Neelkumar/my-embedding-gemma-5424

SentenceTransformer based on google/embeddinggemma-300m

This is a sentence-transformers model finetuned from google/embeddinggemma-300m. 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: google/embeddinggemma-300m
• Maximum Sequence Length: 2048 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': 2048, 'do_lower_case': False, 'architecture': 'Gemma3TextModel'})
  (1): Pooling({'word_embedding_dimension': 768, '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): Dense({'in_features': 768, 'out_features': 3072, 'bias': False, 'activation_function': 'torch.nn.modules.linear.Identity'})
  (3): Dense({'in_features': 3072, 'out_features': 768, 'bias': False, 'activation_function': 'torch.nn.modules.linear.Identity'})
  (4): 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("Neelkumar/my-embedding-gemma-5424")
# Run inference
queries = [
    "How can I find information about past Access to Information requests?",
]
documents = [
    'Search the summaries of completed Access to Information (ATI) requests to find information about ATI requests made to the Government of Canada after January 2020.',
    'What are the eligibility requirements for the Canada Pension Plan?',
    'This house style was a popular design from 1890-1900.',
]
query_embeddings = model.encode_query(queries)
document_embeddings = model.encode_document(documents)
print(query_embeddings.shape, document_embeddings.shape)
# [1, 768] [3, 768]

# Get the similarity scores for the embeddings
similarities = model.similarity(query_embeddings, document_embeddings)
print(similarities)
# tensor([[ 0.9569,  0.1398, -0.0558]])

Training Details

Training Dataset

Unnamed Dataset

• Size: 5,424 training 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: 15.8 tokens max: 35 tokens	min: 8 tokens mean: 32.04 tokens max: 130 tokens	min: 11 tokens mean: 15.01 tokens max: 42 tokens

• Samples:

  anchor	positive	negative
  Quelles mesures les propriétaires peuvent-ils prendre pour éliminer les punaises de lit?	Les propriétaires peuvent instaurer différentes mesures pour prévenir et éliminer les punaises des lits.	Quelles sont les conditions pour obtenir une assurance automobile?
  Comment les pages web du gouvernement de la Saskatchewan sont-elles traduites en français?	Un certain nombre de pages sur le site web du gouvernement de la Saskatchewan ont été traduites professionnellement en français.	Quelles sont les exigences pour obtenir un permis de conduire?
  How long do plant breeders' rights last in Canada?	Plant breeders receive legal protection for up to 25 years for trees and vines, and 20 years for other plant varieties.	What are the requirements for importing a pet into Canada?

• Loss: MultipleNegativesRankingLoss with these parameters:

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

Training Hyperparameters

Non-Default Hyperparameters

• per_device_train_batch_size: 4
• learning_rate: 2e-05
• num_train_epochs: 10
• warmup_ratio: 0.1
• prompts: task: sentence similarity | query:

All Hyperparameters

Click to expand

• overwrite_output_dir: False
• do_predict: False
• eval_strategy: no
• prediction_loss_only: True
• per_device_train_batch_size: 4
• per_device_eval_batch_size: 8
• 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: 2e-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: 10
• 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: 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}
• parallelism_config: 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
• hub_revision: None
• 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
• 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
• liger_kernel_config: None
• eval_use_gather_object: False
• average_tokens_across_devices: False
• prompts: task: sentence similarity | query:
• batch_sampler: batch_sampler
• multi_dataset_batch_sampler: proportional
• router_mapping: {}
• learning_rate_mapping: {}

