gpt2-text-simplification_1e4_adafactor

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

• Loss: 0.8713

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: 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: 20

Training results

Training Loss	Epoch	Step	Validation Loss
0.8976	1.0	2326	0.8092
0.8236	2.0	4652	0.7974
0.7807	3.0	6978	0.7940
0.7428	4.0	9304	0.7916
0.7094	5.0	11630	0.7955
0.6828	6.0	13956	0.7996
0.6569	7.0	16282	0.8046
0.6365	8.0	18608	0.8103
0.616	9.0	20934	0.8175
0.6001	10.0	23260	0.8212
0.5819	11.0	25586	0.8291
0.5688	12.0	27912	0.8368
0.5562	13.0	30238	0.8378
0.5437	14.0	32564	0.8462
0.5299	15.0	34890	0.8497
0.5242	16.0	37216	0.8568
0.5158	17.0	39542	0.8643
0.5088	18.0	41868	0.8676
0.5027	19.0	44194	0.8703
0.4989	20.0	46520	0.8713

Framework versions

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