README.md

metadata

tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - dataset_size:234000
  - loss:MSELoss
base_model: FacebookAI/xlm-roberta-base
widget:
  - source_sentence: the night before the night before christmas movie
    sentences:
      - hu
      - ' តើការប្រកួតបាល់បោះលីកធំជាងគេដែលវែងជាងគេបំផុតក្នុងប្រវត្តិសាស្ត្រមានអ្វីខ្លះ'
      - Másnapos Karácsony
  - source_sentence: when did star wars a new hope come out
    sentences:
      - Koska alexandrian kirjasto tuhoutui tulipalossa
      - bilakah star wars a new hope keluar
      - ms
  - source_sentence: what is the relative location of new york city
    sentences:
      - ما هو الموقع النسبي لمدينة نيويورك
      - ar
      - dov'è stato girato il film i cannoni di Navarone
  - source_sentence: how many miles from albuquerque new mexico to amarillo texas
    sentences:
      - сколько миль от альбукерке нью мексико до амарилло техас
      - qui a chanté we all live in a yellow submarine
      - ru
  - source_sentence: where does food wars anime end in the manga
    sentences:
      - food wars 动漫是在漫画哪里结束的
      - 《食戟之靈》漫畫幾時完
      - zh_hk
pipeline_tag: sentence-similarity
library_name: sentence-transformers
metrics:
  - negative_mse
model-index:
  - name: SentenceTransformer based on FacebookAI/xlm-roberta-base
    results:
      - task:
          type: knowledge-distillation
          name: Knowledge Distillation
        dataset:
          name: MSE val en to ar
          type: MSE-val-en-to-ar
        metrics:
          - type: negative_mse
            value: -19.935108721256256
            name: Negative Mse
      - task:
          type: knowledge-distillation
          name: Knowledge Distillation
        dataset:
          name: MSE val en to da
          type: MSE-val-en-to-da
        metrics:
          - type: negative_mse
            value: -16.227059066295624
            name: Negative Mse
      - task:
          type: knowledge-distillation
          name: Knowledge Distillation
        dataset:
          name: MSE val en to de
          type: MSE-val-en-to-de
        metrics:
          - type: negative_mse
            value: -17.03149825334549
            name: Negative Mse
      - task:
          type: knowledge-distillation
          name: Knowledge Distillation
        dataset:
          name: MSE val en to en
          type: MSE-val-en-to-en
        metrics:
          - type: negative_mse
            value: -14.746585488319397
            name: Negative Mse
      - task:
          type: knowledge-distillation
          name: Knowledge Distillation
        dataset:
          name: MSE val en to es
          type: MSE-val-en-to-es
        metrics:
          - type: negative_mse
            value: -16.7389914393425
            name: Negative Mse
      - task:
          type: knowledge-distillation
          name: Knowledge Distillation
        dataset:
          name: MSE val en to fi
          type: MSE-val-en-to-fi
        metrics:
          - type: negative_mse
            value: -17.699478566646576
            name: Negative Mse
      - task:
          type: knowledge-distillation
          name: Knowledge Distillation
        dataset:
          name: MSE val en to fr
          type: MSE-val-en-to-fr
        metrics:
          - type: negative_mse
            value: -16.85505211353302
            name: Negative Mse
      - task:
          type: knowledge-distillation
          name: Knowledge Distillation
        dataset:
          name: MSE val en to he
          type: MSE-val-en-to-he
        metrics:
          - type: negative_mse
            value: -19.114328920841217
            name: Negative Mse
      - task:
          type: knowledge-distillation
          name: Knowledge Distillation
        dataset:
          name: MSE val en to hu
          type: MSE-val-en-to-hu
        metrics:
          - type: negative_mse
            value: -17.86249130964279
            name: Negative Mse
      - task:
          type: knowledge-distillation
          name: Knowledge Distillation
        dataset:
          name: MSE val en to it
          type: MSE-val-en-to-it
        metrics:
          - type: negative_mse
            value: -16.931141912937164
            name: Negative Mse
      - task:
          type: knowledge-distillation
          name: Knowledge Distillation
        dataset:
          name: MSE val en to ja
          type: MSE-val-en-to-ja
        metrics:
          - type: negative_mse
