SenhorDasMoscas/acho-ptbr-e4-lr0.0001-08-01-2025

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-e4-lr0.0001-08-01-2025")
# Run inference
sentences = [
    'cenoura organico onde encontrar',
    'hortifruti',
    'moda acessorio',
]
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	0.9378
spearman_cosine	0.8476

Training Details

Training Dataset

Unnamed Dataset

• Size: 19,697 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: 7.76 tokens max: 16 tokens	min: 3 tokens mean: 6.03 tokens max: 11 tokens	min: 0.1 mean: 0.54 max: 1.0

• Samples:

  text1	text2	label
  trufa rechear lindt	doce chocolate	1.0
  ferramento dremel	ferramenta equipamento	1.0
  melatonino 5 mg	suplemento	1.0

• Loss: CosineSimilarityLoss with these parameters:

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

Evaluation Dataset

Unnamed Dataset

• Size: 2,189 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: 7.78 tokens max: 19 tokens	min: 3 tokens mean: 6.16 tokens max: 11 tokens	min: 0.1 mean: 0.53 max: 1.0

• Samples:

  text1	text2	label
  cadeira bar alto	movel	1.0
  vela massagem erotico	bebida alcoolico	0.1
  onde sorvete vegano	comida rapido fastfood	1.0

• 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: 0.0001
• weight_decay: 0.1
• num_train_epochs: 4
• warmup_ratio: 0.1
• warmup_steps: 246
• 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: 0.0001
• weight_decay: 0.1
• adam_beta1: 0.9
• adam_beta2: 0.999
• adam_epsilon: 1e-08
• max_grad_norm: 1.0
• num_train_epochs: 4
• max_steps: -1
• lr_scheduler_type: linear
• lr_scheduler_kwargs: {}
• warmup_ratio: 0.1
• warmup_steps: 246
• 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
0.0081	5	0.1835	-	-
0.0162	10	0.2161	-	-
0.0244	15	0.1918	-	-
0.0325	20	0.1722	-	-
0.0406	25	0.1527	-	-
0.0487	30	0.141	-	-
0.0568	35	0.1279	-	-
0.0649	40	0.1228	-	-
0.0731	45	0.0986	-	-
0.0812	50	0.0875	-	-
0.0893	55	0.0818	-	-
0.0974	60	0.0804	-	-
0.1055	65	0.0779	-	-
0.1136	70	0.0722	-	-
0.1218	75	0.0791	-	-
0.1299	80	0.0749	-	-
0.1380	85	0.0548	-	-
0.1461	90	0.0681	-	-
0.1542	95	0.0643	-	-
0.1623	100	0.0672	-	-
0.1705	105	0.0615	-	-
0.1786	110	0.0804	-	-
0.1867	115	0.0703	-	-
0.1948	120	0.0685	-	-
0.2029	125	0.0573	-	-
0.2110	130	0.0603	-	-
0.2192	135	0.0583	-	-
0.2273	140	0.0528	-	-
0.2354	145	0.0628	-	-
0.2435	150	0.0657	-	-
0.2516	155	0.0489	-	-
0.2597	160	0.0566	-	-
0.2679	165	0.0557	-	-
0.2760	170	0.0522	-	-
0.2841	175	0.0602	-	-
0.2922	180	0.0572	-	-
0.3003	185	0.0546	-	-
0.3084	190	0.0523	-	-
0.3166	195	0.054	-	-
0.3247	200	0.0451	-	-
0.3328	205	0.044	-	-
