AryoshiW/distilbert-en-id-qa

SentenceTransformer based on distilbert/distilbert-base-multilingual-cased

This is a sentence-transformers model finetuned from distilbert/distilbert-base-multilingual-cased on the default dataset. 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: distilbert/distilbert-base-multilingual-cased
• Maximum Sequence Length: 128 tokens
• Output Dimensionality: 768 dimensions
• Similarity Function: Cosine Similarity
• Training Dataset:
  • default

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': 128, 'do_lower_case': False}) with Transformer model: DistilBertModel 
  (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})
)

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("sentence_transformers_model_id")
# Run inference
sentences = [
    '1 Concrete is typically measured by cubic yards (3â\x80\x99x3â\x80\x99x3â\x80\x99). 2  An average cost for a cubic yard of concrete is $75 to $125, depending on how much is needed and local prices. 3  Labor costs to pour and form concrete run somewhere around $3.50 to $7.00 per square foot. An average cost for a cubic yard of concrete is $75 to $125, depending on how much is needed and local prices. 2  Labor costs to pour and form concrete run somewhere around $3.50 to $7.00 per square foot.',
    '1 Beton biasanya diukur dengan meter kubik (3âÂâââx3Ãâ¢Ã‚ââx3âÂââ„¢). 2 Biaya rata-rata untuk satu yard kubik beton adalah $75 sampai $125, tergantung pada berapa banyak yang dibutuhkan dan harga setempat. 3 Biaya tenaga kerja untuk menuangkan dan membentuk beton berkisar antara $3,50 hingga $7,00 per kaki persegi. Biaya rata-rata untuk satu yard kubik beton adalah $75 sampai $125, tergantung pada berapa banyak yang dibutuhkan dan harga lokal. 2 Biaya tenaga kerja untuk menuangkan dan membentuk beton berkisar antara $3,50 hingga $7,00 per kaki persegi.',
    "Parrot Tattoos - Polly ingin cracker.. Ungkapan ini identik dengan 'parrot', terutama yang duduk di bahu bajak laut, seperti yang dibuat terkenal dalam cerita klasik Robert Louis Stevenson, Treasure Island (1883).lint', yang mungkin tidak adalah burung beo pertama yang diasosiasikan dengan nama 'Polly', tapi dia pasti mempopulerkannya. Dan Polly tentu memastikan burung beo itu akan menjadi simbol ikonik dari tradisi bajak laut. Sebagai pendamping legendaris bagi manusia, burung beo menyarankan semacam wali.",
]
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]

Evaluation

Metrics

Knowledge Distillation

• Dataset: default
• Evaluated with MSEEvaluator

Metric	Value
negative_mse	-3.5554

Translation

• Dataset: default
• Evaluated with TranslationEvaluator

Metric	Value
src2trg_accuracy	0.9894
trg2src_accuracy	0.9861
mean_accuracy	0.9877

Training Details

Training Dataset

default

• Dataset: default at c8bc0cb
• Size: 1,000,000 training samples
• Columns: english, indonesian, and label
• Approximate statistics based on the first 1000 samples:

  	english	indonesian	label
  type	string	string	list
  details	min: 4 tokens mean: 44.27 tokens max: 128 tokens	min: 5 tokens mean: 48.93 tokens max: 128 tokens	size: 768 elements

• Samples:

  english	indonesian	label
  This sample job description shares how one smaller sized, growing, multi-site nonprofit organization configured the role of executive director.The executive director is responsible for general management as well as designing a national expansion plan. There also is a heavy emphasis on program evaluation.Feel free to use this sample job description in creating one for your organization.osition. Reporting to the Board of Directors, the Executive Director (ED) will have overall strategic and operational responsibility for XYZ Nonprofit's staff, programs, expansion, and execution of its mission. S/he will initially develop deep knowledge of field, core programs, operations, and business plans.	Uraian tugas contoh ini membagikan bagaimana satu organisasi nirlaba multi-situs berukuran lebih kecil, berkembang, mengonfigurasi peran direktur eksekutif. Direktur eksekutif bertanggung jawab atas manajemen umum serta merancang rencana ekspansi nasional. Ada juga penekanan berat pada evaluasi program. Jangan ragu untuk menggunakan contoh deskripsi pekerjaan ini dalam membuat satu untuk posisi organisasi Anda. Melaporkan kepada Dewan Direksi, Direktur Eksekutif (ED) akan memiliki tanggung jawab strategis dan operasional secara keseluruhan untuk staf, program, ekspansi, dan pelaksanaan misi XYZ Nirlaba. Dia awalnya akan mengembangkan pengetahuan yang mendalam tentang lapangan, program inti, operasi, dan rencana bisnis.	[-0.4337165653705597, -0.0650932714343071, -0.04308838024735451, -0.1756953001022339, 0.32854965329170227, ...]
  Industrial revolution occured last in Russia. In Germany, France and United States industrial revolution occured in early-to-mid 1800's. While in Russia creation of railroads, and foundation of factories happened by govermental initiatives towards the end of XIX century.n Germany, France and United States industrial revolution occured in early-to-mid 1800's.	Revolusi industri terakhir terjadi di Rusia. Di Jerman, Perancis dan Amerika Serikat terjadi revolusi industri pada awal hingga pertengahan 1800-an. Sedangkan di Rusia pembuatan rel kereta api, dan pendirian pabrik terjadi atas inisiatif pemerintah menjelang akhir abad XIX. Revolusi industri Jerman, Prancis dan Amerika Serikat terjadi pada awal hingga pertengahan 1800-an.	[-0.22887374460697174, -0.17583712935447693, 0.08270637691020966, -0.15496928989887238, -0.18010610342025757, ...]
  what causes hordeolum internum left lower eyelid	apa penyebab hordeolum internum kelopak mata kiri bawah	[-0.19872592389583588, 0.4119395911693573, 0.3756648004055023, -0.4884617030620575, 0.15375499427318573, ...]

