DialoGPT-large-faqs-block-size-128-bs-16-lr-1e-5

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: 2.4141

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	40	4.1341
No log	2.0	80	3.3205
No log	3.0	120	2.9338
No log	4.0	160	2.7297
No log	5.0	200	2.6011
No log	6.0	240	2.5211
No log	7.0	280	2.4694
No log	8.0	320	2.4361
No log	9.0	360	2.4157
No log	10.0	400	2.4106
No log	11.0	440	2.3993
No log	12.0	480	2.3882
2.5448	13.0	520	2.3927
2.5448	14.0	560	2.3963
2.5448	15.0	600	2.3977
2.5448	16.0	640	2.4073
2.5448	17.0	680	2.4045
2.5448	18.0	720	2.4151
2.5448	19.0	760	2.4156
2.5448	20.0	800	2.4141

Framework versions

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