Commit
•
7afdf8c
1
Parent(s):
d8150bf
Update README.md
Browse files
README.md
CHANGED
|
@@ -7,4 +7,9 @@ Experiments on training 0.4B RWKV models around midi notation in a manner simila
|
|
| 7 |
|
| 8 |
|
| 9 |
|
| 10 |
-
* WIP v6 pretrain that also sucks. Loss was around 2.3 to 2.5 but I'm guessing it ended up at 2.5, kind of sad but this can be used as a base I guess?
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7 |
|
| 8 |
|
| 9 |
|
| 10 |
+
* WIP v6 pretrain that also sucks. Loss was around 2.3 to 2.5 but I'm guessing it ended up at 2.5, kind of sad but this can be used as a base I guess?
|
| 11 |
+
|
| 12 |
+
## April 12, 2024 Update
|
| 13 |
+
* Added v6 with different layer sizes.
|
| 14 |
+
* Trained a base model on all of bread midi filtered by piano instrument only augumented 10 times. See the following [wandb](https://wandb.ai/smashmaster0045/Generic%20RWKV-6%20Piano%20Midi%20Model%20Base%20L29%20Augumented%20Data%20Test%20Bread%20Only/workspace) for training logs (note experimentation, finalish runs are used for the final file).
|
| 15 |
+
* Used above model as the initial model and then trained on a combined dataset of Breadmidi + Los Angeles + Monster filtered by piano augumented 3x (wish I could have the storage space to do more). See the following [wandb]https://wandb.ai/smashmaster0045/Generic%20RWKV-6%20Piano%20Midi%20Model%20Base%20L29%20Augumented%20Data%20Test%20bread%20to%20diverse%20transfer/workspace()
|