metadata

base_model: dbourget/pb-ds1-48K
datasets: []
language: []
library_name: sentence-transformers
metrics:
  - pearson_cosine
  - spearman_cosine
  - pearson_manhattan
  - spearman_manhattan
  - pearson_euclidean
  - spearman_euclidean
  - pearson_dot
  - spearman_dot
  - pearson_max
  - spearman_max
pipeline_tag: sentence-similarity
tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - dataset_size:106810
  - loss:CosineSimilarityLoss
widget:
  - source_sentence: >-
      In  The Law of Civilization and Decay,  Brooks provides a detailed look at
      the rise and fall of civilizations, offering a critical perspective on the
      impact of capitalism. As societies become prosperous, their pursuit of
      wealth ultimately leads to their own downfall as greed takes over.
    sentences:
      - >-
        Patrick Todd's The Open Future argues that all future contingent
        statements, such as 'It will rain tomorrow', are inherently false.
      - >-
        If propositions are made true in virtue of corresponding to facts, then
        what are the truth-makers of true negative propositions such as ‘The
        apple is not red’? Russell argued that there must be negative facts to
        account for what makes true negative propositions true and false
        positive propositions false. Others, more parsimonious in their
        ontological commitments, have attempted to avoid them. Wittgenstein
        rejected them since he was loath to think that the sign for negation
        referred to a negative element in a fact. A contemporary of Russell’s,
        Raphael Demos, attempted to eliminate them by appealing to
        ‘incompatibility’ facts. More recently, Armstrong has appealed to the
        totality of positive facts as the ground of the truth of true negative
        propositions. Oaklander and Miracchi have suggested that the absence or
        non-existence of the positive fact (which is not itself a further fact)
        is the basis of a positive proposition being false and therefore of the
        truth of its negation.
      - >-
        The Law of Civilization and Decay is an overview of history,
        articulating Brooks' critical view of capitalism. A civilization grows
        wealthy, and then its wealth causes it to crumble upon itself due to
        greed.
  - source_sentence: >-
      It is generally accepted that the development of the modern sciences is
      rooted in experiment. Yet for a long time, experimentation did not occupy
      a prominent role, neither in philosophy nor in history of science. With
      the ‘practical turn’ in studying the sciences and their history, this has
      begun to change. This paper is concerned with systems and cultures of
      experimentation and the consistencies that are generated within such
      systems and cultures. The first part of the paper exposes the forms of
      historical and structural coherence that characterize the experimental
      exploration of epistemic objects. In the second part, a particular
      experimental culture in the life sciences is briefly described as an
      example. A survey will be given of what it means and what it takes to
      analyze biological functions in the test tube
    sentences:
      - >-
        Experimentation has long been overlooked in the study of science, but
        with a new focus on practical aspects, this is starting to change. This
        paper explores the systems and cultures of experimentation and the
        patterns that emerge within them. The first part discusses the
        historical and structural coherence of experimental exploration. The
        second part provides a brief overview of an experimental culture in the
        life sciences. The paper concludes with a discussion on analyzing
        biological functions in the test tube.
      - >-
        Hintikka and Mutanen have introduced Trail-And-Error machines as a new
        way to think about computation, expanding on the traditional Turing
        machine model. This innovation opens up new possibilities in the field
        of computation theory.
      - >-
        As Allaire and Firsirotu (1984) pointed out over a decade ago, the
        concept of culture seemed to be sliding inexorably into a superficial
        explanatory pool that promised everything and nothing. However, since
        then, some sophisticated and interesting theoretical developments have
        prevented drowning in the pool of superficiality and hence theoretical
        redundancy. The purpose of this article is to build upon such
        theoretical developments and to introduce an approach that maintains
        that culture can be theorized in the same way as structure, possessing
        irreducible powers and properties that predispose organizational actors
        towards specific courses of action. The morphogenetic approach is the
        methodological complement of transcendental realism, providing
        explanatory leverage on the conditions that maintain for cultural change
        or stability.
  - source_sentence: >-
      This chapter examines three approaches to applied political and legal
      philosophy: Standard activism is primarily addressed to other
      philosophers, adopts an indirect and coincidental role in creating change,
      and counts articulating sound arguments as success. Extreme activism, in
      contrast, is a form of applied philosophy directly addressed to
      policy-makers, with the goal of bringing about a particular outcome, and
      measures success in terms of whether it makes a direct causal contribution
      to that goal. Finally, conceptual activism (like standard activism),
      primarily targets an audience of fellow philosophers, bears a distant,
