RepairLLaMA-IR1-OR4 / trainer_state.json
Sen Fang
Up
8b75f58
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 2.0,
"eval_steps": 10.0,
"global_step": 1374,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.01,
"learning_rate": 0.0004999346542461473,
"loss": 0.4698,
"step": 10
},
{
"epoch": 0.03,
"learning_rate": 0.0004997386511451298,
"loss": 0.2312,
"step": 20
},
{
"epoch": 0.04,
"learning_rate": 0.0004994120931607106,
"loss": 0.1855,
"step": 30
},
{
"epoch": 0.06,
"learning_rate": 0.0004989551510063109,
"loss": 0.1778,
"step": 40
},
{
"epoch": 0.07,
"learning_rate": 0.0004983680635557671,
"loss": 0.1728,
"step": 50
},
{
"epoch": 0.09,
"learning_rate": 0.0004976511377184557,
"loss": 0.182,
"step": 60
},
{
"epoch": 0.1,
"learning_rate": 0.0004968047482788508,
"loss": 0.1752,
"step": 70
},
{
"epoch": 0.12,
"learning_rate": 0.0004958293377006004,
"loss": 0.1742,
"step": 80
},
{
"epoch": 0.13,
"learning_rate": 0.0004947254158952209,
"loss": 0.1686,
"step": 90
},
{
"epoch": 0.15,
"learning_rate": 0.0004934935599555328,
"loss": 0.1674,
"step": 100
},
{
"epoch": 0.16,
"learning_rate": 0.0004921344138539761,
"loss": 0.1665,
"step": 110
},
{
"epoch": 0.17,
"learning_rate": 0.000490648688105964,
"loss": 0.1673,
"step": 120
},
{
"epoch": 0.19,
"learning_rate": 0.0004890371593984484,
"loss": 0.1706,
"step": 130
},
{
"epoch": 0.2,
"learning_rate": 0.0004873006701838952,
"loss": 0.1674,
"step": 140
},
{
"epoch": 0.22,
"learning_rate": 0.0004854401282398789,
"loss": 0.1662,
"step": 150
},
{
"epoch": 0.23,
"learning_rate": 0.0004834565061945266,
"loss": 0.1615,
"step": 160
},
{
"epoch": 0.25,
"learning_rate": 0.0004813508410180617,
"loss": 0.1643,
"step": 170
},
{
"epoch": 0.26,
"learning_rate": 0.00047912423348071056,
"loss": 0.1634,
"step": 180
},
{
"epoch": 0.28,
"learning_rate": 0.00047677784757725784,
"loss": 0.1552,
"step": 190
},
{
"epoch": 0.29,
"learning_rate": 0.00047431290991854904,
"loss": 0.1605,
"step": 200
},
{
"epoch": 0.31,
"learning_rate": 0.0004717307090902601,
"loss": 0.1523,
"step": 210
},
{
"epoch": 0.32,
"learning_rate": 0.00046903259497926896,
"loss": 0.1603,
"step": 220
},
{
"epoch": 0.33,
"learning_rate": 0.00046621997806798004,
"loss": 0.1599,
"step": 230
},
{
"epoch": 0.35,
"learning_rate": 0.00046329432869697236,
"loss": 0.1624,
"step": 240
},
{
"epoch": 0.36,
"learning_rate": 0.0004602571762963551,
"loss": 0.1669,
"step": 250
},
{
"epoch": 0.38,
"learning_rate": 0.0004571101085862337,
"loss": 0.1579,
"step": 260
},
{
"epoch": 0.39,
"learning_rate": 0.0004538547707467038,
"loss": 0.1665,
"step": 270
},
{
"epoch": 0.41,
"learning_rate": 0.0004504928645578067,
"loss": 0.1632,
"step": 280
},
{
"epoch": 0.42,
"learning_rate": 0.0004470261475098967,
"loss": 0.1571,
"step": 290
},
{
"epoch": 0.44,
"learning_rate": 0.00044345643188488506,
"loss": 0.154,
"step": 300
},
{
"epoch": 0.45,
"learning_rate": 0.00043978558380884013,
"loss": 0.1504,
"step": 310
},
{
"epoch": 0.47,
"learning_rate": 0.00043601552227644035,
"loss": 0.1634,
"step": 320
},
{
"epoch": 0.48,
"learning_rate": 0.00043214821814778904,
"loss": 0.147,
"step": 330
},
{
"epoch": 0.49,
"learning_rate": 0.0004281856931181155,
"loss": 0.1493,
