SenhorDasMoscas/acho-ptbr-e5-lr3e-05-09-01-2025

SentenceTransformer based on neuralmind/bert-large-portuguese-cased

This is a sentence-transformers model finetuned from neuralmind/bert-large-portuguese-cased. It maps sentences & paragraphs to a 1024-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: neuralmind/bert-large-portuguese-cased
• Maximum Sequence Length: 512 tokens
• Output Dimensionality: 1024 dimensions
• Similarity Function: Cosine Similarity

Model Sources

• Documentation: Sentence Transformers Documentation
• Repository: Sentence Transformers on GitHub
• Hugging Face: Sentence Transformers on Hugging Face

Full Model Architecture

SentenceTransformer(
  (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel 
  (1): Pooling({'word_embedding_dimension': 1024, '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("SenhorDasMoscas/acho-ptbr-e5-lr3e-05-09-01-2025")
# Run inference
sentences = [
    'varal chao retratilr',
    'suplemento',
    'servico reparo eletronico',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 1024]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)
# [3, 3]

Evaluation

Metrics

Semantic Similarity

• Dataset: eval-similarity
• Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	0.947
spearman_cosine	0.8542

Training Details

Training Dataset

Unnamed Dataset

• Size: 20,237 training samples
• Columns: text1, text2, and label
• Approximate statistics based on the first 1000 samples:

  	text1	text2	label
  type	string	string	float
  details	min: 3 tokens mean: 7.71 tokens max: 18 tokens	min: 3 tokens mean: 6.1 tokens max: 11 tokens	min: 0.1 mean: 0.56 max: 1.0

• Samples:

  text1	text2	label
  poltrona reclinavel confortavel	livro material literario	0.1
  contratar servico paisagismo	servico area educacao	0.1
  aula canto coral	servico area educacao	1.0

• Loss: CosineSimilarityLoss with these parameters:

  {
      "loss_fct": "torch.nn.modules.loss.MSELoss"
  }
  

Evaluation Dataset

Unnamed Dataset

• Size: 2,249 evaluation samples
• Columns: text1, text2, and label
• Approximate statistics based on the first 1000 samples:

  	text1	text2	label
  type	string	string	float
  details	min: 3 tokens mean: 7.76 tokens max: 17 tokens	min: 3 tokens mean: 6.11 tokens max: 11 tokens	min: 0.1 mean: 0.55 max: 1.0

• Samples:

  text1	text2	label
  brinquedo pet	produto pet animal domestico	1.0
  tapete sala	produto pet animal domestico	0.1
  livro aventura	instrumento musical	0.1

• Loss: CosineSimilarityLoss with these parameters:

  {
      "loss_fct": "torch.nn.modules.loss.MSELoss"
  }
  

Training Hyperparameters

Non-Default Hyperparameters

• eval_strategy: steps
• per_device_train_batch_size: 32
• per_device_eval_batch_size: 32
• learning_rate: 3e-05
• weight_decay: 0.1
• num_train_epochs: 5
• warmup_ratio: 0.1
• warmup_steps: 252
• fp16: True
• 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: 32
• per_device_eval_batch_size: 32
• 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: 3e-05
• weight_decay: 0.1
• 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: 252
• 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: 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: None
• hub_always_push: False
• gradient_checkpointing: False
• gradient_checkpointing_kwargs: None
• include_inputs_for_metrics: False
• include_for_metrics: []
• eval_do_concat_batches: True
• fp16_backend: auto
• push_to_hub_model_id: None
• push_to_hub_organization: None
• mp_parameters:
• auto_find_batch_size: False
• full_determinism: False
• torchdynamo: None
• ray_scope: last
• ddp_timeout: 1800
• torch_compile: False
• torch_compile_backend: None
• torch_compile_mode: None
• dispatch_batches: None
• split_batches: None
• include_tokens_per_second: False
• include_num_input_tokens_seen: False
• neftune_noise_alpha: None
• optim_target_modules: None
• batch_eval_metrics: False
• eval_on_start: False
• use_liger_kernel: False
• eval_use_gather_object: False
• average_tokens_across_devices: False
• prompts: None
• batch_sampler: batch_sampler
• multi_dataset_batch_sampler: proportional

