nafis277/domain-mpnet-normalized

SentenceTransformer based on sentence-transformers/all-mpnet-base-v2

This is a sentence-transformers model finetuned from sentence-transformers/all-mpnet-base-v2. 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: sentence-transformers/all-mpnet-base-v2
• Maximum Sequence Length: 384 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': 384, 'do_lower_case': False, 'architecture': 'MPNetModel'})
  (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): 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("sentence_transformers_model_id")
# Run inference
sentences = [
    'ABC Plumbing has the following current assets and liabilities: Cash, $7,300; Marketable Securities, $14,200, Accounts Receivable, $2,120; Notes Payable, $1,400; Accounts Payable, $1,850. Find the acid-test ratio for ABC, correct to the nearest hundredth.',
    'What is the net price of a calculator list-priced at $100.00 and discounted at 40% and 25%?',
    'InBrowningtown, water is sold to home owners by the cubic foot at the rate of $15.31 for up to and including 3,600 cubic feet, and $.15 for each 100 cubic feet over 3,600 cubic feet. Local taxes on water usage are 4%. If the Thomas family recently received a bill for 35,700 cubic feet of water, how much were they charged?',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 768]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities)
# tensor([[1.0000, 0.9725, 0.9790],
#         [0.9725, 1.0000, 0.9825],
#         [0.9790, 0.9825, 1.0001]])

Evaluation

Metrics

Binary Classification

• Dataset: domain-val
• Evaluated with BinaryClassificationEvaluator

Metric	Value
cosine_accuracy	0.9137
cosine_accuracy_threshold	0.6192
cosine_f1	0.9119
cosine_f1_threshold	0.5619
cosine_precision	0.9184
cosine_recall	0.9056
cosine_ap	0.9694
cosine_mcc	0.8252

Training Details

Training Dataset

Unnamed Dataset

• Size: 30,705 training samples
• Columns: anchor and positive
• Approximate statistics based on the first 1000 samples:

  	anchor	positive
  type	string	string
  details	min: 7 tokens mean: 57.59 tokens max: 282 tokens	min: 7 tokens mean: 57.45 tokens max: 282 tokens

• Samples:

  anchor	positive
  A furniture manufacturer wants to find out how many end tables he produced during a certain week. He knows that 8 employees produced 16 end tables each, 21 employees produced 23 each, 7 produced 27 each, and 4 produced 29 each, Find the total number of end 'tables produced during that week.	What does PEST stand for?
  A furniture manufacturer wants to find out how many end tables he produced during a certain week. He knows that 8 employees produced 16 end tables each, 21 employees produced 23 each, 7 produced 27 each, and 4 produced 29 each, Find the total number of end 'tables produced during that week.	On August 4, a store purchased five sofas invoiced at $7,000, terms 2/10 , n/30 . The invoice was paid August 13. The store paid
  A furniture manufacturer wants to find out how many end tables he produced during a certain week. He knows that 8 employees produced 16 end tables each, 21 employees produced 23 each, 7 produced 27 each, and 4 produced 29 each, Find the total number of end 'tables produced during that week.	$ .01(1/4) a share for stocks under $5 a share par value $ .02(1/2) a share for stocks from $5-$10 a share par value $ .03(3/4) a share for stocks from $10-$20 a share par value $ .05 a share for stocks over $20 a share par value Mr. Carr sold 300 shares of stock having a par value of $50 per share. What was the New York State transfer tax?

