metadata

library_name: transformers
license: llama3.1
base_model: meta-llama/Meta-Llama-3.1-8B
tags:
  - llama-factory
  - full
  - generated_from_trainer
model-index:
  - name: oh_v1.3_opengpt_x8
    results: []

oh_v1.3_opengpt_x8

This model is a fine-tuned version of meta-llama/Meta-Llama-3.1-8B on the mlfoundations-dev/oh_v1.3_opengpt_x8 dataset. It achieves the following results on the evaluation set:

Loss: 0.7300

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: 16
eval_batch_size: 8
seed: 42
distributed_type: multi-GPU
num_devices: 32
total_train_batch_size: 512
total_eval_batch_size: 256
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
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
0.7466	1.0	275	0.7418
0.6841	2.0	550	0.7281
0.6412	3.0	825	0.7300

Framework versions

Transformers 4.46.1
Pytorch 2.4.0
Datasets 3.0.2
Tokenizers 0.20.3