            value: -18.774642050266266
            name: Negative Mse
      - task:
          type: knowledge-distillation
          name: Knowledge Distillation
        dataset:
          name: MSE val en to ko
          type: MSE-val-en-to-ko
        metrics:
          - type: negative_mse
            value: -19.68335211277008
            name: Negative Mse
      - task:
          type: knowledge-distillation
          name: Knowledge Distillation
        dataset:
          name: MSE val en to km
          type: MSE-val-en-to-km
        metrics:
          - type: negative_mse
            value: -19.339339435100555
            name: Negative Mse
      - task:
          type: knowledge-distillation
          name: Knowledge Distillation
        dataset:
          name: MSE val en to ms
          type: MSE-val-en-to-ms
        metrics:
          - type: negative_mse
            value: -16.49850606918335
            name: Negative Mse
      - task:
          type: knowledge-distillation
          name: Knowledge Distillation
        dataset:
          name: MSE val en to nl
          type: MSE-val-en-to-nl
        metrics:
          - type: negative_mse
            value: -15.982428193092346
            name: Negative Mse
      - task:
          type: knowledge-distillation
          name: Knowledge Distillation
        dataset:
          name: MSE val en to no
          type: MSE-val-en-to-no
        metrics:
          - type: negative_mse
            value: -16.261471807956696
            name: Negative Mse
      - task:
          type: knowledge-distillation
          name: Knowledge Distillation
        dataset:
          name: MSE val en to pl
          type: MSE-val-en-to-pl
        metrics:
          - type: negative_mse
            value: -17.510776221752167
            name: Negative Mse
      - task:
          type: knowledge-distillation
          name: Knowledge Distillation
        dataset:
          name: MSE val en to pt
          type: MSE-val-en-to-pt
        metrics:
          - type: negative_mse
            value: -16.528253257274628
            name: Negative Mse
      - task:
          type: knowledge-distillation
          name: Knowledge Distillation
        dataset:
          name: MSE val en to ru
          type: MSE-val-en-to-ru
        metrics:
          - type: negative_mse
            value: -17.358270287513733
            name: Negative Mse
      - task:
          type: knowledge-distillation
          name: Knowledge Distillation
        dataset:
          name: MSE val en to sv
          type: MSE-val-en-to-sv
        metrics:
          - type: negative_mse
            value: -16.31281077861786
            name: Negative Mse
      - task:
          type: knowledge-distillation
          name: Knowledge Distillation
        dataset:
          name: MSE val en to th
          type: MSE-val-en-to-th
        metrics:
          - type: negative_mse
            value: -17.586874961853027
            name: Negative Mse
      - task:
          type: knowledge-distillation
          name: Knowledge Distillation
        dataset:
          name: MSE val en to tr
          type: MSE-val-en-to-tr
        metrics:
          - type: negative_mse
            value: -17.390474677085876
            name: Negative Mse
      - task:
          type: knowledge-distillation
          name: Knowledge Distillation
        dataset:
          name: MSE val en to vi
          type: MSE-val-en-to-vi
        metrics:
          - type: negative_mse
            value: -17.174969613552094
            name: Negative Mse
      - task:
          type: knowledge-distillation
          name: Knowledge Distillation
        dataset:
          name: MSE val en to zh cn
          type: MSE-val-en-to-zh_cn
        metrics:
          - type: negative_mse
            value: -18.12549978494644
            name: Negative Mse
      - task:
          type: knowledge-distillation
          name: Knowledge Distillation
        dataset:
          name: MSE val en to zh hk
          type: MSE-val-en-to-zh_hk
        metrics:
          - type: negative_mse
            value: -18.189936876296997
            name: Negative Mse
      - task:
          type: knowledge-distillation
          name: Knowledge Distillation
        dataset:
          name: MSE val en to zh tw
          type: MSE-val-en-to-zh_tw
        metrics:
          - type: negative_mse
            value: -18.67867261171341
            name: Negative Mse

