tmp_trainer / README.md

B0ketto

garima77622/simaese2.0

f0a0665 verified about 1 year ago

preview code

raw

history blame contribute delete

16.9 kB

metadata

tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - dataset_size:65698
  - loss:ContrastiveLoss
base_model: B0ketto/tmp_trainer
widget:
  - source_sentence: >-
      Enforcement of minor traffic offenses leads to the discovery of more
      serious crimes.
    sentences:
      - >-
        Western culture has created independent women who are strong on their
        own and do not need the protection or support of their husband. This
        reduces the subjugation of women.
      - >-
        Philando Castile, stopped for a broken tailight, was shot seven times
        and killed trying to comply with the officer's request for
        identification.
      - The children will have several older / more mature stepmothers.
  - source_sentence: Women and men can always file for divorce.
    sentences:
      - >-
        A partner having multiple partners is taken care of enough. There is
        probably less need to find even more partners. This is also a matter of
        free time, when having multiple partners free time is probably rare.
      - >-
        The power relations in polygamous marriages should be even more
        favorable to female sponsored divorce as it is more likely that women
        can keep their children while at the same time the man becomes less
        dependent on one woman emotionally.
      - >-
        People close to the individual who commits suicide may feel that they
        could and should have done more to prevent it, thus leaving them with
        intense feelings of guilt.
  - source_sentence: >-
      It's okay that specific groups of people are not allowed to vote. For
      example: children aren't usually allowed to vote, because they are
      considered too young - too inexperienced. The same kind of logic could be
      used to "filter out" people who have very little knowledge of the world or
      terrible analytical capabilities.
    sentences:
      - >-
        Those who have a medically diagnosed incapacity for voting should not be
        allowed to vote, because they may be far more easily swayed to vote one
        way or another. However, this must be regulated to medically diagnosed
        conditions on a mental level.
      - >-
        Representation is foundational to the American DNA. "No taxation without
        representation" is one of our oldest grievance slogans. Removing the
        ability of any group to vote reinstates this 400-year old injustice.
      - >-
        Retailers would supposedly be able to sell the discarded bottles on,
        thereby making a profit after the initial investment into the necessary
        infrastructure.
  - source_sentence: >-
      It's okay that specific groups of people are not allowed to vote. For
      example: children aren't usually allowed to vote, because they are
      considered too young - too inexperienced. The same kind of logic could be
      used to "filter out" people who have very little knowledge of the world or
      terrible analytical capabilities.
    sentences:
      - >-
        Planned Parenthood is not only offering abortions but a host of other
        services, such as clinical breast examination.
      - >-
        Some budgetary problems for local law enforcement would be alleviated by
        removing proactive policing duties from the officer's mission.
      - >-
        The benefit is to keep those who you do not wish to vote, unable to pass
        the test. This can lead to education suppression, as an example. There
        are vast amounts of education imbalance which can be furthered to
        suppress votes from those who wish to change the system-- ergo,
        suppressing those who would wrest power from those who wish to maintain
        it through unfair means.
  - source_sentence: For children, it is bad to grow up in a polygamous family.
    sentences:
      - Polygamous families tend to have more children.
      - >-
        The right of adults to marry should not be precluded by a person's
        distaste for their marital structure. The same argument is used against
        same-sex marriage, and it is invariably irrelevant.
      - This threatens the idea of true democracy.
pipeline_tag: sentence-similarity
library_name: sentence-transformers

SentenceTransformer based on B0ketto/tmp_trainer

This is a sentence-transformers model finetuned from B0ketto/tmp_trainer. 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: B0ketto/tmp_trainer
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}) with Transformer model: 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 = [
    'For children, it is bad to grow up in a polygamous family.',
    'Polygamous families tend to have more children.',
    'This threatens the idea of true democracy.',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 768]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)
# [3, 3]

