vicuna-adv-robust-u15-sft-lora

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

• Loss: 1.7553

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: 0.0003
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• distributed_type: multi-GPU
• num_devices: 4
• gradient_accumulation_steps: 16
• total_train_batch_size: 512
• total_eval_batch_size: 32
• 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
No log	0	0	2.4952
2.5615	1.09	1	2.5270
2.5615	1.09	1	2.5362
2.5615	3.03	2	2.5338
2.5615	4.12	3	2.2734
2.5615	4.12	3	2.3209
2.5615	6.06	4	2.1026
2.3634	7.15	5	2.0141
2.3634	7.15	5	2.0772
2.3634	9.09	6	1.9678
2.3634	9.09	6	1.8940
2.3634	11.03	7	1.8120
2.3634	12.12	8	1.8152
2.3634	12.12	8	1.7991
2.3634	14.06	9	1.7646

Framework versions

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