|
--- |
|
library_name: transformers |
|
license: apache-2.0 |
|
base_model: yiran-wang3/qwen2_chat_reflct_adamw_iter3 |
|
tags: |
|
- alignment-handbook |
|
- generated_from_trainer |
|
- trl |
|
- dpo |
|
datasets: |
|
- self-generate/qw2_reflct_sppo_hard_new_cn_mining_oj_iter3-binarized-reflection-scored |
|
model-index: |
|
- name: qwen2_chat_reflct_adamw_iter4 |
|
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. --> |
|
|
|
# qwen2_chat_reflct_adamw_iter4 |
|
|
|
This model is a fine-tuned version of [yiran-wang3/qwen2_chat_reflct_adamw_iter3](https://huggingface.co/yiran-wang3/qwen2_chat_reflct_adamw_iter3) on the self-generate/qw2_reflct_sppo_hard_new_cn_mining_oj_iter3-binarized-reflection-scored 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-06 |
|
- train_batch_size: 8 |
|
- eval_batch_size: 4 |
|
- seed: 42 |
|
- distributed_type: multi-GPU |
|
- num_devices: 8 |
|
- total_train_batch_size: 64 |
|
- total_eval_batch_size: 32 |
|
- 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: 100 |
|
- num_epochs: 1.0 |
|
|
|
### Training results |
|
|
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.45.0 |
|
- Pytorch 2.4.0+cu121 |
|
- Datasets 2.14.6 |
|
- Tokenizers 0.20.2 |
|
|
