DialoGPT-large-faqs-block-size-16-bs-16-lr-1e-05

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

• Loss: 3.7894

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: 1e-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: 20

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	321	3.4739
4.182	2.0	642	3.0932
4.182	3.0	963	2.9670
2.6449	4.0	1284	2.9128
2.0623	5.0	1605	2.9541
2.0623	6.0	1926	3.0378
1.6514	7.0	2247	3.1422
1.3414	8.0	2568	3.2869
1.3414	9.0	2889	3.3904
1.1036	10.0	3210	3.4720
0.9535	11.0	3531	3.5315
0.9535	12.0	3852	3.5810
0.8249	13.0	4173	3.6205
0.8249	14.0	4494	3.6689
0.7545	15.0	4815	3.7067
0.686	16.0	5136	3.7433
0.686	17.0	5457	3.7534
0.649	18.0	5778	3.7751
0.6241	19.0	6099	3.7854
0.6241	20.0	6420	3.7894

Framework versions

• Transformers 4.33.0.dev0
• Pytorch 2.0.1+cu118
• Datasets 2.14.4.dev0
• Tokenizers 0.13.3