Training Logs

Click to expand

Epoch	Step	Training Loss
0.0147	20	0.1138
0.0295	40	0.0682
0.0442	60	0.0099
0.0590	80	0.0212
0.0737	100	0.0447
0.0885	120	0.0047
0.1032	140	0.0057
0.1180	160	0.0025
0.1327	180	0.0036
0.1475	200	0.0062
0.1622	220	0.0285
0.1770	240	0.0069
0.1917	260	0.0008
0.2065	280	0.0104
0.2212	300	0.0019
0.2360	320	0.0576
0.2507	340	0.0088
0.2655	360	0.0046
0.2802	380	0.0014
0.2950	400	0.001
0.3097	420	0.0184
0.3245	440	0.0016
0.3392	460	0.0019
0.3540	480	0.0192
0.3687	500	0.0392
0.3835	520	0.0051
0.3982	540	0.0023
0.4130	560	0.0119
0.4277	580	0.0022
0.4425	600	0.0046
0.4572	620	0.0041
0.4720	640	0.0066
0.4867	660	0.0115
0.5015	680	0.0112
0.5162	700	0.0327
0.5310	720	0.0009
0.5457	740	0.0031
0.5605	760	0.0007
0.5752	780	0.0367
0.5900	800	0.0344
0.6047	820	0.0027
0.6195	840	0.0105
0.6342	860	0.0597
0.6490	880	0.0594
0.6637	900	0.0022
0.6785	920	0.0177
0.6932	940	0.0041
0.7080	960	0.0123
0.7227	980	0.0988
0.7375	1000	0.0248
0.7522	1020	0.0021
0.7670	1040	0.0376
0.7817	1060	0.0216
0.7965	1080	0.0779
0.8112	1100	0.0317
0.8260	1120	0.0233
0.8407	1140	0.0201
0.8555	1160	0.1391
0.8702	1180	0.0846
0.8850	1200	0.0064
0.8997	1220	0.1509
0.9145	1240	0.0196
0.9292	1260	0.0198
0.9440	1280	0.0174
0.9587	1300	0.117
0.9735	1320	0.0741
0.9882	1340	0.3282
1.0029	1360	0.0314
1.0177	1380	0.1522
1.0324	1400	0.0378
1.0472	1420	0.025
1.0619	1440	0.0442
1.0767	1460	0.0314
1.0914	1480	0.0745
1.1062	1500	0.0272
1.1209	1520	0.1248
1.1357	1540	0.299
1.1504	1560	0.0123
1.1652	1580	0.0245
1.1799	1600	0.0153
1.1947	1620	0.0171
1.2094	1640	0.0146
1.2242	1660	0.0313
1.2389	1680	0.0317
1.2537	1700	0.084
1.2684	1720	0.0569
1.2832	1740	0.1958
1.2979	1760	0.09
1.3127	1780	0.0526
1.3274	1800	0.0956
1.3422	1820	0.1601
1.3569	1840	0.156
1.3717	1860	0.0296
1.3864	1880	0.0391
1.4012	1900	0.0816
1.4159	1920	0.1262
1.4307	1940	0.1375
1.4454	1960	0.3373
1.4602	1980	0.094
1.4749	2000	0.0875
1.4897	2020	0.1161
1.5044	2040	0.1739
1.5192	2060	0.0526
1.5339	2080	0.1364
1.5487	2100	0.0508
1.5634	2120	0.0614
1.5782	2140	0.0589
1.5929	2160	0.0593
1.6077	2180	0.0078
1.6224	2200	0.2009
1.6372	2220	0.1356
1.6519	2240	0.1268
1.6667	2260	0.0257
1.6814	2280	0.0679
1.6962	2300	0.0229
1.7109	2320	0.1467
1.7257	2340	0.1239
1.7404	2360	0.0138
1.7552	2380	0.0997
1.7699	2400	0.0197
1.7847	2420	0.0358
1.7994	2440	0.0368
1.8142	2460	0.0755
1.8289	2480	0.1305
1.8437	2500	0.0164
1.8584	2520	0.1273
1.8732	2540	0.0255
1.8879	2560	0.0547
1.9027	2580	0.0494
1.9174	2600	0.1257
1.9322	2620	0.0434
1.9469	2640	0.0358
1.9617	2660	0.1272
1.9764	2680	0.022
1.9912	2700	0.054
2.0059	2720	0.0281
2.0206	2740	0.0229
2.0354	2760	0.0117
2.0501	2780	0.0242
