metadata

language:
  - en
license: apache-2.0
tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - dataset_size:5822
  - loss:MatryoshkaLoss
  - loss:MultipleNegativesRankingLoss
base_model: nomic-ai/modernbert-embed-base
widget:
  - source_sentence: |-
      members and the partners may not assume that all lawyers 
      associated with the firm will inevitably conform to the rules. 
      Subdivision (c) expresses a general principle of personal 
      responsibility for acts of another. See also rule 4-8.4(a). 
      Subdivision (c)(2) defines the duty of a partner or other lawyer 
      having comparable managerial authority in a law firm, as well as a
    sentences:
      - On what date did the CIA locate and release the document in part?
      - >-
        Can members and partners assume that all lawyers will conform to the
        rules?
      - >-
        Where is the statement about Senetas's belief regarding DR's technology
        located?
  - source_sentence: >-
      9 Galbally Dep. Tr. 56:20-22; 58:2-10 (“FDA approval to me was one of the
      most 

      important aspects as to why I invested, and the fact that it was likely to
      be approved at 

      some stage during 2017”); 98:7-9. 

      10 Galbally Dep. Tr. 20:11-24. 

      Senetas Corporation, Ltd. v. DeepRadiology Corporation 

      C.A. No.  2019-0170-PWG 

      July 30, 2019 
       
      4
    sentences:
      - What does the Agency offer to the potential requester?
      - >-
        On what date was the document titled 'Senetas Corporation, Ltd. v.
        DeepRadiology Corporation C.A. No. 2019-0170-PWG' created?
      - ¿Qué no logró establecer la parte apelada?
  - source_sentence: |-
      relacionados los tres señalamientos de error, los discutiremos de 
      forma conjunta. 
       
       
       
      KLAN202300916 
       
      18
      Es la contención de la parte apelante que, al ser titular del 
      material audiovisual en controversia, ostenta todo el derecho de 
      desplegarlo en la Internet y en cualquier otro medio bajo la Ley de 
      Derecho de Autor federal (Copyright Act).  Arguye que, el reclamo de
    sentences:
      - Which exhibit did the image displayed by the prosecutor come from?
      - >-
        ¿Qué parte sostiene tener el derecho de desplegar el material
        audiovisual?
      - >-
        Where in the Defendant's Reply can information about the 'hourly rate
        build up' be found?
  - source_sentence: >-
      jurisdiction under subsection (b) in his reply brief. Generally, “[p]oints
      not argued” in an appellant’s 

      initial brief “are forfeited and shall not be raised in the reply brief.”
      Ill. S. Ct. R. 341(h)(7) (eff. Oct. 1, 

      2020). 
       
      9The statement of jurisdiction in defendant’s brief stated that the notice
      was filed on May 17, 2022, 

      but this appears to be a typo. 
       
      - 8 -
    sentences:
      - >-
        On what date did the statement of jurisdiction in defendant’s brief
        claim the notice was filed?
      - What do agencies use to make source selection decisions?
      - >-
        During which part of the proceeding is the plaintiffs' suggestion
        referenced?
  - source_sentence: >-
      No. 11-445, ECF No. 52-1; id. Ex. B at 1, No. 11-445, ECF No. 52-1.  On
      December 8, 2009, the 

      plaintiff limited the scope of this request by notifying the CIA that it
      could “limit [its] search for 

      requests submitted by Michael Ravnitzky to only requests submitted in 2006
      and 2009” and that 

      it could “limit [its] search to the last four years in which requests were
      received from [each]
    sentences:
      - How is the document listed in the Vaughn index?
      - Whose requests did the CIA specifically limit its search to?
      - >-
        What court case is referenced alongside the American Immigration
        Council?
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: ModernBERT Embed base Legal Matryoshka
    results:
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: dim 768
          type: dim_768
        metrics:
          - type: cosine_accuracy@1
            value: 0.5703245749613601
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.624420401854714
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.6924265842349304
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.7743431221020093
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.5703245749613601
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.5455950540958269
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.41452859350850085
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.24018547140649152
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.20556414219474498
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.5334878928387429
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.6562339000515199
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.7582431736218445
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.6719357607925999
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.6179423959176661
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.6566999443914384
            name: Cosine Map@100
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: dim 512
          type: dim_512
        metrics:
          - type: cosine_accuracy@1
            value: 0.5564142194744977
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.6197836166924265
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.6970633693972179
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.7573415765069552
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.5564142194744977
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.5358062854198866
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.41051004636785166
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.23693972179289027
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.20066975785677482
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.526275115919629
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.6527563111798043
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.7465224111282844
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.661632178488043
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.6061688869262281
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.6465145932511888
            name: Cosine Map@100
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: dim 256
          type: dim_256
        metrics:
          - type: cosine_accuracy@1
            value: 0.5409582689335394
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.5765069551777434
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.6537867078825348
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.7279752704791345
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.5409582689335394
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.508500772797527
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.3839258114374034
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.226275115919629
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.19410097887686759
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.4988408037094281
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.6115404430705821
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.7134209170530655
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.6311397137767786
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.5805567822182967
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.6192535685391065
            name: Cosine Map@100
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: dim 128
          type: dim_128
        metrics:
          - type: cosine_accuracy@1
            value: 0.46986089644513135
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.5146831530139103
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.5857805255023184
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.6646058732612056
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.46986089644513135
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.4487377640391551
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.34188562596599686
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.2054095826893354
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.16911385883565172
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.4416537867078825
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.5471406491499228
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.6505667181865017
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.5655614028820953
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.5130118250288265
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.5535347867731277
            name: Cosine Map@100
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: dim 64
          type: dim_64
        metrics:
          - type: cosine_accuracy@1
            value: 0.3678516228748068
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.401854714064915
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.4775888717156105
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.5564142194744977
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.3678516228748068
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.3498196805770222
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.2751159196290572
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.171097372488408
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.13111798042246264
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.3422205048943843
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.43469860896445134
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.5414734672849046
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.4576624400779507
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.40745626947327096
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.4494322513495018
            name: Cosine Map@100

