generated from xuyuqing/ailab
260 lines
5.2 KiB
JSON
260 lines
5.2 KiB
JSON
{
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 0.99812382739212,
|
|
"global_step": 399,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"epoch": 0.03,
|
|
"learning_rate": 4.992254676005419e-05,
|
|
"loss": 2.3336,
|
|
"step": 10
|
|
},
|
|
{
|
|
"epoch": 0.05,
|
|
"learning_rate": 4.969066696056699e-05,
|
|
"loss": 2.2307,
|
|
"step": 20
|
|
},
|
|
{
|
|
"epoch": 0.08,
|
|
"learning_rate": 4.9305797388878264e-05,
|
|
"loss": 2.1497,
|
|
"step": 30
|
|
},
|
|
{
|
|
"epoch": 0.1,
|
|
"learning_rate": 4.877032279661073e-05,
|
|
"loss": 2.0895,
|
|
"step": 40
|
|
},
|
|
{
|
|
"epoch": 0.13,
|
|
"learning_rate": 4.8087561123130764e-05,
|
|
"loss": 2.1052,
|
|
"step": 50
|
|
},
|
|
{
|
|
"epoch": 0.15,
|
|
"learning_rate": 4.726174293673612e-05,
|
|
"loss": 2.0591,
|
|
"step": 60
|
|
},
|
|
{
|
|
"epoch": 0.18,
|
|
"learning_rate": 4.629798522095818e-05,
|
|
"loss": 2.0869,
|
|
"step": 70
|
|
},
|
|
{
|
|
"epoch": 0.2,
|
|
"learning_rate": 4.520225966840574e-05,
|
|
"loss": 2.065,
|
|
"step": 80
|
|
},
|
|
{
|
|
"epoch": 0.23,
|
|
"learning_rate": 4.398135567860972e-05,
|
|
"loss": 2.078,
|
|
"step": 90
|
|
},
|
|
{
|
|
"epoch": 0.25,
|
|
"learning_rate": 4.264283828914392e-05,
|
|
"loss": 2.0751,
|
|
"step": 100
|
|
},
|
|
{
|
|
"epoch": 0.28,
|
|
"learning_rate": 4.119500130069138e-05,
|
|
"loss": 2.0628,
|
|
"step": 110
|
|
},
|
|
{
|
|
"epoch": 0.3,
|
|
"learning_rate": 3.964681588650562e-05,
|
|
"loss": 2.0149,
|
|
"step": 120
|
|
},
|
|
{
|
|
"epoch": 0.33,
|
|
"learning_rate": 3.800787500469589e-05,
|
|
"loss": 2.0432,
|
|
"step": 130
|
|
},
|
|
{
|
|
"epoch": 0.35,
|
|
"learning_rate": 3.628833395777224e-05,
|
|
"loss": 2.031,
|
|
"step": 140
|
|
},
|
|
{
|
|
"epoch": 0.38,
|
|
"learning_rate": 3.4498847467759e-05,
|
|
"loss": 2.0232,
|
|
"step": 150
|
|
},
|
|
{
|
|
"epoch": 0.4,
|
|
"learning_rate": 3.2650503656775446e-05,
|
|
"loss": 1.9852,
|
|
"step": 160
|
|
},
|
|
{
|
|
"epoch": 0.43,
|
|
"learning_rate": 3.075475534215712e-05,
|
|
"loss": 2.0334,
|
|
"step": 170
|
|
},
|
|
{
|
|
"epoch": 0.45,
|
|
"learning_rate": 2.882334907183115e-05,
|
|
"loss": 2.0359,
|
|
"step": 180
|
|
},
|
|
{
|
|
"epoch": 0.48,
|
|
"learning_rate": 2.686825233966061e-05,
|
|
"loss": 1.987,
|
|
"step": 190
|
|
},
|
|
{
|
|
"epoch": 0.5,
|
|
"learning_rate": 2.4901579431750625e-05,
|
|
"loss": 2.0376,
|
|
"step": 200
|
|
},
|
|
{
|
|
"epoch": 0.53,
|
|
