Hugging Face's logo

ammumadhu
/
Indic_Bert-8-layers

Sentence Similarity
sentence-transformers
Safetensors
English
bert
feature-extraction
dataset_size:1M<n<10M
loss:MSELoss
Eval Results (legacy)
text-embeddings-inference
Model card Files
xet
 Community
Indic_Bert-8-layers / README.md
ammumadhu's picture
ammumadhu
Add new SentenceTransformer model.
31ce749 verified
preview code
|
raw
history blame contribute delete
19.3 kB
metadata 
language:
  - en
library_name: sentence-transformers
tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - dataset_size:1M<n<10M
  - loss:MSELoss
base_model: l3cube-pune/indic-sentence-similarity-sbert
metrics:
  - pearson_cosine
  - spearman_cosine
  - pearson_manhattan
  - spearman_manhattan
  - pearson_euclidean
  - spearman_euclidean
  - pearson_dot
  - spearman_dot
  - pearson_max
  - spearman_max
  - negative_mse
widget:
  - source_sentence: Nobody is standing
    sentences:
      - The person staring has no vision.
      - The person in black T-shirt is sitting.
      - The two girls are at the amusement park.
  - source_sentence: The door is open.
    sentences:
      - A child is looking out of a door.
      - a woman is shopping by fisher's popcorn
      - Team owner, president and head coach Don Sims is a Christian.
  - source_sentence: A man is jogging.
    sentences:
      - A man is rock climbing with protective rope.
      - There is a Coca-Cola sign on a building.
      - A group of women are selling their wares
  - source_sentence: A woman is outside
    sentences:
      - A girl is posing outside.
      - A woman is having a drink with a friend.
      - The man is sitting on Santa's lap.
  - source_sentence: Men are outdoors.
    sentences:
      - A man is outside.
      - A Little girl is enjoying cake outside.
      - The child is dancing inside.
pipeline_tag: sentence-similarity
model-index:
  - name: SentenceTransformer based on l3cube-pune/indic-sentence-similarity-sbert
    results:
      - task:
          type: semantic-similarity
          name: Semantic Similarity
        dataset:
          name: sts dev
          type: sts-dev
        metrics:
          - type: pearson_cosine
            value: 0.6061168880496322
            name: Pearson Cosine
          - type: spearman_cosine
            value: 0.63159627628102
            name: Spearman Cosine
          - type: pearson_manhattan
            value: 0.4867734432158827
            name: Pearson Manhattan
          - type: spearman_manhattan
            value: 0.5132315973464433
            name: Spearman Manhattan
          - type: pearson_euclidean
            value: 0.5060055860550953
            name: Pearson Euclidean
          - type: spearman_euclidean
            value: 0.530647353370298
            name: Spearman Euclidean
          - type: pearson_dot
            value: 0.2197998289852973
            name: Pearson Dot
          - type: spearman_dot
            value: 0.2098437681521414
            name: Spearman Dot
          - type: pearson_max
            value: 0.6061168880496322
            name: Pearson Max
          - type: spearman_max
            value: 0.63159627628102
            name: Spearman Max
      - task:
          type: knowledge-distillation
          name: Knowledge Distillation
        dataset:
          name: Unknown
          type: unknown
        metrics:
          - type: negative_mse
            value: -3.0273379758000374
            name: Negative Mse
      - task:
          type: semantic-similarity
          name: Semantic Similarity
        dataset:
          name: sts test
          type: sts-test
        metrics:
          - type: pearson_cosine
            value: 0.7908829263963781
            name: Pearson Cosine
          - type: spearman_cosine
            value: 0.7964877056053918
            name: Spearman Cosine
          - type: pearson_manhattan
            value: 0.7759961128627
            name: Pearson Manhattan
          - type: spearman_manhattan
            value: 0.7730137991653084
            name: Spearman Manhattan
          - type: pearson_euclidean
            value: 0.7764317252322528
            name: Pearson Euclidean
          - type: spearman_euclidean
            value: 0.7735945428555226
            name: Spearman Euclidean
          - type: pearson_dot
            value: 0.6958642398985296
            name: Pearson Dot
          - type: spearman_dot
            value: 0.6842506896957747
            name: Spearman Dot
          - type: pearson_max
            value: 0.7908829263963781
            name: Pearson Max
          - type: spearman_max
            value: 0.7964877056053918
            name: Spearman Max

SentenceTransformer based on l3cube-pune/indic-sentence-similarity-sbert

This is a sentence-transformers model finetuned from l3cube-pune/indic-sentence-similarity-sbert. 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 Sources

Full Model Architecture 

SentenceTransformer(
  (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel 
  (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("ammumadhu/Indic_Bert-8-layers")
# Run inference
sentences = [
    'Men are outdoors.',
    'A man is outside.',
    'A Little girl is enjoying cake outside.',
]
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]