0.3409	210	0.0439	-	-
0.3490	215	0.0706	-	-
0.3571	220	0.0569	-	-
0.3653	225	0.0512	-	-
0.3734	230	0.064	-	-
0.3815	235	0.0691	-	-
0.3896	240	0.0531	-	-
0.3977	245	0.0536	-	-
0.4058	250	0.0369	-	-
0.4140	255	0.0678	-	-
0.4221	260	0.0517	-	-
0.4302	265	0.0832	-	-
0.4383	270	0.0529	-	-
0.4464	275	0.0519	-	-
0.4545	280	0.0692	-	-
0.4627	285	0.0455	-	-
0.4708	290	0.0733	-	-
0.4789	295	0.0534	-	-
0.4870	300	0.0345	-	-
0.4951	305	0.0534	-	-
0.5032	310	0.0384	-	-
0.5114	315	0.0622	-	-
0.5195	320	0.0477	-	-
0.5276	325	0.0571	-	-
0.5357	330	0.0481	-	-
0.5438	335	0.0647	-	-
0.5519	340	0.0606	-	-
0.5601	345	0.0493	-	-
0.5682	350	0.0536	-	-
0.5763	355	0.0466	-	-
0.5844	360	0.0747	-	-
0.5925	365	0.0658	-	-
0.6006	370	0.0456	-	-
0.6088	375	0.0369	-	-
0.6169	380	0.0563	-	-
0.625	385	0.0751	-	-
0.6331	390	0.0475	-	-
0.6412	395	0.0654	-	-
0.6494	400	0.0498	-	-
0.6575	405	0.0625	-	-
0.6656	410	0.0614	-	-
0.6737	415	0.0403	-	-
0.6818	420	0.0474	-	-
0.6899	425	0.0483	-	-
0.6981	430	0.057	-	-
0.7062	435	0.0754	-	-
0.7143	440	0.0608	-	-
0.7224	445	0.0411	-	-
0.7305	450	0.0586	-	-
0.7386	455	0.0494	-	-
0.7468	460	0.0422	-	-
0.7549	465	0.0595	-	-
0.7630	470	0.0605	-	-
0.7711	475	0.0648	-	-
0.7792	480	0.0559	-	-
0.7873	485	0.0432	-	-
0.7955	490	0.0587	-	-
0.8036	495	0.0316	-	-
0.8117	500	0.0363	-	-
0.8198	505	0.053	-	-
0.8279	510	0.0665	-	-
0.8360	515	0.0237	-	-
0.8442	520	0.0323	-	-
0.8523	525	0.0651	-	-
0.8604	530	0.0346	-	-
0.8685	535	0.0537	-	-
0.8766	540	0.0413	-	-
0.8847	545	0.0406	-	-
0.8929	550	0.0609	-	-
0.9010	555	0.0304	-	-
0.9091	560	0.0455	-	-
0.9172	565	0.0382	-	-
0.9253	570	0.0423	-	-
0.9334	575	0.0479	-	-
0.9416	580	0.0469	-	-
0.9497	585	0.0519	-	-
0.9578	590	0.047	-	-
0.9659	595	0.0365	-	-
0.9740	600	0.0365	-	-
0.9821	605	0.036	-	-
0.9903	610	0.0426	-	-
0.9984	615	0.0571	-	-
1.0065	620	0.0368	-	-
1.0146	625	0.0347	-	-
1.0227	630	0.0295	-	-
1.0308	635	0.0487	-	-
1.0390	640	0.038	-	-
1.0471	645	0.0278	-	-
1.0552	650	0.038	-	-
1.0633	655	0.0185	-	-
1.0714	660	0.0293	0.0346	0.8404
1.0795	665	0.034	-	-
1.0877	670	0.0306	-	-
1.0958	675	0.0237	-	-
1.1039	680	0.0336	-	-
1.1120	685	0.0318	-	-
1.1201	690	0.0294	-	-
1.1282	695	0.0257	-	-
1.1364	700	0.0202	-	-
1.1445	705	0.0407	-	-
1.1526	710	0.0191	-	-
1.1607	715	0.0557	-	-
1.1688	720	0.0287	-	-
1.1769	725	0.0284	-	-
1.1851	730	0.0476	-	-
1.1932	735	0.0306	-	-
1.2013	740	0.0168	-	-
1.2094	745	0.0338	-	-
1.2175	750	0.0244	-	-
1.2256	755	0.0384	-	-
1.2338	760	0.0145	-	-
1.2419	765	0.031	-	-
1.25	770	0.024	-	-
1.2581	775	0.0268	-	-
1.2662	780	0.0293	-	-
1.2744	785	0.0217	-	-
1.2825	790	0.0323	-	-
