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_90/mmlu_stem/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl +0 -0
- eval_results_avg4/global_step_10/aime24/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/aime25/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_100/amc23/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json +15 -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/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_10/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_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/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_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_100/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": 55.0,
|
| 8 |
+
"pass@k": {
|
| 9 |
+
"1": 35.0,
|
| 10 |
+
"2": 46.7,
|
| 11 |
+
"4": 55.0
|
| 12 |
+
},
|
| 13 |
+
"time_use_in_second": 183.80354595184326,
|
| 14 |
+
"time_use_in_minite": "3:03"
|
| 15 |
+
}
|
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": 5.0,
|
| 7 |
+
"pass_acc": 13.3,
|
| 8 |
+
"pass@k": {
|
| 9 |
+
"1": 5.0,
|
| 10 |
+
"2": 8.9,
|
| 11 |
+
"4": 13.3
|
| 12 |
+
},
|
| 13 |
+
"time_use_in_second": 183.42364764213562,
|
| 14 |
+
"time_use_in_minite": "3:03"
|
| 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": 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": 191.82226300239563,
|
| 14 |
+
"time_use_in_minite": "3:11"
|
| 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": 28.7,
|
| 7 |
+
"pass_acc": 50.0,
|
| 8 |
+
"pass@k": {
|
| 9 |
+
"1": 28.7,
|
| 10 |
+
"2": 39.2,
|
| 11 |
+
"4": 50.0
|
| 12 |
+
},
|
| 13 |
+
"time_use_in_second": 182.40337824821472,
|
| 14 |
+
"time_use_in_minite": "3:02"
|
| 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": 4.2,
|
| 7 |
+
"pass_acc": 10.0,
|
| 8 |
+
"pass@k": {
|
| 9 |
+
"1": 4.2,
|
| 10 |
+
"2": 7.2,
|
| 11 |
+
"4": 10.0
|
| 12 |
+
},
|
| 13 |
+
"time_use_in_second": 188.02974700927734,
|
| 14 |
+
"time_use_in_minite": "3:08"
|
| 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": 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": 176.24369168281555,
|
| 14 |
+
"time_use_in_minite": "2:56"
|
| 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": 31.2,
|
| 7 |
+
"pass_acc": 52.5,
|
| 8 |
+
"pass@k": {
|
| 9 |
+
"1": 31.2,
|
| 10 |
+
"2": 40.8,
|
| 11 |
+
"4": 52.5
|
| 12 |
+
},
|
| 13 |
+
"time_use_in_second": 181.08854174613953,
|
| 14 |
+
"time_use_in_minite": "3:01"
|
| 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": 7.5,
|
| 7 |
+
"pass_acc": 13.3,
|
| 8 |
+
"pass@k": {
|
| 9 |
+
"1": 7.5,
|
| 10 |
+
"2": 11.1,
|
| 11 |
+
"4": 13.3
|
| 12 |
+
},
|
| 13 |
+
"time_use_in_second": 188.8461208343506,
|
| 14 |
+
"time_use_in_minite": "3:08"
|
| 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": 5.8,
|
| 7 |
+
"pass_acc": 16.7,
|
| 8 |
+
"pass@k": {
|
| 9 |
+
"1": 5.8,
|
| 10 |
+
"2": 10.0,
|
| 11 |
+
"4": 16.7
|
| 12 |
+
},
|
| 13 |
+
"time_use_in_second": 182.82907247543335,
|
| 14 |
+
"time_use_in_minite": "3:02"
|
| 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": 0,
|
| 5 |
+
"empty_samples": 0,
|
| 6 |
+
"acc": 35.0,
|
| 7 |
+
"pass_acc": 57.5,
|
| 8 |
+
"pass@k": {
|
| 9 |
+
"1": 35.0,
|
| 10 |
+
"2": 46.7,
|
| 11 |
+
"4": 57.5
|
| 12 |
+
},
|
| 13 |
+
"time_use_in_second": 175.68424129486084,
|
| 14 |
+
"time_use_in_minite": "2:55"
|
| 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": 5.8,
|
| 7 |
+
"pass_acc": 16.7,
|
| 8 |
+
"pass@k": {
|
| 9 |
+
"1": 5.8,
|
| 10 |
+
"2": 10.6,
|
| 11 |
+
"4": 16.7
|
| 12 |
+
},
|
| 13 |
+
