SenhorDasMoscas/acho-ptbr-e4-lr3e-05-29-12-2024

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-05-29-12-2024")
# Run inference
sentences = [
    'circulo mdf decorar',
    'decoracao festa',
    '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	0.9114
spearman_cosine	0.8357

Training Details

Training Dataset

Unnamed Dataset

• Size: 17,147 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: 7.53 tokens max: 18 tokens	min: 3 tokens mean: 6.34 tokens max: 11 tokens	min: 0.1 mean: 0.56 max: 1.0

• Samples:

  text1	text2	label
  batedor manual massa	livro material literario	0.1
  procuro cerveja Chimay	bebida alcoolico	1.0
  livro ficcao cientifico	item colecao	0.1

• Loss: CosineSimilarityLoss with these parameters:

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

Evaluation Dataset

Unnamed Dataset

• Size: 1,906 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: 7.58 tokens max: 16 tokens	min: 3 tokens mean: 6.35 tokens max: 11 tokens	min: 0.1 mean: 0.55 max: 1.0

• Samples:

  text1	text2	label
  alugar barco passeio	servico area educacao	0.1
  pneu Michelin Primacy 4 195/55r15	peca acessorio automotivo	1.0
  querer heineken bem gelado	bebida alcoolico	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: 3e-05
• weight_decay: 0.1
• num_train_epochs: 4
• warmup_ratio: 0.1
• warmup_steps: 214
• 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: 214
• 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
0.0093	5	0.2225	-	-
0.0187	10	0.2123	-	-
0.0280	15	0.2135	-	-
0.0373	20	0.2118	-	-
0.0466	25	0.1799	-	-
0.0560	30	0.1873	-	-
0.0653	35	0.1685	-	-
0.0746	40	0.1646	-	-
0.0840	45	0.1619	-	-
0.0933	50	0.1451	-	-
0.1026	55	0.1444	-	-
0.1119	60	0.1492	-	-
0.1213	65	0.1262	-	-
0.1306	70	0.1213	-	-
0.1399	75	0.112	-	-
0.1493	80	0.1119	-	-
0.1586	85	0.0931	-	-
0.1679	90	0.0962	-	-
0.1772	95	0.1061	-	-
0.1866	100	0.0912	-	-
0.1959	105	0.0738	-	-
0.2052	110	0.0899	-	-
0.2146	115	0.075	-	-
0.2239	120	0.0757	-	-
0.2332	125	0.0734	-	-
0.2425	130	0.0652	-	-
0.2519	135	0.0676	-	-
0.2612	140	0.071	-	-
0.2705	145	0.0685	-	-
0.2799	150	0.0813	-	-
0.2892	155	0.0764	-	-
0.2985	160	0.085	-	-
0.3078	165	0.0701	-	-
0.3172	170	0.0509	-	-
0.3265	175	0.0719	-	-
0.3358	180	0.0671	-	-
0.3451	185	0.0599	-	-
0.3545	190	0.0691	-	-
0.3638	195	0.0839	-	-
0.3731	200	0.0713	-	-
0.3825	205	0.0681	-	-
0.3918	210	0.0487	-	-
0.4011	215	0.0596	-	-
0.4104	220	0.0554	-	-
0.4198	225	0.07	-	-
0.4291	230	0.0648	-	-
0.4384	235	0.0637	-	-
0.4478	240	0.0412	-	-
0.4571	245	0.0705	-	-
0.4664	250	0.0642	-	-
0.4757	255	0.051	-	-
0.4851	260	0.0662	-	-
0.4944	265	0.0733	-	-
0.5037	270	0.0755	-	-
0.5131	275	0.0478	-	-
0.5224	280	0.0518	-	-
0.5317	285	0.0578	-	-
0.5410	290	0.0586	-	-
0.5504	295	0.0675	-	-
0.5597	300	0.057	0.0561	0.8090
0.5690	305	0.0631	-	-
