idt5-base-ae_adapter_v2 – AI Model by hawalurahman | AlphaNeural AI

You can deploy this model and start earning money today!

hawalurahman/
idt5-base-ae_adapter_v2

like

0

generated_from_trainer

muchad/idt5-base

Views

No views yet

idt5-base-ae_adapter_v2

This model is a fine-tuned version of muchad/idt5-base on the None dataset. It achieves the following results on the evaluation set:

Loss: 1.6189
Rouge1: 0.2865
Rouge2: 0.1723
Rougel: 0.2835
Rougelsum: 0.2833
Bleu: 0.1327

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: 0.0001
train_batch_size: 8
eval_batch_size: 8
seed: 42
optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Bleu
2.3292	1.0	3235	1.8863	0.2475	0.1449	0.2451	0.2454	0.1103
2.0895	2.0	6470	1.6991	0.2761	0.1678	0.2725	0.2727	0.1388
1.9092	3.0	9705	1.6346	0.2798	0.1671	0.2773	0.2775	0.1278
1.9178	4.0	12940	1.6246	0.2839	0.1705	0.2813	0.2809	0.1227
1.9038	5.0	16175	1.6189	0.2865	0.1723	0.2835	0.2833	0.1327

Framework versions

PEFT 0.13.2
Transformers 4.46.0
Pytorch 2.4.0a0+f70bd71a48.nv24.06
Datasets 3.0.2
Tokenizers 0.20.1