Hugging Face's logo

Spaces:
SaylorTwift
/
long_horizon_execution
Running

App Files Community
SaylorTwift HF Staff commited on
Commit
2a427ee
·
verified ·
1 Parent(s): efb8ab4

Upload folder using huggingface_hub

Browse files
Files changed (22) hide show
  1. .gitattributes +10 -0
  2. assets/favicon.svg +4 -0
  3. assets/index.css +0 -0
  4. assets/index.js +0 -0
  5. index.html +26 -17
  6. logs/2025-11-20T15-33-02+01-00_long-horizon-execution-1024_hFHo95vmjgTchZGoSC4pPM.eval +0 -0
  7. logs/2025-11-20T15-33-02+01-00_long-horizon-execution-16384_MSnnENqGY9aXtE549VWfYY.eval +3 -0
  8. logs/2025-11-20T15-33-02+01-00_long-horizon-execution-2048_g4ytLJepzwxhnKAFsCRkcZ.eval +0 -0
  9. logs/2025-11-20T15-33-02+01-00_long-horizon-execution-32768_Vh2nnbhMtb7hpmk8zMRe7R.eval +3 -0
  10. logs/2025-11-20T15-33-02+01-00_long-horizon-execution-4096_6KngaNoJcesYZ3n4wHJtgr.eval +0 -0
  11. logs/2025-11-20T15-33-02+01-00_long-horizon-execution-65536_MKNbbyxFi2SboYmzcZJg7i.eval +3 -0
  12. logs/2025-11-20T15-33-02+01-00_long-horizon-execution-8192_QZ55FqjvLpVzDPfU4CgkdJ.eval +0 -0
  13. logs/2025-11-20T15-36-58+01-00_long-horizon-execution-1024_Q8FPP67tZkwjmyx7MrkPdK.eval +3 -0
  14. logs/2025-11-20T15-36-58+01-00_long-horizon-execution-16384_mwMLFEBj8eYRiiYPvyD7Xd.eval +3 -0
  15. logs/2025-11-20T15-36-58+01-00_long-horizon-execution-2048_Uvr76zF8hkt4PgnsUPDWDS.eval +3 -0
  16. logs/2025-11-20T15-36-58+01-00_long-horizon-execution-32768_FZ9Z2AZfBoMdRpzJ3Rt4Sx.eval +3 -0
  17. logs/2025-11-20T15-36-58+01-00_long-horizon-execution-4096_W3QMv8KVUf2BLSRZArAxzd.eval +3 -0
  18. logs/2025-11-20T15-36-58+01-00_long-horizon-execution-65536_GmtEQzBe5eEKggR8HdoNoV.eval +3 -0
  19. logs/2025-11-20T15-36-59+01-00_long-horizon-execution-8192_Gm6T2GREQg6indZWYr7qUY.eval +3 -0
  20. logs/eval-set.json +89 -0
  21. logs/listing.json +240 -0
  22. robots.txt +2 -0
.gitattributes CHANGED
@@ -33,3 +33,13 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ logs/2025-11-20T15-33-02+01-00_long-horizon-execution-16384_MSnnENqGY9aXtE549VWfYY.eval filter=lfs diff=lfs merge=lfs -text
37
+ logs/2025-11-20T15-33-02+01-00_long-horizon-execution-32768_Vh2nnbhMtb7hpmk8zMRe7R.eval filter=lfs diff=lfs merge=lfs -text
38
+ logs/2025-11-20T15-33-02+01-00_long-horizon-execution-65536_MKNbbyxFi2SboYmzcZJg7i.eval filter=lfs diff=lfs merge=lfs -text
39
+ logs/2025-11-20T15-36-58+01-00_long-horizon-execution-1024_Q8FPP67tZkwjmyx7MrkPdK.eval filter=lfs diff=lfs merge=lfs -text
40
+ logs/2025-11-20T15-36-58+01-00_long-horizon-execution-16384_mwMLFEBj8eYRiiYPvyD7Xd.eval filter=lfs diff=lfs merge=lfs -text
41
+ logs/2025-11-20T15-36-58+01-00_long-horizon-execution-2048_Uvr76zF8hkt4PgnsUPDWDS.eval filter=lfs diff=lfs merge=lfs -text
42
+ logs/2025-11-20T15-36-58+01-00_long-horizon-execution-32768_FZ9Z2AZfBoMdRpzJ3Rt4Sx.eval filter=lfs diff=lfs merge=lfs -text
43
+ logs/2025-11-20T15-36-58+01-00_long-horizon-execution-4096_W3QMv8KVUf2BLSRZArAxzd.eval filter=lfs diff=lfs merge=lfs -text
44
+ logs/2025-11-20T15-36-58+01-00_long-horizon-execution-65536_GmtEQzBe5eEKggR8HdoNoV.eval filter=lfs diff=lfs merge=lfs -text
45
+ logs/2025-11-20T15-36-59+01-00_long-horizon-execution-8192_Gm6T2GREQg6indZWYr7qUY.eval filter=lfs diff=lfs merge=lfs -text
assets/favicon.svg ADDED
assets/index.css ADDED
The diff for this file is too large to render. See raw diff
 
