MiniLM-L6-v2 finetuned on allpanelexch9.co API routes

This is a sentence-transformers model finetuned from sentence-transformers/all-MiniLM-L6-v2 on the json dataset. It maps inputs to a 384-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, classification, clustering, and more.

Model Details

Model Description

Model Type: Sentence Transformer
Base model: sentence-transformers/all-MiniLM-L6-v2
Maximum Sequence Length: 256 tokens
Output Dimensionality: 384 dimensions
Similarity Function: Cosine Similarity
Supported Modality: Text
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({'transformer_task': 'feature-extraction', 'modality_config': {'text': {'method': 'forward', 'method_output_name': 'last_hidden_state'}}, 'module_output_name': 'token_embeddings', 'architecture': 'BertModel'})
  (1): Pooling({'embedding_dimension': 384, 'pooling_mode': 'mean', 'include_prompt': True})
  (2): Normalize({'module_input_name': 'sentence_embedding', 'module_output_name': 'sentence_embedding'})
)

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("Shaurya2020/allpanel-api-minilm")
# Run inference
queries = [
    'allpanelexch9 auth 2fa authon',
]
documents = [
    'POST https://allpanelexch9.co/api/front/authon (auth_2fa)',
    'POST https://allpanelexch9.co/api/front/accountstatement (account)',
    'POST https://allpanelexch9.co/api/front/save-subscription (account)',
]
query_embeddings = model.encode_query(queries)
document_embeddings = model.encode_document(documents)
print(query_embeddings.shape, document_embeddings.shape)
# [1, 384] [3, 384]

# Get the similarity scores for the embeddings
similarities = model.similarity(query_embeddings, document_embeddings)
print(similarities)
# tensor([[0.8341, 0.3827, 0.2623]])

Evaluation

Metrics

Information Retrieval

Dataset: allpanel-api
Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.8571
cosine_accuracy@5	0.8571
cosine_accuracy@10	0.8571
cosine_precision@1	0.8571
cosine_precision@3	0.8571
cosine_precision@5	0.8571
cosine_precision@10	0.8571
cosine_recall@1	0.0466
cosine_recall@3	0.1398
cosine_recall@5	0.233
cosine_recall@10	0.4661
cosine_ndcg@10	0.8571
cosine_mrr@10	0.8571
cosine_map@100	0.8471

Training Details

Training Dataset

json

Dataset: json
Size: 138 training samples
Columns: anchor and positive
Approximate statistics based on the first 100 samples:
anchor positive
type string string

modality text text
details
min: 10 tokens
mean: 13.69 tokens
max: 19 tokens

min: 24 tokens
mean: 28.98 tokens
max: 35 tokens

	anchor	positive
type	string	string
modality	text	text
details	min: 10 tokens mean: 13.69 tokens max: 19 tokens	min: 24 tokens mean: 28.98 tokens max: 35 tokens

Samples:

anchor	positive
`allpanelexch9 account acceptrules`	`POST https://allpanelexch9.co/api/front/acceptrules (account)`
`allpanelexch9 account accountstatement`	`POST https://allpanelexch9.co/api/front/accountstatement (account)`
`allpanelexch9 account activity`	`POST https://allpanelexch9.co/api/front/activity (account)`

Loss: MultipleNegativesRankingLoss with these parameters:

{
    "scale": 20.0,
    "similarity_fct": "cos_sim",
    "gather_across_devices": false,
    "directions": [
        "query_to_doc"
    ],
    "partition_mode": "joint",
    "hardness_mode": null,
    "hardness_strength": 0.0
}

Evaluation Dataset

json

Dataset: json
Size: 13 evaluation samples
Columns: anchor and positive
Approximate statistics based on the first 13 samples:
anchor positive
type string string

modality text text
details
min: 10 tokens
mean: 12.31 tokens
max: 15 tokens

min: 24 tokens
mean: 26.54 tokens
max: 30 tokens

	anchor	positive
type	string	string
modality	text	text
details	min: 10 tokens mean: 12.31 tokens max: 15 tokens	min: 24 tokens mean: 26.54 tokens max: 30 tokens

Samples:

anchor	positive
`allpanelexch9 account acceptrules`	`POST https://allpanelexch9.co/api/front/acceptrules (account)`
`allpanelexch9 account accountstatement`	`POST https://allpanelexch9.co/api/front/accountstatement (account)`
`allpanelexch9 account activity`	`POST https://allpanelexch9.co/api/front/activity (account)`

Loss: MultipleNegativesRankingLoss with these parameters:

{
    "scale": 20.0,
    "similarity_fct": "cos_sim",
    "gather_across_devices": false,
    "directions": [
        "query_to_doc"
    ],
    "partition_mode": "joint",
    "hardness_mode": null,
    "hardness_strength": 0.0
}

Training Hyperparameters

Non-Default Hyperparameters

per_device_train_batch_size: 16
learning_rate: 2e-05
warmup_steps: 0.1
weight_decay: 0.01
per_device_eval_batch_size: 16
load_best_model_at_end: True
seed: 12
batch_sampler: no_duplicates

