Training in progress, step 500
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- model.safetensors +1 -1
- reward_data/all_rewards.csv +2 -2
- reward_plots/advantage_plot_step_250.png +0 -0
- reward_plots/advantage_plot_step_260.png +0 -0
- reward_plots/advantage_plot_step_270.png +0 -0
- reward_plots/advantage_plot_step_280.png +0 -0
- reward_plots/advantage_plot_step_290.png +0 -0
- reward_plots/advantage_plot_step_300.png +0 -0
- reward_plots/advantage_plot_step_310.png +0 -0
- reward_plots/advantage_plot_step_320.png +0 -0
- reward_plots/advantage_plot_step_330.png +0 -0
- reward_plots/advantage_plot_step_340.png +0 -0
- reward_plots/advantage_plot_step_350.png +0 -0
- reward_plots/advantage_plot_step_360.png +0 -0
- reward_plots/advantage_plot_step_370.png +0 -0
- reward_plots/advantage_plot_step_380.png +0 -0
- reward_plots/advantage_plot_step_390.png +0 -0
- reward_plots/advantage_plot_step_400.png +0 -0
- reward_plots/advantage_plot_step_410.png +0 -0
- reward_plots/advantage_plot_step_420.png +0 -0
- reward_plots/advantage_plot_step_430.png +0 -0
- reward_plots/advantage_plot_step_440.png +0 -0
- reward_plots/advantage_plot_step_450.png +0 -0
- reward_plots/advantage_plot_step_460.png +0 -0
- reward_plots/advantage_plot_step_470.png +0 -0
- reward_plots/advantage_plot_step_480.png +0 -0
- reward_plots/advantage_plot_step_490.png +0 -0
- reward_plots/reward_comparison_step_250.png +0 -0
- reward_plots/reward_comparison_step_260.png +0 -0
- reward_plots/reward_comparison_step_270.png +0 -0
- reward_plots/reward_comparison_step_280.png +0 -0
- reward_plots/reward_comparison_step_290.png +0 -0
- reward_plots/reward_comparison_step_300.png +0 -0
- reward_plots/reward_comparison_step_310.png +0 -0
- reward_plots/reward_comparison_step_320.png +0 -0
- reward_plots/reward_comparison_step_330.png +0 -0
- reward_plots/reward_comparison_step_340.png +0 -0
- reward_plots/reward_comparison_step_350.png +0 -0
- reward_plots/reward_comparison_step_360.png +0 -0
- reward_plots/reward_comparison_step_370.png +0 -0
- reward_plots/reward_comparison_step_380.png +0 -0
- reward_plots/reward_comparison_step_390.png +0 -0
- reward_plots/reward_comparison_step_400.png +0 -0
- reward_plots/reward_comparison_step_410.png +0 -0
- reward_plots/reward_comparison_step_420.png +0 -0
- reward_plots/reward_comparison_step_430.png +0 -0
- reward_plots/reward_comparison_step_440.png +0 -0
- reward_plots/reward_comparison_step_450.png +0 -0
- reward_plots/reward_comparison_step_460.png +0 -0
- reward_plots/reward_comparison_step_470.png +0 -0
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3554214752
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a1c0c21b3fde6eae3f5b0efab95e70962e03a706b8b735830938126492a75a97
|
| 3 |
size 3554214752
|
reward_data/all_rewards.csv
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7975414281b33335edf63f902814e9f8652d26def3823295373a47439f917c43
|
| 3 |
+
size 180446461
|
reward_plots/advantage_plot_step_250.png
ADDED
|
reward_plots/advantage_plot_step_260.png
ADDED
|
reward_plots/advantage_plot_step_270.png
ADDED
|
reward_plots/advantage_plot_step_280.png
ADDED
|
reward_plots/advantage_plot_step_290.png
ADDED
|
reward_plots/advantage_plot_step_300.png
ADDED
|
reward_plots/advantage_plot_step_310.png
ADDED
|
reward_plots/advantage_plot_step_320.png
ADDED
|
reward_plots/advantage_plot_step_330.png
ADDED
|
reward_plots/advantage_plot_step_340.png
ADDED
|
reward_plots/advantage_plot_step_350.png
ADDED
|
reward_plots/advantage_plot_step_360.png
ADDED
|
reward_plots/advantage_plot_step_370.png
ADDED
|
reward_plots/advantage_plot_step_380.png
ADDED
|
reward_plots/advantage_plot_step_390.png
ADDED
|
reward_plots/advantage_plot_step_400.png
ADDED
|
reward_plots/advantage_plot_step_410.png
ADDED
|
reward_plots/advantage_plot_step_420.png
ADDED
|
reward_plots/advantage_plot_step_430.png
ADDED
|
reward_plots/advantage_plot_step_440.png
ADDED
|
reward_plots/advantage_plot_step_450.png
ADDED
|
reward_plots/advantage_plot_step_460.png
ADDED
|
reward_plots/advantage_plot_step_470.png
ADDED
|
reward_plots/advantage_plot_step_480.png
ADDED
|
reward_plots/advantage_plot_step_490.png
ADDED
|
reward_plots/reward_comparison_step_250.png
ADDED
|
reward_plots/reward_comparison_step_260.png
ADDED
|
reward_plots/reward_comparison_step_270.png
ADDED
|
reward_plots/reward_comparison_step_280.png
ADDED
|
reward_plots/reward_comparison_step_290.png
ADDED
|
reward_plots/reward_comparison_step_300.png
ADDED
|
reward_plots/reward_comparison_step_310.png
ADDED
|
reward_plots/reward_comparison_step_320.png
ADDED
|
reward_plots/reward_comparison_step_330.png
ADDED
|
reward_plots/reward_comparison_step_340.png
ADDED
|
reward_plots/reward_comparison_step_350.png
ADDED
|
reward_plots/reward_comparison_step_360.png
ADDED
|
reward_plots/reward_comparison_step_370.png
ADDED
|
reward_plots/reward_comparison_step_380.png
ADDED
|
reward_plots/reward_comparison_step_390.png
ADDED
|
reward_plots/reward_comparison_step_400.png
ADDED
|
reward_plots/reward_comparison_step_410.png
ADDED
|
reward_plots/reward_comparison_step_420.png
ADDED
|
reward_plots/reward_comparison_step_430.png
ADDED
|
reward_plots/reward_comparison_step_440.png
ADDED
|
reward_plots/reward_comparison_step_450.png
ADDED
|
reward_plots/reward_comparison_step_460.png
ADDED
|
reward_plots/reward_comparison_step_470.png
ADDED
|