b1k_model / evaluation /per_instance.json
davidwdw's picture
Upload B1K model checkpoints, training recipes, and evaluation artifacts (part 8)
c556874 verified
Raw History Blame Contribute Delete
7.33 kB
[
{
"variant": "human",
"instance_id": 301,
"success": false,
"q_score": 0.0,
"steps": 3225
},
{
"variant": "human",
"instance_id": 302,
"success": false,
"q_score": 0.0,
"steps": 3225
},
{
"variant": "human",
"instance_id": 303,
"success": true,
"q_score": 1.0,
"steps": 1611
},
{
"variant": "human",
"instance_id": 304,
"success": true,
"q_score": 1.0,
"steps": 1118
},
{
"variant": "human",
"instance_id": 305,
"success": false,
"q_score": 0.0,
"steps": 3225
},
{
"variant": "human",
"instance_id": 306,
"success": false,
"q_score": 0.0,
"steps": 3225
},
{
"variant": "human",
"instance_id": 307,
"success": true,
"q_score": 1.0,
"steps": 1265
},
{
"variant": "human",
"instance_id": 308,
"success": true,
"q_score": 1.0,
"steps": 2112
},
{
"variant": "human",
"instance_id": 309,
"success": false,
"q_score": 0.0,
"steps": 3225
},
{
"variant": "human",
"instance_id": 310,
"success": false,
"q_score": 0.0,
"steps": 3225
},
{
"variant": "human",
"instance_id": 311,
"success": false,
"q_score": 0.0,
"steps": 3225
},
{
"variant": "human",
"instance_id": 312,
"success": true,
"q_score": 1.0,
"steps": 1825
},
{
"variant": "human",
"instance_id": 313,
"success": true,
"q_score": 1.0,
"steps": 1299
},
{
"variant": "human",
"instance_id": 314,
"success": false,
"q_score": 0.0,
"steps": 3225
},
{
"variant": "human",
"instance_id": 315,
"success": true,
"q_score": 1.0,
"steps": 1449
},
{
"variant": "human",
"instance_id": 316,
"success": false,
"q_score": 0.0,
"steps": 3225
},
{
"variant": "human",
"instance_id": 317,
"success": false,
"q_score": 0.0,
"steps": 3225
},
{
"variant": "human",
"instance_id": 318,
"success": false,
"q_score": 0.0,
"steps": 3225
},
{
"variant": "human",
"instance_id": 319,
"success": false,
"q_score": 0.0,
"steps": 3225
},
{
"variant": "human",
"instance_id": 320,
"success": true,
"q_score": 1.0,
"steps": 995
},
{
"variant": "codegen_success",
"instance_id": 301,
"success": false,
"q_score": 0.0,
"steps": 3225
},
{
"variant": "codegen_success",
"instance_id": 302,
"success": false,
"q_score": 0.0,
"steps": 3225
},
{
"variant": "codegen_success",
"instance_id": 303,
"success": false,
"q_score": 0.0,
"steps": 3225
},
{
"variant": "codegen_success",
"instance_id": 304,
"success": false,
"q_score": 0.0,
"steps": 3225
},
{
"variant": "codegen_success",
"instance_id": 305,
"success": false,
"q_score": 0.0,
"steps": 3225
},
{
"variant": "codegen_success",
"instance_id": 306,
"success": true,
"q_score": 1.0,
"steps": 486
},
{
"variant": "codegen_success",
"instance_id": 307,
"success": false,
"q_score": 0.0,
"steps": 3225
},
{
"variant": "codegen_success",
"instance_id": 308,
"success": false,
"q_score": 0.0,
"steps": 3225
},
{
"variant": "codegen_success",
"instance_id": 309,
"success": false,
"q_score": 0.0,
"steps": 3225
},
{
"variant": "codegen_success",
"instance_id": 310,
"success": false,