• Loss: domain_encoder_ft.losses.NormalizedMultipleNegativesRankingLoss

Training Hyperparameters

Non-Default Hyperparameters

• per_device_train_batch_size: 24
• num_train_epochs: 10
• learning_rate: 2e-05
• warmup_steps: 0.1
• weight_decay: 0.01
• bf16: True
• eval_strategy: epoch
• load_best_model_at_end: True

All Hyperparameters

Click to expand

• per_device_train_batch_size: 24
• num_train_epochs: 10
• max_steps: -1
• learning_rate: 2e-05
• lr_scheduler_type: linear
• lr_scheduler_kwargs: None
• warmup_steps: 0.1
• optim: adamw_torch_fused
• optim_args: None
• weight_decay: 0.01
• adam_beta1: 0.9
• adam_beta2: 0.999
• adam_epsilon: 1e-08
• optim_target_modules: None
• gradient_accumulation_steps: 1
• average_tokens_across_devices: True
• max_grad_norm: 1.0
• label_smoothing_factor: 0.0
• bf16: True
• fp16: False
• bf16_full_eval: False
• fp16_full_eval: False
• tf32: None
• gradient_checkpointing: False
• gradient_checkpointing_kwargs: None
• torch_compile: False
• torch_compile_backend: None
• torch_compile_mode: None
• use_liger_kernel: False
• liger_kernel_config: None
• use_cache: False
• neftune_noise_alpha: None
• torch_empty_cache_steps: None
• auto_find_batch_size: False
• log_on_each_node: True
• logging_nan_inf_filter: True
• include_num_input_tokens_seen: no
• log_level: passive
• log_level_replica: warning
• disable_tqdm: False
• project: huggingface
• trackio_space_id: trackio
• eval_strategy: epoch
• per_device_eval_batch_size: 8
• prediction_loss_only: True
• eval_on_start: False
• eval_do_concat_batches: True
• eval_use_gather_object: False
• eval_accumulation_steps: None
• include_for_metrics: []
• batch_eval_metrics: False
• save_only_model: False
• save_on_each_node: False
• enable_jit_checkpoint: False
• push_to_hub: False
• hub_private_repo: None
• hub_model_id: None
• hub_strategy: every_save
• hub_always_push: False
• hub_revision: None
• load_best_model_at_end: True
• ignore_data_skip: False
• restore_callback_states_from_checkpoint: False
• full_determinism: False
• seed: 42
• data_seed: None
• use_cpu: False
• 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
• dataloader_drop_last: False
• dataloader_num_workers: 0
• dataloader_pin_memory: True
• dataloader_persistent_workers: False
• dataloader_prefetch_factor: None
• remove_unused_columns: True
• label_names: None
• train_sampling_strategy: random
• length_column_name: length
• ddp_find_unused_parameters: None
• ddp_bucket_cap_mb: None
• ddp_broadcast_buffers: False
• ddp_backend: None
• ddp_timeout: 1800
• fsdp: []
• fsdp_config: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
• deepspeed: None
• debug: []
• skip_memory_metrics: True
• do_predict: False
• resume_from_checkpoint: None
• warmup_ratio: None
• local_rank: -1
• prompts: None
• batch_sampler: batch_sampler
• multi_dataset_batch_sampler: proportional
• router_mapping: {}
• learning_rate_mapping: {}

