e8efbe1ca9
Model: W-61/llama-3-8b-base-new-dpo-ultrafeedback-4xh200-batch-128-q_t-0.43-s_star-0.4-20260429-230725 Source: Original Platform
82 lines
3.2 KiB
Markdown
82 lines
3.2 KiB
Markdown
---
|
|
library_name: transformers
|
|
base_model: W-61/llama-3-8b-base-sft-ultrachat-8xh200
|
|
tags:
|
|
- alignment-handbook
|
|
- new-dpo
|
|
- generated_from_trainer
|
|
datasets:
|
|
- HuggingFaceH4/ultrafeedback_binarized
|
|
model-index:
|
|
- name: llama-3-8b-base-new-dpo-ultrafeedback-4xh200-batch-128-q_t-0.43-s_star-0.4-20260429-230725
|
|
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-new-dpo-ultrafeedback-4xh200-batch-128-q_t-0.43-s_star-0.4-20260429-230725
|
|
|
|
This model is a fine-tuned version of [W-61/llama-3-8b-base-sft-ultrachat-8xh200](https://huggingface.co/W-61/llama-3-8b-base-sft-ultrachat-8xh200) on the HuggingFaceH4/ultrafeedback_binarized dataset.
|
|
It achieves the following results on the evaluation set:
|
|
- Loss: 0.6016
|
|
- Fcm Dpo/beta: 0.0024
|
|
- Margin Dpo/margin Mean: 110.8150
|
|
- Margin Dpo/margin Std: 193.4060
|
|
- Logps/chosen: -564.3179
|
|
- Logps/rejected: -654.2360
|
|
- Logps/ref Chosen: -287.8268
|
|
- Logps/ref Rejected: -266.9300
|
|
- Kl/chosen Kl Mean: -276.4911
|
|
- Kl/rejected Kl Mean: -387.3060
|
|
- Kl/mean: -331.8985
|
|
- Kl/std: 172.4884
|
|
- Logits/chosen: -0.8581
|
|
- Logits/rejected: -0.8405
|
|
|
|
## 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: 4
|
|
- eval_batch_size: 2
|
|
- seed: 42
|
|
- distributed_type: multi-GPU
|
|
- num_devices: 4
|
|
- gradient_accumulation_steps: 8
|
|
- total_train_batch_size: 128
|
|
- total_eval_batch_size: 8
|
|
- 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 | Fcm Dpo/beta | Margin Dpo/margin Mean | Margin Dpo/margin Std | Logps/chosen | Logps/rejected | Logps/ref Chosen | Logps/ref Rejected | Kl/chosen Kl Mean | Kl/rejected Kl Mean | Kl/mean | Kl/std | Logits/chosen | Logits/rejected |
|
|
|:-------------:|:------:|:----:|:---------------:|:------------:|:----------------------:|:---------------------:|:------------:|:--------------:|:----------------:|:------------------:|:-----------------:|:-------------------:|:---------:|:--------:|:-------------:|:---------------:|
|
|
| 4.8804 | 0.4188 | 200 | 0.5899 | 0.0054 | 57.3948 | 97.5992 | -411.1033 | -447.6013 | -287.8268 | -266.9300 | -123.2765 | -180.6713 | -151.9739 | 89.3493 | -0.9016 | -0.8836 |
|
|
| 4.8661 | 0.8377 | 400 | 0.6016 | 0.0024 | 110.8150 | 193.4060 | -564.3179 | -654.2360 | -287.8268 | -266.9300 | -276.4911 | -387.3060 | -331.8985 | 172.4884 | -0.8581 | -0.8405 |
|
|
|
|
|
|
### Framework versions
|
|
|
|
- Transformers 4.51.0
|
|
- Pytorch 2.3.1+cu121
|
|
- Datasets 2.21.0
|
|
- Tokenizers 0.21.4
|