AmelieSchreiber's picture
Rename trainer_state (5).json to trainer_state.json
5ee6df2
raw
history blame
18.4 kB
{
"best_metric": 0.3476562916154915,
"best_model_checkpoint": "esm2_t12_35M-lora-binding-sites_2023-09-11_16-28-57/checkpoint-28970",
"epoch": 1.0,
"eval_steps": 500,
"global_step": 28970,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.01,
"learning_rate": 0.0005701554508678478,
"loss": 0.4954,
"step": 200
},
{
"epoch": 0.01,
"learning_rate": 0.000570151359481901,
"loss": 0.3627,
"step": 400
},
{
"epoch": 0.02,
"learning_rate": 0.0005701445314265366,
"loss": 0.325,
"step": 600
},
{
"epoch": 0.03,
"learning_rate": 0.0005701349667673032,
"loss": 0.2797,
"step": 800
},
{
"epoch": 0.03,
"learning_rate": 0.0005701226655960202,
"loss": 0.2708,
"step": 1000
},
{
"epoch": 0.04,
"learning_rate": 0.0005701076280307777,
"loss": 0.2547,
"step": 1200
},
{
"epoch": 0.05,
"learning_rate": 0.0005700898542159346,
"loss": 0.2395,
"step": 1400
},
{
"epoch": 0.06,
"learning_rate": 0.0005700693443221178,
"loss": 0.2348,
"step": 1600
},
{
"epoch": 0.06,
"learning_rate": 0.0005700460985462198,
"loss": 0.218,
"step": 1800
},
{
"epoch": 0.07,
"learning_rate": 0.0005700202538231217,
"loss": 0.2284,
"step": 2000
},
{
"epoch": 0.08,
"learning_rate": 0.000569991550655178,
"loss": 0.2307,
"step": 2200
},
{
"epoch": 0.08,
"learning_rate": 0.000569960112351964,
"loss": 0.22,
"step": 2400
},
{
"epoch": 0.09,
"learning_rate": 0.000569925939215284,
"loss": 0.2117,
"step": 2600
},
{
"epoch": 0.1,
"learning_rate": 0.0005698890315731962,
"loss": 0.2246,
"step": 2800
},
{
"epoch": 0.1,
"learning_rate": 0.0005698493897800102,
"loss": 0.2392,
"step": 3000
},
{
"epoch": 0.11,
"learning_rate": 0.0005698070142162829,
"loss": 0.2078,
"step": 3200
},
{
"epoch": 0.12,
"learning_rate": 0.0005697619052888148,
"loss": 0.2098,
"step": 3400
},
{
"epoch": 0.12,
"learning_rate": 0.0005697140634306472,
"loss": 0.1919,
"step": 3600
},
{
"epoch": 0.13,
"learning_rate": 0.0005696634891010563,
"loss": 0.1957,
"step": 3800
},
{
"epoch": 0.14,
"learning_rate": 0.0005696101827855504,
"loss": 0.2156,
"step": 4000
},
{
"epoch": 0.14,
"learning_rate": 0.0005695544319784758,
"loss": 0.1983,
"step": 4200
},
{
"epoch": 0.15,
"learning_rate": 0.0005694956769058657,
"loss": 0.2104,
"step": 4400
},
{
"epoch": 0.16,
"learning_rate": 0.0005694341914583195,
"loss": 0.1789,
"step": 4600
},
{
"epoch": 0.17,
"learning_rate": 0.0005693699762260905,
"loss": 0.1944,
"step": 4800
},
{
"epoch": 0.17,
"learning_rate": 0.0005693030318256384,
"loss": 0.1895,
"step": 5000
},
{
"epoch": 0.18,
"learning_rate": 0.0005692333588996219,
"loss": 0.2007,
"step": 5200
},
{
"epoch": 0.19,
"learning_rate": 0.0005691609581168934,
"loss": 0.1852,
"step": 5400
},
{
