Add files using upload-large-folder tool
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- eval_results/global_step_80/mmlu_stem/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl +0 -0
- eval_results/global_step_90/mmlu_stem/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl +0 -0
- eval_results_avg4/global_step_0/amc23/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl +0 -0
- eval_results_avg4/global_step_10/amc23/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl +0 -0
- eval_results_avg4/global_step_100/amc23/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl +0 -0
- eval_results_avg4/global_step_20/aime24/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl +0 -0
- eval_results_avg4/global_step_20/aime24/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json +15 -0
- eval_results_avg4/global_step_20/aime25/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl +0 -0
- eval_results_avg4/global_step_20/aime25/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json +15 -0
- eval_results_avg4/global_step_20/amc23/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl +0 -0
- eval_results_avg4/global_step_20/amc23/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json +15 -0
- eval_results_avg4/global_step_30/aime24/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl +0 -0
- eval_results_avg4/global_step_30/aime24/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json +15 -0
- eval_results_avg4/global_step_30/aime25/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl +0 -0
- eval_results_avg4/global_step_30/aime25/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json +15 -0
- eval_results_avg4/global_step_30/amc23/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl +0 -0
- eval_results_avg4/global_step_30/amc23/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json +15 -0
- eval_results_avg4/global_step_40/aime24/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl +0 -0
- eval_results_avg4/global_step_40/aime24/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json +15 -0
- eval_results_avg4/global_step_40/aime25/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl +0 -0
- eval_results_avg4/global_step_40/aime25/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json +15 -0
- eval_results_avg4/global_step_40/amc23/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl +0 -0
- eval_results_avg4/global_step_40/amc23/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json +15 -0
- eval_results_avg4/global_step_50/aime24/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl +0 -0
- eval_results_avg4/global_step_50/aime24/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json +15 -0
- eval_results_avg4/global_step_50/aime25/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl +0 -0
- eval_results_avg4/global_step_50/aime25/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json +15 -0
- eval_results_avg4/global_step_50/amc23/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl +0 -0
- eval_results_avg4/global_step_50/amc23/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json +15 -0
- eval_results_avg4/global_step_60/aime24/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl +0 -0
- eval_results_avg4/global_step_60/aime24/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json +15 -0
- eval_results_avg4/global_step_60/aime25/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl +0 -0
- eval_results_avg4/global_step_60/aime25/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json +15 -0
- eval_results_avg4/global_step_60/amc23/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl +0 -0
