300 lines
4.6 KiB
JSON
300 lines
4.6 KiB
JSON
{
|
|
"pairs": 124,
|
|
"sft_adapter": "outputs/legal-3b-v3/checkpoint-300",
|
|
"beta": 0.1,
|
|
"epochs": 3,
|
|
"optimizer_steps": 48,
|
|
"final_loss": 0.5268,
|
|
"final_margin": 0.366,
|
|
"history": [
|
|
{
|
|
"step": 1,
|
|
"epoch": 0,
|
|
"loss": 0.6931,
|
|
"margin": 0.0
|
|
},
|
|
{
|
|
"step": 2,
|
|
"epoch": 0,
|
|
"loss": 0.7271,
|
|
"margin": -0.0668
|
|
},
|
|
{
|
|
"step": 3,
|
|
"epoch": 0,
|
|
"loss": 0.6067,
|
|
"margin": 0.1811
|
|
},
|
|
{
|
|
"step": 4,
|
|
"epoch": 0,
|
|
"loss": 0.6631,
|
|
"margin": 0.0611
|
|
},
|
|
{
|
|
"step": 5,
|
|
"epoch": 0,
|
|
"loss": 0.7499,
|
|
"margin": -0.1104
|
|
},
|
|
{
|
|
"step": 6,
|
|
"epoch": 0,
|
|
"loss": 0.6343,
|
|
"margin": 0.1214
|
|
},
|
|
{
|
|
"step": 7,
|
|
"epoch": 0,
|
|
"loss": 0.7168,
|
|
"margin": -0.0468
|
|
},
|
|
{
|
|
"step": 8,
|
|
"epoch": 0,
|
|
"loss": 0.6645,
|
|
"margin": 0.0581
|
|
},
|
|
{
|
|
"step": 9,
|
|
"epoch": 0,
|
|
"loss": 0.6587,
|
|
"margin": 0.0701
|
|
},
|
|
{
|
|
"step": 10,
|
|
"epoch": 0,
|
|
"loss": 0.6732,
|
|
"margin": 0.0402
|
|
},
|
|
{
|
|
"step": 11,
|
|
"epoch": 0,
|
|
"loss": 0.589,
|
|
"margin": 0.2205
|
|
},
|
|
{
|
|
"step": 12,
|
|
"epoch": 0,
|
|
"loss": 0.6851,
|
|
"margin": 0.0162
|
|
},
|
|
{
|
|
"step": 13,
|
|
"epoch": 0,
|
|
"loss": 0.6826,
|
|
"margin": 0.0212
|
|
},
|
|
{
|
|
"step": 14,
|
|
"epoch": 0,
|
|
"loss": 0.5937,
|
|
"margin": 0.2099
|
|
},
|
|
{
|
|
"step": 15,
|
|
"epoch": 0,
|
|
"loss": 0.759,
|
|
"margin": -0.1277
|
|
},
|
|
{
|
|
"step": 16,
|
|
"epoch": 0,
|
|
"loss": 0.7671,
|
|
"margin": -0.1427
|
|
},
|
|
{
|
|
"step": 17,
|
|
"epoch": 1,
|
|
"loss": 0.5843,
|
|
"margin": 0.231
|
|
},
|
|
{
|
|
"step": 18,
|
|
"epoch": 1,
|
|
"loss": 0.7993,
|
|
"margin": -0.2021
|
|
},
|
|
{
|
|
"step": 19,
|
|
"epoch": 1,
|
|
"loss": 0.6293,
|
|
"margin": 0.132
|
|
},
|
|
{
|
|
"step": 20,
|
|
"epoch": 1,
|
|
"loss": 0.7464,
|
|
"margin": -0.1038
|
|
},
|
|
{
|
|
"step": 21,
|
|
"epoch": 1,
|
|
"loss": 0.6757,
|
|
"margin": 0.0353
|
|
},
|
|
{
|
|
"step": 22,
|
|
"epoch": 1,
|
|
"loss": 0.713,
|
|
"margin": -0.0393
|
|
},
|
|
{
|
|
"step": 23,
|
|
"epoch": 1,
|
|
"loss": 0.5206,
|
|