Training Logs

Click to expand

Epoch	Step	Training Loss	domain-val_cosine_ap
0.0156	20	1.2836	-
0.0312	40	1.1540	-
0.0469	60	1.1903	-
0.0625	80	1.1989	-
0.0781	100	1.2550	-
0.0938	120	1.1286	-
0.1094	140	1.1315	-
0.125	160	1.0759	-
0.1406	180	0.8953	-
0.1562	200	0.8962	-
0.1719	220	0.8871	-
0.1875	240	0.8370	-
0.2031	260	0.8041	-
0.2188	280	0.6277	-
0.2344	300	0.6101	-
0.25	320	0.5950	-
0.2656	340	0.5216	-
0.2812	360	0.4675	-
0.2969	380	0.4305	-
0.3125	400	0.4532	-
0.3281	420	0.3666	-
0.3438	440	0.3723	-
0.3594	460	0.3453	-
0.375	480	0.3500	-
0.3906	500	0.3192	-
0.4062	520	0.3321	-
0.4219	540	0.3488	-
0.4375	560	0.3250	-
0.4531	580	0.3098	-
0.4688	600	0.3055	-
0.4844	620	0.2813	-
0.5	640	0.2846	-
0.5156	660	0.2823	-
0.5312	680	0.2812	-
0.5469	700	0.2627	-
0.5625	720	0.2721	-
0.5781	740	0.2726	-
0.5938	760	0.2653	-
0.6094	780	0.2627	-
0.625	800	0.2451	-
0.6406	820	0.2637	-
0.6562	840	0.2668	-
0.6719	860	0.2378	-
0.6875	880	0.2364	-
0.7031	900	0.2344	-
0.7188	920	0.2188	-
0.7344	940	0.2302	-
0.75	960	0.2237	-
0.7656	980	0.2228	-
0.7812	1000	0.2042	-
0.7969	1020	0.2001	-
0.8125	1040	0.2066	-
0.8281	1060	0.1777	-
0.8438	1080	0.2129	-
0.8594	1100	0.2227	-
0.875	1120	0.2038	-
0.8906	1140	0.2077	-
0.9062	1160	0.1987	-
0.9219	1180	0.2186	-
0.9375	1200	0.1873	-
0.9531	1220	0.1997	-
0.9688	1240	0.1670	-
0.9844	1260	0.1695	-
1.0	1280	0.1889	0.9535
1.0156	1300	0.1660	-
1.0312	1320	0.1624	-
1.0469	1340	0.1670	-
1.0625	1360	0.1693	-
1.0781	1380	0.1527	-
1.0938	1400	0.1505	-
1.1094	1420	0.1529	-
1.125	1440	0.1662	-
1.1406	1460	0.1521	-
1.1562	1480	0.1396	-
1.1719	1500	0.1603	-
1.1875	1520	0.1616	-
1.2031	1540	0.1438	-
1.2188	1560	0.1542	-
1.2344	1580	0.1377	-
1.25	1600	0.1512	-
1.2656	1620	0.1412	-
1.2812	1640	0.1661	-
1.2969	1660	0.1277	-
1.3125	1680	0.1344	-
1.3281	1700	0.1305	-
1.3438	1720	0.1464	-
1.3594	1740	0.1237	-
1.375	1760	0.1513	-
1.3906	1780	0.1355	-
1.4062	1800	0.1259	-
1.4219	1820	0.1200	-
1.4375	1840	0.1434	-
1.4531	1860	0.1437	-
1.4688	1880	0.1253	-
1.4844	1900	0.1275	-
1.5	1920	0.1237	-
1.5156	1940	0.1372	-
1.5312	1960	0.1231	-
1.5469	1980	0.1077	-
1.5625	2000	0.1132	-
1.5781	2020	0.1202	-
1.5938	2040	0.1175	-
1.6094	2060	0.1118	-
1.625	2080	0.1219	-
1.6406	2100	0.1097	-
1.6562	2120	0.1215	-
1.6719	2140	0.1302	-
1.6875	2160	0.1175	-
1.7031	2180	0.1097	-
