SenhorDasMoscas/acho-ptbr-e4-lr3e-05-30-12-2024

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-lr3e-05-30-12-2024")
# Run inference
sentences = [
    'cafe moido gourmet',
    'comida rapido fastfood',
    'bebida alcoolico',
]
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	0.9023
spearman_cosine	0.8365

Training Details

Training Dataset

Unnamed Dataset

• Size: 17,687 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: 7.51 tokens max: 15 tokens	min: 3 tokens mean: 6.42 tokens max: 11 tokens	min: 0.1 mean: 0.55 max: 1.0

• Samples:

  text1	text2	label
  carrinho brinquedo virar robo	brinquedo jogo educativo	1.0
  cuecar boxer sensual	item adulto brinquedo sexual	1.0
  alicate	peixaria pescado	0.1

• Loss: CosineSimilarityLoss with these parameters:

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

Evaluation Dataset

Unnamed Dataset

• Size: 1,966 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: 7.59 tokens max: 17 tokens	min: 3 tokens mean: 6.47 tokens max: 11 tokens	min: 0.1 mean: 0.56 max: 1.0

• Samples:

  text1	text2	label
  balanco crianca	item adulto brinquedo sexual	0.1
  onde comprar Chaves fenda festa	decoracao festa	0.1
  querer monitor ultrawide	padaria confeitaria	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: 4
• warmup_ratio: 0.1
• warmup_steps: 220
• 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: 4
• max_steps: -1
• lr_scheduler_type: linear
• lr_scheduler_kwargs: {}
• warmup_ratio: 0.1
• warmup_steps: 220
• 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
0.0090	5	0.2027	-	-
0.0181	10	0.2312	-	-
0.0271	15	0.2105	-	-
0.0362	20	0.2046	-	-
0.0452	25	0.1887	-	-
0.0542	30	0.1768	-	-
0.0633	35	0.1691	-	-
0.0723	40	0.1604	-	-
0.0814	45	0.1602	-	-
0.0904	50	0.1578	-	-
0.0995	55	0.1386	-	-
0.1085	60	0.144	-	-
0.1175	65	0.1238	-	-
0.1266	70	0.1155	-	-
0.1356	75	0.1156	-	-
0.1447	80	0.0948	-	-
0.1537	85	0.0999	-	-
0.1627	90	0.083	-	-
0.1718	95	0.0848	-	-
0.1808	100	0.0947	-	-
0.1899	105	0.0721	-	-
0.1989	110	0.0747	-	-
0.2080	115	0.1082	-	-
0.2170	120	0.0836	-	-
0.2260	125	0.0793	-	-
0.2351	130	0.0746	-	-
0.2441	135	0.063	-	-
0.2532	140	0.0678	-	-
0.2622	145	0.0708	-	-
0.2712	150	0.0734	-	-
0.2803	155	0.0668	-	-
0.2893	160	0.0626	-	-
0.2984	165	0.0625	-	-
0.3074	170	0.0654	-	-
0.3165	175	0.0686	-	-
0.3255	180	0.0576	-	-