      non-direct, relation to a desired outcome, and counts success in terms of
      whether it encourages a particular understanding and adoption of the
      concepts under examination.
    sentences:
      - >-
        John Rawls’ resistance to any kind of global egalitarian principle has
        seemed strange and unconvincing to many commentators, including those
        generally supportive of Rawls’ project. His rejection of a global
        egalitarian principle seems to rely on an assumption that states are
        economically bounded and separate from one another, which is not an
        accurate portrayal of economic relations among states in our globalised
        world. In this article, I examine the implications of the domestic
        theory of justice as fairness to argue that Rawls has good reason to
        insist on economically bounded states. I argue that certain central
        features of the contemporary global economy, particularly the free
        movement of capital across borders, undermine the distributional
        autonomy required for states to realise Rawls’ principles of justice,
        and the domestic theory thus requires a certain degree of economic
        separation among states prior to the convening of the international
        original position. Given this, I defend Rawls’ reluctance to endorse a
        global egalitarian principle and defend a policy regime of international
        capital controls, to restore distributional autonomy and make the
        realisation of the principles of justice as fairness possible.
      - >-
        Bibliography of the writings by Hilary Putnam: 16 books, 198 articles,
        10 translations into German (up to 1994).
      - >-
        The jurisprudence under international human rights treaties has had a
        considerable impact across countries. Known for addressing complex
        agendas, the work of expert bodies under the treaties has been credited
        and relied upon for filling the gaps in the realization of several
        objectives, including the peace and security agenda.  In 1982, the Human
        Rights Committee (ICCPR), in a General Comment observed that “states
        have the supreme duty to prevent wars, acts of genocide and other acts
        of mass violence ... Every effort … to avert the danger of war,
        especially thermonuclear war, and to strengthen international peace and
        security would constitute the most important condition and guarantee for
        the safeguarding of the right to life.” Over the years, all treaty
        bodies have contributed in this direction, endorsing peace and security
        so as “to protect people against direct and structural violence … as
        systemic problems and not merely as isolated incidents …”. A closer look
        at the jurisprudence on peace and security, emanating from treaty
        monitoring mechanisms including state periodic reports, interpretive
        statements, the individual communications procedure, and others, reveals
        its distinctive nature
  - source_sentence: >-
      Autonomist accounts of cognitive science suggest that cognitive model
      building and theory construction (can or should) proceed independently of
      findings in neuroscience. Common functionalist justifications of autonomy
      rely on there being relatively few constraints between neural structure
      and cognitive function (e.g., Weiskopf, 2011). In contrast, an integrative
      mechanistic perspective stresses the mutual constraining of structure and
      function (e.g., Piccinini & Craver, 2011; Povich, 2015). In this paper, I
      show how model-based cognitive neuroscience (MBCN) epitomizes the
      integrative mechanistic perspective and concentrates the most
      revolutionary elements of the cognitive neuroscience revolution (Boone &
      Piccinini, 2016). I also show how the prominent subset account of
      functional realization supports the integrative mechanistic perspective I
      take on MBCN and use it to clarify the intralevel and interlevel
      components of integration.
    sentences:
      - >-
        Fictional truth, or truth in fiction/pretense, has been the object of
        extended scrutiny among philosophers and logicians in recent decades.
        Comparatively little attention, however, has been paid to its
        inferential relationships with time and with certain deliberate and
        contingent human activities, namely, the creation of fictional works.
        The aim of the paper is to contribute to filling the gap. Toward this
        goal, a formal framework is outlined that is consistent with a variety
        of conceptions of fictional truth and based upon a specific formal
        treatment of time and agency, that of so-called stit logics. Moreover, a
        complete axiomatic theory of fiction-making TFM is defined, where
        fiction-making is understood as the exercise of agency and choice in
        time over what is fictionally true. The language \ of TFM is an
        extension of the language of propositional logic, with the addition of
        temporal and modal operators. A distinctive feature of \ with respect to
        other modal languages is a variety of operators having to do with
        fictional truth, including a ‘fictionality’ operator \ . Some
        applications of TFM are outlined, and some interesting linguistic and
        inferential phenomena, which are not so easily dealt with in other
        frameworks, are accounted for
      - >-
        We have structured our response according to five questions arising from
        the commentaries: (i) What is sentience? (ii) Is sentience a necessary
