himanshu23099/bge_embedding_finetune1

SentenceTransformer based on BAAI/bge-small-en-v1.5

This is a sentence-transformers model finetuned from BAAI/bge-small-en-v1.5. 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: BAAI/bge-small-en-v1.5
• Maximum Sequence Length: 512 tokens
• Output Dimensionality: 384 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': True}) with Transformer model: BertModel 
  (1): Pooling({'word_embedding_dimension': 384, '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})
  (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("himanshu23099/bge_embedding_finetune1")
# Run inference
sentences = [
    'Tourists visit reason',
    'What is All Saints Cathedral, and why is it architecturally significant?\nAll Saints Cathedral, locally known as Patthar Girja (Stone Church), is a renowned Anglican Christian Church located on M.G. Marg, Allahabad. Built in the late 19th century, it is one of the most beautiful and architecturally significant churches in Uttar Pradesh, attracting both tourists and pilgrims.',
    "What attractions are closest to the city center?\nNear the city center, you’ll find several attractions within a short distance. Anand Bhavan and Swaraj Bhavan are centrally located and offer insights into the Nehru family and India’s freedom movement. All Saints’ Cathedral, a magnificent Gothic-style church also known as the “Patthar Girja,” is located in Civil Lines and is one of Prayagraj's architectural gems. Company Bagh, a peaceful park, is also close by and ideal for a quiet stroll. Chandrashekhar Azad Park and Khusro Bagh are both centrally located as well, providing green spaces along with historical importance.",
]
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: val_evaluator
• Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.358
cosine_accuracy@5	0.7092
cosine_accuracy@10	0.7993
cosine_precision@1	0.358
cosine_precision@5	0.1418
cosine_precision@10	0.0799
cosine_recall@1	0.358
cosine_recall@5	0.7092
cosine_recall@10	0.7993
cosine_ndcg@5	0.5539
cosine_ndcg@10	0.5832
cosine_ndcg@100	0.619
cosine_mrr@5	0.5013
cosine_mrr@10	0.5136
cosine_mrr@100	0.521
cosine_map@100	0.521

Training Details

Training Dataset

Unnamed Dataset

• Size: 3,507 training samples
• Columns: anchor, positive, and negative
• Approximate statistics based on the first 1000 samples:

  	anchor	positive	negative
  type	string	string	string
  details	min: 4 tokens mean: 11.76 tokens max: 32 tokens	min: 8 tokens mean: 116.82 tokens max: 504 tokens	min: 19 tokens mean: 121.15 tokens max: 424 tokens

• Samples:

  anchor	positive	negative
  Where are the shuttle bus pickup points located within the Kumbh Mela grounds?	No, shuttle buses will not have dedicated volunteers specifically, but for assistance, you can reach out to the nearest information center.	The ancient art of weaving has captivated many cultures worldwide. In some regions, artisans use intricate patterns to tell stories, while others focus on vibrant colors that highlight their heritage. Experimentation with different materials can yield unique textures, adding depth to the final product. Workshops often provide insights into traditional techniques, ensuring these skills are passed down through generations.
  Hotel Ilawart start place	Is hotel pickup and drop-off available for the tours? Fixed pickup points, such as Hotel Ilawart, are provided for all tours. In some cases, pickup and drop-off can be arranged for locations within a 5 km radius of the starting point, but you must confirm this with the tour operator at the time of booking.	What all is included in the trip package? The trip package typically includes transportation, tour guide services, and breakfast. Meals such as lunch and dinner can be purchased separately. Hotel bookings are usually not included in the package, so you will need to arrange accommodation independently.
  Are there food stalls or restaurants at the Railway Junction that cater to dietary restrictions for pilgrims?	Yes, there are food stalls and restaurants available at the Railway Junction that cater to various dietary needs, including vegetarian and other dietary restrictions suitable for pilgrims.	The sound of the ocean waves rhythmically crashing against the shore creates a soothing symphony that invites relaxation. Seagulls soar above, occasionally diving down to catch a glimpse of fish beneath the surface. Beachgoers spread out their colorful towels, soaking up the sun's golden rays while children build sandcastles, their laughter mingling with the salty breeze. A distant sailboat glides across the horizon, hinting at adventures beyond the vast expanse of blue. As the sun sets, the sky transforms into a canvas of vibrant hues, signaling the end of another beautiful day by the sea.

