LimaRP-UtopiaXL-13B-v3-lora – AI Model by Undi95 | AlphaNeural AI

You can deploy this model and start earning money today!

Undi95/
LimaRP-UtopiaXL-13B-v3-lora

like

0

text-generation

not-for-all-audiences

autotrain_compatible

text-generation-inference

endpoints_compatible

Views

No views yet

Built with Axolotl

UtopiaXL-LimaRP

This lora was trained from the LimaRP dataset Version 2023-10-19 (2003 samples) on the UtopiaXL-13B model I cooked (before applying it obviously).

It achieves the following results on the evaluation set:

Loss: 1.7890

Intended uses & limitations

This LoRA was created to be used on my own model, but since it's done, I share it.

Should work on any Llama2-13B model, but I can't tell you if the result will be good.

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 0.00065
train_batch_size: 2
eval_batch_size: 2
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: constant
lr_scheduler_warmup_steps: 10
num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss
1.9885	0.0	1	1.8980
1.8291	0.1	96	1.7738
1.9424	0.2	192	1.7654
1.6578	0.3	288	1.7633
1.9735	0.4	384	1.7534
1.867	0.5	480	1.7555
1.8471	0.6	576	1.7573
1.85	0.7	672	1.7555
1.8832	0.8	768	1.7534
1.8443	0.9	864	1.7473
1.682	1.0	960	1.7623
1.6491	1.1	1056	1.7830
1.4387	1.21	1152	1.7881
1.8196	1.31	1248	1.7929
1.7265	1.41	1344	1.8038
1.6219	1.51	1440	1.7906
1.4174	1.61	1536	1.7956
1.86	1.71	1632	1.7959
1.9297	1.81	1728	1.8033
1.6009	1.91	1824	1.7890

Framework versions

Transformers 4.36.0.dev0
Pytorch 2.0.1+cu117
Datasets 2.14.6
Tokenizers 0.14.1

If you want to support me, you can here.