q1

This model is a fine-tuned version of distilbert/distilgpt2 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.0078

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: 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: 20

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	1	0.0221
No log	2.0	2	0.0199
No log	3.0	3	0.0181
No log	4.0	4	0.0166
No log	5.0	5	0.0153
No log	6.0	6	0.0140
No log	7.0	7	0.0130
No log	8.0	8	0.0120
No log	9.0	9	0.0112
No log	10.0	10	0.0105
No log	11.0	11	0.0099
No log	12.0	12	0.0095
No log	13.0	13	0.0091
No log	14.0	14	0.0087
No log	15.0	15	0.0084
No log	16.0	16	0.0082
No log	17.0	17	0.0080
No log	18.0	18	0.0079
No log	19.0	19	0.0078
No log	20.0	20	0.0078

Framework versions

• Transformers 4.38.2
• Pytorch 2.2.1+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2