BGE base SQL Matryoshka

This is a sentence-transformers model finetuned from BAAI/bge-base-en-v1.5 on the json dataset. 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: BAAI/bge-base-en-v1.5
Maximum Sequence Length: 512 tokens
Output Dimensionality: 768 dimensions
Similarity Function: Cosine Similarity
Training Dataset:
- json
Language: en
License: apache-2.0

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': True}) with Transformer model: BertModel 
  (1): Pooling({'word_embedding_dimension': 768, '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("dat-ai/bge-base-for_text2sql")
# Run inference
sentences = [
    '\n  Given  the Column informations, generate an SQL query for the following question:\n  Column: Nomination | Actors Name | Film Name | Director | Country\n  Question: What was the film Falling up nominated for?\n  SQL Query: SELECT Nomination FROM table WHERE Film Name = Falling Up\n  ',
    'What was the film Falling up nominated for?',
    'Who wrote an episode watched by 19.01 million US viewers?',
]
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

Information Retrieval

Datasets: dim_768, dim_512, dim_256, dim_128 and dim_64
Evaluated with InformationRetrievalEvaluator

Metric	dim_768	dim_512	dim_256	dim_128	dim_64
cosine_accuracy@1	0.4676	0.4678	0.4675	0.4677	0.4678
cosine_accuracy@3	0.4697	0.4697	0.4697	0.4696	0.4696
cosine_accuracy@5	0.4697	0.4697	0.4697	0.4698	0.4696
cosine_accuracy@10	0.4697	0.4697	0.4698	0.4698	0.4697
cosine_precision@1	0.4676	0.4678	0.4675	0.4677	0.4678
cosine_precision@3	0.1566	0.1566	0.1566	0.1565	0.1565
cosine_precision@5	0.0939	0.0939	0.0939	0.094	0.0939
cosine_precision@10	0.047	0.047	0.047	0.047	0.047
cosine_recall@1	0.4676	0.4678	0.4675	0.4677	0.4678
cosine_recall@3	0.4697	0.4697	0.4697	0.4696	0.4696
cosine_recall@5	0.4697	0.4697	0.4697	0.4698	0.4696
cosine_recall@10	0.4697	0.4697	0.4698	0.4698	0.4697
cosine_ndcg@10	0.4689	0.469	0.4689	0.4689	0.469
cosine_mrr@10	0.4686	0.4687	0.4686	0.4687	0.4687
cosine_map@100	0.4686	0.4687	0.4686	0.4687	0.4687

Training Details

Training Dataset

json

Dataset: json
Size: 56,355 training samples
Columns: context and question
Approximate statistics based on the first 1000 samples:
context question
type string string
details
min: 45 tokens
mean: 72.61 tokens
max: 196 tokens

min: 7 tokens
mean: 15.41 tokens
max: 36 tokens

	context	question
type	string	string
details	min: 45 tokens mean: 72.61 tokens max: 196 tokens	min: 7 tokens mean: 15.41 tokens max: 36 tokens

Samples:

context	question
`Given the Column informations, generate an SQL query for the following question: Column: State/territory`	Text/background colour
`Given the Column informations, generate an SQL query for the following question: Column: State/territory`	Text/background colour
`Given the Column informations, generate an SQL query for the following question: Column: State/territory`	Text/background colour

Loss: MatryoshkaLoss with these parameters:

{
    "loss": "MultipleNegativesRankingLoss",
    "matryoshka_dims": [
        768,
        512
    ],
    "matryoshka_weights": [
        1,
        1
    ],
    "n_dims_per_step": -1
}

Training Hyperparameters

Non-Default Hyperparameters

eval_strategy: epoch
per_device_train_batch_size: 16
gradient_accumulation_steps: 8
learning_rate: 2e-05
num_train_epochs: 4
lr_scheduler_type: cosine
warmup_ratio: 0.1
fp16: True
load_best_model_at_end: True
optim: adamw_torch_fused
batch_sampler: no_duplicates

All Hyperparameters

Click to expand

overwrite_output_dir: False
do_predict: False
eval_strategy: epoch
prediction_loss_only: True
per_device_train_batch_size: 16
per_device_eval_batch_size: 8
per_gpu_train_batch_size: None
per_gpu_eval_batch_size: None
gradient_accumulation_steps: 8
eval_accumulation_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: 4
max_steps: -1
lr_scheduler_type: cosine
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: 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_fused
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
prompts: None
batch_sampler: no_duplicates
multi_dataset_batch_sampler: proportional

Training Logs