2.0649	2800	0.0819
2.0796	2820	0.0625
2.0944	2840	0.0622
2.1091	2860	0.0316
2.1239	2880	0.2254
2.1386	2900	0.0857
2.1534	2920	0.026
2.1681	2940	0.0023
2.1829	2960	0.0053
2.1976	2980	0.004
2.2124	3000	0.0087
2.2271	3020	0.0068
2.2419	3040	0.0207
2.2566	3060	0.0522
2.2714	3080	0.005
2.2861	3100	0.038
2.3009	3120	0.0059
2.3156	3140	0.035
2.3304	3160	0.0603
2.3451	3180	0.0209
2.3599	3200	0.0103
2.3746	3220	0.0109
2.3894	3240	0.0755
2.4041	3260	0.0021
2.4189	3280	0.1019
2.4336	3300	0.1014
2.4484	3320	0.0198
2.4631	3340	0.0205
2.4779	3360	0.0431
2.4926	3380	0.1268
2.5074	3400	0.0097
2.5221	3420	0.0035
2.5369	3440	0.0292
2.5516	3460	0.0175
2.5664	3480	0.0687
2.5811	3500	0.021
2.5959	3520	0.0438
2.6106	3540	0.0024
2.6254	3560	0.0029
2.6401	3580	0.0267
2.6549	3600	0.0288
2.6696	3620	0.0058
2.6844	3640	0.0634
2.6991	3660	0.0404
2.7139	3680	0.0253
2.7286	3700	0.0127
2.7434	3720	0.0786
2.7581	3740	0.0739
2.7729	3760	0.0348
2.7876	3780	0.0697
2.8024	3800	0.0143
2.8171	3820	0.015
2.8319	3840	0.0139
2.8466	3860	0.023
2.8614	3880	0.0625
2.8761	3900	0.01
2.8909	3920	0.0656
2.9056	3940	0.0435
2.9204	3960	0.0367
2.9351	3980	0.0482
2.9499	4000	0.0557
2.9646	4020	0.1046
2.9794	4040	0.0578
2.9941	4060	0.0793
3.0088	4080	0.0053
3.0236	4100	0.0035
3.0383	4120	0.0095
3.0531	4140	0.001
3.0678	4160	0.0368
3.0826	4180	0.0251
3.0973	4200	0.0084
3.1121	4220	0.0224
3.1268	4240	0.0407
3.1416	4260	0.0611
3.1563	4280	0.0226
3.1711	4300	0.0092
3.1858	4320	0.0052
3.2006	4340	0.0578
3.2153	4360	0.0259
3.2301	4380	0.0002
3.2448	4400	0.0787
3.2596	4420	0.0194
3.2743	4440	0.0002
3.2891	4460	0.0006
3.3038	4480	0.0188
3.3186	4500	0.0722
3.3333	4520	0.0621
3.3481	4540	0.0017
3.3628	4560	0.1242
3.3776	4580	0.0057
3.3923	4600	0.0064
3.4071	4620	0.0016
3.4218	4640	0.0007
3.4366	4660	0.1187
3.4513	4680	0.0529
3.4661	4700	0.0294
3.4808	4720	0.1213
3.4956	4740	0.0221
3.5103	4760	0.0234
3.5251	4780	0.0034
3.5398	4800	0.0107
3.5546	4820	0.012
3.5693	4840	0.0351
3.5841	4860	0.0099
3.5988	4880	0.002
3.6136	4900	0.0024
3.6283	4920	0.0321
3.6431	4940	0.0008
3.6578	4960	0.038
3.6726	4980	0.0944
3.6873	5000	0.0227
3.7021	5020	0.0088
3.7168	5040	0.0573
3.7316	5060	0.2029
3.7463	5080	0.0522
3.7611	5100	0.012
3.7758	5120	0.0044
3.7906	5140	0.0178
3.8053	5160	0.0032
3.8201	5180	0.0375
3.8348	5200	0.0322
3.8496	5220	0.0066
3.8643	5240	0.0108
3.8791	5260	0.0143
3.8938	5280	0.0271
3.9086	5300	0.003
3.9233	5320	0.0183
3.9381	5340	0.0307
3.9528	5360	0.0026
3.9676	5380	0.0031
3.9823	5400	0.0011
3.9971	5420	0.0749
4.0118	5440	0.0192
4.0265	5460	0.037
4.0413	5480	0.0017
4.0560	5500	0.0013
4.0708	5520	0.0246
4.0855	5540	0.0007
4.1003	5560	0.045
