SRBedding-base-distilled-v1

SentenceTransformer based on intfloat/multilingual-e5-base

This is a sentence-transformers model finetuned from intfloat/multilingual-e5-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: intfloat/multilingual-e5-base <!-- at revision d13f1b27baf31030b7fd040960d60d909913633f -->
• Maximum Sequence Length: 512 tokens
• Output Dimensionality: 768 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': 512, '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})
  (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("sentence_transformers_model_id")
# Run inference
sentences = [
    '• Mastering the creation and developments of a sales organization;',
    '• Savladaju kreiranje i razvoj prodajne organizacije;',
    'Uslijed takvih percepcija koje su se ukorjenjivale tokom dugog niza godina, ovakva ponašanja postala su dio našeg DNK, i na jednoj i na drugoj strani.',
]
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]

<!-- ### 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

Knowledge Distillation

• Dataset: en-sr
• Evaluated with <code>MSEEvaluator</code>

Translation

• Dataset: en-sr
• Evaluated with <code>TranslationEvaluator</code>

Semantic Similarity

• Dataset: sts17-test
• Evaluated with <code>EmbeddingSimilarityEvaluator</code>

Semantic Similarity

• Dataset: sts17-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: 1,765,391 training samples
• Columns: <code>english</code>, <code>non_english</code>, and <code>label</code>
• Approximate statistics based on the first 1000 samples:

  	english	non_english	label
  type	string	string	list
  details	<ul><li>min: 3 tokens</li><li>mean: 33.36 tokens</li><li>max: 178 tokens</li></ul>	<ul><li>min: 5 tokens</li><li>mean: 36.18 tokens</li><li>max: 202 tokens</li></ul>	<ul><li>size: 768 elements</li></ul>

• Samples:

  english	non_english	label
  <code>All the participants of these visits expressed a readiness to continue to participate and initiate this kind and similar activities, and they stressed their commitment to activities that contribute to reconciliation in their local environments and the region.</code>	<code>Svi učesnici ovih posjeta izrazili su spremnost da nastave učestvovati i inicirati ovakve i slične aktivnosti, te su istakli svoju posvećenost aktivnostima koje doprinose pomirenju u njihovim lokalnim sredinama i u regiji.</code>	<code>[-0.023944344371557236, -0.022687293589115143, -0.03220286965370178, -0.0246198121458292, 0.030504269525408745, ...]</code>
  <code>🚗 Car Rental Ayers Rock Airport	Rent a car Ayers Rock – Rentalcargroup.com</code>	<code>🚗 Reykjavik Najam automobila - Rentalcargroup.com</code>
  <code>SESAME ROLLS - Tvojih5minuta</code>	<code>Susam kifle - Tvojih5minuta</code>	<code>[-0.025164667516946793, -0.02409234829246998, -0.030587544664740562, 0.006792992819100618, 0.03685637190937996, ...]</code>

• Loss: <code>MSELoss</code>

Evaluation Dataset

Unnamed Dataset

• Size: 36,029 evaluation samples
• Columns: <code>english</code>, <code>non_english</code>, and <code>label</code>
• Approximate statistics based on the first 1000 samples:

  	english	non_english	label
  type	string	string	list
  details	<ul><li>min: 4 tokens</li><li>mean: 33.49 tokens</li><li>max: 173 tokens</li></ul>	<ul><li>min: 4 tokens</li><li>mean: 36.99 tokens</li><li>max: 198 tokens</li></ul>	<ul><li>size: 768 elements</li></ul>

• Samples:

  english	non_english	label
  <code>Andrew proposed Laura, he really liked to work with her, and I said great, she's a great actress.</code>	<code>Razmišljali smo o njegovoj mami, i onda je Endru na kastingu predložio Loru, hteo je da radi s njom i ja sam se složio, ona je sjajna glumica.</code>	<code>[-0.017107214778661728, -0.054064393043518066, -0.009186248295009136, -0.026429275050759315, 0.06628632545471191, ...]</code>
  <code>Oskar Schindler was a German industrialist and member of the Nazi party who saved 1,200 Jews during World War II.</code>	<code>Oskar Šindler je bio njemački idustrijalista i član nacističke partije koji je spasio 1.200 Jevreja tokom Drugog svjetskog rata tako što ih je zaposlio u svim fabrikama.</code>	<code>[-0.028540322557091713, -0.0467195138335228, -0.06506078690290451, 0.010401058942079544, 0.02002905309200287, ...]</code>
  <code>Here you can sing and dance all night long and for good fun you can blame music that is deffinetely best in town.</code>	<code>Na ovom mestu se igra i peva do zore i to je uvek tako, za tako dobar provod definitvno je kriva muzika koja je malo je reći najbolja i najtraženija u gradu.</code>	<code>[-0.027667256072163582, -0.0402180515229702, 0.022323550656437874, -0.005031000357121229, 0.032226040959358215, ...]</code>

• Loss: <code>MSELoss</code>

Training Hyperparameters

Non-Default Hyperparameters

• eval_strategy: steps
• per_device_train_batch_size: 16
• per_device_eval_batch_size: 16
• gradient_accumulation_steps: 2
• learning_rate: 2e-05
• num_train_epochs: 6
• warmup_ratio: 0.1
• fp16: 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: 16
• per_device_eval_batch_size: 16
• per_gpu_train_batch_size: None
• per_gpu_eval_batch_size: None
• gradient_accumulation_steps: 2
• 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: 6
• 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
• 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.