Llama-2-7b-QLoRA-03 – AI Model by onuralp | AlphaNeural AI

You can deploy this model and start earning money today!

onuralp/
Llama-2-7b-QLoRA-03

like

0

text-generation

generated_from_trainer

meta-llama/Llama-2-7b-hf

autotrain_compatible

endpoints_compatible

Views

No views yet

Built with Axolotl

qlora-out

This model is a fine-tuned version of meta-llama/Llama-2-7b-hf on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.5703

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: 0.0004
train_batch_size: 1
eval_batch_size: 1
seed: 42
gradient_accumulation_steps: 16
total_train_batch_size: 16
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 100
num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss
0.8756	0.06	20	0.7111
0.9058	0.11	40	0.6764
0.7526	0.17	60	0.6669
0.6926	0.23	80	0.6363
0.6731	0.28	100	0.6187
0.647	0.34	120	0.6162
0.6219	0.4	140	0.6041
0.5781	0.45	160	0.5937
0.6346	0.51	180	0.6006
0.7663	0.57	200	0.5926
0.5864	0.62	220	0.5866
0.5943	0.68	240	0.5756
0.5029	0.74	260	0.5733
0.5482	0.79	280	0.5712
0.5413	0.85	300	0.5820
0.657	0.91	320	0.5696
0.506	0.96	340	0.5839
0.4804	1.02	360	0.5803
0.5095	1.08	380	0.5974
0.4404	1.13	400	0.5746
0.3869	1.19	420	0.5740
0.4129	1.25	440	0.5777
0.4209	1.3	460	0.5825
0.4014	1.36	480	0.5742
0.3333	1.42	500	0.5851
0.5041	1.47	520	0.5798
0.5528	1.53	540	0.5631
0.4372	1.59	560	0.5747
0.3901	1.64	580	0.5625
0.5271	1.7	600	0.5746
0.4283	1.76	620	0.5662
0.4336	1.81	640	0.5652
0.3534	1.87	660	0.5697
0.4728	1.93	680	0.5713
0.5159	1.98	700	0.5703

Framework versions

Transformers 4.34.1
Pytorch 2.0.1+cu118
Datasets 2.14.6
Tokenizers 0.14.1