albert-xxl-squad-sentences / trainer_state.json
apohllo's picture
Upload trainer_state.json with huggingface_hub
c0f4fa6
raw
history blame contribute delete
No virus
12.9 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.999853279209664,
"global_step": 5111,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 1e-08,
"loss": 1.082,
"step": 1
},
{
"epoch": 0.01,
"learning_rate": 5.000000000000001e-07,
"loss": 0.9046,
"step": 50
},
{
"epoch": 0.02,
"learning_rate": 1.0000000000000002e-06,
"loss": 0.518,
"step": 100
},
{
"epoch": 0.03,
"learning_rate": 1.5e-06,
"loss": 0.3212,
"step": 150
},
{
"epoch": 0.04,
"learning_rate": 2.0000000000000003e-06,
"loss": 0.2435,
"step": 200
},
{
"epoch": 0.05,
"learning_rate": 2.5e-06,
"loss": 0.186,
"step": 250
},
{
"epoch": 0.06,
"learning_rate": 3e-06,
"loss": 0.1809,
"step": 300
},
{
"epoch": 0.07,
"learning_rate": 3.5e-06,
"loss": 0.16,
"step": 350
},
{
"epoch": 0.08,
"learning_rate": 4.000000000000001e-06,
"loss": 0.1625,
"step": 400
},
{
"epoch": 0.09,
"learning_rate": 4.5e-06,
"loss": 0.1502,
"step": 450
},
{
"epoch": 0.1,
"learning_rate": 5e-06,
"loss": 0.1401,
"step": 500
},
{
"epoch": 0.11,
"learning_rate": 5.500000000000001e-06,
"loss": 0.1206,
"step": 550
},
{
"epoch": 0.12,
"learning_rate": 6e-06,
"loss": 0.1291,
"step": 600
},
{
"epoch": 0.13,
"learning_rate": 6.5000000000000004e-06,
"loss": 0.1382,
"step": 650
},
{
"epoch": 0.14,
"learning_rate": 7e-06,
"loss": 0.13,
"step": 700
},
{
"epoch": 0.15,
"learning_rate": 7.500000000000001e-06,
"loss": 0.1262,
"step": 750
},
{
"epoch": 0.16,
"learning_rate": 8.000000000000001e-06,
"loss": 0.1218,
"step": 800
},
{
"epoch": 0.17,
"learning_rate": 8.5e-06,
"loss": 0.1223,
"step": 850
},
{
"epoch": 0.18,
"learning_rate": 9e-06,
"loss": 0.1128,
"step": 900
},
{
"epoch": 0.19,
"learning_rate": 9.5e-06,
"loss": 0.1188,
"step": 950
},
{
"epoch": 0.2,
"learning_rate": 1e-05,
"loss": 0.1203,
"step": 1000
},
{
"epoch": 0.21,
"learning_rate": 9.979637548360824e-06,
"loss": 0.107,
"step": 1050
},
{
"epoch": 0.22,
"learning_rate": 9.959275096721645e-06,
"loss": 0.1155,
"step": 1100
},
{
"epoch": 0.22,
"learning_rate": 9.93891264508247e-06,
"loss": 0.1112,
"step": 1150
},
{
"epoch": 0.23,
"learning_rate": 9.91855019344329e-06,
"loss": 0.1149,
"step": 1200
},
{
"epoch": 0.24,
"learning_rate": 9.898187741804114e-06,
"loss": 0.1043,
"step": 1250
},
{
"epoch": 0.25,
"learning_rate": 9.877825290164937e-06,
"loss": 0.1103,
"step": 1300
},
{
"epoch": 0.26,
"learning_rate": 9.85746283852576e-06,
"loss": 0.114,
"step": 1350
},
{
"epoch": 0.27,
"learning_rate": 9.837100386886582e-06,
"loss": 0.1246,
"step": 1400
},
{
"epoch": 0.28,
"learning_rate": 9.816737935247405e-06,
"loss": 0.1068,
"step": 1450
},
{
"epoch": 0.29,
"learning_rate": 9.796375483608226e-06,
"loss": 0.118,
"step": 1500
},
{
"epoch": 0.3,
"learning_rate": 9.77601303196905e-06,
"loss": 0.1014,
"step": 1550
},
{
"epoch": 0.31,
"learning_rate": 9.755650580329872e-06,
"loss": 0.1089,
"step": 1600
},
{
"epoch": 0.32,
"learning_rate": 9.735288128690695e-06,
"loss": 0.0997,
"step": 1650
},
{
"epoch": 0.33,
"learning_rate": 9.714925677051518e-06,
"loss": 0.1009,
"step": 1700
},
{
"epoch": 0.34,
"learning_rate": 9.69456322541234e-06,
