vicuna-adv-robust-ul15-sft-full

This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.6864

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: 2e-05
• train_batch_size: 32
• eval_batch_size: 16
• seed: 42
• distributed_type: multi-GPU
• num_devices: 8
• gradient_accumulation_steps: 2
• total_train_batch_size: 512
• total_eval_batch_size: 128
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• num_epochs: 15

Training results

Training Loss	Epoch	Step	Validation Loss
1.0543	0.61	15	1.0329
0.9704	1.61	30	1.0141
0.9103	2.61	45	1.0125
0.8485	3.61	60	1.0221
0.785	4.61	75	1.0448
0.7207	5.61	90	1.0821
0.6444	6.61	105	1.1344
0.5673	7.61	120	1.1993
0.4883	8.61	135	1.2800
0.4137	9.61	150	1.3778
0.345	10.61	165	1.4092
0.3022	11.61	180	1.5371
0.2649	12.61	195	1.5054
0.2272	13.61	210	1.5542
0.1929	14.61	225	1.6869

Framework versions

• Transformers 4.35.0
• Pytorch 2.1.0a0+32f93b1
• Datasets 2.14.6
• Tokenizers 0.14.1