1.2906	795	0.0286	-	-
1.2987	800	0.0325	-	-
1.3068	805	0.04	-	-
1.3149	810	0.0449	-	-
1.3231	815	0.0302	-	-
1.3312	820	0.033	-	-
1.3393	825	0.022	-	-
1.3474	830	0.0377	-	-
1.3555	835	0.0301	-	-
1.3636	840	0.0303	-	-
1.3718	845	0.0396	-	-
1.3799	850	0.0298	-	-
1.3880	855	0.0192	-	-
1.3961	860	0.0203	-	-
1.4042	865	0.041	-	-
1.4123	870	0.0271	-	-
1.4205	875	0.0368	-	-
1.4286	880	0.0383	-	-
1.4367	885	0.0399	-	-
1.4448	890	0.0364	-	-
1.4529	895	0.0236	-	-
1.4610	900	0.0279	-	-
1.4692	905	0.0441	-	-
1.4773	910	0.0235	-	-
1.4854	915	0.0248	-	-
1.4935	920	0.0329	-	-
1.5016	925	0.0306	-	-
1.5097	930	0.0278	-	-
1.5179	935	0.0303	-	-
1.5260	940	0.0384	-	-
1.5341	945	0.0364	-	-
1.5422	950	0.0334	-	-
1.5503	955	0.0317	-	-
1.5584	960	0.0199	-	-
1.5666	965	0.0232	-	-
1.5747	970	0.0249	-	-
1.5828	975	0.023	-	-
1.5909	980	0.022	-	-
1.5990	985	0.0131	-	-
1.6071	990	0.023	-	-
1.6153	995	0.0323	-	-
1.6234	1000	0.0224	-	-
1.6315	1005	0.022	-	-
1.6396	1010	0.0266	-	-
1.6477	1015	0.027	-	-
1.6558	1020	0.0316	-	-
1.6640	1025	0.0242	-	-
1.6721	1030	0.0267	-	-
1.6802	1035	0.0303	-	-
1.6883	1040	0.0163	-	-
1.6964	1045	0.0221	-	-
1.7045	1050	0.0308	-	-
1.7127	1055	0.0183	-	-
1.7208	1060	0.0143	-	-
1.7289	1065	0.0186	-	-
1.7370	1070	0.0172	-	-
1.7451	1075	0.0224	-	-
1.7532	1080	0.0357	-	-
1.7614	1085	0.0192	-	-
1.7695	1090	0.0264	-	-
1.7776	1095	0.02	-	-
1.7857	1100	0.021	-	-
1.7938	1105	0.0292	-	-
1.8019	1110	0.0246	-	-
1.8101	1115	0.0144	-	-
1.8182	1120	0.0377	-	-
1.8263	1125	0.0267	-	-
1.8344	1130	0.0275	-	-
1.8425	1135	0.0279	-	-
1.8506	1140	0.0242	-	-
1.8588	1145	0.0235	-	-
1.8669	1150	0.0302	-	-
1.875	1155	0.025	-	-
1.8831	1160	0.037	-	-
1.8912	1165	0.0244	-	-
1.8994	1170	0.0361	-	-
1.9075	1175	0.0255	-	-
1.9156	1180	0.0381	-	-
1.9237	1185	0.0224	-	-
1.9318	1190	0.0331	-	-
1.9399	1195	0.0201	-	-
1.9481	1200	0.0353	-	-
1.9562	1205	0.0337	-	-
1.9643	1210	0.0135	-	-
1.9724	1215	0.0238	-	-
1.9805	1220	0.0346	-	-
1.9886	1225	0.043	-	-
1.9968	1230	0.0231	-	-
2.0049	1235	0.0185	-	-
2.0130	1240	0.0142	-	-
2.0211	1245	0.0144	-	-
2.0292	1250	0.0168	-	-
2.0373	1255	0.0114	-	-
2.0455	1260	0.0109	-	-
2.0536	1265	0.0221	-	-
2.0617	1270	0.0158	-	-
2.0698	1275	0.0297	-	-
2.0779	1280	0.0214	-	-
2.0860	1285	0.0108	-	-
2.0942	1290	0.0194	-	-
2.1023	1295	0.0164	-	-
2.1104	1300	0.0199	-	-
2.1185	1305	0.0147	-	-
2.1266	1310	0.0132	-	-
2.1347	1315	0.0205	-	-
2.1429	1320	0.0152	0.0286	0.8450
2.1510	1325	0.02	-	-
2.1591	1330	0.0123	-	-
2.1672	1335	0.0233	-	-
2.1753	1340	0.0125	-	-
2.1834	1345	0.0108	-	-
2.1916	1350	0.0112	-	-
2.1997	1355	0.0205	-	-
