t5-small-finetuned-manimml – AI Model by BienThuy | AlphaNeural AI

You can deploy this model and start earning money today!

BienThuy/
t5-small-finetuned-manimml

like

0

text2text-generation

generated_from_trainer

google-t5/t5-small

text-generation-inference

endpoints_compatible

Views

No views yet

t5-small-finetuned-manimml

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

Loss: 0.0265
Rouge1: 26.6541
Rouge2: 21.4995
Rougel: 26.6415
Rougelsum: 26.6456
Gen Len: 19.0

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: 16
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 10
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
No log	1.0	350	0.1263	26.5707	20.5692	26.3449	26.3437	18.9986
0.7594	2.0	700	0.0655	26.6351	21.4219	26.6247	26.6217	19.0
0.122	3.0	1050	0.0487	26.654	21.4338	26.6451	26.6484	19.0
0.122	4.0	1400	0.0393	26.6598	21.4549	26.653	26.6554	19.0
0.0796	5.0	1750	0.0343	26.6454	21.4591	26.6392	26.637	19.0
0.0627	6.0	2100	0.0312	26.6488	21.4607	26.6402	26.6391	19.0
0.0627	7.0	2450	0.0286	26.6408	21.463	26.6335	26.6317	19.0
0.0526	8.0	2800	0.0274	26.6408	21.463	26.6335	26.6317	19.0
0.0478	9.0	3150	0.0266	26.6541	21.4995	26.6415	26.6456	19.0
0.046	10.0	3500	0.0265	26.6541	21.4995	26.6415	26.6456	19.0

Framework versions

Transformers 4.38.2
Pytorch 2.2.1+cu121
Datasets 2.18.0
Tokenizers 0.15.2