Training Logs

Click to expand

Epoch	Step	Training Loss	Validation Loss	eval-similarity_spearman_cosine
0.0079	5	0.2353	-	-
0.0158	10	0.2114	-	-
0.0237	15	0.2089	-	-
0.0316	20	0.1935	-	-
0.0395	25	0.1799	-	-
0.0474	30	0.178	-	-
0.0553	35	0.1686	-	-
0.0632	40	0.1602	-	-
0.0711	45	0.1502	-	-
0.0790	50	0.1446	-	-
0.0869	55	0.1399	-	-
0.0948	60	0.1318	-	-
0.1027	65	0.1251	-	-
0.1106	70	0.1035	-	-
0.1185	75	0.1064	-	-
0.1264	80	0.0886	-	-
0.1343	85	0.108	-	-
0.1422	90	0.0877	-	-
0.1501	95	0.1023	-	-
0.1580	100	0.0868	-	-
0.1659	105	0.0932	-	-
0.1738	110	0.0678	-	-
0.1817	115	0.0748	-	-
0.1896	120	0.0774	-	-
0.1975	125	0.0758	-	-
0.2054	130	0.0576	-	-
0.2133	135	0.0604	-	-
0.2212	140	0.0569	-	-
0.2291	145	0.0647	-	-
0.2370	150	0.0632	-	-
0.2449	155	0.0619	-	-
0.2528	160	0.0543	-	-
0.2607	165	0.0536	-	-
0.2686	170	0.0707	-	-
0.2765	175	0.0528	-	-
0.2844	180	0.0613	-	-
0.2923	185	0.0536	-	-
0.3002	190	0.0573	-	-
0.3081	195	0.0483	-	-
0.3160	200	0.0553	-	-
0.3239	205	0.0547	-	-
0.3318	210	0.0632	-	-
0.3397	215	0.0445	-	-
0.3476	220	0.0763	-	-
0.3555	225	0.0566	-	-
0.3633	230	0.0527	-	-
0.3712	235	0.0554	-	-
0.3791	240	0.0445	-	-
0.3870	245	0.0456	-	-
0.3949	250	0.0504	-	-
0.4028	255	0.063	-	-
0.4107	260	0.0441	-	-
0.4186	265	0.053	-	-
0.4265	270	0.0494	-	-
0.4344	275	0.0394	-	-
0.4423	280	0.0565	-	-
0.4502	285	0.0431	-	-
0.4581	290	0.0368	-	-
0.4660	295	0.0392	-	-
0.4739	300	0.0496	0.0412	0.8389
0.4818	305	0.0482	-	-
0.4897	310	0.048	-	-
0.4976	315	0.0373	-	-
0.5055	320	0.0279	-	-
0.5134	325	0.0447	-	-
0.5213	330	0.0412	-	-
0.5292	335	0.0338	-	-
0.5371	340	0.0468	-	-
0.5450	345	0.0508	-	-
0.5529	350	0.0447	-	-
0.5608	355	0.0407	-	-
0.5687	360	0.042	-	-
0.5766	365	0.0452	-	-
0.5845	370	0.0346	-	-
0.5924	375	0.0506	-	-
0.6003	380	0.0367	-	-
0.6082	385	0.0413	-	-
0.6161	390	0.0523	-	-
0.6240	395	0.037	-	-
0.6319	400	0.0497	-	-
0.6398	405	0.0375	-	-
0.6477	410	0.045	-	-
0.6556	415	0.0346	-	-
0.6635	420	0.0428	-	-
0.6714	425	0.022	-	-
0.6793	430	0.0422	-	-
0.6872	435	0.0514	-	-
0.6951	440	0.0454	-	-
0.7030	445	0.0418	-	-
0.7109	450	0.0587	-	-
0.7188	455	0.0477	-	-
0.7267	460	0.0515	-	-
0.7346	465	0.0466	-	-
0.7425	470	0.0331	-	-
