Detomo/cl-nagoya-sup-simcse-ja-for-standard-name-v1_1

SentenceTransformer based on cl-nagoya/sup-simcse-ja-base

This is a sentence-transformers model finetuned from cl-nagoya/sup-simcse-ja-base. 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
• Base model: cl-nagoya/sup-simcse-ja-base
• 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-for-standard-name-v1_1")
# Run inference
sentences = [
    '科目：ユニット及びその他。名称：4F透析室カウンター。',
    '科目：ユニット及びその他。名称：2F初療1、2カウンター。',
    '科目：ユニット及びその他。名称：9Fスタッフステーション1カウンター。',
]
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: 8,788 training samples
• Columns: sentence and label
• Approximate statistics based on the first 1000 samples:

  	sentence	label
  type	string	int
  details	min: 13 tokens mean: 23.19 tokens max: 41 tokens	0: ~0.20% 1: ~0.30% 2: ~0.30% 3: ~0.30% 4: ~0.20% 5: ~0.20% 6: ~0.20% 7: ~0.20% 8: ~0.30% 9: ~0.30% 10: ~0.20% 11: ~0.20% 12: ~0.20% 13: ~0.20% 14: ~0.20% 15: ~0.20% 16: ~0.40% 17: ~0.20% 18: ~0.20% 19: ~0.20% 20: ~0.20% 21: ~0.20% 22: ~0.20% 23: ~0.20% 24: ~0.20% 25: ~0.20% 26: ~0.20% 27: ~0.20% 28: ~0.20% 29: ~0.20% 30: ~0.20% 31: ~0.20% 32: ~0.20% 33: ~0.20% 34: ~0.20% 35: ~0.20% 36: ~0.20% 37: ~0.20% 38: ~0.20% 39: ~0.20% 40: ~0.20% 41: ~0.20% 42: ~0.60% 43: ~0.70% 44: ~0.20% 45: ~0.30% 46: ~0.20% 47: ~0.20% 48: ~0.30% 49: ~0.20% 50: ~0.20% 51: ~0.20% 52: ~0.20% 53: ~0.30% 54: ~0.40% 55: ~0.30% 56: ~0.20% 57: ~0.20% 58: ~0.20% 59: ~0.20% 60: ~0.20% 61: ~0.30% 62: ~0.20% 63: ~0.20% 64: ~0.20% 65: ~0.20% 66: ~0.40% 67: ~0.40% 68: ~0.20% 69: ~0.60% 70: ~0.20% 71: ~0.20% 72: ~0.20% 73: ~0.20% 74: ~0.20% 75: ~0.30% 76: ~0.20% 77: ~0.40% 78: ~0.20% 79: ~0.20% 80: ~0.50% 81: ~0.30% 82: ~0.60% 83: ~0.20% 84: ~0.30% 85: ~0.20% 86: ~0.20% 87: ~0.20% 88: ~0.20% 89: ~1.10% 90: ~1.70% 91: ~2.20% 92: ~0.50% 93: ~0.20% 94: ~0.20% 95: ~1.60% 96: ~0.20% 97: ~0.20% 98: ~0.20% 99: ~0.20% 100: ~0.30% 101: ~1.70% 102: ~0.20% 103: ~0.20% 104: ~0.40% 105: ~0.40% 106: ~0.20% 107: ~0.20% 108: ~0.20% 109: ~1.10% 110: ~0.20% 111: ~0.40% 112: ~0.50% 113: ~0.20% 114: ~0.20% 115: ~0.20% 116: ~0.20% 