DialoGPT-large-faqs-block-size-350-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: 2.5721

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	15	5.5711
No log	2.0	30	4.8235
No log	3.0	45	4.2941
No log	4.0	60	3.8396
No log	5.0	75	3.5024
No log	6.0	90	3.2479
No log	7.0	105	3.0807
No log	8.0	120	2.9507
No log	9.0	135	2.8704
No log	10.0	150	2.8030
No log	11.0	165	2.7481
No log	12.0	180	2.6972
No log	13.0	195	2.6681
No log	14.0	210	2.6349
No log	15.0	225	2.6192
No log	16.0	240	2.5990
No log	17.0	255	2.5850
No log	18.0	270	2.5767
No log	19.0	285	2.5741
No log	20.0	300	2.5721

Framework versions

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