ayushexel/emb-all-MiniLM-L6-v2-gooaq-1-epochs

SentenceTransformer based on sentence-transformers/all-MiniLM-L6-v2

This is a sentence-transformers model finetuned from sentence-transformers/all-MiniLM-L6-v2 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: sentence-transformers/all-MiniLM-L6-v2
• Maximum Sequence Length: 256 tokens
• Output Dimensionality: 384 dimensions
• Similarity Function: Cosine Similarity
• Training Dataset:
  • gooaq
• Language: en

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': 256, '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})
  (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("ayushexel/emb-all-MiniLM-L6-v2-gooaq-1-epochs")
# Run inference
sentences = [
    'what is usb c ss?',
    'The USB Type-C specification is pretty confusing. ... The standard USB logo to identify USB 2.0 ports or slower. "SS" markings, which stand for SuperSpeed, to identify USB 3.0 ports, otherwise known as USB 3.1 gen 1. "10" markings, which stand for 10 Gbps, to identify USB 3.1 gen 2 ports with ultra-fast connectivity.',
    '“Global warming” refers to the rise in global temperatures due mainly to the increasing concentrations of greenhouse gases in the atmosphere. “Climate change” refers to the increasing changes in the measures of climate over a long period of time – including precipitation, temperature, and wind patterns.',
]
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

Triplet

• Dataset: gooqa-dev
• Evaluated with TripletEvaluator

Metric	Value
cosine_accuracy	0.5692

Training Details

Training Dataset

gooaq

• Dataset: gooaq at b089f72
• Size: 1,995,000 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: 23 tokens	min: 14 tokens mean: 60.74 tokens max: 133 tokens

• Samples:

  question	answer
  can twine be a noun?	noun. a strong thread or string composed of two or more strands twisted together. an act of twining, twisting, or interweaving.
  what is bo id in nsdl?	The demat account number allotted to the beneficiary holder(s) by DP is known as the BO-ID. In CDSL it is 16 digits number. It is an intermediary (an institution) between the investor and the depository.
  how much does it cost to run an electric fan all night?	The average indoor ceiling fan costs around 0.13c to 1.29c per hour to run, or between $1.90 and $18.85 each year. This will depend on the fan's speed settings, how frequently it's used, and the rate you pay on electricity. Like most electrical appliances, a ceiling fan's power is measured in watts.

• Loss: MultipleNegativesRankingLoss with these parameters:

  {
      "scale": 20.0,
      "similarity_fct": "cos_sim"
  }
  

Evaluation Dataset

gooaq

• Dataset: gooaq at b089f72
• Size: 5,000 evaluation samples
• Columns: question and answer
• Approximate statistics based on the first 1000 samples:

  	question	answer
  type	string	string
  details	min: 8 tokens mean: 11.8 tokens max: 21 tokens	min: 14 tokens mean: 60.68 tokens max: 123 tokens

• Samples:

  question	answer
  how much water should a person drink in 8 hours?	Health authorities commonly recommend eight 8-ounce glasses, which equals about 2 liters, or half a gallon. This is called the 8×8 rule and is very easy to remember. However, some health gurus believe that you need to sip on water constantly throughout the day, even when you're not thirsty.
  what does this mean in excel #name?	Important: The #NAME? error signifies that something needs to be corrected in the syntax, so when you see the error in your formula, resolve it. Do not use any error-handling functions such as IFERROR to mask the error. To avoid typos in formula names, use the Formula Wizard in Excel.
  are hydroflask good for the environment?	Hydro Flasks are a new fad among many students and adults to help minimize plastic waste in the oceans. Hydro Flasks are great because they use a type of metal called TempShield, which keeps your beverage or food either hot for up to six hours or cold for up to twenty-four hours.

