theunnecessarythings commited on
Commit
1ab2aa5
1 Parent(s): 6656ad9

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +53 -0
README.md ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language: en
3
+ license: apache-2.0
4
+ library_name: diffusers
5
+ tags: []
6
+ metrics: []
7
+ ---
8
+
9
+ <!-- This model card has been generated automatically according to the information the training script had access to. You
10
+ should probably proofread and complete it, then remove this comment. -->
11
+
12
+ # ddpm-ema-fairface-64
13
+
14
+ ## Model description
15
+
16
+ This diffusion model is trained with the [🤗 Diffusers](https://github.com/huggingface/diffusers) library
17
+ on the `None` dataset.
18
+
19
+ ## Intended uses & limitations
20
+
21
+ #### How to use
22
+
23
+ ```python
24
+ # TODO: add an example code snippet for running this diffusion pipeline
25
+ ```
26
+
27
+ #### Limitations and bias
28
+
29
+ [TODO: provide examples of latent issues and potential remediations]
30
+
31
+ ## Training data
32
+
33
+ [TODO: describe the data used to train the model]
34
+
35
+ ### Training hyperparameters
36
+
37
+ The following hyperparameters were used during training:
38
+ - learning_rate: 0.0001
39
+ - train_batch_size: 128
40
+ - eval_batch_size: 16
41
+ - gradient_accumulation_steps: 1
42
+ - optimizer: AdamW with betas=(0.95, 0.999), weight_decay=1e-06 and epsilon=1e-08
43
+ - lr_scheduler: cosine
44
+ - lr_warmup_steps: 500
45
+ - ema_inv_gamma: 1.0
46
+ - ema_inv_gamma: 0.75
47
+ - ema_inv_gamma: 0.9999
48
+ - mixed_precision: no
49
+
50
+ ### Training results
51
+
52
+ 📈 [TensorBoard logs](https://huggingface.co/sreerajr000/ddpm-ema-fairface-64/tensorboard?#scalars)
53
+