"loss": 0.1187,
"step": 1750
},
{
"epoch": 0.35,
"learning_rate": 9.674200773773164e-06,
"loss": 0.113,
"step": 1800
},
{
"epoch": 0.36,
"learning_rate": 9.653838322133987e-06,
"loss": 0.1009,
"step": 1850
},
{
"epoch": 0.37,
"learning_rate": 9.633475870494808e-06,
"loss": 0.0976,
"step": 1900
},
{
"epoch": 0.38,
"learning_rate": 9.613113418855631e-06,
"loss": 0.1059,
"step": 1950
},
{
"epoch": 0.39,
"learning_rate": 9.592750967216454e-06,
"loss": 0.1104,
"step": 2000
},
{
"epoch": 0.4,
"learning_rate": 9.572388515577277e-06,
"loss": 0.0943,
"step": 2050
},
{
"epoch": 0.41,
"learning_rate": 9.5520260639381e-06,
"loss": 0.1057,
"step": 2100
},
{
"epoch": 0.42,
"learning_rate": 9.53166361229892e-06,
"loss": 0.1032,
"step": 2150
},
{
"epoch": 0.43,
"learning_rate": 9.511301160659744e-06,
"loss": 0.1017,
"step": 2200
},
{
"epoch": 0.44,
"learning_rate": 9.490938709020567e-06,
"loss": 0.1056,
"step": 2250
},
{
"epoch": 0.45,
"learning_rate": 9.47057625738139e-06,
"loss": 0.1058,
"step": 2300
},
{
"epoch": 0.46,
"learning_rate": 9.450213805742212e-06,
"loss": 0.108,
"step": 2350
},
{
"epoch": 0.47,
"learning_rate": 9.429851354103035e-06,
"loss": 0.1048,
"step": 2400
},
{
"epoch": 0.48,
"learning_rate": 9.409488902463856e-06,
"loss": 0.1033,
"step": 2450
},
{
"epoch": 0.49,
"learning_rate": 9.389126450824681e-06,
"loss": 0.0972,
"step": 2500
},
{
"epoch": 0.5,
"learning_rate": 9.368763999185502e-06,
"loss": 0.0988,
"step": 2550
},
{
"epoch": 0.51,
"learning_rate": 9.348401547546325e-06,
"loss": 0.0971,
"step": 2600
},
{
"epoch": 0.52,
"learning_rate": 9.328039095907148e-06,
"loss": 0.0982,
"step": 2650
},
{
"epoch": 0.53,
"learning_rate": 9.307676644267971e-06,
"loss": 0.096,
"step": 2700
},
{
"epoch": 0.54,
"learning_rate": 9.287314192628794e-06,
"loss": 0.0997,
"step": 2750
},
{
"epoch": 0.55,
"learning_rate": 9.266951740989615e-06,
"loss": 0.1173,
"step": 2800
},
{
"epoch": 0.56,
"learning_rate": 9.246589289350438e-06,
"loss": 0.0936,
"step": 2850
},
{
"epoch": 0.57,
"learning_rate": 9.226226837711261e-06,
"loss": 0.1038,
"step": 2900
},
{
"epoch": 0.58,
"learning_rate": 9.205864386072084e-06,
"loss": 0.1035,
"step": 2950
},
{
"epoch": 0.59,
"learning_rate": 9.185501934432907e-06,
"loss": 0.0876,
"step": 3000
},
{
"epoch": 0.6,
"learning_rate": 9.16513948279373e-06,
"loss": 0.1002,
"step": 3050
},
{
"epoch": 0.61,
"learning_rate": 9.14477703115455e-06,
"loss": 0.1077,
"step": 3100
},
{
"epoch": 0.62,
"learning_rate": 9.124414579515375e-06,
"loss": 0.0979,
"step": 3150
},
{
"epoch": 0.63,
"learning_rate": 9.104052127876197e-06,
"loss": 0.1003,
"step": 3200
},
{
"epoch": 0.64,
"learning_rate": 9.08368967623702e-06,
"loss": 0.0984,
"step": 3250
},
{
"epoch": 0.65,
"learning_rate": 9.063327224597842e-06,
"loss": 0.0964,
"step": 3300
},
{
"epoch": 0.66,
"learning_rate": 9.042964772958665e-06,
"loss": 0.1046,
"step": 3350
},
{
"epoch": 0.67,
"learning_rate": 9.022602321319488e-06,
"loss": 0.1042,
"step": 3400
},
{
"epoch": 0.67,
"learning_rate": 9.002239869680311e-06,
"loss": 0.0948,
"step": 3450
},
{
"epoch": 0.68,
"learning_rate": 8.981877418041132e-06,
"loss": 0.0904,
"step": 3500
},
{
"epoch": 0.69,
"learning_rate": 8.961514966401955e-06,