"epoch": 0.19,
"learning_rate": 0.0005690858301724929,
"loss": 0.1728,
"step": 5600
},
{
"epoch": 0.2,
"learning_rate": 0.0005690079757876402,
"loss": 0.2076,
"step": 5800
},
{
"epoch": 0.21,
"learning_rate": 0.0005689273957097291,
"loss": 0.1844,
"step": 6000
},
{
"epoch": 0.21,
"learning_rate": 0.0005688445140142318,
"loss": 0.173,
"step": 6200
},
{
"epoch": 0.22,
"learning_rate": 0.0005687584985156089,
"loss": 0.189,
"step": 6400
},
{
"epoch": 0.23,
"learning_rate": 0.0005686697597188824,
"loss": 0.1728,
"step": 6600
},
{
"epoch": 0.23,
"learning_rate": 0.0005685782984759349,
"loss": 0.1764,
"step": 6800
},
{
"epoch": 0.24,
"learning_rate": 0.0005684841156647846,
"loss": 0.1817,
"step": 7000
},
{
"epoch": 0.25,
"learning_rate": 0.0005683872121895759,
"loss": 0.184,
"step": 7200
},
{
"epoch": 0.26,
"learning_rate": 0.000568287588980572,
"loss": 0.1611,
"step": 7400
},
{
"epoch": 0.26,
"learning_rate": 0.0005681852469941448,
"loss": 0.1782,
"step": 7600
},
{
"epoch": 0.27,
"learning_rate": 0.000568080187212766,
"loss": 0.1674,
"step": 7800
},
{
"epoch": 0.28,
"learning_rate": 0.0005679724106449985,
"loss": 0.1592,
"step": 8000
},
{
"epoch": 0.28,
"learning_rate": 0.0005678619183254852,
"loss": 0.188,
"step": 8200
},
{
"epoch": 0.29,
"learning_rate": 0.0005677487113149407,
"loss": 0.1724,
"step": 8400
},
{
"epoch": 0.3,
"learning_rate": 0.00056763279070014,
"loss": 0.1734,
"step": 8600
},
{
"epoch": 0.3,
"learning_rate": 0.0005675141575939082,
"loss": 0.1802,
"step": 8800
},
{
"epoch": 0.31,
"learning_rate": 0.0005673934265999777,
"loss": 0.1735,
"step": 9000
},
{
"epoch": 0.32,
"learning_rate": 0.0005672693855015051,
"loss": 0.1768,
"step": 9200
},
{
"epoch": 0.32,
"learning_rate": 0.0005671426354002519,
"loss": 0.1759,
"step": 9400
},
{
"epoch": 0.33,
"learning_rate": 0.0005670131775130054,
"loss": 0.1646,
"step": 9600
},
{
"epoch": 0.34,
"learning_rate": 0.0005668810130825471,
"loss": 0.1684,
"step": 9800
},
{
"epoch": 0.35,
"learning_rate": 0.0005667461433776413,
"loss": 0.1636,
"step": 10000
},
{
"epoch": 0.35,
"learning_rate": 0.0005666085696930225,
"loss": 0.1492,
"step": 10200
},
{
"epoch": 0.36,
"learning_rate": 0.0005664682933493831,
"loss": 0.1636,
"step": 10400
},
{
"epoch": 0.37,
"learning_rate": 0.0005663253156933608,
"loss": 0.1647,
"step": 10600
},
{
"epoch": 0.37,
"learning_rate": 0.0005661796380975255,
"loss": 0.181,
"step": 10800
},
{
"epoch": 0.38,
"learning_rate": 0.0005660320105513283,
"loss": 0.1708,
"step": 11000
},
{
"epoch": 0.39,
"learning_rate": 0.0005658809507792387,
"loss": 0.1702,
"step": 11200
},
{
"epoch": 0.39,
"learning_rate": 0.0005657271953331912,
"loss": 0.1617,
"step": 11400
},
{
"epoch": 0.4,
"learning_rate": 0.000565570745689221,
"loss": 0.1722,
"step": 11600
