This is a sentence-transformers model finetuned from BAAI/bge-base-en-v1.5. It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for retrieval.

Model Details

Model Description

Model Type: Sentence Transformer
Base model: BAAI/bge-base-en-v1.5
Maximum Sequence Length: 512 tokens
Output Dimensionality: 768 dimensions
Similarity Function: Cosine Similarity
Supported Modality: Text

Model Sources

Documentation: Sentence Transformers Documentation
Repository: Sentence Transformers on GitHub
Hugging Face: Sentence Transformers on Hugging Face

Full Model Architecture

SentenceTransformer(
  (0): Transformer({'transformer_task': 'feature-extraction', 'modality_config': {'text': {'method': 'forward', 'method_output_name': 'last_hidden_state'}}, 'module_output_name': 'token_embeddings', 'architecture': 'BertModel'})
  (1): Pooling({'embedding_dimension': 768, 'pooling_mode': 'cls', '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.

python

from sentence_transformers import SentenceTransformer

# Download from the 🤗 Hub
model = SentenceTransformer("RinKana/bge-base-en-v1.5-afterimage-v.0.1")
# Run inference
sentences = [
    "Represent this dialogue context for retrieving the missing turn: Speaker A is replying. Previous context: Speaker B: They don't all have leather jackets. Speaker A: Anyway, on your birthday Mom and Dad gave you what you asked for! Speaker B: That's true, but all I asked for was a pair of new jeans! Speaker A: I hate this raincoat. Speaker B: All right, how much is a leather jacket? Following context: Speaker B: OK. I'll lend you the $ 50, but you have to pay me back. Speaker A: Great! I'll pay you back, sis!",
    'Candidate response: If I return this raincoat, I only need another $ 50.',
    'Candidate response: I asked them for a leather jacket for my birthday, and they just got me this ugly raincoat.',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 768]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities)
# tensor([[1.0000, 0.7217, 0.5031],
#         [0.7217, 1.0000, 0.5850],
#         [0.5031, 0.5850, 1.0000]])

Evaluation

Metrics

Information Retrieval

Dataset: gap-to-candidate-eval
Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.3322
cosine_accuracy@3	0.4429
cosine_accuracy@5	0.4983
cosine_accuracy@10	0.5744
cosine_precision@1	0.3322
cosine_precision@3	0.1476
cosine_precision@5	0.0997
cosine_precision@10	0.0574
cosine_recall@1	0.3322
cosine_recall@3	0.4429
cosine_recall@5	0.4983
cosine_recall@10	0.5744
cosine_ndcg@10	0.4448
cosine_mrr@10	0.4047
cosine_map@100	0.4116

Training Details

Training Dataset

Unnamed Dataset

Size: 4,744 training samples
Columns: anchor, positive, and negative
Approximate statistics based on the first 1000 samples:
anchor positive negative
type string string string
details
min: 51 tokens
mean: 114.19 tokens
max: 296 tokens
min: 8 tokens
mean: 19.66 tokens
max: 71 tokens
min: 9 tokens
mean: 19.62 tokens
max: 59 tokens

Samples:

anchor	positive	negative
Represent this dialogue context for retrieving the missing turn: Speaker B is replying. Previous context: Speaker A: Oh, yes. Could you tell me your name? Speaker B: Oh, Jerry Lynn. Speaker A: Well, what exactly is it that interests you about the job? Speaker B: I just thought that it was right up my street, you know. Speaker A: Really? Could you tell me a little about yourself? Following context: Speaker A: Do you have any special skills? Speaker B: Well, I speak two foreign languages, French and Italian. Speaker A: Well, I see.	`Candidate response: I've been working abroad doing secretarial work. Previous to that I was at university. I've got a degree in English.`	`Candidate response: Thank you . Could you tell me the specials today ?`
Represent this dialogue context for retrieving the missing turn: Speaker B is replying. Previous context: Speaker A: We'll have to get you to a hospital for an X-ray . Speaker B: Is that really necessary ? Speaker A: It may be worse than it seems . How's it feel ? Speaker B: About the same . Speaker A: Someone will be out to take a look any minute now . Following context: Speaker A: Of course ! It's the sort of thing a hospital emergency ward is for . Will we have to wait much longer ? Speaker B: I hope not.It isn't that busy .	`Candidate response: Should we be here , Alice ? I don't think it's that serious .`	`Candidate response: You don't have to worry about it . We have a one year warranty .`
Represent this dialogue context for retrieving the missing turn: Speaker B is replying. Previous context: Speaker A: ( Bob groans . ) What's the matter.Bob ? Speaker B: I think it's my ankle . Speaker A: What happened ? Speaker B: One of my snowshoes got caught on a rock . Speaker A: Can you stand ? Following context: Speaker A: We'll have to get you to a hospital for an X-ray . Speaker B: Is that really necessary ? Speaker A: It may be worse than it seems . How's it feel ? Speaker B: About the same . Speaker A: Someone will be out to take a look any minute now .	`Candidate response: I don't think so.It ' s kind of sore .`	`Candidate response: You don't have to worry about it . We have a one year warranty .`