• Loss: GISTEmbedLoss with these parameters:

  {'guide': 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()
  ), 'temperature': 0.01}
  

Evaluation Dataset

Unnamed Dataset

• Size: 877 evaluation samples
• Columns: anchor, positive, and negative
• Approximate statistics based on the first 877 samples:

  	anchor	positive	negative
  type	string	string	string
  details	min: 5 tokens mean: 12.21 tokens max: 32 tokens	min: 3 tokens mean: 115.93 tokens max: 471 tokens	min: 15 tokens mean: 118.09 tokens max: 422 tokens

• Samples:

  anchor	positive	negative
  Ganga bath benefit	What is the ritual of Snan or bathing? Taking bath at the confluence of Ganga, Yamuna and invisible Saraswati during Mahakumbh has special significance. It is believed that by bathing in this holy confluence, all the sins of a person are washed away and he attains salvation. Bathing not only symbolizes personal purification, but it also conveys the message of social harmony and unity, where people from different cultures and communities come together to participate in this sacred ritual. It is considered that in special circumstances, the water of rivers also acquires a special life-giving quality, i.e. nectar, which not only leads to spiritual development along with purification of the mind, but also gives physical benefits by getting health. List of Aliases: [['Snan', 'bathing'], ]	What benefits will I get by attending the Kumbh Mela? It is believed that bathing in the holy rivers during this time washes away sins and grants liberation from the cycle of life and death. Attending the Kumbh and taking a dip in the sacred rivers provides a unique opportunity for spiritual growth, purification, and selfrealization. ✨
  Guide provide what	What is the guide-to-participant ratio for each tour? Each tour is led by one guide per group, ensuring a personalized experience with ample opportunity for detailed insights and engagement. The guide will provide context, historical background, and answer any questions during the tour, offering a rich, informative experience for participants.	How many people can join a group tour? Group sizes depend on the type of vehicle selected. For instance, a Dzire accommodates up to 4 people, an Innova is suitable for 5-6 people, and larger groups (minimum 10 people) can travel in a Tempo Traveller. For even larger groups, multiple vehicles can be arranged to ensure everyone can travel together comfortably.
  How many rules must a Kalpvasi observe?	A Kalpvasi must observe 21 rules during Kalpvas, involving disciplines of the mind, speech, and actions.	The dancing colors of autumn leaves create a tapestry of nature’s beauty, inviting every eye to witness the grandeur of the changing seasons. Every gust of wind carries a whisper of nostalgia as trees shed their vibrant garments.

• Loss: GISTEmbedLoss with these parameters:

  {'guide': 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()
  ), 'temperature': 0.01}
  

Training Hyperparameters

Non-Default Hyperparameters

• eval_strategy: steps
• per_device_train_batch_size: 16
• gradient_accumulation_steps: 2
• learning_rate: 1e-05
• weight_decay: 0.01
• num_train_epochs: 30
• warmup_ratio: 0.1
• load_best_model_at_end: True

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: 8
• per_gpu_train_batch_size: None
• per_gpu_eval_batch_size: None
• gradient_accumulation_steps: 2
• 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: 30
• 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: 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: True
• 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
• 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: batch_sampler
• multi_dataset_batch_sampler: proportional