- eval_results_avg4/global_step_60/amc23/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json +15 -0
- eval_results_avg4/global_step_70/aime24/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl +0 -0
- eval_results_avg4/global_step_70/aime24/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json +15 -0
- eval_results_avg4/global_step_70/aime25/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl +0 -0
- eval_results_avg4/global_step_70/aime25/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json +15 -0
- eval_results_avg4/global_step_70/amc23/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl +0 -0
- eval_results_avg4/global_step_70/amc23/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json +15 -0
- eval_results_avg4/global_step_80/aime24/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl +0 -0
- eval_results_avg4/global_step_80/aime24/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json +15 -0
- eval_results_avg4/global_step_80/aime25/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl +0 -0
- eval_results_avg4/global_step_80/aime25/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json +15 -0
- eval_results_avg4/global_step_80/amc23/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl +0 -0
- eval_results_avg4/global_step_80/amc23/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json +15 -0
- eval_results_avg4/global_step_90/aime24/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl +0 -0
- eval_results_avg4/global_step_90/aime24/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json +15 -0
- eval_results_avg4/global_step_90/aime25/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl +0 -0
eval_results/global_step_80/mmlu_stem/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
eval_results/global_step_90/mmlu_stem/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
eval_results_avg4/global_step_0/amc23/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
eval_results_avg4/global_step_10/amc23/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
eval_results_avg4/global_step_100/amc23/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
eval_results_avg4/global_step_20/aime24/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
eval_results_avg4/global_step_20/aime24/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"num_samples": 30,
|
| 3 |
+
"num_scores": 120,
|
| 4 |
+
"timeout_samples": 0,
|
| 5 |
+
"empty_samples": 0,
|
| 6 |
+
"acc": 7.5,
|
| 7 |
+
"pass_acc": 13.3,
|
| 8 |
+
"pass@k": {
|
| 9 |
+
"1": 7.5,
|
| 10 |
+
"2": 10.0,
|
| 11 |
+
"4": 13.3
|
| 12 |
+
},
|
| 13 |
+
"time_use_in_second": 186.08295559883118,
|
| 14 |
+
"time_use_in_minite": "3:06"
|
| 15 |
+
}
|
eval_results_avg4/global_step_20/aime25/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
eval_results_avg4/global_step_20/aime25/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"num_samples": 30,
|
| 3 |
+
"num_scores": 120,
|
| 4 |
+
"timeout_samples": 2,
|
| 5 |
+
"empty_samples": 0,
|
| 6 |
+
"acc": 3.3,
|
| 7 |
+
"pass_acc": 6.7,
|
| 8 |
+
"pass@k": {
|
| 9 |
+
"1": 3.3,
|
| 10 |
+
"2": 5.0,
|
| 11 |
+
"4": 6.7
|
| 12 |
+
},
|
| 13 |
+
"time_use_in_second": 192.41068124771118,
|
| 14 |
+
"time_use_in_minite": "3:12"
|
| 15 |
+
}
|
eval_results_avg4/global_step_20/amc23/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
eval_results_avg4/global_step_20/amc23/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"num_samples": 40,
|
| 3 |
+
"num_scores": 160,
|
| 4 |
+
"timeout_samples": 0,
|
| 5 |
+
"empty_samples": 0,
|
| 6 |
+
"acc": 31.9,
|
| 7 |
+
