v4 – AI Model by woosterheert | AlphaNeural AI

You can deploy this model and start earning money today!

woosterheert/
v4

like

0

generated_from_trainer

google/paligemma-3b-pt-224

text-generation-inference

endpoints_compatible

Views

No views yet

v4

This model is a fine-tuned version of google/paligemma-3b-pt-224 on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.1302

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: 4
eval_batch_size: 8
seed: 42
optimizer: Use OptimizerNames.ADAMW_HF 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: 2
num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss
0.1867	1.0	2500	0.1205
0.0812	2.0	5000	0.1371
0.1012	3.0	7500	0.1244
0.1027	4.0	10000	0.1316
0.0475	5.0	12500	0.1302

Framework versions

Transformers 4.47.1
Pytorch 2.5.1+cu124
Datasets 3.2.0
Tokenizers 0.21.0