DialoGPT_EmpAI_final2

This model is a fine-tuned version of microsoft/DialoGPT-small on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 2.7547

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: 0.0001
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 64
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 25000
• num_epochs: 15
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
4.5766	1.0	1500	3.9055
3.6326	2.0	3000	3.3553
3.3738	3.0	4500	3.1776
3.2193	4.0	6000	3.0785
3.1067	5.0	7500	3.0097
3.0286	6.0	9000	2.9714
2.961	7.0	10500	2.9407
2.8925	8.0	12000	2.9111
2.8291	9.0	13500	2.8815
2.7617	10.0	15000	2.8577
2.7061	11.0	16500	2.8126
2.6515	12.0	18000	2.7981
2.6165	13.0	19500	2.7822
2.5813	14.0	21000	2.7689
2.5213	15.0	22500	2.7547

Framework versions

• Transformers 4.38.2
• Pytorch 2.2.1+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2