assets/index.js ADDED
The diff for this file is too large to render. See raw diff
 
index.html CHANGED
@@ -1,19 +1,28 @@
1
  <!doctype html>
2
- <html>
3
- <head>
4
- <meta charset="utf-8" />
5
- <meta name="viewport" content="width=device-width" />
6
- <title>My static Space</title>
7
- <link rel="stylesheet" href="style.css" />
8
- </head>
9
- <body>
10
- <div class="card">
11
- <h1>Welcome to your static Space!</h1>
12
- <p>You can modify this app directly by editing <i>index.html</i> in the Files and versions tab.</p>
13
- <p>
14
- Also don't forget to check the
15
- <a href="https://huggingface.co/docs/hub/spaces" target="_blank">Spaces documentation</a>.
16
- </p>
17
- </div>
18
- </body>
 
 
 
 
 
 
 
 
 
19
  </html>
 
1
  <!doctype html>
2
+ <html lang="en" data-bs-theme="light">
3
+ <head>
4
+ <meta charset="utf-8" />
5
+ <meta name="viewport" content="width=device-width, initial-scale=1" />
6
+ <title>Inspect View</title>
7
+ <link rel="icon" href="./assets/favicon.svg" />
8
+
9
+ <script>
10
+ // Forward the theme (dark or light) onto the root html element
11
+ // this parameter will tend to appear when the view is hosted within
12
+ // an iframe (e.g. in vscode)
13
+ const urlParams = new URLSearchParams(window.location.search);
14
+ const theme = urlParams.get("inspectLogviewThemeCategory");
15
+ if (theme) {
16
+ document.documentElement.setAttribute("data-text-highlight", theme);
17
+ document.documentElement.setAttribute("data-bs-theme", theme);
18
+ }
19
+ </script>
20
+ <script type="module" crossorigin src="./assets/index.js"></script>
21
+ <link rel="stylesheet" crossorigin href="./assets/index.css">
22
+ <script id="log_dir_context" type="application/json">{"log_dir": "logs"}</script>
23
+ </head>
24
+
25
+ <body style="min-width: 450px">
26
+ <div id="app"></div>
27
+ </body>
28
  </html>
logs/2025-11-20T15-33-02+01-00_long-horizon-execution-1024_hFHo95vmjgTchZGoSC4pPM.eval ADDED
Binary file (11.8 kB). View file
 
logs/2025-11-20T15-33-02+01-00_long-horizon-execution-16384_MSnnENqGY9aXtE549VWfYY.eval ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d993b8cb3f69e087207e6a2ee200feed331c5264aecc73408fdc1a6c6553fbb2
3
+ size 155875
logs/2025-11-20T15-33-02+01-00_long-horizon-execution-2048_g4ytLJepzwxhnKAFsCRkcZ.eval ADDED
Binary file (24.1 kB). View file
 
