Update README.md
Browse files
README.md
CHANGED
|
@@ -18,8 +18,16 @@ Sun and Moon are hereby deemed burned. My next target is to run the train entire
|
|
| 18 |
|
| 19 |
This was a high-risk possibility and I gambled. The results were most likely the deterministic results and yet I still ran them. Now the post-moretem.
|
| 20 |
|
|
|
|
|
|
|
|
|
|
| 21 |
In the coming days I'll be preparing a much more accurate timestep + pattern distillation system. I expect it to be far more accurate and much more compact.
|
| 22 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 23 |
|
| 24 |
|
| 25 |
# I've decided to name this model
|
|
|
|
| 18 |
|
| 19 |
This was a high-risk possibility and I gambled. The results were most likely the deterministic results and yet I still ran them. Now the post-moretem.
|
| 20 |
|
| 21 |
+
|
| 22 |
+
|
| 23 |
+
|
| 24 |
In the coming days I'll be preparing a much more accurate timestep + pattern distillation system. I expect it to be far more accurate and much more compact.
|
| 25 |
|
| 26 |
+
I've learned that David's timestep bias pushed the flow-state of the model towards the higher timesteps based on the probes.
|
| 27 |
+
I should have been wiser about this earlier on and weighted heavier, but I doubt this would have mattered in the long run.
|
| 28 |
+
David simply wasn't ready to teach, and the model is too bulky to learn much more.
|
| 29 |
+
|
| 30 |
+
The only answer is a smaller and more concise model specific to the task.
|
| 31 |
|
| 32 |
|
| 33 |
# I've decided to name this model
|