"learning_rate": 2.2935516363191693e-05,
|
|
"loss": 2.0186,
|
|
"step": 210
|
|
},
|
|
{
|
|
"epoch": 0.55,
|
|
"learning_rate": 2.0982245370351645e-05,
|
|
"loss": 2.0056,
|
|
"step": 220
|
|
},
|
|
{
|
|
"epoch": 0.58,
|
|
"learning_rate": 1.9053869426581475e-05,
|
|
"loss": 1.9924,
|
|
"step": 230
|
|
},
|
|
{
|
|
"epoch": 0.6,
|
|
"learning_rate": 1.7162337249055477e-05,
|
|
"loss": 2.0295,
|
|
"step": 240
|
|
},
|
|
{
|
|
"epoch": 0.63,
|
|
"learning_rate": 1.531936926142254e-05,
|
|
"loss": 2.0122,
|
|
"step": 250
|
|
},
|
|
{
|
|
"epoch": 0.65,
|
|
"learning_rate": 1.3536384971023359e-05,
|
|
"loss": 2.049,
|
|
"step": 260
|
|
},
|
|
{
|
|
"epoch": 0.68,
|
|
"learning_rate": 1.182443221066303e-05,
|
|
"loss": 2.0183,
|
|
"step": 270
|
|
},
|
|
{
|
|
"epoch": 0.7,
|
|
"learning_rate": 1.0194118683375503e-05,
|
|
"loss": 2.0236,
|
|
"step": 280
|
|
},
|
|
{
|
|
"epoch": 0.73,
|
|
"learning_rate": 8.65554623434604e-06,
|
|
"loss": 2.0514,
|
|
"step": 290
|
|
},
|
|
{
|
|
"epoch": 0.75,
|
|
"learning_rate": 7.218248257260127e-06,
|
|
"loss": 2.0722,
|
|
"step": 300
|
|
},
|
|
{
|
|
"epoch": 0.78,
|
|
"learning_rate": 5.891130622925209e-06,
|
|
"loss": 2.0315,
|
|
"step": 310
|
|
},
|
|
{
|
|
"epoch": 0.8,
|
|
"learning_rate": 4.68241649618675e-06,
|
|
"loss": 2.0229,
|
|
"step": 320
|
|
},
|
|
{
|
|
"epoch": 0.83,
|
|
"learning_rate": 3.8057545285486053e-06,
|
|
"loss": 2.0299,
|
|
"step": 330
|
|
},
|
|
{
|
|
"epoch": 0.85,
|
|
"learning_rate": 2.8285175036914107e-06,
|
|
"loss": 2.0282,
|
|
"step": 340
|
|
},
|
|
{
|
|
"epoch": 0.88,
|
|
"learning_rate": 1.988660731133499e-06,
|
|
"loss": 2.0454,
|
|
"step": 350
|
|
},
|
|
{
|
|
"epoch": 0.9,
|
|
"learning_rate": 1.2913881811248696e-06,
|
|
"loss": 1.9951,
|
|
"step": 360
|
|
},
|
|
{
|
|
"epoch": 0.93,
|
|
"learning_rate": 7.410203351154083e-07,
|
|
"loss": 2.047,
|
|
"step": 370
|
|
},
|
|
{
|
|
"epoch": 0.95,
|
|
"learning_rate": 3.4096741493194197e-07,
|
|
"loss": 1.9984,
|
|
"step": 380
|
|
},
|
|
{
|
|
"epoch": 0.98,
|
|
"learning_rate": 9.370825215991308e-08,
|
|
"loss": 2.0279,
|
|
"step": 390
|
|
},
|
|
{
|
|
"epoch": 1.0,
|
|
"step": 399,
|
|
"total_flos": 3.1993772256945766e+17,
|
|
"train_loss": 2.0517517462708894,
|
|
"train_runtime": 920.588,
|
|
"train_samples_per_second": 55.563,
|
|
"train_steps_per_second": 0.433
|
|
}
|
|
],
|
|
"max_steps": 399,
|
|
"num_train_epochs": 1,
|
|
"total_flos": 3.1993772256945766e+17,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|