|
--- |
|
library_name: transformers |
|
license: llama3 |
|
base_model: meta-llama/Meta-Llama-3-8B-Instruct |
|
tags: |
|
- alignment-handbook |
|
- generated_from_trainer |
|
datasets: |
|
- princeton-nlp/llama3-ultrafeedback-armorm |
|
model-index: |
|
- name: llama-3-8b-instruct-gapo-v2-rouge2-beta10-gamma0.3-lr1.0e-6-he_scale-rerun |
|
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. --> |
|
|
|
# llama-3-8b-instruct-gapo-v2-rouge2-beta10-gamma0.3-lr1.0e-6-he_scale-rerun |
|
|
|
This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on the princeton-nlp/llama3-ultrafeedback-armorm dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.3605 |
|
- Rewards/chosen: -16.9816 |
|
- Rewards/rejected: -22.7240 |
|
- Rewards/accuracies: 0.8455 |
|
- Rewards/margins: 5.7425 |
|
- Logps/rejected: -2.2724 |
|
- Logps/chosen: -1.6982 |
|
- Logits/rejected: -1.3613 |
|
- Logits/chosen: -1.3520 |
|
|
|
## 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: 2 |
|
- eval_batch_size: 4 |
|
- seed: 42 |
|
- distributed_type: multi-GPU |
|
- num_devices: 4 |
|
- gradient_accumulation_steps: 16 |
|
- total_train_batch_size: 128 |
|
- total_eval_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: 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 | |
|
|:-------------:|:------:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:| |
|
| 1.2555 | 0.8550 | 400 | 1.3605 | -16.9816 | -22.7240 | 0.8455 | 5.7425 | -2.2724 | -1.6982 | -1.3613 | -1.3520 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.44.2 |
|
- Pytorch 2.2.0 |
|
- Datasets 2.21.0 |
|
- Tokenizers 0.19.1 |
|
|
