d8351d8ef7
Model: jackf857/qwen3-8b-base-beta-dpo-hh-harmless-4xh200-batch-64 Source: Original Platform
85 lines
4.8 KiB
Markdown
85 lines
4.8 KiB
Markdown
---
|
|
library_name: transformers
|
|
tags:
|
|
- alignment-handbook
|
|
- beta-dpo
|
|
- generated_from_trainer
|
|
datasets:
|
|
- Anthropic/hh-rlhf
|
|
model-index:
|
|
- name: qwen3-8b-base-beta-dpo-hh-harmless-4xh200-batch-64-20260418-012645
|
|
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. -->
|
|
|
|
# qwen3-8b-base-beta-dpo-hh-harmless-4xh200-batch-64-20260418-012645
|
|
|
|
This model is a fine-tuned version of `/scratch/qu.yang1/dynamic-dpo-v4/outputs/qwen3-8b-base-sft-hh-helpful-4xh200-batch-64-20260417-214452` on the Anthropic/hh-rlhf dataset.
|
|
It achieves the following results on the evaluation set:
|
|
- Loss: 0.6518
|
|
- Beta Dpo/beta: 0.1628
|
|
- Beta Dpo/loss Margin Mean: 8.6336
|
|
- Beta Dpo/beta Margin Mean: 1.6614
|
|
- Beta Dpo/beta Margin Std: 2.5181
|
|
- Beta Dpo/beta Margin Grad Mean: -0.3428
|
|
- Beta Dpo/beta Margin Grad Std: 0.2482
|
|
- Beta Dpo/gap Mean: 7.7476
|
|
- Beta Dpo/gap Std: 14.8995
|
|
- Beta Dpo/beta Used Raw: 0.1532
|
|
- Beta Dpo/beta Used: 0.1628
|
|
- Beta Dpo/mask Keep Frac: 1.0
|
|
- Logits/chosen: 1.2071
|
|
- Logits/rejected: 1.1403
|
|
|
|
## 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: 8
|
|
- eval_batch_size: 8
|
|
- seed: 42
|
|
- distributed_type: multi-GPU
|
|
- num_devices: 4
|
|
- gradient_accumulation_steps: 2
|
|
- total_train_batch_size: 64
|
|
- total_eval_batch_size: 32
|
|
- 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/beta | Beta Dpo/loss Margin Mean | Beta Dpo/beta Margin Mean | Beta Dpo/beta Margin Std | Beta Dpo/beta Margin Grad Mean | Beta Dpo/beta Margin Grad Std | 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 |
|
|
|:-------------:|:------:|:----:|:---------------:|:-------------:|:-------------------------:|:-------------------------:|:------------------------:|:------------------------------:|:-----------------------------:|:-----------------:|:----------------:|:----------------------:|:------------------:|:-----------------------:|:-------------:|:---------------:|
|
|
| 1.3654 | 0.1512 | 100 | 0.6641 | 0.1110 | 0.6060 | 0.0717 | 0.2130 | -0.4824 | 0.0521 | 0.4233 | 1.6301 | 0.1110 | 0.1110 | 1.0 | 1.3014 | 1.2543 |
|
|
| 0.9954 | 0.3023 | 200 | 0.6120 | 0.0999 | 4.1607 | 0.5099 | 0.9505 | -0.4145 | 0.1620 | 4.2136 | 9.3730 | 0.0968 | 0.0999 | 1.0 | 0.9179 | 0.8638 |
|
|
| 1.2007 | 0.4535 | 300 | 0.6115 | 0.1346 | 6.6135 | 1.0588 | 1.7069 | -0.3695 | 0.2169 | 6.1583 | 12.2942 | 0.1273 | 0.1346 | 1.0 | 1.2327 | 1.1646 |
|
|
| 1.3823 | 0.6047 | 400 | 0.5951 | 0.1019 | 6.9792 | 0.8735 | 1.3552 | -0.3881 | 0.1738 | 7.2064 | 12.6529 | 0.0864 | 0.1019 | 1.0 | 1.2965 | 1.2260 |
|
|
| 1.2301 | 0.7559 | 500 | 0.6311 | 0.1290 | 8.6766 | 1.3653 | 2.0186 | -0.3625 | 0.2097 | 8.4351 | 15.6317 | 0.1145 | 0.1290 | 1.0 | 1.2194 | 1.1512 |
|
|
| 1.0426 | 0.9070 | 600 | 0.6518 | 0.1628 | 8.6336 | 1.6614 | 2.5181 | -0.3428 | 0.2482 | 7.7476 | 14.8995 | 0.1532 | 0.1628 | 1.0 | 1.2071 | 1.1403 |
|
|
|
|
|
|
### Framework versions
|
|
|
|
- Transformers 4.51.0
|
|
- Pytorch 2.3.1+cu121
|
|
- Datasets 2.21.0
|
|
- Tokenizers 0.21.4
|