metadata
base_model: BAAI/bge-m3
datasets: []
language:
- ca
library_name: sentence-transformers
license: apache-2.0
metrics:
- cosine_accuracy@1
- cosine_accuracy@3
- cosine_accuracy@5
- cosine_accuracy@10
- cosine_precision@1
- cosine_precision@3
- cosine_precision@5
- cosine_precision@10
- cosine_recall@1
- cosine_recall@3
- cosine_recall@5
- cosine_recall@10
- cosine_ndcg@10
- cosine_mrr@10
- cosine_map@100
pipeline_tag: sentence-similarity
tags:
- sentence-transformers
- sentence-similarity
- feature-extraction
- generated_from_trainer
- dataset_size:3755
- loss:MatryoshkaLoss
- loss:MultipleNegativesRankingLoss
widget:
- source_sentence: >-
En el cas que la persona beneficiària mantingui les condicions
d’elegibilitat es podrà concedir la pròrroga de la prestació sempre que la
persona interessada ho sol·liciti i ho permetin les dotacions
pressupostàries de cada exercici.
sentences:
- Quin és el benefici de l'ajut a la consolidació d'empreses?
- Quin és el requisit per a la persona beneficiària?
- >-
Quin és el benefici del Registre municipal d'entitats per a
l'Ajuntament?
- source_sentence: >-
Aquest tràmit permet la presentació de les sol·licituds per a l’atorgament
de llicències d’aprofitament especial sense transformació del domini
públic marítim terrestre consistent en la instal·lació i explotació
d'escola per oferir activitats nàutiques, amb zona d’avarada, durant la
temporada.
sentences:
- >-
Quin és el propòsit de la llicència d'aprofitament especial sense
transformació del domini públic marítim terrestre?
- >-
Quin és el termini per a presentar les sol·licituds de subvencions per a
projectes i activitats a entitats de l'àmbit de drets civils?
- Quin és el lloc on es realitzen les activitats amb aquest permís?
- source_sentence: >-
en cas de compliment dels requisits establerts (persones residents,
titulars de plaça d'aparcament, autotaxis, establiments hotelers)
sentences:
- >-
Quin és el paper de l'administració en la justificació del
projecte/activitat subvencionada?
- Quin és el benefici de ser un autotaxi?
- >-
Quin és el benefici per als establiments de la instal·lació de terrasses
o vetlladors?
- source_sentence: >-
La convocatòria és el document que estableix les condicions i els
requisits per a poder sol·licitar les subvencions pel suport educatiu a
les escoles públiques de Sitges.
sentences:
- >-
Quin és el paper de la convocatòria en les subvencions pel suport
educatiu a les escoles públiques de Sitges?
- >-
Quin és el benefici de la consulta prèvia de classificació d'activitat
per a l'Ajuntament de Sitges?
- >-
Quin és el tipus d'ocupació de la via pública que es pot realitzar amb
aquest permís?
- source_sentence: >-
Cal revisar la informació i els terminis de la convocatòria específica de
cada procés que trobareu a la Seu electrònica de l'Ajuntament de Sitges.
sentences:
- >-
Quin és el document que es necessita per acreditar l'any de construcció
i l'adequació a la legalitat urbanística d'un immoble?
- >-
Quin és el paper de l'Ajuntament en la gestió de les activitats per
temporades?
- >-
On es pot trobar la informació sobre els terminis de presentació
d'al·legacions en un procés de selecció de personal de l'Ajuntament de
Sitges?