0.7504	475	0.0339	-	-
0.7583	480	0.0367	-	-
0.7662	485	0.0342	-	-
0.7741	490	0.0343	-	-
0.7820	495	0.0423	-	-
0.7899	500	0.0548	-	-
0.7978	505	0.0393	-	-
0.8057	510	0.0371	-	-
0.8136	515	0.0222	-	-
0.8215	520	0.0411	-	-
0.8294	525	0.0321	-	-
0.8373	530	0.0408	-	-
0.8452	535	0.0296	-	-
0.8531	540	0.0306	-	-
0.8610	545	0.0329	-	-
0.8689	550	0.034	-	-
0.8768	555	0.0482	-	-
0.8847	560	0.0376	-	-
0.8926	565	0.054	-	-
0.9005	570	0.0345	-	-
0.9084	575	0.0335	-	-
0.9163	580	0.0506	-	-
0.9242	585	0.0444	-	-
0.9321	590	0.0276	-	-
0.9400	595	0.0343	-	-
0.9479	600	0.0393	0.0313	0.8469
0.9558	605	0.0288	-	-
0.9637	610	0.0328	-	-
0.9716	615	0.0256	-	-
0.9795	620	0.0273	-	-
0.9874	625	0.0361	-	-
0.9953	630	0.0298	-	-
1.0032	635	0.0213	-	-
1.0111	640	0.0319	-	-
1.0190	645	0.0185	-	-
1.0269	650	0.0296	-	-
1.0348	655	0.0186	-	-
1.0427	660	0.0246	-	-
1.0506	665	0.0286	-	-
1.0585	670	0.0252	-	-
1.0664	675	0.0257	-	-
1.0742	680	0.0334	-	-
1.0821	685	0.0172	-	-
1.0900	690	0.0225	-	-
1.0979	695	0.0206	-	-
1.1058	700	0.0271	-	-
1.1137	705	0.0224	-	-
1.1216	710	0.0148	-	-
1.1295	715	0.0215	-	-
1.1374	720	0.0373	-	-
1.1453	725	0.0204	-	-
1.1532	730	0.0191	-	-
1.1611	735	0.0224	-	-
1.1690	740	0.0243	-	-
1.1769	745	0.0401	-	-
1.1848	750	0.0196	-	-
1.1927	755	0.0358	-	-
1.2006	760	0.0399	-	-
1.2085	765	0.0169	-	-
1.2164	770	0.0173	-	-
1.2243	775	0.0252	-	-
1.2322	780	0.0342	-	-
1.2401	785	0.0287	-	-
1.2480	790	0.0227	-	-
1.2559	795	0.012	-	-
1.2638	800	0.0259	-	-
1.2717	805	0.0254	-	-
1.2796	810	0.0363	-	-
1.2875	815	0.0256	-	-
1.2954	820	0.0264	-	-
1.3033	825	0.0209	-	-
1.3112	830	0.0326	-	-
1.3191	835	0.0193	-	-
1.3270	840	0.0234	-	-
1.3349	845	0.0551	-	-
1.3428	850	0.0283	-	-
1.3507	855	0.0188	-	-
1.3586	860	0.0224	-	-
1.3665	865	0.0249	-	-
1.3744	870	0.0239	-	-
1.3823	875	0.0276	-	-
1.3902	880	0.0222	-	-
1.3981	885	0.0246	-	-
1.4060	890	0.0269	-	-
1.4139	895	0.0194	-	-
1.4218	900	0.0241	0.0272	0.8494
1.4297	905	0.0204	-	-
1.4376	910	0.019	-	-
1.4455	915	0.0362	-	-
1.4534	920	0.015	-	-
1.4613	925	0.0211	-	-
1.4692	930	0.0257	-	-
1.4771	935	0.019	-	-
1.4850	940	0.029	-	-
1.4929	945	0.0213	-	-
1.5008	950	0.0174	-	-
1.5087	955	0.0141	-	-
1.5166	960	0.0114	-	-