"step": 340
},
{
"epoch": 0.51,
"learning_rate": 0.0004241300186609015,
"loss": 0.1543,
"step": 350
},
{
"epoch": 0.52,
"learning_rate": 0.0004199833149449853,
"loss": 0.1519,
"step": 360
},
{
"epoch": 0.54,
"learning_rate": 0.00041574774972620956,
"loss": 0.152,
"step": 370
},
{
"epoch": 0.55,
"learning_rate": 0.00041142553721419184,
"loss": 0.155,
"step": 380
},
{
"epoch": 0.57,
"learning_rate": 0.0004070189369148116,
"loss": 0.1585,
"step": 390
},
{
"epoch": 0.58,
"learning_rate": 0.0004025302524490166,
"loss": 0.1518,
"step": 400
},
{
"epoch": 0.6,
"learning_rate": 0.0003979618303485687,
"loss": 0.1536,
"step": 410
},
{
"epoch": 0.61,
"learning_rate": 0.0003933160588293564,
"loss": 0.1477,
"step": 420
},
{
"epoch": 0.63,
"learning_rate": 0.00038859536654291705,
"loss": 0.1494,
"step": 430
},
{
"epoch": 0.64,
"learning_rate": 0.00038380222130681986,
"loss": 0.1578,
"step": 440
},
{
"epoch": 0.66,
"learning_rate": 0.00037893912881457507,
"loss": 0.1533,
"step": 450
},
{
"epoch": 0.67,
"learning_rate": 0.00037400863132574223,
"loss": 0.1511,
"step": 460
},
{
"epoch": 0.68,
"learning_rate": 0.0003690133063369238,
"loss": 0.1548,
"step": 470
},
{
"epoch": 0.7,
"learning_rate": 0.00036395576523433673,
"loss": 0.1459,
"step": 480
},
{
"epoch": 0.71,
"learning_rate": 0.0003588386519286688,
"loss": 0.1518,
"step": 490
},
{
"epoch": 0.73,
"learning_rate": 0.00035366464147293223,
"loss": 0.1529,
"step": 500
},
{
"epoch": 0.74,
"learning_rate": 0.0003484364386640365,
"loss": 0.1608,
"step": 510
},
{
"epoch": 0.76,
"learning_rate": 0.00034315677662881205,
"loss": 0.1616,
"step": 520
},
{
"epoch": 0.77,
"learning_rate": 0.0003378284153952254,
"loss": 0.1549,
"step": 530
},
{
"epoch": 0.79,
"learning_rate": 0.00033245414044952927,
"loss": 0.155,
"step": 540
},
{
"epoch": 0.8,
"learning_rate": 0.00032703676128010553,
"loss": 0.1514,
"step": 550
},
{
"epoch": 0.82,
"learning_rate": 0.0003215791099087601,
"loss": 0.1462,
"step": 560
},
{
"epoch": 0.83,
"learning_rate": 0.0003160840394102379,
"loss": 0.1528,
"step": 570
},
{
"epoch": 0.84,
"learning_rate": 0.0003105544224207326,
"loss": 0.1517,
"step": 580
},
{
"epoch": 0.86,
"learning_rate": 0.00030499314963616987,
"loss": 0.1532,
"step": 590
},
{
"epoch": 0.87,
"learning_rate": 0.0002994031283010493,
"loss": 0.155,
"step": 600
},
{
"epoch": 0.89,
"learning_rate": 0.00029378728068863683,
"loss": 0.1499,
"step": 610
},
{
"epoch": 0.9,
"learning_rate": 0.00028814854257329825,
"loss": 0.1591,
"step": 620
},
{
"epoch": 0.92,
"learning_rate": 0.00028248986169577693,
"loss": 0.1501,
"step": 630
},
{
"epoch": 0.93,
"learning_rate": 0.00027681419622221514,
"loss": 0.1449,
"step": 640
},
{
"epoch": 0.95,
"learning_rate": 0.00027112451319772447,
"loss": 0.1423,
"step": 650
},
{
"epoch": 0.96,
"learning_rate": 0.00026542378699531645,
"loss": 0.1462,
"step": 660
},
{
"epoch": 0.98,
"learning_rate": 0.00025971499776100064,
"loss": 0.1469,
"step": 670
},
{
"epoch": 0.99,
"learning_rate": 0.00025400112985586587,
"loss": 0.1418,
"step": 680
},
{
"epoch": 1.0,
"learning_rate": 0.00024828517029595767,
"loss": 0.1397,
"step": 690
},
{
"epoch": 1.02,
"learning_rate": 0.00024257010719076723,
