|
--- |
|
license: mit |
|
library_name: peft |
|
tags: |
|
- trl |
|
- dpo |
|
- generated_from_trainer |
|
base_model: microsoft/phi-2 |
|
model-index: |
|
- name: phi-2-gpo-test-longest-iter-random2-1 |
|
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. --> |
|
|
|
# phi-2-gpo-test-longest-iter-random2-1 |
|
|
|
This model is a fine-tuned version of [microsoft/phi-2](https://huggingface.co/microsoft/phi-2) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.0019 |
|
- Rewards/chosen: -0.0069 |
|
- Rewards/rejected: -0.0057 |
|
- Rewards/accuracies: 0.4870 |
|
- Rewards/margins: -0.0013 |
|
- Logps/rejected: -279.4207 |
|
- Logps/chosen: -307.2596 |
|
- Logits/rejected: 0.0397 |
|
- Logits/chosen: -0.0578 |
|
|
|
## 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: 4 |
|
- seed: 42 |
|
- distributed_type: multi-GPU |
|
- gradient_accumulation_steps: 4 |
|
- total_train_batch_size: 16 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: cosine |
|
- lr_scheduler_warmup_ratio: 0.1 |
|
- num_epochs: 4 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:| |
|
| 0.0012 | 1.6 | 100 | 0.0018 | -0.0023 | -0.0010 | 0.4940 | -0.0012 | -278.9591 | -306.7935 | 0.0183 | -0.0784 | |
|
| 0.001 | 3.2 | 200 | 0.0019 | -0.0046 | -0.0029 | 0.4775 | -0.0017 | -279.1457 | -307.0229 | 0.0539 | -0.0452 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.7.1 |
|
- Transformers 4.36.2 |
|
- Pytorch 2.2.1+cu121 |
|
- Datasets 2.14.6 |
|
- Tokenizers 0.15.2 |
