Downloads · 30 days
5
2% of all-time downloads
W-61/llama-3-8b-base-new-dpo-hh-harmless-s_star1.0-4xh200-batch-64-20260422-051621
llama-3-8b-base-new-dpo-hh-harmless-s_star1.0-4xh200-batch-64-20260422-051621 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
2% of all-time downloads
All-time downloads
219
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-hh-harmless-4xh200 on the Anthropic/hh-rlhf 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 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0.9787 | 0.3023 | 200 | 0.5567 | 0.3734 | 2.2014 | 3.8516 | -79.5191 | -86.4100 | -74.8595 | -79.5490 | 0.2193 | 0.1797 |
| 0.9615 | 0.6047 | 400 | 0.5477 | 0.2316 | 3.5794 | 6.0796 | -81.7112 | -89.9802 | -74.8595 | -79.5490 | 0.2572 | 0.2148 |
| 1.1151 | 0.9070 | 600 | 0.5433 | 0.2164 | 4.4651 | 7.3418 | -82.6101 | -91.7648 | -74.8595 | -79.5490 | 0.2606 | 0.2177 |