trail_leaderboard / e3c_llm_results /Qwen /Qwen3-30B-A3B-Instruct-2507_10_SL.json
Sfarzi's picture
Initial clone with modifications
f7a50a0
{
"average_CPS": 59.600933166666664,
"config": {
"model_name": "Qwen/Qwen3-30B-A3B-Instruct-2507",
"num_fewshot": "10",
"batch_size": 1,
"LANG": "SL",
"model": "Qwen/Qwen3-30B-A3B-Instruct-2507",
"base_model": "Qwen3MoeForCausalLM",
"revision": "61082d4deaa4785f64943b443cbc2b5de7524fad",
"submitted_time": "2025-07-28 07:31:27+00:00",
"num_params_billion": 30.532122624,
"language": ""
},
"tasks": {
"NER": {
"prompts": [
{
"prompt": "p1",
"metric": "f1",
"value": 66.14999999999999,
"stderr": 0.0
},
{
"prompt": "p2",
"metric": "f1",
"value": 59.440000000000005,
"stderr": 0.0
},
{
"prompt": "p3",
"metric": "f1",
"value": 66.14999999999999,
"stderr": 0.0
}
],
"average_accuracy": 63.913333333333334,
"best_prompt": 66.14999999999999,
"prompt_id": "p1",
"CPS": 64.670445,
"is_dummy": false,
"std_accuracy": 3.874020306262381
},
"RE": {
"prompts": [
{
"prompt": "p1",
"metric": "f1",
"value": 50.62,
"stderr": 0.0
},
{
"prompt": "p2",
"metric": "f1",
"value": 55.76,
"stderr": 0.0
},
{
"prompt": "p3",
"metric": "f1",
"value": 54.290000000000006,
"stderr": 0.0
}
],
"average_accuracy": 53.55666666666667,
"best_prompt": 55.76,
"prompt_id": "p2",
"CPS": 54.531421333333334,
"is_dummy": false,
"std_accuracy": 2.647306807556189
},
"RML": {
"prompts": [
{
"prompt": "p1",
"metric": "f1",
"value": 0.0,
"stderr": 0.0
}
],
"average_accuracy": null,
"std_accuracy": null,
"best_prompt": null,
"prompt_id": null,
"CPS": null,
"is_dummy": true
},
"HIS": {
"prompts": [
{
"prompt": "p1",
"metric": "f1",
"value": 0.0,
"stderr": 0.0
}
],
"average_accuracy": null,
"std_accuracy": null,
"best_prompt": null,
"prompt_id": null,
"CPS": null,
"is_dummy": true
},
"DIA": {
"prompts": [
{
"prompt": "p1",
"metric": "f1",
"value": 0.0,
"stderr": 0.0
}
],
"average_accuracy": null,
"std_accuracy": null,
"best_prompt": null,
"prompt_id": null,
"CPS": null,
"is_dummy": true
}
}
}