Training in progress, step 350
Browse files- model.safetensors +1 -1
- reward_data/all_rewards.csv +2 -2
- 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/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
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 sha256:60013fe7d1d4781636a042f0dee13e46431f7387b2b66c33f26f6504774fff6d
|
| 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 sha256:2ab0bfd655b1e510d461da48edde13b76c1394e9d8a2ac86d03cbe41ba226b31
|
| 3 |
+
size 223268759
|
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/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
|