metadata
base_model: meta-llama/Meta-Llama-3-8B
datasets:
- HuggingFaceH4/ultrachat_200k
library_name: peft
license: llama3
tags:
- alignment-handbook
- trl
- sft
- generated_from_trainer
model-index:
- name: llama3-sudo
results: []
llama3-sudo
This model is a fine-tuned version of meta-llama/Meta-Llama-3-8B on the HuggingFaceH4/ultrachat_200k dataset. It achieves the following results on the evaluation set:
- Loss: 1.0100
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: 0.0002
- train_batch_size: 16
- eval_batch_size: 4
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 4
- total_train_batch_size: 256
- total_eval_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.3252 | 0.9697 | 24 | 1.1693 |
| 1.1352 | 1.9798 | 49 | 1.0709 |
| 1.1265 | 1.9899 | 98 | 1.0308 |
| 1.1113 | 2.9798 | 147 | 1.0100 |
Framework versions
- PEFT 0.12.0
- Transformers 4.44.0
- Pytorch 2.1.2
- Datasets 2.20.0
- Tokenizers 0.19.1