flan-t5-large-da-multiwoz2.1_80-loss-ep50 – AI Model by Zekunli | AlphaNeural AI

You can deploy this model and start earning money today!

Zekunli/
flan-t5-large-da-multiwoz2.1_80-loss-ep50

like

0

text2text-generation

generated_from_trainer

text-generation-inference

endpoints_compatible

Views

No views yet

flan-t5-large-da-multiwoz2.1_80-loss-ep50

This model is a fine-tuned version of google/flan-t5-large on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.4579
Accuracy: 33.9166
Num: 7365
Gen Len: 16.1092

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: 24
eval_batch_size: 192
seed: 1799
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 50

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Num	Gen Len
1.1431	8.0	200	0.4916	29.9135	7365	15.2805
0.4731	16.0	400	0.4579	33.9166	7365	16.1092
0.3788	24.0	600	0.4705	34.9699	7365	15.9742
0.3188	32.0	800	0.4872	34.3973	7365	15.6263
0.2879	40.0	1000	0.4989	35.5581	7365	15.8967
0.2672	48.0	1200	0.5088	35.5744	7365	15.9563

Framework versions

Transformers 4.18.0
Pytorch 1.10.0+cu111
Datasets 2.5.1
Tokenizers 0.12.1