percentage prompts, deleting previous

Significant-Gravitas · Sep 22, 2023 · 6194c30 · 6194c30
1 parent 8cdfe4d
commit 6194c30
Show file tree

Hide file tree

Showing 8 changed files with 27,143 additions and 44 deletions.
diff --git a/paper/monitor.ipynb b/paper/monitor.ipynb
diff --git a/paper/results/reasoning_coarse_optimization_1/optimization_run_logs.txt b/paper/results/reasoning_coarse_optimization_1/optimization_run_logs.txt
@@ -706,3 +706,14 @@ An error occurred: You exceeded your current quota, please check your plan and b
 An error occurred: You exceeded your current quota, please check your plan and billing details.. Retrying... (attempt 5)
 An error occurred: You exceeded your current quota, please check your plan and billing details.. Retrying... (attempt 6)
 Error: None
+An error occurred: You exceeded your current quota, please check your plan and billing details.. Retrying... (attempt 1)
+An error occurred: You exceeded your current quota, please check your plan and billing details.. Retrying... (attempt 1)
+An error occurred: You exceeded your current quota, please check your plan and billing details.. Retrying... (attempt 2)
+An error occurred: You exceeded your current quota, please check your plan and billing details.. Retrying... (attempt 2)
+An error occurred: You exceeded your current quota, please check your plan and billing details.. Retrying... (attempt 3)
+An error occurred: You exceeded your current quota, please check your plan and billing details.. Retrying... (attempt 3)
+An error occurred: You exceeded your current quota, please check your plan and billing details.. Retrying... (attempt 4)
+An error occurred: You exceeded your current quota, please check your plan and billing details.. Retrying... (attempt 4)
+An error occurred: You exceeded your current quota, please check your plan and billing details.. Retrying... (attempt 5)
+An error occurred: You exceeded your current quota, please check your plan and billing details.. Retrying... (attempt 5)
+An error occurred: You exceeded your current quota, please check your plan and billing details.. Retrying... (attempt 6)

diff --git a/paper/results/training_iteration_6/2023-09-21_23-45-32_1.json b/paper/results/training_iteration_6/2023-09-21_23-45-32_1.json
diff --git a/paper/results/training_iteration_6/2023-09-21_23-51-34_1.json b/paper/results/training_iteration_6/2023-09-21_23-51-34_1.json
diff --git a/paper/results/training_iteration_6/2023-09-21_23-52-09_1.json b/paper/results/training_iteration_6/2023-09-21_23-52-09_1.json
diff --git a/paper/results/training_iteration_6/2023-09-21_23-58-09_1.json b/paper/results/training_iteration_6/2023-09-21_23-58-09_1.json
diff --git a/paper/results/training_iteration_6/2023-09-21_23-58-33_1.json b/paper/results/training_iteration_6/2023-09-21_23-58-33_1.json
diff --git a/paper/run_status_log.txt b/paper/run_status_log.txt
@@ -2,26 +2,26 @@
 ============================================================
                        STATUS UPDATE                        
 ============================================================
-Start Time: 2023-09-21_09-55-05
-Params: agent_explanation_msg: 1, scoring_msg: 1, not_too_strict_msg: 1, few_shot_msg: 1, description_msg: 1, previous_action: 1, prompt_msg: 1, whitelist_msg: 1, pre_read_msg: 0
+Start Time: 2023-09-22_00-06-05
+Params: agent_explanation_msg: 1, scoring_msg: 1, not_too_strict_msg: 1, few_shot_msg: 1, description_msg: 1, previous_action: 0, prompt_msg: 1, whitelist_msg: 1, pre_read_msg: 1
 
-Time: 2023-09-21 09:58:56
-Challenges processed: 27
-Runs processed: 41
-Total logs processed: 132
-Inserted logs processed: 39
-Total tokens used: 397723
-Total Overall Cost: $1.2
+Time: 2023-09-22 00:06:43
+Challenges processed: 3
+Runs processed: 5
+Total logs processed: 13
+Inserted logs processed: 2
+Total tokens used: 39174
+Total Overall Cost: $0.118
 
-Running Accuracy: 66.667%
-Precision: 46.988%
+Running Accuracy: 30.769%
+Precision: 18.182%
 Recall: 100.0%
-F1 Score: 63.934%
-Counters: TP: 39, FP: 44, TN: 49, FN: 0
-Running Average Score: 0.371
+F1 Score: 30.769%
+Counters: TP: 2, FP: 9, TN: 2, FN: 0
+Running Average Score: 31.585
 
-Current Challenge: TestRememberGoal_Simple
-Current Run: 2023-08-13 01:10:00+00:00
-Current Log: 1
-Challenges left: 2
+Current Challenge: TestAdaptLink
+Current Run: 2023-08-14 21:38:00+00:00
+Current Log: 2
+Challenges left: 26
 ============================================================