Upload PolyGuard training artifacts: outputs/plots
Browse files- .gitattributes +2 -0
- outputs/plots/anti_cheat_failure_rates.png +0 -0
- outputs/plots/avg_process_fidelity.png +0 -0
- outputs/plots/avg_reward.png +0 -0
- outputs/plots/grpo_reward_curves.png +3 -0
- outputs/plots/inference_latency_validity.png +0 -0
- outputs/plots/inference_validity_reward.png +0 -0
- outputs/plots/legality_rate.png +0 -0
- outputs/plots/policy_stack_avg_reward.png +0 -0
- outputs/plots/qwen_model_grpo_reward.png +0 -0
- outputs/plots/qwen_model_sft_loss.png +0 -0
- outputs/plots/qwen_model_sft_reward.png +0 -0
- outputs/plots/reward_component_bars.png +3 -0
- outputs/plots/sft_loss_curves.png +0 -0
- outputs/plots/sft_validity_reward.png +0 -0
- outputs/plots/sft_vs_grpo_reward.png +0 -0
- outputs/plots/success_rate.png +0 -0
- outputs/plots/train_holdout_gap.png +0 -0
.gitattributes
CHANGED
|
@@ -45,3 +45,5 @@ checkpoints/sweeps/qwen-qwen2-5-3b-instruct/merged/tokenizer.json filter=lfs dif
|
|
| 45 |
checkpoints/sft_adapter/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 46 |
checkpoints/grpo_adapter/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 47 |
checkpoints/merged/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
| 45 |
checkpoints/sft_adapter/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 46 |
checkpoints/grpo_adapter/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 47 |
checkpoints/merged/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 48 |
+
outputs/plots/grpo_reward_curves.png filter=lfs diff=lfs merge=lfs -text
|
| 49 |
+
outputs/plots/reward_component_bars.png filter=lfs diff=lfs merge=lfs -text
|
outputs/plots/anti_cheat_failure_rates.png
ADDED
|
outputs/plots/avg_process_fidelity.png
ADDED
|
outputs/plots/avg_reward.png
ADDED
|
outputs/plots/grpo_reward_curves.png
ADDED
|
Git LFS Details
|
outputs/plots/inference_latency_validity.png
ADDED
|
outputs/plots/inference_validity_reward.png
ADDED
|
outputs/plots/legality_rate.png
ADDED
|
outputs/plots/policy_stack_avg_reward.png
ADDED
|
outputs/plots/qwen_model_grpo_reward.png
ADDED
|
outputs/plots/qwen_model_sft_loss.png
ADDED
|
outputs/plots/qwen_model_sft_reward.png
ADDED
|
outputs/plots/reward_component_bars.png
ADDED
|
Git LFS Details
|
outputs/plots/sft_loss_curves.png
ADDED
|
outputs/plots/sft_validity_reward.png
ADDED
|
outputs/plots/sft_vs_grpo_reward.png
ADDED
|
outputs/plots/success_rate.png
ADDED
|
outputs/plots/train_holdout_gap.png
ADDED
|