gpt2-NaturalQuestions_2000-ep20

This model is a fine-tuned version of gpt2 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.3117

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: 48
• eval_batch_size: 96
• seed: 1799
• 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
1.77	1.19	50	1.3795
1.3768	2.38	100	1.3164
1.2208	3.57	150	1.2818
1.1183	4.76	200	1.2704
1.0477	5.95	250	1.2626
0.9721	7.14	300	1.2632
0.914	8.33	350	1.2670
0.8714	9.52	400	1.2714
0.835	10.71	450	1.2737
0.7959	11.9	500	1.2799
0.7513	13.1	550	1.2892
0.7323	14.29	600	1.2951
0.7097	15.48	650	1.3033
0.6948	16.67	700	1.3060
0.6764	17.86	750	1.3094
0.6655	19.05	800	1.3115

Framework versions

• Transformers 4.29.2
• Pytorch 1.10.0+cu111
• Datasets 2.5.1
• Tokenizers 0.13.3