Evaluation

Metrics

Semantic Similarity

Metric Value
pearson_cosine 0.6061
spearman_cosine 0.6316
pearson_manhattan 0.4868
spearman_manhattan 0.5132
pearson_euclidean 0.506
spearman_euclidean 0.5306
pearson_dot 0.2198
spearman_dot 0.2098
pearson_max 0.6061
spearman_max 0.6316

Knowledge Distillation

Metric Value
negative_mse -3.0273

Semantic Similarity

Metric Value
pearson_cosine 0.7909
spearman_cosine 0.7965
pearson_manhattan 0.776
spearman_manhattan 0.773
pearson_euclidean 0.7764
spearman_euclidean 0.7736
pearson_dot 0.6959
spearman_dot 0.6843
pearson_max 0.7909
spearman_max 0.7965

Training Details

Training Dataset

Unnamed Dataset

  • Size: 1,147,385 training samples
  • Columns: sentence and label
  • Approximate statistics based on the first 1000 samples:
    sentence label
    type string list
    details
    • min: 4 tokens
    • mean: 12.59 tokens
    • max: 52 tokens
    • size: 768 elements
  • Samples:
    sentence label
    A person on a horse jumps over a broken down airplane. [-0.0009042086312547326, 0.02319158799946308, 0.016657305881381035, -0.004571350757032633, -0.008184989914298058, ...]
    Children smiling and waving at camera [-0.020024249330163002, -0.0005705401999875903, 0.025419672951102257, -0.014105383306741714, 0.009407470934092999, ...]
    A boy is jumping on skateboard in the middle of a red bridge. [-0.01713346689939499, -2.3264645278686658e-05, -0.0005397812929004431, 0.002506087301298976, 0.027286207303404808, ...]
  • Loss: MSELoss

Evaluation Dataset

sentence-transformers/wikipedia-en-sentences

  • Dataset: sentence-transformers/wikipedia-en-sentences at 4a0972d
  • Size: 10,000 evaluation samples
  • Columns: sentence and label
  • Approximate statistics based on the first 1000 samples:
    sentence label
    type string list
    details
    • min: 5 tokens
    • mean: 13.53 tokens
    • max: 61 tokens
    • size: 768 elements
  • Samples:
    sentence label
    Two women are embracing while holding to go packages. [-0.000599742284975946, 0.0042074089869856834, 0.0013686479069292545, -0.0009170330595225096, -0.010106148198246956, ...]
    Two young children in blue jerseys, one with the number 9 and one with the number 2 are standing on wooden steps in a bathroom and washing their hands in a sink. [0.003711540251970291, -0.005768307950347662, -0.03475787863135338, 0.010626137256622314, -0.0023863380774855614, ...]
    A man selling donuts to a customer during a world exhibition event held in the city of Angeles [-0.014246350154280663, 0.015385480597615242, 0.0016394935082644224, -0.013386472128331661, -0.015061145648360252, ...]
  • Loss: MSELoss

Training Hyperparameters

Non-Default Hyperparameters

  • eval_strategy: steps
  • per_device_train_batch_size: 64
  • per_device_eval_batch_size: 64
  • learning_rate: 0.0001
  • num_train_epochs: 1
  • warmup_ratio: 0.1
  • fp16: True
  • load_best_model_at_end: True

All Hyperparameters

Click to expand
  • overwrite_output_dir: False
  • do_predict: False
  • eval_strategy: steps
  • prediction_loss_only: True
  • per_device_train_batch_size: 64
  • per_device_eval_batch_size: 64
  • per_gpu_train_batch_size: None
  • per_gpu_eval_batch_size: None
  • gradient_accumulation_steps: 1
  • eval_accumulation_steps: None
  • learning_rate: 0.0001
  • weight_decay: 0.0
  • adam_beta1: 0.9
  • adam_beta2: 0.999
  • adam_epsilon: 1e-08
  • max_grad_norm: 1.0
  • num_train_epochs: 1
  • max_steps: -1
  • lr_scheduler_type: linear
  • lr_scheduler_kwargs: {}
  • warmup_ratio: 0.1
  • 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: 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: True
  • 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: proportional

Training Logs

Epoch Step Training Loss negative_mse sts-dev_spearman_cosine sts-test_spearman_cosine
0 0 - -3.0273 0.6316 -
0.2231 1000 0.0015 - - -
0.4462 2000 0.0001 - - -
0.6693 3000 0.0001 - - -
0.8925 4000 0.0001 - - -
1.0 4482 - - - 0.7965

Framework Versions

  • Python: 3.10.14
  • Sentence Transformers: 3.0.0
  • Transformers: 4.41.2
  • PyTorch: 2.1.0
  • Accelerate: 0.30.1
  • Datasets: 2.19.2
  • 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",
}

MSELoss 

@inproceedings{reimers-2020-multilingual-sentence-bert,
    title = "Making Monolingual Sentence Embeddings Multilingual using Knowledge Distillation",
    author = "Reimers, Nils and Gurevych, Iryna",
    booktitle = "Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing",
    month = "11",
    year = "2020",
    publisher = "Association for Computational Linguistics",
    url = "https://arxiv.org/abs/2004.09813",
}