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 Google Gemini's recent feature compare to ChatGPT's live video
      option?
    sentences:
      - >-
        The environmental impact got much, much worse

        The much bigger problem here is the enormous competitive buildout of the
        infrastructure that is imagined to be necessary for these models in the
        future.

        Companies like Google, Meta, Microsoft and Amazon are all spending
        billions of dollars rolling out new datacenters, with a very material
        impact on the electricity grid and the environment. There’s even talk of
        spinning up new nuclear power stations, but those can take decades.

        Is this infrastructure necessary? DeepSeek v3’s $6m training cost and
        the continued crash in LLM prices might hint that it’s not. But would
        you want to be the big tech executive that argued NOT to build out this
        infrastructure only to be proven wrong in a few years’ time?
      - >-
        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.
      - >-
        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.
  - source_sentence: >-
      What are the potential environmental impacts of the competitive buildout
      of infrastructure by major tech companies?
    sentences:
      - >-
        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
      - >-
        The environmental impact got much, much worse

        The much bigger problem here is the enormous competitive buildout of the
        infrastructure that is imagined to be necessary for these models in the
        future.

        Companies like Google, Meta, Microsoft and Amazon are all spending
        billions of dollars rolling out new datacenters, with a very material
        impact on the electricity grid and the environment. There’s even talk of
        spinning up new nuclear power stations, but those can take decades.

        Is this infrastructure necessary? DeepSeek v3’s $6m training cost and
        the continued crash in LLM prices might hint that it’s not. But would
        you want to be the big tech executive that argued NOT to build out this
        infrastructure only to be proven wrong in a few years’ time?
      - >-
        7th: Prompts.js


        9th: I can now run a GPT-4 class model on my laptop


        10th: ChatGPT Canvas can make API requests now, but it’s complicated


        11th: Gemini 2.0 Flash: An outstanding multi-modal LLM with a sci-fi
        streaming mode


        19th: Building Python tools with a one-shot prompt using uv run and
        Claude Projects


        19th: Gemini 2.0 Flash “Thinking mode”


        20th: December in LLMs has been a lot


        20th: Live blog: the 12th day of OpenAI—“Early evals for OpenAI o3”


        24th: Trying out QvQ—Qwen’s new visual reasoning model


        31st: Things we learned about LLMs in 2024





        (This list generated using Django SQL Dashboard with a SQL query written
        for me by Claude.)
  - source_sentence: >-
      What are some of the capabilities of Large Language Models (LLMs)
      mentioned in the context?
    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:
      - >-
        Here’s the sequel to this post: Things we learned about LLMs in 2024.

        Large Language Models

        In the past 24-36 months, our species has discovered that you can take a
        GIANT corpus of text, run it through a pile of GPUs, and use it to
        create a fascinating new kind of software.

        LLMs can do a lot of things. They can answer questions, summarize
        documents, translate from one language to another, extract information
        and even write surprisingly competent code.

        They can also help you cheat at your homework, generate unlimited
        streams of fake content and be used for all manner of nefarious
        purposes.
      - >-
        24th: Notes on the new Claude analysis JavaScript code execution tool


        27th: Run a prompt to generate and execute jq programs using llm-jq


        29th: You can now run prompts against images, audio and video in your
        terminal using LLM


        30th: W̶e̶e̶k̶n̶o̶t̶e̶s̶  Monthnotes for October




        November


        4th: Claude 3.5 Haiku


        7th: Project: VERDAD—tracking misinformation in radio broadcasts using
        Gemini 1.5


        12th: Qwen2.5-Coder-32B is an LLM that can code well that runs on my Mac


        19th: Notes from Bing Chat—Our First Encounter With Manipulative AI


        25th: Ask questions of SQLite databases and CSV/JSON files in your
        terminal




        December


        4th: First impressions of the new Amazon Nova LLMs (via a new
        llm-bedrock plugin)


        7th: Prompts.js
  - source_sentence: What significant event occurred in 2024 related to the term "slop"?
    sentences:
      - >-
        Then there’s the rest. If you browse the Chatbot Arena leaderboard
        today—still the most useful single place to get a vibes-based evaluation
        of models—you’ll see that GPT-4-0314 has fallen to around 70th place.
        The 18 organizations with higher scoring models are Google, OpenAI,
        Alibaba, Anthropic, Meta, Reka AI, 01 AI, Amazon, Cohere, DeepSeek,
        Nvidia, Mistral, NexusFlow, Zhipu AI, xAI, AI21 Labs, Princeton and
        Tencent.

        Training a GPT-4 beating model was a huge deal in 2023. In 2024 it’s an
        achievement that isn’t even particularly notable, though I personally
        still celebrate any time a new organization joins that list.

        Some of those GPT-4 models run on my laptop
      - |-
        The year of slop
        Synthetic training data works great
        LLMs somehow got even harder to use
        Knowledge is incredibly unevenly distributed
        LLMs need better criticism
        Everything tagged “llms” on my blog in 2024
      - >-
        The year of slop

        2024 was the year that the word "slop" became a term of art. I wrote
        about this in May, expanding on this tweet by @deepfates:
  - source_sentence: >-
      How does the user experience with the default LLM chat UI compare to using
      a more familiar interface?
    sentences:
      - >-
        The models may have got more capable, but most of the limitations
        remained the same. OpenAI’s o1 may finally be able to (mostly) count the
        Rs in strawberry, but its abilities are still limited by its nature as
        an LLM and the constraints placed on it by the harness it’s running in.
        o1 can’t run web searches or use Code Interpreter, but GPT-4o can—both
        in that same ChatGPT UI. (o1 will pretend to do those things if you ask
        it to, a regression to the URL hallucinations bug from early 2023).

