SentenceTransformer based on BAAI/bge-base-en
This is a sentence-transformers model finetuned from BAAI/bge-base-en. It maps sentences & paragraphs to a 768-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-base-en
- Maximum Sequence Length: 512 tokens
- Output Dimensionality: 768 dimensions
- Similarity Function: Cosine Similarity
Model Sources
Full Model Architecture
SentenceTransformer(
(0): Transformer({'max_seq_length': 512, 'do_lower_case': True, 'architecture': 'BertModel'})
(1): Pooling({'word_embedding_dimension': 768, '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("aaa961/finetuned-bge-base-en-firefox-bugs-bugs")
sentences = [
"Some bookmark icons disappear over time User Agent: Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:109.0) Gecko/20100101 Firefox/112.0\n\nSteps to reproduce:\n\nI have two bookmarks in my Bookmarks Menu for which sometimes Firefox resets the icon to the default (globe) icon from time to time for no reason. I don't visit them or do anything to those boookmarks. It's these two sites that have this problem, all other bookmarks' icons stay in tact. \n\nTo fix it, I have to click on the respective bookmark and wait for the page load - after that the proper site icon is shown again.",
'After closing or opening a tab without leaving the tab strip, there is no delay in displaying the tab preview **Found in**\n* 126.0a1 (2024-04-04)\n\n\n\n**Affected versions**\n* 126.0a1 (2024-04-04)\n\n\n\n**Tested platforms**\n* Affected platforms: Windows 10x64, Ubuntu 23, macOS 12\n* Unaffected platforms: none\n\n**Preconditions**\n* browser.tabs.cardPreview.enabled: true\n\n**Steps to reproduce**\n1. Open some random tabs and hover over them until the tab preview is displayed.\n2. Without leaving the tab strip close a tab located in the middle of the other tabs.\n\n**Expected result** \n* The tab preview is displayed after 500ms.\n\n\n\n**Actual result**\n* The tab preview is displayed instantly. \n\n\n**Regression range**\n* Pushlog: https://hg.mozilla.org/integration/autoland/pushloghtml?fromchange=7b609d9f295fce7ab954f09492fea414b72843e6&tochange=a387d4331dd332c954d2689a4a8b64c2181690b1 \nPossible regressor: Bug 1876522 \n\n**Additional notes**\n* Attached a screen recording.\n* This also happens when opening a new tab.',
'Adding Opensearch search engine does not work for .onion addresses User Agent: Mozilla/5.0 (X11; Linux x86_64; rv:82.0) Gecko/20100101 Firefox/82.0\n\nSteps to reproduce:\n\n1. Navigate to a search engine website hosted on the TOR network (like http://yra4tke2pwcnatxjkufpw6kvebu3h3ti2jca2lcdpgx3mpwol326lzid.onion/ ).\nThe website must provide an Opensearch descriptor.\n\n2. Click "Page Actions" -> "Add Search Engine".\n\n\nActual results:\n\nFirefox cannot add the search engine despite the website providing a valid Opensearch descriptor. Following message is shown:\n```\nFirefox could not download the search plugin from: http://yra4tke2pwcnatxjkufpw6kvebu3h3ti2jca2lcdpgx3mpwol326lzid.onion/opensearch.xml\n```\n\n\nExpected results:\n\nWhen fetching the Opensearch descriptor Firefox should use the proxy settings provided by the user. In the case of TOR requests to .onion websites will fail when not using the SOCKS5 proxy.\n\nWorkaround: Downloading the index.html and the opensearch.xml descriptor file manually and serving them locally. After navigating to the local address, the search engine can be added normally.',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
similarities = model.similarity(embeddings, embeddings)
print(similarities)
Evaluation
Metrics
Triplet
- Datasets:
bge-base-en-eval and bge-base-en-train
- Evaluated with
TripletEvaluator
| Metric |
bge-base-en-eval |
bge-base-en-train |
| cosine_accuracy |
0.5159 |
0.6812 |
Training Details
Training Dataset
Unnamed Dataset
Evaluation Dataset
Unnamed Dataset
Training Hyperparameters
Non-Default Hyperparameters
eval_strategy: steps
per_device_train_batch_size: 16
per_device_eval_batch_size: 32
gradient_accumulation_steps: 8
learning_rate: 2e-05
num_train_epochs: 7
warmup_ratio: 0.1
fp16: True
batch_sampler: no_duplicates
All Hyperparameters
Click to expand
overwrite_output_dir: False
do_predict: False
eval_strategy: steps
prediction_loss_only: True
per_device_train_batch_size: 16
per_device_eval_batch_size: 32
per_gpu_train_batch_size: None
per_gpu_eval_batch_size: None
gradient_accumulation_steps: 8
eval_accumulation_steps: None
torch_empty_cache_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: 7
max_steps: -1
lr_scheduler_type: linear
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: 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: False
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}
parallelism_config: 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
hub_revision: None
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
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
liger_kernel_config: None
eval_use_gather_object: False
average_tokens_across_devices: False
prompts: None
batch_sampler: no_duplicates
multi_dataset_batch_sampler: proportional
router_mapping: {}
learning_rate_mapping: {}
Training Logs
| Epoch |
Step |
Training Loss |
Validation Loss |
bge-base-en-eval_cosine_accuracy |
bge-base-en-train_cosine_accuracy |
| -1 |
-1 |
- |
- |
0.5073 |
- |
| 2.3304 |
100 |
4.8424 |
4.9209 |
- |
0.6825 |
| 4.6608 |
200 |
4.488 |
4.8791 |
- |
0.6829 |
| 6.9912 |
300 |
4.4078 |
4.9009 |
- |
0.6812 |
| -1 |
-1 |
- |
- |
0.5159 |
- |
Framework Versions
- Python: 3.10.10
- Sentence Transformers: 5.1.0
- Transformers: 4.56.0
- PyTorch: 2.7.1+cu128
- Accelerate: 1.10.1
- Datasets: 4.0.0
- Tokenizers: 0.22.0
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",
}
TripletLoss
@misc{hermans2017defense,
title={In Defense of the Triplet Loss for Person Re-Identification},
author={Alexander Hermans and Lucas Beyer and Bastian Leibe},
year={2017},
eprint={1703.07737},
archivePrefix={arXiv},
primaryClass={cs.CV}
}