distilgpt2-lotr

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

• Loss: 3.3901

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: 64
• eval_batch_size: 64
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 15
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	73	3.6392
No log	2.0	146	3.5466
No log	3.0	219	3.5038
No log	4.0	292	3.4761
No log	5.0	365	3.4546
No log	6.0	438	3.4379
3.6024	7.0	511	3.4265
3.6024	8.0	584	3.4160
3.6024	9.0	657	3.4096
3.6024	10.0	730	3.4025
3.6024	11.0	803	3.3969
3.6024	12.0	876	3.3933
3.6024	13.0	949	3.3916
3.4101	14.0	1022	3.3910
3.4101	15.0	1095	3.3901

Framework versions

• Transformers 4.20.1
• Pytorch 1.11.0
• Datasets 2.1.0
• Tokenizers 0.12.1