4.1150	5580	0.038
4.1298	5600	0.0179
4.1445	5620	0.021
4.1593	5640	0.0012
4.1740	5660	0.0001
4.1888	5680	0.0004
4.2035	5700	0.0001
4.2183	5720	0.0021
4.2330	5740	0.0279
4.2478	5760	0.0044
4.2625	5780	0.0063
4.2773	5800	0.0046
4.2920	5820	0.0692
4.3068	5840	0.0007
4.3215	5860	0.0053
4.3363	5880	0.0288
4.3510	5900	0.0197
4.3658	5920	0.0007
4.3805	5940	0.002
4.3953	5960	0.0059
4.4100	5980	0.0258
4.4248	6000	0.001
4.4395	6020	0.0017
4.4543	6040	0.0024
4.4690	6060	0.0748
4.4838	6080	0.002
4.4985	6100	0.0498
4.5133	6120	0.0016
4.5280	6140	0.0018
4.5428	6160	0.0022
4.5575	6180	0.0012
4.5723	6200	0.009
4.5870	6220	0.0659
4.6018	6240	0.0121
4.6165	6260	0.0294
4.6313	6280	0.0002
4.6460	6300	0.0184
4.6608	6320	0.0158
4.6755	6340	0.0104
4.6903	6360	0.0498
4.7050	6380	0.0061
4.7198	6400	0.0305
4.7345	6420	0.0427
4.7493	6440	0.0004
4.7640	6460	0.0009
4.7788	6480	0.0001
4.7935	6500	0.0261
4.8083	6520	0.0019
4.8230	6540	0.0024
4.8378	6560	0.0228
4.8525	6580	0.0002
4.8673	6600	0.002
4.8820	6620	0.0005
4.8968	6640	0.0082
4.9115	6660	0.0119
4.9263	6680	0.0175
4.9410	6700	0.0011
4.9558	6720	0.0021
4.9705	6740	0.0106
4.9853	6760	0.018
5.0	6780	0.019
5.0147	6800	0.0629
5.0295	6820	0.0076
5.0442	6840	0.0004
5.0590	6860	0.0014
5.0737	6880	0.0012
5.0885	6900	0.0021
5.1032	6920	0.0032
5.1180	6940	0.0275
5.1327	6960	0.019
5.1475	6980	0.0006
5.1622	7000	0.0006
5.1770	7020	0.0049
5.1917	7040	0.0359
5.2065	7060	0.0028
5.2212	7080	0.0012
5.2360	7100	0.0138
5.2507	7120	0.0042
5.2655	7140	0.0003
5.2802	7160	0.0056
5.2950	7180	0.0329
5.3097	7200	0.0016
5.3245	7220	0.0092
5.3392	7240	0.0002
5.3540	7260	0.0211
5.3687	7280	0.019
5.3835	7300	0.0012
5.3982	7320	0.0002
5.4130	7340	0.0002
5.4277	7360	0.0143
5.4425	7380	0.0004
5.4572	7400	0.0004
5.4720	7420	0.0068
5.4867	7440	0.0201
5.5015	7460	0.0003
5.5162	7480	0.0042
5.5310	7500	0.0007
5.5457	7520	0.0664
5.5605	7540	0.0014
5.5752	7560	0.0175
5.5900	7580	0.0362
5.6047	7600	0.0225
5.6195	7620	0.0003
5.6342	7640	0.0025
5.6490	7660	0.0128
5.6637	7680	0.0013
5.6785	7700	0.0042
5.6932	7720	0.0012
5.7080	7740	0.0017
5.7227	7760	0.0039
5.7375	7780	0.0013
5.7522	7800	0.0008
5.7670	7820	0.006
5.7817	7840	0.0177
5.7965	7860	0.0189
5.8112	7880	0.0015
5.8260	7900	0.0003
5.8407	7920	0.001
5.8555	7940	0.0269
5.8702	7960	0.0006
5.8850	7980	0.0176
5.8997	8000	0.0048
5.9145	8020	0.0031
5.9292	8040	0.0056
5.9440	8060	0.0015
5.9587	8080	0.0102
5.9735	8100	0.0047
5.9882	8120	0.0339
6.0029	8140	0.0027
6.0177	8160	0.0008
6.0324	8180	0.0014
6.0472	8200	0.0001
6.0619	8220	0.0183
6.0767	8240	0.0142
6.0914	8260	0.0004
6.1062	8280	0.0392
6.1209	8300	0.0016
6.1357	8320	0.0025
6.1504	8340	0.0017
6.1652	8360	0.018