2.2078	1360	0.022	-	-
2.2159	1365	0.0144	-	-
2.2240	1370	0.0183	-	-
2.2321	1375	0.01	-	-
2.2403	1380	0.0106	-	-
2.2484	1385	0.02	-	-
2.2565	1390	0.0116	-	-
2.2646	1395	0.0129	-	-
2.2727	1400	0.014	-	-
2.2808	1405	0.0178	-	-
2.2890	1410	0.0111	-	-
2.2971	1415	0.0164	-	-
2.3052	1420	0.018	-	-
2.3133	1425	0.012	-	-
2.3214	1430	0.011	-	-
2.3295	1435	0.017	-	-
2.3377	1440	0.0106	-	-
2.3458	1445	0.012	-	-
2.3539	1450	0.0123	-	-
2.3620	1455	0.0186	-	-
2.3701	1460	0.0135	-	-
2.3782	1465	0.0125	-	-
2.3864	1470	0.0216	-	-
2.3945	1475	0.0132	-	-
2.4026	1480	0.0184	-	-
2.4107	1485	0.0214	-	-
2.4188	1490	0.0255	-	-
2.4269	1495	0.026	-	-
2.4351	1500	0.0241	-	-
2.4432	1505	0.0181	-	-
2.4513	1510	0.0182	-	-
2.4594	1515	0.0156	-	-
2.4675	1520	0.0182	-	-
2.4756	1525	0.0104	-	-
2.4838	1530	0.0141	-	-
2.4919	1535	0.0206	-	-
2.5	1540	0.0119	-	-
2.5081	1545	0.0152	-	-
2.5162	1550	0.0132	-	-
2.5244	1555	0.0188	-	-
2.5325	1560	0.0217	-	-
2.5406	1565	0.0179	-	-
2.5487	1570	0.0163	-	-
2.5568	1575	0.0334	-	-
2.5649	1580	0.0082	-	-
2.5731	1585	0.0118	-	-
2.5812	1590	0.0131	-	-
2.5893	1595	0.0178	-	-
2.5974	1600	0.0172	-	-
2.6055	1605	0.0065	-	-
2.6136	1610	0.0147	-	-
2.6218	1615	0.0266	-	-
2.6299	1620	0.0134	-	-
2.6380	1625	0.0213	-	-
2.6461	1630	0.0184	-	-
2.6542	1635	0.0221	-	-
2.6623	1640	0.0088	-	-
2.6705	1645	0.0172	-	-
2.6786	1650	0.0094	-	-
2.6867	1655	0.0109	-	-
2.6948	1660	0.0114	-	-
2.7029	1665	0.0119	-	-
2.7110	1670	0.0119	-	-
2.7192	1675	0.0143	-	-
2.7273	1680	0.0124	-	-
2.7354	1685	0.0184	-	-
2.7435	1690	0.0204	-	-
2.7516	1695	0.0091	-	-
2.7597	1700	0.0118	-	-
2.7679	1705	0.0115	-	-
2.7760	1710	0.0203	-	-
2.7841	1715	0.0102	-	-
2.7922	1720	0.0159	-	-
2.8003	1725	0.014	-	-
2.8084	1730	0.0244	-	-
2.8166	1735	0.0208	-	-
2.8247	1740	0.0158	-	-
2.8328	1745	0.0156	-	-
2.8409	1750	0.008	-	-
2.8490	1755	0.0142	-	-
2.8571	1760	0.014	-	-
2.8653	1765	0.0136	-	-
2.8734	1770	0.0194	-	-
2.8815	1775	0.018	-	-
2.8896	1780	0.0159	-	-
2.8977	1785	0.0202	-	-
2.9058	1790	0.0103	-	-
2.9140	1795	0.0134	-	-
2.9221	1800	0.0194	-	-
2.9302	1805	0.0168	-	-
2.9383	1810	0.0162	-	-
2.9464	1815	0.0233	-	-
2.9545	1820	0.0146	-	-
2.9627	1825	0.0151	-	-
2.9708	1830	0.0256	-	-
2.9789	1835	0.0243	-	-
2.9870	1840	0.0126	-	-
2.9951	1845	0.0186	-	-
3.0032	1850	0.0202	-	-
3.0114	1855	0.0071	-	-
3.0195	1860	0.0037	-	-
3.0276	1865	0.0029	-	-
3.0357	1870	0.0063	-	-
3.0438	1875	0.0085	-	-
3.0519	1880	0.0112	-	-
3.0601	1885	0.0151	-	-
3.0682	1890	0.0099	-	-
3.0763	1895	0.0108	-	-
3.0844	1900	0.0107	-	-
3.0925	1905	0.0025	-	-
3.1006	1910	0.0159	-	-
3.1088	1915	0.0038	-	-
