This model is a fine-tuned version of meta-llama/Llama-3.1-8B-Instruct on the metacog0/mbpp_finetune_training_100_qa_False_test_True_code_False_rule_False_100.jsonl dataset. It achieves the following results on the evaluation set:

Loss: 0.0194

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: 8
eval_batch_size: 8
seed: 42
distributed_type: multi-GPU
num_devices: 8
gradient_accumulation_steps: 2
total_train_batch_size: 128
total_eval_batch_size: 64
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.1
num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss
0.0721	0.9867	37	0.0936
0.024	2.0	75	0.0248
0.0057	2.96	111	0.0194

Framework versions

PEFT 0.13.2
Transformers 4.45.0.dev0
Pytorch 2.4.0+cu121
Datasets 4.0.0
Tokenizers 0.19.1

metacog0/llama3.1-8b-ins-lora-100-toy-pure2

llama3.1-8b-ins-lora-100-toy-pure2

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

metacog0/
llama3.1-8b-ins-lora-100-toy-pure2