"pass_acc": 57.5,
|
| 8 |
+
"pass@k": {
|
| 9 |
+
"1": 31.9,
|
| 10 |
+
"2": 43.8,
|
| 11 |
+
"4": 57.5
|
| 12 |
+
},
|
| 13 |
+
"time_use_in_second": 180.19133973121643,
|
| 14 |
+
"time_use_in_minite": "3:00"
|
| 15 |
+
}
|
eval_results_avg4/global_step_30/aime24/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
eval_results_avg4/global_step_30/aime24/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"num_samples": 30,
|
| 3 |
+
"num_scores": 120,
|
| 4 |
+
"timeout_samples": 0,
|
| 5 |
+
"empty_samples": 0,
|
| 6 |
+
"acc": 8.3,
|
| 7 |
+
"pass_acc": 16.7,
|
| 8 |
+
"pass@k": {
|
| 9 |
+
"1": 8.3,
|
| 10 |
+
"2": 11.7,
|
| 11 |
+
"4": 16.7
|
| 12 |
+
},
|
| 13 |
+
"time_use_in_second": 199.80340933799744,
|
| 14 |
+
"time_use_in_minite": "3:19"
|
| 15 |
+
}
|
eval_results_avg4/global_step_30/aime25/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
eval_results_avg4/global_step_30/aime25/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"num_samples": 30,
|
| 3 |
+
"num_scores": 120,
|
| 4 |
+
"timeout_samples": 0,
|
| 5 |
+
"empty_samples": 0,
|
| 6 |
+
"acc": 2.5,
|
| 7 |
+
"pass_acc": 6.7,
|
| 8 |
+
"pass@k": {
|
| 9 |
+
"1": 2.5,
|
| 10 |
+
"2": 4.4,
|
| 11 |
+
"4": 6.7
|
| 12 |
+
},
|
| 13 |
+
"time_use_in_second": 177.68960404396057,
|
| 14 |
+
"time_use_in_minite": "2:57"
|
| 15 |
+
}
|
eval_results_avg4/global_step_30/amc23/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
eval_results_avg4/global_step_30/amc23/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"num_samples": 40,
|
| 3 |
+
"num_scores": 160,
|
| 4 |
+
"timeout_samples": 0,
|
| 5 |
+
"empty_samples": 0,
|
| 6 |
+
"acc": 35.0,
|
| 7 |
+
"pass_acc": 57.5,
|
| 8 |
+
"pass@k": {
|
| 9 |
+
"1": 35.0,
|
| 10 |
+
"2": 46.2,
|
| 11 |
+
"4": 57.5
|
| 12 |
+
},
|
| 13 |
+
"time_use_in_second": 171.15805864334106,
|
| 14 |
+
"time_use_in_minite": "2:51"
|
| 15 |
+
}
|
eval_results_avg4/global_step_40/aime24/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
eval_results_avg4/global_step_40/aime24/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"num_samples": 30,
|
| 3 |
+
"num_scores": 120,
|
| 4 |
+
"timeout_samples": 0,
|
| 5 |
+
"empty_samples": 0,
|
| 6 |
+
"acc": 5.8,
|
| 7 |
+
"pass_acc": 13.3,
|
| 8 |
+
"pass@k": {
|
| 9 |
+
"1": 5.8,
|
| 10 |
+
"2": 8.3,
|
| 11 |
+
"4": 13.3
|
| 12 |
+
},
|
| 13 |
+
"time_use_in_second": 197.28611159324646,
|
| 14 |
+
"time_use_in_minite": "3:17"
|
| 15 |
+
}
|
eval_results_avg4/global_step_40/aime25/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
eval_results_avg4/global_step_40/aime25/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"num_samples": 30,
|
| 3 |
+
"num_scores": 120,
|
| 4 |
+
"timeout_samples": 0,
|
| 5 |
+
"empty_samples": 0,
|
| 6 |
+
"acc": 4.2,
|
| 7 |
+
"pass_acc": 6.7,
|
| 8 |
+
"pass@k": {
|
| 9 |
+
"1": 4.2,
|
| 10 |
+
"2": 5.0,
|
| 11 |
+
"4": 6.7
|
| 12 |
+
},
|
| 13 |
+
"time_use_in_second": 148.28442645072937,
|
| 14 |
+
"time_use_in_minite": "2:28"
|
| 15 |
+
}
|
eval_results_avg4/global_step_40/amc23/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
eval_results_avg4/global_step_40/amc23/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"num_samples": 40,
|
| 3 |
+
"num_scores": 160,
|
| 4 |
+
"timeout_samples": 1,
|
| 5 |
+
"empty_samples": 0,
|
| 6 |
+
"acc": 33.1,
|
| 7 |
+
"pass_acc": 52.5,
|
| 8 |
+
"pass@k": {
|
| 9 |
+
"1": 33.1,
|
| 10 |
+
"2": 44.2,
|
| 11 |
+
"4": 52.5
|
| 12 |
+
},
|
| 13 |
+
"time_use_in_second": 48.400896310806274,
|
| 14 |
+
"time_use_in_minite": "0:48"
|
| 15 |
+
}
|
eval_results_avg4/global_step_50/aime24/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
