progress on tackling that problem in 2024, and we’ve
        been talking about it since September 2022.

        I’m beginning to see the most popular idea of “agents” as dependent on
        AGI itself. A model that’s robust against gulliblity is a very tall
        order indeed.

        Evals really matter

        Anthropic’s Amanda Askell (responsible for much of the work behind
        Claude’s Character):
      - >-
        A year ago, the only organization that had released a generally useful
        LLM was OpenAI. We’ve now seen better-than-GPT-3 class models produced
        by Anthropic, Mistral, Google, Meta, EleutherAI, Stability AI, TII in
        Abu Dhabi (Falcon), Microsoft Research, xAI, Replit, Baidu and a bunch
        of other organizations.

        The training cost (hardware and electricity) is still
        significant—initially millions of dollars, but that seems to have
        dropped to the tens of thousands already. Microsoft’s Phi-2 claims to
        have used “14 days on 96 A100 GPUs”, which works out at around $35,000
        using current Lambda pricing.
      - >-
        Getting back to models that beat GPT-4: Anthropic’s Claude 3 series
        launched in March, and Claude 3 Opus quickly became my new favourite
        daily-driver. They upped the ante even more in June with the launch of
        Claude 3.5 Sonnet—a model that is still my favourite six months later
        (though it got a significant upgrade on October 22, confusingly keeping
        the same 3.5 version number. Anthropic fans have since taken to calling
        it Claude 3.6).
  - source_sentence: >-
      Why might fine-tuning an existing LLM be more accessible to hobbyists than
      training one from scratch?
    sentences:
      - >-
        I run a bunch of them on my laptop. I run Mistral 7B (a surprisingly
        great model) on my iPhone. You can install several different apps to get
        your own, local, completely private LLM. My own LLM project provides a
        CLI tool for running an array of different models via plugins.

        You can even run them entirely in your browser using WebAssembly and the
        latest Chrome!

        Hobbyists can build their own fine-tuned models

        I said earlier that building an LLM was still out of reach of hobbyists.
        That may be true for training from scratch, but fine-tuning one of those
        models is another matter entirely.
      - >-
        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.
      - >-
        Nothing yet from Anthropic or Meta but I would be very surprised if they
        don’t have their own inference-scaling models in the works. Meta
        published a relevant paper Training Large Language Models to Reason in a
        Continuous Latent Space in December.

        Was the best currently available LLM trained in China for less than $6m?

        Not quite, but almost! It does make for a great attention-grabbing
        headline.

        The big news to end the year was the release of DeepSeek v3—dropped on
        Hugging Face on Christmas Day without so much as a README file, then
        followed by documentation and a paper the day after that.
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: 0.9166666666666666
            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: 0.9166666666666666
            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: 0.9166666666666666
            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: 0.9692441461309548
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.9583333333333334
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.9583333333333334
            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("dwb2023/legal-ft-c53d04b6-ee03-4160-9525-a7af282c08e8")
# Run inference
sentences = [
    'Why might fine-tuning an existing LLM be more accessible to hobbyists than training one from scratch?',
    'I run a bunch of them on my laptop. I run Mistral 7B (a surprisingly great model) on my iPhone. You can install several different apps to get your own, local, completely private LLM. My own LLM project provides a CLI tool for running an array of different models via plugins.\nYou can even run them entirely in your browser using WebAssembly and the latest Chrome!\nHobbyists can build their own fine-tuned models\nI said earlier that building an LLM was still out of reach of hobbyists. That may be true for training from scratch, but fine-tuning one of those models is another matter entirely.',
    'Nothing yet from Anthropic or Meta but I would be very surprised if they don’t have their own inference-scaling models in the works. Meta published a relevant paper Training Large Language Models to Reason in a Continuous Latent Space in December.\nWas the best currently available LLM trained in China for less than $6m?\nNot quite, but almost! It does make for a great attention-grabbing headline.\nThe big news to end the year was the release of DeepSeek v3—dropped on Hugging Face on Christmas Day without so much as a README file, then followed by documentation and a paper the day after that.',
]
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	0.9167
cosine_accuracy@3	1.0
cosine_accuracy@5	1.0
cosine_accuracy@10	1.0
cosine_precision@1	0.9167
cosine_precision@3	0.3333
cosine_precision@5	0.2
cosine_precision@10	0.1
cosine_recall@1	0.9167
cosine_recall@3	1.0
cosine_recall@5	1.0
cosine_recall@10	1.0
cosine_ndcg@10	0.9692
cosine_mrr@10	0.9583
cosine_map@100	0.9583

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: 20.94 tokens max: 32 tokens	min: 43 tokens mean: 135.14 tokens max: 214 tokens

• Samples:

  sentence_0	sentence_1
  When did Meta release the original Llama model?	Then in February, Meta released Llama. And a few weeks later in March, Georgi Gerganov released code that got it working on a MacBook. I wrote about how Large language models are having their Stable Diffusion moment, and with hindsight that was a very good call! This unleashed a whirlwind of innovation, which was accelerated further in July when Meta released Llama 2—an improved version which, crucially, included permission for commercial use. Today there are literally thousands of LLMs that can be run locally, on all manner of different devices.
  What was significant about the release of Llama 2 in July?	Then in February, Meta released Llama. And a few weeks later in March, Georgi Gerganov released code that got it working on a MacBook. I wrote about how Large language models are having their Stable Diffusion moment, and with hindsight that was a very good call! This unleashed a whirlwind of innovation, which was accelerated further in July when Meta released Llama 2—an improved version which, crucially, included permission for commercial use. Today there are literally thousands of LLMs that can be run locally, on all manner of different devices.
  What are some companies mentioned that have developed multi-modal audio models?	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.

• 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}
• tp_size: 0
• 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
• 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	0.9638
2.0	32	0.9638
3.0	48	0.9692
3.125	50	0.9692
4.0	64	0.9692
5.0	80	0.9539
6.0	96	0.9539
6.25	100	0.9539
7.0	112	0.9539
8.0	128	0.9539
9.0	144	0.9692
9.375	150	0.9692
10.0	160	0.9692

Framework Versions

• Python: 3.11.12
• Sentence Transformers: 4.1.0
• Transformers: 4.51.3
• PyTorch: 2.6.0+cu124
• Accelerate: 1.6.0
• Datasets: 3.5.1
• Tokenizers: 0.21.1

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}
}