• Loss: MSELoss

Evaluation Dataset

default

• Dataset: default at c8bc0cb
• Size: 1,000,000 evaluation samples
• Columns: english, indonesian, and label
• Approximate statistics based on the first 1000 samples:

  	english	indonesian	label
  type	string	string	list
  details	min: 5 tokens mean: 46.58 tokens max: 128 tokens	min: 5 tokens mean: 51.0 tokens max: 128 tokens	size: 768 elements

• Samples:

  english	indonesian	label
  do appraisers give adjustments for lot size	apakah penilai memberikan penyesuaian untuk ukuran lot?	[0.12256570905447006, 0.011573846451938152, -0.19426874816417694, -0.17596185207366943, 0.35024771094322205, ...]
  hotels in binghamton ny	hotel di binghamton ny	[0.14259624481201172, -0.048470016568899155, 0.1078888401389122, 0.06728225946426392, 0.6096671223640442, ...]
  guitarist kenny greenberg	gitaris kenny greenberg	[-0.6973275542259216, 0.27737292647361755, -0.09295299649238586, 0.24035970866680145, 0.154855415225029, ...]

• Loss: MSELoss

Training Hyperparameters

Non-Default Hyperparameters

• eval_strategy: epoch
• per_device_train_batch_size: 64
• per_device_eval_batch_size: 64
• learning_rate: 2e-05
• num_train_epochs: 5
• warmup_ratio: 0.1
• fp16: True

