Training in progress, step 450
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_150.png +0 -0
- reward_plots/advantage_plot_step_160.png +0 -0
- reward_plots/advantage_plot_step_170.png +0 -0
- reward_plots/advantage_plot_step_180.png +0 -0
- reward_plots/advantage_plot_step_190.png +0 -0
- reward_plots/advantage_plot_step_200.png +0 -0
- reward_plots/advantage_plot_step_210.png +0 -0
- reward_plots/advantage_plot_step_220.png +0 -0
- reward_plots/advantage_plot_step_230.png +0 -0
- reward_plots/advantage_plot_step_240.png +0 -0
- 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/reward_comparison_step_150.png +0 -0
- reward_plots/reward_comparison_step_160.png +0 -0
- reward_plots/reward_comparison_step_170.png +0 -0
- reward_plots/reward_comparison_step_180.png +0 -0
- reward_plots/reward_comparison_step_190.png +0 -0
- reward_plots/reward_comparison_step_200.png +0 -0
- reward_plots/reward_comparison_step_210.png +0 -0
- reward_plots/reward_comparison_step_220.png +0 -0
- reward_plots/reward_comparison_step_230.png +0 -0
- reward_plots/reward_comparison_step_240.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
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 sha256:1d98ba19bca22aae235340178a672a43e55842ee59324f8afe927c23c8a32d93
|
| 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 sha256:1ca629b352c1b6aa6c766eeb8cd6b723abdda8286b28f52a243e972169e6c8f0
|
| 3 |
+
size 179745457
|
reward_plots/advantage_plot_step_150.png
ADDED
|
reward_plots/advantage_plot_step_160.png
ADDED
|
reward_plots/advantage_plot_step_170.png
ADDED
|
reward_plots/advantage_plot_step_180.png
ADDED
|
reward_plots/advantage_plot_step_190.png
ADDED
|
reward_plots/advantage_plot_step_200.png
ADDED
|
reward_plots/advantage_plot_step_210.png
ADDED
|
reward_plots/advantage_plot_step_220.png
ADDED
|
reward_plots/advantage_plot_step_230.png
ADDED
|
reward_plots/advantage_plot_step_240.png
ADDED
|
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/reward_comparison_step_150.png
ADDED
|
reward_plots/reward_comparison_step_160.png
ADDED
|
reward_plots/reward_comparison_step_170.png
ADDED
|
reward_plots/reward_comparison_step_180.png
ADDED
|
reward_plots/reward_comparison_step_190.png
ADDED
|
reward_plots/reward_comparison_step_200.png
ADDED
|
reward_plots/reward_comparison_step_210.png
ADDED
|
reward_plots/reward_comparison_step_220.png
ADDED
|
reward_plots/reward_comparison_step_230.png
ADDED
|
reward_plots/reward_comparison_step_240.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
|