Detomo/cl-nagoya-sup-simcse-ja-nss-v0_9_13

SentenceTransformer

This is a sentence-transformers model trained. 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
• Maximum Sequence Length: 512 tokens
• Output Dimensionality: 768 dimensions
• Similarity Function: Cosine Similarity

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': 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})
)

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("Detomo/cl-nagoya-sup-simcse-ja-nss-v0_9_13")
# Run inference
sentences = [
    '科目：建具。名称：GCW-#窓。',
    '科目：建具。名称：AW-#窓。',
    '科目：建具。名称：STW-#窓。',
]
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]

Training Details

Training Dataset

Unnamed Dataset

• Size: 1,546 training samples
• Columns: sentence and label
• Approximate statistics based on the first 1000 samples:

  	sentence	label
  type	string	int
  details	min: 11 tokens mean: 17.07 tokens max: 27 tokens	0: ~0.30% 1: ~0.30% 2: ~0.30% 3: ~0.30% 4: ~0.30% 5: ~0.30% 6: ~0.30% 7: ~0.30% 8: ~0.30% 9: ~0.30% 10: ~0.30% 11: ~0.40% 12: ~0.30% 13: ~0.30% 14: ~0.30% 15: ~0.30% 16: ~0.30% 17: ~0.30% 18: ~0.50% 19: ~0.30% 20: ~0.30% 21: ~0.30% 22: ~0.30% 23: ~0.30% 24: ~0.30% 25: ~0.30% 26: ~0.30% 27: ~0.30% 28: ~0.30% 29: ~0.30% 30: ~0.30% 31: ~0.30% 32: ~0.30% 33: ~0.30% 34: ~0.30% 35: ~0.30% 36: ~0.30% 37: ~0.30% 38: ~0.30% 39: ~0.30% 40: ~0.40% 41: ~0.30% 42: ~0.30% 43: ~0.30% 44: ~0.60% 45: ~0.70% 46: ~0.30% 47: ~0.30% 48: ~0.30% 49: ~0.30% 50: ~0.30% 51: ~0.30% 52: ~0.30% 53: ~0.30% 54: ~0.30% 55: ~0.30% 56: ~0.30% 57: ~0.80% 58: ~0.30% 59: ~0.30% 60: ~0.30% 61: ~0.30% 62: ~0.30% 63: ~0.30% 64: ~0.30% 65: ~0.30% 66: ~0.50% 67: ~0.30% 68: ~0.30% 69: ~0.30% 70: ~0.30% 71: ~0.30% 72: ~0.60% 73: ~0.30% 74: ~0.30% 75: ~0.30% 76: ~0.30% 77: ~0.30% 78: ~0.30% 79: ~0.30% 80: ~0.30% 81: ~0.30% 82: ~0.30% 83: ~0.30% 84: ~0.30% 85: ~0.30% 86: ~0.80% 87: ~0.60% 88: ~0.50% 89: ~0.30% 90: ~0.30% 91: ~0.60% 92: ~8.00% 93: ~1.70% 94: ~0.30% 95: ~0.30% 96: ~0.60% 97: ~0.30% 98: ~0.30% 99: ~0.30% 100: ~0.30% 101: ~1.20% 102: ~0.30% 103: ~0.30% 104: ~0.30% 105: ~0.30% 106: ~0.30% 107: ~0.30% 108: ~0.30% 109: ~0.30% 110: ~0.30% 111: ~0.30% 112: ~0.30% 113: ~0.30% 114: ~0.30% 115: ~0.30% 116: ~0.30% 117: ~0.30% 118: ~0.30% 119: ~0.30% 120: ~0.30% 121: ~0.50% 122: ~0.30% 123: ~0.30% 124: ~0.30% 125: ~0.30% 126: ~0.30% 127: ~0.30% 128: ~0.30% 129: ~0.40% 130: ~0.70% 131: ~0.30% 132: ~3.10% 133: ~0.30% 134: ~2.30% 135: ~0.30% 136: ~0.30% 137: ~0.50% 138: ~0.50% 139: ~0.50% 140: ~0.30% 141: ~0.30% 142: ~0.30% 143: ~0.30% 144: ~0.80% 145: ~0.30% 146: ~0.30% 147: ~0.30% 148: ~0.30% 149: ~0.30% 150: ~0.30% 151: ~0.30% 152: ~0.30% 153: ~0.30% 154: ~0.30% 155: ~0.30% 156: ~0.30% 157: ~0.30% 158: ~0.30% 159: ~0.30% 160: ~0.30% 161: ~0.30% 162: ~0.30% 163: ~0.30% 164: ~0.30% 165: ~0.30% 166: ~0.30% 167: ~0.30% 168: ~0.60% 169: ~0.30% 170: ~0.30% 171: ~0.30% 172: ~0.30% 173: ~0.30% 174: ~0.70% 175: ~0.30% 176: ~0.30% 177: ~0.30% 178: ~1.30% 179: ~0.30% 180: ~0.30% 181: ~0.30% 182: ~0.30% 183: ~0.30% 184: ~0.30% 185: ~1.10% 186: ~0.30% 187: ~0.30% 188: ~0.30% 189: ~0.30% 190: ~0.30% 191: ~0.30% 192: ~0.30% 193: ~0.30% 194: ~1.50% 195: ~0.30% 196: ~0.30% 197: ~0.30% 198: ~0.30% 199: ~1.00% 200: ~0.30% 201: ~0.30% 202: ~0.30% 203: ~1.80% 204: ~0.30% 205: ~0.50% 206: ~0.70% 207: ~0.30% 208: ~0.30% 209: ~0.30% 210: ~0.30% 211: ~0.30% 212: ~0.30% 213: ~0.30% 214: ~0.30% 215: ~4.00% 216: ~0.30% 217: ~0.30% 218: ~0.30% 219: ~0.60% 220: ~0.30% 221: ~0.30% 222: ~0.70% 223: ~0.30% 224: ~0.30% 225: ~0.30% 226: ~0.60% 227: ~0.30% 228: ~0.10%

