voxsign-flan-t5-lora – AI Model by victort93 | AlphaNeural AI

You can deploy this model and start earning money today!

victort93/
voxsign-flan-t5-lora

like

0

generated_from_trainer

google/flan-t5-base

Views

No views yet

voxsign-flan-t5-lora

This model is a fine-tuned version of google/flan-t5-base on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.0478
Rouge1: 0.9873
Rouge2: 0.9743
Rougel: 0.9867
Rougelsum: 0.9865

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: 5e-05
train_batch_size: 8
eval_batch_size: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 100
num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum
0.0594	1.0	750	0.0509	0.9828	0.9655	0.9813	0.9811
0.0129	2.0	1500	0.0431	0.9863	0.973	0.9854	0.9852
0.0333	3.0	2250	0.0373	0.9861	0.9735	0.9855	0.9852
0.0371	4.0	3000	0.0392	0.9864	0.9726	0.9855	0.9853
0.0125	5.0	3750	0.0435	0.9865	0.9724	0.9854	0.9852
0.0361	6.0	4500	0.0427	0.9869	0.9729	0.9857	0.9855
0.0027	7.0	5250	0.0433	0.9874	0.9738	0.9865	0.9863
0.0238	8.0	6000	0.0485	0.9877	0.9735	0.9866	0.9865
0.011	9.0	6750	0.0480	0.987	0.9731	0.9863	0.986
0.0134	10.0	7500	0.0478	0.9873	0.9743	0.9867	0.9865

Framework versions

PEFT 0.10.0
Transformers 4.40.0
Pytorch 2.12.0+cu130
Datasets 2.19.0
Tokenizers 0.19.1