You can deploy this model and start earning money today!

Sailesh9999/
peft-starcoder-lora-a100

Name: peft-starcoder-lora-a100
Availability: InStock

peft

tensorboard

safetensors

generated_from_trainer

meta-llama/Llama-3.2-1B-Instruct

adapter

llama3.2

Views

No views yet

peft-starcoder-lora-a100

This model is a fine-tuned version of meta-llama/Llama-3.2-1B-Instruct on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 1.4134

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: 0.0005
train_batch_size: 16
eval_batch_size: 16
seed: 42
optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 30
training_steps: 2000

Training results

Training Loss	Epoch	Step	Validation Loss
1.4261	0.05	100	1.3509
1.3393	0.1	200	1.3586
1.5034	0.15	300	1.3774
1.0945	0.2	400	1.3768
1.3357	0.25	500	1.3915
1.3062	0.3	600	1.3792
1.2152	0.35	700	1.3873
1.269	0.4	800	1.3911
1.1954	0.45	900	1.3966
1.1436	0.5	1000	1.3949
0.9746	0.55	1100	1.3982
1.2696	0.6	1200	1.4043
1.0225	0.65	1300	1.4104
1.1184	0.7	1400	1.4065
1.212	0.75	1500	1.4089
1.3207	0.8	1600	1.4102
1.0669	0.85	1700	1.4143
1.1501	0.9	1800	1.4133
1.2002	0.95	1900	1.4128
1.0119	1.0	2000	1.4134

Framework versions

PEFT 0.14.0
Transformers 4.47.1
Pytorch 2.5.1+cu124
Datasets 3.2.0
Tokenizers 0.21.0

Sailesh9999/peft-starcoder-lora-a100

peft-starcoder-lora-a100

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

Sailesh9999/
peft-starcoder-lora-a100