1.7188	2200	0.1091	-
1.7344	2220	0.1104	-
1.75	2240	0.1237	-
1.7656	2260	0.1253	-
1.7812	2280	0.1115	-
1.7969	2300	0.1119	-
1.8125	2320	0.1089	-
1.8281	2340	0.1244	-
1.8438	2360	0.1030	-
1.8594	2380	0.1119	-
1.875	2400	0.1110	-
1.8906	2420	0.1033	-
1.9062	2440	0.1165	-
1.9219	2460	0.0986	-
1.9375	2480	0.0967	-
1.9531	2500	0.1081	-
1.9688	2520	0.1139	-
1.9844	2540	0.1129	-
2.0	2560	0.0945	0.9688
2.0156	2580	0.0917	-
2.0312	2600	0.0804	-
2.0469	2620	0.0901	-
2.0625	2640	0.0936	-
2.0781	2660	0.0944	-
2.0938	2680	0.1014	-
2.1094	2700	0.0986	-
2.125	2720	0.0926	-
2.1406	2740	0.0985	-
2.1562	2760	0.0919	-
2.1719	2780	0.0908	-
2.1875	2800	0.0810	-
2.2031	2820	0.0926	-
2.2188	2840	0.0872	-
2.2344	2860	0.0989	-
2.25	2880	0.0883	-
2.2656	2900	0.0885	-
2.2812	2920	0.1092	-
2.2969	2940	0.0962	-
2.3125	2960	0.0913	-
2.3281	2980	0.0825	-
2.3438	3000	0.0953	-
2.3594	3020	0.0869	-
2.375	3040	0.0896	-
2.3906	3060	0.0895	-
2.4062	3080	0.0934	-
2.4219	3100	0.0888	-
2.4375	3120	0.0929	-
2.4531	3140	0.0882	-
2.4688	3160	0.0907	-
2.4844	3180	0.0858	-
2.5	3200	0.0856	-
2.5156	3220	0.0851	-
2.5312	3240	0.0792	-
2.5469	3260	0.0934	-
2.5625	3280	0.0916	-
2.5781	3300	0.0864	-
2.5938	3320	0.0874	-
2.6094	3340	0.0995	-
2.625	3360	0.0810	-
2.6406	3380	0.0889	-
2.6562	3400	0.0805	-
2.6719	3420	0.0898	-
2.6875	3440	0.0861	-
2.7031	3460	0.0938	-
2.7188	3480	0.0729	-
2.7344	3500	0.0881	-
2.75	3520	0.0828	-
2.7656	3540	0.0887	-
2.7812	3560	0.0795	-
2.7969	3580	0.0870	-
2.8125	3600	0.0866	-
2.8281	3620	0.0896	-
2.8438	3640	0.0779	-
2.8594	3660	0.0867	-
2.875	3680	0.0842	-
2.8906	3700	0.0878	-
2.9062	3720	0.0821	-
2.9219	3740	0.0675	-
2.9375	3760	0.0857	-
2.9531	3780	0.0862	-
2.9688	3800	0.0822	-
2.9844	3820	0.0866	-
3.0	3840	0.0776	0.9674
3.0156	3860	0.0857	-
3.0312	3880	0.0765	-
3.0469	3900	0.0799	-
3.0625	3920	0.0807	-
3.0781	3940	0.0838	-
3.0938	3960	0.0824	-
3.1094	3980	0.0691	-
3.125	4000	0.0819	-
3.1406	4020	0.0871	-
3.1562	4040	0.0880	-
3.1719	4060	0.0823	-
3.1875	4080	0.0762	-
3.2031	4100	0.0776	-
3.2188	4120	0.0794	-
3.2344	4140	0.0877	-
3.25	4160	0.0934	-
3.2656	4180	0.0766	-
3.2812	4200	0.0797	-
3.2969	4220	0.0728	-
3.3125	4240	0.0801	-
3.3281	4260	0.0744	-
3.3438	4280	0.0746	-
3.3594	4300	0.0805	-
3.375	4320	0.0857	-
3.3906	4340	0.0924	-
3.4062	4360	0.0803	-
3.4219	4380	0.0752	-
3.4375	4400	0.0750	-
