DialoGPT-large-faqs-block-size-128-bs-16-lr-1e-05-deepspeed-True

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: 2.4123

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
• distributed_type: multi-GPU
• 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	4.2794
No log	2.0	80	3.5733
No log	3.0	120	3.1236
No log	4.0	160	2.8903
No log	5.0	200	2.7397
No log	6.0	240	2.6359
No log	7.0	280	2.5643
No log	8.0	320	2.5171
No log	9.0	360	2.4800
No log	10.0	400	2.4612
No log	11.0	440	2.4394
No log	12.0	480	2.4236
2.7705	13.0	520	2.4172
2.7705	14.0	560	2.4118
2.7705	15.0	600	2.4087
2.7705	16.0	640	2.4154
2.7705	17.0	680	2.4089
2.7705	18.0	720	2.4139
2.7705	19.0	760	2.4138
2.7705	20.0	800	2.4123

Framework versions

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