SentenceTransformer based on distilbert/distilroberta-base
This is a sentence-transformers model finetuned from distilbert/distilroberta-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: distilbert/distilroberta-base
- 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: RobertaModel
(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("trbeers/distilroberta-base-nli-v0")
# Run inference
sentences = [
'Ability to manage TikTok Shop setup and troubleshoot operational issues effectively.',
'Troubleshot various operational issues during the setup of a TikTok Shop',
'Handled customer support queries for social media platforms',
]
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 | 0.7649 |
spearman_cosine | 0.7805 |
pearson_manhattan | 0.7679 |
spearman_manhattan | 0.7676 |
pearson_euclidean | 0.7663 |
spearman_euclidean | 0.7664 |
pearson_dot | 0.4592 |
spearman_dot | 0.4523 |
pearson_max | 0.7679 |
spearman_max | 0.7805 |
Semantic Similarity
- Dataset:
sts-test
- Evaluated with
EmbeddingSimilarityEvaluator
Metric | Value |
---|---|
pearson_cosine | 0.7168 |
spearman_cosine | 0.7027 |
pearson_manhattan | 0.7172 |
spearman_manhattan | 0.6972 |
pearson_euclidean | 0.7149 |
spearman_euclidean | 0.6949 |
pearson_dot | 0.4195 |
spearman_dot | 0.4186 |
pearson_max | 0.7172 |
spearman_max | 0.7027 |
Training Details
Training Dataset
Unnamed Dataset
- Size: 2,036 training samples
- Columns:
anchor
,positive
, andnegative
- Approximate statistics based on the first 1000 samples:
anchor positive negative type string string string details - min: 7 tokens
- mean: 16.49 tokens
- max: 36 tokens
- min: 7 tokens
- mean: 12.04 tokens
- max: 24 tokens
- min: 5 tokens
- mean: 9.27 tokens
- max: 15 tokens
- Samples:
anchor positive negative Sensitivity to the needs of patients, families, and physicians to deliver compassionate care.
worked closely with families to address patient concerns
specialized in technical equipment management without direct patient contact
Ability to lift 25 lbs. or more as required for handling athletic equipment.
Handled and organized equipment, ensuring safe lifting of heavy items
Coordinated scheduling for team practices and meetings
The candidate should have significant development experience, preferably around 10 years.
developed and implemented data architecture projects for a decade
worked in customer service for 5 years
- Loss:
MultipleNegativesRankingLoss
with these parameters:{ "scale": 20.0, "similarity_fct": "cos_sim" }
Evaluation Dataset
Unnamed Dataset
- Size: 510 evaluation samples
- Columns:
anchor
,positive
, andnegative
- Approximate statistics based on the first 1000 samples:
anchor positive negative type string string string details - min: 8 tokens
- mean: 16.8 tokens
- max: 37 tokens
- min: 7 tokens
- mean: 12.08 tokens
- max: 21 tokens
- min: 5 tokens
- mean: 9.28 tokens
- max: 16 tokens
- Samples:
anchor positive negative Qualified to provide personalized and friendly client interactions
Assisted clients with inquiries and ensured a welcoming environment
Conducted market research for product development
Understanding of network architecture principles and design patterns is critical.
Designed and implemented network architectures for cloud-based solutions
Managed on-premises server infrastructure
Knowledge of cloud technologies and their implications for customer engagement.
