t5-base-prompter-multiarith_300-repeated-ep10 – AI Model by Zekunli | AlphaNeural AI

You can deploy this model and start earning money today!

Zekunli/
t5-base-prompter-multiarith_300-repeated-ep10

like

0

text2text-generation

generated_from_trainer

text-generation-inference

endpoints_compatible

Views

No views yet

t5-base-prompter-multiarith_300-repeated-ep10

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

Loss: 0.2140
Rouge1: 51.8167
Rouge2: 40.6702
Rougel: 51.7
Rougelsum: 51.8
Gen Len: 9.0

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: 16
eval_batch_size: 64
seed: 1799
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
0.9903	1.55	200	0.2269	48.2245	36.1266	48.1021	48.2726	12.6133
0.288	3.1	400	0.2190	49.1321	36.7892	48.9713	49.0819	11.24
0.2616	4.65	600	0.2182	48.8628	38.2572	48.7884	48.8079	8.3133
0.2595	6.2	800	0.2160	51.8167	40.6702	51.7	51.8	9.0
0.2488	7.75	1000	0.2149	51.6138	40.4037	51.4575	51.5664	9.2
0.25	9.3	1200	0.2139	51.8167	40.6702	51.7	51.8	9.0

Framework versions

Transformers 4.18.0
Pytorch 1.11.0+cu113
Datasets 2.5.1
Tokenizers 0.12.1