• Samples:

  sentence	label
  科目：コンクリート。名称：免震基礎天端ｸﾞﾗｳﾄ注入。	0
  科目：コンクリート。名称：免震基礎天端ｸﾞﾗｳﾄ注入。	0
  科目：コンクリート。名称：免震基礎天端ｸﾞﾗｳﾄ注入。	0

• Loss: sentence_transformer_lib.custom_batch_all_trip_loss.CustomBatchAllTripletLoss

Training Hyperparameters

Non-Default Hyperparameters

• per_device_train_batch_size: 512
• per_device_eval_batch_size: 512
• learning_rate: 1e-05
• weight_decay: 0.01
• num_train_epochs: 250
• warmup_ratio: 0.1
• fp16: True
• batch_sampler: group_by_label

All Hyperparameters

Click to expand

• overwrite_output_dir: False
• do_predict: False
• eval_strategy: no
• prediction_loss_only: True
• per_device_train_batch_size: 512
• per_device_eval_batch_size: 512
• 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: 1e-05
• weight_decay: 0.01
• adam_beta1: 0.9
• adam_beta2: 0.999
• adam_epsilon: 1e-08
• max_grad_norm: 1.0
• num_train_epochs: 250
• 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: group_by_label
• multi_dataset_batch_sampler: proportional

Training Logs

Epoch	Step	Training Loss
2.5	10	34.4458
5.0	20	9.5341
7.5	30	2.0511
10.0	40	1.5025
12.5	50	1.4347
15.0	60	1.1549
17.5	70	1.2308
20.0	80	1.0908
22.5	90	1.1238
25.0	100	0.9793
2.5	10	1.1269
5.0	20	0.8895
7.5	30	0.8496
10.0	40	0.6124
12.5	50	0.5591
15.0	60	0.4262
17.5	70	0.3892
20.0	80	0.3309
22.5	90	0.3195
25.0	100	0.0781
7.5455	200	0.072
11.4242	300	0.073
15.3030	400	0.0715
19.1818	500	0.069
23.0606	600	0.0682
26.7273	700	0.0659
30.6061	800	0.0628
34.4848	900	0.0618
38.3636	1000	0.0639
42.2424	1100	0.0635
46.1212	1200	0.0635
49.7879	1300	0.0627
53.6667	1400	0.0593
57.5455	1500	0.0605
61.4242	1600	0.055
65.3030	1700	0.0556
69.1818	1800	0.0589
73.0606	1900	0.0585
76.7273	2000	0.0568
80.6061	2100	0.0521
84.4848	2200	0.0559
88.3636	2300	0.0508
92.2424	2400	0.051
96.1212	2500	0.0532
99.7879	2600	0.0545
103.6667	2700	0.0532
107.5455	2800	0.0542
111.4242	2900	0.052
115.3030	3000	0.0497
119.1818	3100	0.0486
123.0606	3200	0.0562
126.7273	3300	0.0544
130.6061	3400	0.0516
134.4848	3500	0.0491
138.3636	3600	0.0578
142.2424	3700	0.0508
146.1212	3800	0.0533
149.7879	3900	0.0487
153.6667	4000	0.045
157.5455	4100	0.0454
161.4242	4200	0.0497
165.3030	4300	0.0466
169.1818	4400	0.045
173.0606	4500	0.0477
176.7273	4600	0.0421
180.6061	4700	0.051
184.4848	4800	0.0389
188.3636	4900	0.0449
192.2424	5000	0.0425
196.1212	5100	0.0456
199.7879	5200	0.0465
203.6667	5300	0.0435
207.5455	5400	0.04
211.4242	5500	0.0405
215.3030	5600	0.0432
219.1818	5700	0.0394
223.0606	5800	0.0511
226.7273	5900	0.0462
230.6061	6000	0.0397
234.4848	6100	0.0413
238.3636	6200	0.0443
242.2424	6300	0.0377
246.1212	6400	0.0437
249.7879	6500	0.0407

Framework Versions

• Python: 3.11.11
• Sentence Transformers: 3.4.1
• 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",
}

CustomBatchAllTripletLoss

@misc{hermans2017defense,
    title={In Defense of the Triplet Loss for Person Re-Identification},
    author={Alexander Hermans and Lucas Beyer and Bastian Leibe},
    year={2017},
    eprint={1703.07737},
    archivePrefix={arXiv},
    primaryClass={cs.CV}
}