3.4531	4420	0.0753	-
3.4688	4440	0.0986	-
3.4844	4460	0.0820	-
3.5	4480	0.0830	-
3.5156	4500	0.0831	-
3.5312	4520	0.0774	-
3.5469	4540	0.1006	-
3.5625	4560	0.0771	-
3.5781	4580	0.0764	-
3.5938	4600	0.0843	-
3.6094	4620	0.0718	-
3.625	4640	0.0882	-
3.6406	4660	0.0869	-
3.6562	4680	0.0776	-
3.6719	4700	0.0829	-
3.6875	4720	0.0755	-
3.7031	4740	0.0882	-
3.7188	4760	0.0801	-
3.7344	4780	0.0935	-
3.75	4800	0.0873	-
3.7656	4820	0.0751	-
3.7812	4840	0.0793	-
3.7969	4860	0.0781	-
3.8125	4880	0.0793	-
3.8281	4900	0.0821	-
3.8438	4920	0.0920	-
3.8594	4940	0.0701	-
3.875	4960	0.0851	-
3.8906	4980	0.0785	-
3.9062	5000	0.0839	-
3.9219	5020	0.0700	-
3.9375	5040	0.0794	-
3.9531	5060	0.0820	-
3.9688	5080	0.0777	-
3.9844	5100	0.0834	-
4.0	5120	0.0911	0.9693
4.0156	5140	0.0833	-
4.0312	5160	0.0807	-
4.0469	5180	0.0748	-
4.0625	5200	0.0818	-
4.0781	5220	0.0793	-
4.0938	5240	0.0879	-
4.1094	5260	0.0825	-
4.125	5280	0.0786	-
4.1406	5300	0.0852	-
4.1562	5320	0.0813	-
4.1719	5340	0.0854	-
4.1875	5360	0.0886	-
4.2031	5380	0.0753	-
4.2188	5400	0.0743	-
4.2344	5420	0.0816	-
4.25	5440	0.0755	-
4.2656	5460	0.0712	-
4.2812	5480	0.0754	-
4.2969	5500	0.0731	-
4.3125	5520	0.0799	-
4.3281	5540	0.0743	-
4.3438	5560	0.0796	-
4.3594	5580	0.0731	-
4.375	5600	0.0743	-
4.3906	5620	0.0791	-
4.4062	5640	0.0863	-
4.4219	5660	0.0879	-
4.4375	5680	0.0775	-
4.4531	5700	0.0786	-
4.4688	5720	0.0820	-
4.4844	5740	0.0771	-
4.5	5760	0.0863	-
4.5156	5780	0.0870	-
4.5312	5800	0.0761	-
4.5469	5820	0.0837	-
4.5625	5840	0.0826	-
4.5781	5860	0.0721	-
4.5938	5880	0.0812	-
4.6094	5900	0.0693	-
4.625	5920	0.0789	-
4.6406	5940	0.0807	-
4.6562	5960	0.0772	-
4.6719	5980	0.0774	-
4.6875	6000	0.0833	-
4.7031	6020	0.0804	-
4.7188	6040	0.0851	-
4.7344	6060	0.0753	-
4.75	6080	0.0795	-
4.7656	6100	0.0826	-
4.7812	6120	0.0791	-
4.7969	6140	0.0758	-
4.8125	6160	0.0769	-
4.8281	6180	0.0831	-
4.8438	6200	0.0753	-
4.8594	6220	0.0739	-
4.875	6240	0.0777	-
4.8906	6260	0.0796	-
4.9062	6280	0.0786	-
4.9219	6300	0.0841	-
4.9375	6320	0.0838	-
4.9531	6340	0.0737	-
4.9688	6360	0.0844	-
4.9844	6380	0.0752	-
5.0	6400	0.0741	0.9711
5.0156	6420	0.0758	-
5.0312	6440	0.0760	-
5.0469	6460	0.0771	-
5.0625	6480	0.0788	-
5.0781	6500	0.0832	-
5.0938	6520	0.0816	-
5.1094	6540	0.0745	-
5.125	6560	0.0724	-
5.1406	6580	0.0721	-
5.1562	6600	0.0791	-