ModernBERT Embed base Legal Matryoshka

This is a sentence-transformers model finetuned from nomic-ai/modernbert-embed-base on the json dataset. 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: nomic-ai/modernbert-embed-base
Maximum Sequence Length: 8192 tokens
Output Dimensionality: 768 dimensions
Similarity Function: Cosine Similarity
Training Dataset:
- json
Language: en
License: apache-2.0

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': 8192, 'do_lower_case': False}) with Transformer model: ModernBertModel 
  (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})
  (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("PhilLel/modernbert-embed-base-legal-matryoshka-2")
# Run inference
sentences = [
    'No. 11-445, ECF No. 52-1; id. Ex. B at 1, No. 11-445, ECF No. 52-1.  On December 8, 2009, the \nplaintiff limited the scope of this request by notifying the CIA that it could “limit [its] search for \nrequests submitted by Michael Ravnitzky to only requests submitted in 2006 and 2009” and that \nit could “limit [its] search to the last four years in which requests were received from [each]',
    'Whose requests did the CIA specifically limit its search to?',
    'How is the document listed in the Vaughn index?',
]
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

Information Retrieval

Dataset: dim_768
Evaluated with InformationRetrievalEvaluator with these parameters:
```
{
    "truncate_dim": 768
}
```

Metric	Value
cosine_accuracy@1	0.5703
cosine_accuracy@3	0.6244
cosine_accuracy@5	0.6924
cosine_accuracy@10	0.7743
cosine_precision@1	0.5703
cosine_precision@3	0.5456
cosine_precision@5	0.4145
cosine_precision@10	0.2402
cosine_recall@1	0.2056
cosine_recall@3	0.5335
cosine_recall@5	0.6562
cosine_recall@10	0.7582
cosine_ndcg@10	0.6719
cosine_mrr@10	0.6179
cosine_map@100	0.6567

Information Retrieval

Dataset: dim_512
Evaluated with InformationRetrievalEvaluator with these parameters:
```
{
    "truncate_dim": 512
}
```

Metric	Value
cosine_accuracy@1	0.5564
cosine_accuracy@3	0.6198
cosine_accuracy@5	0.6971
cosine_accuracy@10	0.7573
cosine_precision@1	0.5564
cosine_precision@3	0.5358
cosine_precision@5	0.4105
cosine_precision@10	0.2369
cosine_recall@1	0.2007
cosine_recall@3	0.5263
cosine_recall@5	0.6528
cosine_recall@10	0.7465
cosine_ndcg@10	0.6616
cosine_mrr@10	0.6062
cosine_map@100	0.6465

Information Retrieval

Dataset: dim_256
Evaluated with InformationRetrievalEvaluator with these parameters:
```
{
    "truncate_dim": 256
}
```

Metric	Value
cosine_accuracy@1	0.541
cosine_accuracy@3	0.5765
cosine_accuracy@5	0.6538
cosine_accuracy@10	0.728
cosine_precision@1	0.541
cosine_precision@3	0.5085
cosine_precision@5	0.3839
cosine_precision@10	0.2263
cosine_recall@1	0.1941
cosine_recall@3	0.4988
cosine_recall@5	0.6115
cosine_recall@10	0.7134
cosine_ndcg@10	0.6311
cosine_mrr@10	0.5806
cosine_map@100	0.6193

Information Retrieval

Dataset: dim_128
Evaluated with InformationRetrievalEvaluator with these parameters:
```
{
    "truncate_dim": 128
}
```

Metric	Value
cosine_accuracy@1	0.4699
cosine_accuracy@3	0.5147
cosine_accuracy@5	0.5858
cosine_accuracy@10	0.6646
cosine_precision@1	0.4699
cosine_precision@3	0.4487
cosine_precision@5	0.3419
cosine_precision@10	0.2054
cosine_recall@1	0.1691
cosine_recall@3	0.4417
cosine_recall@5	0.5471
cosine_recall@10	0.6506
cosine_ndcg@10	0.5656
cosine_mrr@10	0.513
cosine_map@100	0.5535