model-index:
- name: BGE SITGES CAT
results:
- task:
type: information-retrieval
name: Information Retrieval
dataset:
name: dim 1024
type: dim_1024
metrics:
- type: cosine_accuracy@1
value: 0.12679425837320574
name: Cosine Accuracy@1
- type: cosine_accuracy@3
value: 0.21291866028708134
name: Cosine Accuracy@3
- type: cosine_accuracy@5
value: 0.30861244019138756
name: Cosine Accuracy@5
- type: cosine_accuracy@10
value: 0.49521531100478466
name: Cosine Accuracy@10
- type: cosine_precision@1
value: 0.12679425837320574
name: Cosine Precision@1
- type: cosine_precision@3
value: 0.07097288676236044
name: Cosine Precision@3
- type: cosine_precision@5
value: 0.06172248803827751
name: Cosine Precision@5
- type: cosine_precision@10
value: 0.049521531100478466
name: Cosine Precision@10
- type: cosine_recall@1
value: 0.12679425837320574
name: Cosine Recall@1
- type: cosine_recall@3
value: 0.21291866028708134
name: Cosine Recall@3
- type: cosine_recall@5
value: 0.30861244019138756
name: Cosine Recall@5
- type: cosine_recall@10
value: 0.49521531100478466
name: Cosine Recall@10
- type: cosine_ndcg@10
value: 0.27514703200596163
name: Cosine Ndcg@10
- type: cosine_mrr@10
value: 0.20944786207944124
name: Cosine Mrr@10
- type: cosine_map@100
value: 0.23684652150885108
name: Cosine Map@100
- task:
type: information-retrieval
name: Information Retrieval
dataset:
name: dim 768
type: dim_768
metrics:
- type: cosine_accuracy@1
value: 0.11961722488038277
name: Cosine Accuracy@1
- type: cosine_accuracy@3
value: 0.20574162679425836
name: Cosine Accuracy@3
- type: cosine_accuracy@5
value: 0.31100478468899523
name: Cosine Accuracy@5
- type: cosine_accuracy@10
value: 0.49760765550239233
name: Cosine Accuracy@10
- type: cosine_precision@1
value: 0.11961722488038277
name: Cosine Precision@1
- type: cosine_precision@3
value: 0.06858054226475278
name: Cosine Precision@3
- type: cosine_precision@5
value: 0.06220095693779904
name: Cosine Precision@5
- type: cosine_precision@10
value: 0.04976076555023923
name: Cosine Precision@10
- type: cosine_recall@1
value: 0.11961722488038277
name: Cosine Recall@1
- type: cosine_recall@3
value: 0.20574162679425836
name: Cosine Recall@3
- type: cosine_recall@5
value: 0.31100478468899523
name: Cosine Recall@5
- type: cosine_recall@10
value: 0.49760765550239233
name: Cosine Recall@10
- type: cosine_ndcg@10
value: 0.2725409285822112
name: Cosine Ndcg@10
- type: cosine_mrr@10
value: 0.2052479684058634
name: Cosine Mrr@10
- type: cosine_map@100
value: 0.23218215402287107
name: Cosine Map@100
- task:
type: information-retrieval
name: Information Retrieval
dataset:
name: dim 512
type: dim_512
metrics:
- type: cosine_accuracy@1
value: 0.12440191387559808
name: Cosine Accuracy@1
- type: cosine_accuracy@3
value: 0.215311004784689
name: Cosine Accuracy@3
- type: cosine_accuracy@5
value: 0.33014354066985646
name: Cosine Accuracy@5
- type: cosine_accuracy@10
value: 0.5047846889952153
name: Cosine Accuracy@10
- type: cosine_precision@1
value: 0.12440191387559808
name: Cosine Precision@1
- type: cosine_precision@3
value: 0.07177033492822966
name: Cosine Precision@3
- type: cosine_precision@5
value: 0.0660287081339713
name: Cosine Precision@5
- type: cosine_precision@10
value: 0.050478468899521525
name: Cosine Precision@10
- type: cosine_recall@1
value: 0.12440191387559808
name: Cosine Recall@1