        or sufficient condition for moral standing? (iii) What methods should
        guide comparative cognitive research in general, and specifically in
        studying invertebrates? (iv) How should we balance scientific
        uncertainty and moral risk? (v) What practical strategies can help
        reduce biases and morally dismissive attitudes toward invertebrates?
      - >-
        In 2007, ten world-renowned neuroscientists proposed “A Decade of the
        Mind Initiative.” The contention was that, despite the successes of the
        Decade of the Brain, “a fundamental understanding of how the brain gives
        rise to the mind [was] still lacking” (2007, 1321). The primary aims of
        the decade of the mind were “to build on the progress of the recent
        Decade of the Brain (1990-99)” by focusing on “four broad but
        intertwined areas” of research, including: healing and protecting,
        understanding, enriching, and modeling the mind. These four aims were to
        be the result of “transdisciplinary and multiagency” research spanning
        “across disparate fields, such as cognitive science, medicine,
        neuroscience, psychology, mathematics, engineering, and computer
        science.” The proposal for a decade of the mind prompted many questions
        (See Spitzer 2008). In this chapter, I address three of them: (1) How do
        proponents of this new decade conceive of the mind? (2) Why should a
        decade be devoted to understanding it? (3) What should this decade look
        like?
  - source_sentence: >-
      This essay explores the historical and modern perspectives on the Gettier
      problem, highlighting the connections between this issue, skepticism, and
      relevance. Through methods such as historical analysis, induction, and
      deduction, it is found that while contextual theories and varying
      definitions of knowledge do not fully address skeptical challenges, they
      can help clarify our understanding of knowledge. Ultimately, embracing
      subjectivity and intuition can provide insight into what it truly means to
      claim knowledge.
    sentences:
      - >-
        In this article I present and analyze three popular moral justifications
        for hunting. My purpose is to expose the moral terrain of this issue and
        facilitate more fruitful, philosophically relevant discussions about the
        ethics of hunting.
      - >-
        Teaching competency in bioethics has been a concern since the field's
        inception. The first report on the teaching of contemporary bioethics
        was published in 1976 by The Hastings Center, which concluded that
        graduate programs were not necessary at the time. However, the report
        speculated that future developments may require new academic structures
        for graduate education in bioethics. The creation of a terminal degree
        in bioethics has its critics, with scholars debating whether bioethics
        is a discipline with its own methods and theoretical grounding, a
        multidisciplinary field, or something else entirely. Despite these
        debates, new bioethics training programs have emerged at all
        postsecondary levels in the U.S. This essay examines the number and
        types of programs and degrees in this growing field.
      - >-
        Objective: In this essay,  I will try to track some historical and
        modern stages of the discussion on the Gettier problem, and point out
        the interrelations of the questions that this problem raises for
        epistemologists, with sceptical arguments, and a so-called problem of
        relevance. Methods: historical analysis, induction, generalization,
        deduction, discourse, intuition results: Albeit the contextual theories
        of knowledge, the use of different definitions of knowledge, and the
        different ways of the uses of knowledge do not resolve all the issues
        that the sceptic can put forward, but they can be productive in giving
        clarity to a concept of knowledge for us. On the other hand, our
        knowledge will always have an element of intuition and subjectivity,
        however not equating to epistemic luck and probability.  Significance
        novelty: the approach to the context in general, not giving up being a
        Subject may give us a clarity about the sense of what it means to say –
        “I know”.
model-index:
  - name: SentenceTransformer based on dbourget/pb-ds1-48K
    results:
      - task:
          type: semantic-similarity
          name: Semantic Similarity
        dataset:
          name: sts dev
          type: sts-dev
        metrics:
          - type: pearson_cosine
            value: 0.9378177365442741
            name: Pearson Cosine
          - type: spearman_cosine
            value: 0.8943299298202461
            name: Spearman Cosine
          - type: pearson_manhattan
            value: 0.9709949018414847
            name: Pearson Manhattan
          - type: spearman_manhattan
            value: 0.8969442622028955
            name: Spearman Manhattan
          - type: pearson_euclidean
            value: 0.9711044669329696
            name: Pearson Euclidean
          - type: spearman_euclidean
            value: 0.8966133108746955
            name: Spearman Euclidean
          - type: pearson_dot
            value: 0.9419649751470724
            name: Pearson Dot
          - type: spearman_dot
            value: 0.8551487313582053
            name: Spearman Dot
          - type: pearson_max
            value: 0.9711044669329696
            name: Pearson Max
          - type: spearman_max
            value: 0.8969442622028955
            name: Spearman Max

