SentenceTransformer based on WhereIsAI/UAE-Large-V1
This is a sentence-transformers model finetuned from WhereIsAI/UAE-Large-V1. It maps sentences & paragraphs to a 1024-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: WhereIsAI/UAE-Large-V1
- Maximum Sequence Length: 512 tokens
- Output Dimensionality: 1024 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: BertModel
(1): Pooling({'word_embedding_dimension': 1024, '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})
)
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("Naveen20o1/UAE_Large_V1_nav2")
# Run inference
sentences = [
'account_id',
'ID',
'Quantity',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 1024]
# 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 | 0.8925 |
spearman_cosine | 0.8235 |
pearson_manhattan | 0.8606 |
spearman_manhattan | 0.8165 |
pearson_euclidean | 0.8608 |
spearman_euclidean | 0.8151 |
pearson_dot | 0.8741 |
spearman_dot | 0.834 |
pearson_max | 0.8925 |
spearman_max | 0.834 |
Semantic Similarity
- Dataset:
sts-dev_test
- Evaluated with
EmbeddingSimilarityEvaluator
Metric | Value |
---|---|
pearson_cosine | 0.7743 |
spearman_cosine | 0.735 |
pearson_manhattan | 0.8012 |
spearman_manhattan | 0.7482 |
pearson_euclidean | 0.7974 |
spearman_euclidean | 0.7482 |
pearson_dot | 0.7746 |
spearman_dot | 0.7482 |
pearson_max | 0.8012 |
spearman_max | 0.7482 |
Training Details
Training Dataset
Unnamed Dataset
- Size: 1,100 training samples
- Columns:
sentence1
,sentence2
, andscore
- Approximate statistics based on the first 1000 samples:
sentence1 sentence2 score type string string float details - min: 3 tokens
- mean: 4.32 tokens
- max: 10 tokens
- min: 3 tokens
- mean: 3.12 tokens
- max: 4 tokens
- min: 0.0
- mean: 0.51
- max: 1.0
- Samples:
sentence1 sentence2 score enrollment
Quantity
1.0
instrument
Artifact
1.0
stock_level
Geographical
0.0
- Loss:
CoSENTLoss
with these parameters:{ "scale": 20.0, "similarity_fct": "pairwise_cos_sim" }
Evaluation Dataset
Unnamed Dataset
- Size: 100 evaluation samples
- Columns:
sentence1
,sentence2
, andscore
- Approximate statistics based on the first 1000 samples:
sentence1 sentence2 score type string string float details - min: 3 tokens
- mean: 4.29 tokens
- max: 7 tokens
- min: 3 tokens
- mean: 3.09 tokens
- max: 4 tokens
- min: 0.0
- mean: 0.56
- max: 1.0
- Samples:
sentence1 sentence2 score review
Quantity
0.0
machinery
Artifact
1.0
locality
Geographical
1.0
- Loss:
CoSENTLoss
with these parameters:{ "scale": 20.0, "similarity_fct": "pairwise_cos_sim" }
Training Hyperparameters
Non-Default Hyperparameters
eval_strategy
: stepsper_device_train_batch_size
: 16per_device_eval_batch_size
: 16learning_rate
: 2e-05num_train_epochs
: 11warmup_ratio
: 0.1fp16
: True
All Hyperparameters
Click to expand
overwrite_output_dir
: Falsedo_predict
: Falseeval_strategy
: stepsprediction_loss_only
: Trueper_device_train_batch_size
: 16per_device_eval_batch_size
: 16per_gpu_train_batch_size
: Noneper_gpu_eval_batch_size
: Nonegradient_accumulation_steps
: 1eval_accumulation_steps
: Nonelearning_rate
: 2e-05weight_decay
: 0.0adam_beta1
: 0.9adam_beta2
: 0.999adam_epsilon
: 1e-08max_grad_norm
: 1.0num_train_epochs
: 11max_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
: Truefp16_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
: batch_samplermulti_dataset_batch_sampler
: proportional
Training Logs
Epoch | Step | Training Loss | loss | sts-dev_spearman_cosine | sts-dev_test_spearman_cosine |
---|---|---|---|---|---|
0.7246 | 50 | 2.9649 | - | - | - |
1.4493 | 100 | 1.0967 | 1.4481 | 0.8368 | - |
2.1739 | 150 | 0.5062 | - | - | - |
2.8986 | 200 | 0.3909 | 1.3760 | 0.8242 | - |
3.6232 | 250 | 0.2006 | - | - | - |
4.3478 | 300 | 0.0324 | 2.3098 | 0.8124 | - |
5.0725 | 350 | 0.0564 | - | - | - |
5.7971 | 400 | 0.0729 | 1.5758 | 0.8193 | - |
6.5217 | 450 | 0.0051 | - | - | - |
7.2464 | 500 | 0.0091 | 2.2818 | 0.8165 | - |
7.9710 | 550 | 0.0084 | - | - | - |
8.6957 | 600 | 0.0319 | 1.9056 | 0.8144 | - |
9.4203 | 650 | 0.0023 | - | - | - |
10.1449 | 700 | 0.0136 | 2.1295 | 0.8235 | - |
10.8696 | 750 | 0.0156 | - | - | - |
11.0 | 759 | - | - | - | 0.7350 |
Framework Versions
- Python: 3.10.12
- Sentence Transformers: 3.0.1
- Transformers: 4.41.2
- PyTorch: 2.3.0+cu121
- Accelerate: 0.31.0
- Datasets: 2.20.0
- 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",
}
CoSENTLoss
@online{kexuefm-8847,
title={CoSENT: A more efficient sentence vector scheme than Sentence-BERT},
author={Su Jianlin},
year={2022},
month={Jan},
url={https://kexue.fm/archives/8847},
}
- Downloads last month
- 5
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 Naveen20o1/UAE_Large_V1_nav2
Base model
WhereIsAI/UAE-Large-V1Evaluation results
- Pearson Cosine on sts devself-reported0.892
- Spearman Cosine on sts devself-reported0.824
- Pearson Manhattan on sts devself-reported0.861
- Spearman Manhattan on sts devself-reported0.817
- Pearson Euclidean on sts devself-reported0.861
- Spearman Euclidean on sts devself-reported0.815
- Pearson Dot on sts devself-reported0.874
- Spearman Dot on sts devself-reported0.834
- Pearson Max on sts devself-reported0.892
- Spearman Max on sts devself-reported0.834