42e9e465a7
Model: jackf857/qwen3-8b-base-epsilon-dpo-hh-harmless-4xh200-batch-64-20260424-040415 Source: Original Platform
85 lines
4.2 KiB
Markdown
85 lines
4.2 KiB
Markdown
---
|
|
library_name: transformers
|
|
base_model: jackf857/qwen3-8b-base-sft-hh-harmless-4xh200-batch-64-20260417-214452
|
|
tags:
|
|
- alignment-handbook
|
|
- epsilon-dpo
|
|
- generated_from_trainer
|
|
datasets:
|
|
- Anthropic/hh-rlhf
|
|
model-index:
|
|
- name: qwen3-8b-base-epsilon-dpo-hh-harmless-4xh200-batch-64-20260424-040415
|
|
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-epsilon-dpo-hh-harmless-4xh200-batch-64-20260424-040415
|
|
|
|
This model is a fine-tuned version of [jackf857/qwen3-8b-base-sft-hh-harmless-4xh200-batch-64-20260417-214452](https://huggingface.co/jackf857/qwen3-8b-base-sft-hh-harmless-4xh200-batch-64-20260417-214452) on the Anthropic/hh-rlhf dataset.
|
|
It achieves the following results on the evaluation set:
|
|
- Loss: 0.5633
|
|
- Rewards/chosen: -0.6512
|
|
- Rewards/rejected: -1.0488
|
|
- Rewards/accuracies: 0.7328
|
|
- Rewards/margins: 0.3976
|
|
- Logps/chosen: -149.9445
|
|
- Logps/rejected: -198.7271
|
|
- Logps/ref Chosen: -86.9018
|
|
- Logps/ref Rejected: -96.6964
|
|
- Logits/chosen: -1.3052
|
|
- Logits/rejected: -1.4319
|
|
- Kl/p Epsilon Steps: 0.7289
|
|
- Kl/n Epsilon Steps: 0.2689
|
|
|
|
## 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 | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/chosen | Logps/rejected | Logps/ref Chosen | Logps/ref Rejected | Logits/chosen | Logits/rejected | Kl/p Epsilon Steps | Kl/n Epsilon Steps |
|
|
|:-------------:|:------:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:------------:|:--------------:|:----------------:|:------------------:|:-------------:|:---------------:|:------------------:|:------------------:|
|
|
| 1.3249 | 0.1512 | 100 | 0.6600 | 0.0570 | -0.0181 | 0.6822 | 0.0751 | -86.2224 | -96.9165 | -86.9018 | -96.6964 | -0.7700 | -0.7965 | 0.6761 | 0.3226 |
|
|
| 1.1555 | 0.3023 | 200 | 0.5709 | -0.2620 | -0.7050 | 0.7091 | 0.4431 | -91.2424 | -108.5375 | -86.9018 | -96.6964 | -1.2620 | -1.3218 | 0.6923 | 0.3050 |
|
|
| 1.1837 | 0.4535 | 300 | 0.5444 | -0.9429 | -1.5861 | 0.7377 | 0.6432 | -110.7582 | -137.0542 | -86.9018 | -96.6964 | -1.3035 | -1.4158 | 0.7306 | 0.2689 |
|
|
| 1.2239 | 0.6047 | 400 | 0.5372 | -0.9501 | -1.5951 | 0.7430 | 0.6451 | -124.1300 | -159.5326 | -86.9018 | -96.6964 | -1.2494 | -1.3749 | 0.7372 | 0.2614 |
|
|
| 1.0454 | 0.7559 | 500 | 0.5415 | -0.9468 | -1.5190 | 0.7350 | 0.5722 | -145.2611 | -190.7861 | -86.9018 | -96.6964 | -1.2671 | -1.3971 | 0.7293 | 0.2680 |
|
|
| 1.1764 | 0.9070 | 600 | 0.5633 | -0.6512 | -1.0488 | 0.7328 | 0.3976 | -149.9445 | -198.7271 | -86.9018 | -96.6964 | -1.3052 | -1.4319 | 0.7289 | 0.2689 |
|
|
|
|
|
|
### Framework versions
|
|
|
|
- Transformers 4.51.0
|
|
- Pytorch 2.3.1+cu121
|
|
- Datasets 2.21.0
|
|
- Tokenizers 0.21.4
|