You can deploy this model and start earning money today!

sy-volkov/
rubert-tiny2-sentiment-tuned2

Name: rubert-tiny2-sentiment-tuned2
Availability: InStock

generated_from_trainer

seara/rubert-tiny2-russian-sentiment

Views

No views yet

rubert-tiny2-sentiment-tuned2

This model is a fine-tuned version of seara/rubert-tiny2-russian-sentiment on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.2691
Accuracy: 0.9151
F1: 0.9227

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: 2e-07
train_batch_size: 32
eval_batch_size: 32
seed: 42
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
num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
0.535	0.1926	500	0.4057	0.8544	0.8991
0.3757	0.3852	1000	0.3217	0.8964	0.9164
0.3092	0.5778	1500	0.2882	0.9093	0.9209
0.287	0.7704	2000	0.2742	0.9132	0.9220
0.2854	0.9630	2500	0.2691	0.9151	0.9227

Framework versions

Transformers 4.48.3
Pytorch 2.5.1+cu124
Datasets 3.3.1
Tokenizers 0.21.0

sy-volkov/rubert-tiny2-sentiment-tuned2

rubert-tiny2-sentiment-tuned2

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

sy-volkov/
rubert-tiny2-sentiment-tuned2