"margin": 0.3812
|
|
},
|
|
{
|
|
"step": 24,
|
|
"epoch": 1,
|
|
"loss": 0.7103,
|
|
"margin": -0.034
|
|
},
|
|
{
|
|
"step": 25,
|
|
"epoch": 1,
|
|
"loss": 0.6525,
|
|
"margin": 0.083
|
|
},
|
|
{
|
|
"step": 26,
|
|
"epoch": 1,
|
|
"loss": 0.63,
|
|
"margin": 0.1305
|
|
},
|
|
{
|
|
"step": 27,
|
|
"epoch": 1,
|
|
"loss": 0.5864,
|
|
"margin": 0.2263
|
|
},
|
|
{
|
|
"step": 28,
|
|
"epoch": 1,
|
|
"loss": 0.4905,
|
|
"margin": 0.457
|
|
},
|
|
{
|
|
"step": 29,
|
|
"epoch": 1,
|
|
"loss": 0.6076,
|
|
"margin": 0.1791
|
|
},
|
|
{
|
|
"step": 30,
|
|
"epoch": 1,
|
|
"loss": 0.6098,
|
|
"margin": 0.1743
|
|
},
|
|
{
|
|
"step": 31,
|
|
"epoch": 1,
|
|
"loss": 0.4762,
|
|
"margin": 0.4945
|
|
},
|
|
{
|
|
"step": 32,
|
|
"epoch": 1,
|
|
"loss": 0.5189,
|
|
"margin": 0.3854
|
|
},
|
|
{
|
|
"step": 33,
|
|
"epoch": 2,
|
|
"loss": 0.5235,
|
|
"margin": 0.374
|
|
},
|
|
{
|
|
"step": 34,
|
|
"epoch": 2,
|
|
"loss": 0.3293,
|
|
"margin": 0.9416
|
|
},
|
|
{
|
|
"step": 35,
|
|
"epoch": 2,
|
|
"loss": 0.4656,
|
|
"margin": 0.5226
|
|
},
|
|
{
|
|
"step": 36,
|
|
"epoch": 2,
|
|
"loss": 0.6588,
|
|
"margin": 0.0699
|
|
},
|
|
{
|
|
"step": 37,
|
|
"epoch": 2,
|
|
"loss": 0.4392,
|
|
"margin": 0.5951
|
|
},
|
|
{
|
|
"step": 38,
|
|
"epoch": 2,
|
|
"loss": 0.5389,
|
|
"margin": 0.3368
|
|
},
|
|
{
|
|
"step": 39,
|
|
"epoch": 2,
|
|
"loss": 0.7196,
|
|
"margin": -0.0523
|
|
},
|
|
{
|
|
"step": 40,
|
|
"epoch": 2,
|
|
"loss": 0.4093,
|
|
"margin": 0.6817
|
|
},
|
|
{
|
|
"step": 41,
|
|
"epoch": 2,
|
|
"loss": 0.5289,
|
|
"margin": 0.3609
|
|
},
|
|
{
|
|
"step": 42,
|
|
"epoch": 2,
|
|
"loss": 0.4894,
|
|
"margin": 0.4599
|
|
},
|
|
{
|
|
"step": 43,
|
|
"epoch": 2,
|
|
"loss": 0.6129,
|
|
"margin": 0.1675
|
|
},
|
|
{
|
|
"step": 44,
|
|
"epoch": 2,
|
|
"loss": 0.5136,
|
|
"margin": 0.3986
|
|
},
|
|
{
|
|
"step": 45,
|
|
"epoch": 2,
|
|
"loss": 0.3373,
|
|
"margin": 0.9133
|
|
},
|
|
{
|
|
"step": 46,
|
|
"epoch": 2,
|
|
"loss": 0.4089,
|
|
"margin": 0.683
|
|
},
|
|
{
|
|
"step": 47,
|
|
"epoch": 2,
|
|
"loss": 0.2918,
|
|
"margin": 1.0822
|
|
},
|
|
{
|
|
"step": 48,
|
|
"epoch": 2,
|
|
"loss": 0.5268,
|
|
"margin": 0.366
|
|
}
|
|
],
|
|
"seconds": 760
|
|
} |