You can deploy this model and start earning money today!

Views

No views yet

MPNet base trained on AllNLI triplets

Name: MiniLM-L6-H384-uncased-gooaq-no-asym
Availability: InStock

This is a sentence-transformers model finetuned from nreimers/MiniLM-L6-H384-uncased on the gooaq dataset. It maps sentences & paragraphs to a 384-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: nreimers/MiniLM-L6-H384-uncased
Maximum Sequence Length: 512 tokens
Output Dimensionality: 384 dimensions
Similarity Function: Cosine Similarity
Training Dataset:
- gooaq
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': False}) with Transformer model: BertModel 
  (1): Pooling({'word_embedding_dimension': 384, '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.

python

from sentence_transformers import SentenceTransformer

# Download from the 🤗 Hub
model = SentenceTransformer("tomaarsen/MiniLM-L6-H384-uncased-gooaq-no-asym")
# Run inference
sentences = [
    'is jordyn a boy or girl?',
    'Gender Popularity of the Name "Jordyn" Jordyn: It\'s a girl! Since 1880, a total of 2,696 boys have been given the name Jordyn while 39,618 girls were named Jordyn.',
    'Currently there is no research showing that juice cleanses are beneficial to weight loss or that they should be recommended at all. Even though it is possible to cut a significant amount of calories by only drinking juice, you could also be missing out on some essential nutrition - like protein, fiber and healthy fats.',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 384]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)
# [3, 3]

Evaluation

Metrics

Information Retrieval

Dataset: gooaq-dev
Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.5589
cosine_accuracy@3	0.7234
cosine_accuracy@5	0.7801
cosine_accuracy@10	0.8456
cosine_precision@1	0.5589
cosine_precision@3	0.2411
cosine_precision@5	0.156
cosine_precision@10	0.0846
cosine_recall@1	0.5589
cosine_recall@3	0.7234
cosine_recall@5	0.7801
cosine_recall@10	0.8456
cosine_ndcg@10	0.7
cosine_mrr@10	0.6536
cosine_map@100	0.6594

Training Details

Training Dataset

gooaq

Dataset: gooaq at b089f72
Size: 3,012,496 training samples
Columns: question and answer
Approximate statistics based on the first 1000 samples:
question answer
type string string
details
min: 8 tokens
mean: 11.86 tokens
max: 21 tokens
min: 14 tokens
mean: 60.48 tokens
max: 138 tokens

Samples:

question	answer
`what is the difference between broilers and layers?`	`An egg laying poultry is called egger or layer whereas broilers are reared for obtaining meat. So a layer should be able to produce more number of large sized eggs, without growing too much. On the other hand, a broiler should yield more meat and hence should be able to grow well.`
`what is the difference between chronological order and spatial order?`	`As a writer, you should always remember that unlike chronological order and the other organizational methods for data, spatial order does not take into account the time. Spatial order is primarily focused on the location. All it does is take into account the location of objects and not the time.`
`is kamagra same as viagra?`	`Kamagra is thought to contain the same active ingredient as Viagra, sildenafil citrate. In theory, it should work in much the same way as Viagra, taking about 45 minutes to take effect, and lasting for around 4-6 hours. However, this will vary from person to person.`

Loss: MultipleNegativesRankingLoss with these parameters:
json
1{ 2 "scale": 20.0, 3 "similarity_fct": "cos_sim" 4}

Evaluation Dataset

gooaq

Dataset: gooaq at b089f72
Size: 3,012,496 evaluation samples
Columns: question and answer
Approximate statistics based on the first 1000 samples:
question answer
type string string
details
min: 8 tokens
mean: 11.88 tokens
max: 22 tokens
min: 14 tokens
mean: 61.03 tokens
max: 127 tokens

Samples:

question	answer
`how do i program my directv remote with my tv?`	`['Press MENU on your remote.', 'Select Settings & Help > Settings > Remote Control > Program Remote.', 'Choose the device (TV, audio, DVD) you wish to program. ... ', 'Follow the on-screen prompts to complete programming.']`
`are rodrigues fruit bats nocturnal?`	`Before its numbers were threatened by habitat destruction, storms, and hunting, some of those groups could number 500 or more members. Sunrise, sunset. Rodrigues fruit bats are most active at dawn, at dusk, and at night.`
`why does your heart rate increase during exercise bbc bitesize?`	`During exercise there is an increase in physical activity and muscle cells respire more than they do when the body is at rest. The heart rate increases during exercise. The rate and depth of breathing increases - this makes sure that more oxygen is absorbed into the blood, and more carbon dioxide is removed from it.`

Loss: MultipleNegativesRankingLoss with these parameters:
json
1{ 2 "scale": 20.0, 3 "similarity_fct": "cos_sim" 4}

