peft-starcoder-lora-a100 – AI Model by Charlie3006 | AlphaNeural AI

You can deploy this model and start earning money today!

Charlie3006/
peft-starcoder-lora-a100

like

0

generated_from_trainer

bigcode/starcoderbase-1b

bigcode-openrail-m

Views

No views yet

peft-starcoder-lora-a100

This model is a fine-tuned version of bigcode/starcoderbase-1b on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.8163

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: 2
eval_batch_size: 2
seed: 42
optimizer: Use OptimizerNames.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
1.0488	0.05	100	0.9203
0.766	0.1	200	0.8664
0.8261	0.15	300	0.8255
0.7837	0.2	400	0.8087
0.7211	0.25	500	0.7944
0.6909	0.3	600	0.8020
0.7019	0.35	700	0.7912
0.6232	0.4	800	0.7917
0.6041	0.45	900	0.7836
0.7069	0.5	1000	0.7867
0.5512	0.55	1100	0.8163

Framework versions

PEFT 0.14.0
Transformers 4.48.3
Pytorch 2.6.0+cu124
Datasets 3.2.0
Tokenizers 0.21.0