0.5784	310	0.0702	-	-
0.5877	315	0.0538	-	-
0.5970	320	0.0546	-	-
0.6063	325	0.0435	-	-
0.6157	330	0.0544	-	-
0.625	335	0.0424	-	-
0.6343	340	0.0398	-	-
0.6437	345	0.0452	-	-
0.6530	350	0.052	-	-
0.6623	355	0.0418	-	-
0.6716	360	0.0439	-	-
0.6810	365	0.0531	-	-
0.6903	370	0.0612	-	-
0.6996	375	0.0452	-	-
0.7090	380	0.049	-	-
0.7183	385	0.0491	-	-
0.7276	390	0.0508	-	-
0.7369	395	0.066	-	-
0.7463	400	0.0465	-	-
0.7556	405	0.042	-	-
0.7649	410	0.0573	-	-
0.7743	415	0.0646	-	-
0.7836	420	0.0472	-	-
0.7929	425	0.0523	-	-
0.8022	430	0.0569	-	-
0.8116	435	0.0621	-	-
0.8209	440	0.0611	-	-
0.8302	445	0.0404	-	-
0.8396	450	0.0426	-	-
0.8489	455	0.0501	-	-
0.8582	460	0.0586	-	-
0.8675	465	0.054	-	-
0.8769	470	0.0558	-	-
0.8862	475	0.0728	-	-
0.8955	480	0.0426	-	-
0.9049	485	0.0269	-	-
0.9142	490	0.0446	-	-
0.9235	495	0.0603	-	-
0.9328	500	0.0515	-	-
0.9422	505	0.0359	-	-
0.9515	510	0.0469	-	-
0.9608	515	0.0528	-	-
0.9701	520	0.0462	-	-
0.9795	525	0.0383	-	-
0.9888	530	0.0413	-	-
0.9981	535	0.0626	-	-
1.0075	540	0.0474	-	-
1.0168	545	0.0421	-	-
1.0261	550	0.0352	-	-
1.0354	555	0.0394	-	-
1.0448	560	0.0437	-	-
1.0541	565	0.0299	-	-
1.0634	570	0.0283	-	-
1.0728	575	0.0343	-	-
1.0821	580	0.0396	-	-
1.0914	585	0.0329	-	-
1.1007	590	0.0265	-	-
1.1101	595	0.0507	-	-
1.1194	600	0.0496	0.0432	0.8319
1.1287	605	0.0211	-	-
1.1381	610	0.0266	-	-
1.1474	615	0.0312	-	-
1.1567	620	0.0312	-	-
1.1660	625	0.0265	-	-
1.1754	630	0.0395	-	-
1.1847	635	0.0384	-	-
1.1940	640	0.03	-	-
1.2034	645	0.0293	-	-
1.2127	650	0.0161	-	-
1.2220	655	0.0365	-	-
1.2313	660	0.0377	-	-
1.2407	665	0.0346	-	-
1.25	670	0.0478	-	-
1.2593	675	0.0401	-	-
1.2687	680	0.0523	-	-
1.2780	685	0.0347	-	-
1.2873	690	0.0421	-	-
1.2966	695	0.0281	-	-
1.3060	700	0.0277	-	-
1.3153	705	0.0317	-	-
1.3246	710	0.0504	-	-
1.3340	715	0.0344	-	-
1.3433	720	0.0371	-	-
1.3526	725	0.0406	-	-
1.3619	730	0.0346	-	-
1.3713	735	0.0376	-	-
1.3806	740	0.0416	-	-
1.3899	745	0.0453	-	-
1.3993	750	0.0529	-	-
1.4086	755	0.0398	-	-
1.4179	760	0.0328	-	-
1.4272	765	0.0362	-	-
1.4366	770	0.047	-	-
1.4459	775	0.0408	-	-
1.4552	780	0.0294	-	-
1.4646	785	0.0533	-	-
1.4739	790	0.0495	-	-
1.4832	795	0.0314	-	-
1.4925	800	0.0349	-	-
1.5019	805	0.0355	-	-
1.5112	810	0.0539	-	-
1.5205	815	0.0518	-	-
1.5299	820	0.0192	-	-
1.5392	825	0.0364	-	-
1.5485	830	0.0376	-	-
1.5578	835	0.0405	-	-
1.5672	840	0.0258	-	-
1.5765	845	0.0216	-	-
1.5858	850	0.0313	-	-
1.5951	855	0.028	-	-
1.6045	860	0.0339	-	-
1.6138	865	0.033	-	-
1.6231	870	0.0466	-	-
1.6325	875	0.024	-	-
1.6418	880	0.0214	-	-
1.6511	885	0.0371	-	-
1.6604	890	0.0282	-	-
1.6698	895	0.0498	-	-
1.6791	900	0.0185	0.0407	0.8339
1.6884	905	0.0271	-	-
1.6978	910	0.0186	-	-
1.7071	915	0.029	-	-
1.7164	920	0.0442	-	-
1.7257	925	0.0314	-	-
1.7351	930	0.0446	-	-
1.7444	935	0.019	-	-
1.7537	940	0.0477	-	-
