Downloads · 30 days
3
12% of all-time downloads
pythia-2.8b-dpo_hh_rlhf
mnoukhov/pythia-2.8b-dpo_hh_rlhf
pythia-2.8b-dpo_hh_rlhf is a machine learning model from mnoukhov. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for peft.
should probably proofread and complete it, then remove this comment. --
All-time downloads
26
Public
Repo size
1.5 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors83.9 MB · 98%
At a glance
- Library
- peft
- Access
- Public
- Created
- May 1, 2024
- Updated
- May 13, 2024
- SHA
- ac3b8e8e
Base models
Model card
From the Hugging Face model README
<!-- 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. -->
pythia-2.8b-dpo_hh_rlhf
This model is a fine-tuned version of mnoukhov/pythia-2.8b-sft_hh_rlhf on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.6257
- Rewards/chosen: -0.6630
- Rewards/rejected: -1.0092
- Rewards/accuracies: 0.6427
- Rewards/margins: 0.3462
- Logps/rejected: -143.9225
- Logps/chosen: -143.9225
- Logps/ref Rejected: -134.7867
- Logps/ref Chosen: -137.2922
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: 3e-05
- train_batch_size: 8
- eval_batch_size: 4
- seed: 42
- distributed_type: multi-GPU
- gradient_accumulation_steps: 8
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- num_epochs: 1.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logps/ref Rejected | Logps/ref Chosen |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 0.6591 | 0.2 | 503 | 0.6625 | -0.2937 | -0.4623 | 0.5935 | 0.1685 | -140.2295 | -140.2295 | -134.7867 | -137.2922 |
| 0.6446 | 0.4 | 1006 | 0.6412 | -0.3936 | -0.6444 | 0.6209 | 0.2507 | -141.2284 | -141.2284 | -134.7867 | -137.2922 |
| 0.6289 | 0.6 | 1509 | 0.6296 | -0.6299 | -0.9621 | 0.6365 | 0.3322 | -143.5909 | -143.5909 | -134.7867 | -137.2922 |
| 0.6215 | 0.8 | 2012 | 0.6257 | -0.6630 | -1.0092 | 0.6427 | 0.3462 | -143.9225 | -143.9225 | -134.7867 | -137.2922 |
Framework versions
- PEFT 0.10.0
- Transformers 4.38.2
- Pytorch 2.1.2+cu121
- Datasets 2.17.0
- Tokenizers 0.15.2
- Library
- peft
- Created
- May 1, 2024
- Updated
- May 13, 2024