gpt2_bwgenerator

This model is a fine-tuned version of openai-community/gpt2 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.1070

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: 5e-05
• train_batch_size: 32
• eval_batch_size: 32
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss
0.5956	0.1574	300	0.1631
0.1683	0.3148	600	0.1376
0.1471	0.4722	900	0.1288
0.1364	0.6296	1200	0.1198
0.1302	0.7870	1500	0.1188
0.1262	0.9444	1800	0.1147
0.1233	1.1018	2100	0.1122
0.1208	1.2592	2400	0.1108
0.119	1.4166	2700	0.1098
0.1176	1.5740	3000	0.1084
0.1161	1.7314	3300	0.1084
0.1153	1.8888	3600	0.1070

Framework versions

• Transformers 4.44.0
• Pytorch 2.3.0+cu121
• Datasets 2.14.7
• Tokenizers 0.19.1