- type: cosine_recall@3
value: 0.215311004784689
name: Cosine Recall@3
- type: cosine_recall@5
value: 0.33014354066985646
name: Cosine Recall@5
- type: cosine_recall@10
value: 0.5047846889952153
name: Cosine Recall@10
- type: cosine_ndcg@10
value: 0.2802134368260993
name: Cosine Ndcg@10
- type: cosine_mrr@10
value: 0.21296422875370263
name: Cosine Mrr@10
- type: cosine_map@100
value: 0.23912050845024263
name: Cosine Map@100
- task:
type: information-retrieval
name: Information Retrieval
dataset:
name: dim 256
type: dim_256
metrics:
- type: cosine_accuracy@1
value: 0.11961722488038277
name: Cosine Accuracy@1
- type: cosine_accuracy@3
value: 0.23205741626794257
name: Cosine Accuracy@3
- type: cosine_accuracy@5
value: 0.32057416267942584
name: Cosine Accuracy@5
- type: cosine_accuracy@10
value: 0.47607655502392343
name: Cosine Accuracy@10
- type: cosine_precision@1
value: 0.11961722488038277
name: Cosine Precision@1
- type: cosine_precision@3
value: 0.07735247208931419
name: Cosine Precision@3
- type: cosine_precision@5
value: 0.06411483253588517
name: Cosine Precision@5
- type: cosine_precision@10
value: 0.04760765550239234
name: Cosine Precision@10
- type: cosine_recall@1
value: 0.11961722488038277
name: Cosine Recall@1
- type: cosine_recall@3
value: 0.23205741626794257
name: Cosine Recall@3
- type: cosine_recall@5
value: 0.32057416267942584
name: Cosine Recall@5
- type: cosine_recall@10
value: 0.47607655502392343
name: Cosine Recall@10
- type: cosine_ndcg@10
value: 0.2689946292721634
name: Cosine Ndcg@10
- type: cosine_mrr@10
value: 0.20637104123946248
name: Cosine Mrr@10
- type: cosine_map@100
value: 0.23511603125214608
name: Cosine Map@100
- task:
type: information-retrieval
name: Information Retrieval
dataset:
name: dim 128
type: dim_128
metrics:
- type: cosine_accuracy@1
value: 0.11961722488038277
name: Cosine Accuracy@1
- type: cosine_accuracy@3
value: 0.21770334928229665
name: Cosine Accuracy@3
- type: cosine_accuracy@5
value: 0.3253588516746411
name: Cosine Accuracy@5
- type: cosine_accuracy@10
value: 0.5
name: Cosine Accuracy@10
- type: cosine_precision@1
value: 0.11961722488038277
name: Cosine Precision@1
- type: cosine_precision@3
value: 0.07256778309409888
name: Cosine Precision@3
- type: cosine_precision@5
value: 0.06507177033492824
name: Cosine Precision@5
- type: cosine_precision@10
value: 0.049999999999999996
name: Cosine Precision@10
- type: cosine_recall@1
value: 0.11961722488038277
name: Cosine Recall@1
- type: cosine_recall@3
value: 0.21770334928229665
name: Cosine Recall@3
- type: cosine_recall@5
value: 0.3253588516746411
name: Cosine Recall@5
- type: cosine_recall@10
value: 0.5
name: Cosine Recall@10
- type: cosine_ndcg@10
value: 0.2754707963170229
name: Cosine Ndcg@10
- type: cosine_mrr@10
value: 0.20811498443077409
name: Cosine Mrr@10
- type: cosine_map@100
value: 0.23411435647414974
name: Cosine Map@100
- task:
type: information-retrieval
name: Information Retrieval
dataset:
name: dim 64
type: dim_64
metrics:
- type: cosine_accuracy@1
value: 0.1291866028708134
name: Cosine Accuracy@1
- type: cosine_accuracy@3
value: 0.21291866028708134
name: Cosine Accuracy@3
- type: cosine_accuracy@5
value: 0.32057416267942584
name: Cosine Accuracy@5
- type: cosine_accuracy@10
value: 0.48086124401913877
name: Cosine Accuracy@10
- type: cosine_precision@1
value: 0.1291866028708134
