SentenceTransformer based on sentence-transformers/paraphrase-MiniLM-L6-v2
This is a sentence-transformers model finetuned from sentence-transformers/paraphrase-MiniLM-L6-v2. It maps sentences & paragraphs to a 384-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/paraphrase-MiniLM-L6-v2
- Maximum Sequence Length: 128 tokens
- Output Dimensionality: 384 tokens
- 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': 128, 'do_lower_case': False}) with Transformer model: BertModel
(1): Pooling({'word_embedding_dimension': 384, '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("tomasravel/modelo_finetuneadoX3")
# Run inference
sentences = [
'buenos aires general pueyrredon mar del plata victorio tetamanti desde 1502 hasta 1600',
'general pueyrredon buenos aires mar del plata victorio tetamanti desde 1502 hasta 1600',
'buenos aires general pueyrredon mar del plata arana y goiri 13200',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 384]
# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)
# [3, 3]
Training Details
Training Dataset
Unnamed Dataset
- Size: 88,382 training samples
- Columns:
sentence_0
,sentence_1
, andlabel
- Approximate statistics based on the first 1000 samples:
sentence_0 sentence_1 label type string string float details - min: 4 tokens
- mean: 20.84 tokens
- max: 31 tokens
- min: 5 tokens
- mean: 19.48 tokens
- max: 30 tokens
- min: 0.2
- mean: 0.76
- max: 1.0
- Samples:
sentence_0 sentence_1 label capital federal ciudad autonoma buenos aires miralla desde 1501 hasta 1599
capital federal ciudad autonoma buenos aires miralla desde 1701 hasta 1799
0.8947368421052632
capital federal ciudad autonoma buenos aires holmberg desde 2502 hasta 2600
ciudad autonoma buenos aires capital federal holmberg desde 2502 hasta 2600
1.0
buenos aires avellaneda pieyro uruguay desde 201 hasta 299
buenos aires avellaneda villa vatteone uruguay desde 201 hasta 299
0.5
- Loss:
CoSENTLoss
with these parameters:{ "scale": 20.0, "similarity_fct": "pairwise_cos_sim" }
Training Hyperparameters
Non-Default Hyperparameters
per_device_train_batch_size
: 16per_device_eval_batch_size
: 16multi_dataset_batch_sampler
: round_robin
All Hyperparameters
Click to expand
overwrite_output_dir
: Falsedo_predict
: Falseeval_strategy
: noprediction_loss_only
: Trueper_device_train_batch_size
: 16per_device_eval_batch_size
: 16per_gpu_train_batch_size
: Noneper_gpu_eval_batch_size
: Nonegradient_accumulation_steps
: 1eval_accumulation_steps
: Nonetorch_empty_cache_steps
: Nonelearning_rate
: 5e-05weight_decay
: 0.0adam_beta1
: 0.9adam_beta2
: 0.999adam_epsilon
: 1e-08max_grad_norm
: 1num_train_epochs
: 3max_steps
: -1lr_scheduler_type
: linearlr_scheduler_kwargs
: {}warmup_ratio
: 0.0warmup_steps
: 0log_level
: passivelog_level_replica
: warninglog_on_each_node
: Truelogging_nan_inf_filter
: Truesave_safetensors
: Truesave_on_each_node
: Falsesave_only_model
: Falserestore_callback_states_from_checkpoint
: Falseno_cuda
: Falseuse_cpu
: Falseuse_mps_device
: Falseseed
: 42data_seed
: Nonejit_mode_eval
: Falseuse_ipex
: Falsebf16
: Falsefp16
: Falsefp16_opt_level
: O1half_precision_backend
: autobf16_full_eval
: Falsefp16_full_eval
: Falsetf32
: Nonelocal_rank