117: ~0.50% 118: ~0.20% 119: ~0.20% 120: ~0.20% 121: ~0.20% 122: ~0.20% 123: ~0.20% 124: ~0.30% 125: ~0.20% 126: ~0.20% 127: ~0.20% 128: ~0.40% 129: ~0.20% 130: ~0.20% 131: ~0.20% 132: ~0.20% 133: ~0.20% 134: ~0.20% 135: ~0.20% 136: ~0.20% 137: ~0.20% 138: ~0.30% 139: ~0.20% 140: ~0.30% 141: ~0.30% 142: ~0.20% 143: ~0.20% 144: ~0.20% 145: ~0.20% 146: ~0.20% 147: ~0.20% 148: ~0.20% 149: ~0.20% 150: ~0.20% 151: ~0.20% 152: ~0.20% 153: ~0.20% 154: ~0.20% 155: ~0.20% 156: ~0.60% 157: ~0.20% 158: ~1.50% 159: ~0.20% 160: ~0.20% 161: ~0.20% 162: ~0.20% 163: ~0.50% 164: ~0.20% 165: ~0.20% 166: ~0.20% 167: ~0.20% 168: ~0.20% 169: ~0.30% 170: ~0.30% 171: ~0.20% 172: ~0.20% 173: ~1.30% 174: ~0.20% 175: ~0.20% 176: ~0.20% 177: ~0.20% 178: ~0.60% 179: ~0.20% 180: ~0.20% 181: ~0.20% 182: ~0.20% 183: ~0.20% 184: ~0.20% 185: ~0.30% 186: ~0.20% 187: ~0.20% 188: ~0.30% 189: ~0.20% 190: ~0.90% 191: ~0.30% 192: ~0.30% 193: ~0.20% 194: ~0.30% 195: ~0.20% 196: ~0.80% 197: ~0.20% 198: ~0.20% 199: ~0.30% 200: ~0.20% 201: ~0.20% 202: ~0.20% 203: ~0.20% 204: ~0.20% 205: ~1.20% 206: ~0.40% 207: ~0.20% 208: ~0.20% 209: ~0.20% 210: ~0.20% 211: ~0.30% 212: ~0.20% 213: ~0.80% 214: ~0.30% 215: ~0.20% 216: ~1.10% 217: ~0.30% 218: ~0.20% 219: ~0.20% 220: ~0.20% 221: ~0.20% 222: ~0.20% 223: ~0.20% 224: ~0.20% 225: ~0.30% 226: ~0.20% 227: ~0.90% 228: ~4.70% 229: ~0.20% 230: ~0.20% 231: ~0.20% 232: ~0.70% 233: ~0.20% 234: ~0.80% 235: ~0.20% 236: ~0.40% 237: ~0.30% 238: ~0.40% 239: ~0.20% 240: ~0.30% 241: ~0.50% 242: ~0.30% 243: ~0.20% 244: ~0.20% 245: ~0.30% 246: ~0.30% 247: ~0.30% 248: ~0.60% 249: ~0.20% 250: ~0.20% 251: ~0.20% 252: ~0.30% 253: ~0.30% 254: ~1.90% 255: ~0.20% 256: ~0.20% 257: ~0.20% 258: ~0.20% 259: ~0.20% 260: ~0.50% 261: ~0.20% 262: ~0.30% 263: ~0.20% 264: ~0.20% 265: ~1.00% 266: ~0.20% 267: ~0.20% 268: ~0.20% 269: ~0.40% 270: ~0.20% 271: ~0.20% 272: ~0.20% 273: ~0.20% 274: ~0.20% 275: ~0.20% 276: ~0.20% 277: ~3.70% 278: ~0.20% 279: ~0.40% 280: ~0.20% 281: ~0.20% 282: ~0.90% 283: ~0.40% 284: ~0.20% 285: ~2.30% 286: ~0.30% 287: ~0.20% 288: ~0.30% 289: ~0.60%