Training Logs

Click to expand

Epoch	Step	Training Loss	Validation Loss	val_evaluator_cosine_ndcg@100
0.0909	10	-	1.0916	0.4285
0.1818	20	-	1.0683	0.4295
0.2727	30	-	1.0320	0.4301
0.3636	40	-	0.9845	0.4309
0.4545	50	1.8466	0.9320	0.4340
0.5455	60	-	0.8804	0.4352
0.6364	70	-	0.8284	0.4368
0.7273	80	-	0.7754	0.4420
0.8182	90	-	0.7211	0.4425
0.9091	100	1.4317	0.6711	0.4442
1.0	110	-	0.6193	0.4483
1.0909	120	-	0.5700	0.4555
1.1818	130	-	0.5271	0.4603
1.2727	140	-	0.4892	0.4620
1.3636	150	1.0007	0.4611	0.4651
1.4545	160	-	0.4276	0.4706
1.5455	170	-	0.4005	0.4698
1.6364	180	-	0.3818	0.4728
1.7273	190	-	0.3573	0.4763
1.8182	200	0.7585	0.3321	0.4783
1.9091	210	-	0.3091	0.4806
2.0	220	-	0.2963	0.4833
2.0909	230	-	0.2875	0.4834
2.1818	240	-	0.2793	0.4842
2.2727	250	0.5586	0.2729	0.4879
2.3636	260	-	0.2663	0.4885
2.4545	270	-	0.2576	0.4925
2.5455	280	-	0.2477	0.5006
2.6364	290	-	0.2353	0.5058
2.7273	300	0.4751	0.2278	0.5112
2.8182	310	-	0.2206	0.5096
2.9091	320	-	0.2130	0.5144
3.0	330	-	0.2043	0.5202
3.0909	340	-	0.1973	0.5214
3.1818	350	0.381	0.1964	0.5271
3.2727	360	-	0.1968	0.5325
3.3636	370	-	0.1922	0.5289
3.4545	380	-	0.1869	0.5329
3.5455	390	-	0.1789	0.5391
3.6364	400	0.3886	0.1743	0.5464
3.7273	410	-	0.1730	0.5472
3.8182	420	-	0.1699	0.5479
3.9091	430	-	0.1644	0.5525
4.0	440	-	0.1623	0.5511
4.0909	450	0.2977	0.1600	0.5513
4.1818	460	-	0.1540	0.5519
4.2727	470	-	0.1492	0.5589
4.3636	480	-	0.1450	0.5624
4.4545	490	-	0.1426	0.5644
4.5455	500	0.2496	0.1407	0.5629
4.6364	510	-	0.1390	0.5663
4.7273	520	-	0.1399	0.5695
4.8182	530	-	0.1377	0.5764
4.9091	540	-	0.1357	0.5753
5.0	550	0.2322	0.1364	0.5827
5.0909	560	-	0.1327	0.5804
5.1818	570	-	0.1300	0.5799
5.2727	580	-	0.1307	0.5816
5.3636	590	-	0.1331	0.5868
5.4545	600	0.2219	0.1322	0.5839
5.5455	610	-	0.1332	0.5822
5.6364	620	-	0.1323	0.5817
5.7273	630	-	0.1311	0.5845
5.8182	640	-	0.1282	0.5834
5.9091	650	0.1982	0.1253	0.5870
6.0	660	-	0.1242	0.5880
6.0909	670	-	0.1241	0.5859
6.1818	680	-	0.1265	0.5885
6.2727	690	-	0.1287	0.5964
6.3636	700	0.1613	0.1321	0.5968
6.4545	710	-	0.1332	0.5979
6.5455	720	-	0.1295	0.6016
6.6364	730	-	0.1262	0.6022
6.7273	740	-	0.1242	0.6020
6.8182	750	0.172	0.1238	0.6037
6.9091	760	-	0.1222	0.6036
7.0	770	-	0.1213	0.6038
7.0909	780	-	0.1208	0.6038
7.1818	790	-	0.1200	0.6011
7.2727	800	0.1486	0.1196	0.5979
7.3636	810	-	0.1227	0.6015
7.4545	820	-	0.1225	0.6004
7.5455	830	-	0.1195	0.6045
7.6364	840	-	0.1202	0.6045
7.7273	850	0.1501	0.1208	0.6044
7.8182	860	-	0.1177	0.6038
7.9091	870	-	0.1161	0.6031
8.0	880	-	0.1168	0.6024
8.0909	890	-	0.1175	0.6050