0.3345	185	0.0612	-	-
0.3436	190	0.0522	-	-
0.3526	195	0.0607	-	-
0.3617	200	0.0538	-	-
0.3707	205	0.0663	-	-
0.3797	210	0.0577	-	-
0.3888	215	0.0681	-	-
0.3978	220	0.0712	-	-
0.4069	225	0.0481	-	-
0.4159	230	0.0632	-	-
0.4250	235	0.0597	-	-
0.4340	240	0.0681	-	-
0.4430	245	0.0617	-	-
0.4521	250	0.0715	-	-
0.4611	255	0.0574	-	-
0.4702	260	0.0467	-	-
0.4792	265	0.0521	-	-
0.4882	270	0.0632	-	-
0.4973	275	0.0693	-	-
0.5063	280	0.0605	-	-
0.5154	285	0.0506	-	-
0.5244	290	0.0448	-	-
0.5335	295	0.0565	-	-
0.5425	300	0.0669	0.0522	0.8167
0.5515	305	0.0679	-	-
0.5606	310	0.0582	-	-
0.5696	315	0.0483	-	-
0.5787	320	0.0629	-	-
0.5877	325	0.0555	-	-
0.5967	330	0.0437	-	-
0.6058	335	0.0448	-	-
0.6148	340	0.0338	-	-
0.6239	345	0.0583	-	-
0.6329	350	0.0555	-	-
0.6420	355	0.0478	-	-
0.6510	360	0.0611	-	-
0.6600	365	0.064	-	-
0.6691	370	0.0646	-	-
0.6781	375	0.0516	-	-
0.6872	380	0.0565	-	-
0.6962	385	0.0573	-	-
0.7052	390	0.0529	-	-
0.7143	395	0.0488	-	-
0.7233	400	0.0589	-	-
0.7324	405	0.0555	-	-
0.7414	410	0.0633	-	-
0.7505	415	0.0413	-	-
0.7595	420	0.0581	-	-
0.7685	425	0.0477	-	-
0.7776	430	0.0445	-	-
0.7866	435	0.0379	-	-
0.7957	440	0.0393	-	-
0.8047	445	0.0393	-	-
0.8137	450	0.0619	-	-
0.8228	455	0.0591	-	-
0.8318	460	0.0495	-	-
0.8409	465	0.0348	-	-
0.8499	470	0.0352	-	-
0.8590	475	0.0462	-	-
0.8680	480	0.0463	-	-
0.8770	485	0.0772	-	-
0.8861	490	0.0396	-	-
0.8951	495	0.0548	-	-
0.9042	500	0.042	-	-
0.9132	505	0.0564	-	-
0.9222	510	0.0441	-	-
0.9313	515	0.0358	-	-
0.9403	520	0.0669	-	-
0.9494	525	0.0339	-	-
0.9584	530	0.0327	-	-
0.9675	535	0.058	-	-
0.9765	540	0.0476	-	-
0.9855	545	0.0482	-	-
0.9946	550	0.0411	-	-
1.0036	555	0.0527	-	-
1.0127	560	0.0315	-	-
1.0217	565	0.0355	-	-
1.0307	570	0.033	-	-
1.0398	575	0.037	-	-
1.0488	580	0.0391	-	-
1.0579	585	0.0456	-	-
1.0669	590	0.0363	-	-
1.0759	595	0.0261	-	-
1.0850	600	0.0348	0.0458	0.8274
1.0940	605	0.0403	-	-
1.1031	610	0.0476	-	-
1.1121	615	0.0269	-	-
1.1212	620	0.0277	-	-
1.1302	625	0.045	-	-
1.1392	630	0.0493	-	-
1.1483	635	0.0175	-	-
1.1573	640	0.0404	-	-
1.1664	645	0.0365	-	-
1.1754	650	0.0253	-	-
1.1844	655	0.0444	-	-
1.1935	660	0.0333	-	-
1.2025	665	0.0393	-	-
1.2116	670	0.0217	-	-
1.2206	675	0.0265	-	-
1.2297	680	0.032	-	-
1.2387	685	0.0387	-	-
1.2477	690	0.0351	-	-
1.2568	695	0.0268	-	-
1.2658	700	0.0405	-	-
1.2749	705	0.0268	-	-