1.5245	965	0.0325	-	-
1.5324	970	0.018	-	-
1.5403	975	0.0167	-	-
1.5482	980	0.0156	-	-
1.5561	985	0.023	-	-
1.5640	990	0.0208	-	-
1.5719	995	0.0187	-	-
1.5798	1000	0.0202	-	-
1.5877	1005	0.0148	-	-
1.5956	1010	0.0248	-	-
1.6035	1015	0.015	-	-
1.6114	1020	0.0265	-	-
1.6193	1025	0.0415	-	-
1.6272	1030	0.0233	-	-
1.6351	1035	0.0212	-	-
1.6430	1040	0.0248	-	-
1.6509	1045	0.0236	-	-
1.6588	1050	0.0147	-	-
1.6667	1055	0.0242	-	-
1.6746	1060	0.0415	-	-
1.6825	1065	0.0249	-	-
1.6904	1070	0.0239	-	-
1.6983	1075	0.0182	-	-
1.7062	1080	0.0155	-	-
1.7141	1085	0.0352	-	-
1.7220	1090	0.0269	-	-
1.7299	1095	0.0182	-	-
1.7378	1100	0.0271	-	-
1.7457	1105	0.0168	-	-
1.7536	1110	0.0222	-	-
1.7615	1115	0.0253	-	-
1.7694	1120	0.0249	-	-
1.7773	1125	0.025	-	-
1.7852	1130	0.0253	-	-
1.7930	1135	0.0197	-	-
1.8009	1140	0.0205	-	-
1.8088	1145	0.0289	-	-
1.8167	1150	0.0218	-	-
1.8246	1155	0.0241	-	-
1.8325	1160	0.0191	-	-
1.8404	1165	0.0199	-	-
1.8483	1170	0.028	-	-
1.8562	1175	0.0135	-	-
1.8641	1180	0.0218	-	-
1.8720	1185	0.0226	-	-
1.8799	1190	0.0227	-	-
1.8878	1195	0.0148	-	-
1.8957	1200	0.0327	0.0255	0.8500
1.9036	1205	0.025	-	-
1.9115	1210	0.0174	-	-
1.9194	1215	0.0155	-	-
1.9273	1220	0.0169	-	-
1.9352	1225	0.0163	-	-
1.9431	1230	0.0142	-	-
1.9510	1235	0.012	-	-
1.9589	1240	0.015	-	-
1.9668	1245	0.0356	-	-
1.9747	1250	0.0238	-	-
1.9826	1255	0.0199	-	-
1.9905	1260	0.0167	-	-
1.9984	1265	0.0339	-	-
2.0063	1270	0.0107	-	-
2.0142	1275	0.0121	-	-
2.0221	1280	0.0171	-	-
2.0300	1285	0.0128	-	-
2.0379	1290	0.0123	-	-
2.0458	1295	0.0156	-	-
2.0537	1300	0.0186	-	-
2.0616	1305	0.0142	-	-
2.0695	1310	0.0086	-	-
2.0774	1315	0.0074	-	-
2.0853	1320	0.0098	-	-
2.0932	1325	0.0213	-	-
2.1011	1330	0.0117	-	-
2.1090	1335	0.0123	-	-
2.1169	1340	0.0092	-	-
2.1248	1345	0.011	-	-
2.1327	1350	0.0127	-	-
2.1406	1355	0.0133	-	-
2.1485	1360	0.0127	-	-
2.1564	1365	0.0133	-	-
2.1643	1370	0.0144	-	-
2.1722	1375	0.0165	-	-
2.1801	1380	0.0106	-	-
2.1880	1385	0.0167	-	-
2.1959	1390	0.0124	-	-
2.2038	1395	0.0107	-	-
2.2117	1400	0.0173	-	-
2.2196	1405	0.0165	-	-
2.2275	1410	0.0179	-	-
2.2354	1415	0.0131	-	-
2.2433	1420	0.0118	-	-
2.2512	1425	0.0094	-	-
2.2591	1430	0.0114	-	-