All Hyperparameters

Click to expand

• overwrite_output_dir: False
• do_predict: False
• eval_strategy: epoch
• prediction_loss_only: True
• per_device_train_batch_size: 64
• per_device_eval_batch_size: 64
• 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: 5
• 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: 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	default loss	default_negative_mse	default_mean_accuracy
0.0065	100	0.1968	-	-	-
0.0129	200	0.1797	-	-	-
0.0194	300	0.1596	-	-	-
0.0259	400	0.1367	-	-	-
0.0323	500	0.1167	-	-	-
0.0388	600	0.103	-	-	-
0.0453	700	0.0954	-	-	-
0.0517	800	0.0909	-	-	-
0.0582	900	0.088	-	-	-
0.0646	1000	0.0861	-	-	-
0.0711	1100	0.0847	-	-	-
0.0776	1200	0.082	-	-	-
0.0840	1300	0.0818	-	-	-
0.0905	1400	0.0813	-	-	-
0.0970	1500	0.0804	-	-	-
0.1034	1600	0.0817	-	-	-
0.1099	1700	0.0799	-	-	-
0.1164	1800	0.0804	-	-	-
0.1228	1900	0.0802	-	-	-
0.1293	2000	0.0791	-	-	-
0.1358	2100	0.0789	-	-	-
0.1422	2200	0.0783	-	-	-
0.1487	2300	0.0783	-	-	-
0.1551	2400	0.077	-	-	-
0.1616	2500	0.0762	-	-	-
0.1681	2600	0.0762	-	-	-
0.1745	2700	0.0754	-	-	-
0.1810	2800	0.075	-	-	-
0.1875	2900	0.0735	-	-	-
0.1939	3000	0.0745	-	-	-
0.2004	3100	0.0739	-	-	-
0.2069	3200	0.0732	-	-	-
0.2133	3300	0.0724	-	-	-
0.2198	3400	0.0727	-	-	-
0.2263	3500	0.0726	-	-	-
0.2327	3600	0.071	-	-	-
0.2392	3700	0.0713	-	-	-
0.2457	3800	0.0708	-	-	-
0.2521	3900	0.0704	-	-	-
0.2586	4000	0.0703	-	-	-
0.2650	4100	0.0704	-	-	-
0.2715	4200	0.0695	-	-	-
0.2780	4300	0.068	-	-	-
0.2844	4400	0.0681	-	-	-
0.2909	4500	0.0683	-	-	-
0.2974	4600	0.0674	-	-	-
0.3038	4700	0.0683	-	-	-
0.3103	4800	0.0674	-	-	-
0.3168	4900	0.0674	-	-	-
0.3232	5000	0.0666	-	-	-
0.3297	5100	0.0677	-	-	-
0.3362	5200	0.066	-	-	-
0.3426	5300	0.0655	-	-	-
0.3491	5400	0.0658	-	-	-
0.3555	5500	0.0658	-	-	-
0.3620	5600	0.0646	-	-	-
0.3685	5700	0.0638	-	-	-
0.3749	5800	0.065	-	-	-
0.3814	5900	0.0648	-	-	-
0.3879	6000	0.0636	-	-	-
0.3943	6100	0.0637	-	-	-
0.4008	6200	0.0636	-	-	-
0.4073	6300	0.0633	-	-	-
0.4137	6400	0.0629	-	-	-
0.4202	6500	0.0638	-	-	-
0.4267	6600	0.0625	-	-	-
0.4331	6700	0.0615	-	-	-
0.4396	6800	0.062	-	-	-
0.4461	6900	0.062	-	-	-
0.4525	7000	0.0614	-	-	-
0.4590	7100	0.0622	-	-	-
0.4654	7200	0.061	-	-	-
0.4719	7300	0.06	-	-	-
0.4784	7400	0.0606	-	-	-
0.4848	7500	0.0606	-	-	-
0.4913	7600	0.0597	-	-	-
0.4978	7700	0.0598	-	-	-
0.5042	7800	0.0594	-	-	-
0.5107	7900	0.0596	-	-	-
0.5172	8000	0.0584	-	-	-
0.5236	8100	0.0589	-	-	-
0.5301	8200	0.0587	-	-	-
0.5366	8300	0.059	-	-	-
0.5430	8400	0.0592	-	-	-
0.5495	8500	0.058	-	-	-
0.5560	8600	0.0576	-	-	-
0.5624	8700	0.0577	-	-	-
0.5689	8800	0.0575	-	-	-
0.5753	8900	0.0576	-	-	-
0.5818	9000	0.0575	-	-	-
0.5883	9100	0.0567	-	-	-
0.5947	9200	0.0568	-	-	-
0.6012	9300	0.0558	-	-	-
0.6077	9400	0.0558	-	-	-
0.6141	9500	0.0563	-	-	-
0.6206	9600	0.0565	-	-	-
0.6271	9700	0.0547	-	-	-
0.6335	9800	0.0555	-	-	-
0.6400	9900	0.0551	-	-	-
0.6465	10000	0.055	-	-	-
0.6529	10100	0.0553	-	-	-
0.6594	10200	0.0548	-	-	-
0.6658	10300	0.0542	-	-	-
0.6723	10400	0.0551	-	-	-
0.6788	10500	0.0545	-	-	-
0.6852	10600	0.0545	-	-	-
0.6917	10700	0.0542	-	-	-
0.6982	10800	0.0538	-	-	-
0.7046	10900	0.0532	-	-	-
0.7111	11000	0.0534	-	-	-
0.7176	11100	0.053	-	-	-
0.7240	11200	0.0534	-	-	-
0.7305	11300	0.0532	-	-	-
0.7370	11400	0.0535	-	-	-
0.7434	11500	0.0533	-	-	-
0.7499	11600	0.0532	-	-	-
0.7564	11700	0.053	-	-	-
0.7628	11800	0.0526	-	-	-
0.7693	11900	0.0527	-	-	-
0.7757	12000	0.053	-	-	-
0.7822	12100	0.0522	-	-	-
0.7887	12200	0.0521	-	-	-
0.7951	12300	0.0524	-	-	-
0.8016	12400	0.0518	-	-	-