1.7631	945	0.0251	-	-
1.7724	950	0.0319	-	-
1.7817	955	0.0295	-	-
1.7910	960	0.0342	-	-
1.8004	965	0.0352	-	-
1.8097	970	0.032	-	-
1.8190	975	0.0221	-	-
1.8284	980	0.0424	-	-
1.8377	985	0.0406	-	-
1.8470	990	0.0354	-	-
1.8563	995	0.0419	-	-
1.8657	1000	0.0456	-	-
1.875	1005	0.0302	-	-
1.8843	1010	0.024	-	-
1.8937	1015	0.0372	-	-
1.9030	1020	0.0133	-	-
1.9123	1025	0.0349	-	-
1.9216	1030	0.0252	-	-
1.9310	1035	0.0272	-	-
1.9403	1040	0.0417	-	-
1.9496	1045	0.043	-	-
1.9590	1050	0.0342	-	-
1.9683	1055	0.0276	-	-
1.9776	1060	0.0307	-	-
1.9869	1065	0.0461	-	-
1.9963	1070	0.0422	-	-
2.0056	1075	0.0355	-	-
2.0149	1080	0.0241	-	-
2.0243	1085	0.0222	-	-
2.0336	1090	0.0203	-	-
2.0429	1095	0.0227	-	-
2.0522	1100	0.0162	-	-
2.0616	1105	0.0262	-	-
2.0709	1110	0.0102	-	-
2.0802	1115	0.0181	-	-
2.0896	1120	0.028	-	-
2.0989	1125	0.0239	-	-
2.1082	1130	0.0262	-	-
2.1175	1135	0.0323	-	-
2.1269	1140	0.0268	-	-
2.1362	1145	0.0247	-	-
2.1455	1150	0.0182	-	-
2.1549	1155	0.019	-	-
2.1642	1160	0.0144	-	-
2.1735	1165	0.0289	-	-
2.1828	1170	0.0236	-	-
2.1922	1175	0.0165	-	-
2.2015	1180	0.0112	-	-
2.2108	1185	0.0281	-	-
2.2201	1190	0.0286	-	-
2.2295	1195	0.0234	-	-
2.2388	1200	0.022	0.0390	0.8324
2.2481	1205	0.0217	-	-
2.2575	1210	0.0223	-	-
2.2668	1215	0.027	-	-
2.2761	1220	0.0429	-	-
2.2854	1225	0.0204	-	-
2.2948	1230	0.0421	-	-
2.3041	1235	0.0109	-	-
2.3134	1240	0.0262	-	-
2.3228	1245	0.013	-	-
2.3321	1250	0.0143	-	-
2.3414	1255	0.0291	-	-
2.3507	1260	0.0364	-	-
2.3601	1265	0.0169	-	-
2.3694	1270	0.0211	-	-
2.3787	1275	0.0304	-	-
2.3881	1280	0.0147	-	-
2.3974	1285	0.0295	-	-
2.4067	1290	0.0362	-	-
2.4160	1295	0.0185	-	-
2.4254	1300	0.0166	-	-
2.4347	1305	0.0119	-	-
2.4440	1310	0.0211	-	-
2.4534	1315	0.0208	-	-
2.4627	1320	0.0135	-	-
2.4720	1325	0.0321	-	-
2.4813	1330	0.0229	-	-
2.4907	1335	0.0198	-	-
2.5	1340	0.028	-	-
2.5093	1345	0.0179	-	-
2.5187	1350	0.0187	-	-
2.5280	1355	0.0309	-	-
2.5373	1360	0.0286	-	-
2.5466	1365	0.0349	-	-
2.5560	1370	0.0247	-	-
2.5653	1375	0.0223	-	-
2.5746	1380	0.0292	-	-
2.5840	1385	0.0152	-	-
2.5933	1390	0.0128	-	-
2.6026	1395	0.0256	-	-
2.6119	1400	0.017	-	-
2.6213	1405	0.028	-	-
2.6306	1410	0.0228	-	-
2.6399	1415	0.023	-	-
2.6493	1420	0.0311	-	-
2.6586	1425	0.0231	-	-
2.6679	1430	0.025	-	-
2.6772	1435	0.0188	-	-
2.6866	1440	0.0315	-	-
2.6959	1445	0.0156	-	-
2.7052	1450	0.0352	-	-
2.7146	1455	0.0224	-	-
2.7239	1460	0.0269	-	-
2.7332	1465	0.0217	-	-
2.7425	1470	0.0222	-	-
2.7519	1475	0.0298	-	-
2.7612	1480	0.0182	-	-
2.7705	1485	0.0181	-	-
2.7799	1490	0.0283	-	-
2.7892	1495	0.0238	-	-
2.7985	1500	0.0215	0.0366	0.8337
2.8078	1505	0.025	-	-
2.8172	1510	0.0207	-	-
2.8265	1515	0.0217	-	-
2.8358	1520	0.0193	-	-
2.8451	1525	0.0123	-	-
2.8545	1530	0.0153	-	-
2.8638	1535	0.0161	-	-
2.8731	1540	0.0234	-	-
2.8825	1545	0.0255	-	-
2.8918	1550	0.0291	-	-