3.1169	1920	0.0104	-	-
3.125	1925	0.0118	-	-
3.1331	1930	0.0086	-	-
3.1412	1935	0.0054	-	-
3.1494	1940	0.0138	-	-
3.1575	1945	0.0111	-	-
3.1656	1950	0.0143	-	-
3.1737	1955	0.0082	-	-
3.1818	1960	0.0122	-	-
3.1899	1965	0.0063	-	-
3.1981	1970	0.0124	-	-
3.2062	1975	0.0113	-	-
3.2143	1980	0.0091	0.025	0.8476
3.2224	1985	0.0077	-	-
3.2305	1990	0.0058	-	-
3.2386	1995	0.0087	-	-
3.2468	2000	0.0042	-	-
3.2549	2005	0.0149	-	-
3.2630	2010	0.0071	-	-
3.2711	2015	0.0121	-	-
3.2792	2020	0.0128	-	-
3.2873	2025	0.0088	-	-
3.2955	2030	0.0114	-	-
3.3036	2035	0.0097	-	-
3.3117	2040	0.0139	-	-
3.3198	2045	0.0074	-	-
3.3279	2050	0.0065	-	-
3.3360	2055	0.0146	-	-
3.3442	2060	0.0088	-	-
3.3523	2065	0.0032	-	-
3.3604	2070	0.0176	-	-
3.3685	2075	0.0129	-	-
3.3766	2080	0.0092	-	-
3.3847	2085	0.0068	-	-
3.3929	2090	0.0099	-	-
3.4010	2095	0.01	-	-
3.4091	2100	0.0082	-	-
3.4172	2105	0.0086	-	-
3.4253	2110	0.0036	-	-
3.4334	2115	0.0169	-	-
3.4416	2120	0.003	-	-
3.4497	2125	0.0055	-	-
3.4578	2130	0.0114	-	-
3.4659	2135	0.0099	-	-
3.4740	2140	0.0139	-	-
3.4821	2145	0.008	-	-
3.4903	2150	0.0094	-	-
3.4984	2155	0.0096	-	-
3.5065	2160	0.0069	-	-
3.5146	2165	0.0035	-	-
3.5227	2170	0.008	-	-
3.5308	2175	0.0071	-	-
3.5390	2180	0.0067	-	-
3.5471	2185	0.0181	-	-
3.5552	2190	0.0062	-	-
3.5633	2195	0.0086	-	-
3.5714	2200	0.0037	-	-
3.5795	2205	0.0103	-	-
3.5877	2210	0.0032	-	-
3.5958	2215	0.004	-	-
3.6039	2220	0.0032	-	-
3.6120	2225	0.0051	-	-
3.6201	2230	0.0068	-	-
3.6282	2235	0.0171	-	-
3.6364	2240	0.0094	-	-
3.6445	2245	0.0039	-	-
3.6526	2250	0.0088	-	-
3.6607	2255	0.0021	-	-
3.6688	2260	0.0174	-	-
3.6769	2265	0.0108	-	-
3.6851	2270	0.0071	-	-
3.6932	2275	0.0189	-	-
3.7013	2280	0.0027	-	-
3.7094	2285	0.0086	-	-
3.7175	2290	0.0089	-	-
3.7256	2295	0.0195	-	-
3.7338	2300	0.0032	-	-
3.7419	2305	0.0153	-	-
3.75	2310	0.0115	-	-
3.7581	2315	0.0041	-	-
3.7662	2320	0.0095	-	-
3.7744	2325	0.0067	-	-
3.7825	2330	0.0102	-	-
3.7906	2335	0.0056	-	-
3.7987	2340	0.0076	-	-
3.8068	2345	0.0143	-	-
3.8149	2350	0.0104	-	-
3.8231	2355	0.0162	-	-
3.8312	2360	0.0109	-	-
3.8393	2365	0.0098	-	-
3.8474	2370	0.0081	-	-
3.8555	2375	0.0149	-	-
3.8636	2380	0.0088	-	-
3.8718	2385	0.0166	-	-
3.8799	2390	0.0087	-	-
3.8880	2395	0.0108	-	-
3.8961	2400	0.0051	-	-
3.9042	2405	0.0081	-	-
3.9123	2410	0.0055	-	-
3.9205	2415	0.0069	-	-
3.9286	2420	0.0059	-	-
3.9367	2425	0.0145	-	-
3.9448	2430	0.005	-	-
3.9529	2435	0.0091	-	-
3.9610	2440	0.0071	-	-
3.9692	2445	0.0157	-	-
3.9773	2450	0.0039	-	-
3.9854	2455	0.0089	-	-
3.9935	2460	0.0061	-	-

• 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",
}