name: Cosine Precision@1
- type: cosine_precision@3
value: 0.07097288676236044
name: Cosine Precision@3
- type: cosine_precision@5
value: 0.06411483253588518
name: Cosine Precision@5
- type: cosine_precision@10
value: 0.04808612440191388
name: Cosine Precision@10
- type: cosine_recall@1
value: 0.1291866028708134
name: Cosine Recall@1
- type: cosine_recall@3
value: 0.21291866028708134
name: Cosine Recall@3
- type: cosine_recall@5
value: 0.32057416267942584
name: Cosine Recall@5
- type: cosine_recall@10
value: 0.48086124401913877
name: Cosine Recall@10
- type: cosine_ndcg@10
value: 0.2704775725936489
name: Cosine Ndcg@10
- type: cosine_mrr@10
value: 0.20746753246753263
name: Cosine Mrr@10
- type: cosine_map@100
value: 0.23395020532132502
name: Cosine Map@100
BGE SITGES CAT
This is a sentence-transformers model finetuned from BAAI/bge-m3. 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: BAAI/bge-m3
- Maximum Sequence Length: 8192 tokens
- Output Dimensionality: 1024 tokens
- Similarity Function: Cosine Similarity
- Language: ca
- License: apache-2.0
Model Sources
Full Model Architecture
SentenceTransformer(
(0): Transformer({'max_seq_length': 8192, 'do_lower_case': False}) with Transformer model: XLMRobertaModel
(1): Pooling({'word_embedding_dimension': 1024, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
(2): Normalize()
)
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
model = SentenceTransformer("adriansanz/SITGES-BAAI3")
sentences = [
"Cal revisar la informació i els terminis de la convocatòria específica de cada procés que trobareu a la Seu electrònica de l'Ajuntament de Sitges.",
"On es pot trobar la informació sobre els terminis de presentació d'al·legacions en un procés de selecció de personal de l'Ajuntament de Sitges?",
"Quin és el document que es necessita per acreditar l'any de construcció i l'adequació a la legalitat urbanística d'un immoble?",
]
embeddings = model.encode(sentences)
print(embeddings.shape)
similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)
Evaluation
Metrics
Information Retrieval
Metric |
Value |
cosine_accuracy@1 |
0.1268 |
cosine_accuracy@3 |
0.2129 |
cosine_accuracy@5 |
0.3086 |
cosine_accuracy@10 |
0.4952 |
cosine_precision@1 |
0.1268 |
cosine_precision@3 |
0.071 |
cosine_precision@5 |
0.0617 |
cosine_precision@10 |
0.0495 |
cosine_recall@1 |
0.1268 |
cosine_recall@3 |
0.2129 |
cosine_recall@5 |
0.3086 |
cosine_recall@10 |
0.4952 |
cosine_ndcg@10 |
0.2751 |
cosine_mrr@10 |
0.2094 |
cosine_map@100 |
0.2368 |
Information Retrieval
Metric |
Value |
cosine_accuracy@1 |
0.1196 |
cosine_accuracy@3 |
0.2057 |
cosine_accuracy@5 |
0.311 |
cosine_accuracy@10 |
0.4976 |
cosine_precision@1 |
0.1196 |
cosine_precision@3 |
0.0686 |
cosine_precision@5 |
0.0622 |
cosine_precision@10 |
0.0498 |
cosine_recall@1 |
0.1196 |
cosine_recall@3 |
0.2057 |
cosine_recall@5 |
0.311 |
cosine_recall@10 |
0.4976 |
cosine_ndcg@10 |
0.2725 |
cosine_mrr@10 |
0.2052 |
cosine_map@100 |
0.2322 |
Information Retrieval
Metric |
Value |
cosine_accuracy@1 |
0.1244 |
cosine_accuracy@3 |
0.2153 |
cosine_accuracy@5 |
0.3301 |
cosine_accuracy@10 |
0.5048 |
cosine_precision@1 |
0.1244 |
cosine_precision@3 |
0.0718 |
cosine_precision@5 |
0.066 |
cosine_precision@10 |
0.0505 |
cosine_recall@1 |
0.1244 |
cosine_recall@3 |
0.2153 |
cosine_recall@5 |
0.3301 |
cosine_recall@10 |