logs/2025-11-20T15-33-02+01-00_long-horizon-execution-32768_Vh2nnbhMtb7hpmk8zMRe7R.eval ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:766e3d3d230a60688beabbe84d2e31c94755be2374793a219b5ca972e0ca091d
3
+ size 297800
logs/2025-11-20T15-33-02+01-00_long-horizon-execution-4096_6KngaNoJcesYZ3n4wHJtgr.eval ADDED
Binary file (42.2 kB). View file
 
logs/2025-11-20T15-33-02+01-00_long-horizon-execution-65536_MKNbbyxFi2SboYmzcZJg7i.eval ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84eb2bd4edc9de53b4923423ef3950dfa3f8dfc0a56d4f6ec94f35f61a34f6d1
3
+ size 585935
logs/2025-11-20T15-33-02+01-00_long-horizon-execution-8192_QZ55FqjvLpVzDPfU4CgkdJ.eval ADDED
Binary file (79.2 kB). View file
 
logs/2025-11-20T15-36-58+01-00_long-horizon-execution-1024_Q8FPP67tZkwjmyx7MrkPdK.eval ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd22453901153ff4663decf2b2a1a76026efe104640707de96f783b8bf64fa4c
3
+ size 401102
logs/2025-11-20T15-36-58+01-00_long-horizon-execution-16384_mwMLFEBj8eYRiiYPvyD7Xd.eval ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1427fdee9378019c228b60c027d4c797fd0157a4dd663f2e666169d046653e5
3
+ size 7326345
logs/2025-11-20T15-36-58+01-00_long-horizon-execution-2048_Uvr76zF8hkt4PgnsUPDWDS.eval ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2164d26ffa1e034d397916f6fe5609da277160f9508618720b2dbf8486900821
3
+ size 1059036
logs/2025-11-20T15-36-58+01-00_long-horizon-execution-32768_FZ9Z2AZfBoMdRpzJ3Rt4Sx.eval ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dfdde29052452c4ecf0e0efb1152028f98a0e787e50b0a0c4b5d5313bfa011be
3
+ size 14786800
logs/2025-11-20T15-36-58+01-00_long-horizon-execution-4096_W3QMv8KVUf2BLSRZArAxzd.eval ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7444e5ce0a1cc3f07df57d0a8c7e1eea24dad4a5d585ee3ae7e196a96ba4a3a
3
+ size 2998143
logs/2025-11-20T15-36-58+01-00_long-horizon-execution-65536_GmtEQzBe5eEKggR8HdoNoV.eval ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7702513bc4d00cc4ec6d35bdd06e8880a2464ebdc8a987ad5a413e8c124a4434
3
+ size 28971699
logs/2025-11-20T15-36-59+01-00_long-horizon-execution-8192_Gm6T2GREQg6indZWYr7qUY.eval ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c0f52db4d30810b8ad3cef1a7895e58c6a733b21643d0e4eaa2c7039a995abe
3
+ size 4243349
logs/eval-set.json ADDED
@@ -0,0 +1,89 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "eval_set_id": "LRN27267EfNTtsRtExw2SW",
3
+ "tasks": [
4
+ {
5
+ "name": "long_horizon_execution:1024",
6
+ "task_id": "Q8FPP67tZkwjmyx7MrkPdK",
7
+ "task_args": {
8
+ "lighteval_task_config": "long_horizon_execution:1024",
9
+ "epochs": 1,
10
+ "epochs_reducer": null
11
+ },
12
+ "model": "hf-inference-providers/openai/gpt-oss-20b",
