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

You can deploy this model and start earning money today!

ChuTuanDuc/
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: 0.1282
Rouge1: 28.7233
Rouge2: 22.5063
Rougel: 28.7351
Rougelsum: 28.7458
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	51	1.8683	4.5065	0.0	4.2606	4.2608	19.0
No log	2.0	102	0.9891	12.4913	4.6839	12.1031	12.1311	19.0
No log	3.0	153	0.5423	23.4776	12.6037	22.8404	22.8681	19.0
No log	4.0	204	0.3146	27.0397	17.6072	26.5138	26.4996	19.0
No log	5.0	255	0.2220	28.5726	20.2637	28.036	28.0719	19.0
No log	6.0	306	0.1746	28.3603	21.0344	28.1316	28.1861	19.0
No log	7.0	357	0.1500	28.4084	21.8872	28.4034	28.4717	19.0
No log	8.0	408	0.1377	28.479	22.2039	28.4944	28.5289	19.0
No log	9.0	459	0.1303	28.6748	22.4501	28.6834	28.6942	19.0
1.0117	10.0	510	0.1282	28.7233	22.5063	28.7351	28.7458	19.0

Framework versions

Transformers 4.38.2
Pytorch 2.2.1+cu121
Datasets 2.18.0
Tokenizers 0.15.2