eval_results_avg4/global_step_50/aime24/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"num_samples": 30,
|
| 3 |
+
"num_scores": 120,
|
| 4 |
+
"timeout_samples": 0,
|
| 5 |
+
"empty_samples": 0,
|
| 6 |
+
"acc": 8.3,
|
| 7 |
+
"pass_acc": 16.7,
|
| 8 |
+
"pass@k": {
|
| 9 |
+
"1": 8.3,
|
| 10 |
+
"2": 12.2,
|
| 11 |
+
"4": 16.7
|
| 12 |
+
},
|
| 13 |
+
"time_use_in_second": 185.73703575134277,
|
| 14 |
+
"time_use_in_minite": "3:05"
|
| 15 |
+
}
|
eval_results_avg4/global_step_50/aime25/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
eval_results_avg4/global_step_50/aime25/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"num_samples": 30,
|
| 3 |
+
"num_scores": 120,
|
| 4 |
+
"timeout_samples": 0,
|
| 5 |
+
"empty_samples": 0,
|
| 6 |
+
"acc": 3.3,
|
| 7 |
+
"pass_acc": 6.7,
|
| 8 |
+
"pass@k": {
|
| 9 |
+
"1": 3.3,
|
| 10 |
+
"2": 5.0,
|
| 11 |
+
"4": 6.7
|
| 12 |
+
},
|
| 13 |
+
"time_use_in_second": 164.7588677406311,
|
| 14 |
+
"time_use_in_minite": "2:44"
|
| 15 |
+
}
|
eval_results_avg4/global_step_50/amc23/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
eval_results_avg4/global_step_50/amc23/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"num_samples": 40,
|
| 3 |
+
"num_scores": 160,
|
| 4 |
+
"timeout_samples": 0,
|
| 5 |
+
"empty_samples": 0,
|
| 6 |
+
"acc": 38.1,
|
| 7 |
+
"pass_acc": 57.5,
|
| 8 |
+
"pass@k": {
|
| 9 |
+
"1": 38.1,
|
| 10 |
+
"2": 46.7,
|
| 11 |
+
"4": 57.5
|
| 12 |
+
},
|
| 13 |
+
"time_use_in_second": 181.3206844329834,
|
| 14 |
+
"time_use_in_minite": "3:01"
|
| 15 |
+
}
|
eval_results_avg4/global_step_60/aime24/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
eval_results_avg4/global_step_60/aime24/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"num_samples": 30,
|
| 3 |
+
"num_scores": 120,
|
| 4 |
+
"timeout_samples": 0,
|
| 5 |
+
"empty_samples": 0,
|
| 6 |
+
"acc": 7.5,
|
| 7 |
+
"pass_acc": 13.3,
|
| 8 |
+
"pass@k": {
|
| 9 |
+
"1": 7.5,
|
| 10 |
+
"2": 10.6,
|
| 11 |
+
"4": 13.3
|
| 12 |
+
},
|
| 13 |
+
"time_use_in_second": 171.7105691432953,
|
| 14 |
+
"time_use_in_minite": "2:51"
|
| 15 |
+
}
|
eval_results_avg4/global_step_60/aime25/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
eval_results_avg4/global_step_60/aime25/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"num_samples": 30,
|
| 3 |
+
"num_scores": 120,
|
| 4 |
+
"timeout_samples": 0,
|
| 5 |
+
"empty_samples": 0,
|
| 6 |
+
"acc": 2.5,
|
| 7 |
+
"pass_acc": 6.7,
|
| 8 |
+
"pass@k": {
|
| 9 |
+
"1": 2.5,
|
| 10 |
+
"2": 4.4,
|
| 11 |
+
"4": 6.7
|
| 12 |
+
},
|
| 13 |
+
"time_use_in_second": 187.81442284584045,
|
| 14 |
+
"time_use_in_minite": "3:07"
|
| 15 |
+
}
|
eval_results_avg4/global_step_60/amc23/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
eval_results_avg4/global_step_60/amc23/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"num_samples": 40,
|
| 3 |
+
"num_scores": 160,
|
| 4 |
+
"timeout_samples": 0,
|
| 5 |
+
"empty_samples": 0,
|
| 6 |
+
"acc": 36.9,
|
| 7 |
+
"pass_acc": 57.5,
|
| 8 |
+
"pass@k": {
|
| 9 |
+
"1": 36.9,
|
| 10 |
+
"2": 47.9,
|
| 11 |
+
"4": 57.5
|
| 12 |
+
},
|
| 13 |
+
"time_use_in_second": 174.99398565292358,
|
| 14 |
+
"time_use_in_minite": "2:54"
|
| 15 |
+
}
|
eval_results_avg4/global_step_70/aime24/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
eval_results_avg4/global_step_70/aime24/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"num_samples": 30,
|
| 3 |
+
"num_scores": 120,
|
| 4 |
+
"timeout_samples": 0,
|
| 5 |
+
"empty_samples": 0,
|
| 6 |
+
"acc": 9.2,
|
| 7 |
+
"pass_acc": 16.7,
|
| 8 |
+