5.1719	6620	0.0720	-
5.1875	6640	0.0787	-
5.2031	6660	0.0776	-
5.2188	6680	0.0812	-
5.2344	6700	0.0743	-
5.25	6720	0.0806	-
5.2656	6740	0.0798	-
5.2812	6760	0.0729	-
5.2969	6780	0.0740	-
5.3125	6800	0.0882	-
5.3281	6820	0.0737	-
5.3438	6840	0.0734	-
5.3594	6860	0.0809	-
5.375	6880	0.0732	-
5.3906	6900	0.0849	-
5.4062	6920	0.0806	-
5.4219	6940	0.0712	-
5.4375	6960	0.0724	-
5.4531	6980	0.0782	-
5.4688	7000	0.0892	-
5.4844	7020	0.0746	-
5.5	7040	0.0774	-
5.5156	7060	0.0755	-
5.5312	7080	0.0762	-
5.5469	7100	0.0741	-
5.5625	7120	0.0836	-
5.5781	7140	0.0745	-
5.5938	7160	0.0757	-
5.6094	7180	0.0820	-
5.625	7200	0.0802	-
5.6406	7220	0.0767	-
5.6562	7240	0.0722	-
5.6719	7260	0.0861	-
5.6875	7280	0.0744	-
5.7031	7300	0.0785	-
5.7188	7320	0.0867	-
5.7344	7340	0.0781	-
5.75	7360	0.0773	-
5.7656	7380	0.0808	-
5.7812	7400	0.0776	-
5.7969	7420	0.0734	-
5.8125	7440	0.0779	-
5.8281	7460	0.0773	-
5.8438	7480	0.0803	-
5.8594	7500	0.0785	-
5.875	7520	0.0743	-
5.8906	7540	0.0811	-
5.9062	7560	0.0725	-
5.9219	7580	0.0805	-
5.9375	7600	0.0788	-
5.9531	7620	0.0877	-
5.9688	7640	0.0760	-
5.9844	7660	0.0713	-
6.0	7680	0.0784	0.9673
6.0156	7700	0.0771	-
6.0312	7720	0.0724	-
6.0469	7740	0.0753	-
6.0625	7760	0.0763	-
6.0781	7780	0.0757	-
6.0938	7800	0.0772	-
6.1094	7820	0.0716	-
6.125	7840	0.0715	-
6.1406	7860	0.0721	-
6.1562	7880	0.0741	-
6.1719	7900	0.0787	-
6.1875	7920	0.0729	-
6.2031	7940	0.0762	-
6.2188	7960	0.0738	-
6.2344	7980	0.0779	-
6.25	8000	0.0834	-
6.2656	8020	0.0785	-
6.2812	8040	0.0753	-
6.2969	8060	0.0734	-
6.3125	8080	0.0754	-
6.3281	8100	0.0848	-
6.3438	8120	0.0778	-
6.3594	8140	0.0748	-
6.375	8160	0.0696	-
6.3906	8180	0.0717	-
6.4062	8200	0.0768	-
6.4219	8220	0.0731	-
6.4375	8240	0.0744	-
6.4531	8260	0.0748	-
6.4688	8280	0.0729	-
6.4844	8300	0.0794	-
6.5	8320	0.0776	-
6.5156	8340	0.0774	-
6.5312	8360	0.0722	-
6.5469	8380	0.0761	-
6.5625	8400	0.0766	-
6.5781	8420	0.0788	-
6.5938	8440	0.0742	-
6.6094	8460	0.0741	-
6.625	8480	0.0780	-
6.6406	8500	0.0746	-
6.6562	8520	0.0723	-
6.6719	8540	0.0764	-
6.6875	8560	0.0694	-
6.7031	8580	0.0815	-
6.7188	8600	0.0824	-
6.7344	8620	0.0758	-
6.75	8640	0.0742	-
6.7656	8660	0.0779	-
6.7812	8680	0.0743	-
6.7969	8700	0.0746	-
6.8125	8720	0.0755	-
6.8281	8740	0.0688	-
6.8438	8760	0.0843	-
6.8594	8780	0.0801	-
6.875	8800	0.0692	-
6.8906	8820	0.0731	-
