Upload sentence_bert_finetuned for Smart Exam System

689cfd8 verified 2 months ago

13.3 kB

tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - dense
  - generated_from_trainer
  - dataset_size:3000
  - loss:CosineSimilarityLoss
base_model: sentence-transformers/all-mpnet-base-v2
widget:
  - source_sentence: A man on skis on a snow-covered hill with mountains in the background
    sentences:
      - >-
        In turning down the NIMA offer, Gehman said, ''there were a number of
        bureaucratic and administrative missed signals here.
      - >-
        A dog enjoys a romp in the water with mountains and sand in the
        background.
      - You mean, you believe the word of the SpringHallConvert?
  - source_sentence: A little boy and a little girl playing together outside.
    sentences:
      - A young boy and a young girl walking towards each other
      - Gameday for the orioles game is frozen for me.
      - The man is playing the piano with his nose.
  - source_sentence: Two girls on the shore watch people in a boat fish.
    sentences:
      - A man is walking down a sidewalk.
      - >-
        The Atlanta Olympic Games attack killed one woman and injured more than
        100 other people.
      - Two males, one in red and one in white playing a basketball game.
  - source_sentence: A woman is firing a rifle.
    sentences:
      - No. Jury nullification does not mean that a law is unconstuitutional.
      - A woman is cutting a lemon.
      - Racers are running down a track.
  - source_sentence: Two men are fighting in a cow pasture.
    sentences:
      - Two men are fighting in a cattle pen.
      - A man is holding a animal.
      - Did the transaction take place?
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: stsb eval
          type: stsb_eval
        metrics:
          - type: pearson_cosine
            value: 0.9385142265383294
            name: Pearson Cosine
          - type: spearman_cosine
            value: 0.9372455714456923
            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 = [
    'Two men are fighting in a cow pasture.',
    'Two men are fighting in a cattle pen.',
    'Did the transaction take place?',
]
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,  0.8048, -0.0474],
#         [ 0.8048,  1.0000, -0.0168],
#         [-0.0474, -0.0168,  1.0000]])

Evaluation

Metrics

Semantic Similarity

Dataset: stsb_eval
Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	0.9385
spearman_cosine	0.9372

Training Details

Training Dataset

Unnamed Dataset

Size: 3,000 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: 13.87 tokens
max: 46 tokens

min: 5 tokens
mean: 14.0 tokens
max: 45 tokens

min: 0.0
mean: 0.51
max: 1.0

	sentence_0	sentence_1	label
type	string	string	float
details	min: 6 tokens mean: 13.87 tokens max: 46 tokens	min: 5 tokens mean: 14.0 tokens max: 45 tokens	min: 0.0 mean: 0.51 max: 1.0

Samples:

sentence_0	sentence_1	label
`A person is slicing an onion.`	`A solenodon is walking along the ground.`	`0.0`
`A woman with a young girl pose with bear statues in front of a store.`	`A man in a jersey stands in front of a large crowd.`	`0.12`
`billion . Everyone in the world at Mexico's current prosperity level.`	`Everyone in the world at the current "prosperity" level of Northwest Africa.`	`0.3067`

Loss: CosineSimilarityLoss with these parameters:

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

Training Hyperparameters

Non-Default Hyperparameters

eval_strategy: steps
per_device_train_batch_size: 16
per_device_eval_batch_size: 16
num_train_epochs: 5
multi_dataset_batch_sampler: round_robin

All Hyperparameters

Click to expand

do_predict: False
eval_strategy: steps
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
num_train_epochs: 5
max_steps: -1
lr_scheduler_type: linear
lr_scheduler_kwargs: None
warmup_ratio: None
warmup_steps: 0
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: False
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: False
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: batch_sampler
multi_dataset_batch_sampler: round_robin
router_mapping: {}
learning_rate_mapping: {}

Training Logs

Epoch	Step	Training Loss	stsb_eval_spearman_cosine
1.0	188	-	0.9366
1.0638	200	-	0.9359
2.0	376	-	0.9336
2.1277	400	-	0.9360
2.6596	500	0.0127	-
3.0	564	-	0.9358
3.1915	600	-	0.9368
4.0	752	-	0.9372

Framework Versions

Python: 3.12.12
Sentence Transformers: 5.2.3
Transformers: 5.0.0
PyTorch: 2.10.0+cu128
Accelerate: 1.12.0
Datasets: 4.0.0
Tokenizers: 0.22.2

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",
}