8.1818	900	0.1563	0.1157	0.6063
8.2727	910	-	0.1146	0.6056
8.3636	920	-	0.1152	0.6073
8.4545	930	-	0.1167	0.6077
8.5455	940	-	0.1172	0.6087
8.6364	950	0.1247	0.1169	0.6077
8.7273	960	-	0.1159	0.6056
8.8182	970	-	0.1151	0.6066
8.9091	980	-	0.1161	0.6089
9.0	990	-	0.1187	0.6071
9.0909	1000	0.1497	0.1157	0.6110
9.1818	1010	-	0.1148	0.6086
9.2727	1020	-	0.1134	0.6125
9.3636	1030	-	0.1173	0.6114
9.4545	1040	-	0.1174	0.6118
9.5455	1050	0.1025	0.1159	0.6127
9.6364	1060	-	0.1118	0.6093
9.7273	1070	-	0.1114	0.6103
9.8182	1080	-	0.1128	0.6102
9.9091	1090	-	0.1142	0.6116
10.0	1100	0.128	0.1147	0.6115
10.0909	1110	-	0.1143	0.6095
10.1818	1120	-	0.1134	0.6073
10.2727	1130	-	0.1137	0.6059
10.3636	1140	-	0.1143	0.6049
10.4545	1150	0.1413	0.1145	0.6047
10.5455	1160	-	0.1154	0.6032
10.6364	1170	-	0.1158	0.6044
10.7273	1180	-	0.1151	0.6060
10.8182	1190	-	0.1145	0.6081
10.9091	1200	0.1223	0.1133	0.6084
11.0	1210	-	0.1121	0.6090
11.0909	1220	-	0.1130	0.6129
11.1818	1230	-	0.1134	0.6089
11.2727	1240	-	0.1136	0.6112
11.3636	1250	0.1199	0.1142	0.6134
11.4545	1260	-	0.1128	0.6145
11.5455	1270	-	0.1097	0.6148
11.6364	1280	-	0.1081	0.6122
11.7273	1290	-	0.1074	0.6126
11.8182	1300	0.1143	0.1063	0.6167
11.9091	1310	-	0.1067	0.6163
12.0	1320	-	0.1067	0.6190
12.0909	1330	-	0.1075	0.6193
12.1818	1340	-	0.1092	0.6222
12.2727	1350	0.0974	0.1087	0.6199
12.3636	1360	-	0.1078	0.6183
12.4545	1370	-	0.1072	0.6180
12.5455	1380	-	0.1072	0.6172
12.6364	1390	-	0.1072	0.6209
12.7273	1400	0.1257	0.1056	0.6152
12.8182	1410	-	0.1046	0.6149
12.9091	1420	-	0.1034	0.6142
13.0	1430	-	0.1034	0.6165
13.0909	1440	-	0.1046	0.6165
13.1818	1450	0.0866	0.1064	0.6177
13.2727	1460	-	0.1070	0.6158
13.3636	1470	-	0.1055	0.6151
13.4545	1480	-	0.1040	0.6182
13.5455	1490	-	0.1042	0.6144
13.6364	1500	0.0757	0.1042	0.6151
13.7273	1510	-	0.1056	0.6169
13.8182	1520	-	0.1059	0.6172
13.9091	1530	-	0.1059	0.6181
14.0	1540	-	0.1042	0.6167
14.0909	1550	0.0754	0.1043	0.6198
14.1818	1560	-	0.1044	0.6215
14.2727	1570	-	0.1042	0.6205
14.3636	1580	-	0.1058	0.6196
14.4545	1590	-	0.1076	0.6212
14.5455	1600	0.0901	0.1098	0.6219
14.6364	1610	-	0.1095	0.6247
14.7273	1620	-	0.1084	0.6209
14.8182	1630	-	0.1063	0.6164
14.9091	1640	-	0.1049	0.6170
15.0	1650	0.1034	0.1043	0.6199
15.0909	1660	-	0.1033	0.6216
15.1818	1670	-	0.1035	0.6244
15.2727	1680	-	0.1048	0.6286
15.3636	1690	-	0.1070	0.6239
15.4545	1700	0.0821	0.1084	0.6237
15.5455	1710	-	0.1095	0.6234
15.6364	1720	-	0.1090	0.6221
15.7273	1730	-	0.1089	0.6227
15.8182	1740	-	0.1091	0.6201
15.9091	1750	0.074	0.1089	0.6195
16.0	1760	-	0.1082	0.6205
