Downloads · 30 days
4
9% of all-time downloads
W-61/llama-3-8b-base-new-dpo-ultrafeedback-4xh200-batch-128-q_star-0.5-20260425-111846
llama-3-8b-base-new-dpo-ultrafeedback-4xh200-batch-128-q_star-0.5-20260425-111846 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
4
9% of all-time downloads
All-time downloads
44
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 | Logits/chosen | Logits/rejected |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 4.5242 | 0.4188 | 200 | 0.5418 | 0.1032 | 5.5540 | 8.2716 | -285.2001 | -269.8573 | -287.8268 | -266.9300 | -0.6722 | -0.6840 |
| 4.2077 | 0.8377 | 400 | 0.5320 | 0.0448 | 13.8314 | 19.8413 | -289.8538 | -282.7885 | -287.8268 | -266.9300 | -0.7499 | -0.7545 |