"loss": 0.142,
"step": 700
},
{
"epoch": 1.03,
"learning_rate": 0.00023685892818115019,
"loss": 0.1395,
"step": 710
},
{
"epoch": 1.05,
"learning_rate": 0.00023115461887748858,
"loss": 0.1392,
"step": 720
},
{
"epoch": 1.06,
"learning_rate": 0.00022546016129891568,
"loss": 0.1458,
"step": 730
},
{
"epoch": 1.08,
"learning_rate": 0.0002197785323144176,
"loss": 0.1341,
"step": 740
},
{
"epoch": 1.09,
"learning_rate": 0.00021411270208662698,
"loss": 0.1475,
"step": 750
},
{
"epoch": 1.11,
"learning_rate": 0.00020846563251912355,
"loss": 0.149,
"step": 760
},
{
"epoch": 1.12,
"learning_rate": 0.00020284027570805074,
"loss": 0.1399,
"step": 770
},
{
"epoch": 1.14,
"learning_rate": 0.00019723957239886066,
"loss": 0.1455,
"step": 780
},
{
"epoch": 1.15,
"learning_rate": 0.00019166645044899205,
"loss": 0.147,
"step": 790
},
{
"epoch": 1.16,
"learning_rate": 0.00018612382329728588,
"loss": 0.1499,
"step": 800
},
{
"epoch": 1.18,
"learning_rate": 0.00018061458844093858,
"loss": 0.1353,
"step": 810
},
{
"epoch": 1.19,
"learning_rate": 0.0001751416259207889,
"loss": 0.1433,
"step": 820
},
{
"epoch": 1.21,
"learning_rate": 0.00016970779681573046,
"loss": 0.1487,
"step": 830
},
{
"epoch": 1.22,
"learning_rate": 0.00016431594174703645,
"loss": 0.1459,
"step": 840
},
{
"epoch": 1.24,
"learning_rate": 0.00015896887939338,
"loss": 0.153,
"step": 850
},
{
"epoch": 1.25,
"learning_rate": 0.0001536694050173242,
"loss": 0.1411,
"step": 860
},
{
"epoch": 1.27,
"learning_rate": 0.00014842028900405421,
"loss": 0.1426,
"step": 870
},
{
"epoch": 1.28,
"learning_rate": 0.00014322427541311347,
"loss": 0.1455,
"step": 880
},
{
"epoch": 1.3,
"learning_rate": 0.0001380840805439031,
"loss": 0.1485,
"step": 890
},
{
"epoch": 1.31,
"learning_rate": 0.00013300239151569252,
"loss": 0.152,
"step": 900
},
{
"epoch": 1.32,
"learning_rate": 0.00012798186486288483,
"loss": 0.145,
"step": 910
},
{
"epoch": 1.34,
"learning_rate": 0.0001230251251462708,
"loss": 0.1311,
"step": 920
},
{
"epoch": 1.35,
"learning_rate": 0.00011813476358099823,
"loss": 0.1411,
"step": 930
},
{
"epoch": 1.37,
"learning_rate": 0.0001133133366819717,
"loss": 0.1384,
"step": 940
},
{
"epoch": 1.38,
"learning_rate": 0.00010856336492739407,
"loss": 0.1455,
"step": 950
},
{
"epoch": 1.4,
"learning_rate": 0.00010388733144114604,
"loss": 0.1307,
"step": 960
},
{
"epoch": 1.41,
"learning_rate": 9.928768069469313e-05,
"loss": 0.1404,
"step": 970
},
{
"epoch": 1.43,
"learning_rate": 9.476681722919939e-05,
"loss": 0.1333,
"step": 980
},
{
"epoch": 1.44,
"learning_rate": 9.032710439851444e-05,
"loss": 0.144,
"step": 990
},
{
"epoch": 1.46,
"learning_rate": 8.597086313369271e-05,
"loss": 0.1499,
"step": 1000
},
{
"epoch": 1.47,
"learning_rate": 8.170037072968967e-05,
"loss": 0.1471,
"step": 1010
},
{
"epoch": 1.48,
"learning_rate": 7.751785965486893e-05,
"loss": 0.1312,
"step": 1020
},
{
"epoch": 1.5,
"learning_rate": 7.342551638394385e-05,
"loss": 0.1466,
"step": 1030
},
{
"epoch": 1.51,
"learning_rate": 6.942548025496312e-05,
"loss": 0.147,
"step": 1040
},
{
"epoch": 1.53,
"learning_rate": 6.551984235093692e-05,
"loss": 0.1375,
"step": 1050
},
{
"epoch": 1.54,
"learning_rate": 6.171064440669014e-05,
