Phase 1 checkpoint, epoch None

README.md

@@ -7,7 +7,7 @@ tags:
 - mamba
 ---
 
-# mmm
+# MMM
 
 Retrieval augmented state space model for real time character animation: a
 Mamba backbone that takes a joystick request, its own previous pose, and `k`
@@ -25,8 +25,8 @@ The database this checkpoint was trained against:
 
 | | |
 | --- | --- |
-| fingerprint | `f2afa3c11db090a3` |
-| rows (frames) | 978,767 |
+| fingerprint | `eb460d0093b66709` |
+| rows (frames) | 962,891 |
 | pose width | 151 |
 | frame time | 0.016666666666666666 s |
 | clips | 77 (aiming1_subject1, aiming1_subject4, aiming2_subject2, aiming2_subject3...) |
@@ -59,11 +59,11 @@ retrieved poses are in a different space from the ones the model learned on.
 
 | epoch | train | validation |
 | --- | --- | --- |
-| 1 (first) | 1.3656 | 0.9081 |
-| 48 (best) | 0.2830 | 0.2620 |
-| 50 (last) | 0.2826 | 0.2622 |
+| 1 (first) | 1.1842 | 0.5915 |
+| 55 (best) | 0.2827 | 0.2243 |
+| 56 (last) | 0.2816 | 0.2262 |
 
-Trained for 50 epochs.
+Trained for 56 epochs.
 
 ## Retrieval gain
 
@@ -80,8 +80,8 @@ to ignore retrieval, and its gain sits at zero whatever the model has learned.
 
 | regime | with retrieval | without | gain |
 | --- | --- | --- | --- |
-| teacher forced | 0.2620 | 0.2620 | +0.0000 |
-| **free running** | 0.5766 | 0.5766 | **+0.0000** |
+| teacher forced | 0.2243 | 0.2243 | +0.0000 |
+| **free running** | 0.7945 | 0.7945 | **+0.0000** |
 
 ## Provenance