SentenceTransformer based on sanganaka/bge-m3-sanskritFT

This is a sentence-transformers model finetuned from sanganaka/bge-m3-sanskritFT. It maps sentences & paragraphs to a 1024-dimensional dense vector space and can be used for retrieval.

Model Details

Model Description

Model Type: Sentence Transformer
Base model: sanganaka/bge-m3-sanskritFT
Maximum Sequence Length: 256 tokens
Output Dimensionality: 1024 dimensions
Similarity Function: Cosine Similarity
Supported Modality: Text

Model Sources

Documentation: Sentence Transformers Documentation
Repository: Sentence Transformers on GitHub
Hugging Face: Sentence Transformers on Hugging Face

Full Model Architecture

SentenceTransformer(
  (0): Transformer({'transformer_task': 'feature-extraction', 'modality_config': {'text': {'method': 'forward', 'method_output_name': 'last_hidden_state'}}, 'module_output_name': 'token_embeddings', 'architecture': 'XLMRobertaModel'})
  (1): Pooling({'embedding_dimension': 1024, 'pooling_mode': 'cls', '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 = [
    "I've been grieving a significant loss for a long time, and while I know I need to move forward, my thoughts constantly pull me back to the past. How do I let go and find peace?",
    'uddhared ātmanātmānaṃ nātmānam avasādayet | ātmaiva hy ātmano bandhur ātmaiva ripur ātmanaḥ ||5||',
    'etair vimuktaḥ kaunteya tamo-dvārais tribhir naraḥ | ācaraty ātmanaḥ śreyas tato yāti parāṃ gatim ||22||',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 1024]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities)
# tensor([[1.0000, 0.4964, 0.1087],
#         [0.4964, 1.0000, 0.3406],
#         [0.1087, 0.3406, 1.0000]])

Training Details

Training Dataset

Unnamed Dataset

Size: 4,858 training samples
Columns: sentence_0, sentence_1, and sentence_2

Approximate statistics based on the first 100 samples:

	sentence_0	sentence_1	sentence_2
type	string	string	string
modality	text	text	text
details	min: 18 tokens mean: 46.5 tokens max: 72 tokens	min: 34 tokens mean: 66.11 tokens max: 242 tokens	min: 42 tokens mean: 84.2 tokens max: 256 tokens

Samples:

sentence_0	sentence_1	sentence_2
`As a professional, I feel constantly burnt out, always chasing the next promotion or project. I've lost touch with why I even started, and joy seems like a distant memory. Is there a way to reconnect with my passion?`	`yaṃ labdhvā cāparaṃ lābhaṃ manyate nādhikaṃ tataḥ \| yasmin sthito na duḥkhena guruṇāpi vicālyate \|\|22\|\| taṃ vidyād duḥkha-saṃyoga-viyogaṃ yoga-saṃjñitam \| sa niścayena yoktavyo yogo 'nirviṇṇa-cetasā \|\|23\|\|`	`yaṃ hi na vyathayanty ete puruṣaṃ puruṣarṣabha \| sama-duḥkha-sukhaṃ dhīraṃ so 'mṛtatvāya kalpate \|\|15\|\|`
`My teenage son is rebelling and pushing me away. I feel like I'm losing him. What can I do?`	`ayaneṣu ca sarveṣu yathābhāgam avasthitāḥ \| bhīṣmam evābhirakṣantu bhavantaḥ sarva eva hi \|\|11\|\|`	`acchedyo 'yam adāhyo 'yam akledyo 'śoṣya eva ca \| nityaḥ sarva-gataḥ sthāṇur acalo 'yaṃ sanātanaḥ \|\|24\|\|`
`I'm constantly worried about the future – what if my plans fail? What if things don't go my way? This anxiety paralyzes me and prevents me from acting.`	`yajñadānatapaḥkarma na tyājyaṃ kāryam eva tat \| yajño dānaṃ tapaś caiva pāvanāni manīṣiṇām \|\|5\|\|`	`ahiṃsā samatā tuṣṭis tapo dānaṃ yaśo 'yaśaḥ \| bhavanti bhāvā bhūtānāṃ matta eva pṛthagvidhāḥ \|\|5\|\|`

