python-gpt2-large-issues-128

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

• Loss: 1.2286

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: 5e-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: 16

Training results

Training Loss	Epoch	Step	Validation Loss
1.9843	1.0	1163	1.6715
1.5713	2.0	2326	1.4301
1.4226	3.0	3489	1.3808
1.332	4.0	4652	1.3806
1.2708	5.0	5815	1.2737
1.2089	6.0	6978	1.2354
1.167	7.0	8141	1.2250
1.126	8.0	9304	1.2262
1.0846	9.0	10467	1.1891
1.0647	10.0	11630	1.2263
1.0301	11.0	12793	1.1383
1.0054	12.0	13956	1.0922
0.9714	13.0	15119	1.1141
0.9713	14.0	16282	1.1614
0.9362	15.0	17445	1.0753
0.9382	16.0	18608	1.2286

Framework versions

• Transformers 4.17.0
• Pytorch 1.10.2+cu102
• Datasets 1.18.3
• Tokenizers 0.11.6