You can deploy this model and start earning money today!

Ferdi/
CodeLlama-7B-Instruct-AWQ-FaVe-rank16-5epochs

Name: CodeLlama-7B-Instruct-AWQ-FaVe-rank16-5epochs
Rating: 2.5 (5 reviews)

generated_from_trainer

TheBloke/CodeLlama-7B-Instruct-AWQ

adapter

llama2

Views

No views yet

CodeLlama-7B-Instruct-AWQ-FaVe-rank16-5epochs

This model is a fine-tuned version of TheBloke/CodeLlama-7B-Instruct-AWQ on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.4559

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: 1
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 4
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 10
num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.2685	10	2.1904
2.1539	0.5369	20	1.3867
2.1539	0.8054	30	0.9114
0.9417	1.0738	40	0.7705
0.9417	1.3423	50	0.7068
0.632	1.6107	60	0.6554
0.632	1.8792	70	0.6145
0.5044	2.1477	80	0.5866
0.5044	2.4161	90	0.5553
0.4666	2.6846	100	0.5301
0.4666	2.9530	110	0.5144
0.366	3.2215	120	0.4953
0.366	3.4899	130	0.4918
0.342	3.7584	140	0.4698
0.342	4.0268	150	0.4638
0.2842	4.2953	160	0.4748
0.2842	4.5638	170	0.4599
0.2764	4.8322	180	0.4559

Framework versions

PEFT 0.10.0
Transformers 4.40.2
Pytorch 2.2.1+cu121
Datasets 2.19.1
Tokenizers 0.19.1

Ferdi/CodeLlama-7B-Instruct-AWQ-FaVe-rank16-5epochs

CodeLlama-7B-Instruct-AWQ-FaVe-rank16-5epochs

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

Ferdi/
CodeLlama-7B-Instruct-AWQ-FaVe-rank16-5epochs