Training Hyperparameters

Non-Default Hyperparameters

eval_strategy: steps
per_device_train_batch_size: 128
per_device_eval_batch_size: 128
learning_rate: 2e-05
num_train_epochs: 1
warmup_ratio: 0.1
seed: 24
bf16: True
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: 128
per_device_eval_batch_size: 128
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: 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: 1
max_steps: -1
lr_scheduler_type: linear
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: 24
data_seed: None
jit_mode_eval: False
use_ipex: False
bf16: True
fp16: False
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: False
resume_from_checkpoint: None
hub_model_id: None
hub_strategy: every_save
hub_private_repo: None
hub_always_push: False
gradient_checkpointing: False
gradient_checkpointing_kwargs: None
include_inputs_for_metrics: False
include_for_metrics: []
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
use_liger_kernel: False
eval_use_gather_object: False
average_tokens_across_devices: False
prompts: None
batch_sampler: no_duplicates
multi_dataset_batch_sampler: proportional

Training Logs

Epoch	Step	Training Loss	Validation Loss	gooaq-dev_cosine_ndcg@10
-1	-1	-	-	0.0303
0.0003	1	4.2106	-	-
0.0128	50	4.1241	-	-
0.0256	100	3.3791	-	-
0.0384	150	1.8925	-	-
0.0512	200	1.1582	-	-
0.0640	250	0.8751	-	-
0.0768	300	0.6851	-	-
0.0896	350	0.5779	-	-
0.1024	400	0.5251	-	-
0.1152	450	0.4873	-	-
0.1280	500	0.4467	0.3056	0.6054
0.1408	550	0.3989	-	-
0.1536	600	0.398	-	-
0.1664	650	0.3708	-	-
0.1792	700	0.3656	-	-
0.1920	750	0.3382	-	-
0.2048	800	0.3333	-	-
0.2176	850	0.3006	-	-
0.2304	900	0.3065	-	-
0.2432	950	0.3277	-	-
0.2560	1000	0.2941	0.2089	0.6556
0.2687	1050	0.2918	-	-
0.2815	1100	0.2935	-	-
0.2943	1150	0.2834	-	-
0.3071	1200	0.2795	-	-
0.3199	1250	0.2783	-	-
0.3327	1300	0.2828	-	-
0.3455	1350	0.2727	-	-
0.3583	1400	0.2626	-	-
0.3711	1450	0.2519	-	-
0.3839	1500	0.2461	0.1769	0.6743
0.3967	1550	0.2602	-	-
0.4095	1600	0.2398	-	-
0.4223	1650	0.2421	-	-
0.4351	1700	0.2365	-	-
0.4479	1750	0.2351	-	-
0.4607	1800	0.2412	-	-
0.4735	1850	0.2308	-	-
0.4863	1900	0.2217	-	-
0.4991	1950	0.2315	-	-
0.5119	2000	0.2295	0.1598	0.6856
0.5247	2050	0.2157	-	-
0.5375	2100	0.2123	-	-
0.5503	2150	0.2236	-	-
0.5631	2200	0.2098	-	-
0.5759	2250	0.2208	-	-
0.5887	2300	0.2159	-	-
0.6015	2350	0.2087	-	-
0.6143	2400	0.22	-	-
0.6271	2450	0.2002	-	-
0.6399	2500	0.1999	0.1466	0.6915
0.6527	2550	0.1986	-	-
0.6655	2600	0.2238	-	-
0.6783	2650	0.2141	-	-
0.6911	2700	0.2154	-	-
0.7039	2750	0.1993	-	-
0.7167	2800	0.1946	-	-
0.7295	2850	0.2064	-	-
0.7423	2900	0.2179	-	-
0.7551	2950	0.1976	-	-
0.7679	3000	0.2081	0.1384	0.6964
0.7807	3050	0.1863	-	-
0.7934	3100	0.2022	-	-
0.8062	3150	0.2132	-	-
0.8190	3200	0.1991	-	-
0.8318	3250	0.1904	-	-
0.8446	3300	0.1804	-	-
0.8574	3350	0.1944	-	-
0.8702	3400	0.1981	-	-
0.8830	3450	0.195	-	-
0.8958	3500	0.1984	0.1357	0.6994
0.9086	3550	0.1947	-	-
0.9214	3600	0.1912	-	-
0.9342	3650	0.1898	-	-
0.9470	3700	0.1945	-	-
0.9598	3750	0.1893	-	-
0.9726	3800	0.1919	-	-
0.9854	3850	0.1994	-	-
0.9982	3900	0.1864	-	-
-1	-1	-	-	0.7000

Environmental Impact

Carbon emissions were measured using CodeCarbon.

Energy Consumed: 0.057 kWh
Carbon Emitted: 0.022 kg of CO2
Hours Used: 0.206 hours

Training Hardware

On Cloud: No
GPU Model: 1 x NVIDIA GeForce RTX 3090
CPU Model: 13th Gen Intel(R) Core(TM) i7-13700K
RAM Size: 31.78 GB

Framework Versions

Python: 3.11.6
Sentence Transformers: 3.5.0.dev0
Transformers: 4.49.0.dev0
PyTorch: 2.5.0+cu121
Accelerate: 1.3.0
Datasets: 2.20.0
Tokenizers: 0.21.0

Citation

BibTeX

Sentence Transformers

bibtex

@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

bibtex

@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}
}

	question	answer
type	string	string
details	min: 8 tokens mean: 11.86 tokens max: 21 tokens	min: 14 tokens mean: 60.48 tokens max: 138 tokens