SentenceTransformer based on FacebookAI/xlm-roberta-base

This is a sentence-transformers model finetuned from FacebookAI/xlm-roberta-base. 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: FacebookAI/xlm-roberta-base
• Maximum Sequence Length: 128 tokens
• Output Dimensionality: 768 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': 128, 'do_lower_case': False}) with Transformer model: XLMRobertaModel 
  (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("luanafelbarros/xlm-roberta-base-multilingual-mkqa")
# Run inference
sentences = [
    'where does food wars anime end in the manga',
    '《食戟之靈》漫畫幾時完',
    'zh_hk',
]
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

Knowledge Distillation

• Datasets: MSE-val-en-to-ar, MSE-val-en-to-da, MSE-val-en-to-de, MSE-val-en-to-en, MSE-val-en-to-es, MSE-val-en-to-fi, MSE-val-en-to-fr, MSE-val-en-to-he, MSE-val-en-to-hu, MSE-val-en-to-it, MSE-val-en-to-ja, MSE-val-en-to-ko, MSE-val-en-to-km, MSE-val-en-to-ms, MSE-val-en-to-nl, MSE-val-en-to-no, MSE-val-en-to-pl, MSE-val-en-to-pt, MSE-val-en-to-ru, MSE-val-en-to-sv, MSE-val-en-to-th, MSE-val-en-to-tr, MSE-val-en-to-vi, MSE-val-en-to-zh_cn, MSE-val-en-to-zh_hk and MSE-val-en-to-zh_tw
• Evaluated with MSEEvaluator

Metric	MSE-val-en-to-ar	MSE-val-en-to-da	MSE-val-en-to-de	MSE-val-en-to-en	MSE-val-en-to-es	MSE-val-en-to-fi	MSE-val-en-to-fr	MSE-val-en-to-he	MSE-val-en-to-hu	MSE-val-en-to-it	MSE-val-en-to-ja	MSE-val-en-to-ko	MSE-val-en-to-km	MSE-val-en-to-ms	MSE-val-en-to-nl	MSE-val-en-to-no	MSE-val-en-to-pl	MSE-val-en-to-pt	MSE-val-en-to-ru	MSE-val-en-to-sv	MSE-val-en-to-th	MSE-val-en-to-tr	MSE-val-en-to-vi	MSE-val-en-to-zh_cn	MSE-val-en-to-zh_hk	MSE-val-en-to-zh_tw
negative_mse	-19.9351	-16.2271	-17.0315	-14.7466	-16.739	-17.6995	-16.8551	-19.1143	-17.8625	-16.9311	-18.7746	-19.6834	-19.3393	-16.4985	-15.9824	-16.2615	-17.5108	-16.5283	-17.3583	-16.3128	-17.5869	-17.3905	-17.175	-18.1255	-18.1899	-18.6787

Training Details

Training Dataset

Unnamed Dataset

• Size: 234,000 training samples
• Columns: english, non-english, target, and label
• Approximate statistics based on the first 1000 samples:

  	english	non-english	target	label
  type	string	string	string	list
  details	min: 10 tokens mean: 13.21 tokens max: 19 tokens	min: 7 tokens mean: 13.87 tokens max: 31 tokens	min: 3 tokens mean: 3.38 tokens max: 6 tokens	size: 768 elements

• Samples:

  english	non-english	target	label
  what are all the wizard of oz movies	the wizard of oz ما هي كل افلام	ar	[0.5303382277488708, -0.31762194633483887, -0.2945275902748108, -0.6602655649185181, -1.4617066383361816, ...]
  what are all the wizard of oz movies	hvad er alle troldmanden fra oz filmene	da	[0.5303382277488708, -0.31762194633483887, -0.2945275902748108, -0.6602655649185181, -1.4617066383361816, ...]
  what are all the wizard of oz movies	Wie heißen alle Der Zauberer von Oz Filme	de	[0.5303382277488708, -0.31762194633483887, -0.2945275902748108, -0.6602655649185181, -1.4617066383361816, ...]

