oh_v3-1_only_metamath_40k

This model is a fine-tuned version of meta-llama/Meta-Llama-3.1-8B on the mlfoundations-dev/oh_v3-1_only_metamath_40k dataset. It achieves the following results on the evaluation set:

  • Loss: 0.2824

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: 5e-06
  • train_batch_size: 2
  • eval_batch_size: 2
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 8
  • gradient_accumulation_steps: 32
  • total_train_batch_size: 512
  • total_eval_batch_size: 16
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: constant
  • lr_scheduler_warmup_ratio: 0.1
  • lr_scheduler_warmup_steps: 1738
  • num_epochs: 3.0

Training results

Training Loss Epoch Step Validation Loss
0.4671 0.9639 15 0.3353
0.3019 1.9920 31 0.2970
0.2815 2.8916 45 0.2824

Framework versions

  • Transformers 4.45.2
  • Pytorch 2.4.0+cu121
  • Datasets 3.0.2
  • Tokenizers 0.20.1
Downloads last month
316
Safetensors
Model size
8.03B params
Tensor type
BF16
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for mlfoundations-dev/oh_v3-1_only_metamath_40k

Finetuned
(524)
this model