rubert-tiny2-distilled-from-LaBSE-en-ru

SentenceTransformer based on cointegrated/rubert-tiny2

This is a sentence-transformers model finetuned from cointegrated/rubert-tiny2. It maps sentences & paragraphs to a 312-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: cointegrated/rubert-tiny2 <!-- at revision dad72b8f77c5eef6995dd3e4691b758ba56b90c3 -->
• Maximum Sequence Length: 2048 tokens
• Output Dimensionality: 312 tokens
• Similarity Function: Cosine Similarity

<!-- - **Training Dataset:** Unknown --> <!-- - **Language:** Unknown --> <!-- - **License:** Unknown -->

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': 2048, 'do_lower_case': False}) with Transformer model: BertModel 
  (1): Pooling({'word_embedding_dimension': 312, '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("whitemouse84/rubert-tiny2-distilled-from-LaBSE-en-ru")
# Run inference
sentences = [
    'Nobody knew where they went.',
    'The chaotic regime contrasts starkly with the ordered regime.',
    'This applies to both C-R relationships defined by a single C-R function and those defined by a pooling of multiple C-R functions.',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 312]

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

<!-- ### Direct Usage (Transformers) <details><summary>Click to see the direct usage in Transformers</summary> </details> --> <!-- ### Downstream Usage (Sentence Transformers) You can finetune this model on your own dataset. <details><summary>Click to expand</summary> </details> --> <!-- ### Out-of-Scope Use *List how the model may foreseeably be misused and address what users ought not to do with the model.* -->

Evaluation

Metrics

Semantic Similarity

• Dataset: sts-dev
• Evaluated with <code>EmbeddingSimilarityEvaluator</code>

Knowledge Distillation

• Evaluated with <code>MSEEvaluator</code>

Semantic Similarity

• Dataset: sts-test
• Evaluated with <code>EmbeddingSimilarityEvaluator</code>

<!-- ## Bias, Risks and Limitations *What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.* --> <!-- ### Recommendations *What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.* -->

Training Details

Training Dataset

Unnamed Dataset

• Size: 10,000,000 training samples
• Columns: <code>sentence</code> and <code>label</code>
• Approximate statistics based on the first 1000 samples:

  	sentence	label
  type	string	list
  details	<ul><li>min: 5 tokens</li><li>mean: 27.28 tokens</li><li>max: 210 tokens</li></ul>	<ul><li>size: 312 elements</li></ul>

• Samples:

  sentence	label
  <code>Это действительно та мысль , которая имеет значение , и prudie надеется , что ваши родственники оценят ваш продуманный выбор .</code>	<code>[-0.499659925699234, -0.11499621719121933, 0.09910979121923447, -0.028659146279096603, -0.08436408638954163, ...]</code>
  <code>A progressive match- providing a higher match for low-income workers and eliminating the match for high-income workers-would serve to target low-income</code>	<code>[-0.1623910814523697, -0.13584381341934204, 0.15065298974514008, -0.12182427942752838, 0.10419385135173798, ...]</code>
  <code>Должны ли мы просто набраться смелости и пригласить их , или пригласить их на ужин / напитки в ресторане ?</code>	<code>[-0.5938871502876282, -0.08154283463954926, 0.022086789831519127, -0.022560089826583862, -0.07033800333738327, ...]</code>

• Loss: <code>MSELoss</code>

Evaluation Dataset

Unnamed Dataset

• Size: 10,000 evaluation samples
• Columns: <code>sentence</code> and <code>label</code>
• Approximate statistics based on the first 1000 samples:

  	sentence	label
  type	string	list
  details	<ul><li>min: 5 tokens</li><li>mean: 24.73 tokens</li><li>max: 62 tokens</li></ul>	<ul><li>size: 312 elements</li></ul>

• Samples:

  sentence	label
  <code>Отчет ФБР, рейс №93, неявившиеся пассажиры 11/09/01, 18 сентября 2001 г.</code>	<code>[-0.3285815119743347, -0.05295126512646675, -0.0864153802394867, -0.018464216962456703, 0.11339661478996277, ...]</code>
  <code>Данная коллекция европейских и пуэрто-риканских предметов искусства является по-видимому самой лучшей в Карибском бассейне. Она подойдет по духу любой европейской столице.</code>	<code>[-0.4392591416835785, -0.2423635721206665, 0.1603011041879654, 0.07435077428817749, -0.11357224732637405, ...]</code>
  <code>Понятие возможность для обучения, хотя на данный момент оно всего лишь формируется, является частью основополагающего интереса при проведении мероприятий по реабилитации бывших алкоголиков в отделениях интенсивной терапии.</code>	<code>[-0.4496175944805145, -0.16721466183662415, 0.09532374888658524, 0.006283232010900974, 0.007752248551696539, ...]</code>

• Loss: <code>MSELoss</code>

Training Hyperparameters

Non-Default Hyperparameters

• eval_strategy: steps
• per_device_train_batch_size: 64
• per_device_eval_batch_size: 64
• learning_rate: 0.0001
• num_train_epochs: 1
• warmup_ratio: 0.1
• bf16: True
• load_best_model_at_end: True

All Hyperparameters

<details><summary>Click to expand</summary>

• 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: 0.0001
• weight_decay: 0.0
• adam_beta1: 0.9
• adam_beta2: 0.999
• adam_epsilon: 1e-08
• max_grad_norm: 1.0
• num_train_epochs: 1
• 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: 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}
• 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
• eval_use_gather_object: False
• batch_sampler: batch_sampler
• multi_dataset_batch_sampler: proportional

</details>

Training Logs

<details><summary>Click to expand</summary>

The model card is truncated. Read the rest on Hugging Face.