: 0ddp_backend
: Nonetpu_num_cores
: Nonetpu_metrics_debug
: Falsedebug
: []dataloader_drop_last
: Falsedataloader_num_workers
: 0dataloader_prefetch_factor
: Nonepast_index
: -1disable_tqdm
: Falseremove_unused_columns
: Truelabel_names
: Noneload_best_model_at_end
: Falseignore_data_skip
: Falsefsdp
: []fsdp_min_num_params
: 0fsdp_config
: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}fsdp_transformer_layer_cls_to_wrap
: Noneaccelerator_config
: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}deepspeed
: Nonelabel_smoothing_factor
: 0.0optim
: adamw_torchoptim_args
: Noneadafactor
: Falsegroup_by_length
: Falselength_column_name
: lengthddp_find_unused_parameters
: Noneddp_bucket_cap_mb
: Noneddp_broadcast_buffers
: Falsedataloader_pin_memory
: Truedataloader_persistent_workers
: Falseskip_memory_metrics
: Trueuse_legacy_prediction_loop
: Falsepush_to_hub
: Falseresume_from_checkpoint
: Nonehub_model_id
: Nonehub_strategy
: every_savehub_private_repo
: Falsehub_always_push
: Falsegradient_checkpointing
: Falsegradient_checkpointing_kwargs
: Noneinclude_inputs_for_metrics
: Falseeval_do_concat_batches
: Truefp16_backend
: autopush_to_hub_model_id
: Nonepush_to_hub_organization
: Nonemp_parameters
:auto_find_batch_size
: Falsefull_determinism
: Falsetorchdynamo
: Noneray_scope
: lastddp_timeout
: 1800torch_compile
: Falsetorch_compile_backend
: Nonetorch_compile_mode
: Nonedispatch_batches
: Nonesplit_batches
: Noneinclude_tokens_per_second
: Falseinclude_num_input_tokens_seen
: Falseneftune_noise_alpha
: Noneoptim_target_modules
: Nonebatch_eval_metrics
: Falseeval_on_start
: Falseeval_use_gather_object
: Falsebatch_sampler
: batch_samplermulti_dataset_batch_sampler
: round_robin
Training Logs
Epoch | Step | Training Loss |
---|---|---|
0.0905 | 500 | 4.2422 |
0.1810 | 1000 | 3.8113 |
0.2715 | 1500 | 3.6673 |
0.3621 | 2000 | 3.5338 |
0.4526 | 2500 | 3.4364 |
0.5431 | 3000 | 3.3542 |
0.6336 | 3500 | 3.3524 |
0.7241 | 4000 | 3.2701 |
0.8146 | 4500 | 3.2073 |
0.9051 | 5000 | 3.1503 |
0.9957 | 5500 | 3.1106 |
1.0862 | 6000 | 3.0974 |
1.1767 | 6500 | 3.0709 |
1.2672 | 7000 | 3.0324 |
1.3577 | 7500 | 2.9326 |
1.4482 | 8000 | 2.95 |
1.5387 | 8500 | 2.9143 |
1.6293 | 9000 | 2.9444 |
1.7198 | 9500 | 2.8928 |
1.8103 | 10000 | 2.8763 |
1.9008 | 10500 | 2.8199 |
1.9913 | 11000 | 2.8009 |
2.0818 | 11500 | 2.7721 |
2.1723 | 12000 | 2.7581 |
2.2629 | 12500 | 2.7454 |
2.3534 | 13000 | 2.7045 |
2.4439 | 13500 | 2.6874 |
2.5344 | 14000 | 2.688 |
2.6249 | 14500 | 2.6657 |
2.7154 | 15000 | 2.6703 |
2.8059 | 15500 | 2.7008 |
2.8965 | 16000 | 2.6403 |
2.9870 | 16500 | 2.6422 |
Framework Versions
- Python: 3.9.12
- Sentence Transformers: 3.0.1
- Transformers: 4.44.2
- PyTorch: 2.2.2
- Accelerate: 0.34.2
- Datasets: 2.21.0
- Tokenizers: 0.19.1
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",
}
CoSENTLoss
@online{kexuefm-8847,
title={CoSENT: A more efficient sentence vector scheme than Sentence-BERT},
author={Su Jianlin},
year={2022},
month={Jan},
url={https://kexue.fm/archives/8847},
}
- Downloads last month
- 0
Inference API (serverless) is not available, repository is disabled.
Model tree for tomasravel/modelo_finetuneadoX3
Finetuned
this model