52 lines
877 B
JSON
52 lines
877 B
JSON
{
|
|
"wandb_run": "run-20260630_144559-s6sllh44",
|
|
"wandb_output_log": "/mnt/mole/SDPO/L2T/wandb/run-20260630_144559-s6sllh44/files/output.log",
|
|
"metric_key": "val-aux/sciknoweval/reward/mean@16",
|
|
"evals": [
|
|
{
|
|
"step": 10,
|
|
"mean16": 0.6046875
|
|
},
|
|
{
|
|
"step": 20,
|
|
"mean16": 0.6203125
|
|
},
|
|
{
|
|
"step": 30,
|
|
"mean16": 0.64921875
|
|
},
|
|
{
|
|
"step": 40,
|
|
"mean16": 0.6515625
|
|
},
|
|
{
|
|
"step": 50,
|
|
"mean16": 0.69375
|
|
},
|
|
{
|
|
"step": 60,
|
|
"mean16": 0.7171875
|
|
},
|
|
{
|
|
"step": 70,
|
|
"mean16": 0.72421875
|
|
},
|
|
{
|
|
"step": 80,
|
|
"mean16": 0.7296875
|
|
},
|
|
{
|
|
"step": 90,
|
|
"mean16": 0.75546875
|
|
},
|
|
{
|
|
"step": 100,
|
|
"mean16": 0.75
|
|
}
|
|
],
|
|
"best_step": 90,
|
|
"best_mean16": 0.75546875,
|
|
"final_step": 100,
|
|
"final_mean16": 0.75
|
|
}
|