vicuna-ul15-sft-full

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

• Loss: 1.4380

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
1.0541	0.68	14	1.0341
0.9708	1.71	29	1.0142
0.9142	2.68	43	1.0111
0.8637	3.71	58	1.0239
0.8091	4.68	72	1.0363
0.7516	5.71	87	1.0780
0.6884	6.68	101	1.0987
0.6309	7.71	116	1.1394
0.5696	8.68	130	1.1820
0.4752	9.71	145	1.2695
0.448	10.68	159	1.3109
0.3955	11.71	174	1.3877
0.3579	12.68	188	1.3923
0.3228	13.71	203	1.4064
0.2914	14.68	217	1.4377

Framework versions

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