• Loss: MultipleNegativesRankingLoss with these parameters:

  {
      "scale": 20.0,
      "similarity_fct": "cos_sim"
  }
  

Training Hyperparameters

Non-Default Hyperparameters

• eval_strategy: steps
• per_device_train_batch_size: 256
• per_device_eval_batch_size: 256
• num_train_epochs: 1
• warmup_ratio: 0.1
• fp16: 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: 256
• per_device_eval_batch_size: 256
• 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: 5e-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: 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}
• tp_size: 0
• 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	gooqa-dev_cosine_accuracy
-1	-1	-	-	0.5368
0.0128	100	0.0756	-	-
0.0257	200	0.0701	-	-
0.0385	300	0.0661	-	-
0.0513	400	0.0655	-	-
0.0642	500	0.0667	-	-
0.0770	600	0.0683	-	-
0.0898	700	0.0665	-	-
0.1027	800	0.0641	-	-
0.1155	900	0.067	-	-
0.1283	1000	0.0655	0.0460	0.5366
0.1412	1100	0.065	-	-
0.1540	1200	0.0643	-	-
0.1668	1300	0.0607	-	-
0.1796	1400	0.0605	-	-
0.1925	1500	0.0596	-	-
0.2053	1600	0.0609	-	-
0.2181	1700	0.0611	-	-
0.2310	1800	0.0608	-	-
0.2438	1900	0.0613	-	-
0.2566	2000	0.0593	0.0393	0.5468
0.2695	2100	0.0599	-	-
0.2823	2200	0.0551	-	-
0.2951	2300	0.0559	-	-
0.3080	2400	0.0573	-	-
0.3208	2500	0.0532	-	-
0.3336	2600	0.0541	-	-
0.3465	2700	0.0554	-	-
0.3593	2800	0.055	-	-
0.3721	2900	0.0555	-	-
0.3850	3000	0.0537	0.0386	0.5452
0.3978	3100	0.057	-	-
0.4106	3200	0.0516	-	-
0.4235	3300	0.0535	-	-
0.4363	3400	0.0554	-	-
0.4491	3500	0.0509	-	-
0.4620	3600	0.0503	-	-
0.4748	3700	0.0496	-	-
0.4876	3800	0.0499	-	-
0.5004	3900	0.0525	-	-
0.5133	4000	0.0484	0.0355	0.5582
0.5261	4100	0.0497	-	-
0.5389	4200	0.0476	-	-
0.5518	4300	0.0476	-	-
0.5646	4400	0.0496	-	-
0.5774	4500	0.0497	-	-
0.5903	4600	0.0488	-	-
0.6031	4700	0.0486	-	-
0.6159	4800	0.048	-	-
0.6288	4900	0.0496	-	-
0.6416	5000	0.049	0.0333	0.5630
0.6544	5100	0.0476	-	-
0.6673	5200	0.047	-	-
0.6801	5300	0.0474	-	-
0.6929	5400	0.0514	-	-
0.7058	5500	0.0468	-	-
0.7186	5600	0.0477	-	-
0.7314	5700	0.0466	-	-
0.7443	5800	0.0449	-	-
0.7571	5900	0.0458	-	-
0.7699	6000	0.0438	0.0325	0.5636
0.7828	6100	0.047	-	-
0.7956	6200	0.0463	-	-
0.8084	6300	0.0435	-	-
0.8212	6400	0.0481	-	-
0.8341	6500	0.0448	-	-
0.8469	6600	0.0472	-	-
0.8597	6700	0.0445	-	-
0.8726	6800	0.0452	-	-
0.8854	6900	0.0448	-	-
0.8982	7000	0.0441	0.0307	0.5670
0.9111	7100	0.0428	-	-
0.9239	7200	0.044	-	-
0.9367	7300	0.0429	-	-
0.9496	7400	0.0436	-	-
0.9624	7500	0.0444	-	-
0.9752	7600	0.0419	-	-
0.9881	7700	0.043	-	-
-1	-1	-	-	0.5692

Framework Versions

• Python: 3.11.0
• Sentence Transformers: 4.0.1
• Transformers: 4.50.3
• PyTorch: 2.6.0+cu124
• Accelerate: 1.5.2
• Datasets: 3.5.0
• Tokenizers: 0.21.1

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",
}

MultipleNegativesRankingLoss

@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}
}