2.2670	1435	0.0251	-	-
2.2749	1440	0.0293	-	-
2.2828	1445	0.0108	-	-
2.2907	1450	0.0099	-	-
2.2986	1455	0.0178	-	-
2.3065	1460	0.0264	-	-
2.3144	1465	0.0091	-	-
2.3223	1470	0.0118	-	-
2.3302	1475	0.014	-	-
2.3381	1480	0.0209	-	-
2.3460	1485	0.0068	-	-
2.3539	1490	0.012	-	-
2.3618	1495	0.0105	-	-
2.3697	1500	0.0149	0.0250	0.8494
2.3776	1505	0.0114	-	-
2.3855	1510	0.0179	-	-
2.3934	1515	0.0136	-	-
2.4013	1520	0.0096	-	-
2.4092	1525	0.0131	-	-
2.4171	1530	0.0137	-	-
2.4250	1535	0.0194	-	-
2.4329	1540	0.013	-	-
2.4408	1545	0.0289	-	-
2.4487	1550	0.0074	-	-
2.4566	1555	0.0142	-	-
2.4645	1560	0.0041	-	-
2.4724	1565	0.0138	-	-
2.4803	1570	0.0163	-	-
2.4882	1575	0.0259	-	-
2.4961	1580	0.0127	-	-
2.5039	1585	0.0056	-	-
2.5118	1590	0.0101	-	-
2.5197	1595	0.012	-	-
2.5276	1600	0.0099	-	-
2.5355	1605	0.0292	-	-
2.5434	1610	0.0182	-	-
2.5513	1615	0.0088	-	-
2.5592	1620	0.0206	-	-
2.5671	1625	0.0058	-	-
2.5750	1630	0.0244	-	-
2.5829	1635	0.0243	-	-
2.5908	1640	0.0311	-	-
2.5987	1645	0.0099	-	-
2.6066	1650	0.011	-	-
2.6145	1655	0.0076	-	-
2.6224	1660	0.0159	-	-
2.6303	1665	0.017	-	-
2.6382	1670	0.008	-	-
2.6461	1675	0.0108	-	-
2.6540	1680	0.0088	-	-
2.6619	1685	0.0094	-	-
2.6698	1690	0.0086	-	-
2.6777	1695	0.0159	-	-
2.6856	1700	0.013	-	-
2.6935	1705	0.0236	-	-
2.7014	1710	0.0182	-	-
2.7093	1715	0.0123	-	-
2.7172	1720	0.0157	-	-
2.7251	1725	0.027	-	-
2.7330	1730	0.0079	-	-
2.7409	1735	0.0146	-	-
2.7488	1740	0.0129	-	-
2.7567	1745	0.0096	-	-
2.7646	1750	0.0187	-	-
2.7725	1755	0.0099	-	-
2.7804	1760	0.0081	-	-
2.7883	1765	0.0217	-	-
2.7962	1770	0.0103	-	-
2.8041	1775	0.009	-	-
2.8120	1780	0.0148	-	-
2.8199	1785	0.0144	-	-
2.8278	1790	0.0167	-	-
2.8357	1795	0.0104	-	-
2.8436	1800	0.0166	0.0231	0.8522
2.8515	1805	0.0241	-	-
2.8594	1810	0.0158	-	-
2.8673	1815	0.0112	-	-
2.8752	1820	0.0195	-	-
2.8831	1825	0.0187	-	-
2.8910	1830	0.0107	-	-
2.8989	1835	0.0188	-	-
2.9068	1840	0.0173	-	-
2.9147	1845	0.0079	-	-
2.9226	1850	0.0224	-	-
2.9305	1855	0.0195	-	-
2.9384	1860	0.007	-	-
2.9463	1865	0.0088	-	-
2.9542	1870	0.0094	-	-
2.9621	1875	0.012	-	-
2.9700	1880	0.0089	-	-
2.9779	1885	0.0086	-	-
2.9858	1890	0.0084	-	-
2.9937	1895	0.0207	-	-