},
{
"epoch": 0.41,
"learning_rate": 0.000565411603349228,
"loss": 0.1702,
"step": 11800
},
{
"epoch": 0.41,
"learning_rate": 0.0005652497698409615,
"loss": 0.1543,
"step": 12000
},
{
"epoch": 0.42,
"learning_rate": 0.0005650852467180052,
"loss": 0.1654,
"step": 12200
},
{
"epoch": 0.43,
"learning_rate": 0.0005649180355597633,
"loss": 0.1676,
"step": 12400
},
{
"epoch": 0.43,
"learning_rate": 0.000564748137971445,
"loss": 0.16,
"step": 12600
},
{
"epoch": 0.44,
"learning_rate": 0.0005645755555840486,
"loss": 0.1627,
"step": 12800
},
{
"epoch": 0.45,
"learning_rate": 0.0005644002900543462,
"loss": 0.1712,
"step": 13000
},
{
"epoch": 0.46,
"learning_rate": 0.0005642232394671313,
"loss": 0.1603,
"step": 13200
},
{
"epoch": 0.46,
"learning_rate": 0.0005640426261206144,
"loss": 0.1648,
"step": 13400
},
{
"epoch": 0.47,
"learning_rate": 0.0005638593347478565,
"loss": 0.1608,
"step": 13600
},
{
"epoch": 0.48,
"learning_rate": 0.0005636733671084348,
"loss": 0.162,
"step": 13800
},
{
"epoch": 0.48,
"learning_rate": 0.0005634847249876185,
"loss": 0.1516,
"step": 14000
},
{
"epoch": 0.49,
"learning_rate": 0.0005632934101963515,
"loss": 0.1638,
"step": 14200
},
{
"epoch": 0.5,
"learning_rate": 0.000563099424571235,
"loss": 0.1691,
"step": 14400
},
{
"epoch": 0.5,
"learning_rate": 0.0005629027699745098,
"loss": 0.149,
"step": 14600
},
{
"epoch": 0.51,
"learning_rate": 0.0005627034482940388,
"loss": 0.1713,
"step": 14800
},
{
"epoch": 0.52,
"learning_rate": 0.0005625014614432885,
"loss": 0.1615,
"step": 15000
},
{
"epoch": 0.52,
"learning_rate": 0.0005622978412332689,
"loss": 0.1618,
"step": 15200
},
{
"epoch": 0.53,
"learning_rate": 0.0005620905431860859,
"loss": 0.1695,
"step": 15400
},
{
"epoch": 0.54,
"learning_rate": 0.0005618805858524459,
"loss": 0.1575,
"step": 15600
},
{
"epoch": 0.55,
"learning_rate": 0.0005616679712479168,
"loss": 0.1494,
"step": 15800
},
{
"epoch": 0.55,
"learning_rate": 0.0005614527014135753,
"loss": 0.1441,
"step": 16000
},
{
"epoch": 0.56,
"learning_rate": 0.0005612347784159886,
"loss": 0.1554,
"step": 16200
},
{
"epoch": 0.57,
"learning_rate": 0.000561014204347194,
"loss": 0.1597,
"step": 16400
},
{
"epoch": 0.57,
"learning_rate": 0.0005607909813246783,
"loss": 0.1603,
"step": 16600
},
{
"epoch": 0.58,
"learning_rate": 0.0005605651114913586,
"loss": 0.1566,
"step": 16800
},
{
"epoch": 0.59,
"learning_rate": 0.0005603365970155604,
"loss": 0.148,
"step": 17000
},
{
"epoch": 0.59,
"learning_rate": 0.0005601054400909981,
"loss": 0.153,
"step": 17200
},
{
"epoch": 0.6,
"learning_rate": 0.0005598728184863933,
"loss": 0.1551,
"step": 17400
},
{
"epoch": 0.61,
"learning_rate": 0.000559636396531194,
"loss": 0.1808,
"step": 17600
},
{
"epoch": 0.61,
"learning_rate": 0.0005593973388490791,