1.2839	710	0.0298	-	-
1.2929	715	0.0409	-	-
1.3020	720	0.0293	-	-
1.3110	725	0.0298	-	-
1.3201	730	0.0222	-	-
1.3291	735	0.0256	-	-
1.3382	740	0.0392	-	-
1.3472	745	0.0459	-	-
1.3562	750	0.0234	-	-
1.3653	755	0.0267	-	-
1.3743	760	0.0296	-	-
1.3834	765	0.0212	-	-
1.3924	770	0.0239	-	-
1.4014	775	0.0378	-	-
1.4105	780	0.0403	-	-
1.4195	785	0.0331	-	-
1.4286	790	0.0194	-	-
1.4376	795	0.0287	-	-
1.4467	800	0.0359	-	-
1.4557	805	0.0236	-	-
1.4647	810	0.0253	-	-
1.4738	815	0.0327	-	-
1.4828	820	0.0398	-	-
1.4919	825	0.0188	-	-
1.5009	830	0.0359	-	-
1.5099	835	0.0451	-	-
1.5190	840	0.036	-	-
1.5280	845	0.0502	-	-
1.5371	850	0.0285	-	-
1.5461	855	0.038	-	-
1.5552	860	0.0239	-	-
1.5642	865	0.0339	-	-
1.5732	870	0.0342	-	-
1.5823	875	0.0282	-	-
1.5913	880	0.0252	-	-
1.6004	885	0.0213	-	-
1.6094	890	0.0268	-	-
1.6184	895	0.0337	-	-
1.6275	900	0.0567	0.0436	0.8243
1.6365	905	0.0249	-	-
1.6456	910	0.0342	-	-
1.6546	915	0.0358	-	-
1.6637	920	0.0495	-	-
1.6727	925	0.0351	-	-
1.6817	930	0.0357	-	-
1.6908	935	0.0442	-	-
1.6998	940	0.0236	-	-
1.7089	945	0.02	-	-
1.7179	950	0.0516	-	-
1.7269	955	0.0304	-	-
1.7360	960	0.0343	-	-
1.7450	965	0.0261	-	-
1.7541	970	0.0304	-	-
1.7631	975	0.0266	-	-
1.7722	980	0.0306	-	-
1.7812	985	0.0274	-	-
1.7902	990	0.0427	-	-
1.7993	995	0.0391	-	-
1.8083	1000	0.0435	-	-
1.8174	1005	0.0371	-	-
1.8264	1010	0.0357	-	-
1.8354	1015	0.031	-	-
1.8445	1020	0.0338	-	-
1.8535	1025	0.0372	-	-
1.8626	1030	0.0496	-	-
1.8716	1035	0.0223	-	-
1.8807	1040	0.034	-	-
1.8897	1045	0.0276	-	-
1.8987	1050	0.0273	-	-
1.9078	1055	0.0345	-	-
1.9168	1060	0.0374	-	-
1.9259	1065	0.0276	-	-
1.9349	1070	0.0399	-	-
1.9439	1075	0.0251	-	-
1.9530	1080	0.0329	-	-
1.9620	1085	0.0263	-	-
1.9711	1090	0.036	-	-
1.9801	1095	0.0325	-	-
1.9892	1100	0.0333	-	-
1.9982	1105	0.0287	-	-
2.0072	1110	0.0266	-	-
2.0163	1115	0.0186	-	-
2.0253	1120	0.0167	-	-
2.0344	1125	0.037	-	-
2.0434	1130	0.0294	-	-
2.0524	1135	0.0181	-	-
2.0615	1140	0.0196	-	-
2.0705	1145	0.0127	-	-
2.0796	1150	0.0261	-	-
2.0886	1155	0.0133	-	-
2.0976	1160	0.0233	-	-
2.1067	1165	0.0189	-	-
2.1157	1170	0.0266	-	-
2.1248	1175	0.0155	-	-
2.1338	1180	0.0327	-	-
2.1429	1185	0.0248	-	-
2.1519	1190	0.0222	-	-
2.1609	1195	0.0201	-	-
2.1700	1200	0.0186	0.0402	0.8352
2.1790	1205	0.0301	-	-
2.1881	1210	0.0141	-	-
2.1971	1215	0.0204	-	-