Managed customer onboarding for cloud-based services
Handled sales inquiries for software licenses
- Loss:
MultipleNegativesRankingLoss
with these parameters:{ "scale": 20.0, "similarity_fct": "cos_sim" }
Training Hyperparameters
Non-Default Hyperparameters
eval_strategy
: stepsper_device_train_batch_size
: 128per_device_eval_batch_size
: 128num_train_epochs
: 1warmup_ratio
: 0.1batch_sampler
: no_duplicates
All Hyperparameters
Click to expand
overwrite_output_dir
: Falsedo_predict
: Falseeval_strategy
: stepsprediction_loss_only
: Trueper_device_train_batch_size
: 128per_device_eval_batch_size
: 128per_gpu_train_batch_size
: Noneper_gpu_eval_batch_size
: Nonegradient_accumulation_steps
: 1eval_accumulation_steps
: Nonelearning_rate
: 5e-05weight_decay
: 0.0adam_beta1
: 0.9adam_beta2
: 0.999adam_epsilon
: 1e-08max_grad_norm
: 1.0num_train_epochs
: 1max_steps
: -1lr_scheduler_type
: linearlr_scheduler_kwargs
: {}warmup_ratio
: 0.1warmup_steps
: 0log_level
: passivelog_level_replica
: warninglog_on_each_node
: Truelogging_nan_inf_filter
: Truesave_safetensors
: Truesave_on_each_node
: Falsesave_only_model
: Falserestore_callback_states_from_checkpoint
: Falseno_cuda
: Falseuse_cpu
: Falseuse_mps_device
: Falseseed
: 42data_seed
: Nonejit_mode_eval
: Falseuse_ipex
: Falsebf16
: Falsefp16
: Falsefp16_opt_level
: O1half_precision_backend
: autobf16_full_eval
: Falsefp16_full_eval
: Falsetf32
: Nonelocal_rank
: 0ddp_backend
: Nonetpu_num_cores
: Nonetpu_metrics_debug
: Falsedebug
: []dataloader_drop_last
: Falsedataloader_num_workers
: 0dataloader_prefetch_factor
: Nonepast_index
: -1disable_tqdm
: Falseremove_unused_columns
: Truelabel_names
: Noneload_best_model_at_end
: Falseignore_data_skip
: Falsefsdp
: []fsdp_min_num_params
: 0fsdp_config
: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}fsdp_transformer_layer_cls_to_wrap
: Noneaccelerator_config
: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}deepspeed
: Nonelabel_smoothing_factor
: 0.0optim
: adamw_torchoptim_args
: Noneadafactor
: Falsegroup_by_length
: Falselength_column_name
: lengthddp_find_unused_parameters
: Noneddp_bucket_cap_mb
: Noneddp_broadcast_buffers
: Falsedataloader_pin_memory
: Truedataloader_persistent_workers
: Falseskip_memory_metrics
: Trueuse_legacy_prediction_loop
: Falsepush_to_hub
: Falseresume_from_checkpoint
: Nonehub_model_id
: Nonehub_strategy
: every_savehub_private_repo
: Falsehub_always_push
: Falsegradient_checkpointing
: Falsegradient_checkpointing_kwargs
: Noneinclude_inputs_for_metrics
: Falseeval_do_concat_batches
: Truefp16_backend
: autopush_to_hub_model_id
: Nonepush_to_hub_organization
: Nonemp_parameters
:auto_find_batch_size
: Falsefull_determinism
: Falsetorchdynamo
: Noneray_scope
: lastddp_timeout
: 1800torch_compile
: Falsetorch_compile_backend
: Nonetorch_compile_mode
: Nonedispatch_batches
: Nonesplit_batches
: Noneinclude_tokens_per_second
: Falseinclude_num_input_tokens_seen
: Falseneftune_noise_alpha
: Noneoptim_target_modules
: Nonebatch_eval_metrics
: Falsebatch_sampler
: no_duplicatesmulti_dataset_batch_sampler
: proportional
Training Logs
Epoch | Step | loss | sts-dev_spearman_cosine | sts-test_spearman_cosine |
---|---|---|---|---|
0 | 0 | - | 0.6375 | - |
0.625 | 10 | 2.0178 | 0.7805 | - |
1.0 | 16 | - | - | 0.7027 |
Framework Versions
- Python: 3.10.11
- Sentence Transformers: 3.0.1
- Transformers: 4.41.2
- PyTorch: 2.3.1
- Accelerate: 0.31.0
- Datasets: 2.19.1
- 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",
}
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}
}
- Downloads last month
- 2
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.
Model tree for trbeers/distilroberta-base-nli-v0
Base model
distilbert/distilroberta-base
Finetuned
this model
Evaluation results
- Pearson Cosine on sts devself-reported0.765
- Spearman Cosine on sts devself-reported0.780
- Pearson Manhattan on sts devself-reported0.768
- Spearman Manhattan on sts devself-reported0.768
- Pearson Euclidean on sts devself-reported0.766
- Spearman Euclidean on sts devself-reported0.766
- Pearson Dot on sts devself-reported0.459
- Spearman Dot on sts devself-reported0.452
- Pearson Max on sts devself-reported0.768
- Spearman Max on sts devself-reported0.780