ru_to_ossbert

This model is a fine-tuned version of ai-forever/ruBert-base on the None dataset. It achieves the following results on the evaluation set:

• Loss: 2.2399

Model description

Ossetic ruBert-base trained for experimental purpose

Training and evaluation data

Ossetic National Corpus (approx. 250K tokens)

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_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.7273	200	2.8286
No log	1.4545	400	2.5696
No log	2.1818	600	2.4407
No log	2.9091	800	2.3352
No log	3.6364	1000	2.3069
No log	4.3636	1200	2.2399

Framework versions

• Transformers 4.57.1
• Pytorch 2.8.0+cu126
• Datasets 4.0.0
• Tokenizers 0.22.1