SMARTICT/gte-small-finetune-test

gte small finetuned on NLI

This is a sentence-transformers model finetuned from thenlper/gte-small on the sentence-transformers/all-nli 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: thenlper/gte-small
• Maximum Sequence Length: 512 tokens
• Output Dimensionality: 384 tokens
• Similarity Function: Cosine Similarity
• Training Dataset:
  • sentence-transformers/all-nli
• 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})
  (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("SMARTICT/gte-small-finetune-test")
# Run inference
sentences = [
    'A construction worker peeking out of a manhole while his coworker sits on the sidewalk smiling.',
    'A worker is looking out of a manhole.',
    'The workers are both inside the manhole.',
]
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: all-nli-dev
• Evaluated with TripletEvaluator

Metric	Value
cosine_accuracy	0.926
dot_accuracy	0.074
manhattan_accuracy	0.9253
euclidean_accuracy	0.926
max_accuracy	0.926

Triplet

• Dataset: all-nli-test
• Evaluated with TripletEvaluator

Metric	Value
cosine_accuracy	0.9348
dot_accuracy	0.0652
manhattan_accuracy	0.9331
euclidean_accuracy	0.9348
max_accuracy	0.9348

Training Details

Training Dataset

sentence-transformers/all-nli

• Dataset: sentence-transformers/all-nli at d482672
• Size: 100,000 training samples
• Columns: anchor, positive, and negative
• Approximate statistics based on the first 1000 samples:

  	anchor	positive	negative
  type	string	string	string
  details	min: 7 tokens mean: 10.46 tokens max: 46 tokens	min: 6 tokens mean: 12.81 tokens max: 40 tokens	min: 5 tokens mean: 13.4 tokens max: 50 tokens

• Samples:

  anchor	positive	negative
  A person on a horse jumps over a broken down airplane.	A person is outdoors, on a horse.	A person is at a diner, ordering an omelette.
  Children smiling and waving at camera	There are children present	The kids are frowning
  A boy is jumping on skateboard in the middle of a red bridge.	The boy does a skateboarding trick.	The boy skates down the sidewalk.

• Loss: MultipleNegativesRankingLoss with these parameters:

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

Evaluation Dataset

sentence-transformers/all-nli

• Dataset: sentence-transformers/all-nli at d482672
• Size: 6,584 evaluation samples
• Columns: anchor, positive, and negative
• Approximate statistics based on the first 1000 samples:

  	anchor	positive	negative
  type	string	string	string
  details	min: 6 tokens mean: 17.95 tokens max: 63 tokens	min: 4 tokens mean: 9.78 tokens max: 29 tokens	min: 5 tokens mean: 10.35 tokens max: 29 tokens

• Samples:

  anchor	positive	negative
  Two women are embracing while holding to go packages.	Two woman are holding packages.	The men are fighting outside a deli.
  Two young children in blue jerseys, one with the number 9 and one with the number 2 are standing on wooden steps in a bathroom and washing their hands in a sink.	Two kids in numbered jerseys wash their hands.	Two kids in jackets walk to school.
  A man selling donuts to a customer during a world exhibition event held in the city of Angeles	A man selling donuts to a customer.	A woman drinks her coffee in a small cafe.

• 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: 16
• per_device_eval_batch_size: 16
• num_train_epochs: 1
• warmup_ratio: 0.1
• 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: 16
• per_device_eval_batch_size: 16
• per_gpu_train_batch_size: None
• per_gpu_eval_batch_size: None
• gradient_accumulation_steps: 1
• eval_accumulation_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: 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: 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
• eval_on_start: False
• batch_sampler: no_duplicates
• multi_dataset_batch_sampler: proportional