"loss": 0.1537,
"step": 17800
},
{
"epoch": 0.62,
"learning_rate": 0.0005591556477349764,
"loss": 0.1488,
"step": 18000
},
{
"epoch": 0.63,
"learning_rate": 0.0005589113255090943,
"loss": 0.1632,
"step": 18200
},
{
"epoch": 0.64,
"learning_rate": 0.0005586643745168998,
"loss": 0.1595,
"step": 18400
},
{
"epoch": 0.64,
"learning_rate": 0.0005584147971290952,
"loss": 0.1692,
"step": 18600
},
{
"epoch": 0.65,
"learning_rate": 0.0005581625957415966,
"loss": 0.1454,
"step": 18800
},
{
"epoch": 0.66,
"learning_rate": 0.0005579077727755101,
"loss": 0.1608,
"step": 19000
},
{
"epoch": 0.66,
"learning_rate": 0.0005576503306771081,
"loss": 0.1506,
"step": 19200
},
{
"epoch": 0.67,
"learning_rate": 0.0005573915787164281,
"loss": 0.1639,
"step": 19400
},
{
"epoch": 0.68,
"learning_rate": 0.000557128918857334,
"loss": 0.1463,
"step": 19600
},
{
"epoch": 0.68,
"learning_rate": 0.0005568636473428375,
"loss": 0.159,
"step": 19800
},
{
"epoch": 0.69,
"learning_rate": 0.0005565957667195164,
"loss": 0.1792,
"step": 20000
},
{
"epoch": 0.7,
"learning_rate": 0.0005563252795589956,
"loss": 0.1512,
"step": 20200
},
{
"epoch": 0.7,
"learning_rate": 0.0005560521884579225,
"loss": 0.1604,
"step": 20400
},
{
"epoch": 0.71,
"learning_rate": 0.000555776496037942,
"loss": 0.1563,
"step": 20600
},
{
"epoch": 0.72,
"learning_rate": 0.0005554982049456713,
"loss": 0.1598,
"step": 20800
},
{
"epoch": 0.72,
"learning_rate": 0.0005552173178526746,
"loss": 0.1429,
"step": 21000
},
{
"epoch": 0.73,
"learning_rate": 0.0005549338374554378,
"loss": 0.1544,
"step": 21200
},
{
"epoch": 0.74,
"learning_rate": 0.0005546477664753415,
"loss": 0.1435,
"step": 21400
},
{
"epoch": 0.75,
"learning_rate": 0.00055436055738539,
"loss": 0.1562,
"step": 21600
},
{
"epoch": 0.75,
"learning_rate": 0.0005540693264215625,
"loss": 0.1501,
"step": 21800
},
{
"epoch": 0.76,
"learning_rate": 0.0005537755131740878,
"loss": 0.1511,
"step": 22000
},
{
"epoch": 0.77,
"learning_rate": 0.0005534791204635411,
"loss": 0.1456,
"step": 22200
},
{
"epoch": 0.77,
"learning_rate": 0.0005531801511352604,
"loss": 0.1507,
"step": 22400
},
{
"epoch": 0.78,
"learning_rate": 0.0005528786080593183,
"loss": 0.1477,
"step": 22600
},
{
"epoch": 0.79,
"learning_rate": 0.000552574494130496,
"loss": 0.1507,
"step": 22800
},
{
"epoch": 0.79,
"learning_rate": 0.000552267812268254,
"loss": 0.1494,
"step": 23000
},
{
"epoch": 0.8,
"learning_rate": 0.0005519585654167048,
"loss": 0.1489,
"step": 23200
},
{
"epoch": 0.81,
"learning_rate": 0.0005516467565445848,
"loss": 0.1495,
"step": 23400
},
{
"epoch": 0.81,
"learning_rate": 0.0005513323886452253,
"loss": 0.1467,
"step": 23600
},
{
"epoch": 0.82,
"learning_rate": 0.0005510154647365238,
"loss": 0.1465,
"step": 23800
},
