Beta
Explore
Marketplace
Neural Labs
Playground
Wallet
Docs
llama_3_gsm8k_per_class_reflect – AI Model by CharlesLi | AlphaNeural AI
You can deploy this model and start earning money today!
CharlesLi
/
llama_3_gsm8k_per_class_reflect
like
0
peft
tensorboard
safetensors
llama
alignment-handbook
trl
sft
generated_from_trainer
meta-llama/Llama-3.1-8B-Instruct
adapter
llama3.1
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
llama_3_gsm8k_per_class_reflect
This model is a fine-tuned version of
meta-llama/Llama-3.1-8B-Instruct
on the None dataset. It achieves the following results on the evaluation set:
Loss: 0.5984
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: 4
eval_batch_size: 4
seed: 42
distributed_type: multi-GPU
num_devices: 2
gradient_accumulation_steps: 2
total_train_batch_size: 16
total_eval_batch_size: 8
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.1
training_steps: 30
Training results
Training Loss
Epoch
Step
Validation Loss
0.9807
0.7692
5
0.7104
0.6536
1.5385
10
0.6398
0.5897
2.3077
15
0.6169
0.5312
3.0769
20
0.6066
0.4917
3.8462
25
0.5994
0.4808
4.6154
30
0.5984
Framework versions
PEFT 0.12.0
Transformers 4.44.2
Pytorch 2.4.1+cu121
Datasets 3.0.0
Tokenizers 0.19.1