Training Details

Training Dataset

Unnamed Dataset

Size: 65,698 training samples
Columns: sentence1, sentence2, and label
Approximate statistics based on the first 1000 samples:
sentence1 sentence2 label
type string string int
details
min: 7 tokens
mean: 25.0 tokens
max: 130 tokens

min: 6 tokens
mean: 31.05 tokens
max: 130 tokens

0: ~55.50%
1: ~44.50%

	sentence1	sentence2	label
type	string	string	int
details	min: 7 tokens mean: 25.0 tokens max: 130 tokens	min: 6 tokens mean: 31.05 tokens max: 130 tokens	0: ~55.50% 1: ~44.50%

Samples:

sentence1	sentence2	label
`Public opinion favors euthanasia which suggests some support for a right to die.`	`Europeans generally support euthanasia. For example, more than 70% of citizens of Spain, Germany, France and Britain are in favor.`	`1`
`Public opinion favors euthanasia which suggests some support for a right to die.`	`In the US, support for assisted suicide has risen to 69% acceptance rate in the last few decades.`	`1`
`Public opinion favors euthanasia which suggests some support for a right to die.`	`The young and healthy that are asked in polls cannot imagine a situation of disability. This, so the criticism goes, blurs their image of euthanasia.`	`0`

Loss: ContrastiveLoss with these parameters:

{
    "distance_metric": "SiameseDistanceMetric.COSINE_DISTANCE",
    "margin": 0.5,
    "size_average": true
}

Training Hyperparameters

All Hyperparameters

Click to expand

overwrite_output_dir: False
do_predict: False
eval_strategy: no
prediction_loss_only: True
per_device_train_batch_size: 8
per_device_eval_batch_size: 8
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: 1.0
num_train_epochs: 3.0
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
use_ipex: False
bf16: False
fp16: False
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}
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
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
dispatch_batches: None
split_batches: 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
eval_use_gather_object: False
average_tokens_across_devices: False
prompts: None
batch_sampler: batch_sampler
multi_dataset_batch_sampler: proportional

Training Logs

Epoch	Step	Training Loss
0.0609	500	0.0256
0.1218	1000	0.0257
0.1826	1500	0.0263
0.2435	2000	0.0291
0.3044	2500	0.0276
0.3653	3000	0.0304
0.4262	3500	0.0297
0.4870	4000	0.0332
0.5479	4500	0.033
0.6088	5000	0.0328
0.6697	5500	0.0328
0.7305	6000	0.0331
0.7914	6500	0.0321
0.8523	7000	0.0326
0.9132	7500	0.0329
0.9741	8000	0.0318
1.0349	8500	0.0323
1.0958	9000	0.0321
1.1567	9500	0.0321
1.2176	10000	0.0322
1.2785	10500	0.0321
1.3393	11000	0.0317
1.4002	11500	0.0317
1.4611	12000	0.0315
1.5220	12500	0.0318
1.5829	13000	0.0319
1.6437	13500	0.0315
1.7046	14000	0.0313
1.7655	14500	0.0294
1.8264	15000	0.0292
1.8873	15500	0.0278
1.9481	16000	0.0286
2.0090	16500	0.0274
2.0699	17000	0.0273
2.1308	17500	0.027
2.1916	18000	0.0271
2.2525	18500	0.0265
2.3134	19000	0.0262
2.3743	19500	0.0254
2.4352	20000	0.0255
2.4960	20500	0.0256
2.5569	21000	0.0252
2.6178	21500	0.0246
2.6787	22000	0.0251
2.7396	22500	0.0238
2.8004	23000	0.025
2.8613	23500	0.0247
2.9222	24000	0.0252
2.9831	24500	0.0237

Framework Versions

Python: 3.11.11
Sentence Transformers: 3.4.1
Transformers: 4.48.3
PyTorch: 2.5.1+cu124
Accelerate: 1.3.0
Datasets: 3.3.1
Tokenizers: 0.21.0

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",
}

ContrastiveLoss

@inproceedings{hadsell2006dimensionality,
    author={Hadsell, R. and Chopra, S. and LeCun, Y.},
    booktitle={2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06)},
    title={Dimensionality Reduction by Learning an Invariant Mapping},
    year={2006},
    volume={2},
    number={},
    pages={1735-1742},
    doi={10.1109/CVPR.2006.100}
}