64 lines
1.5 KiB
Markdown
64 lines
1.5 KiB
Markdown
|
---
|
||
|
|
license: other
|
||
|
|
base_model: TencentARC/Mistral_Pro_8B_v0.1
|
||
|
|
tags:
|
||
|
|
- generated_from_trainer
|
||
|
|
model-index:
|
||
|
|
- name: sft-4e-exp2
|
||
|
|
results: []
|
||
|
|
---
|
||
|
|
|
||
|
|
# sft-4e-exp2
|
||
|
|
|
||
|
|
This model is an experimental fine-tuned version of [TencentARC/Mistral_Pro_8B_v0.1](https://huggingface.co/TencentARC/Mistral_Pro_8B_v0.1).
|
||
|
|
|
||
|
|
This model is intended for safety research only.
|
||
|
|
|
||
|
|
## 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: 4
|
||
|
|
- 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_steps: 10
|
||
|
|
- num_epochs: 4
|
||
|
|
|
||
|
|
### Training results
|
||
|
|
|
||
|
|
|
||
|
|
| arc (25) | hellaswag (10) | mmlu (5) | truthfulqa_mc (20) | winogrande | gsm8k (exact) | avg (exact) |
|
||
|
|
|:--------:|:--------------:|:--------:|:------------------:|:----------:|:-------------:|:-----------:|
|
||
|
|
| 0.6305 | 0.8413 | 0.6041 | 0.5535 | 0.7624 | 0.5754 | 0.6612 |
|
||
|
|
|
||
|
|
### Framework versions
|
||
|
|
|
||
|
|
- Transformers 4.38.2
|
||
|
|
- Pytorch 2.2.1+cu121
|
||
|
|
- Datasets 2.18.0
|
||
|
|
- Tokenizers 0.15.0
|
||
|
|
|
||
|
|
### License
|
||
|
|
This version is to be used for non-commercial research purposes only. We will release open models after we have finished training and evaluations.
|