• Samples:

  sentence	label
  科目：コンクリート。名称：免震基礎天端グラウト注入。	0
  科目：コンクリート。名称：免震基礎天端グラウト注入。	0
  科目：コンクリート。名称：コンクリートポンプ圧送。	1

• Loss: BatchAllTripletLoss

Training Hyperparameters

Non-Default Hyperparameters

• per_device_train_batch_size: 256
• per_device_eval_batch_size: 256
• 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: 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: 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}
• 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

Click to expand

Epoch	Step	Training Loss
0.5714	20	0.787
1.2	40	0.7827
1.7714	60	0.7361
2.4	80	0.6798
3.0286	100	0.6569
3.6	120	0.6669
4.2286	140	0.6163
4.8	160	0.6277
5.4286	180	0.6449
6.0571	200	0.6135
6.6286	220	0.6445
7.2571	240	0.6572
7.8286	260	0.6268
8.4571	280	0.6034
9.0857	300	0.5598
9.6571	320	0.5801
10.2857	340	0.5471
10.8571	360	0.6579
11.4857	380	0.6059
12.1143	400	0.5715
12.6857	420	0.5986
13.3143	440	0.5601
13.8857	460	0.5547
14.5143	480	0.5642
15.1429	500	0.697
15.7143	520	0.5688
16.3429	540	0.5736
16.9143	560	0.5088
17.5429	580	0.5677
18.1714	600	0.6028
18.7429	620	0.5674
19.3714	640	0.5665
19.9429	660	0.6289
20.5714	680	0.5456
21.2	700	0.4944
21.7714	720	0.5712
22.4	740	0.6106
23.0286	760	0.5209
23.6	780	0.5236
24.2286	800	0.6091
24.8	820	0.6678
25.4286	840	0.4693
26.0571	860	0.4582
26.6286	880	0.5627
27.2571	900	0.5525
27.8286	920	0.503
28.4571	940	0.4801
29.0857	960	0.5039
29.6571	980	0.5049
30.2857	1000	0.595
30.8571	1020	0.4733
31.4857	1040	0.5804
32.1143	1060	0.4101
32.6857	1080	0.4311
33.3143	1100	0.4746
33.8857	1120	0.4964
34.5143	1140	0.4436
35.1429	1160	0.6351
35.7143	1180	0.5267
36.3429	1200	0.4685
36.9143	1220	0.4201
37.5429	1240	0.4256
38.1714	1260	0.5543
38.7429	1280	0.5176
39.3714	1300	0.4328
39.9429	1320	0.4746
40.5714	1340	0.4768
41.2	1360	0.4663
41.7714	1380	0.4729
42.4	1400	0.4141
43.0286	1420	0.3195
43.6	1440	0.3789
44.2286	1460	0.4032
44.8	1480	0.443
45.4286	1500	0.4116
46.0571	1520	0.4951
46.6286	1540	0.3845
47.2571	1560	0.3461
47.8286	1580	0.4754
48.4571	1600	0.5583
49.0857	1620	0.4282
49.6571	1640	0.436
50.2857	1660	0.4097
50.8571	1680	0.4642
51.4857	1700	0.3243
52.1143	1720	0.4395
52.6857	1740	0.3672
53.3143	1760	0.4781
53.8857	1780	0.5362
54.5143	1800	0.4401
55.1429	1820	0.4313
55.7143	1840	0.2751
56.3429	1860	0.331
56.9143	1880	0.4325
57.5429	1900	0.2995
58.1714	1920	0.4159
58.7429	1940	0.5603
59.3714	1960	0.4575
59.9429	1980	0.4677
60.5714	2000	0.4653
61.2	2020	0.3098
61.7714	2040	0.3188
62.4	2060	0.3769
63.0286	2080	0.2902
63.6	2100	0.4064
64.2286	2120	0.3663
64.8	2140	0.3184
65.4286	2160	0.4874
66.0571	2180	0.4094
66.6286	2200	0.4261
67.2571	2220	0.3808
67.8286	2240	0.2991
68.4571	2260	0.3242
69.0857	2280	0.2582
69.6571	2300	0.3806
70.2857	2320	0.3573
70.8571	2340	0.3183
71.4857	2360	0.4043
72.1143	2380	0.4266
72.6857	2400	0.5612
73.3143	2420	0.3476
73.8857	2440	0.3018
74.5143	2460	0.2952
75.1429	2480	0.2633
75.7143	2500	0.3564
76.3429	2520	0.2283
76.9143	2540	0.3615
77.5429	2560	0.2174
78.1714	2580	0.3049
78.7429	2600	0.2838
79.3714	2620	0.3191
