CPTGPT2

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

• Loss: 2.6245

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: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Use 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	140	2.8133
No log	2.0	280	2.7469
No log	3.0	420	2.7122
2.8365	4.0	560	2.6884
2.8365	5.0	700	2.6759
2.8365	6.0	840	2.6615
2.8365	7.0	980	2.6519
2.543	8.0	1120	2.6480
2.543	9.0	1260	2.6392
2.543	10.0	1400	2.6332
2.402	11.0	1540	2.6298
2.402	12.0	1680	2.6257
2.402	13.0	1820	2.6257
2.402	14.0	1960	2.6266
2.3078	15.0	2100	2.6239
2.3078	16.0	2240	2.6246
2.3078	17.0	2380	2.6240
2.2519	18.0	2520	2.6252
2.2519	19.0	2660	2.6250
2.2519	20.0	2800	2.6245

Framework versions

• Transformers 4.46.1
• Pytorch 2.4.0+cu121
• Datasets 3.0.1
• Tokenizers 0.20.1