• Loss: MSELoss

Evaluation Dataset

Unnamed Dataset

• Size: 13,000 evaluation samples
• Columns: english, non-english, target, and label
• Approximate statistics based on the first 1000 samples:

  	english	non-english	target	label
  type	string	string	string	list
  details	min: 10 tokens mean: 13.05 tokens max: 22 tokens	min: 5 tokens mean: 13.79 tokens max: 34 tokens	min: 3 tokens mean: 3.38 tokens max: 6 tokens	size: 768 elements

• Samples:

  english	non-english	target	label
  a change to the constitution must be approved by	يجب الموافقة على تغيير الدستور	ar	[1.0918692350387573, 0.8024187684059143, 0.23035858571529388, 0.16300565004348755, -0.6033854484558105, ...]
  a change to the constitution must be approved by	en ændring af forfatningen skal godkendes af	da	[1.0918692350387573, 0.8024187684059143, 0.23035858571529388, 0.16300565004348755, -0.6033854484558105, ...]
  a change to the constitution must be approved by	Eine Änderung der Verfassung muss gebilligt werden durch	de	[1.0918692350387573, 0.8024187684059143, 0.23035858571529388, 0.16300565004348755, -0.6033854484558105, ...]

• Loss: MSELoss

Training Hyperparameters

Non-Default Hyperparameters

• eval_strategy: steps
• per_device_train_batch_size: 64
• per_device_eval_batch_size: 64
• learning_rate: 2e-05
• warmup_ratio: 0.1
• fp16: True

All Hyperparameters

Click to expand

• overwrite_output_dir: False
• do_predict: False
• eval_strategy: steps
• prediction_loss_only: True
• per_device_train_batch_size: 64
• per_device_eval_batch_size: 64
• 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: 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: 3
• 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: False
• fp16: True
• 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
• 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: proportional