0.8081	12500	0.0521	-	-	-
0.8145	12600	0.0516	-	-	-
0.8210	12700	0.0517	-	-	-
0.8275	12800	0.0511	-	-	-
0.8339	12900	0.0517	-	-	-
0.8404	13000	0.0516	-	-	-
0.8469	13100	0.0516	-	-	-
0.8533	13200	0.0509	-	-	-
0.8598	13300	0.0508	-	-	-
0.8662	13400	0.0506	-	-	-
0.8727	13500	0.0507	-	-	-
0.8792	13600	0.0507	-	-	-
0.8856	13700	0.0503	-	-	-
0.8921	13800	0.0504	-	-	-
0.8986	13900	0.0506	-	-	-
0.9050	14000	0.0507	-	-	-
0.9115	14100	0.0503	-	-	-
0.9180	14200	0.0496	-	-	-
0.9244	14300	0.0498	-	-	-
0.9309	14400	0.0499	-	-	-
0.9374	14500	0.0504	-	-	-
0.9438	14600	0.0493	-	-	-
0.9503	14700	0.0495	-	-	-
0.9568	14800	0.0493	-	-	-
0.9632	14900	0.0494	-	-	-
0.9697	15000	0.0495	-	-	-
0.9761	15100	0.0496	-	-	-
0.9826	15200	0.0486	-	-	-
0.9891	15300	0.0491	-	-	-
0.9955	15400	0.0485	-	-	-
1.0	15469	-	0.0479	-4.9594	0.9693
1.0020	15500	0.0487	-	-	-
1.0085	15600	0.0488	-	-	-
1.0149	15700	0.0482	-	-	-
1.0214	15800	0.0486	-	-	-
1.0279	15900	0.0487	-	-	-
1.0343	16000	0.0487	-	-	-
1.0408	16100	0.0484	-	-	-
1.0473	16200	0.0478	-	-	-
1.0537	16300	0.0478	-	-	-
1.0602	16400	0.048	-	-	-
1.0666	16500	0.048	-	-	-
1.0731	16600	0.048	-	-	-
1.0796	16700	0.0478	-	-	-
1.0860	16800	0.0478	-	-	-
1.0925	16900	0.0478	-	-	-
1.0990	17000	0.0472	-	-	-
1.1054	17100	0.048	-	-	-
1.1119	17200	0.047	-	-	-
1.1184	17300	0.0477	-	-	-
1.1248	17400	0.0476	-	-	-
1.1313	17500	0.0473	-	-	-
1.1378	17600	0.0474	-	-	-
1.1442	17700	0.0472	-	-	-
1.1507	17800	0.0473	-	-	-
1.1572	17900	0.0468	-	-	-
1.1636	18000	0.047	-	-	-
1.1701	18100	0.0471	-	-	-
1.1765	18200	0.0467	-	-	-
1.1830	18300	0.0464	-	-	-
1.1895	18400	0.0463	-	-	-
1.1959	18500	0.047	-	-	-
1.2024	18600	0.0463	-	-	-
1.2089	18700	0.0466	-	-	-
1.2153	18800	0.0458	-	-	-
1.2218	18900	0.0465	-	-	-
1.2283	19000	0.0466	-	-	-
1.2347	19100	0.0459	-	-	-
1.2412	19200	0.0464	-	-	-
1.2477	19300	0.0457	-	-	-
1.2541	19400	0.0459	-	-	-
1.2606	19500	0.0463	-	-	-
1.2671	19600	0.0458	-	-	-
1.2735	19700	0.0463	-	-	-
1.2800	19800	0.0449	-	-	-
1.2864	19900	0.0455	-	-	-
1.2929	20000	0.0457	-	-	-
1.2994	20100	0.0455	-	-	-
1.3058	20200	0.0456	-	-	-
1.3123	20300	0.0453	-	-	-
1.3188	20400	0.0453	-	-	-
1.3252	20500	0.0454	-	-	-
1.3317	20600	0.0458	-	-	-
1.3382	20700	0.0449	-	-	-
1.3446	20800	0.0449	-	-	-
1.3511	20900	0.0454	-	-	-
1.3576	21000	0.0448	-	-	-
1.3640	21100	0.0445	-	-	-
1.3705	21200	0.0445	-	-	-
1.3769	21300	0.045	-	-	-
1.3834	21400	0.0448	-	-	-
1.3899	21500	0.0444	-	-	-
1.3963	21600	0.0446	-	-	-
1.4028	21700	0.0446	-	-	-
1.4093	21800	0.0444	-	-	-
1.4157	21900	0.0449	-	-	-
1.4222	22000	0.0447	-	-	-
1.4287	22100	0.044	-	-	-
1.4351	22200	0.0444	-	-	-
1.4416	22300	0.044	-	-	-
1.4481	22400	0.0443	-	-	-
1.4545	22500	0.0443	-	-	-
1.4610	22600	0.0445	-	-	-
1.4675	22700	0.0436	-	-	-
1.4739	22800	0.0438	-	-	-
1.4804	22900	0.0441	-	-	-
1.4868	23000	0.0437	-	-	-
1.4933	23100	0.0434	-	-	-
1.4998	23200	0.0437	-	-	-
1.5062	23300	0.0435	-	-	-
1.5127	23400	0.0437	-	-	-
1.5192	23500	0.043	-	-	-
1.5256	23600	0.0434	-	-	-
1.5321	23700	0.0436	-	-	-
1.5386	23800	0.0439	-	-	-
1.5450	23900	0.0438	-	-	-
1.5515	24000	0.0433	-	-	-
1.5580	24100	0.0429	-	-	-
1.5644	24200	0.0433	-	-	-
1.5709	24300	0.0428	-	-	-
1.5773	24400	0.0434	-	-	-
1.5838	24500	0.0432	-	-	-
1.5903	24600	0.0433	-	-	-
1.5967	24700	0.0426	-	-	-
1.6032	24800	0.0426	-	-	-
1.6097	24900	0.0425	-	-	-
1.6161	25000	0.0432	-	-	-
1.6226	25100	0.043	-	-	-
1.6291	25200	0.042	-	-	-
1.6355	25300	0.0427	-	-	-
1.6420	25400	0.0425	-	-	-
1.6485	25500	0.0422	-	-	-
1.6549	25600	0.0428	-	-	-
1.6614	25700	0.0423	-	-	-
1.6679	25800	0.0422	-	-	-
