metadata

license: other
tags:
  - alignment-handbook
  - trl
  - dpo
  - generated_from_trainer
  - trl
  - dpo
  - generated_from_trainer
base_model: ZhangShenao/0.0_llama_nodpo_3iters_bs128_531lr_iter_1
datasets:
  - updated
  - original
model-index:
  - name: 0.0_llama_nodpo_3iters_bs128_531lr_iter_2
    results: []

0.0_llama_nodpo_3iters_bs128_531lr_iter_2

This model is a fine-tuned version of ZhangShenao/0.0_llama_nodpo_3iters_bs128_531lr_iter_1 on the updated and the original datasets.

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: 3e-07
train_batch_size: 4
eval_batch_size: 4
seed: 42
distributed_type: multi-GPU
num_devices: 8
gradient_accumulation_steps: 4
total_train_batch_size: 128
total_eval_batch_size: 32
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.1
num_epochs: 1

Training results

Framework versions

Transformers 4.40.2
Pytorch 2.1.2+cu121
Datasets 2.14.6
Tokenizers 0.19.1

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	68.63
AI2 Reasoning Challenge (25-Shot)	64.42
HellaSwag (10-Shot)	81.35
MMLU (5-Shot)	68.21
TruthfulQA (0-shot)	56.40
Winogrande (5-shot)	74.74
GSM8k (5-shot)	66.64