distilgpt2-finetuned-wikitext2

This model is a fine-tuned version of distilgpt2 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 3.2676

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: 10

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	28	3.7190
No log	2.0	56	3.5623
No log	3.0	84	3.4554
No log	4.0	112	3.3877
No log	5.0	140	3.3390
No log	6.0	168	3.3063
No log	7.0	196	3.2878
No log	8.0	224	3.2761
No log	9.0	252	3.2698
No log	10.0	280	3.2676

Framework versions

• Transformers 4.33.2
• Pytorch 2.0.1+cu118
• Datasets 2.14.5
• Tokenizers 0.13.3