Loss: MultipleNegativesRankingLoss with these parameters:

{
    "scale": 20.0,
    "similarity_fct": "cos_sim",
    "gather_across_devices": false,
    "directions": [
        "query_to_doc"
    ],
    "partition_mode": "joint",
    "hardness_mode": null,
    "hardness_strength": 0.0
}

Training Hyperparameters

Non-Default Hyperparameters

per_device_train_batch_size: 16
num_train_epochs: 2
per_device_eval_batch_size: 16
multi_dataset_batch_sampler: round_robin

All Hyperparameters

Click to expand

per_device_train_batch_size: 16
num_train_epochs: 2
max_steps: -1
learning_rate: 5e-05
lr_scheduler_type: linear
lr_scheduler_kwargs: None
warmup_steps: 0
optim: adamw_torch_fused
optim_args: None
weight_decay: 0.0
adam_beta1: 0.9
adam_beta2: 0.999
adam_epsilon: 1e-08
optim_target_modules: None
gradient_accumulation_steps: 1
average_tokens_across_devices: True
max_grad_norm: 1
label_smoothing_factor: 0.0
bf16: False
fp16: False
bf16_full_eval: False
fp16_full_eval: False
tf32: None
gradient_checkpointing: False
gradient_checkpointing_kwargs: None
torch_compile: False
torch_compile_backend: None
torch_compile_mode: None
use_liger_kernel: False
liger_kernel_config: None
use_cache: False
neftune_noise_alpha: None
torch_empty_cache_steps: None
auto_find_batch_size: False
log_on_each_node: True
logging_nan_inf_filter: True
include_num_input_tokens_seen: no
log_level: passive
log_level_replica: warning
disable_tqdm: False
project: huggingface
trackio_space_id: None
trackio_bucket_id: None
trackio_static_space_id: None
per_device_eval_batch_size: 16
prediction_loss_only: True
eval_on_start: False
eval_do_concat_batches: True
eval_use_gather_object: False
eval_accumulation_steps: None
include_for_metrics: []
batch_eval_metrics: False
save_only_model: False
save_on_each_node: False
enable_jit_checkpoint: False
push_to_hub: False
hub_private_repo: None
hub_model_id: None
hub_strategy: every_save
hub_always_push: False
hub_revision: None
load_best_model_at_end: False
ignore_data_skip: False
restore_callback_states_from_checkpoint: False
full_determinism: False
seed: 42
data_seed: None
use_cpu: 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
dataloader_drop_last: False
dataloader_num_workers: 0
dataloader_pin_memory: True
dataloader_persistent_workers: False
dataloader_prefetch_factor: None
remove_unused_columns: True
label_names: None
train_sampling_strategy: random
length_column_name: length
ddp_find_unused_parameters: None
ddp_bucket_cap_mb: None
ddp_broadcast_buffers: False
ddp_static_graph: None
ddp_backend: None
ddp_timeout: 1800
fsdp: None
fsdp_config: None
deepspeed: None
debug: []
skip_memory_metrics: True
do_predict: False
resume_from_checkpoint: None
warmup_ratio: None
local_rank: -1
prompts: None
batch_sampler: batch_sampler
multi_dataset_batch_sampler: round_robin
router_mapping: {}
learning_rate_mapping: {}

Training Logs

Epoch	Step	Training Loss
1.6447	500	2.8599

Training Time

Training: 10.0 minutes

Framework Versions

Python: 3.11.12
Sentence Transformers: 5.5.1
Transformers: 5.12.1
PyTorch: 2.12.0+cu130
Accelerate: 1.14.0
Datasets: 5.0.0
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",
}

MultipleNegativesRankingLoss

@misc{oord2019representationlearningcontrastivepredictive,
      title={Representation Learning with Contrastive Predictive Coding},
      author={Aaron van den Oord and Yazhe Li and Oriol Vinyals},
      year={2019},
      eprint={1807.03748},
      archivePrefix={arXiv},
      primaryClass={cs.LG},
      url={https://arxiv.org/abs/1807.03748},
}