rus_gpt2_3_epoch

This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:

• Loss: 2.8266

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: 0.005
• train_batch_size: 128
• eval_batch_size: 128
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 50
• num_epochs: 1
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
3.8634	0.2411	2000	3.4019
3.3647	0.4821	4000	3.1744
3.1311	0.7232	6000	2.9441
2.9332	0.9642	8000	2.8266

Framework versions

• Transformers 4.42.4
• Pytorch 2.3.1+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1