6.9062	8840	0.0781	-
6.9219	8860	0.0760	-
6.9375	8880	0.0745	-
6.9531	8900	0.0726	-
6.9688	8920	0.0739	-
6.9844	8940	0.0860	-
7.0	8960	0.0721	0.9697
7.0156	8980	0.0788	-
7.0312	9000	0.0714	-
7.0469	9020	0.0724	-
7.0625	9040	0.0726	-
7.0781	9060	0.0742	-
7.0938	9080	0.0731	-
7.1094	9100	0.0756	-
7.125	9120	0.0766	-
7.1406	9140	0.0730	-
7.1562	9160	0.0761	-
7.1719	9180	0.0705	-
7.1875	9200	0.0692	-
7.2031	9220	0.0707	-
7.2188	9240	0.0776	-
7.2344	9260	0.0765	-
7.25	9280	0.0675	-
7.2656	9300	0.0677	-
7.2812	9320	0.0721	-
7.2969	9340	0.0717	-
7.3125	9360	0.0692	-
7.3281	9380	0.0780	-
7.3438	9400	0.0748	-
7.3594	9420	0.0804	-
7.375	9440	0.0781	-
7.3906	9460	0.0733	-
7.4062	9480	0.0784	-
7.4219	9500	0.0773	-
7.4375	9520	0.0713	-
7.4531	9540	0.0760	-
7.4688	9560	0.0705	-
7.4844	9580	0.0729	-
7.5	9600	0.0708	-
7.5156	9620	0.0788	-
7.5312	9640	0.0734	-
7.5469	9660	0.0768	-
7.5625	9680	0.0716	-
7.5781	9700	0.0730	-
7.5938	9720	0.0744	-
7.6094	9740	0.0677	-
7.625	9760	0.0766	-
7.6406	9780	0.0790	-
7.6562	9800	0.0764	-
7.6719	9820	0.0770	-
7.6875	9840	0.0792	-
7.7031	9860	0.0727	-
7.7188	9880	0.0780	-
7.7344	9900	0.0702	-
7.75	9920	0.0779	-
7.7656	9940	0.0701	-
7.7812	9960	0.0805	-
7.7969	9980	0.0758	-
7.8125	10000	0.0688	-
7.8281	10020	0.0706	-
7.8438	10040	0.0739	-
7.8594	10060	0.0765	-
7.875	10080	0.0721	-
7.8906	10100	0.0803	-
7.9062	10120	0.0714	-
7.9219	10140	0.0758	-
7.9375	10160	0.0708	-
7.9531	10180	0.0748	-
7.9688	10200	0.0795	-
7.9844	10220	0.0695	-
8.0	10240	0.0834	0.9700
8.0156	10260	0.0695	-
8.0312	10280	0.0696	-
8.0469	10300	0.0712	-
8.0625	10320	0.0680	-
8.0781	10340	0.0687	-
8.0938	10360	0.0728	-
8.1094	10380	0.0725	-
8.125	10400	0.0678	-
8.1406	10420	0.0645	-
8.1562	10440	0.0640	-
8.1719	10460	0.0717	-
8.1875	10480	0.0745	-
8.2031	10500	0.0747	-
8.2188	10520	0.0769	-
8.2344	10540	0.0725	-
8.25	10560	0.0720	-
8.2656	10580	0.0685	-
8.2812	10600	0.0742	-
8.2969	10620	0.0670	-
8.3125	10640	0.0692	-
8.3281	10660	0.0736	-
8.3438	10680	0.0722	-
8.3594	10700	0.0642	-
8.375	10720	0.0703	-
8.3906	10740	0.0744	-
8.4062	10760	0.0671	-
8.4219	10780	0.0723	-
8.4375	10800	0.0732	-
8.4531	10820	0.0765	-
8.4688	10840	0.0711	-
8.4844	10860	0.0746	-
8.5	10880	0.0730	-
8.5156	10900	0.0758	-
8.5312	10920	0.0698	-
8.5469	10940	0.0759	-
8.5625	10960	0.0737	-
8.5781	10980	0.0761	-
