You can deploy this model and start earning money today!

olusegunola/
phi3-pruned-distilled-from-logits_all_med

Name: phi3-pruned-distilled-from-logits_all_med
Availability: InStock

olusegunola/phi3-pruned-layer-struct

Views

No views yet

phi3-pruned-distilled-from-logits_all_med

This model is a fine-tuned version of olusegunola/phi3-pruned-layer-struct on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 3.1225
Ce Loss: 2.2006
Kl Loss: 4.1091

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: 0.0002
train_batch_size: 20
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 16
total_train_batch_size: 320
optimizer: Use paged_adamw_8bit with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 12

Training results

Training Loss	Epoch	Step	Validation Loss	Loss
3.9717	1.0	137	3.9690	5.0872
3.7165	2.0	274	3.6357	4.6179
3.5338	3.0	411	3.4908	4.1808
3.3728	4.0	548	3.3725	4.1091
3.2873	5.0	685	3.2868	4.0136
3.1802	6.0	822	3.2491	4.0678
3.1293	7.0	959	3.1925	3.9867
3.1394	8.0	1096	3.1614	3.8336
3.0588	9.0	1233	3.1458	3.9480
3.0751	10.0	1370	3.1323	4.0484
3.0529	11.0	1507	3.1257	3.8559
2.9652	12.0	1644	3.1225	4.1091

Framework versions

PEFT 0.17.1
Transformers 4.56.1
Pytorch 2.8.0+cu128
Datasets 3.2.0
Tokenizers 0.22.0

olusegunola/phi3-pruned-distilled-from-logits_all_med

phi3-pruned-distilled-from-logits_all_med

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

olusegunola/
phi3-pruned-distilled-from-logits_all_med