"loss": 0.1398,
"step": 1060
},
{
"epoch": 1.56,
"learning_rate": 5.7999877741512744e-05,
"loss": 0.1337,
"step": 1070
},
{
"epoch": 1.57,
"learning_rate": 5.438948221816559e-05,
"loss": 0.1351,
"step": 1080
},
{
"epoch": 1.59,
"learning_rate": 5.088134522878601e-05,
"loss": 0.1417,
"step": 1090
},
{
"epoch": 1.6,
"learning_rate": 4.74773007082237e-05,
"loss": 0.14,
"step": 1100
},
{
"epoch": 1.62,
"learning_rate": 4.417912817532133e-05,
"loss": 0.1423,
"step": 1110
},
{
"epoch": 1.63,
"learning_rate": 4.098855180264285e-05,
"loss": 0.1327,
"step": 1120
},
{
"epoch": 1.64,
"learning_rate": 3.7907239515134697e-05,
"loss": 0.1405,
"step": 1130
},
{
"epoch": 1.66,
"learning_rate": 3.493680211819103e-05,
"loss": 0.1444,
"step": 1140
},
{
"epoch": 1.67,
"learning_rate": 3.207879245557976e-05,
"loss": 0.1421,
"step": 1150
},
{
"epoch": 1.69,
"learning_rate": 2.933470459766821e-05,
"loss": 0.1389,
"step": 1160
},
{
"epoch": 1.7,
"learning_rate": 2.6705973060374117e-05,
"loss": 0.1457,
"step": 1170
},
{
"epoch": 1.72,
"learning_rate": 2.4193972055249343e-05,
"loss": 0.1451,
"step": 1180
},
{
"epoch": 1.73,
"learning_rate": 2.180001477108867e-05,
"loss": 0.1343,
"step": 1190
},
{
"epoch": 1.75,
"learning_rate": 1.9525352687439546e-05,
"loss": 0.1267,
"step": 1200
},
{
"epoch": 1.76,
"learning_rate": 1.737117492037091e-05,
"loss": 0.1364,
"step": 1210
},
{
"epoch": 1.78,
"learning_rate": 1.533860760084374e-05,
"loss": 0.1511,
"step": 1220
},
{
"epoch": 1.79,
"learning_rate": 1.3428713286008004e-05,
"loss": 0.1418,
"step": 1230
},
{
"epoch": 1.8,
"learning_rate": 1.1642490403733995e-05,
"loss": 0.1403,
"step": 1240
},
{
"epoch": 1.82,
"learning_rate": 9.980872730667972e-06,
"loss": 0.1433,
"step": 1250
},
{
"epoch": 1.83,
"learning_rate": 8.444728904085736e-06,
"loss": 0.1491,
"step": 1260
},
{
"epoch": 1.85,
"learning_rate": 7.0348619677982066e-06,
"loss": 0.1332,
"step": 1270
},
{
"epoch": 1.86,
"learning_rate": 5.752008952347648e-06,
"loss": 0.1351,
"step": 1280
},
{
"epoch": 1.88,
"learning_rate": 4.596840489713095e-06,
"loss": 0.1471,
"step": 1290
},
{
"epoch": 1.89,
"learning_rate": 3.5699604627266734e-06,
"loss": 0.1572,
"step": 1300
},
{
"epoch": 1.91,
"learning_rate": 2.6719056893842463e-06,
"loss": 0.1436,
"step": 1310
},
{
"epoch": 1.92,
"learning_rate": 1.9031456422151373e-06,
"loss": 0.1482,
"step": 1320
},
{
"epoch": 1.94,
"learning_rate": 1.2640822028578414e-06,
"loss": 0.1386,
"step": 1330
},
{
"epoch": 1.95,
"learning_rate": 7.550494519699968e-07,
"loss": 0.1294,
"step": 1340
},
{
"epoch": 1.97,
"learning_rate": 3.7631349458230877e-07,
"loss": 0.1439,
"step": 1350
},
{
"epoch": 1.98,
"learning_rate": 1.280723209880208e-07,
"loss": 0.135,
"step": 1360
},
{
"epoch": 1.99,
"learning_rate": 1.0455703240069836e-08,
"loss": 0.1345,
"step": 1370
},
{
"epoch": 2.0,
"step": 1374,
"total_flos": 3.2608758262451405e+18,
"train_loss": 0.1525881653095784,
"train_runtime": 23876.5124,
"train_samples_per_second": 3.681,
"train_steps_per_second": 0.058
}
],
"logging_steps": 10,
"max_steps": 1374,
"num_train_epochs": 2,
"save_steps": 150,
"total_flos": 3.2608758262451405e+18,
"trial_name": null,
"trial_params": null
}