vicuna-adv-robust-u5-sft-lora

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

• Loss: 1.2913

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: 3e-05
• train_batch_size: 4
• eval_batch_size: 8
• seed: 42
• distributed_type: multi-GPU
• num_devices: 4
• gradient_accumulation_steps: 128
• total_train_batch_size: 2048
• total_eval_batch_size: 32
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss
1.4063	0.63	7	1.3767
1.3987	1.61	14	1.3552
1.3645	2.59	21	1.3310
1.35	3.57	28	1.3090
1.3197	4.64	36	1.2913

Framework versions

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