SentenceTransformer based on dbourget/pb-ds1-48K

This is a sentence-transformers model finetuned from dbourget/pb-ds1-48K. It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.

Model Details

Model Description

Model Type: Sentence Transformer
Base model: dbourget/pb-ds1-48K
Maximum Sequence Length: 512 tokens
Output Dimensionality: 768 tokens
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': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
)

Usage

Direct Usage (Sentence Transformers)

First install the Sentence Transformers library:

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("dbourget/pb-ds1-48K-philsim")
# Run inference
sentences = [
    'This essay explores the historical and modern perspectives on the Gettier problem, highlighting the connections between this issue, skepticism, and relevance. Through methods such as historical analysis, induction, and deduction, it is found that while contextual theories and varying definitions of knowledge do not fully address skeptical challenges, they can help clarify our understanding of knowledge. Ultimately, embracing subjectivity and intuition can provide insight into what it truly means to claim knowledge.',
    'Objective: In this essay,  I will try to track some historical and modern stages of the discussion on the Gettier problem, and point out the interrelations of the questions that this problem raises for epistemologists, with sceptical arguments, and a so-called problem of relevance. Methods: historical analysis, induction, generalization, deduction, discourse, intuition results: Albeit the contextual theories of knowledge, the use of different definitions of knowledge, and the different ways of the uses of knowledge do not resolve all the issues that the sceptic can put forward, but they can be productive in giving clarity to a concept of knowledge for us. On the other hand, our knowledge will always have an element of intuition and subjectivity, however not equating to epistemic luck and probability.  Significance novelty: the approach to the context in general, not giving up being a Subject may give us a clarity about the sense of what it means to say – “I know”.',
    "Teaching competency in bioethics has been a concern since the field's inception. The first report on the teaching of contemporary bioethics was published in 1976 by The Hastings Center, which concluded that graduate programs were not necessary at the time. However, the report speculated that future developments may require new academic structures for graduate education in bioethics. The creation of a terminal degree in bioethics has its critics, with scholars debating whether bioethics is a discipline with its own methods and theoretical grounding, a multidisciplinary field, or something else entirely. Despite these debates, new bioethics training programs have emerged at all postsecondary levels in the U.S. This essay examines the number and types of programs and degrees in this growing field.",
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 768]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)
# [3, 3]

Evaluation

Metrics

Semantic Similarity

Dataset: sts-dev
Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	0.9378
spearman_cosine	0.8943
pearson_manhattan	0.971
spearman_manhattan	0.8969
pearson_euclidean	0.9711
spearman_euclidean	0.8966
pearson_dot	0.942
spearman_dot	0.8551
pearson_max	0.9711
spearman_max	0.8969

Training Details

Training Hyperparameters

Non-Default Hyperparameters

eval_strategy: steps
per_device_train_batch_size: 190
per_device_eval_batch_size: 190
learning_rate: 5e-06
num_train_epochs: 2
warmup_ratio: 0.1
bf16: True
batch_sampler: no_duplicates

All Hyperparameters

Click to expand

overwrite_output_dir: False
do_predict: False
eval_strategy: steps
prediction_loss_only: True
per_device_train_batch_size: 190
per_device_eval_batch_size: 190
per_gpu_train_batch_size: None
per_gpu_eval_batch_size: None
gradient_accumulation_steps: 1
eval_accumulation_steps: None
learning_rate: 5e-06
weight_decay: 0.0
adam_beta1: 0.9
adam_beta2: 0.999
adam_epsilon: 1e-08
max_grad_norm: 1.0
num_train_epochs: 2
max_steps: -1
lr_scheduler_type: linear
lr_scheduler_kwargs: {}
warmup_ratio: 0.1
warmup_steps: 0
log_level: passive
log_level_replica: warning
log_on_each_node: True
logging_nan_inf_filter: True
save_safetensors: True
save_on_each_node: False
save_only_model: False
restore_callback_states_from_checkpoint: False
no_cuda: False
use_cpu: False
use_mps_device: False
seed: 42
data_seed: None
jit_mode_eval: False
use_ipex: False
bf16: True
fp16: False
fp16_opt_level: O1
half_precision_backend: auto
bf16_full_eval: False
fp16_full_eval: False
tf32: None
local_rank: 0
ddp_backend: None
tpu_num_cores: None
tpu_metrics_debug: False
debug: []
dataloader_drop_last: 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: False
hub_always_push: False
gradient_checkpointing: False
gradient_checkpointing_kwargs: None
include_inputs_for_metrics: False
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
batch_sampler: no_duplicates
multi_dataset_batch_sampler: proportional

