|
|
--- |
|
|
base_model: mistralai/Mistral-7B-v0.1 |
|
|
tags: |
|
|
- alignment-handbook |
|
|
- trl |
|
|
- orpo |
|
|
- generated_from_trainer |
|
|
- trl |
|
|
- orpo |
|
|
- generated_from_trainer |
|
|
- entity linking |
|
|
datasets: |
|
|
- daisd-ai/anydef-kilt-tasks |
|
|
model-index: |
|
|
- name: anydef-orpo |
|
|
results: [] |
|
|
license: apache-2.0 |
|
|
inference: false |
|
|
--- |
|
|
|
|
|
<!-- 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. --> |
|
|
|
|
|
# anydef-orpo |
|
|
|
|
|
This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the daisd-ai/anydef-kilt-tasks dataset. |
|
|
|
|
|
Find out about Model description, Intended uses & limitations and Training and evaluation data on our [github](https://github.com/daisd-ai/universal-el). |
|
|
|
|
|
## 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: 8 |
|
|
- total_train_batch_size: 64 |
|
|
- total_eval_batch_size: 64 |
|
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
|
- lr_scheduler_type: inverse_sqrt |
|
|
- lr_scheduler_warmup_steps: 100 |
|
|
- num_epochs: 3 |
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.39.3 |
|
|
- Pytorch 2.1.2+cu121 |
|
|
- Datasets 2.18.0 |
|
|
- Tokenizers 0.15.2 |