0.5048 |
cosine_ndcg@10 |
0.2802 |
cosine_mrr@10 |
0.213 |
cosine_map@100 |
0.2391 |
Information Retrieval
Metric |
Value |
cosine_accuracy@1 |
0.1196 |
cosine_accuracy@3 |
0.2321 |
cosine_accuracy@5 |
0.3206 |
cosine_accuracy@10 |
0.4761 |
cosine_precision@1 |
0.1196 |
cosine_precision@3 |
0.0774 |
cosine_precision@5 |
0.0641 |
cosine_precision@10 |
0.0476 |
cosine_recall@1 |
0.1196 |
cosine_recall@3 |
0.2321 |
cosine_recall@5 |
0.3206 |
cosine_recall@10 |
0.4761 |
cosine_ndcg@10 |
0.269 |
cosine_mrr@10 |
0.2064 |
cosine_map@100 |
0.2351 |
Information Retrieval
Metric |
Value |
cosine_accuracy@1 |
0.1196 |
cosine_accuracy@3 |
0.2177 |
cosine_accuracy@5 |
0.3254 |
cosine_accuracy@10 |
0.5 |
cosine_precision@1 |
0.1196 |
cosine_precision@3 |
0.0726 |
cosine_precision@5 |
0.0651 |
cosine_precision@10 |
0.05 |
cosine_recall@1 |
0.1196 |
cosine_recall@3 |
0.2177 |
cosine_recall@5 |
0.3254 |
cosine_recall@10 |
0.5 |
cosine_ndcg@10 |
0.2755 |
cosine_mrr@10 |
0.2081 |
cosine_map@100 |
0.2341 |
Information Retrieval
Metric |
Value |
cosine_accuracy@1 |
0.1292 |
cosine_accuracy@3 |
0.2129 |
cosine_accuracy@5 |
0.3206 |
cosine_accuracy@10 |
0.4809 |
cosine_precision@1 |
0.1292 |
cosine_precision@3 |
0.071 |
cosine_precision@5 |
0.0641 |
cosine_precision@10 |
0.0481 |
cosine_recall@1 |
0.1292 |
cosine_recall@3 |
0.2129 |
cosine_recall@5 |
0.3206 |
cosine_recall@10 |
0.4809 |
cosine_ndcg@10 |
0.2705 |
cosine_mrr@10 |
0.2075 |
cosine_map@100 |
0.234 |
Training Details
Training Hyperparameters
Non-Default Hyperparameters
eval_strategy
: epoch
per_device_train_batch_size
: 16
per_device_eval_batch_size
: 16
gradient_accumulation_steps
: 16
learning_rate
: 2e-05
num_train_epochs
: 6
lr_scheduler_type
: cosine
warmup_ratio
: 0.1
bf16
: True
tf32
: True
load_best_model_at_end
: True
optim
: adamw_torch_fused
batch_sampler
: no_duplicates
All Hyperparameters
Click to expand
overwrite_output_dir
: False
do_predict
: False
eval_strategy
: epoch
prediction_loss_only
: True
per_device_train_batch_size
: 16
per_device_eval_batch_size
: 16
per_gpu_train_batch_size
: None
per_gpu_eval_batch_size
: None
gradient_accumulation_steps
: 16
eval_accumulation_steps
: None
learning_rate
: 2e-05
weight_decay
: 0.0
adam_beta1
: 0.9
adam_beta2
: 0.999
adam_epsilon
: 1e-08
max_grad_norm
: 1.0
num_train_epochs
: 6
max_steps
: -1
lr_scheduler_type
: cosine
lr_scheduler_kwargs
: {}
warmup_ratio
: 0.1
warmup_steps
: 0
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
: True
fp16
: False
fp16_opt_level
: O1
half_precision_backend
: auto
bf16_full_eval
: False
fp16_full_eval
: False
tf32
: True
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_fused
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
: False
hub_always_push
: False
gradient_checkpointing
: False
gradient_checkpointing_kwargs
: None
include_inputs_for_metrics
: False
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
batch_sampler
: no_duplicates
multi_dataset_batch_sampler
: proportional
Training Logs
Epoch |
Step |
Training Loss |
loss |
dim_1024_cosine_map@100 |
dim_128_cosine_map@100 |
dim_256_cosine_map@100 |
dim_512_cosine_map@100 |
dim_64_cosine_map@100 |
dim_768_cosine_map@100 |
0.3404 |
5 |
3.3256 |
- |
- |
- |
- |
- |
- |
- |
0.6809 |
10 |
2.2115 |
- |
- |
- |
- |
- |
- |
- |
0.9532 |
14 |
- |
1.2963 |
0.2260 |
0.2148 |
0.2144 |
0.2258 |
0.2069 |
