README.md

metadata

base_model: ai-forever/ruRoberta-large
tags:
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: logs
    results: []

logs

This model is a fine-tuned version of ai-forever/ruRoberta-large on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 3.5528
• Accuracy: 0.4286

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: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 30

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	95	3.0691	0.2857
No log	2.0	190	2.3608	0.4656
No log	3.0	285	2.8215	0.4180
No log	4.0	380	2.7833	0.3651
No log	5.0	475	2.3186	0.4550
0.5693	6.0	570	2.3792	0.4180
0.5693	7.0	665	2.5442	0.4603
0.5693	8.0	760	2.6696	0.4444
0.5693	9.0	855	2.3096	0.4762
0.5693	10.0	950	2.8165	0.4550
0.4429	11.0	1045	3.2277	0.4233
0.4429	12.0	1140	3.0367	0.4233
0.4429	13.0	1235	3.3685	0.4127
0.4429	14.0	1330	3.3807	0.4180
0.4429	15.0	1425	3.5592	0.4021
0.3361	16.0	1520	3.8085	0.3915
0.3361	17.0	1615	3.3284	0.4233
0.3361	18.0	1710	3.2054	0.4339
0.3361	19.0	1805	3.6119	0.4180
0.3361	20.0	1900	3.5837	0.4339
0.3361	21.0	1995	3.4894	0.4180
0.2764	22.0	2090	3.3315	0.4074
0.2764	23.0	2185	3.5583	0.4127
0.2764	24.0	2280	3.4930	0.4127
0.2764	25.0	2375	3.5141	0.4339
0.2764	26.0	2470	3.5180	0.4339
0.2182	27.0	2565	3.6063	0.4233
0.2182	28.0	2660	3.5765	0.4233
0.2182	29.0	2755	3.5506	0.4233
0.2182	30.0	2850	3.5528	0.4286

Framework versions

• Transformers 4.38.2
• Pytorch 2.2.1+cu121
• Datasets 2.19.0
• Tokenizers 0.15.2