2.2061	1220	0.0213	-	-
2.2152	1225	0.01	-	-
2.2242	1230	0.0112	-	-
2.2333	1235	0.027	-	-
2.2423	1240	0.0215	-	-
2.2514	1245	0.028	-	-
2.2604	1250	0.024	-	-
2.2694	1255	0.0216	-	-
2.2785	1260	0.027	-	-
2.2875	1265	0.0206	-	-
2.2966	1270	0.0364	-	-
2.3056	1275	0.0266	-	-
2.3146	1280	0.0262	-	-
2.3237	1285	0.0194	-	-
2.3327	1290	0.0343	-	-
2.3418	1295	0.0123	-	-
2.3508	1300	0.0189	-	-
2.3599	1305	0.0233	-	-
2.3689	1310	0.0286	-	-
2.3779	1315	0.0228	-	-
2.3870	1320	0.0138	-	-
2.3960	1325	0.0317	-	-
2.4051	1330	0.0278	-	-
2.4141	1335	0.015	-	-
2.4231	1340	0.0293	-	-
2.4322	1345	0.0224	-	-
2.4412	1350	0.0174	-	-
2.4503	1355	0.0123	-	-
2.4593	1360	0.0293	-	-
2.4684	1365	0.0134	-	-
2.4774	1370	0.0217	-	-
2.4864	1375	0.0207	-	-
2.4955	1380	0.0352	-	-
2.5045	1385	0.0232	-	-
2.5136	1390	0.018	-	-
2.5226	1395	0.0373	-	-
2.5316	1400	0.0248	-	-
2.5407	1405	0.037	-	-
2.5497	1410	0.019	-	-
2.5588	1415	0.0212	-	-
2.5678	1420	0.0192	-	-
2.5769	1425	0.0209	-	-
2.5859	1430	0.0349	-	-
2.5949	1435	0.0134	-	-
2.6040	1440	0.0191	-	-
2.6130	1445	0.0125	-	-
2.6221	1450	0.0177	-	-
2.6311	1455	0.0277	-	-
2.6401	1460	0.0265	-	-
2.6492	1465	0.0363	-	-
2.6582	1470	0.0229	-	-
2.6673	1475	0.0291	-	-
2.6763	1480	0.0165	-	-
2.6854	1485	0.0229	-	-
2.6944	1490	0.0247	-	-
2.7034	1495	0.0139	-	-
2.7125	1500	0.0191	0.0397	0.8344
2.7215	1505	0.0172	-	-
2.7306	1510	0.0147	-	-
2.7396	1515	0.0238	-	-
2.7486	1520	0.0275	-	-
2.7577	1525	0.0274	-	-
2.7667	1530	0.0276	-	-
2.7758	1535	0.0178	-	-
2.7848	1540	0.0206	-	-
2.7939	1545	0.0107	-	-
2.8029	1550	0.0167	-	-
2.8119	1555	0.0188	-	-
2.8210	1560	0.0261	-	-
2.8300	1565	0.0177	-	-
2.8391	1570	0.0213	-	-
2.8481	1575	0.0291	-	-
2.8571	1580	0.0251	-	-
2.8662	1585	0.0303	-	-
2.8752	1590	0.0242	-	-
2.8843	1595	0.0217	-	-
2.8933	1600	0.0101	-	-
2.9024	1605	0.0218	-	-
2.9114	1610	0.0163	-	-
2.9204	1615	0.0149	-	-
2.9295	1620	0.0159	-	-
2.9385	1625	0.022	-	-
2.9476	1630	0.0242	-	-
2.9566	1635	0.017	-	-
2.9656	1640	0.0204	-	-
2.9747	1645	0.0176	-	-
2.9837	1650	0.0221	-	-
2.9928	1655	0.0265	-	-
3.0018	1660	0.0193	-	-
3.0108	1665	0.0172	-	-
3.0199	1670	0.016	-	-
3.0289	1675	0.0128	-	-
3.0380	1680	0.0205	-	-
3.0470	1685	0.0123	-	-
3.0561	1690	0.0111	-	-
3.0651	1695	0.0163	-	-
3.0741	1700	0.0283	-	-
3.0832	1705	0.0134	-	-
3.0922	1710	0.0169	-	-
3.1013	1715	0.0159	-	-
3.1103	1720	0.0153	-	-