Training Logs

Click to expand

Epoch	Step	Training Loss	Validation Loss	MSE-val-en-to-ar_negative_mse	MSE-val-en-to-da_negative_mse	MSE-val-en-to-de_negative_mse	MSE-val-en-to-en_negative_mse	MSE-val-en-to-es_negative_mse	MSE-val-en-to-fi_negative_mse	MSE-val-en-to-fr_negative_mse	MSE-val-en-to-he_negative_mse	MSE-val-en-to-hu_negative_mse	MSE-val-en-to-it_negative_mse	MSE-val-en-to-ja_negative_mse	MSE-val-en-to-ko_negative_mse	MSE-val-en-to-km_negative_mse	MSE-val-en-to-ms_negative_mse	MSE-val-en-to-nl_negative_mse	MSE-val-en-to-no_negative_mse	MSE-val-en-to-pl_negative_mse	MSE-val-en-to-pt_negative_mse	MSE-val-en-to-ru_negative_mse	MSE-val-en-to-sv_negative_mse	MSE-val-en-to-th_negative_mse	MSE-val-en-to-tr_negative_mse	MSE-val-en-to-vi_negative_mse	MSE-val-en-to-zh_cn_negative_mse	MSE-val-en-to-zh_hk_negative_mse	MSE-val-en-to-zh_tw_negative_mse
0.0273	100	0.7471	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0547	200	0.5344	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0820	300	0.4011	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1094	400	0.3686	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1367	500	0.3558	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1641	600	0.3527	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1914	700	0.3479	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.2188	800	0.3373	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.2461	900	0.3315	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.2734	1000	0.3243	0.3143	-31.0036	-30.4995	-30.5974	-30.3236	-30.5190	-30.6680	-30.5902	-30.8805	-30.7873	-30.6191	-30.7149	-30.7932	-30.8955	-30.5254	-30.5554	-30.5243	-30.6522	-30.5353	-30.5800	-30.5240	-30.7348	-30.7127	-30.6429	-30.5608	-30.5626	-30.5837
0.3008	1100	0.3175	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.3281	1200	0.3126	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.3555	1300	0.3082	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.3828	1400	0.3049	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.4102	1500	0.3019	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.4375	1600	0.2988	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.4649	1700	0.2979	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.4922	1800	0.2926	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.5196	1900	0.2885	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.5469	2000	0.2879	0.2787	-26.4435	-25.3475	-25.5656	-24.8280	-25.4096	-25.8103	-25.4399	-26.1209	-25.8292	-25.5216	-26.0866	-26.4725	-26.2586	-25.5986	-25.3495	-25.2907	-25.6509	-25.3489	-25.4795	-25.3660	-25.7628	-25.7572	-25.6763	-25.7273	-25.7893	-25.8524
0.5742	2100	0.2843	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.6016	2200	0.2821	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.6289	2300	0.2795	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.6563	2400	0.2808	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.6836	2500	0.2771	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.7110	2600	0.2745	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.7383	2700	0.272	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.7657	2800	0.2711	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.7930	2900	0.2685	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.8203	3000	0.267	0.2638	-24.2447	-22.3985	-22.7542	-21.5879	-22.5929	-23.2891	-22.6798	-23.7047	-23.1739	-22.7708	-23.5962	-24.2250	-23.9269	-22.8039	-22.2681	-22.3432	-22.9390	-22.5717	-22.8201	-22.4143	-23.1236	-23.1100	-22.9658	-23.0786	-23.2390	-23.3243
0.8477	3100	0.2718	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.8750	3200	0.2674	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.9024	3300	0.2662	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.9297	3400	0.2631	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.9571	3500	0.26	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.9844	3600	0.2586	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
1.0118	3700	0.2575	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
1.0391	3800	0.2549	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
1.0664	3900	0.2529	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
1.0938	4000	0.2511	0.2469	-22.9347	-20.4196	-20.9011	-19.3762	-20.7242	-21.5322	-20.7711	-22.3208	-21.5176	-20.9047	-22.1008	-22.8701	-22.4827	-20.7383	-20.2571	-20.3842	-21.1960	-20.6791	-21.0474	-20.4460	-21.3999	-21.3937	-21.1382	-21.5265	-21.6918	-21.8791
1.1211	4100	0.2502	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
1.1485	4200	0.2491	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
1.1758	4300	0.248	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
1.2032	4400	0.2463	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
1.2305	4500	0.2445	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
1.2579	4600	0.2432	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
1.2852	4700	0.2419	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
1.3126	4800	0.2405	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
1.3399	4900	0.2404	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
1.3672	5000	0.2394	0.2354	-21.7963	-18.8622	-19.4636	-17.6703	-19.2473	-20.1437	-19.3378	-21.1200	-20.1560	-19.4587	-20.9473	-21.6343	-21.2979	-19.1964	-18.6653	-18.8517	-19.8565	-19.1500	-19.6760	-18.9243	-19.9718	-19.9191	-19.6695	-20.2707	-20.4090	-20.6846
1.3946	5100	0.2375	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
1.4219	5200	0.2374	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
1.4493	5300	0.236	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
1.4766	5400	0.2335	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
