Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
llama3-8b-math-sft-mix-8-1 – AI Model by Dynosaur | AlphaNeural AI
You can deploy this model and start earning money today!
Dynosaur
/
llama3-8b-math-sft-mix-8-1
like
0
transformers
tensorboard
safetensors
llama
text-generation
alignment-handbook
trl
sft
generated_from_trainer
conversational
hexuan21/math-sft-mix-8-1
Dynosaur/llama3-8b-math-sft
finetune
llama3
autotrain_compatible
text-generation-inference
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
llama3-8b-math-sft-mix-8-1
This model is a fine-tuned version of
Dynosaur/llama3-8b-math-sft
on the hexuan21/math-sft-mix-8-1 dataset.
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: 2e-05
train_batch_size: 2
eval_batch_size: 8
seed: 42
distributed_type: multi-GPU
num_devices: 4
gradient_accumulation_steps: 8
total_train_batch_size: 64
total_eval_batch_size: 32
optimizer: Use 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_ratio: 0.1
num_epochs: 2
Training results
Framework versions
Transformers 4.46.3
Pytorch 2.5.1+cu124
Datasets 3.1.0
Tokenizers 0.20.3