1.6743	25900	0.0425	-	-	-
1.6808	26000	0.0424	-	-	-
1.6872	26100	0.0426	-	-	-
1.6937	26200	0.0422	-	-	-
1.7002	26300	0.0419	-	-	-
1.7066	26400	0.0416	-	-	-
1.7131	26500	0.0421	-	-	-
1.7196	26600	0.0416	-	-	-
1.7260	26700	0.0422	-	-	-
1.7325	26800	0.0418	-	-	-
1.7390	26900	0.0425	-	-	-
1.7454	27000	0.0421	-	-	-
1.7519	27100	0.0421	-	-	-
1.7584	27200	0.0418	-	-	-
1.7648	27300	0.042	-	-	-
1.7713	27400	0.0419	-	-	-
1.7777	27500	0.0423	-	-	-
1.7842	27600	0.0415	-	-	-
1.7907	27700	0.0413	-	-	-
1.7971	27800	0.0423	-	-	-
1.8036	27900	0.0413	-	-	-
1.8101	28000	0.0414	-	-	-
1.8165	28100	0.0418	-	-	-
1.8230	28200	0.0414	-	-	-
1.8295	28300	0.0411	-	-	-
1.8359	28400	0.0418	-	-	-
1.8424	28500	0.0416	-	-	-
1.8489	28600	0.0417	-	-	-
1.8553	28700	0.041	-	-	-
1.8618	28800	0.0413	-	-	-
1.8683	28900	0.0409	-	-	-
1.8747	29000	0.0413	-	-	-
1.8812	29100	0.0413	-	-	-
1.8876	29200	0.0411	-	-	-
1.8941	29300	0.0408	-	-	-
1.9006	29400	0.0415	-	-	-
1.9070	29500	0.0415	-	-	-
1.9135	29600	0.0408	-	-	-
1.9200	29700	0.0407	-	-	-
1.9264	29800	0.0409	-	-	-
1.9329	29900	0.0414	-	-	-
1.9394	30000	0.0409	-	-	-
1.9458	30100	0.0407	-	-	-
1.9523	30200	0.0404	-	-	-
1.9588	30300	0.0408	-	-	-
1.9652	30400	0.0409	-	-	-
1.9717	30500	0.0409	-	-	-
1.9781	30600	0.0408	-	-	-
1.9846	30700	0.0403	-	-	-
1.9911	30800	0.0403	-	-	-
1.9975	30900	0.0405	-	-	-
2.0	30938	-	0.0394	-4.1528	0.9835
2.0040	31000	0.0407	-	-	-
2.0105	31100	0.0403	-	-	-
2.0169	31200	0.0401	-	-	-
2.0234	31300	0.0404	-	-	-
2.0299	31400	0.0406	-	-	-
2.0363	31500	0.0408	-	-	-
2.0428	31600	0.0402	-	-	-
2.0493	31700	0.0402	-	-	-
2.0557	31800	0.0398	-	-	-
2.0622	31900	0.0403	-	-	-
2.0687	32000	0.0401	-	-	-
2.0751	32100	0.0405	-	-	-
2.0816	32200	0.0401	-	-	-
2.0880	32300	0.04	-	-	-
2.0945	32400	0.0399	-	-	-
2.1010	32500	0.0398	-	-	-
2.1074	32600	0.0406	-	-	-
2.1139	32700	0.0397	-	-	-
2.1204	32800	0.0403	-	-	-
2.1268	32900	0.0399	-	-	-
2.1333	33000	0.0401	-	-	-
2.1398	33100	0.0401	-	-	-
2.1462	33200	0.0403	-	-	-
2.1527	33300	0.0399	-	-	-
2.1592	33400	0.0398	-	-	-
2.1656	33500	0.0399	-	-	-
2.1721	33600	0.0398	-	-	-
2.1786	33700	0.0395	-	-	-
2.1850	33800	0.0395	-	-	-
2.1915	33900	0.0396	-	-	-
2.1979	34000	0.0399	-	-	-
2.2044	34100	0.0398	-	-	-
2.2109	34200	0.0393	-	-	-
2.2173	34300	0.0393	-	-	-
2.2238	34400	0.0399	-	-	-
2.2303	34500	0.0393	-	-	-
2.2367	34600	0.0398	-	-	-
2.2432	34700	0.0394	-	-	-
2.2497	34800	0.0392	-	-	-
2.2561	34900	0.0397	-	-	-
2.2626	35000	0.0399	-	-	-
2.2691	35100	0.0393	-	-	-
2.2755	35200	0.0394	-	-	-
2.2820	35300	0.0389	-	-	-
2.2884	35400	0.0392	-	-	-
2.2949	35500	0.0393	-	-	-
2.3014	35600	0.0393	-	-	-
2.3078	35700	0.0393	-	-	-
2.3143	35800	0.0391	-	-	-
2.3208	35900	0.0389	-	-	-
2.3272	36000	0.0398	-	-	-
2.3337	36100	0.0394	-	-	-
2.3402	36200	0.0389	-	-	-
2.3466	36300	0.0388	-	-	-
2.3531	36400	0.0392	-	-	-
2.3596	36500	0.0386	-	-	-
2.3660	36600	0.039	-	-	-
2.3725	36700	0.0387	-	-	-
2.3790	36800	0.0391	-	-	-
2.3854	36900	0.0389	-	-	-
2.3919	37000	0.0389	-	-	-
2.3983	37100	0.0387	-	-	-
2.4048	37200	0.0388	-	-	-
2.4113	37300	0.0387	-	-	-
2.4177	37400	0.0391	-	-	-
2.4242	37500	0.039	-	-	-
2.4307	37600	0.0384	-	-	-
2.4371	37700	0.0388	-	-	-
2.4436	37800	0.0385	-	-	-
2.4501	37900	0.0388	-	-	-
2.4565	38000	0.039	-	-	-
2.4630	38100	0.0387	-	-	-
2.4695	38200	0.0382	-	-	-
2.4759	38300	0.0384	-	-	-
2.4824	38400	0.0388	-	-	-
2.4888	38500	0.0381	-	-	-
2.4953	38600	0.0384	-	-	-
2.5018	38700	0.0384	-	-	-
2.5082	38800	0.0383	-	-	-
2.5147	38900	0.0382	-	-	-
2.5212	39000	0.0381	-	-	-
2.5276	39100	0.0382	-	-	-
2.5341	39200	0.0384	-	-	-
