mt5-large-ie-budquo-finetuned – AI Model by RamsesDIIP | AlphaNeural AI

You can deploy this model and start earning money today!

RamsesDIIP/
mt5-large-ie-budquo-finetuned

like

0

text2text-generation

generated_from_trainer

google/mt5-large

endpoints_compatible

Views

No views yet

mt5-large-ie-budquo-finetuned

This model is a fine-tuned version of google/mt5-large on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.0322
Rouge1: 0.0564
Rouge2: 0.0299
Rougel: 0.0562
Rougelsum: 0.0564

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: 0.0003
train_batch_size: 1
eval_batch_size: 1
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 4
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum
0.1063	0.9998	1156	0.0669	0.1300	0.0852	0.1264	0.1299
0.0516	1.9996	2312	0.0366	0.0609	0.0328	0.0608	0.0608
0.0338	2.9994	3468	0.0265	0.1055	0.0668	0.1039	0.1057
0.0253	4.0	4625	0.0223	0.1245	0.0741	0.1227	0.1246
0.021	4.9989	5780	0.0206	0.1297	0.0834	0.1268	0.1298

Framework versions

Transformers 4.44.2
Pytorch 2.4.1+cu121
Datasets 3.0.1
Tokenizers 0.19.1