"pass@k": {
|
| 9 |
+
"1": 9.2,
|
| 10 |
+
"2": 13.3,
|
| 11 |
+
"4": 16.7
|
| 12 |
+
},
|
| 13 |
+
"time_use_in_second": 190.03795075416565,
|
| 14 |
+
"time_use_in_minite": "3:10"
|
| 15 |
+
}
|
eval_results_avg4/global_step_70/aime25/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
eval_results_avg4/global_step_70/aime25/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"num_samples": 30,
|
| 3 |
+
"num_scores": 120,
|
| 4 |
+
"timeout_samples": 1,
|
| 5 |
+
"empty_samples": 0,
|
| 6 |
+
"acc": 4.2,
|
| 7 |
+
"pass_acc": 13.3,
|
| 8 |
+
"pass@k": {
|
| 9 |
+
"1": 4.2,
|
| 10 |
+
"2": 7.8,
|
| 11 |
+
"4": 13.3
|
| 12 |
+
},
|
| 13 |
+
"time_use_in_second": 174.40136766433716,
|
| 14 |
+
"time_use_in_minite": "2:54"
|
| 15 |
+
}
|
eval_results_avg4/global_step_70/amc23/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
eval_results_avg4/global_step_70/amc23/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"num_samples": 40,
|
| 3 |
+
"num_scores": 160,
|
| 4 |
+
"timeout_samples": 0,
|
| 5 |
+
"empty_samples": 0,
|
| 6 |
+
"acc": 38.8,
|
| 7 |
+
"pass_acc": 57.5,
|
| 8 |
+
"pass@k": {
|
| 9 |
+
"1": 38.8,
|
| 10 |
+
"2": 50.0,
|
| 11 |
+
"4": 57.5
|
| 12 |
+
},
|
| 13 |
+
"time_use_in_second": 153.37841844558716,
|
| 14 |
+
"time_use_in_minite": "2:33"
|
| 15 |
+
}
|
eval_results_avg4/global_step_80/aime24/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
eval_results_avg4/global_step_80/aime24/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"num_samples": 30,
|
| 3 |
+
"num_scores": 120,
|
| 4 |
+
"timeout_samples": 0,
|
| 5 |
+
"empty_samples": 0,
|
| 6 |
+
"acc": 4.2,
|
| 7 |
+
"pass_acc": 6.7,
|
| 8 |
+
"pass@k": {
|
| 9 |
+
"1": 4.2,
|
| 10 |
+
"2": 5.0,
|
| 11 |
+
"4": 6.7
|
| 12 |
+
},
|
| 13 |
+
"time_use_in_second": 185.43139123916626,
|
| 14 |
+
"time_use_in_minite": "3:05"
|
| 15 |
+
}
|
eval_results_avg4/global_step_80/aime25/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
eval_results_avg4/global_step_80/aime25/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"num_samples": 30,
|
| 3 |
+
"num_scores": 120,
|
| 4 |
+
"timeout_samples": 1,
|
| 5 |
+
"empty_samples": 0,
|
| 6 |
+
"acc": 2.5,
|
| 7 |
+
"pass_acc": 6.7,
|
| 8 |
+
"pass@k": {
|
| 9 |
+
"1": 2.5,
|
| 10 |
+
"2": 4.4,
|
| 11 |
+
"4": 6.7
|
| 12 |
+
},
|
| 13 |
+
"time_use_in_second": 169.12618327140808,
|
| 14 |
+
"time_use_in_minite": "2:49"
|
| 15 |
+
}
|
eval_results_avg4/global_step_80/amc23/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
eval_results_avg4/global_step_80/amc23/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"num_samples": 40,
|
| 3 |
+
"num_scores": 160,
|
| 4 |
+
"timeout_samples": 0,
|
| 5 |
+
"empty_samples": 0,
|
| 6 |
+
"acc": 36.2,
|
| 7 |
+
"pass_acc": 60.0,
|
| 8 |
+
"pass@k": {
|
| 9 |
+
"1": 36.2,
|
| 10 |
+
"2": 47.5,
|
| 11 |
+
"4": 60.0
|
| 12 |
+
},
|
| 13 |
+
"time_use_in_second": 168.92390275001526,
|
| 14 |
+
"time_use_in_minite": "2:48"
|
| 15 |
+
}
|
eval_results_avg4/global_step_90/aime24/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
eval_results_avg4/global_step_90/aime24/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"num_samples": 30,
|
| 3 |
+
"num_scores": 120,
|
| 4 |
+
"timeout_samples": 0,
|
| 5 |
+
"empty_samples": 0,
|
| 6 |
+
"acc": 5.8,
|
| 7 |
+
"pass_acc": 13.3,
|
| 8 |
+
"pass@k": {
|
| 9 |
+
"1": 5.8,
|
| 10 |
+
"2": 9.4,
|
| 11 |
+
"4": 13.3
|
| 12 |
+
},
|
| 13 |
+
"time_use_in_second": 177.2330482006073,
|
| 14 |
+
"time_use_in_minite": "2:57"
|
| 15 |
+
}
|
eval_results_avg4/global_step_90/aime25/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|