6.1799	8380	0.0031
6.1947	8400	0.0021
6.2094	8420	0.0244
6.2242	8440	0.0263
6.2389	8460	0.0183
6.2537	8480	0.0367
6.2684	8500	0.0009
6.2832	8520	0.0
6.2979	8540	0.0001
6.3127	8560	0.0011
6.3274	8580	0.0007
6.3422	8600	0.0004
6.3569	8620	0.0044
6.3717	8640	0.0174
6.3864	8660	0.0002
6.4012	8680	0.0176
6.4159	8700	0.0341
6.4307	8720	0.0015
6.4454	8740	0.0002
6.4602	8760	0.0043
6.4749	8780	0.0036
6.4897	8800	0.0001
6.5044	8820	0.0004
6.5192	8840	0.0474
6.5339	8860	0.0001
6.5487	8880	0.0003
6.5634	8900	0.0021
6.5782	8920	0.0014
6.5929	8940	0.0004
6.6077	8960	0.0176
6.6224	8980	0.0001
6.6372	9000	0.0009
6.6519	9020	0.0015
6.6667	9040	0.0003
6.6814	9060	0.0001
6.6962	9080	0.0016
6.7109	9100	0.0182
6.7257	9120	0.0002
6.7404	9140	0.0009
6.7552	9160	0.0018
6.7699	9180	0.0182
6.7847	9200	0.0
6.7994	9220	0.0206
6.8142	9240	0.0001
6.8289	9260	0.0002
6.8437	9280	0.0037
6.8584	9300	0.0238
6.8732	9320	0.0002
6.8879	9340	0.0
6.9027	9360	0.0002
6.9174	9380	0.019
6.9322	9400	0.0059
6.9469	9420	0.0002
6.9617	9440	0.0001
6.9764	9460	0.0004
6.9912	9480	0.0023
7.0059	9500	0.0006
7.0206	9520	0.0019
7.0354	9540	0.0176
7.0501	9560	0.0026
7.0649	9580	0.0014
7.0796	9600	0.0003
7.0944	9620	0.0001
7.1091	9640	0.0002
7.1239	9660	0.0362
7.1386	9680	0.001
7.1534	9700	0.0001
7.1681	9720	0.0002
7.1829	9740	0.0029
7.1976	9760	0.0002
7.2124	9780	0.0003
7.2271	9800	0.0027
7.2419	9820	0.0001
7.2566	9840	0.0001
7.2714	9860	0.0002
7.2861	9880	0.0124
7.3009	9900	0.0361
7.3156	9920	0.0039
7.3304	9940	0.0
7.3451	9960	0.0
7.3599	9980	0.0008
7.3746	10000	0.0002
7.3894	10020	0.0003
7.4041	10040	0.0001
7.4189	10060	0.0174
7.4336	10080	0.0015
7.4484	10100	0.0152
7.4631	10120	0.0351
7.4779	10140	0.0007
7.4926	10160	0.0005
7.5074	10180	0.0005
7.5221	10200	0.0001
7.5369	10220	0.0002
7.5516	10240	0.0001
7.5664	10260	0.001
7.5811	10280	0.0057
7.5959	10300	0.0012
7.6106	10320	0.0001
7.6254	10340	0.0005
7.6401	10360	0.0016
7.6549	10380	0.0072
7.6696	10400	0.0007
7.6844	10420	0.0001
7.6991	10440	0.0002
7.7139	10460	0.0036
7.7286	10480	0.0001
7.7434	10500	0.0002
7.7581	10520	0.0001
7.7729	10540	0.0001
7.7876	10560	0.0007
7.8024	10580	0.0002
7.8171	10600	0.0001
7.8319	10620	0.018
7.8466	10640	0.0882
7.8614	10660	0.0006
7.8761	10680	0.0001
7.8909	10700	0.0001
7.9056	10720	0.0001
7.9204	10740	0.0176
7.9351	10760	0.0002
7.9499	10780	0.0231
7.9646	10800	0.0002
7.9794	10820	0.0002
7.9941	10840	0.0
8.0088	10860	0.0001
8.0236	10880	0.0001
8.0383	10900	0.0003
8.0531	10920	0.0172
8.0678	10940	0.0002
8.0826	10960	0.018
8.0973	10980	0.0174
8.1121	11000	0.0001
8.1268	11020	0.0174
8.1416	11040	0.0
8.1563	11060	0.0039
8.1711	11080	0.0001
8.1858	11100	0.0
