Update README.md
Browse files
README.md
CHANGED
|
@@ -99,7 +99,7 @@ This model used weights pretrained by [lxj616](https://huggingface.co/lxj616/mak
|
|
| 99 |
* 1 x 5 epochs: LR warmup for 0.5 epochs to 5e-6 then cosine annealing to 2.5e-6 (17,000 samples per ep)
|
| 100 |
* some restarts were required due to NaNs appearing in the gradient (see training logs)
|
| 101 |
* **Total update steps:** ~200,000
|
| 102 |
-
* **Hardware:**
|
| 103 |
|
| 104 |
Trainig statistics are available at [Weights and Biases](https://wandb.ai/tempofunk/makeavid-sd-tpu).
|
| 105 |
|
|
|
|
| 99 |
* 1 x 5 epochs: LR warmup for 0.5 epochs to 5e-6 then cosine annealing to 2.5e-6 (17,000 samples per ep)
|
| 100 |
* some restarts were required due to NaNs appearing in the gradient (see training logs)
|
| 101 |
* **Total update steps:** ~200,000
|
| 102 |
+
* **Hardware:** TPUv4-8 (provided by Google Cloud for the [HuggingFace JAX/Diffusers Sprint Event](https://github.com/huggingface/community-events/tree/main/jax-controlnet-sprint))
|
| 103 |
|
| 104 |
Trainig statistics are available at [Weights and Biases](https://wandb.ai/tempofunk/makeavid-sd-tpu).
|
| 105 |
|