"loss": 0.095,
"step": 3550
},
{
"epoch": 0.7,
"learning_rate": 8.941152514762778e-06,
"loss": 0.0993,
"step": 3600
},
{
"epoch": 0.71,
"learning_rate": 8.920790063123601e-06,
"loss": 0.0949,
"step": 3650
},
{
"epoch": 0.72,
"learning_rate": 8.900427611484424e-06,
"loss": 0.0956,
"step": 3700
},
{
"epoch": 0.73,
"learning_rate": 8.880065159845245e-06,
"loss": 0.0956,
"step": 3750
},
{
"epoch": 0.74,
"learning_rate": 8.859702708206068e-06,
"loss": 0.0967,
"step": 3800
},
{
"epoch": 0.75,
"learning_rate": 8.839340256566893e-06,
"loss": 0.0985,
"step": 3850
},
{
"epoch": 0.76,
"learning_rate": 8.818977804927714e-06,
"loss": 0.0985,
"step": 3900
},
{
"epoch": 0.77,
"learning_rate": 8.798615353288537e-06,
"loss": 0.0988,
"step": 3950
},
{
"epoch": 0.78,
"learning_rate": 8.77825290164936e-06,
"loss": 0.1032,
"step": 4000
},
{
"epoch": 0.79,
"learning_rate": 8.757890450010183e-06,
"loss": 0.1008,
"step": 4050
},
{
"epoch": 0.8,
"learning_rate": 8.737527998371005e-06,
"loss": 0.0928,
"step": 4100
},
{
"epoch": 0.81,
"learning_rate": 8.717165546731827e-06,
"loss": 0.0836,
"step": 4150
},
{
"epoch": 0.82,
"learning_rate": 8.69680309509265e-06,
"loss": 0.0958,
"step": 4200
},
{
"epoch": 0.83,
"learning_rate": 8.676440643453472e-06,
"loss": 0.0956,
"step": 4250
},
{
"epoch": 0.84,
"learning_rate": 8.656078191814295e-06,
"loss": 0.1009,
"step": 4300
},
{
"epoch": 0.85,
"learning_rate": 8.635715740175118e-06,
"loss": 0.098,
"step": 4350
},
{
"epoch": 0.86,
"learning_rate": 8.615353288535941e-06,
"loss": 0.0982,
"step": 4400
},
{
"epoch": 0.87,
"learning_rate": 8.594990836896762e-06,
"loss": 0.0983,
"step": 4450
},
{
"epoch": 0.88,
"learning_rate": 8.574628385257587e-06,
"loss": 0.0923,
"step": 4500
},
{
"epoch": 0.89,
"learning_rate": 8.554265933618408e-06,
"loss": 0.0941,
"step": 4550
},
{
"epoch": 0.9,
"learning_rate": 8.533903481979231e-06,
"loss": 0.0951,
"step": 4600
},
{
"epoch": 0.91,
"learning_rate": 8.513541030340054e-06,
"loss": 0.092,
"step": 4650
},
{
"epoch": 0.92,
"learning_rate": 8.493178578700875e-06,
"loss": 0.1038,
"step": 4700
},
{
"epoch": 0.93,
"learning_rate": 8.4728161270617e-06,
"loss": 0.0972,
"step": 4750
},
{
"epoch": 0.94,
"learning_rate": 8.452453675422521e-06,
"loss": 0.0915,
"step": 4800
},
{
"epoch": 0.95,
"learning_rate": 8.432091223783344e-06,
"loss": 0.0989,
"step": 4850
},
{
"epoch": 0.96,
"learning_rate": 8.411728772144167e-06,
"loss": 0.0956,
"step": 4900
},
{
"epoch": 0.97,
"learning_rate": 8.39136632050499e-06,
"loss": 0.1001,
"step": 4950
},
{
"epoch": 0.98,
"learning_rate": 8.371003868865813e-06,
"loss": 0.0969,
"step": 5000
},
{
"epoch": 0.98,
"eval_accuracy": 0.9705359974627339,
"eval_f1": 0.8414134516899965,
"eval_loss": 0.08369224518537521,
"eval_precision": 0.8542461005199307,
"eval_recall": 0.8289606458123108,
"eval_runtime": 2321.5551,
"eval_samples_per_second": 27.163,
"eval_steps_per_second": 0.849,
"step": 5000
},
{
"epoch": 0.99,
"learning_rate": 8.350641417226635e-06,
"loss": 0.0819,
"step": 5050
},
{
"epoch": 1.0,
"learning_rate": 8.330278965587457e-06,
"loss": 0.0952,
"step": 5100
}
],
"max_steps": 25555,
"num_train_epochs": 5,
"total_flos": 4.395776611183227e+17,
"trial_name": null,
"trial_params": null
}