{
"epoch": 0.83,
"learning_rate": 0.0005506975915907354,
"loss": 0.1725,
"step": 24000
},
{
"epoch": 0.84,
"learning_rate": 0.0005503755775569938,
"loss": 0.1604,
"step": 24200
},
{
"epoch": 0.84,
"learning_rate": 0.0005500510166991929,
"loss": 0.1492,
"step": 24400
},
{
"epoch": 0.85,
"learning_rate": 0.0005497239121330815,
"loss": 0.1446,
"step": 24600
},
{
"epoch": 0.86,
"learning_rate": 0.0005493942669988278,
"loss": 0.1492,
"step": 24800
},
{
"epoch": 0.86,
"learning_rate": 0.0005490620844609896,
"loss": 0.152,
"step": 25000
},
{
"epoch": 0.87,
"learning_rate": 0.0005487273677084831,
"loss": 0.1601,
"step": 25200
},
{
"epoch": 0.88,
"learning_rate": 0.0005483901199545525,
"loss": 0.1432,
"step": 25400
},
{
"epoch": 0.88,
"learning_rate": 0.0005480503444367399,
"loss": 0.153,
"step": 25600
},
{
"epoch": 0.89,
"learning_rate": 0.0005477080444168533,
"loss": 0.1446,
"step": 25800
},
{
"epoch": 0.9,
"learning_rate": 0.0005473649535531743,
"loss": 0.1543,
"step": 26000
},
{
"epoch": 0.9,
"learning_rate": 0.0005470176269927267,
"loss": 0.1652,
"step": 26200
},
{
"epoch": 0.91,
"learning_rate": 0.0005466677858441803,
"loss": 0.1463,
"step": 26400
},
{
"epoch": 0.92,
"learning_rate": 0.0005463154334659722,
"loss": 0.152,
"step": 26600
},
{
"epoch": 0.93,
"learning_rate": 0.0005459605732406469,
"loss": 0.1572,
"step": 26800
},
{
"epoch": 0.93,
"learning_rate": 0.0005456032085748239,
"loss": 0.1439,
"step": 27000
},
{
"epoch": 0.94,
"learning_rate": 0.0005452433428991655,
"loss": 0.1483,
"step": 27200
},
{
"epoch": 0.95,
"learning_rate": 0.000544880979668343,
"loss": 0.1633,
"step": 27400
},
{
"epoch": 0.95,
"learning_rate": 0.0005445161223610037,
"loss": 0.1559,
"step": 27600
},
{
"epoch": 0.96,
"learning_rate": 0.0005441487744797385,
"loss": 0.1582,
"step": 27800
},
{
"epoch": 0.97,
"learning_rate": 0.000543778939551047,
"loss": 0.1607,
"step": 28000
},
{
"epoch": 0.97,
"learning_rate": 0.0005434084888892294,
"loss": 0.1444,
"step": 28200
},
{
"epoch": 0.98,
"learning_rate": 0.0005430337029313361,
"loss": 0.1411,
"step": 28400
},
{
"epoch": 0.99,
"learning_rate": 0.0005426564406305822,
"loss": 0.145,
"step": 28600
},
{
"epoch": 0.99,
"learning_rate": 0.0005422767056086448,
"loss": 0.1543,
"step": 28800
},
{
"epoch": 1.0,
"eval_accuracy": 0.9266715807717144,
"eval_auc": 0.8547374969101048,
"eval_f1": 0.3476562916154915,
"eval_loss": 0.36462366580963135,
"eval_precision": 0.22375778821030992,
"eval_recall": 0.7790042059793111,
"eval_runtime": 1778.9025,
"eval_samples_per_second": 24.978,
"eval_steps_per_second": 4.163,
"step": 28970
}
],
"logging_steps": 200,
"max_steps": 202790,
"num_train_epochs": 7,
"save_steps": 500,
"total_flos": 3.4755022197e+16,
"trial_name": null,
"trial_params": null
}