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-abusive-comments-ta
    results: []

indic-sentence-bert-nli-abusive-comments-ta

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: 1.3335
Accuracy: 0.6148
Precision: 0.0769
Recall: 0.125
F1: 0.0952

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: 16
eval_batch_size: 128
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 32
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
1.3249	1.0	186	1.3335	0.6176	0.0772	0.125	0.0955
1.3468	2.0	372	1.3318	0.6176	0.0772	0.125	0.0955
1.3534	3.0	558	1.3310	0.6176	0.0772	0.125	0.0955
1.1991	4.0	744	1.3412	0.6176	0.0772	0.125	0.0955
1.3534	5.0	930	1.3315	0.6176	0.0772	0.125	0.0955
1.4725	6.0	1116	1.3313	0.6176	0.0772	0.125	0.0955
1.3451	7.0	1302	1.3314	0.6176	0.0772	0.125	0.0955
1.315	8.0	1488	1.3315	0.6176	0.0772	0.125	0.0955
1.3157	9.0	1674	1.3324	0.6176	0.0772	0.125	0.0955
1.2015	10.0	1860	1.3319	0.6176	0.0772	0.125	0.0955

Framework versions

Transformers 4.45.1
Pytorch 2.4.0
Datasets 3.0.1
Tokenizers 0.20.0