You can deploy this model and start earning money today!

olusegunola/
phi3-pruned-distilled-hard-labels

Name: phi3-pruned-distilled-hard-labels
Availability: InStock

peft

safetensors

generated_from_trainer

olusegunola/phi3-pruned-layer-struct

adapter

Views

No views yet

phi3-pruned-distilled-hard-labels

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: 2.6250

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: 8
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 32
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
num_epochs: 14

Training results

Training Loss	Epoch	Step	Validation Loss
6.4466	1.0	4	5.9380
5.1099	2.0	8	4.8578
4.1947	3.0	12	4.0313
3.7232	4.0	16	3.5621
3.4109	5.0	20	3.2691
2.9733	6.0	24	3.0787
2.9298	7.0	28	2.9415
2.7085	8.0	32	2.8369
2.6781	9.0	36	2.7646
2.6069	10.0	40	2.7119
2.5621	11.0	44	2.6734
2.4646	12.0	48	2.6473
2.424	13.0	52	2.6314
2.4161	14.0	56	2.6250

Framework versions

PEFT 0.15.2
Transformers 4.52.4
Pytorch 2.6.0+cu124
Datasets 3.2.0
Tokenizers 0.21.2

olusegunola/phi3-pruned-distilled-hard-labels

phi3-pruned-distilled-hard-labels

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

olusegunola/
phi3-pruned-distilled-hard-labels