SentenceTransformer based on distilbert/distilroberta-base

This is a sentence-transformers model finetuned from distilbert/distilroberta-base. 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: distilbert/distilroberta-base
Maximum Sequence Length: 512 tokens
Output Dimensionality: 768 tokens
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': 512, 'do_lower_case': False}) with Transformer model: RobertaModel 
  (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})
)

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("jeevansai93/Jeevan_cv_run2_roberta_5_epoc")
# Run inference
sentences = [
    'Sour Cream Coconut Cake ["2 c. sugar", "2 (8 oz.) carton sour cream", "2 pkg. frozen coconut", "1 (3-layer) cake, baked"] ["Bake cake; split the 3 layers into 6 layers."]',
    'Milk Chocolate Bar Cake ["1 (18 oz.) pkg. Swiss chocolate cake mix", "1 (8 oz.) pkg. cream cheese, softened", "1 c. powdered sugar", "1/2 c. granulated sugar", "10 (15 oz.) milk chocolate candy bars with almonds, divided", "1 (12 oz.) carton thawed Cool Whip"] ["Prepare cake batter according to directions on box.", "Pour into 2 greased and floured 8-inch round cake pans.", "Bake at 325\\u00b0 for 20 to 25 minutes.", "Cool and divide to make 4 layers."]',
    'Chili Sauce ["12 ripe tomatoes", "4 onions", "2 green peppers", "1 red pepper", "4 Tbsp. sugar", "2 Tbsp. salt", "2 tsp. cinnamon", "2 tsp. cloves", "2 tsp. allspice", "1 tsp. ginger", "1 qt. vinegar"] ["Peel onions and tomatoes, seed peppers and chop all fine, add the spices and put over the fire. Boil steadily for two hours; cool, bottle and seal."]',
]
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: 4,149 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: 42 tokens mean: 136.35 tokens max: 326 tokens	min: 34 tokens mean: 137.99 tokens max: 358 tokens	min: 0.0 mean: 0.24 max: 1.0

Samples:

sentence_0	sentence_1	label
`Quick Barbecue Wings ["chicken wings (as many as you need for dinner)", "flour", "barbecue sauce (your choice)"] ["Clean wings.", "Flour and fry until done.", "Place fried chicken wings in microwave bowl.", "Stir in barbecue sauce.", "Microwave on High (stir once) for 4 minutes."]`	Spaghetti Sauce To Can ["1/2 bushel tomatoes", "1 c. oil", "1/4 c. minced garlic", "6 cans tomato paste", "3 peppers (2 sweet and 1 hot)", "1 1/2 c. sugar", "1/2 c. salt", "1 Tbsp. sweet basil", "2 Tbsp. oregano", "1 tsp. Italian seasoning"] ["Cook ground or chopped peppers and onions in oil for 1/2 hour. Cook tomatoes and garlic as for juice.", "Put through the mill.", "(I use a food processor and do my tomatoes uncooked.", "I then add the garlic right to the juice.)", "Add peppers and onions to juice and remainder of ingredients.", "Cook approximately 1 hour.", "Put in jars and seal.", "Yields 7 quarts."]	`0.15000000000000002`
`Grandma Mary'S Butter Cookies ["1 c. sweet butter", "1 c. granulated sugar", "3 egg yolks", "2 1/2 c. sifted flour", "1 tsp. vanilla"] ["Cream butter.", "Beat into sugar.", "Add egg yolks and vanilla. Beat well after adding each yolk.", "Add flour and beat after each 1/2 cup is added.", "Chill about 1 hour."]`	Magic Cookie Bars ["1/2 c. butter", "1 1/2 c. graham cracker crumbs", "1 (14 oz.) can Eagle Brand milk", "6 oz. semi-sweet chocolate chips", "1 (3 1/2 oz.) can flaked coconut (1 1/2 c.)", "1 c. chopped nuts"] ["Preheat oven to 350\u00b0 (325\u00b0 for glass dish).", "In 13 x 9-inch pan, melt butter in oven.", "Sprinkle with crumbs.", "Top with Eagle Brand milk evenly.", "Top with remaining ingredients.", "Press down. Bake 25 to 30 minutes until lightly brown.", "Cool or chill.", "Cut into bars; store, loosely covered, at room temperature."]	`0.65`
`Angel Biscuits ["5 c. flour", "3 Tbsp. sugar", "4 tsp. baking powder", "1 1/2 pkg. dry yeast", "2 c. buttermilk", "1 tsp. soda", "1 1/2 sticks margarine", "1/2 c. warm water"] ["Mix flour, sugar, baking powder, soda and salt together.", "Cut in margarine, dissolve yeast in warm water.", "Stir into buttermilk and add to dry mixture.", "Cover and chill."]`	Mexican Cookie Rings ["1 1/2 c. sifted flour", "1/2 tsp. baking powder", "1/2 tsp. salt", "1/2 c. butter", "2/3 c. sugar", "3 egg yolks", "1 tsp. vanilla", "multi-colored candies"] ["Sift flour, baking powder and salt together.", "Cream together butter and sugar.", "Add egg yolks and vanilla.", "Beat until light and fluffy.", "Mix in sifted dry ingredients.", "Shape into 1-inch balls.", "Push wooden spoon handle through center (twist).", "Shape into rings.", "Dip each cookie into candies.", "Place on lightly greased baking sheets.", "Bake in 375\u00b0 oven for 10 to 12 minutes or until golden brown.", "Cool on racks.", "Serves 2 dozen."]	`0.1`

Loss: CosineSimilarityLoss with these parameters:

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

Training Hyperparameters

Non-Default Hyperparameters

per_device_train_batch_size: 16
per_device_eval_batch_size: 16
num_train_epochs: 1
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: 16
per_device_eval_batch_size: 16
per_gpu_train_batch_size: None
per_gpu_eval_batch_size: None
gradient_accumulation_steps: 1
eval_accumulation_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: 1
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: False
hub_always_push: False
gradient_checkpointing: False
gradient_checkpointing_kwargs: None
include_inputs_for_metrics: False
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
batch_sampler: batch_sampler
multi_dataset_batch_sampler: round_robin

Framework Versions

Python: 3.10.12
Sentence Transformers: 3.0.0
Transformers: 4.41.1
PyTorch: 2.3.0+cu121
Accelerate: 0.30.0
Datasets: 2.19.1
Tokenizers: 0.19.1

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",
}

jeevansai93
/

Jeevan_cv_run2_roberta_5_epoc