test_trainer_16_05

This model is a fine-tuned version of sismetanin/rubert-ru-sentiment-rusentiment on the None dataset. It achieves the following results on the evaluation set:

Loss: 1.2726
Accuracy: 0.8545
Precision: 0.8305
Recall: 0.8909
F1: 0.8596

Model description

A fine-tuned version of Ru-BERT, finetuned on sentiment analysis tasks. Two class sarcasm detection, trained on a manually annotated dataset of russian negative product reviews (3 annotators), partially tested on an ambiguious data.

Intended uses & limitations

More information needed

Training and evaluation data

A manually annotated dataset of russian negative product reviews (3 annotators)

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 5e-05
train_batch_size: 8
eval_batch_size: 8
seed: 29
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
num_epochs: 8
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1
No log	1.0	96	0.6391	0.7091	0.6949	0.7455	0.7193
No log	2.0	192	0.5919	0.7545	0.7188	0.8364	0.7731
No log	3.0	288	0.6562	0.8364	0.7937	0.9091	0.8475
No log	4.0	384	1.2275	0.8	0.7391	0.9273	0.8226
No log	5.0	480	1.2310	0.8364	0.8033	0.8909	0.8448
0.3037	6.0	576	1.2434	0.8545	0.8305	0.8909	0.8596
0.3037	7.0	672	1.3317	0.8364	0.8033	0.8909	0.8448
0.3037	8.0	768	1.2726	0.8545	0.8305	0.8909	0.8596

Framework versions

Transformers 4.51.3
Pytorch 2.6.0+cu124
Datasets 2.14.4
Tokenizers 0.21.1

MaryObr
/

sarcasm-RuBERT