Training Logs

Epoch	Step	Training Loss	loss	all-nli-dev_max_accuracy	all-nli-test_max_accuracy
0	0	-	-	0.9160	-
0.016	100	1.4107	0.6660	0.9069	-
0.032	200	0.7368	0.6155	0.8950	-
0.048	300	1.0729	0.5522	0.9054	-
0.064	400	0.719	0.5647	0.8957	-
0.08	500	0.7273	0.6278	0.8829	-
0.096	600	0.9222	0.5652	0.8975	-
0.112	700	0.8402	0.5837	0.8947	-
0.128	800	0.9511	0.6110	0.8864	-
0.144	900	1.0713	0.5923	0.8852	-
0.16	1000	0.9495	0.5216	0.8888	-
0.176	1100	1.0079	0.6263	0.8777	-
0.192	1200	0.9195	0.5970	0.8777	-
0.208	1300	0.8018	0.6342	0.8765	-
0.224	1400	0.7124	0.6462	0.8764	-
0.24	1500	0.709	0.5232	0.8964	-
0.256	1600	0.6055	0.6109	0.8838	-
0.272	1700	0.7887	0.6620	0.8768	-
0.288	1800	0.789	0.5957	0.8829	-
0.304	1900	0.6711	0.5377	0.8946	-
0.32	2000	0.6086	0.5596	0.8932	-
0.336	2100	0.5067	0.5676	0.8861	-
0.352	2200	0.5387	0.5704	0.8900	-
0.368	2300	0.6574	0.5308	0.8890	-
0.384	2400	0.6232	0.5051	0.8928	-
0.4	2500	0.6045	0.5179	0.9023	-
0.416	2600	0.4795	0.4766	0.8960	-
0.432	2700	0.7372	0.5463	0.8979	-
0.448	2800	0.7593	0.5337	0.8878	-
0.464	2900	0.7384	0.5203	0.8923	-
0.48	3000	0.6336	0.5099	0.8897	-
0.496	3100	0.6634	0.4803	0.8954	-
0.512	3200	0.5443	0.4524	0.9048	-
0.528	3300	0.5292	0.4232	0.9104	-
0.544	3400	0.4633	0.4414	0.9093	-
0.56	3500	0.4442	0.4393	0.9087	-
0.576	3600	0.4443	0.4178	0.9128	-
0.592	3700	0.4736	0.4123	0.9134	-
0.608	3800	0.4077	0.4025	0.9174	-
0.624	3900	0.4069	0.4032	0.9156	-
0.64	4000	0.6939	0.4353	0.9146	-
0.656	4100	0.865	0.4154	0.9172	-
0.672	4200	0.8518	0.3925	0.9172	-
0.688	4300	0.5989	0.3864	0.9190	-
0.704	4400	0.5399	0.3679	0.9197	-
0.72	4500	0.497	0.3766	0.9221	-
0.736	4600	0.585	0.3708	0.9228	-
0.752	4700	0.6454	0.3608	0.9203	-
0.768	4800	0.5414	0.3593	0.9213	-
0.784	4900	0.4648	0.3634	0.9210	-
0.8	5000	0.5781	0.3782	0.9216	-
0.816	5100	0.4401	0.3662	0.9227	-
0.832	5200	0.5241	0.3595	0.9215	-
0.848	5300	0.459	0.3618	0.9215	-
0.864	5400	0.5529	0.3693	0.9216	-
0.88	5500	0.5202	0.3573	0.9218	-
0.896	5600	0.4703	0.3529	0.9231	-
0.912	5700	0.5658	0.3513	0.9245	-
0.928	5800	0.5016	0.3491	0.9236	-
0.944	5900	0.6306	0.3492	0.9257	-
0.96	6000	0.6721	0.3507	0.9266	-
0.976	6100	0.586	0.3509	0.9257	-
0.992	6200	0.0014	0.3511	0.9260	-
1.0	6250	-	-	-	0.9348

Framework Versions

• Python: 3.10.12
• Sentence Transformers: 3.0.1
• Transformers: 4.42.4
• PyTorch: 2.4.0+cu121
• Accelerate: 0.32.1
• Datasets: 2.21.0
• 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",
}

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}
}