52 lines
852 B
JSON
52 lines
852 B
JSON
{
|
|
"wandb_run": "run-20260630_224949-g2gxclf3",
|
|
"wandb_output_log": "/mnt/mole/SDPO/L2T/wandb/run-20260630_224949-g2gxclf3/files/output.log",
|
|
"metric_key": "val-aux/sciknoweval/reward/mean@16",
|
|
"evals": [
|
|
{
|
|
"step": 10,
|
|
"mean16": 0.32
|
|
},
|
|
{
|
|
"step": 20,
|
|
"mean16": 0.35625
|
|
},
|
|
{
|
|
"step": 30,
|
|
"mean16": 0.47125
|
|
},
|
|
{
|
|
"step": 40,
|
|
"mean16": 0.5225
|
|
},
|
|
{
|
|
"step": 50,
|
|
"mean16": 0.55625
|
|
},
|
|
{
|
|
"step": 60,
|
|
"mean16": 0.5575
|
|
},
|
|
{
|
|
"step": 70,
|
|
"mean16": 0.59875
|
|
},
|
|
{
|
|
"step": 80,
|
|
"mean16": 0.61375
|
|
},
|
|
{
|
|
"step": 90,
|
|
"mean16": 0.555
|
|
},
|
|
{
|
|
"step": 100,
|
|
"mean16": 0.6425
|
|
}
|
|
],
|
|
"best_step": 100,
|
|
"best_mean16": 0.6425,
|
|
"final_step": 100,
|
|
"final_mean16": 0.6425
|
|
}
|