13
+ "model_args": {},
14
+ "sequence": 0
15
+ },
16
+ {
17
+ "name": "long_horizon_execution:16384",
18
+ "task_id": "mwMLFEBj8eYRiiYPvyD7Xd",
19
+ "task_args": {
20
+ "lighteval_task_config": "long_horizon_execution:16384",
21
+ "epochs": 1,
22
+ "epochs_reducer": null
23
+ },
24
+ "model": "hf-inference-providers/openai/gpt-oss-20b",
25
+ "model_args": {},
26
+ "sequence": 1
27
+ },
28
+ {
29
+ "name": "long_horizon_execution:2048",
30
+ "task_id": "Uvr76zF8hkt4PgnsUPDWDS",
31
+ "task_args": {
32
+ "lighteval_task_config": "long_horizon_execution:2048",
33
+ "epochs": 1,
34
+ "epochs_reducer": null
35
+ },
36
+ "model": "hf-inference-providers/openai/gpt-oss-20b",
37
+ "model_args": {},
38
+ "sequence": 2
39
+ },
40
+ {
41
+ "name": "long_horizon_execution:32768",
42
+ "task_id": "FZ9Z2AZfBoMdRpzJ3Rt4Sx",
43
+ "task_args": {
44
+ "lighteval_task_config": "long_horizon_execution:32768",
45
+ "epochs": 1,
46
+ "epochs_reducer": null
47
+ },
48
+ "model": "hf-inference-providers/openai/gpt-oss-20b",
49
+ "model_args": {},
50
+ "sequence": 3
51
+ },
52
+ {
53
+ "name": "long_horizon_execution:4096",
54
+ "task_id": "W3QMv8KVUf2BLSRZArAxzd",
55
+ "task_args": {
56
+ "lighteval_task_config": "long_horizon_execution:4096",
57
+ "epochs": 1,
58
+ "epochs_reducer": null
59
+ },
60
+ "model": "hf-inference-providers/openai/gpt-oss-20b",
61
+ "model_args": {},
62
+ "sequence": 4
63
+ },
64
+ {
65
+ "name": "long_horizon_execution:65536",
66
+ "task_id": "GmtEQzBe5eEKggR8HdoNoV",
67
+ "task_args": {
68
+ "lighteval_task_config": "long_horizon_execution:65536",
69
+ "epochs": 1,
70
+ "epochs_reducer": null
71
+ },
72
+ "model": "hf-inference-providers/openai/gpt-oss-20b",
73
+ "model_args": {},
74
+ "sequence": 5
75
+ },
76
+ {
77
+ "name": "long_horizon_execution:8192",
78
+ "task_id": "Gm6T2GREQg6indZWYr7qUY",
79
+ "task_args": {
80
+ "lighteval_task_config": "long_horizon_execution:8192",
81
+ "epochs": 1,
82
+ "epochs_reducer": null
83
+ },
84
+ "model": "hf-inference-providers/openai/gpt-oss-20b",
85
+ "model_args": {},
86
+ "sequence": 6
87
+ }
88
+ ]
89
+ }
logs/listing.json ADDED
@@ -0,0 +1,240 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "2025-11-20T15-36-59+01-00_long-horizon-execution-8192_Gm6T2GREQg6indZWYr7qUY.eval": {
3
+ "eval_id": "NA7cVCboUagosQMLCMyfpQ",
4
+ "run_id": "bpaANsnXqDLDYGsQaQY7As",
5
+ "task": "long_horizon_execution:8192",
6
+ "task_id": "Gm6T2GREQg6indZWYr7qUY",
7
+ "task_version": 0,
8
+ "version": 2,
9
+ "status": "success",
10
+ "model": "hf-inference-providers/openai/gpt-oss-20b",
11
+ "started_at": "2025-11-20T15:38:46+01:00",
12
+ "completed_at": "2025-11-20T15:44:01+01:00",
