metadata

library_name: transformers
license: cc-by-4.0
base_model: l3cube-pune/indic-sentence-bert-nli
tags:
  - generated_from_trainer
metrics:
  - accuracy
  - precision
  - recall
  - f1
model-index:
  - name: indic-sentence-bert-nli-hinglish-binary
    results: []

indic-sentence-bert-nli-hinglish-binary

This model is a fine-tuned version of l3cube-pune/indic-sentence-bert-nli on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.5934
Accuracy: 0.6987
Precision: 0.6929
Recall: 0.6155
F1: 0.6125

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 5e-05
train_batch_size: 32
eval_batch_size: 128
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 128
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1
0.663	0.9709	25	0.6551	0.6376	0.3188	0.5	0.3894
0.6284	1.9806	51	0.6314	0.6676	0.7906	0.5430	0.4785
0.6266	2.9903	77	0.6725	0.5095	0.6373	0.5975	0.4974
0.6261	4.0	103	0.6008	0.7112	0.7124	0.6307	0.6311
0.6202	4.9709	128	0.6025	0.7057	0.7005	0.6264	0.6265
0.5987	5.9806	154	0.5907	0.7112	0.7216	0.6258	0.6236
0.5856	6.9903	180	0.5818	0.7193	0.7253	0.6404	0.6427
0.5753	8.0	206	0.5804	0.7166	0.7502	0.6252	0.6201
0.5416	8.9709	231	0.5667	0.7221	0.7424	0.6376	0.6378
0.5419	9.7087	250	0.5599	0.7330	0.7439	0.6575	0.6632

Framework versions

Transformers 4.45.1
Pytorch 2.4.0
Datasets 3.0.1
Tokenizers 0.20.0