0.2252 |
1.0213 |
15 |
1.7921 |
- |
- |
- |
- |
- |
- |
- |
1.3617 |
20 |
1.2295 |
- |
- |
- |
- |
- |
- |
- |
1.7021 |
25 |
0.9048 |
- |
- |
- |
- |
- |
- |
- |
1.9745 |
29 |
- |
0.8667 |
0.2311 |
0.2267 |
0.2292 |
0.2279 |
0.2121 |
0.2278 |
2.0426 |
30 |
0.7256 |
- |
- |
- |
- |
- |
- |
- |
2.3830 |
35 |
0.5252 |
- |
- |
- |
- |
- |
- |
- |
2.7234 |
40 |
0.4648 |
- |
- |
- |
- |
- |
- |
- |
2.9957 |
44 |
- |
0.692 |
0.2311 |
0.2243 |
0.2332 |
0.2319 |
0.2211 |
0.2354 |
3.0638 |
45 |
0.3518 |
- |
- |
- |
- |
- |
- |
- |
3.4043 |
50 |
0.321 |
- |
- |
- |
- |
- |
- |
- |
3.7447 |
55 |
0.2923 |
- |
- |
- |
- |
- |
- |
- |
3.9489 |
58 |
- |
0.6514 |
0.2343 |
0.2210 |
0.2293 |
0.2338 |
0.2242 |
0.2331 |
4.0851 |
60 |
0.2522 |
- |
- |
- |
- |
- |
- |
- |
4.4255 |
65 |
0.2445 |
- |
- |
- |
- |
- |
- |
- |
4.7660 |
70 |
0.2358 |
- |
- |
- |
- |
- |
- |
- |
4.9702 |
73 |
- |
0.6481 |
0.2348 |
0.2239 |
0.2252 |
0.2332 |
0.2167 |
0.2298 |
5.1064 |
75 |
0.2301 |
- |
- |
- |
- |
- |
- |
- |
5.4468 |
80 |
0.2262 |
- |
- |
- |
- |
- |
- |
- |
5.7191 |
84 |
- |
0.6460 |
0.2430 |
0.2308 |
0.2343 |
0.2408 |
0.2212 |
0.2378 |
0.3404 |
5 |
0.1585 |
- |
- |
- |
- |
- |
- |
- |
0.6809 |
10 |
0.1465 |
- |
- |
- |
- |
- |
- |
- |
0.9532 |
14 |
- |
0.6325 |
0.2407 |
0.2255 |
0.2328 |
0.2333 |
0.2266 |
0.2429 |
1.0213 |
15 |
0.1411 |
- |
- |
- |
- |
- |
- |
- |
1.3617 |
20 |
0.079 |
- |
- |
- |
- |
- |
- |
- |
1.7021 |
25 |
0.1159 |
- |
- |
- |
- |
- |
- |
- |
1.9745 |
29 |
- |
0.6772 |
0.2361 |
0.2287 |
0.2252 |
0.2325 |
0.2228 |
0.2387 |
2.0426 |
30 |
0.0838 |
- |
- |
- |
- |
- |
- |
- |
2.3830 |
35 |
0.0647 |
- |
- |
- |
- |
- |
- |
- |
2.7234 |
40 |
0.0752 |
- |
- |
- |
- |
- |
- |
- |
2.9957 |
44 |
- |
0.6668 |
0.2304 |
0.2354 |
0.2304 |
0.2344 |
0.2155 |
0.2321 |
3.0638 |
45 |
0.0706 |
- |
- |
- |
- |
- |
- |
- |
3.4043 |
50 |
0.0478 |
- |
- |
- |
- |
- |
- |
- |
3.7447 |
55 |
0.0768 |
- |
- |
- |
- |
- |
- |
- |
3.9489 |
58 |
- |
0.6040 |
0.2318 |
0.2293 |
0.2292 |
0.2305 |
0.2165 |
0.2264 |
4.0851 |
60 |
0.0793 |
- |
- |
- |
- |
- |
- |
- |
4.4255 |
65 |
0.0559 |
- |
- |
- |
- |
- |
- |
- |
4.7660 |
70 |
0.0654 |
- |
- |
- |
- |
- |
- |
- |
4.9702 |
73 |
- |
0.6105 |
0.2328 |
0.2328 |
0.2313 |
0.2364 |
0.2279 |
0.2320 |
5.1064 |
75 |
0.0734 |
- |
- |
- |
- |
- |
- |
- |
5.4468 |
80 |
0.0616 |
- |
- |
- |
- |
- |
- |
- |
5.7191 |
84 |
- |
0.6107 |
0.2368 |
0.2341 |
0.2351 |
0.2391 |
0.2340 |
0.2322 |
- The bold row denotes the saved checkpoint.
Framework Versions
- Python: 3.10.12
- Sentence Transformers: 3.0.1
- Transformers: 4.42.3
- PyTorch: 2.3.1+cu121
- Accelerate: 0.32.1
- Datasets: 2.20.0
- 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",
}
MatryoshkaLoss
@misc{kusupati2024matryoshka,
title={Matryoshka Representation Learning},
author={Aditya Kusupati and Gantavya Bhatt and Aniket Rege and Matthew Wallingford and Aditya Sinha and Vivek Ramanujan and William Howard-Snyder and Kaifeng Chen and Sham Kakade and Prateek Jain and Ali Farhadi},
year={2024},
eprint={2205.13147},
archivePrefix={arXiv},
primaryClass={cs.LG}
}
MultipleNegativesRankingLoss
@misc{henderson2017efficient,
title={Efficient Natural Language Response Suggestion for Smart Reply},
author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil},
year={2017},
eprint={1705.00652},
archivePrefix={arXiv},
primaryClass={cs.CL}
}