8.2006	11120	0.002
8.2153	11140	0.0176
8.2301	11160	0.0022
8.2448	11180	0.0001
8.2596	11200	0.0
8.2743	11220	0.0027
8.2891	11240	0.0198
8.3038	11260	0.0
8.3186	11280	0.0003
8.3333	11300	0.0223
8.3481	11320	0.0092
8.3628	11340	0.0001
8.3776	11360	0.0009
8.3923	11380	0.0014
8.4071	11400	0.0006
8.4218	11420	0.0006
8.4366	11440	0.0006
8.4513	11460	0.0005
8.4661	11480	0.0192
8.4808	11500	0.0347
8.4956	11520	0.0009
8.5103	11540	0.0002
8.5251	11560	0.0
8.5398	11580	0.0
8.5546	11600	0.0002
8.5693	11620	0.0174
8.5841	11640	0.0001
8.5988	11660	0.0171
8.6136	11680	0.0001
8.6283	11700	0.0001
8.6431	11720	0.0428
8.6578	11740	0.0003
8.6726	11760	0.0
8.6873	11780	0.0001
8.7021	11800	0.0176
8.7168	11820	0.0358
8.7316	11840	0.0002
8.7463	11860	0.0002
8.7611	11880	0.0001
8.7758	11900	0.0002
8.7906	11920	0.0015
8.8053	11940	0.0001
8.8201	11960	0.0001
8.8348	11980	0.0112
8.8496	12000	0.0033
8.8643	12020	0.0001
8.8791	12040	0.001
8.8938	12060	0.0174
8.9086	12080	0.0001
8.9233	12100	0.0002
8.9381	12120	0.0001
8.9528	12140	0.0001
8.9676	12160	0.0222
8.9823	12180	0.0003
8.9971	12200	0.0001
9.0118	12220	0.0
9.0265	12240	0.0001
9.0413	12260	0.0182
9.0560	12280	0.0174
9.0708	12300	0.0
9.0855	12320	0.0
9.1003	12340	0.0023
9.1150	12360	0.0001
9.1298	12380	0.0248
9.1445	12400	0.0
9.1593	12420	0.0
9.1740	12440	0.0
9.1888	12460	0.0001
9.2035	12480	0.0087
9.2183	12500	0.0
9.2330	12520	0.0003
9.2478	12540	0.0174
9.2625	12560	0.0
9.2773	12580	0.0006
9.2920	12600	0.0001
9.3068	12620	0.0053
9.3215	12640	0.0
9.3363	12660	0.0174
9.3510	12680	0.0001
9.3658	12700	0.0002
9.3805	12720	0.0001
9.3953	12740	0.0001
9.4100	12760	0.0001
9.4248	12780	0.0002
9.4395	12800	0.0002
9.4543	12820	0.0023
9.4690	12840	0.0
9.4838	12860	0.0018
9.4985	12880	0.0028
9.5133	12900	0.0174
9.5280	12920	0.0001
9.5428	12940	0.0001
9.5575	12960	0.0174
9.5723	12980	0.0003
9.5870	13000	0.0
9.6018	13020	0.0174
9.6165	13040	0.0001
9.6313	13060	0.0
9.6460	13080	0.0001
9.6608	13100	0.0174
9.6755	13120	0.0173
9.6903	13140	0.0
9.7050	13160	0.0005
9.7198	13180	0.0001
9.7345	13200	0.0002
9.7493	13220	0.0
9.7640	13240	0.0001
9.7788	13260	0.0
9.7935	13280	0.0026
9.8083	13300	0.0003
9.8230	13320	0.0001
9.8378	13340	0.0174
9.8525	13360	0.0099
9.8673	13380	0.0002
9.8820	13400	0.0
9.8968	13420	0.0032
9.9115	13440	0.0177
9.9263	13460	0.0175
9.9410	13480	0.0176
9.9558	13500	0.0001
9.9705	13520	0.0
9.9853	13540	0.0011
10.0	13560	0.0174

Framework Versions

• Python: 3.11.13
• Sentence Transformers: 5.1.1
• Transformers: 4.57.0.dev0
• PyTorch: 2.6.0+cu124
• Accelerate: 1.8.1
• Datasets: 3.6.0
• Tokenizers: 0.22.1

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}
}