13
+ "primary_metric": {
14
+ "name": "accuracy",
15
+ "value": 0.01,
16
+ "params": {}
17
+ }
18
+ },
19
+ "2025-11-20T15-36-58+01-00_long-horizon-execution-4096_W3QMv8KVUf2BLSRZArAxzd.eval": {
20
+ "eval_id": "jJPdv4eRojLxynfw2MAedo",
21
+ "run_id": "bpaANsnXqDLDYGsQaQY7As",
22
+ "task": "long_horizon_execution:4096",
23
+ "task_id": "W3QMv8KVUf2BLSRZArAxzd",
24
+ "task_version": 0,
25
+ "version": 2,
26
+ "status": "success",
27
+ "model": "hf-inference-providers/openai/gpt-oss-20b",
28
+ "started_at": "2025-11-20T15:37:40+01:00",
29
+ "completed_at": "2025-11-20T15:42:05+01:00",
30
+ "primary_metric": {
31
+ "name": "accuracy",
32
+ "value": 0.84,
33
+ "params": {}
34
+ }
35
+ },
36
+ "2025-11-20T15-36-58+01-00_long-horizon-execution-65536_GmtEQzBe5eEKggR8HdoNoV.eval": {
37
+ "eval_id": "VhLNjTUfqn7yKq944iKk22",
38
+ "run_id": "bpaANsnXqDLDYGsQaQY7As",
39
+ "task": "long_horizon_execution:65536",
40
+ "task_id": "GmtEQzBe5eEKggR8HdoNoV",
41
+ "task_version": 0,
42
+ "version": 2,
43
+ "status": "success",
44
+ "model": "hf-inference-providers/openai/gpt-oss-20b",
45
+ "started_at": "2025-11-20T15:37:50+01:00",
46
+ "completed_at": "2025-11-20T15:40:03+01:00",
47
+ "primary_metric": {
48
+ "name": "accuracy",
49
+ "value": 0.0,
50
+ "params": {}
51
+ }
52
+ },
53
+ "2025-11-20T15-36-58+01-00_long-horizon-execution-2048_Uvr76zF8hkt4PgnsUPDWDS.eval": {
54
+ "eval_id": "UjKsVmVMSAm66eNny39LSK",
55
+ "run_id": "bpaANsnXqDLDYGsQaQY7As",
56
+ "task": "long_horizon_execution:2048",
57
+ "task_id": "Uvr76zF8hkt4PgnsUPDWDS",
58
+ "task_version": 0,
59
+ "version": 2,
60
+ "status": "success",
61
+ "model": "hf-inference-providers/openai/gpt-oss-20b",
62
+ "started_at": "2025-11-20T15:36:59+01:00",
63
+ "completed_at": "2025-11-20T15:39:10+01:00",
64
+ "primary_metric": {
65
+ "name": "accuracy",
66
+ "value": 1.0,
67
+ "params": {}
68
+ }
69
+ },
70
+ "2025-11-20T15-36-58+01-00_long-horizon-execution-32768_FZ9Z2AZfBoMdRpzJ3Rt4Sx.eval": {
71
+ "eval_id": "ad6DnHZEH9zkVdEAgJhwCP",
72
+ "run_id": "bpaANsnXqDLDYGsQaQY7As",
73
+ "task": "long_horizon_execution:32768",
74
+ "task_id": "FZ9Z2AZfBoMdRpzJ3Rt4Sx",
75
+ "task_version": 0,
76
+ "version": 2,
77
+ "status": "success",
78
+ "model": "hf-inference-providers/openai/gpt-oss-20b",
79
+ "started_at": "2025-11-20T15:36:59+01:00",
80
+ "completed_at": "2025-11-20T15:38:46+01:00",
81
+ "primary_metric": {
82
+ "name": "accuracy",
83
+ "value": 0.0,
84
+ "params": {}
85
+ }
86
+ },
87
+ "2025-11-20T15-36-58+01-00_long-horizon-execution-16384_mwMLFEBj8eYRiiYPvyD7Xd.eval": {
88
+ "eval_id": "QAVERTysNLU62kRvZQoAk5",
89
+ "run_id": "bpaANsnXqDLDYGsQaQY7As",
90
+ "task": "long_horizon_execution:16384",
