atles / README.md

Upload README.md with huggingface_hub

7ed74be verified 5 months ago

13.5 kB

tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - dense
  - generated_from_trainer
  - dataset_size:5749
  - loss:CosineSimilarityLoss
base_model: sentence-transformers/all-mpnet-base-v2
widget:
  - source_sentence: Red sports car racing down track.
    sentences:
      - A red sports car driving quickly on a track.
      - Mali's Interim President Sworn Into Office
      - Iran, world powers pledge new nuclear talks
  - source_sentence: A dog running along the beach.
    sentences:
      - Boy and girl running along the beach.
      - Conte said Druce will be charged with murder.
      - >-
        But they don't realize that until it's too late (of course) because
        they're potential victims.
  - source_sentence: US Troops Killed in Afghan Insider Attack
    sentences:
      - China yuan weakens to 6.1510 against USD
      - A woman is riding a horse.
      - NATO troops killed in Afghan 'insider attack'
  - source_sentence: Three die after car crash at Tian'anmen
    sentences:
      - >-
        russia would not hesitate to increase military strength along russian
        borders if the need arises.
      - The lady peeled the shrimp.
      - Three Killed In Crash At Tiananmen Square
  - source_sentence: Japan scrambles jets against Russian military planes
    sentences:
      - Separatists down Ukraine military plane, several dead
      - A woman is chopping some shiso leaves.
      - A man is riding a horse in an arena.
pipeline_tag: sentence-similarity
library_name: sentence-transformers
metrics:
  - pearson_cosine
  - spearman_cosine
model-index:
  - name: SentenceTransformer based on sentence-transformers/all-mpnet-base-v2
    results:
      - task:
          type: semantic-similarity
          name: Semantic Similarity
        dataset:
          name: sts dev
          type: sts-dev
        metrics:
          - type: pearson_cosine
            value: 0.6055915526117108
            name: Pearson Cosine
          - type: spearman_cosine
            value: 0.6081754566424775
            name: Spearman Cosine

SentenceTransformer based on sentence-transformers/all-mpnet-base-v2

This is a sentence-transformers model finetuned from sentence-transformers/all-mpnet-base-v2. 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: sentence-transformers/all-mpnet-base-v2
Maximum Sequence Length: 384 tokens
Output Dimensionality: 768 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': 384, 'do_lower_case': False, 'architecture': 'MPNetModel'})
  (1): Pooling({'word_embedding_dimension': 768, '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})
  (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

# Download from the 🤗 Hub
model = SentenceTransformer("sentence_transformers_model_id")
# Run inference
sentences = [
    'Japan scrambles jets against Russian military planes',
    'Separatists down Ukraine military plane, several dead',
    'A woman is chopping some shiso leaves.',
]
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, 0.4481, 0.2550],
#         [0.4481, 1.0000, 0.3009],
#         [0.2550, 0.3009, 1.0000]])

Evaluation

Metrics

Semantic Similarity

Dataset: sts-dev
Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	0.6056
spearman_cosine	0.6082

Training Details

Training Dataset

Unnamed Dataset

Size: 5,749 training samples
Columns: sentence_0, sentence_1, and label
Approximate statistics based on the first 1000 samples:
sentence_0 sentence_1 label
type string string float
details
min: 6 tokens
mean: 14.52 tokens
max: 46 tokens

min: 5 tokens
mean: 14.51 tokens
max: 45 tokens

min: 0.0
mean: 0.11
max: 0.2

	sentence_0	sentence_1	label
type	string	string	float
details	min: 6 tokens mean: 14.52 tokens max: 46 tokens	min: 5 tokens mean: 14.51 tokens max: 45 tokens	min: 0.0 mean: 0.11 max: 0.2

Samples:

sentence_0	sentence_1	label
`billion . Everyone in the world at Mexico's current prosperity level.`	`Everyone in the world at the current "prosperity" level of Northwest Africa.`	`0.062`
`Two women sitting on brown couch.`	`Two women standing outside of a bus.`	`0.04`
`A woman peels an apple.`	`A man pops wheelies on a motorcycle.`	`0.0`

Loss: CosineSimilarityLoss with these parameters:

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

Training Hyperparameters

Non-Default Hyperparameters

per_device_train_batch_size: 32
per_device_eval_batch_size: 32
fp16: True
multi_dataset_batch_sampler: round_robin

All Hyperparameters

Click to expand

overwrite_output_dir: False
do_predict: False
eval_strategy: no
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: 5e-05
weight_decay: 0.0
adam_beta1: 0.9
adam_beta2: 0.999
adam_epsilon: 1e-08
max_grad_norm: 1
num_train_epochs: 3
max_steps: -1
lr_scheduler_type: linear
lr_scheduler_kwargs: {}
warmup_ratio: 0.0
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
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_fused
optim_args: None
adafactor: False
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
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: 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
prompts: None
batch_sampler: batch_sampler
multi_dataset_batch_sampler: round_robin
router_mapping: {}
learning_rate_mapping: {}

Training Logs

Epoch	Step	Training Loss	sts-dev_spearman_cosine
1.0	180	-	0.5522
2.0	360	-	0.5536
2.7778	500	0.0428	-
3.0	540	-	0.6082

Framework Versions

Python: 3.12.3
Sentence Transformers: 5.1.2
Transformers: 4.57.1
PyTorch: 2.8.0+cu128
Accelerate: 1.11.0
Datasets: 4.4.1
Tokenizers: 0.22.1

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",
}