3.1193	1725	0.0136	-	-
3.1284	1730	0.0093	-	-
3.1374	1735	0.0222	-	-
3.1465	1740	0.0156	-	-
3.1555	1745	0.0124	-	-
3.1646	1750	0.0145	-	-
3.1736	1755	0.0196	-	-
3.1826	1760	0.0125	-	-
3.1917	1765	0.0054	-	-
3.2007	1770	0.0174	-	-
3.2098	1775	0.0106	-	-
3.2188	1780	0.0127	-	-
3.2278	1785	0.01	-	-
3.2369	1790	0.0064	-	-
3.2459	1795	0.011	-	-
3.2550	1800	0.0162	0.0399	0.8343
3.2640	1805	0.0109	-	-
3.2731	1810	0.0202	-	-
3.2821	1815	0.0169	-	-
3.2911	1820	0.0121	-	-
3.3002	1825	0.0152	-	-
3.3092	1830	0.0255	-	-
3.3183	1835	0.0205	-	-
3.3273	1840	0.0137	-	-
3.3363	1845	0.0108	-	-
3.3454	1850	0.0195	-	-
3.3544	1855	0.028	-	-
3.3635	1860	0.0253	-	-
3.3725	1865	0.0177	-	-
3.3816	1870	0.0102	-	-
3.3906	1875	0.0114	-	-
3.3996	1880	0.01	-	-
3.4087	1885	0.0105	-	-
3.4177	1890	0.0123	-	-
3.4268	1895	0.0116	-	-
3.4358	1900	0.0157	-	-
3.4448	1905	0.0197	-	-
3.4539	1910	0.0172	-	-
3.4629	1915	0.011	-	-
3.4720	1920	0.0106	-	-
3.4810	1925	0.0199	-	-
3.4901	1930	0.0166	-	-
3.4991	1935	0.0284	-	-
3.5081	1940	0.0138	-	-
3.5172	1945	0.0252	-	-
3.5262	1950	0.017	-	-
3.5353	1955	0.0234	-	-
3.5443	1960	0.0173	-	-
3.5533	1965	0.0136	-	-
3.5624	1970	0.0184	-	-
3.5714	1975	0.0128	-	-
3.5805	1980	0.0162	-	-
3.5895	1985	0.0185	-	-
3.5986	1990	0.0201	-	-
3.6076	1995	0.018	-	-
3.6166	2000	0.0157	-	-
3.6257	2005	0.0208	-	-
3.6347	2010	0.0267	-	-
3.6438	2015	0.0121	-	-
3.6528	2020	0.0197	-	-
3.6618	2025	0.0141	-	-
3.6709	2030	0.0154	-	-
3.6799	2035	0.0049	-	-
3.6890	2040	0.0171	-	-
3.6980	2045	0.0087	-	-
3.7071	2050	0.0102	-	-
3.7161	2055	0.009	-	-
3.7251	2060	0.0171	-	-
3.7342	2065	0.0181	-	-
3.7432	2070	0.0144	-	-
3.7523	2075	0.0116	-	-
3.7613	2080	0.0175	-	-
3.7703	2085	0.0205	-	-
3.7794	2090	0.0153	-	-
3.7884	2095	0.0146	-	-
3.7975	2100	0.0155	0.0385	0.8365
3.8065	2105	0.0101	-	-
3.8156	2110	0.0101	-	-
3.8246	2115	0.0238	-	-
3.8336	2120	0.0087	-	-
3.8427	2125	0.0071	-	-
3.8517	2130	0.0192	-	-
3.8608	2135	0.013	-	-
3.8698	2140	0.0049	-	-
3.8788	2145	0.0119	-	-
3.8879	2150	0.0071	-	-
3.8969	2155	0.0126	-	-
3.9060	2160	0.0224	-	-
3.9150	2165	0.0117	-	-
3.9241	2170	0.0258	-	-
3.9331	2175	0.0191	-	-
3.9421	2180	0.0255	-	-
3.9512	2185	0.0076	-	-
3.9602	2190	0.0168	-	-
3.9693	2195	0.0138	-	-
3.9783	2200	0.0098	-	-
3.9873	2205	0.0217	-	-
3.9964	2210	0.0143	-	-

• 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",
}