|
--- |
|
library_name: peft |
|
tags: |
|
- alignment-handbook |
|
- trl |
|
- dpo |
|
- generated_from_trainer |
|
base_model: NbAiLab/nb-gpt-j-6B-v2 |
|
datasets: |
|
- hugodk-sch/aftonposten_title_prefs |
|
model-index: |
|
- name: aftonposten-6b-align-scan |
|
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. --> |
|
|
|
# aftonposten-6b-align-scan |
|
|
|
This model is a fine-tuned version of [data/ap-gpt-j-6b-sft-qlora-04-08](https://huggingface.co/data/ap-gpt-j-6b-sft-qlora-04-08) on the hugodk-sch/aftonposten_title_prefs dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.4937 |
|
- Rewards/chosen: 0.2548 |
|
- Rewards/rejected: 0.2285 |
|
- Rewards/accuracies: 0.5274 |
|
- Rewards/margins: 0.0263 |
|
- Logps/rejected: -37.2627 |
|
- Logps/chosen: -33.7514 |
|
- Logits/rejected: -2.2263 |
|
- Logits/chosen: -2.2311 |
|
|
|
## 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: 4 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- distributed_type: multi-GPU |
|
- gradient_accumulation_steps: 2 |
|
- total_train_batch_size: 8 |
|
- 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 |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:| |
|
| 0.4639 | 0.26 | 100 | 0.4939 | 0.1483 | 0.1205 | 0.5627 | 0.0278 | -37.3828 | -33.8698 | -2.2305 | -2.2354 | |
|
| 0.4308 | 0.52 | 200 | 0.4894 | 0.2606 | 0.2153 | 0.5544 | 0.0453 | -37.2774 | -33.7450 | -2.2290 | -2.2338 | |
|
| 0.374 | 0.78 | 300 | 0.4904 | 0.2570 | 0.2171 | 0.5220 | 0.0399 | -37.2754 | -33.7490 | -2.2259 | -2.2308 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.8.2 |
|
- Transformers 4.37.2 |
|
- Pytorch 2.1.2+cu121 |
|
- Datasets 2.17.0 |
|
- Tokenizers 0.15.1 |