2.5406	39300	0.0387	-	-	-
2.5470	39400	0.0384	-	-	-
2.5535	39500	0.0381	-	-	-
2.5600	39600	0.038	-	-	-
2.5664	39700	0.0384	-	-	-
2.5729	39800	0.0379	-	-	-
2.5794	39900	0.0385	-	-	-
2.5858	40000	0.0381	-	-	-
2.5923	40100	0.0382	-	-	-
2.5987	40200	0.0377	-	-	-
2.6052	40300	0.0375	-	-	-
2.6117	40400	0.038	-	-	-
2.6181	40500	0.0384	-	-	-
2.6246	40600	0.0378	-	-	-
2.6311	40700	0.0379	-	-	-
2.6375	40800	0.0376	-	-	-
2.6440	40900	0.0378	-	-	-
2.6505	41000	0.0376	-	-	-
2.6569	41100	0.0381	-	-	-
2.6634	41200	0.0374	-	-	-
2.6699	41300	0.0377	-	-	-
2.6763	41400	0.038	-	-	-
2.6828	41500	0.0377	-	-	-
2.6892	41600	0.0379	-	-	-
2.6957	41700	0.0377	-	-	-
2.7022	41800	0.0373	-	-	-
2.7086	41900	0.0374	-	-	-
2.7151	42000	0.0373	-	-	-
2.7216	42100	0.0374	-	-	-
2.7280	42200	0.0375	-	-	-
2.7345	42300	0.0375	-	-	-
2.7410	42400	0.0379	-	-	-
2.7474	42500	0.0379	-	-	-
2.7539	42600	0.0378	-	-	-
2.7604	42700	0.0375	-	-	-
2.7668	42800	0.0375	-	-	-
2.7733	42900	0.0377	-	-	-
2.7798	43000	0.0378	-	-	-
2.7862	43100	0.0372	-	-	-
2.7927	43200	0.0374	-	-	-
2.7991	43300	0.0376	-	-	-
2.8056	43400	0.0374	-	-	-
2.8121	43500	0.0371	-	-	-
2.8185	43600	0.0377	-	-	-
2.8250	43700	0.0368	-	-	-
2.8315	43800	0.0376	-	-	-
2.8379	43900	0.0374	-	-	-
2.8444	44000	0.0378	-	-	-
2.8509	44100	0.0375	-	-	-
2.8573	44200	0.0371	-	-	-
2.8638	44300	0.037	-	-	-
2.8703	44400	0.0371	-	-	-
2.8767	44500	0.0374	-	-	-
2.8832	44600	0.037	-	-	-
2.8897	44700	0.0374	-	-	-
2.8961	44800	0.0368	-	-	-
2.9026	44900	0.0377	-	-	-
2.9090	45000	0.0375	-	-	-
2.9155	45100	0.0367	-	-	-
2.9220	45200	0.0368	-	-	-
2.9284	45300	0.0372	-	-	-
2.9349	45400	0.0374	-	-	-
2.9414	45500	0.0367	-	-	-
2.9478	45600	0.037	-	-	-
2.9543	45700	0.0368	-	-	-
2.9608	45800	0.0367	-	-	-
2.9672	45900	0.0372	-	-	-
2.9737	46000	0.0375	-	-	-
2.9802	46100	0.0368	-	-	-
2.9866	46200	0.0368	-	-	-
2.9931	46300	0.0367	-	-	-
2.9995	46400	0.0366	-	-	-
3.0	46407	-	0.0357	-3.7998	0.9869
3.0060	46500	0.0372	-	-	-
3.0125	46600	0.0365	-	-	-
3.0189	46700	0.0369	-	-	-
3.0254	46800	0.0368	-	-	-
3.0319	46900	0.037	-	-	-
3.0383	47000	0.037	-	-	-
3.0448	47100	0.0367	-	-	-
3.0513	47200	0.0364	-	-	-
3.0577	47300	0.0366	-	-	-
3.0642	47400	0.0366	-	-	-
3.0707	47500	0.0371	-	-	-
3.0771	47600	0.0367	-	-	-
3.0836	47700	0.0368	-	-	-
3.0901	47800	0.0366	-	-	-
3.0965	47900	0.0362	-	-	-
3.1030	48000	0.0368	-	-	-
3.1094	48100	0.0366	-	-	-
3.1159	48200	0.0367	-	-	-
3.1224	48300	0.0369	-	-	-
3.1288	48400	0.0366	-	-	-
3.1353	48500	0.0366	-	-	-
3.1418	48600	0.0367	-	-	-
3.1482	48700	0.037	-	-	-
3.1547	48800	0.0367	-	-	-
3.1612	48900	0.0362	-	-	-
3.1676	49000	0.0367	-	-	-
3.1741	49100	0.0365	-	-	-
3.1806	49200	0.0363	-	-	-
3.1870	49300	0.036	-	-	-
3.1935	49400	0.0366	-	-	-
3.1999	49500	0.0366	-	-	-
3.2064	49600	0.0366	-	-	-
3.2129	49700	0.0361	-	-	-
3.2193	49800	0.0365	-	-	-
3.2258	49900	0.0365	-	-	-
3.2323	50000	0.0361	-	-	-
3.2387	50100	0.0365	-	-	-
3.2452	50200	0.0363	-	-	-
3.2517	50300	0.0362	-	-	-
3.2581	50400	0.0366	-	-	-
3.2646	50500	0.0366	-	-	-
3.2711	50600	0.0367	-	-	-
3.2775	50700	0.0361	-	-	-
3.2840	50800	0.0359	-	-	-
3.2905	50900	0.0363	-	-	-
3.2969	51000	0.0361	-	-	-
3.3034	51100	0.0364	-	-	-
3.3098	51200	0.0363	-	-	-
3.3163	51300	0.0362	-	-	-
3.3228	51400	0.0359	-	-	-
3.3292	51500	0.0368	-	-	-
3.3357	51600	0.0361	-	-	-
3.3422	51700	0.0359	-	-	-
3.3486	51800	0.0362	-	-	-
3.3551	51900	0.0363	-	-	-
3.3616	52000	0.0357	-	-	-
3.3680	52100	0.0358	-	-	-
3.3745	52200	0.036	-	-	-
3.3810	52300	0.0365	-	-	-
3.3874	52400	0.0359	-	-	-
3.3939	52500	0.0359	-	-	-
3.4003	52600	0.0362	-	-	-
3.4068	52700	0.0358	-	-	-