3.0016	1900	0.0071	-	-
3.0095	1905	0.0092	-	-
3.0174	1910	0.0054	-	-
3.0253	1915	0.009	-	-
3.0332	1920	0.0087	-	-
3.0411	1925	0.0074	-	-
3.0490	1930	0.0044	-	-
3.0569	1935	0.007	-	-
3.0648	1940	0.0136	-	-
3.0727	1945	0.0074	-	-
3.0806	1950	0.0131	-	-
3.0885	1955	0.0048	-	-
3.0964	1960	0.0149	-	-
3.1043	1965	0.0031	-	-
3.1122	1970	0.0146	-	-
3.1201	1975	0.0066	-	-
3.1280	1980	0.009	-	-
3.1359	1985	0.0122	-	-
3.1438	1990	0.0145	-	-
3.1517	1995	0.016	-	-
3.1596	2000	0.0111	-	-
3.1675	2005	0.0058	-	-
3.1754	2010	0.0081	-	-
3.1833	2015	0.0123	-	-
3.1912	2020	0.0098	-	-
3.1991	2025	0.0069	-	-
3.2070	2030	0.0111	-	-
3.2148	2035	0.0048	-	-
3.2227	2040	0.0028	-	-
3.2306	2045	0.0088	-	-
3.2385	2050	0.0092	-	-
3.2464	2055	0.0088	-	-
3.2543	2060	0.0043	-	-
3.2622	2065	0.0074	-	-
3.2701	2070	0.0043	-	-
3.2780	2075	0.0086	-	-
3.2859	2080	0.0026	-	-
3.2938	2085	0.012	-	-
3.3017	2090	0.0057	-	-
3.3096	2095	0.0088	-	-
3.3175	2100	0.0107	0.0217	0.8537
3.3254	2105	0.0099	-	-
3.3333	2110	0.0103	-	-
3.3412	2115	0.0079	-	-
3.3491	2120	0.0106	-	-
3.3570	2125	0.0166	-	-
3.3649	2130	0.0178	-	-
3.3728	2135	0.0106	-	-
3.3807	2140	0.0037	-	-
3.3886	2145	0.0107	-	-
3.3965	2150	0.0084	-	-
3.4044	2155	0.0085	-	-
3.4123	2160	0.0084	-	-
3.4202	2165	0.0056	-	-
3.4281	2170	0.005	-	-
3.4360	2175	0.0224	-	-
3.4439	2180	0.012	-	-
3.4518	2185	0.0094	-	-
3.4597	2190	0.0041	-	-
3.4676	2195	0.0078	-	-
3.4755	2200	0.0058	-	-
3.4834	2205	0.0061	-	-
3.4913	2210	0.0049	-	-
3.4992	2215	0.0114	-	-
3.5071	2220	0.0062	-	-
3.5150	2225	0.0064	-	-
3.5229	2230	0.0044	-	-
3.5308	2235	0.0054	-	-
3.5387	2240	0.0122	-	-
3.5466	2245	0.0082	-	-
3.5545	2250	0.0125	-	-
3.5624	2255	0.0113	-	-
3.5703	2260	0.01	-	-
3.5782	2265	0.0046	-	-
3.5861	2270	0.0092	-	-
3.5940	2275	0.0061	-	-
3.6019	2280	0.0104	-	-
3.6098	2285	0.0032	-	-
3.6177	2290	0.0108	-	-
3.6256	2295	0.0139	-	-
3.6335	2300	0.0129	-	-
3.6414	2305	0.0068	-	-
3.6493	2310	0.0096	-	-
3.6572	2315	0.0117	-	-
3.6651	2320	0.019	-	-
3.6730	2325	0.0084	-	-
3.6809	2330	0.0145	-	-
3.6888	2335	0.0056	-	-
3.6967	2340	0.0043	-	-
3.7046	2345	0.0087	-	-
3.7125	2350	0.0141	-	-
3.7204	2355	0.0073	-	-
3.7283	2360	0.0056	-	-
3.7362	2365	0.0139	-	-
