Downloads · 30 days
5
1% of all-time downloads
W-61/llama-3-8b-base-new-dpo-ultrafeedback-4xh200-batch-128-q_t-0.43-s_star-0.4-20260429-230725
llama-3-8b-base-new-dpo-ultrafeedback-4xh200-batch-128-q_t-0.43-s_star-0.4-20260429-230725 is a text generation model from W-61. Use it when you need the model to write or continue text. It is set up for transformers.
should probably proofread and complete it, then remove this comment. --
Downloads · 30 days
5
1% of all-time downloads
All-time downloads
400
Public
Parameters
8B
32.1 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors32.1 GB · 100%
From the Hugging Face model README
This model is a fine-tuned version of W-61/llama-3-8b-base-sft-ultrachat-8xh200 on the HuggingFaceH4/ultrafeedback_binarized dataset. It achieves the following results on the evaluation set:
More information needed
More information needed
More information needed
The following hyperparameters were used during training:
| 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 |