metadata

library_name: transformers
license: llama3.1
base_model: meta-llama/Llama-3.1-8B
tags:
  - llama-factory
  - full
  - generated_from_trainer
model-index:
  - name: OH_original_wo_evol_instruct_140k
    results: []

OH_original_wo_evol_instruct_140k

This model is a fine-tuned version of meta-llama/Llama-3.1-8B on the mlfoundations-dev/OH_original_wo_evol_instruct_140k dataset. It achieves the following results on the evaluation set:

Loss: 0.6121

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: 8
eval_batch_size: 8
seed: 42
distributed_type: multi-GPU
num_devices: 16
gradient_accumulation_steps: 4
total_train_batch_size: 512
total_eval_batch_size: 128
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
0.6185	0.9976	307	0.6178
0.5652	1.9984	615	0.6080
0.5197	2.9927	921	0.6121

Framework versions

Transformers 4.45.2
Pytorch 2.3.0
Datasets 2.21.0
Tokenizers 0.20.1