3.4133	52800	0.036	-	-	-
3.4197	52900	0.0366	-	-	-
3.4262	53000	0.036	-	-	-
3.4327	53100	0.0357	-	-	-
3.4391	53200	0.036	-	-	-
3.4456	53300	0.036	-	-	-
3.4521	53400	0.036	-	-	-
3.4585	53500	0.0364	-	-	-
3.4650	53600	0.0359	-	-	-
3.4715	53700	0.0354	-	-	-
3.4779	53800	0.0359	-	-	-
3.4844	53900	0.036	-	-	-
3.4909	54000	0.0355	-	-	-
3.4973	54100	0.0358	-	-	-
3.5038	54200	0.0355	-	-	-
3.5102	54300	0.036	-	-	-
3.5167	54400	0.0354	-	-	-
3.5232	54500	0.0357	-	-	-
3.5296	54600	0.0356	-	-	-
3.5361	54700	0.036	-	-	-
3.5426	54800	0.036	-	-	-
3.5490	54900	0.0358	-	-	-
3.5555	55000	0.0356	-	-	-
3.5620	55100	0.0357	-	-	-
3.5684	55200	0.0356	-	-	-
3.5749	55300	0.0358	-	-	-
3.5814	55400	0.036	-	-	-
3.5878	55500	0.0356	-	-	-
3.5943	55600	0.0358	-	-	-
3.6007	55700	0.0351	-	-	-
3.6072	55800	0.0352	-	-	-
3.6137	55900	0.0357	-	-	-
3.6201	56000	0.0359	-	-	-
3.6266	56100	0.035	-	-	-
3.6331	56200	0.0357	-	-	-
3.6395	56300	0.0354	-	-	-
3.6460	56400	0.0352	-	-	-
3.6525	56500	0.0356	-	-	-
3.6589	56600	0.0356	-	-	-
3.6654	56700	0.0349	-	-	-
3.6719	56800	0.0358	-	-	-
3.6783	56900	0.0355	-	-	-
3.6848	57000	0.0353	-	-	-
3.6913	57100	0.0355	-	-	-
3.6977	57200	0.0353	-	-	-
3.7042	57300	0.035	-	-	-
3.7106	57400	0.0351	-	-	-
3.7171	57500	0.035	-	-	-
3.7236	57600	0.0353	-	-	-
3.7300	57700	0.0353	-	-	-
3.7365	57800	0.0356	-	-	-
3.7430	57900	0.0356	-	-	-
3.7494	58000	0.0355	-	-	-
3.7559	58100	0.0355	-	-	-
3.7624	58200	0.0354	-	-	-
3.7688	58300	0.0353	-	-	-
3.7753	58400	0.0357	-	-	-
3.7818	58500	0.0353	-	-	-
3.7882	58600	0.035	-	-	-
3.7947	58700	0.0355	-	-	-
3.8012	58800	0.035	-	-	-
3.8076	58900	0.0355	-	-	-
3.8141	59000	0.0351	-	-	-
3.8205	59100	0.0353	-	-	-
3.8270	59200	0.0349	-	-	-
3.8335	59300	0.0355	-	-	-
3.8399	59400	0.0353	-	-	-
3.8464	59500	0.0357	-	-	-
3.8529	59600	0.0351	-	-	-
3.8593	59700	0.0351	-	-	-
3.8658	59800	0.0352	-	-	-
3.8723	59900	0.035	-	-	-
3.8787	60000	0.0353	-	-	-
3.8852	60100	0.0351	-	-	-
3.8917	60200	0.0352	-	-	-
3.8981	60300	0.0351	-	-	-
3.9046	60400	0.0356	-	-	-
3.9110	60500	0.0352	-	-	-
3.9175	60600	0.0347	-	-	-
3.9240	60700	0.035	-	-	-
3.9304	60800	0.0352	-	-	-
3.9369	60900	0.0356	-	-	-
3.9434	61000	0.0346	-	-	-
3.9498	61100	0.0352	-	-	-
3.9563	61200	0.0349	-	-	-
3.9628	61300	0.0349	-	-	-
3.9692	61400	0.0354	-	-	-
3.9757	61500	0.0354	-	-	-
3.9822	61600	0.0348	-	-	-
3.9886	61700	0.0349	-	-	-
3.9951	61800	0.0347	-	-	-
4.0	61876	-	0.0339	-3.6284	0.9876
4.0016	61900	0.0351	-	-	-
4.0080	62000	0.035	-	-	-
4.0145	62100	0.0348	-	-	-
4.0209	62200	0.0349	-	-	-
4.0274	62300	0.0352	-	-	-
4.0339	62400	0.0351	-	-	-
4.0403	62500	0.0352	-	-	-
4.0468	62600	0.0347	-	-	-
4.0533	62700	0.0347	-	-	-
4.0597	62800	0.0348	-	-	-
4.0662	62900	0.035	-	-	-
4.0727	63000	0.035	-	-	-
4.0791	63100	0.0349	-	-	-
4.0856	63200	0.035	-	-	-
4.0921	63300	0.0349	-	-	-
4.0985	63400	0.0346	-	-	-
4.1050	63500	0.035	-	-	-
4.1114	63600	0.0347	-	-	-
4.1179	63700	0.0351	-	-	-
4.1244	63800	0.0351	-	-	-
4.1308	63900	0.035	-	-	-
4.1373	64000	0.0349	-	-	-
4.1438	64100	0.0352	-	-	-
4.1502	64200	0.0351	-	-	-
4.1567	64300	0.0348	-	-	-
4.1632	64400	0.0347	-	-	-
4.1696	64500	0.0352	-	-	-
4.1761	64600	0.0346	-	-	-
4.1826	64700	0.0345	-	-	-
4.1890	64800	0.0346	-	-	-
4.1955	64900	0.0351	-	-	-
4.2020	65000	0.0348	-	-	-
4.2084	65100	0.035	-	-	-
4.2149	65200	0.0345	-	-	-
4.2213	65300	0.0349	-	-	-
4.2278	65400	0.0351	-	-	-
4.2343	65500	0.0345	-	-	-
4.2407	65600	0.035	-	-	-
4.2472	65700	0.0346	-	-	-
4.2537	65800	0.0347	-	-	-
4.2601	65900	0.0351	-	-	-
4.2666	66000	0.0347	-	-	-
4.2731	66100	0.0354	-	-	-
4.2795	66200	0.0342	-	-	-