All Hyperparameters

Click to expand

per_device_train_batch_size: 16
num_train_epochs: 3
max_steps: -1
learning_rate: 2e-05
lr_scheduler_type: linear
lr_scheduler_kwargs: None
warmup_steps: 0.1
optim: adamw_torch_fused
optim_args: None
weight_decay: 0.01
adam_beta1: 0.9
adam_beta2: 0.999
adam_epsilon: 1e-08
optim_target_modules: None
gradient_accumulation_steps: 1
average_tokens_across_devices: True
max_grad_norm: 1.0
label_smoothing_factor: 0.0
bf16: False
fp16: False
bf16_full_eval: False
fp16_full_eval: False
tf32: None
gradient_checkpointing: False
gradient_checkpointing_kwargs: None
torch_compile: False
torch_compile_backend: None
torch_compile_mode: None
use_liger_kernel: False
liger_kernel_config: None
use_cache: False
neftune_noise_alpha: None
torch_empty_cache_steps: None
auto_find_batch_size: False
log_on_each_node: True
logging_nan_inf_filter: True
include_num_input_tokens_seen: no
log_level: passive
log_level_replica: warning
disable_tqdm: False
project: huggingface
trackio_space_id: None
trackio_bucket_id: None
trackio_static_space_id: None
per_device_eval_batch_size: 16
prediction_loss_only: True
eval_on_start: False
eval_do_concat_batches: True
eval_use_gather_object: False
eval_accumulation_steps: None
include_for_metrics: []
batch_eval_metrics: False
save_only_model: False
save_on_each_node: False
enable_jit_checkpoint: False
push_to_hub: False
hub_private_repo: None
hub_model_id: None
hub_strategy: every_save
hub_always_push: False
hub_revision: None
load_best_model_at_end: True
ignore_data_skip: False
restore_callback_states_from_checkpoint: False
full_determinism: False
seed: 12
data_seed: None
use_cpu: False
accelerator_config: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
parallelism_config: None
dataloader_drop_last: False
dataloader_num_workers: 0
dataloader_pin_memory: True
dataloader_persistent_workers: False
dataloader_prefetch_factor: None
dataloader_multiprocessing_context: None
dataloader_in_order: True
remove_unused_columns: True
label_names: None
train_sampling_strategy: random
length_column_name: length
ddp_find_unused_parameters: None
ddp_bucket_cap_mb: None
ddp_broadcast_buffers: False
ddp_static_graph: None
ddp_backend: None
ddp_timeout: 1800
fsdp: None
fsdp_config: None
deepspeed: None
debug: []
skip_memory_metrics: True
do_predict: False
resume_from_checkpoint: None
local_rank: -1
prompts: None
batch_sampler: no_duplicates
multi_dataset_batch_sampler: proportional
router_mapping: {}
learning_rate_mapping: {}
warmup_ratio: None

Training Logs

Epoch	Step	Training Loss	Validation Loss	allpanel-api_cosine_ndcg@10
-1	-1	-	-	0.8287
0.1111	1	0.4021	-	-
0.2222	2	0.3945	-	-
0.3333	3	0.2125	-	-
0.4444	4	0.1483	-	-
0.5556	5	0.2181	-	-
0.6667	6	0.2660	-	-
0.7778	7	0.1646	-	-
0.8889	8	0.1251	-	-
1.0	9	0.046	0.1124	0.8571
1.1111	10	0.0401	-	-
1.2222	11	0.0467	-	-
1.3333	12	0.0109	-	-
1.4444	13	0.2869	-	-
1.5556	14	0.0594	-	-
1.6667	15	0.0904	-	-
1.7778	16	0.0843	-	-
1.8889	17	0.0857	-	-
2.0	18	0.0003	0.0480	0.8571
2.1111	19	0.0337	-	-
2.2222	20	0.0281	-	-
2.3333	21	0.0118	-	-
2.4444	22	0.0060	-	-
2.5556	23	0.0058	-	-
2.6667	24	0.0051	-	-
2.7778	25	0.0183	-	-
2.8889	26	0.0460	-	-
3.0	27	0.0308	0.0366	0.8571
-1	-1	-	-	0.8571

The bold row denotes the saved checkpoint.

Training Time

Training: 7.3 seconds
Evaluation: 0.5 seconds
Total: 7.9 seconds

Framework Versions

Python: 3.14.6
Sentence Transformers: 6.0.0
Transformers: 5.16.1
PyTorch: 2.13.0
Accelerate: 1.14.0
Datasets: 5.0.1
Tokenizers: 0.23.1

Additional Resources

Training and Finetuning Embedding Models with Sentence Transformers: the end-to-end guide for training or finetuning Sentence Transformer models.
Introduction to Matryoshka Embedding Models: variable-size embeddings that can be truncated with minimal quality loss.
Binary and Scalar Embedding Quantization for Significantly Faster & Cheaper Retrieval: post-training compression of embedding vectors.
Multimodal Embedding & Reranker Models with Sentence Transformers: use text, image, audio, and video models through the same API.
Training and Finetuning Multimodal Embedding & Reranker Models with Sentence Transformers: train multimodal embedding models, with a Visual Document Retrieval walkthrough.

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{oord2019representationlearningcontrastivepredictive,
      title={Representation Learning with Contrastive Predictive Coding},
      author={Aaron van den Oord and Yazhe Li and Oriol Vinyals},
      year={2019},
      eprint={1807.03748},
      archivePrefix={arXiv},
      primaryClass={cs.LG},
      url={https://arxiv.org/abs/1807.03748},
}