rubert_tiny2_mlm_finetuned

This model is a fine-tuned version of milfey21/rubert-tiny2-ner-finetuned on the None dataset. It achieves the following results on the evaluation set:

• Loss: 6.1668

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-05
• train_batch_size: 8
• eval_batch_size: 8
• 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: 20

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	100	8.5417
No log	2.0	200	7.9333
No log	3.0	300	7.6217
No log	4.0	400	7.3350
8.0664	5.0	500	7.0997
8.0664	6.0	600	6.9235
8.0664	7.0	700	6.8104
8.0664	8.0	800	6.6791
8.0664	9.0	900	6.5516
6.645	10.0	1000	6.5125
6.645	11.0	1100	6.4116
6.645	12.0	1200	6.3826
6.645	13.0	1300	6.4044
6.645	14.0	1400	6.1985
6.2093	15.0	1500	6.1378
6.2093	16.0	1600	6.2611
6.2093	17.0	1700	6.2383
6.2093	18.0	1800	6.1616
6.2093	19.0	1900	6.1027
6.0505	20.0	2000	6.1668

Framework versions

• Transformers 4.50.0
• Pytorch 2.6.0
• Datasets 3.5.0
• Tokenizers 0.21.1