README.md

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_platypus
    results: []

OH_original_wo_platypus

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

• Loss: 0.6046

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
0.6134	0.9985	328	0.6086
0.5568	2.0	657	0.5997
0.507	2.9954	984	0.6046

Framework versions

• Transformers 4.45.2
• Pytorch 2.3.0
• Datasets 2.21.0
• Tokenizers 0.20.1