You can deploy this model and start earning money today!

j05hr3d/
SFT-CodeLlama-7B-Instruct_v1.1st

Name: SFT-CodeLlama-7B-Instruct_v1.1st
Availability: InStock

meta-llama/CodeLlama-7b-Instruct-hf

llama2

Views

No views yet

SFT-CodeLlama-7B-Instruct_v1.1st

This model is a fine-tuned version of meta-llama/CodeLlama-7b-Instruct-hf on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.5265

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: 0.0001
train_batch_size: 2
eval_batch_size: 1
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 8
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
lr_scheduler_warmup_ratio: 0.03
num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss
0.8634	0.3049	50	0.8502
0.6605	0.6098	100	0.7614
0.6621	0.9146	150	0.6830
0.5797	1.2195	200	0.6369
0.5003	1.5244	250	0.5963
0.5303	1.8293	300	0.5663
0.4296	2.1341	350	0.5507
0.3805	2.4390	400	0.5363
0.3402	2.7439	450	0.5265

Framework versions

PEFT 0.18.0
Transformers 4.57.3
Pytorch 2.9.0+cu126
Datasets 4.4.1
Tokenizers 0.22.1

j05hr3d/SFT-CodeLlama-7B-Instruct_v1.1st

SFT-CodeLlama-7B-Instruct_v1.1st

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

j05hr3d/
SFT-CodeLlama-7B-Instruct_v1.1st