91
+ "task_id": "mwMLFEBj8eYRiiYPvyD7Xd",
92
+ "task_version": 0,
93
+ "version": 2,
94
+ "status": "success",
95
+ "model": "hf-inference-providers/openai/gpt-oss-20b",
96
+ "started_at": "2025-11-20T15:36:59+01:00",
97
+ "completed_at": "2025-11-20T15:37:50+01:00",
98
+ "primary_metric": {
99
+ "name": "accuracy",
100
+ "value": 0.0,
101
+ "params": {}
102
+ }
103
+ },
104
+ "2025-11-20T15-36-58+01-00_long-horizon-execution-1024_Q8FPP67tZkwjmyx7MrkPdK.eval": {
105
+ "eval_id": "VTJ4tkhiXzyqpfyvDkqQbu",
106
+ "run_id": "bpaANsnXqDLDYGsQaQY7As",
107
+ "task": "long_horizon_execution:1024",
108
+ "task_id": "Q8FPP67tZkwjmyx7MrkPdK",
109
+ "task_version": 0,
110
+ "version": 2,
111
+ "status": "success",
112
+ "model": "hf-inference-providers/openai/gpt-oss-20b",
113
+ "started_at": "2025-11-20T15:36:59+01:00",
114
+ "completed_at": "2025-11-20T15:37:40+01:00",
115
+ "primary_metric": {
116
+ "name": "accuracy",
117
+ "value": 1.0,
118
+ "params": {}
119
+ }
120
+ },
121
+ "2025-11-20T15-33-02+01-00_long-horizon-execution-8192_QZ55FqjvLpVzDPfU4CgkdJ.eval": {
122
+ "eval_id": "XHSj88vvSCBdgLtCbsSZgQ",
123
+ "run_id": "GFRyNerPFXSvUcW5wjmccn",
124
+ "task": "long_horizon_execution:8192",
125
+ "task_id": "QZ55FqjvLpVzDPfU4CgkdJ",
126
+ "task_version": 0,
127
+ "version": 2,
128
+ "status": "success",
129
+ "model": "hf-inference-providers/openai/gpt-oss-20b",
130
+ "started_at": "2025-11-20T15:33:05+01:00",
131
+ "completed_at": "2025-11-20T15:33:19+01:00",
132
+ "primary_metric": {
133
+ "name": "accuracy",
134
+ "value": 0.0,
135
+ "params": {}
136
+ }
137
+ },
138
+ "2025-11-20T15-33-02+01-00_long-horizon-execution-4096_6KngaNoJcesYZ3n4wHJtgr.eval": {
139
+ "eval_id": "eghpYmgJXjVQzyUrJeqNrD",
140
+ "run_id": "GFRyNerPFXSvUcW5wjmccn",
141
+ "task": "long_horizon_execution:4096",
142
+ "task_id": "6KngaNoJcesYZ3n4wHJtgr",
143
+ "task_version": 0,
144
+ "version": 2,
145
+ "status": "success",
146
+ "model": "hf-inference-providers/openai/gpt-oss-20b",
147
+ "started_at": "2025-11-20T15:33:03+01:00",
148
+ "completed_at": "2025-11-20T15:33:19+01:00",
149
+ "primary_metric": {
150
+ "name": "accuracy",
151
+ "value": 0.0,
152
+ "params": {}
153
+ }
154
+ },
155
+ "2025-11-20T15-33-02+01-00_long-horizon-execution-16384_MSnnENqGY9aXtE549VWfYY.eval": {
156
+ "eval_id": "Cbm4Ms6j4DDm82JW6JhjoC",
157
+ "run_id": "GFRyNerPFXSvUcW5wjmccn",
158
+ "task": "long_horizon_execution:16384",
159
+ "task_id": "MSnnENqGY9aXtE549VWfYY",
160
+ "task_version": 0,
161
+ "version": 2,
162
+ "status": "success",
163
+ "model": "hf-inference-providers/openai/gpt-oss-20b",
164
+ "started_at": "2025-11-20T15:33:02+01:00",
165