Training Logs

Click to expand

Epoch	Step	Training Loss	loss	sts-dev_spearman_cosine
0	0	-	-	0.8229
0.0178	10	0.0545	-	-
0.0355	20	0.0556	-	-
0.0533	30	0.0502	-	-
0.0710	40	0.0497	-	-
0.0888	50	0.0413	-	-
0.1066	60	0.0334	-	-
0.1243	70	0.0238	-	-
0.1421	80	0.0206	-	-
0.1599	90	0.0167	-	-
0.1776	100	0.0146	0.0725	0.8788
0.1954	110	0.0127	-	-
0.2131	120	0.0125	-	-
0.2309	130	0.0115	-	-
0.2487	140	0.0116	-	-
0.2664	150	0.0111	-	-
0.2842	160	0.0107	-	-
0.3020	170	0.0113	-	-
0.3197	180	0.0106	-	-
0.3375	190	0.0099	-	-
0.3552	200	0.0092	0.0207	0.8856
0.3730	210	0.0097	-	-
0.3908	220	0.0099	-	-
0.4085	230	0.0087	-	-
0.4263	240	0.0087	-	-
0.4440	250	0.0082	-	-
0.4618	260	0.0083	-	-
0.4796	270	0.0089	-	-
0.4973	280	0.0082	-	-
0.5151	290	0.0078	-	-
0.5329	300	0.0081	0.0078	0.8891
0.5506	310	0.0081	-	-
0.5684	320	0.0072	-	-
0.5861	330	0.0084	-	-
0.6039	340	0.0083	-	-
0.6217	350	0.0078	-	-
0.6394	360	0.0077	-	-
0.6572	370	0.008	-	-
0.6750	380	0.0073	-	-
0.6927	390	0.008	-	-
0.7105	400	0.0073	0.0058	0.8890
0.7282	410	0.0075	-	-
0.7460	420	0.0077	-	-
0.7638	430	0.0074	-	-
0.7815	440	0.0073	-	-
0.7993	450	0.007	-	-
0.8171	460	0.0043	-	-
0.8348	470	0.0052	-	-
0.8526	480	0.0046	-	-
0.8703	490	0.0073	-	-
0.8881	500	0.0056	0.0069	0.8922
0.9059	510	0.0059	-	-
0.9236	520	0.0045	-	-
0.9414	530	0.0033	-	-
0.9591	540	0.0058	-	-
0.9769	550	0.0056	-	-
0.9947	560	0.0046	-	-
1.0124	570	0.003	-	-
1.0302	580	0.0039	-	-
1.0480	590	0.0032	-	-
1.0657	600	0.0031	0.0029	0.8931
1.0835	610	0.0046	-	-
1.1012	620	0.003	-	-
1.1190	630	0.0021	-	-
1.1368	640	0.0031	-	-
1.1545	650	0.0035	-	-
1.1723	660	0.0033	-	-
1.1901	670	0.0024	-	-
1.2078	680	0.0012	-	-
1.2256	690	0.0075	-	-
1.2433	700	0.0028	0.0036	0.8945
1.2611	710	0.0033	-	-
1.2789	720	0.0023	-	-
1.2966	730	0.0034	-	-
1.3144	740	0.0018	-	-
1.3321	750	0.0016	-	-
1.3499	760	0.0025	-	-
1.3677	770	0.002	-	-
1.3854	780	0.0016	-	-
1.4032	790	0.0018	-	-
1.4210	800	0.003	0.0027	0.8944
1.4387	810	0.0018	-	-
1.4565	820	0.0008	-	-
1.4742	830	0.0014	-	-
1.4920	840	0.0025	-	-
1.5098	850	0.0026	-	-
1.5275	860	0.0012	-	-
1.5453	870	0.001	-	-
1.5631	880	0.001	-	-
1.5808	890	0.0012	-	-
1.5986	900	0.0021	0.0021	0.8952
1.6163	910	0.0016	-	-
1.6341	920	0.0008	-	-
1.6519	930	0.0008	-	-
1.6696	940	0.0009	-	-
1.6874	950	0.0004	-	-
1.7052	960	0.0003	-	-
1.7229	970	0.0007	-	-
1.7407	980	0.0007	-	-
1.7584	990	0.0011	-	-
1.7762	1000	0.0007	0.0029	0.8952
1.7940	1010	0.0008	-	-
1.8117	1020	0.001	-	-
1.8295	1030	0.0006	-	-
1.8472	1040	0.0006	-	-
1.8650	1050	0.0015	-	-
1.8828	1060	0.0009	-	-
1.9005	1070	0.0005	-	-
1.9183	1080	0.0006	-	-
1.9361	1090	0.0021	-	-
1.9538	1100	0.0009	0.0023	0.8943
1.9716	1110	0.0007	-	-
1.9893	1120	0.0003	-	-

Framework Versions

Python: 3.10.12
Sentence Transformers: 3.0.1
Transformers: 4.42.3
PyTorch: 2.2.0+cu121
Accelerate: 0.31.0
Datasets: 2.20.0
Tokenizers: 0.19.1

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",
}