"q_score": 0.0,
"steps": 3225
},
{
"variant": "codegen_success",
"instance_id": 311,
"success": false,
"q_score": 0.0,
"steps": 3225
},
{
"variant": "codegen_success",
"instance_id": 312,
"success": false,
"q_score": 0.0,
"steps": 3225
},
{
"variant": "codegen_success",
"instance_id": 313,
"success": false,
"q_score": 0.0,
"steps": 3225
},
{
"variant": "codegen_success",
"instance_id": 314,
"success": false,
"q_score": 0.0,
"steps": 3225
},
{
"variant": "codegen_success",
"instance_id": 315,
"success": false,
"q_score": 0.0,
"steps": 3225
},
{
"variant": "codegen_success",
"instance_id": 316,
"success": false,
"q_score": 0.0,
"steps": 3225
},
{
"variant": "codegen_success",
"instance_id": 317,
"success": false,
"q_score": 0.0,
"steps": 3225
},
{
"variant": "codegen_success",
"instance_id": 318,
"success": false,
"q_score": 0.0,
"steps": 3225
},
{
"variant": "codegen_success",
"instance_id": 319,
"success": false,
"q_score": 0.0,
"steps": 3225
},
{
"variant": "codegen_success",
"instance_id": 320,
"success": false,
"q_score": 0.0,
"steps": 3225
},
{
"variant": "mix_h50_c50",
"instance_id": 301,
"success": false,
"q_score": 0.0,
"steps": 3225
},
{
"variant": "mix_h50_c50",
"instance_id": 302,
"success": false,
"q_score": 0.0,
"steps": 3225
},
{
"variant": "mix_h50_c50",
"instance_id": 303,
"success": false,
"q_score": 0.0,
"steps": 3225
},
{
"variant": "mix_h50_c50",
"instance_id": 304,
"success": false,
"q_score": 0.0,
"steps": 3225
},
{
"variant": "mix_h50_c50",
"instance_id": 305,
"success": false,
"q_score": 0.0,
"steps": 3225
},
{
"variant": "mix_h50_c50",
"instance_id": 306,
"success": false,
"q_score": 0.0,
"steps": 3225
},
{
"variant": "mix_h50_c50",
"instance_id": 307,
"success": false,
"q_score": 0.0,
"steps": 3225
},
{
"variant": "mix_h50_c50",
"instance_id": 308,
"success": false,
"q_score": 0.0,
"steps": 3225
},
{
"variant": "mix_h50_c50",
"instance_id": 309,
"success": false,
"q_score": 0.0,
"steps": 3225
},
{
"variant": "mix_h50_c50",
"instance_id": 310,
"success": false,
"q_score": 0.0,
"steps": 3225
},
{
"variant": "mix_h50_c50",
"instance_id": 311,
"success": false,
"q_score": 0.0,
"steps": 3225
},
{
"variant": "mix_h50_c50",
"instance_id": 312,
"success": true,
"q_score": 1.0,
"steps": 383
},
{
"variant": "mix_h50_c50",
"instance_id": 313,
"success": false,
"q_score": 0.0,
"steps": 3225
},
{
"variant": "mix_h50_c50",
"instance_id": 314,
"success": false,
"q_score": 0.0,
"steps": 3225
},
{
"variant": "mix_h50_c50",
"instance_id": 315,
"success": false,
"q_score": 0.0,
"steps": 3225
},
{
"variant": "mix_h50_c50",
"instance_id": 316,
"success": false,
"q_score": 0.0,
"steps": 3225
},
{
"variant": "mix_h50_c50",
"instance_id": 317,
"success": false,
"q_score": 0.0,
"steps": 3225
},
{
"variant": "mix_h50_c50",
"instance_id": 318,
"success": false,
"q_score": 0.0,
"steps": 3225
},
{
"variant": "mix_h50_c50",
"instance_id": 319,
"success": false,
"q_score": 0.0,
"steps": 3225
},
{
"variant": "mix_h50_c50",
"instance_id": 320,
"success": false,
"q_score": 0.0,
"steps": 3225
}
]