Upload harvest.log with huggingface_hub
Browse files- harvest.log +72 -0
harvest.log
ADDED
|
@@ -0,0 +1,72 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
[harvest] split=verified loading task metadata ...
|
| 2 |
+
[harvest] 500 task entries in 2.1s
|
| 3 |
+
[harvest] harvesting 5 submissions: ['20240620_sweagent_claude3.5sonnet', '20241022_tools_claude-3-5-sonnet-updated', '20241028_agentless-1.5_gpt4o', '20241029_OpenHands-CodeAct-2.1-sonnet-20241022', '20250405_amazon-q-developer-agent-20250405-dev']
|
| 4 |
+
[harvest-s3] listing verified/20240620_sweagent_claude3.5sonnet/logs/ ...
|
| 5 |
+
[harvest-s3] 489 instance dirs
|
| 6 |
+
[harvest-s3] 50/489 (16.5/s, kept=50)
|
| 7 |
+
[harvest-s3] 100/489 (18.7/s, kept=100)
|
| 8 |
+
[harvest-s3] 150/489 (19.6/s, kept=149)
|
| 9 |
+
[harvest-s3] 200/489 (18.4/s, kept=198)
|
| 10 |
+
[harvest-s3] 250/489 (23.5/s, kept=248)
|
| 11 |
+
[harvest-s3] 300/489 (22.6/s, kept=297)
|
| 12 |
+
[harvest-s3] 350/489 (21.7/s, kept=347)
|
| 13 |
+
[harvest-s3] 400/489 (22.6/s, kept=396)
|
| 14 |
+
[harvest-s3] 450/489 (22.4/s, kept=446)
|
| 15 |
+
[harvest-s3] 20240620_sweagent_claude3.5sonnet: kept 485 (resolved=168, rate=34.6%)
|
| 16 |
+
[harvest-s3] listing verified/20241022_tools_claude-3-5-sonnet-updated/logs/ ...
|
| 17 |
+
[harvest-s3] 486 instance dirs
|
| 18 |
+
[harvest-s3] 50/486 (15.7/s, kept=50)
|
| 19 |
+
[harvest-s3] 100/486 (17.6/s, kept=100)
|
| 20 |
+
[harvest-s3] 150/486 (18.0/s, kept=150)
|
| 21 |
+
[harvest-s3] 200/486 (17.7/s, kept=200)
|
| 22 |
+
[harvest-s3] 250/486 (17.9/s, kept=250)
|
| 23 |
+
[harvest-s3] 300/486 (20.8/s, kept=299)
|
| 24 |
+
[harvest-s3] 350/486 (20.8/s, kept=349)
|
| 25 |
+
[harvest-s3] 400/486 (19.2/s, kept=397)
|
| 26 |
+
[harvest-s3] 450/486 (20.1/s, kept=447)
|
| 27 |
+
[harvest-s3] 20241022_tools_claude-3-5-sonnet-updated: kept 483 (resolved=245, rate=50.7%)
|
| 28 |
+
[harvest-s3] listing verified/20241028_agentless-1.5_gpt4o/logs/ ...
|
| 29 |
+
[harvest-s3] 496 instance dirs
|
| 30 |
+
[harvest-s3] 50/496 (16.2/s, kept=50)
|
| 31 |
+
[harvest-s3] 100/496 (17.1/s, kept=100)
|
| 32 |
+
[harvest-s3] 150/496 (16.7/s, kept=150)
|
| 33 |
+
[harvest-s3] 200/496 (18.6/s, kept=200)
|
| 34 |
+
[harvest-s3] 250/496 (18.9/s, kept=250)
|
| 35 |
+
[harvest-s3] 300/496 (18.5/s, kept=300)
|
| 36 |
+
[harvest-s3] 350/496 (18.1/s, kept=350)
|
| 37 |
+
[harvest-s3] 400/496 (21.2/s, kept=400)
|
| 38 |
+
[harvest-s3] 450/496 (20.9/s, kept=449)
|
| 39 |
+
[harvest-s3] 20241028_agentless-1.5_gpt4o: kept 495 (resolved=194, rate=39.2%)
|
| 40 |
+
[harvest-s3] listing verified/20241029_OpenHands-CodeAct-2.1-sonnet-20241022/logs/ ...
|
| 41 |
+
[harvest-s3] 494 instance dirs
|
| 42 |
+
[harvest-s3] 50/494 (15.0/s, kept=50)
|
| 43 |
+
[harvest-s3] 100/494 (15.3/s, kept=100)
|
| 44 |
+
[harvest-s3] 150/494 (18.0/s, kept=149)
|
| 45 |
+
[harvest-s3] 200/494 (18.6/s, kept=199)
|
| 46 |
+
[harvest-s3] 250/494 (18.5/s, kept=249)
|
| 47 |
+
[harvest-s3] 300/494 (18.0/s, kept=299)
|
| 48 |
+
[harvest-s3] 350/494 (17.6/s, kept=349)
|
| 49 |
+
[harvest-s3] 400/494 (19.4/s, kept=399)
|
| 50 |
+
[harvest-s3] 450/494 (19.8/s, kept=449)
|
| 51 |
+
[harvest-s3] 20241029_OpenHands-CodeAct-2.1-sonnet-20241022: kept 493 (resolved=265, rate=53.8%)
|
| 52 |
+
[harvest-s3] listing verified/20250405_amazon-q-developer-agent-20250405-dev/logs/ ...
|
| 53 |
+
[harvest-s3] 500 instance dirs
|
| 54 |
+
[harvest-s3] 50/500 (11.8/s, kept=50)
|
| 55 |
+
[harvest-s3] 100/500 (17.8/s, kept=100)
|
| 56 |
+
[harvest-s3] 150/500 (18.4/s, kept=150)
|
| 57 |
+
[harvest-s3] 200/500 (18.8/s, kept=200)
|
| 58 |
+
[harvest-s3] 250/500 (19.2/s, kept=250)
|
| 59 |
+
[harvest-s3] 300/500 (18.7/s, kept=300)
|
| 60 |
+
[harvest-s3] 350/500 (18.4/s, kept=350)
|
| 61 |
+
[harvest-s3] 400/500 (18.8/s, kept=400)
|
| 62 |
+
[harvest-s3] 450/500 (19.0/s, kept=450)
|
| 63 |
+
[harvest-s3] 500/500 (20.7/s, kept=500)
|
| 64 |
+
[harvest-s3] 20250405_amazon-q-developer-agent-20250405-dev: kept 500 (resolved=330, rate=66.0%)
|
| 65 |
+
|
| 66 |
+
[harvest] wrote 2456 trajs → outputs/traj_real/specs.jsonl
|
| 67 |
+
[harvest] resolved overall: 1202/2456 (48.9%)
|
| 68 |
+
20240620_sweagent_claude3.5sonnet n= 485 resolved= 168 rate=34.6%
|
| 69 |
+
20241022_tools_claude-3-5-sonnet-updated n= 483 resolved= 245 rate=50.7%
|
| 70 |
+
20241028_agentless-1.5_gpt4o n= 495 resolved= 194 rate=39.2%
|
| 71 |
+
20241029_OpenHands-CodeAct-2.1-sonnet-20241022 n= 493 resolved= 265 rate=53.8%
|
| 72 |
+
20250405_amazon-q-developer-agent-20250405-dev n= 500 resolved= 330 rate=66.0%
|