        What are we doing about this? Not much. Most users are thrown in at the
        deep end. The default LLM chat UI is like taking brand new computer
        users, dropping them into a Linux terminal and expecting them to figure
        it all out.
      - >-
        I’ve found myself using this a lot. I noticed how much I was relying on
        it in October and wrote Everything I built with Claude Artifacts this
        week, describing 14 little tools I had put together in a seven day
        period.

        Since then, a whole bunch of other teams have built similar systems.
        GitHub announced their version of this—GitHub Spark—in October. Mistral
        Chat added it as a feature called Canvas in November.

        Steve Krouse from Val Town built a version of it against Cerebras,
        showcasing how a 2,000 token/second LLM can iterate on an application
        with changes visible in less than a second.
      - >-
        I think people who complain that LLM improvement has slowed are often
        missing the enormous advances in these multi-modal models. Being able to
        run prompts against images (and audio and video) is a fascinating new
        way to apply these models.

        Voice and live camera mode are science fiction come to life

        The audio and live video modes that have started to emerge deserve a
        special mention.

        The ability to talk to ChatGPT first arrived in September 2023, but it
        was mostly an illusion: OpenAI used their excellent Whisper
        speech-to-text model and a new text-to-speech model (creatively named
        tts-1) to enable conversations with the ChatGPT mobile apps, but the
        actual model just saw text.
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: 0.8333333333333334
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.9583333333333334
            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: 0.8333333333333334
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.3194444444444444
            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: 0.8333333333333334
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.9583333333333334
            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: 0.9228630130990606
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.8972222222222221
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.8972222222222221
            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("melghorab/legal-ft-v0")
# Run inference
sentences = [
    'How does the user experience with the default LLM chat UI compare to using a more familiar interface?',
    'The models may have got more capable, but most of the limitations remained the same. OpenAI’s o1 may finally be able to (mostly) count the Rs in strawberry, but its abilities are still limited by its nature as an LLM and the constraints placed on it by the harness it’s running in. o1 can’t run web searches or use Code Interpreter, but GPT-4o can—both in that same ChatGPT UI. (o1 will pretend to do those things if you ask it to, a regression to the URL hallucinations bug from early 2023).\nWhat are we doing about this? Not much. Most users are thrown in at the deep end. The default LLM chat UI is like taking brand new computer users, dropping them into a Linux terminal and expecting them to figure it all out.',
    'I think people who complain that LLM improvement has slowed are often missing the enormous advances in these multi-modal models. Being able to run prompts against images (and audio and video) is a fascinating new way to apply these models.\nVoice and live camera mode are science fiction come to life\nThe audio and live video modes that have started to emerge deserve a special mention.\nThe ability to talk to ChatGPT first arrived in September 2023, but it was mostly an illusion: OpenAI used their excellent Whisper speech-to-text model and a new text-to-speech model (creatively named tts-1) to enable conversations with the ChatGPT mobile apps, but the actual model just saw text.',
]
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	0.8333
cosine_accuracy@3	0.9583
cosine_accuracy@5	1.0
cosine_accuracy@10	1.0
cosine_precision@1	0.8333
cosine_precision@3	0.3194
cosine_precision@5	0.2
cosine_precision@10	0.1
cosine_recall@1	0.8333
cosine_recall@3	0.9583
cosine_recall@5	1.0
cosine_recall@10	1.0
cosine_ndcg@10	0.9229
cosine_mrr@10	0.8972
cosine_map@100	0.8972

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: 14 tokens
mean: 20.3 tokens
max: 36 tokens

min: 43 tokens
mean: 130.45 tokens
max: 204 tokens

	sentence_0	sentence_1
type	string	string
details	min: 14 tokens mean: 20.3 tokens max: 36 tokens	min: 43 tokens mean: 130.45 tokens max: 204 tokens

Samples:

sentence_0	sentence_1
`What role does synthetic data play in the pretraining of models, particularly in the Phi series?`	`Synthetic data as a substantial component of pretraining is becoming increasingly common, and the Phi series of models has consistently emphasized the importance of synthetic data. Rather than serving as a cheap substitute for organic data, synthetic data has several direct advantages over organic data.`
`How does synthetic data compare to organic data in terms of advantages?`	`Synthetic data as a substantial component of pretraining is becoming increasingly common, and the Phi series of models has consistently emphasized the importance of synthetic data. Rather than serving as a cheap substitute for organic data, synthetic data has several direct advantages over organic data.`
`What analogy is used to describe LLMs in the context provided?`	A drum I’ve been banging for a while is that LLMs are power-user tools—they’re chainsaws disguised as kitchen knives. They look deceptively simple to use—how hard can it be to type messages to a chatbot?—but in reality you need a huge depth of both understanding and experience to make the most of them and avoid their many pitfalls. If anything, this problem got worse in 2024. We’ve built computer systems you can talk to in human language, that will answer your questions and usually get them right! ... depending on the question, and how you ask it, and whether it’s accurately reflected in the undocumented and secret training set.

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	0.9163
2.0	32	0.9330
3.0	48	0.9330
3.125	50	0.9330
4.0	64	0.9067
5.0	80	0.9067
6.0	96	0.9247
6.25	100	0.9247
7.0	112	0.9247
8.0	128	0.9229
9.0	144	0.9229
9.375	150	0.9229
10.0	160	0.9229

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}
}