3.7441	2370	0.0058	-	-
3.7520	2375	0.0161	-	-
3.7599	2380	0.0053	-	-
3.7678	2385	0.0034	-	-
3.7757	2390	0.0137	-	-
3.7836	2395	0.0115	-	-
3.7915	2400	0.0153	0.0217	0.8547
3.7994	2405	0.0121	-	-
3.8073	2410	0.0129	-	-
3.8152	2415	0.0149	-	-
3.8231	2420	0.0069	-	-
3.8310	2425	0.0077	-	-
3.8389	2430	0.0232	-	-
3.8468	2435	0.008	-	-
3.8547	2440	0.0042	-	-
3.8626	2445	0.0033	-	-
3.8705	2450	0.0057	-	-
3.8784	2455	0.0048	-	-
3.8863	2460	0.0144	-	-
3.8942	2465	0.0105	-	-
3.9021	2470	0.0119	-	-
3.9100	2475	0.0071	-	-
3.9179	2480	0.0075	-	-
3.9258	2485	0.0084	-	-
3.9336	2490	0.0076	-	-
3.9415	2495	0.0071	-	-
3.9494	2500	0.006	-	-
3.9573	2505	0.0048	-	-
3.9652	2510	0.0035	-	-
3.9731	2515	0.0067	-	-
3.9810	2520	0.0106	-	-
3.9889	2525	0.0076	-	-
3.9968	2530	0.0063	-	-
4.0047	2535	0.0103	-	-
4.0126	2540	0.0139	-	-
4.0205	2545	0.0035	-	-
4.0284	2550	0.0061	-	-
4.0363	2555	0.0122	-	-
4.0442	2560	0.0032	-	-
4.0521	2565	0.0048	-	-
4.0600	2570	0.0049	-	-
4.0679	2575	0.0041	-	-
4.0758	2580	0.0051	-	-
4.0837	2585	0.0058	-	-
4.0916	2590	0.0042	-	-
4.0995	2595	0.0094	-	-
4.1074	2600	0.0019	-	-
4.1153	2605	0.0072	-	-
4.1232	2610	0.0026	-	-
4.1311	2615	0.0085	-	-
4.1390	2620	0.0069	-	-
4.1469	2625	0.0026	-	-
4.1548	2630	0.0045	-	-
4.1627	2635	0.0059	-	-
4.1706	2640	0.0065	-	-
4.1785	2645	0.007	-	-
4.1864	2650	0.004	-	-
4.1943	2655	0.0021	-	-
4.2022	2660	0.0034	-	-
4.2101	2665	0.0092	-	-
4.2180	2670	0.0047	-	-
4.2259	2675	0.0076	-	-
4.2338	2680	0.0027	-	-
4.2417	2685	0.0096	-	-
4.2496	2690	0.0035	-	-
4.2575	2695	0.0104	-	-
4.2654	2700	0.0019	0.0216	0.8539
4.2733	2705	0.0073	-	-
4.2812	2710	0.0115	-	-
4.2891	2715	0.0053	-	-
4.2970	2720	0.0047	-	-
4.3049	2725	0.004	-	-
4.3128	2730	0.006	-	-
4.3207	2735	0.0024	-	-
4.3286	2740	0.0034	-	-
4.3365	2745	0.0066	-	-
4.3444	2750	0.0019	-	-
4.3523	2755	0.0085	-	-
4.3602	2760	0.0057	-	-
4.3681	2765	0.0031	-	-
4.3760	2770	0.0173	-	-
4.3839	2775	0.0037	-	-
4.3918	2780	0.0056	-	-
4.3997	2785	0.0111	-	-
4.4076	2790	0.0063	-	-
4.4155	2795	0.0072	-	-
4.4234	2800	0.0125	-	-
4.4313	2805	0.0045	-	-
4.4392	2810	0.0022	-	-
4.4471	2815	0.0037	-	-
4.4550	2820	0.0044	-	-
4.4629	2825	0.0058	-	-
4.4708	2830	0.0061	-	-
