SentenceTransformer based on microsoft/deberta-v3-base

This is a sentence-transformers model finetuned from microsoft/deberta-v3-base on the negation-triplets, vitaminc-pairs, scitail-pairs-qa, scitail-pairs-pos, xsum-pairs, sciq_pairs, qasc_pairs, openbookqa_pairs, msmarco_pairs, nq_pairs, trivia_pairs, gooaq_pairs, paws-pos and global_dataset datasets. 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: microsoft/deberta-v3-base
Maximum Sequence Length: 512 tokens
Output Dimensionality: 768 tokens
Similarity Function: Cosine Similarity
Training Datasets:
- negation-triplets
- vitaminc-pairs
- scitail-pairs-qa
- scitail-pairs-pos
- xsum-pairs
- sciq_pairs
- qasc_pairs
- openbookqa_pairs
- msmarco_pairs
- nq_pairs
- trivia_pairs
- gooaq_pairs
- paws-pos
- global_dataset
Language: en

Evaluation

Metrics

Semantic Similarity

Dataset: sts-test
Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	0.8253
spearman_cosine	0.8709
pearson_manhattan	0.8653
spearman_manhattan	0.8667
pearson_euclidean	0.8671
spearman_euclidean	0.8681
pearson_dot	0.7827
spearman_dot	0.7685
pearson_max	0.8671
spearman_max	0.8709

Training Hyperparameters

Non-Default Hyperparameters

eval_strategy: steps
per_device_train_batch_size: 96
per_device_eval_batch_size: 68
learning_rate: 3.5e-05
weight_decay: 0.0005
num_train_epochs: 2
lr_scheduler_type: cosine_with_min_lr
lr_scheduler_kwargs: {'num_cycles': 3.5, 'min_lr': 1.5e-05}
warmup_ratio: 0.33
save_safetensors: False
fp16: True
push_to_hub: True
hub_model_id: bobox/DeBERTa3-base-STr-CosineWaves-checkpoints-tmp
hub_strategy: all_checkpoints
batch_sampler: no_duplicates

All Hyperparameters

Click to expand

overwrite_output_dir: False
do_predict: False
eval_strategy: steps
prediction_loss_only: True
per_device_train_batch_size: 96
per_device_eval_batch_size: 68
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: 3.5e-05
weight_decay: 0.0005
adam_beta1: 0.9
adam_beta2: 0.999
adam_epsilon: 1e-08
max_grad_norm: 1.0
num_train_epochs: 2
max_steps: -1
lr_scheduler_type: cosine_with_min_lr
lr_scheduler_kwargs: {'num_cycles': 3.5, 'min_lr': 1.5e-05}
warmup_ratio: 0.33
warmup_steps: 0
log_level: passive
log_level_replica: warning
log_on_each_node: True
logging_nan_inf_filter: True
save_safetensors: False
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: True
resume_from_checkpoint: None
hub_model_id: bobox/DeBERTa3-base-STr-CosineWaves-checkpoints-tmp
hub_strategy: all_checkpoints
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: no_duplicates
multi_dataset_batch_sampler: proportional

Framework Versions

Python: 3.10.14
Sentence Transformers: 3.0.1
Transformers: 4.44.0
PyTorch: 2.4.0
Accelerate: 0.33.0
Datasets: 2.21.0
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",
}

bobox
/

DeBERTa3-base-STr-CosineWaves