Loss: MultipleNegativesRankingLoss with these parameters:
json
1{ 2 "scale": 20.0, 3 "similarity_fct": "cos_sim", 4 "gather_across_devices": false, 5 "directions": [ 6 "query_to_doc" 7 ], 8 "partition_mode": "joint", 9 "hardness_mode": null, 10 "hardness_strength": 0.0 11}

Training Hyperparameters

Non-Default Hyperparameters

per_device_train_batch_size: 16
per_device_eval_batch_size: 16
num_train_epochs: 4
warmup_steps: 0.1
fp16: True
load_best_model_at_end: True
batch_sampler: no_duplicates

All Hyperparameters

Click to expand

do_predict: False
prediction_loss_only: True
per_device_train_batch_size: 16
per_device_eval_batch_size: 16
gradient_accumulation_steps: 1
eval_accumulation_steps: None
torch_empty_cache_steps: None
learning_rate: 5e-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: 4
max_steps: -1
lr_scheduler_type: linear
lr_scheduler_kwargs: None
warmup_ratio: None
warmup_steps: 0.1
log_level: passive
log_level_replica: warning
log_on_each_node: True
logging_nan_inf_filter: True
enable_jit_checkpoint: False
save_on_each_node: False
save_only_model: False
restore_callback_states_from_checkpoint: False
use_cpu: False
seed: 42
data_seed: None
bf16: False
fp16: True
bf16_full_eval: False
fp16_full_eval: False
tf32: None
local_rank: -1
ddp_backend: None
debug: []
dataloader_drop_last: False
dataloader_num_workers: 0
dataloader_prefetch_factor: None
disable_tqdm: False
remove_unused_columns: True
label_names: None
load_best_model_at_end: True
ignore_data_skip: False
fsdp: []
fsdp_config: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
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_fused
optim_args: None
group_by_length: False
length_column_name: length
project: huggingface
trackio_space_id: trackio
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
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_for_metrics: []
eval_do_concat_batches: True
auto_find_batch_size: False
full_determinism: False
ddp_timeout: 1800
torch_compile: False
torch_compile_backend: None
torch_compile_mode: None
include_num_input_tokens_seen: no
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: True
use_cache: False
prompts: None
batch_sampler: no_duplicates
multi_dataset_batch_sampler: proportional
router_mapping: {}
learning_rate_mapping: {}

Training Logs

Epoch	Step	Training Loss	gap-to-candidate-eval_cosine_ndcg@10
0.3356	50	2.1410	-
0.6711	100	0.0009	-
1.0	149	-	0.3215
1.0067	150	0.0534	-
1.3423	200	1.3008	-
1.6779	250	0.0003	-
2.0	298	-	0.4130
2.0134	300	0.0418	-
2.3490	350	0.5842	-
2.6846	400	0.0004	-
3.0	447	-	0.4400
3.0201	450	0.0234	-
3.3557	500	0.2901	-
3.6913	550	0.0007	-
4.0	596	-	0.4448

Training Time

Training: 5.7 minutes

Framework Versions

Python: 3.12.13
Sentence Transformers: 5.4.1
Transformers: 5.0.0
PyTorch: 2.10.0+cu128
Accelerate: 1.13.0
Datasets: 5.0.0
Tokenizers: 0.22.2

Citation

BibTeX

Sentence Transformers

bibtex

@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",
}

MultipleNegativesRankingLoss

bibtex

@misc{oord2019representationlearningcontrastivepredictive,
      title={Representation Learning with Contrastive Predictive Coding},
      author={Aaron van den Oord and Yazhe Li and Oriol Vinyals},
      year={2019},
      eprint={1807.03748},
      archivePrefix={arXiv},
      primaryClass={cs.LG},
      url={https://arxiv.org/abs/1807.03748},
}

	anchor	positive	negative
type	string	string	string
details	min: 51 tokens mean: 114.19 tokens max: 296 tokens	min: 8 tokens mean: 19.66 tokens max: 71 tokens	min: 9 tokens mean: 19.62 tokens max: 59 tokens