79.9429	2640	0.2529
80.5714	2660	0.3192
81.2	2680	0.5119
81.7714	2700	0.2459
82.4	2720	0.4136
83.0286	2740	0.3266
83.6	2760	0.2863
84.2286	2780	0.3563
84.8	2800	0.2605
85.4286	2820	0.254
86.0571	2840	0.2252
86.6286	2860	0.3191
87.2571	2880	0.3074
87.8286	2900	0.274
88.4571	2920	0.3864
89.0857	2940	0.3206
89.6571	2960	0.2752
90.2857	2980	0.2033
90.8571	3000	0.3979
91.4857	3020	0.4327
92.1143	3040	0.1999
92.6857	3060	0.3939
93.3143	3080	0.2733
93.8857	3100	0.4334
94.5143	3120	0.3726
95.1429	3140	0.2567
95.7143	3160	0.258
96.3429	3180	0.1805
96.9143	3200	0.3244
97.5429	3220	0.2038
98.1714	3240	0.2689
98.7429	3260	0.433
99.3714	3280	0.1587
99.9429	3300	0.3088
100.5714	3320	0.3049
101.2	3340	0.335
101.7714	3360	0.2688
102.4	3380	0.359
103.0286	3400	0.2512
103.6	3420	0.2818
104.2286	3440	0.3606
104.8	3460	0.3254
105.4286	3480	0.2487
106.0571	3500	0.2184
106.6286	3520	0.2897
107.2571	3540	0.2849
107.8286	3560	0.362
108.4571	3580	0.2418
109.0857	3600	0.1498
109.6571	3620	0.2566
110.2857	3640	0.1181
110.8571	3660	0.3675
111.4857	3680	0.2722
112.1143	3700	0.3779
112.6857	3720	0.3882
113.3143	3740	0.1941
113.8857	3760	0.2281
114.5143	3780	0.2079
115.1429	3800	0.3443
115.7143	3820	0.2763
116.3429	3840	0.2331
116.9143	3860	0.2093
117.5429	3880	0.2439
118.1714	3900	0.1312
118.7429	3920	0.1098
119.3714	3940	0.2295
119.9429	3960	0.2501
120.5714	3980	0.3522
121.2	4000	0.3293
121.7714	4020	0.1698
122.4	4040	0.3992
123.0286	4060	0.1931
123.6	4080	0.1755
124.2286	4100	0.3408
124.8	4120	0.2337
125.4286	4140	0.2121
126.0571	4160	0.1628
126.6286	4180	0.2455
127.2571	4200	0.3342
127.8286	4220	0.1725
128.4571	4240	0.3714
129.0857	4260	0.2775
129.6571	4280	0.1764
130.2857	4300	0.1863
130.8571	4320	0.276
131.4857	4340	0.2006
132.1143	4360	0.2099
132.6857	4380	0.2397
133.3143	4400	0.223
133.8857	4420	0.1321
134.5143	4440	0.2499
135.1429	4460	0.2107
135.7143	4480	0.2374
136.3429	4500	0.2589
136.9143	4520	0.2382
137.5429	4540	0.1058
138.1714	4560	0.2519
138.7429	4580	0.23
139.3714	4600	0.2031
139.9429	4620	0.2424
140.5714	4640	0.1312
141.2	4660	0.1787
141.7714	4680	0.2445
142.4	4700	0.1948
143.0286	4720	0.2601
143.6	4740	0.1906
144.2286	4760	0.35
144.8	4780	0.1674
145.4286	4800	0.2339
146.0571	4820	0.2151
146.6286	4840	0.1986
147.2571	4860	0.1608
147.8286	4880	0.2729
148.4571	4900	0.1555
149.0857	4920	0.1536
149.6571	4940	0.1245
150.2857	4960	0.2635
150.8571	4980	0.1628
151.4857	5000	0.1869
152.1143	5020	0.2142
152.6857	5040	0.1867
153.3143	5060	0.2361
153.8857	5080	0.1811
154.5143	5100	0.4071
155.1429	5120	0.2499
155.7143	5140	0.2398
156.3429	5160	0.1486
156.9143	5180	0.1683
157.5429	5200	0.1434
158.1714	5220	0.1731
158.7429	5240	0.1674
159.3714	5260	0.1085
159.9429	5280	0.2573
160.5714	5300	0.1937
161.2	5320	0.0806
161.7714	5340	0.1411
162.4	5360	0.1603
163.0286	5380	0.1787
163.6	5400	0.2099
164.2286	5420	0.2676
164.8	5440	0.2658
165.4286	5460	0.2632
166.0571	5480	0.1839
166.6286	5500	0.2524
167.2571	5520	0.2018
167.8286	5540	0.2955
168.4571	5560	0.209
169.0857	5580	0.1999
169.6571	5600	0.2836
