|
--- |
|
base_model: meta-llama/Llama-2-7b-hf |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- conceptofmind/FLAN_2022 |
|
model-index: |
|
- name: outputs |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# outputs |
|
|
|
This model is a fine-tuned version of [meta-llama/Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b-hf) on the conceptofmind/FLAN_2022 dataset. |
|
|
|
## 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: 1e-05 |
|
- train_batch_size: 12 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- distributed_type: multi-GPU |
|
- gradient_accumulation_steps: 8 |
|
- total_train_batch_size: 96 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: cosine |
|
- lr_scheduler_warmup_ratio: 0.03 |
|
- num_epochs: 1.0 |
|
|
|
### Training results |
|
|
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.31.0 |
|
- Pytorch 2.0.1+cu117 |
|
- Datasets 2.14.3 |
|
- Tokenizers 0.13.3 |
|
|
|
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard) |
|
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_synapsoft__Llama-2-7b-hf-flan2022-1.2M) |
|
|
|
| Metric | Value | |
|
|-----------------------|---------------------------| |
|
| Avg. | 41.68 | |
|
| ARC (25-shot) | 23.29 | |
|
| HellaSwag (10-shot) | 78.46 | |
|
| MMLU (5-shot) | 42.33 | |
|
| TruthfulQA (0-shot) | 37.97 | |
|
| Winogrande (5-shot) | 75.53 | |
|
| GSM8K (5-shot) | 4.47 | |
|
| DROP (3-shot) | 29.66 | |
|
|
