Update README.md
Browse files
README.md
CHANGED
|
@@ -1,31 +1,13 @@
|
|
| 1 |
---
|
| 2 |
tags:
|
| 3 |
- generated_from_trainer
|
| 4 |
-
|
| 5 |
-
|
| 6 |
-
results: []
|
| 7 |
---
|
| 8 |
|
| 9 |
-
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 10 |
-
should probably proofread and complete it, then remove this comment. -->
|
| 11 |
-
|
| 12 |
-
# pythia-1.4b-sampling-watermark-distill-kgw-k2-gamma0.25-delta2
|
| 13 |
-
|
| 14 |
-
This model is a fine-tuned version of [/scr-ssd/cygu/weights/pythia-1.4b/](https://huggingface.co//scr-ssd/cygu/weights/pythia-1.4b/) on an unknown dataset.
|
| 15 |
-
|
| 16 |
## Model description
|
| 17 |
|
| 18 |
-
|
| 19 |
-
|
| 20 |
-
## Intended uses & limitations
|
| 21 |
-
|
| 22 |
-
More information needed
|
| 23 |
-
|
| 24 |
-
## Training and evaluation data
|
| 25 |
-
|
| 26 |
-
More information needed
|
| 27 |
-
|
| 28 |
-
## Training procedure
|
| 29 |
|
| 30 |
### Training hyperparameters
|
| 31 |
|
|
@@ -39,11 +21,7 @@ The following hyperparameters were used during training:
|
|
| 39 |
- lr_scheduler_type: cosine
|
| 40 |
- lr_scheduler_warmup_steps: 500
|
| 41 |
- num_epochs: 1.0
|
| 42 |
-
|
| 43 |
-
### Training results
|
| 44 |
-
|
| 45 |
-
|
| 46 |
-
|
| 47 |
### Framework versions
|
| 48 |
|
| 49 |
- Transformers 4.29.2
|
|
|
|
| 1 |
---
|
| 2 |
tags:
|
| 3 |
- generated_from_trainer
|
| 4 |
+
- pythia
|
| 5 |
+
license: apache-2.0
|
|
|
|
| 6 |
---
|
| 7 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8 |
## Model description
|
| 9 |
|
| 10 |
+
Sampling-based watermark distilled [Pythia 1.4B](https://huggingface.co/EleutherAI/pythia-1.4b) using the KGW \\(k=2, \gamma=0.25, \delta=2\\) watermarking strategy in the paper [On the Learnability of Watermarks for Language Models](https://arxiv.org/abs/2312.04469).
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11 |
|
| 12 |
### Training hyperparameters
|
| 13 |
|
|
|
|
| 21 |
- lr_scheduler_type: cosine
|
| 22 |
- lr_scheduler_warmup_steps: 500
|
| 23 |
- num_epochs: 1.0
|
| 24 |
+
-
|
|
|
|
|
|
|
|
|
|
|
|
|
| 25 |
### Framework versions
|
| 26 |
|
| 27 |
- Transformers 4.29.2
|