You can deploy this model and start earning money today!

AdnanRiaz107/
CodePhi-3-mini-4k-instruct-appsloraN1k8-16

peft

safetensors

generated_from_trainer

microsoft/Phi-3-mini-128k-instruct

adapter

mit

Views

No views yet

CodePhi-3-mini-4k-instruct-appsloraN1k8-16

This model is a fine-tuned version of microsoft/Phi-3-mini-128k-instruct on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.6704

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-06
train_batch_size: 1
eval_batch_size: 1
seed: 42
gradient_accumulation_steps: 16
total_train_batch_size: 16
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 100
training_steps: 1000

Training results

Training Loss	Epoch	Step	Validation Loss
0.5986	0.1	100	0.7075
0.664	0.2	200	0.6941
0.6599	0.3	300	0.6839
0.6034	0.4	400	0.6769
0.6297	0.5	500	0.6730
0.6152	0.6	600	0.6711
0.6193	0.7	700	0.6705
0.5792	0.8	800	0.6705
0.5947	0.9	900	0.6704
0.5509	1.0	1000	0.6704

Framework versions

PEFT 0.11.0
Transformers 4.40.2
Pytorch 2.3.0+cu121
Datasets 2.19.1
Tokenizers 0.19.1

AdnanRiaz107/CodePhi-3-mini-4k-instruct-appsloraN1k8-16

CodePhi-3-mini-4k-instruct-appsloraN1k8-16

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

AdnanRiaz107/
CodePhi-3-mini-4k-instruct-appsloraN1k8-16