Information Retrieval

Dataset: dim_64
Evaluated with InformationRetrievalEvaluator with these parameters:
```
{
    "truncate_dim": 64
}
```

Metric	Value
cosine_accuracy@1	0.3679
cosine_accuracy@3	0.4019
cosine_accuracy@5	0.4776
cosine_accuracy@10	0.5564
cosine_precision@1	0.3679
cosine_precision@3	0.3498
cosine_precision@5	0.2751
cosine_precision@10	0.1711
cosine_recall@1	0.1311
cosine_recall@3	0.3422
cosine_recall@5	0.4347
cosine_recall@10	0.5415
cosine_ndcg@10	0.4577
cosine_mrr@10	0.4075
cosine_map@100	0.4494

Training Details

Training Dataset

json

Dataset: json
Size: 5,822 training samples
Columns: positive and anchor
Approximate statistics based on the first 1000 samples:
positive anchor
type string string
details
min: 28 tokens
mean: 96.98 tokens
max: 157 tokens

min: 8 tokens
mean: 16.79 tokens
max: 41 tokens

	positive	anchor
type	string	string
details	min: 28 tokens mean: 96.98 tokens max: 157 tokens	min: 8 tokens mean: 16.79 tokens max: 41 tokens

Samples:

positive	anchor
`After the bench conference concluded, the following exchange occurred between the prosecutor and Mr. Zimmerman: [PROSECUTOR:] Did you watch this video in preparation? [MR. ZIMMERMAN:] Yes, I did. [PROSECUTOR:] Okay. And after seeing that video[,] was that a true and accurate depiction of the events that occurred that day? [MR. ZIMMERMAN:] Yes.`	`What was Mr. Zimmerman's response when asked if he watched the video in preparation?`
`those guidelines still left a significant amount of ambiguity about “precisely what records [were] being requested.” Id. (internal quotation marks omitted). Notably, although the plaintiff limited the date range and number of reports requested, the plaintiff’s request would still place an unreasonable search burden for two primary reasons. First, the plaintiff’s guideline asking for`	`What aspect of the plaintiff's request is mentioned as limited?`
`motion without prejudice and permit him to do the same. See Prop. of the People, Inc., 330 F. Supp. 3d at 390 (denying the parties’ motions without prejudice because the agency failed to submit sufficient information justifying its FOIA withholdings and permitting both parties to file renewed motions). Thus, it is hereby ORDERED that Defendant’s Motion for Summary Judgment, ECF`	`What were the parties allowed to do after their motions were denied?`

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: epoch
per_device_train_batch_size: 32
per_device_eval_batch_size: 16
gradient_accumulation_steps: 16
learning_rate: 2e-05
num_train_epochs: 4
lr_scheduler_type: cosine
warmup_ratio: 0.1
bf16: True
tf32: True
load_best_model_at_end: True
optim: adamw_torch_fused
batch_sampler: no_duplicates

All Hyperparameters

Click to expand

overwrite_output_dir: False
do_predict: False
eval_strategy: epoch
prediction_loss_only: True
per_device_train_batch_size: 32
per_device_eval_batch_size: 16
per_gpu_train_batch_size: None
per_gpu_eval_batch_size: None
gradient_accumulation_steps: 16
eval_accumulation_steps: None
torch_empty_cache_steps: None
learning_rate: 2e-05
weight_decay: 0.0
adam_beta1: 0.9
adam_beta2: 0.999
adam_epsilon: 1e-08
max_grad_norm: 1.0
num_train_epochs: 4
max_steps: -1
lr_scheduler_type: cosine
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: True
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: True
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_fused
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: no_duplicates
multi_dataset_batch_sampler: proportional

Training Logs

Epoch	Step	Training Loss	dim_768_cosine_ndcg@10	dim_512_cosine_ndcg@10	dim_256_cosine_ndcg@10	dim_128_cosine_ndcg@10	dim_64_cosine_ndcg@10
1.0	6	-	0.5702	0.5637	0.5165	0.4642	0.3672
1.7033	10	107.719	-	-	-	-	-
2.0	12	-	0.6308	0.6204	0.5816	0.5030	0.3945
3.0	18	-	0.6403	0.6286	0.5892	0.5124	0.3973
3.3516	20	58.188	0.6406	0.6285	0.5906	0.5135	0.3979
1.0	6	-	0.6590	0.6518	0.6151	0.5451	0.4307
1.7033	10	49.076	-	-	-	-	-
2.0	12	-	0.6696	0.6602	0.6247	0.5612	0.4497
3.0	18	-	0.6719	0.6616	0.6311	0.5656	0.4577
3.3516	20	36.707	0.6719	0.6616	0.6311	0.5656	0.4577

The bold row denotes the saved checkpoint.

Framework Versions

Python: 3.10.12
Sentence Transformers: 4.1.0
Transformers: 4.51.3
PyTorch: 2.7.0+cu126
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}
}