2.9011	1555	0.0229	-	-
2.9104	1560	0.0299	-	-
2.9198	1565	0.0183	-	-
2.9291	1570	0.0245	-	-
2.9384	1575	0.0188	-	-
2.9478	1580	0.0115	-	-
2.9571	1585	0.0284	-	-
2.9664	1590	0.0294	-	-
2.9757	1595	0.0197	-	-
2.9851	1600	0.0313	-	-
2.9944	1605	0.0257	-	-
3.0037	1610	0.0115	-	-
3.0131	1615	0.0193	-	-
3.0224	1620	0.0125	-	-
3.0317	1625	0.0155	-	-
3.0410	1630	0.0258	-	-
3.0504	1635	0.0112	-	-
3.0597	1640	0.0148	-	-
3.0690	1645	0.0095	-	-
3.0784	1650	0.0143	-	-
3.0877	1655	0.0165	-	-
3.0970	1660	0.019	-	-
3.1063	1665	0.0154	-	-
3.1157	1670	0.0094	-	-
3.125	1675	0.0156	-	-
3.1343	1680	0.0161	-	-
3.1437	1685	0.017	-	-
3.1530	1690	0.0249	-	-
3.1623	1695	0.0259	-	-
3.1716	1700	0.0167	-	-
3.1810	1705	0.0166	-	-
3.1903	1710	0.02	-	-
3.1996	1715	0.018	-	-
3.2090	1720	0.0105	-	-
3.2183	1725	0.0178	-	-
3.2276	1730	0.0173	-	-
3.2369	1735	0.0169	-	-
3.2463	1740	0.0156	-	-
3.2556	1745	0.0151	-	-
3.2649	1750	0.0083	-	-
3.2743	1755	0.0115	-	-
3.2836	1760	0.0167	-	-
3.2929	1765	0.0159	-	-
3.3022	1770	0.0156	-	-
3.3116	1775	0.0203	-	-
3.3209	1780	0.0178	-	-
3.3302	1785	0.0113	-	-
3.3396	1790	0.0084	-	-
3.3489	1795	0.015	-	-
3.3582	1800	0.0142	0.0353	0.8366
3.3675	1805	0.0088	-	-
3.3769	1810	0.0102	-	-
3.3862	1815	0.0197	-	-
3.3955	1820	0.0191	-	-
3.4049	1825	0.0182	-	-
3.4142	1830	0.0225	-	-
3.4235	1835	0.0241	-	-
3.4328	1840	0.0302	-	-
3.4422	1845	0.0174	-	-
3.4515	1850	0.0171	-	-
3.4608	1855	0.0114	-	-
3.4701	1860	0.0086	-	-
3.4795	1865	0.0144	-	-
3.4888	1870	0.0151	-	-
3.4981	1875	0.0139	-	-
3.5075	1880	0.0103	-	-
3.5168	1885	0.0171	-	-
3.5261	1890	0.0086	-	-
3.5354	1895	0.0234	-	-
3.5448	1900	0.008	-	-
3.5541	1905	0.0098	-	-
3.5634	1910	0.0159	-	-
3.5728	1915	0.0204	-	-
3.5821	1920	0.0152	-	-
3.5914	1925	0.0183	-	-
3.6007	1930	0.0169	-	-
3.6101	1935	0.0135	-	-
3.6194	1940	0.0191	-	-
3.6287	1945	0.0217	-	-
3.6381	1950	0.0152	-	-
3.6474	1955	0.0104	-	-
3.6567	1960	0.0203	-	-
3.6660	1965	0.0098	-	-
3.6754	1970	0.0217	-	-
3.6847	1975	0.0192	-	-
3.6940	1980	0.0138	-	-
3.7034	1985	0.0239	-	-
3.7127	1990	0.0237	-	-
3.7220	1995	0.011	-	-
3.7313	2000	0.0161	-	-
3.7407	2005	0.016	-	-
3.75	2010	0.0118	-	-
3.7593	2015	0.0124	-	-
3.7687	2020	0.0152	-	-
3.7780	2025	0.0171	-	-
3.7873	2030	0.018	-	-
3.7966	2035	0.0131	-	-
3.8060	2040	0.0178	-	-
3.8153	2045	0.0251	-	-
3.8246	2050	0.0124	-	-
3.8340	2055	0.0189	-	-
3.8433	2060	0.0244	-	-
3.8526	2065	0.0169	-	-
3.8619	2070	0.0184	-	-
3.8713	2075	0.019	-	-
3.8806	2080	0.0104	-	-
3.8899	2085	0.0266	-	-
3.8993	2090	0.0136	-	-
3.9086	2095	0.0129	-	-
3.9179	2100	0.0103	0.0353	0.8357
3.9272	2105	0.0085	-	-
3.9366	2110	0.0262	-	-
3.9459	2115	0.0198	-	-
3.9552	2120	0.0069	-	-
3.9646	2125	0.0139	-	-
3.9739	2130	0.014	-	-
3.9832	2135	0.0197	-	-
3.9925	2140	0.0146	-	-

• 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",
}