170.2857	5620	0.1559
170.8571	5640	0.2746
171.4857	5660	0.1939
172.1143	5680	0.1561
172.6857	5700	0.0935
173.3143	5720	0.1927
173.8857	5740	0.3022
174.5143	5760	0.2068
175.1429	5780	0.1384
175.7143	5800	0.086
176.3429	5820	0.1181
176.9143	5840	0.3145
177.5429	5860	0.0974
178.1714	5880	0.1891
178.7429	5900	0.1788
179.3714	5920	0.1954
179.9429	5940	0.1342
180.5714	5960	0.0936
181.2	5980	0.3109
181.7714	6000	0.1879
182.4	6020	0.0798
183.0286	6040	0.097
183.6	6060	0.0835
184.2286	6080	0.0931
184.8	6100	0.1377
185.4286	6120	0.1239
186.0571	6140	0.0307
186.6286	6160	0.1962
187.2571	6180	0.242
187.8286	6200	0.0886
188.4571	6220	0.2103
189.0857	6240	0.0746
189.6571	6260	0.1191
190.2857	6280	0.2356
190.8571	6300	0.2015
191.4857	6320	0.1728
192.1143	6340	0.1624
192.6857	6360	0.2528
193.3143	6380	0.0759
193.8857	6400	0.2138
194.5143	6420	0.1544
195.1429	6440	0.2444
195.7143	6460	0.1896
196.3429	6480	0.1646
196.9143	6500	0.1305
197.5429	6520	0.1379
198.1714	6540	0.1845
198.7429	6560	0.1997
199.3714	6580	0.2049
199.9429	6600	0.2891
200.5714	6620	0.1718
201.2	6640	0.1449
201.7714	6660	0.2096
202.4	6680	0.1056
203.0286	6700	0.0862
203.6	6720	0.0914
204.2286	6740	0.2433
204.8	6760	0.146
205.4286	6780	0.2099
206.0571	6800	0.0877
206.6286	6820	0.1194
207.2571	6840	0.069
207.8286	6860	0.0742
208.4571	6880	0.2773
209.0857	6900	0.1762
209.6571	6920	0.1573
210.2857	6940	0.0922
210.8571	6960	0.1366
211.4857	6980	0.0746
212.1143	7000	0.2004
212.6857	7020	0.0922
213.3143	7040	0.0662
213.8857	7060	0.1828
214.5143	7080	0.1202
215.1429	7100	0.1388
215.7143	7120	0.0638
216.3429	7140	0.2259
216.9143	7160	0.1219
217.5429	7180	0.1599
218.1714	7200	0.2424
218.7429	7220	0.149
219.3714	7240	0.272
219.9429	7260	0.1051
220.5714	7280	0.2117
221.2	7300	0.1466
221.7714	7320	0.1155
222.4	7340	0.2247
223.0286	7360	0.096
223.6	7380	0.0566
224.2286	7400	0.2404
224.8	7420	0.1684
225.4286	7440	0.0927
226.0571	7460	0.1746
226.6286	7480	0.13
227.2571	7500	0.1027
227.8286	7520	0.1359
228.4571	7540	0.0937
229.0857	7560	0.1378
229.6571	7580	0.0458
230.2857	7600	0.0766
230.8571	7620	0.0896
231.4857	7640	0.1541
232.1143	7660	0.1464
232.6857	7680	0.1427
233.3143	7700	0.2471
233.8857	7720	0.1636
234.5143	7740	0.1601
235.1429	7760	0.1583
235.7143	7780	0.1473
236.3429	7800	0.1211
236.9143	7820	0.1582
237.5429	7840	0.1083
238.1714	7860	0.2014
238.7429	7880	0.0981
239.3714	7900	0.2449
239.9429	7920	0.1142
240.5714	7940	0.1177
241.2	7960	0.1241
241.7714	7980	0.2778
242.4	8000	0.1066
243.0286	8020	0.0867
243.6	8040	0.156
244.2286	8060	0.1413
244.8	8080	0.0598
245.4286	8100	0.1206
246.0571	8120	0.1883
246.6286	8140	0.1245
247.2571	8160	0.0949
247.8286	8180	0.1096
248.4571	8200	0.1567
249.0857	8220	0.065
249.6571	8240	0.1075

Framework Versions

• Python: 3.11.11
• Sentence Transformers: 3.3.1
• Transformers: 4.48.3
• PyTorch: 2.5.1+cu124
• Accelerate: 1.3.0
• Datasets: 3.3.2
• Tokenizers: 0.21.0

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",
}

BatchAllTripletLoss

@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}
}