ddecosmo commited on
Commit
80f9c3e
·
verified ·
1 Parent(s): 7e26dd6

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -8
README.md CHANGED
@@ -25,13 +25,6 @@ This model uses the TimmAutoModel with accuracy as the main parameter and multi
25
  - **License:** MIT
26
  - **Finetuned from model:** TimmAutoModel
27
 
28
- ### Model Sources [optional]
29
-
30
- <!-- Provide the basic links for the model. -->
31
-
32
- - **Repository:** {{ repo | default("[More Information Needed]", true)}}
33
-
34
-
35
  ## Uses
36
 
37
  <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
@@ -85,7 +78,7 @@ This model was trained with an AutoML process with accuracy as the main metrics.
85
 
86
  #### Training Hyperparameters
87
 
88
- - **Training regime:** {{ training_regime | default("[More Information Needed]", true)}} <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
89
 
90
 
91
  ## Evaluation
 
25
  - **License:** MIT
26
  - **Finetuned from model:** TimmAutoModel
27
 
 
 
 
 
 
 
 
28
  ## Uses
29
 
30
  <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
 
78
 
79
  #### Training Hyperparameters
80
 
81
+ This model used an adam optimizer, a learning rate decay of 0.9 to increase optimization speed, and 5 epochs with additional mix-up to improve robustness.
82
 
83
 
84
  ## Evaluation