1.5040	5500	0.2346	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
1.5313	5600	0.2335	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
1.5587	5700	0.232	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
1.5860	5800	0.2314	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
1.6133	5900	0.2304	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
1.6407	6000	0.2303	0.2289	-21.1967	-17.9192	-18.5833	-16.6276	-18.3510	-19.2977	-18.4551	-20.3960	-19.3202	-18.5573	-20.1420	-20.9358	-20.6084	-18.2396	-17.7261	-17.9322	-19.0167	-18.2305	-18.8471	-17.9794	-19.1440	-19.0105	-18.7845	-19.4778	-19.6095	-19.9643
1.6680	6100	0.2294	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
1.6954	6200	0.229	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
1.7227	6300	0.2275	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
1.7501	6400	0.2285	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
1.7774	6500	0.2279	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
1.8048	6600	0.2275	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
1.8321	6700	0.2256	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
1.8594	6800	0.2259	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
1.8868	6900	0.2237	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
1.9141	7000	0.2232	0.2242	-20.6888	-17.2295	-17.9547	-15.8517	-17.7267	-18.6854	-17.8191	-19.8853	-18.7432	-17.9054	-19.5866	-20.4321	-20.1381	-17.5215	-16.9982	-17.2683	-18.4340	-17.5295	-18.2454	-17.3006	-18.5072	-18.3554	-18.1438	-18.9634	-19.0843	-19.4826
1.9415	7100	0.2231	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
1.9688	7200	0.2225	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
1.9962	7300	0.2235	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
2.0235	7400	0.2224	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
2.0509	7500	0.2206	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
2.0782	7600	0.2205	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
2.1056	7700	0.2196	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
2.1329	7800	0.22	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
2.1602	7900	0.2188	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
2.1876	8000	0.2184	0.2209	-20.3380	-16.7285	-17.5078	-15.3142	-17.2366	-18.1903	-17.3419	-19.5057	-18.2970	-17.4283	-19.1880	-20.0709	-19.7478	-17.0291	-16.5125	-16.7629	-17.9586	-17.0487	-17.7907	-16.8237	-18.0585	-17.8714	-17.6527	-18.5499	-18.6504	-19.0688
2.2149	8100	0.2189	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
2.2423	8200	0.2178	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
2.2696	8300	0.2185	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
2.2970	8400	0.2175	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
2.3243	8500	0.2183	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
2.3517	8600	0.2176	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
2.3790	8700	0.2169	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
2.4063	8800	0.2172	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
2.4337	8900	0.2153	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
2.4610	9000	0.2162	0.2187	-20.1028	-16.4147	-17.2107	-14.9595	-16.9406	-17.9101	-17.0441	-19.2680	-18.0594	-17.1276	-18.9403	-19.8407	-19.5169	-16.6976	-16.1859	-16.4554	-17.6828	-16.7360	-17.5378	-16.5167	-17.7710	-17.5853	-17.3717	-18.3032	-18.3627	-18.8466
2.4884	9100	0.2159	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
2.5157	9200	0.2161	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
2.5431	9300	0.2148	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
2.5704	9400	0.2148	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
2.5978	9500	0.2154	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
2.6251	9600	0.2142	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
2.6524	9700	0.2144	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
2.6798	9800	0.215	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
2.7071	9900	0.2142	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
2.7345	10000	0.2139	0.2174	-19.9351	-16.2271	-17.0315	-14.7466	-16.7390	-17.6995	-16.8551	-19.1143	-17.8625	-16.9311	-18.7746	-19.6834	-19.3393	-16.4985	-15.9824	-16.2615	-17.5108	-16.5283	-17.3583	-16.3128	-17.5869	-17.3905	-17.1750	-18.1255	-18.1899	-18.6787
2.7618	10100	0.2134	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
2.7892	10200	0.2141	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
2.8165	10300	0.2147	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
2.8439	10400	0.2138	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
2.8712	10500	0.2133	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
2.8986	10600	0.2129	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
2.9259	10700	0.2129	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
2.9532	10800	0.2129	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
2.9806	10900	0.214	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-

Framework Versions

• Python: 3.10.12
• Sentence Transformers: 3.3.1
• Transformers: 4.46.2
• PyTorch: 2.5.1+cu121
• Accelerate: 1.1.1
• Datasets: 3.1.0
• Tokenizers: 0.20.3

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",
}

MSELoss

@inproceedings{reimers-2020-multilingual-sentence-bert,
    title = "Making Monolingual Sentence Embeddings Multilingual using Knowledge Distillation",
    author = "Reimers, Nils and Gurevych, Iryna",
    booktitle = "Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing",
    month = "11",
    year = "2020",
    publisher = "Association for Computational Linguistics",
    url = "https://arxiv.org/abs/2004.09813",
}