76 lines
2.7 KiB
Markdown
76 lines
2.7 KiB
Markdown
---
|
|
library_name: transformers
|
|
base_model: W-61/llama-3-8b-base-sft-hh-helpful-8xh200
|
|
tags:
|
|
- alignment-handbook
|
|
- beta-dpo
|
|
- generated_from_trainer
|
|
datasets:
|
|
- Anthropic/hh-rlhf
|
|
model-index:
|
|
- name: llama-3-8b-base-beta-dpo-hh-helpful-8xh200-20260410-215627
|
|
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-base-beta-dpo-hh-helpful-8xh200-20260410-215627
|
|
|
|
This model is a fine-tuned version of [W-61/llama-3-8b-base-sft-hh-helpful-8xh200](https://huggingface.co/W-61/llama-3-8b-base-sft-hh-helpful-8xh200) on the Anthropic/hh-rlhf dataset.
|
|
It achieves the following results on the evaluation set:
|
|
- Loss: 0.6427
|
|
- Beta Dpo/gap Mean: 20.0887
|
|
- Beta Dpo/gap Std: 30.0787
|
|
- Beta Dpo/beta Used Raw: -0.1169
|
|
- Beta Dpo/beta Used: 0.0317
|
|
- Beta Dpo/mask Keep Frac: 1.0
|
|
- Logits/chosen: -0.6626
|
|
- Logits/rejected: -0.6207
|
|
|
|
## 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-07
|
|
- train_batch_size: 16
|
|
- eval_batch_size: 16
|
|
- seed: 42
|
|
- distributed_type: multi-GPU
|
|
- num_devices: 8
|
|
- total_train_batch_size: 128
|
|
- total_eval_batch_size: 128
|
|
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
|
- lr_scheduler_type: cosine
|
|
- lr_scheduler_warmup_ratio: 0.1
|
|
- num_epochs: 1
|
|
|
|
### Training results
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Beta Dpo/gap Mean | Beta Dpo/gap Std | Beta Dpo/beta Used Raw | Beta Dpo/beta Used | Beta Dpo/mask Keep Frac | Logits/chosen | Logits/rejected |
|
|
|:-------------:|:------:|:----:|:---------------:|:-----------------:|:----------------:|:----------------------:|:------------------:|:-----------------------:|:-------------:|:---------------:|
|
|
| 0.4098 | 0.2941 | 100 | 0.6251 | 7.9978 | 13.2607 | 0.0159 | 0.0433 | 1.0 | -0.6978 | -0.6669 |
|
|
| 0.5527 | 0.5882 | 200 | 0.6421 | 17.1059 | 25.9459 | -0.0801 | 0.0373 | 1.0 | -0.6983 | -0.6587 |
|
|
| 0.5831 | 0.8824 | 300 | 0.6427 | 20.0887 | 30.0787 | -0.1169 | 0.0317 | 1.0 | -0.6626 | -0.6207 |
|
|
|
|
|
|
### Framework versions
|
|
|
|
- Transformers 4.51.0
|
|
- Pytorch 2.3.1+cu121
|
|
- Datasets 2.21.0
|
|
- Tokenizers 0.21.4
|