5lang-sample_13epochs – AI Model by livles | AlphaNeural AI

You can deploy this model and start earning money today!

livles/
5lang-sample_13epochs

like

0

text2text-generation

generated_from_trainer

google/byt5-small

text-generation-inference

endpoints_compatible

Views

No views yet

5lang-sample_13epochs

This model is a fine-tuned version of google/byt5-small on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.2665

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: 5e-05
train_batch_size: 16
eval_batch_size: 16
seed: 42
optimizer: Use adamw_torch_fused with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 500
num_epochs: 13

Training results

Training Loss	Epoch	Step	Validation Loss
2.696	1.0	625	0.7142
0.782	2.0	1250	0.5062
0.5689	3.0	1875	0.4314
0.4129	4.0	2500	0.3782
0.3626	5.0	3125	0.3392
0.3235	6.0	3750	0.3169
0.2891	7.0	4375	0.2902
0.2469	8.0	5000	0.2793
0.2278	9.0	5625	0.2784
0.2186	10.0	6250	0.2697
0.2091	11.0	6875	0.2661
0.1954	12.0	7500	0.2647
0.1878	13.0	8125	0.2665

Framework versions

Transformers 4.57.1
Pytorch 2.9.0+cu128
Datasets 4.3.0
Tokenizers 0.22.1