"time_use_in_second": 201.2400050163269,
|
| 14 |
+
"time_use_in_minite": "3:21"
|
| 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": 4.2,
|
| 7 |
+
"pass_acc": 10.0,
|
| 8 |
+
"pass@k": {
|
| 9 |
+
"1": 4.2,
|
| 10 |
+
"2": 6.7,
|
| 11 |
+
"4": 10.0
|
| 12 |
+
},
|
| 13 |
+
"time_use_in_second": 192.06621289253235,
|
| 14 |
+
"time_use_in_minite": "3:12"
|
| 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": 35.0,
|
| 7 |
+
"pass_acc": 57.5,
|
| 8 |
+
"pass@k": {
|
| 9 |
+
"1": 35.0,
|
| 10 |
+
"2": 45.4,
|
| 11 |
+
"4": 57.5
|
| 12 |
+
},
|
| 13 |
+
"time_use_in_second": 166.2230703830719,
|
| 14 |
+
"time_use_in_minite": "2:46"
|
| 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": 5.0,
|
| 7 |
+
"pass_acc": 10.0,
|
| 8 |
+
"pass@k": {
|
| 9 |
+
"1": 5.0,
|
| 10 |
+
"2": 7.8,
|
| 11 |
+
"4": 10.0
|
| 12 |
+
},
|
| 13 |
+
"time_use_in_second": 236.69900965690613,
|
| 14 |
+
"time_use_in_minite": "3:56"
|
| 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": 1.7,
|
| 7 |
+
"pass_acc": 6.7,
|
| 8 |
+
"pass@k": {
|
| 9 |
+
"1": 1.7,
|
| 10 |
+
"2": 3.3,
|
| 11 |
+
"4": 6.7
|
| 12 |
+
},
|
| 13 |
+
"time_use_in_second": 165.71282768249512,
|
| 14 |
+
"time_use_in_minite": "2:45"
|
| 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": 37.5,
|
| 7 |
+
"pass_acc": 57.5,
|
| 8 |
+
"pass@k": {
|
| 9 |
+
"1": 37.5,
|
| 10 |
+
"2": 47.5,
|
| 11 |
+
"4": 57.5
|
| 12 |
+
},
|
| 13 |
+
"time_use_in_second": 179.17511653900146,
|
| 14 |
+
"time_use_in_minite": "2:59"
|
| 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": 5.8,
|
| 7 |
+
"pass_acc": 16.7,
|
| 8 |
+
"pass@k": {
|
| 9 |
+
"1": 5.8,
|
| 10 |
+
"2": 10.0,
|
| 11 |
+
"4": 16.7
|
| 12 |
+
},
|
| 13 |
+
"time_use_in_second": 196.40622425079346,
|
| 14 |
+
"time_use_in_minite": "3:16"
|
| 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": 0,
|
| 5 |
+
"empty_samples": 0,
|
| 6 |
+
"acc": 6.7,
|
| 7 |
+
"pass_acc": 20.0,
|
| 8 |
+
"pass@k": {
|
| 9 |
+
"1": 6.7,
|
| 10 |
+
"2": 11.7,
|
| 11 |
+
"4": 20.0
|
| 12 |
+
},
|
| 13 |
+
"time_use_in_second": 171.30115938186646,
|
| 14 |
+
"time_use_in_minite": "2:51"
|
| 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": 35.0,
|
| 7 |
+
"pass_acc": 60.0,
|
| 8 |
+
"pass@k": {
|
| 9 |
+
"1": 35.0,
|
| 10 |
+
"2": 47.1,
|
| 11 |
+
"4": 60.0
|
| 12 |
+
},
|
| 13 |
+
"time_use_in_second": 177.5497224330902,
|
| 14 |
+
"time_use_in_minite": "2:57"
|
| 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": 7.5,
|
| 7 |
+
"pass_acc": 16.7,
|
| 8 |
+
"pass@k": {
|
| 9 |
+
"1": 7.5,
|
| 10 |
+
"2": 12.2,
|
| 11 |
+
"4": 16.7
|
| 12 |
+
},
|
| 13 |
+
"time_use_in_second": 185.17819023132324,
|
| 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": 0,
|
| 5 |
+
"empty_samples": 0,
|
| 6 |
+
"acc": 1.7,
|
| 7 |
+
"pass_acc": 3.3,
|
| 8 |
+
"pass@k": {
|
| 9 |
+
"1": 1.7,
|
| 10 |
+
"2": 2.8,
|
| 11 |
+
"4": 3.3
|
| 12 |
+
},
|
| 13 |
+
"time_use_in_second": 170.97129940986633,
|
| 14 |
+
"time_use_in_minite": "2:50"
|
| 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": 39.4,
|
| 7 |
+
"pass_acc": 57.5,
|
| 8 |
+
"pass@k": {
|
| 9 |
+
"1": 39.4,
|
| 10 |
+
"2": 50.8,
|
| 11 |
+
"4": 57.5
|
| 12 |
+
},
|
| 13 |
+
"time_use_in_second": 165.47831511497498,
|
| 14 |
+
"time_use_in_minite": "2:45"
|
| 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": 6.7,
|
| 7 |
+
"pass_acc": 13.3,
|
| 8 |
+
"pass@k": {
|
| 9 |
+
"1": 6.7,
|
| 10 |
+
"2": 9.4,
|
| 11 |
+
"4": 13.3
|
| 12 |
+
},
|
| 13 |
+
"time_use_in_second": 207.00103855133057,
|
| 14 |
+
"time_use_in_minite": "3:27"
|
| 15 |
+
}
|