4.4787	2835	0.0101	-	-
4.4866	2840	0.0021	-	-
4.4945	2845	0.0122	-	-
4.5024	2850	0.0089	-	-
4.5103	2855	0.0035	-	-
4.5182	2860	0.0027	-	-
4.5261	2865	0.0036	-	-
4.5340	2870	0.0035	-	-
4.5419	2875	0.004	-	-
4.5498	2880	0.0082	-	-
4.5577	2885	0.0038	-	-
4.5656	2890	0.0022	-	-
4.5735	2895	0.0023	-	-
4.5814	2900	0.0068	-	-
4.5893	2905	0.0035	-	-
4.5972	2910	0.0025	-	-
4.6051	2915	0.0024	-	-
4.6130	2920	0.0124	-	-
4.6209	2925	0.0048	-	-
4.6288	2930	0.005	-	-
4.6367	2935	0.0052	-	-
4.6445	2940	0.0038	-	-
4.6524	2945	0.0067	-	-
4.6603	2950	0.0031	-	-
4.6682	2955	0.0082	-	-
4.6761	2960	0.0039	-	-
4.6840	2965	0.0031	-	-
4.6919	2970	0.0067	-	-
4.6998	2975	0.0086	-	-
4.7077	2980	0.0041	-	-
4.7156	2985	0.0018	-	-
4.7235	2990	0.0145	-	-
4.7314	2995	0.0095	-	-
4.7393	3000	0.0041	0.0215	0.8542
4.7472	3005	0.015	-	-
4.7551	3010	0.0084	-	-
4.7630	3015	0.0148	-	-
4.7709	3020	0.0023	-	-
4.7788	3025	0.0117	-	-
4.7867	3030	0.0081	-	-
4.7946	3035	0.0074	-	-
4.8025	3040	0.0033	-	-
4.8104	3045	0.0071	-	-
4.8183	3050	0.0068	-	-
4.8262	3055	0.006	-	-
4.8341	3060	0.0084	-	-
4.8420	3065	0.0061	-	-
4.8499	3070	0.0028	-	-
4.8578	3075	0.0118	-	-
4.8657	3080	0.0071	-	-
4.8736	3085	0.0082	-	-
4.8815	3090	0.0044	-	-
4.8894	3095	0.0125	-	-
4.8973	3100	0.003	-	-
4.9052	3105	0.0052	-	-
4.9131	3110	0.0082	-	-
4.9210	3115	0.0019	-	-
4.9289	3120	0.0044	-	-
4.9368	3125	0.011	-	-
4.9447	3130	0.0073	-	-
4.9526	3135	0.0033	-	-
4.9605	3140	0.0091	-	-
4.9684	3145	0.0065	-	-
4.9763	3150	0.0202	-	-
4.9842	3155	0.0094	-	-
4.9921	3160	0.0025	-	-
5.0	3165	0.0073	-	-

• The bold row denotes the saved checkpoint.

Framework Versions

• Python: 3.10.12
• Sentence Transformers: 3.3.1
• Transformers: 4.47.1
• PyTorch: 2.5.1+cu121
• Accelerate: 1.2.1
• Datasets: 2.14.4
• Tokenizers: 0.21.0

Citation

BibTeX

Sentence Transformers

@inproceedings{reimers-2019-sentence-bert,
    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
    author = "Reimers, Nils and Gurevych, Iryna",
    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
    month = "11",
    year = "2019",
    publisher = "Association for Computational Linguistics",
    url = "https://arxiv.org/abs/1908.10084",
}