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-0.45-s_star-0.3-20260428-045924
|
||
|
|
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-0.45-s_star-0.3-20260428-045924
|
||
|
|
|
||
|
|
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: 0.6247
|
||
|
|
- Fcm Dpo/beta: 0.0013
|
||
|
|
- Margin Dpo/margin Mean: 159.3335
|
||
|
|
- Margin Dpo/margin Std: 334.4711
|
||
|
|
- Logps/chosen: -719.7628
|
||
|
|
- Logps/rejected: -858.1997
|
||
|
|
- Logps/ref Chosen: -287.8268
|
||
|
|
- Logps/ref Rejected: -266.9300
|
||
|
|
- Kl/chosen Kl Mean: -431.9361
|
||
|
|
- Kl/rejected Kl Mean: -591.2697
|
||
|
|
- Kl/mean: -511.6028
|
||
|
|
- Kl/std: 291.8582
|
||
|
|
- Logits/chosen: -0.7614
|
||
|
|
- Logits/rejected: -0.7369
|
||
|
|
|
||
|
|
## 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 |
|
||
|
|
|:-------------:|:------:|:----:|:---------------:|:------------:|:----------------------:|:---------------------:|:------------:|:--------------:|:----------------:|:------------------:|:-----------------:|:-------------------:|:---------:|:--------:|:-------------:|:---------------:|
|
||
|
|
| 4.9611 | 0.4188 | 200 | 0.6006 | 0.0042 | 62.7416 | 107.9594 | -420.2400 | -462.0849 | -287.8268 | -266.9300 | -132.4133 | -195.1548 | -163.7841 | 96.7906 | -0.8913 | -0.8725 |
|
||
|
|
| 4.9672 | 0.8377 | 400 | 0.6247 | 0.0013 | 159.3335 | 334.4711 | -719.7628 | -858.1997 | -287.8268 | -266.9300 | -431.9361 | -591.2697 | -511.6028 | 291.8582 | -0.7614 | -0.7369 |
|
||
|
|
|
||
|
|
|
||
|
|
### Framework versions
|
||
|
|
|
||
|
|
- Transformers 4.51.0
|
||
|
|
- Pytorch 2.3.1+cu121
|
||
|
|
- Datasets 2.21.0
|
||
|
|
- Tokenizers 0.21.4
|