8.5938	11000	0.0726	-
8.6094	11020	0.0798	-
8.625	11040	0.0722	-
8.6406	11060	0.0721	-
8.6562	11080	0.0777	-
8.6719	11100	0.0719	-
8.6875	11120	0.0747	-
8.7031	11140	0.0700	-
8.7188	11160	0.0741	-
8.7344	11180	0.0731	-
8.75	11200	0.0701	-
8.7656	11220	0.0704	-
8.7812	11240	0.0675	-
8.7969	11260	0.0707	-
8.8125	11280	0.0712	-
8.8281	11300	0.0667	-
8.8438	11320	0.0679	-
8.8594	11340	0.0752	-
8.875	11360	0.0705	-
8.8906	11380	0.0713	-
8.9062	11400	0.0746	-
8.9219	11420	0.0737	-
8.9375	11440	0.0735	-
8.9531	11460	0.0721	-
8.9688	11480	0.0767	-
8.9844	11500	0.0706	-
9.0	11520	0.0707	0.9696
9.0156	11540	0.0701	-
9.0312	11560	0.0661	-
9.0469	11580	0.0733	-
9.0625	11600	0.0690	-
9.0781	11620	0.0720	-
9.0938	11640	0.0664	-
9.1094	11660	0.0742	-
9.125	11680	0.0659	-
9.1406	11700	0.0700	-
9.1562	11720	0.0693	-
9.1719	11740	0.0704	-
9.1875	11760	0.0683	-
9.2031	11780	0.0731	-
9.2188	11800	0.0688	-
9.2344	11820	0.0732	-
9.25	11840	0.0657	-
9.2656	11860	0.0688	-
9.2812	11880	0.0673	-
9.2969	11900	0.0705	-
9.3125	11920	0.0693	-
9.3281	11940	0.0663	-
9.3438	11960	0.0662	-
9.3594	11980	0.0688	-
9.375	12000	0.0728	-
9.3906	12020	0.0666	-
9.4062	12040	0.0698	-
9.4219	12060	0.0666	-
9.4375	12080	0.0731	-
9.4531	12100	0.0765	-
9.4688	12120	0.0744	-
9.4844	12140	0.0697	-
9.5	12160	0.0742	-
9.5156	12180	0.0710	-
9.5312	12200	0.0668	-
9.5469	12220	0.0709	-
9.5625	12240	0.0720	-
9.5781	12260	0.0700	-
9.5938	12280	0.0750	-
9.6094	12300	0.0695	-
9.625	12320	0.0706	-
9.6406	12340	0.0652	-
9.6562	12360	0.0721	-
9.6719	12380	0.0688	-
9.6875	12400	0.0663	-
9.7031	12420	0.0655	-
9.7188	12440	0.0707	-
9.7344	12460	0.0695	-
9.75	12480	0.0643	-
9.7656	12500	0.0657	-
9.7812	12520	0.0683	-
9.7969	12540	0.0694	-
9.8125	12560	0.0732	-
9.8281	12580	0.0700	-
9.8438	12600	0.0694	-
9.8594	12620	0.0700	-
9.875	12640	0.0711	-
9.8906	12660	0.0758	-
9.9062	12680	0.0686	-
9.9219	12700	0.0687	-
9.9375	12720	0.0771	-
9.9531	12740	0.0669	-
9.9688	12760	0.0720	-
9.9844	12780	0.0729	-
10.0	12800	0.0698	0.9694

• The bold row denotes the saved checkpoint.

Framework Versions

• Python: 3.12.3
• Sentence Transformers: 5.3.0
• Transformers: 5.3.0
• PyTorch: 2.10.0a0+a36e1d39eb.nv26.01.42222806
• Accelerate: 1.13.0
• Datasets: 4.4.2
• Tokenizers: 0.22.2

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",
}