16.0909	1770	-	0.1076	0.6198
16.1818	1780	-	0.1079	0.6195
16.2727	1790	-	0.1081	0.6238
16.3636	1800	0.083	0.1066	0.6219
16.4545	1810	-	0.1055	0.6201
16.5455	1820	-	0.1045	0.6217
16.6364	1830	-	0.1030	0.6198
16.7273	1840	-	0.1012	0.6192
16.8182	1850	0.0569	0.1012	0.6198
16.9091	1860	-	0.1017	0.6224
17.0	1870	-	0.1024	0.6220
17.0909	1880	-	0.1038	0.6217
17.1818	1890	-	0.1046	0.6231
17.2727	1900	0.1054	0.1056	0.6191
17.3636	1910	-	0.1064	0.6220
17.4545	1920	-	0.1078	0.6213
17.5455	1930	-	0.1077	0.6228
17.6364	1940	-	0.1071	0.6194
17.7273	1950	0.0588	0.1073	0.6227
17.8182	1960	-	0.1073	0.6219
17.9091	1970	-	0.1074	0.6217
18.0	1980	-	0.1073	0.6239
18.0909	1990	-	0.1074	0.6210
18.1818	2000	0.0772	0.1076	0.6226
18.2727	2010	-	0.1081	0.6215
18.3636	2020	-	0.1081	0.6206
18.4545	2030	-	0.1073	0.6229
18.5455	2040	-	0.1069	0.6221
18.6364	2050	0.0669	0.1070	0.6233
18.7273	2060	-	0.1062	0.6233
18.8182	2070	-	0.1051	0.6232
18.9091	2080	-	0.1038	0.6211
19.0	2090	-	0.1028	0.6210
19.0909	2100	0.0638	0.1015	0.6214
19.1818	2110	-	0.1021	0.6208
19.2727	2120	-	0.1029	0.6205
19.3636	2130	-	0.1033	0.6205
19.4545	2140	-	0.1044	0.6206
19.5455	2150	0.0805	0.1030	0.6187
19.6364	2160	-	0.1029	0.6199
19.7273	2170	-	0.1041	0.6214
19.8182	2180	-	0.1050	0.6211
19.9091	2190	-	0.1040	0.6207
20.0	2200	0.0932	0.1028	0.6201
20.0909	2210	-	0.1019	0.6212
20.1818	2220	-	0.1030	0.6202
20.2727	2230	-	0.1034	0.6212
20.3636	2240	-	0.1029	0.6224
20.4545	2250	0.0655	0.1034	0.6203
20.5455	2260	-	0.1030	0.6229
20.6364	2270	-	0.1023	0.6193
20.7273	2280	-	0.1022	0.6185
20.8182	2290	-	0.1017	0.6189
20.9091	2300	0.0879	0.1011	0.6178
21.0	2310	-	0.1015	0.6175
21.0909	2320	-	0.1019	0.6182
21.1818	2330	-	0.1013	0.6198
21.2727	2340	-	0.1014	0.6187
21.3636	2350	0.074	0.1022	0.6205
21.4545	2360	-	0.1038	0.6213
21.5455	2370	-	0.1043	0.6236
21.6364	2380	-	0.1044	0.6231
21.7273	2390	-	0.1045	0.6221
21.8182	2400	0.0768	0.1050	0.6224
21.9091	2410	-	0.1054	0.6222
22.0	2420	-	0.1052	0.6214
22.0909	2430	-	0.1051	0.6186
22.1818	2440	-	0.1055	0.6193
22.2727	2450	0.0741	0.1055	0.6205
22.3636	2460	-	0.1053	0.6208
22.4545	2470	-	0.1052	0.6224
22.5455	2480	-	0.1037	0.6191
22.6364	2490	-	0.1032	0.6189
22.7273	2500	0.0669	0.1034	0.6189
22.8182	2510	-	0.1037	0.6224
22.9091	2520	-	0.1038	0.6226
23.0	2530	-	0.1035	0.6203
23.0909	2540	-	0.1030	0.6198
23.1818	2550	0.0762	0.1029	0.6201
23.2727	2560	-	0.1025	0.6195
23.3636	2570	-	0.1024	0.6215
23.4545	2580	-	0.1028	0.6224
23.5455	2590	-	0.1036	0.6232
23.6364	2600	0.0815	0.1037	0.6227
23.7273	2610	-	0.1039	0.6227
23.8182	2620	-	0.1036	0.6211
23.9091	2630	-	0.1034	0.6192