+ "completed_at": "2025-11-20T15:33:10+01:00",
166
+ "primary_metric": {
167
+ "name": "accuracy",
168
+ "value": 0.0,
169
+ "params": {}
170
+ }
171
+ },
172
+ "2025-11-20T15-33-02+01-00_long-horizon-execution-65536_MKNbbyxFi2SboYmzcZJg7i.eval": {
173
+ "eval_id": "2HyufGWpesgASQDYAQWibj",
174
+ "run_id": "GFRyNerPFXSvUcW5wjmccn",
175
+ "task": "long_horizon_execution:65536",
176
+ "task_id": "MKNbbyxFi2SboYmzcZJg7i",
177
+ "task_version": 0,
178
+ "version": 2,
179
+ "status": "success",
180
+ "model": "hf-inference-providers/openai/gpt-oss-20b",
181
+ "started_at": "2025-11-20T15:33:03+01:00",
182
+ "completed_at": "2025-11-20T15:33:10+01:00",
183
+ "primary_metric": {
184
+ "name": "accuracy",
185
+ "value": 0.0,
186
+ "params": {}
187
+ }
188
+ },
189
+ "2025-11-20T15-33-02+01-00_long-horizon-execution-1024_hFHo95vmjgTchZGoSC4pPM.eval": {
190
+ "eval_id": "RGPNvdwwBVqBcb4gwPKdpN",
191
+ "run_id": "GFRyNerPFXSvUcW5wjmccn",
192
+ "task": "long_horizon_execution:1024",
193
+ "task_id": "hFHo95vmjgTchZGoSC4pPM",
194
+ "task_version": 0,
195
+ "version": 2,
196
+ "status": "success",
197
+ "model": "hf-inference-providers/openai/gpt-oss-20b",
198
+ "started_at": "2025-11-20T15:33:02+01:00",
199
+ "completed_at": "2025-11-20T15:33:05+01:00",
200
+ "primary_metric": {
201
+ "name": "accuracy",
202
+ "value": 1.0,
203
+ "params": {}
204
+ }
205
+ },
206
+ "2025-11-20T15-33-02+01-00_long-horizon-execution-32768_Vh2nnbhMtb7hpmk8zMRe7R.eval": {
207
+ "eval_id": "7MNDPdZ7F6phteuzwWGHbq",
208
+ "run_id": "GFRyNerPFXSvUcW5wjmccn",
209
+ "task": "long_horizon_execution:32768",
210
+ "task_id": "Vh2nnbhMtb7hpmk8zMRe7R",
211
+ "task_version": 0,
212
+ "version": 2,
213
+ "status": "success",
214
+ "model": "hf-inference-providers/openai/gpt-oss-20b",
215
+ "started_at": "2025-11-20T15:33:02+01:00",
216
+ "completed_at": "2025-11-20T15:33:03+01:00",
217
+ "primary_metric": {
218
+ "name": "accuracy",
219
+ "value": 0.0,
220
+ "params": {}
221
+ }
222
+ },
223
+ "2025-11-20T15-33-02+01-00_long-horizon-execution-2048_g4ytLJepzwxhnKAFsCRkcZ.eval": {
224
+ "eval_id": "d5GJrLaBTUyvhTWfuCn6Pb",
225
+ "run_id": "GFRyNerPFXSvUcW5wjmccn",
226
+ "task": "long_horizon_execution:2048",
227
+ "task_id": "g4ytLJepzwxhnKAFsCRkcZ",
228
+ "task_version": 0,
229
+ "version": 2,
230
+ "status": "success",
231
+ "model": "hf-inference-providers/openai/gpt-oss-20b",
232
+ "started_at": "2025-11-20T15:33:02+01:00",
233
+ "completed_at": "2025-11-20T15:33:03+01:00",
234
+ "primary_metric": {
235
+ "name": "accuracy",
236
+ "value": 0.5,
237
+ "params": {}
238
+ }
239
+ }
240
+ }
robots.txt ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ User-agent: *
2
+ Disallow: /