12epochs-csb-sent-25perc-byte-pol – AI Model by livles | AlphaNeural AI

You can deploy this model and start earning money today!

livles/
12epochs-csb-sent-25perc-byte-pol

like

0

text2text-generation

generated_from_trainer

livles/csb-pol-byte-25perc-sent

text-generation-inference

endpoints_compatible

Views

No views yet

pol

This model is a fine-tuned version of livles/csb-pol-byte-25perc-sent on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.0623

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: 12

Training results

Training Loss	Epoch	Step	Validation Loss
3.1059	1.0	625	0.2846
0.3593	2.0	1250	0.0969
0.2009	3.0	1875	0.0641
0.0869	4.0	2500	0.0522
0.0682	5.0	3125	0.0530
0.0559	6.0	3750	0.0569
0.0475	7.0	4375	0.0551
0.0376	8.0	5000	0.0570
0.0319	9.0	5625	0.0601
0.0318	10.0	6250	0.0591
0.0291	11.0	6875	0.0626
0.0256	12.0	7500	0.0623

Framework versions

Transformers 5.6.2
Pytorch 2.9.1+cu128
Datasets 4.8.4
Tokenizers 0.22.2