4.2860	66300	0.0345	-	-	-
4.2925	66400	0.0349	-	-	-
4.2989	66500	0.0347	-	-	-
4.3054	66600	0.0347	-	-	-
4.3118	66700	0.0348	-	-	-
4.3183	66800	0.0347	-	-	-
4.3248	66900	0.0346	-	-	-
4.3312	67000	0.0353	-	-	-
4.3377	67100	0.0345	-	-	-
4.3442	67200	0.0343	-	-	-
4.3506	67300	0.035	-	-	-
4.3571	67400	0.0346	-	-	-
4.3636	67500	0.0343	-	-	-
4.3700	67600	0.0344	-	-	-
4.3765	67700	0.0348	-	-	-
4.3830	67800	0.0348	-	-	-
4.3894	67900	0.0345	-	-	-
4.3959	68000	0.0347	-	-	-
4.4024	68100	0.0345	-	-	-
4.4088	68200	0.0346	-	-	-
4.4153	68300	0.0349	-	-	-
4.4217	68400	0.0349	-	-	-
4.4282	68500	0.0345	-	-	-
4.4347	68600	0.0346	-	-	-
4.4411	68700	0.0345	-	-	-
4.4476	68800	0.0347	-	-	-
4.4541	68900	0.0346	-	-	-
4.4605	69000	0.035	-	-	-
4.4670	69100	0.0343	-	-	-
4.4735	69200	0.0346	-	-	-
4.4799	69300	0.0346	-	-	-
4.4864	69400	0.0346	-	-	-
4.4929	69500	0.0342	-	-	-
4.4993	69600	0.0346	-	-	-
4.5058	69700	0.0342	-	-	-
4.5123	69800	0.0348	-	-	-
4.5187	69900	0.0341	-	-	-
4.5252	70000	0.0344	-	-	-
4.5316	70100	0.0345	-	-	-
4.5381	70200	0.0348	-	-	-
4.5446	70300	0.0349	-	-	-
4.5510	70400	0.0344	-	-	-
4.5575	70500	0.0342	-	-	-
4.5640	70600	0.0346	-	-	-
4.5704	70700	0.0342	-	-	-
4.5769	70800	0.0345	-	-	-
4.5834	70900	0.0347	-	-	-
4.5898	71000	0.0345	-	-	-
4.5963	71100	0.0343	-	-	-
4.6028	71200	0.0341	-	-	-
4.6092	71300	0.0341	-	-	-
4.6157	71400	0.0347	-	-	-
4.6221	71500	0.0347	-	-	-
4.6286	71600	0.0339	-	-	-
4.6351	71700	0.0344	-	-	-
4.6415	71800	0.0342	-	-	-
4.6480	71900	0.0342	-	-	-
4.6545	72000	0.0346	-	-	-
4.6609	72100	0.0342	-	-	-
4.6674	72200	0.0341	-	-	-
4.6739	72300	0.0344	-	-	-
4.6803	72400	0.0345	-	-	-
4.6868	72500	0.0345	-	-	-
4.6933	72600	0.0342	-	-	-
4.6997	72700	0.0341	-	-	-
4.7062	72800	0.034	-	-	-
4.7127	72900	0.0343	-	-	-
4.7191	73000	0.0337	-	-	-
4.7256	73100	0.0343	-	-	-
4.7320	73200	0.0343	-	-	-
4.7385	73300	0.0346	-	-	-
4.7450	73400	0.0346	-	-	-
4.7514	73500	0.0345	-	-	-
4.7579	73600	0.0343	-	-	-
4.7644	73700	0.0344	-	-	-
4.7708	73800	0.0345	-	-	-
4.7773	73900	0.0347	-	-	-
4.7838	74000	0.034	-	-	-
4.7902	74100	0.034	-	-	-
4.7967	74200	0.0348	-	-	-
4.8032	74300	0.0338	-	-	-
4.8096	74400	0.0346	-	-	-
4.8161	74500	0.0344	-	-	-
4.8225	74600	0.0342	-	-	-
4.8290	74700	0.034	-	-	-
4.8355	74800	0.0346	-	-	-
4.8419	74900	0.0346	-	-	-
4.8484	75000	0.0346	-	-	-
4.8549	75100	0.034	-	-	-
4.8613	75200	0.0343	-	-	-
4.8678	75300	0.034	-	-	-
4.8743	75400	0.0344	-	-	-
4.8807	75500	0.0344	-	-	-
4.8872	75600	0.0342	-	-	-
4.8937	75700	0.0341	-	-	-
4.9001	75800	0.0345	-	-	-
4.9066	75900	0.0347	-	-	-
4.9131	76000	0.0341	-	-	-
4.9195	76100	0.0339	-	-	-
4.9260	76200	0.0343	-	-	-
4.9324	76300	0.0346	-	-	-
4.9389	76400	0.0344	-	-	-
4.9454	76500	0.0341	-	-	-
4.9518	76600	0.034	-	-	-
4.9583	76700	0.0342	-	-	-
4.9648	76800	0.0344	-	-	-
4.9712	76900	0.0344	-	-	-
4.9777	77000	0.0343	-	-	-
4.9842	77100	0.0341	-	-	-
4.9906	77200	0.0341	-	-	-
4.9971	77300	0.0342	-	-	-
5.0	77345	-	0.0331	-3.5554	0.9877

Framework Versions

• Python: 3.11.9
• Sentence Transformers: 3.3.1
• Transformers: 4.46.3
• PyTorch: 2.4.0
• 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",
}

MSELoss

@inproceedings{reimers-2020-multilingual-sentence-bert,
    title = "Making Monolingual Sentence Embeddings Multilingual using Knowledge Distillation",
    author = "Reimers, Nils and Gurevych, Iryna",
    booktitle = "Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing",
    month = "11",
    year = "2020",
    publisher = "Association for Computational Linguistics",
    url = "https://arxiv.org/abs/2004.09813",
}