You can deploy this model and start earning money today!

dparra19/
dparcon

Name: dparcon
Availability: InStock

DiegoParraCo/descripciones-frutas-y-verduras

gplsi/Aitana-2B-S-base

apache-2.0

Views

No views yet

dparcon

This model is a fine-tuned version of gplsi/Aitana-2B-S-base on the dataset showed in my account (descriptions about fruits and vegetables). It achieves the following results on the evaluation set:

Loss: 1.8984

Model description

The gplsi/Aitana-2B-S-base consists on a generative language model on multilingual data (Spanish, Valencian and English). In this case, we have fine-tuning this model to answer information about certain fruits and vegetables.

Intended uses & limitations

More information needed

Training and evaluation data

We have used the following dataset

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 0.0002
train_batch_size: 4
eval_batch_size: 4
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 16
optimizer: Use OptimizerNames.PAGED_ADAMW_8BIT 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: 10
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
2.1405	1.0	3	2.1311
2.0658	2.0	6	2.0559
1.9534	3.0	9	2.0014
1.8923	4.0	12	1.9646
1.8391	5.0	15	1.9432
1.7374	6.0	18	1.9290
1.7135	7.0	21	1.9172
1.6700	8.0	24	1.9076
1.6643	9.0	27	1.9014
1.6647	10.0	30	1.8984

Framework versions

PEFT 0.19.1
Transformers 5.14.1
Pytorch 2.11.0+cu128
Datasets 5.0.0
Tokenizers 0.22.2

dparra19/dparcon