gpt2-text-simplification_1e4_adafactor_biendata

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

• Loss: 0.9089

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: 0.0001
• 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	464	0.7729
1.0489	2.0	928	0.7546
0.754	3.0	1392	0.7497
0.7034	4.0	1856	0.7530
0.6619	5.0	2320	0.7560
0.6265	6.0	2784	0.7639
0.5921	7.0	3248	0.7747
0.5621	8.0	3712	0.7848
0.5359	9.0	4176	0.7969
0.5115	10.0	4640	0.8113
0.4879	11.0	5104	0.8256
0.4683	12.0	5568	0.8373
0.4491	13.0	6032	0.8519
0.4491	14.0	6496	0.8642
0.4324	15.0	6960	0.8741
0.4176	16.0	7424	0.8841
0.4054	17.0	7888	0.8924
0.3946	18.0	8352	0.8994
0.3868	19.0	8816	0.9043
0.3813	20.0	9280	0.9089

Framework versions

• Transformers 4.30.2
• Pytorch 2.0.1+cu118
• Datasets 2.13.1
• Tokenizers 0.13.3