24.0	2640	-	0.1033	0.6193
24.0909	2650	0.0661	0.1033	0.6178
24.1818	2660	-	0.1027	0.6174
24.2727	2670	-	0.1024	0.6198
24.3636	2680	-	0.1025	0.6184
24.4545	2690	-	0.1020	0.6181
24.5455	2700	0.0679	0.1020	0.6194
24.6364	2710	-	0.1020	0.6185
24.7273	2720	-	0.1027	0.6196
24.8182	2730	-	0.1027	0.6191
24.9091	2740	-	0.1030	0.6196
25.0	2750	0.0713	0.1035	0.6208
25.0909	2760	-	0.1042	0.6187
25.1818	2770	-	0.1049	0.6181
25.2727	2780	-	0.1051	0.6200
25.3636	2790	-	0.1051	0.6204
25.4545	2800	0.0786	0.1048	0.6184
25.5455	2810	-	0.1049	0.6198
25.6364	2820	-	0.1051	0.6200
25.7273	2830	-	0.1051	0.6198
25.8182	2840	-	0.1048	0.6190
25.9091	2850	0.0613	0.1050	0.6196
26.0	2860	-	0.1050	0.6183
26.0909	2870	-	0.1047	0.6198
26.1818	2880	-	0.1046	0.6197
26.2727	2890	-	0.1045	0.6217
26.3636	2900	0.0576	0.1045	0.6208
26.4545	2910	-	0.1047	0.6192
26.5455	2920	-	0.1046	0.6220
26.6364	2930	-	0.1042	0.6189
26.7273	2940	-	0.1039	0.6204
26.8182	2950	0.066	0.1036	0.6215
26.9091	2960	-	0.1032	0.6188
27.0	2970	-	0.1030	0.6209
27.0909	2980	-	0.1027	0.6203
27.1818	2990	-	0.1026	0.6215
27.2727	3000	0.0681	0.1025	0.6212
27.3636	3010	-	0.1026	0.6193
27.4545	3020	-	0.1027	0.6189
27.5455	3030	-	0.1028	0.6195
27.6364	3040	-	0.1030	0.6196
27.7273	3050	0.081	0.1031	0.6187
27.8182	3060	-	0.1032	0.6181
27.9091	3070	-	0.1030	0.6177
28.0	3080	-	0.1029	0.6202
28.0909	3090	-	0.1030	0.6193
28.1818	3100	0.0443	0.1031	0.6195
28.2727	3110	-	0.1031	0.6195
28.3636	3120	-	0.1032	0.6177
28.4545	3130	-	0.1034	0.6187
28.5455	3140	-	0.1035	0.6189
28.6364	3150	0.0646	0.1036	0.6187
28.7273	3160	-	0.1037	0.6199
28.8182	3170	-	0.1038	0.6208
28.9091	3180	-	0.1038	0.6190
29.0	3190	-	0.1038	0.6191
29.0909	3200	0.0692	0.1038	0.6190
29.1818	3210	-	0.1038	0.6201
29.2727	3220	-	0.1038	0.6194
29.3636	3230	-	0.1037	0.6201
29.4545	3240	-	0.1037	0.6189
29.5455	3250	0.084	0.1037	0.6194
29.6364	3260	-	0.1037	0.6189
29.7273	3270	-	0.1038	0.6199
29.8182	3280	-	0.1038	0.6194
29.9091	3290	-	0.1038	0.6191
30.0	3300	0.0598	0.1038	0.6190

• The bold row denotes the saved checkpoint.

Framework Versions

• Python: 3.10.12
• Sentence Transformers: 3.3.0
• Transformers: 4.46.2
• PyTorch: 2.5.1+cu121
• Accelerate: 1.1.1
• Datasets: 3.1.0
• Tokenizers: 0.20.3

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",
}

GISTEmbedLoss

@misc{solatorio2024gistembed,
    title={GISTEmbed: Guided In-sample Selection of Training Negatives for Text Embedding Fine-tuning},
    author={Aivin V. Solatorio},
    year={2024},
    eprint={2402.16829},
    archivePrefix={arXiv},
    primaryClass={cs.LG}
}