Add new SentenceTransformer model

eed8316 verified 2 months ago

13.7 kB

tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - dense
  - generated_from_trainer
  - dataset_size:5749
  - loss:CosineSimilarityLoss
base_model: sentence-transformers/all-MiniLM-L6-v2
widget:
  - source_sentence: Birthday of DPRK to Be Celebrated in Peru
    sentences:
      - Curiosity Rover Celebrates 1 Year on Mars
      - A man is playing a guitar.
      - A guy is going up for a lay-up on a basketball court.
  - source_sentence: >-
      Mr Sahel said police had identified the bodies of seven of the 14-strong
      cell believed to have carried out the five almost simultaneous attacks on
      Saturday.
    sentences:
      - >-
        He said police had identified the bodies of seven of the 14 bombers who
        launched five almost simultaneous raids Friday night.
      - Use of force by aggressor.
      - Hezbollah says it sent drone over Israel
  - source_sentence: Iranian president makes debut on world stage
    sentences:
      - The prices of everything you own IE assets have gone down.
      - Liquid ammonia leak kills at least 15 in Shanghai
      - Iran presidential candidate says western sanctions should be broken
  - source_sentence: Two dogs are peeing at a red fire hydrant.
    sentences:
      - '''No plans'' to resettle Syrian refugees in the UK'
      - >-
        Pratt & Whitney had said that if it won the contract 75 per cent of the
        engine equipment would be outsourced to European suppliers, with final
        assembly in Germany.
      - Two dogs are urinating on the red fire hydrant.
  - source_sentence: >-
      estonian officials stated that some of the cyber attacks that caused
      estonian government websites to shut down temporarily came from computers
      in the administration of russia including in the office of president
      vladimir putin.
    sentences:
      - >-
        officials in estonia including prime minister andrus ansip have claimed
        that some of the cyber attacks came from russian government computers
        including computers in the office of russian president vladimir putin.
      - 43 killed, 86 wounded in attacks in Iraq
      - >-
        "But I do question the motives of a desk-bound president who assumes the
        garb of a warrior for the purposes of a speech."
pipeline_tag: sentence-similarity
library_name: sentence-transformers
metrics:
  - pearson_cosine
  - spearman_cosine
model-index:
  - name: SentenceTransformer based on sentence-transformers/all-MiniLM-L6-v2
    results:
      - task:
          type: semantic-similarity
          name: Semantic Similarity
        dataset:
          name: Unknown
          type: unknown
        metrics:
          - type: pearson_cosine
            value: 0.8954025352430321
            name: Pearson Cosine
          - type: spearman_cosine
            value: 0.8948218008000964
            name: Spearman Cosine

SentenceTransformer based on sentence-transformers/all-MiniLM-L6-v2

This is a sentence-transformers model finetuned from sentence-transformers/all-MiniLM-L6-v2. It maps sentences & paragraphs to a 384-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-MiniLM-L6-v2
Maximum Sequence Length: 256 tokens
Output Dimensionality: 384 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': 256, 'do_lower_case': False, 'architecture': 'BertModel'})
  (1): Pooling({'word_embedding_dimension': 384, '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("shubham-t/fineTune-sbert")
# Run inference
sentences = [
    'estonian officials stated that some of the cyber attacks that caused estonian government websites to shut down temporarily came from computers in the administration of russia including in the office of president vladimir putin.',
    'officials in estonia including prime minister andrus ansip have claimed that some of the cyber attacks came from russian government computers including computers in the office of russian president vladimir putin.',
    '43 killed, 86 wounded in attacks in Iraq',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 384]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities)
# tensor([[1.0000, 0.7744, 0.0361],
#         [0.7744, 1.0000, 0.0079],
#         [0.0361, 0.0079, 1.0000]])

Evaluation

Metrics

Semantic Similarity

Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	0.8954
spearman_cosine	0.8948

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: 14.5 tokens
max: 53 tokens

min: 6 tokens
mean: 14.55 tokens
max: 49 tokens

min: 0.0
mean: 0.55
max: 1.0

	sentence_0	sentence_1	label
type	string	string	float
details	min: 6 tokens mean: 14.5 tokens max: 53 tokens	min: 6 tokens mean: 14.55 tokens max: 49 tokens	min: 0.0 mean: 0.55 max: 1.0

Samples:

sentence_0	sentence_1	label
`A man riding a small bicycle.`	`A man is doing a wheelie on a bike.`	`0.5599999904632569`
`Syria demands guarantees, rebels say peace plan doomed`	`Syria demands written guarantee for troop pullback`	`0.6400000095367432`
`Britain reaches out to Syria opposition`	`Who cares about the Syrian people?`	`0.24000000953674316`

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
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: 3
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	spearman_cosine
1.0	360	-	0.8938
1.3889	500	0.0212	-
2.0	720	-	0.8940
2.7778	1000	0.0142	0.8948

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: 4.5.0
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",
}