XLM / trainer_state.json
spraveenkumar1318's picture
First Commit For XLM-Language Detection Model
4a73888
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 2.6260504201680672,
"global_step": 2500,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.01,
"learning_rate": 2.0000000000000003e-06,
"loss": 4.6151,
"step": 10
},
{
"epoch": 0.02,
"learning_rate": 4.000000000000001e-06,
"loss": 4.6009,
"step": 20
},
{
"epoch": 0.03,
"learning_rate": 6e-06,
"loss": 4.5892,
"step": 30
},
{
"epoch": 0.04,
"learning_rate": 8.000000000000001e-06,
"loss": 4.4933,
"step": 40
},
{
"epoch": 0.05,
"learning_rate": 1e-05,
"loss": 4.4838,
"step": 50
},
{
"epoch": 0.06,
"learning_rate": 1.2e-05,
"loss": 4.0367,
"step": 60
},
{
"epoch": 0.07,
"learning_rate": 1.4e-05,
"loss": 3.6247,
"step": 70
},
{
"epoch": 0.08,
"learning_rate": 1.6000000000000003e-05,
"loss": 3.329,
"step": 80
},
{
"epoch": 0.09,
"learning_rate": 1.8e-05,
"loss": 3.1007,
"step": 90
},
{
"epoch": 0.11,
"learning_rate": 2e-05,
"loss": 2.8089,
"step": 100
},
{
"epoch": 0.12,
"learning_rate": 1.992743105950653e-05,
"loss": 2.5354,
"step": 110
},
{
"epoch": 0.13,
"learning_rate": 1.9854862119013064e-05,
"loss": 2.2403,
"step": 120
},
{
"epoch": 0.14,
"learning_rate": 1.9782293178519596e-05,
"loss": 2.7885,
"step": 130
},
{
"epoch": 0.15,
"learning_rate": 1.9709724238026125e-05,
"loss": 2.4836,
"step": 140
},
{
"epoch": 0.16,
"learning_rate": 1.9637155297532658e-05,
"loss": 2.3569,
"step": 150
},
{
"epoch": 0.17,
"learning_rate": 1.9564586357039187e-05,
"loss": 2.4299,
"step": 160
},
{
"epoch": 0.18,
"learning_rate": 1.949201741654572e-05,
"loss": 2.0131,
"step": 170
},
{
"epoch": 0.19,
"learning_rate": 1.9419448476052253e-05,
"loss": 1.8533,
"step": 180
},
{
"epoch": 0.2,
"learning_rate": 1.9346879535558782e-05,
"loss": 2.0193,
"step": 190
},
{
"epoch": 0.21,
"learning_rate": 1.9274310595065315e-05,
"loss": 2.0059,
"step": 200
},
{
"epoch": 0.22,
"learning_rate": 1.9201741654571844e-05,
"loss": 1.6821,
"step": 210
},
{
"epoch": 0.23,
"learning_rate": 1.9129172714078376e-05,
"loss": 1.8958,
"step": 220
},
{
"epoch": 0.24,
"learning_rate": 1.905660377358491e-05,
"loss": 1.9811,
"step": 230
},
{
"epoch": 0.25,
"learning_rate": 1.898403483309144e-05,
"loss": 2.0177,
"step": 240
},
{
"epoch": 0.26,
"learning_rate": 1.8911465892597968e-05,
"loss": 1.9885,
"step": 250
},
{
"epoch": 0.27,
"learning_rate": 1.88388969521045e-05,
"loss": 1.8754,
"step": 260
},
{
"epoch": 0.28,
"learning_rate": 1.8766328011611033e-05,
"loss": 1.5953,
"step": 270
},
{
"epoch": 0.29,
"learning_rate": 1.8693759071117562e-05,
"loss": 1.9287,
"step": 280
},
{
"epoch": 0.3,
"learning_rate": 1.8621190130624095e-05,
"loss": 1.7173,
"step": 290
},
{
"epoch": 0.32,
"learning_rate": 1.8548621190130624e-05,
"loss": 1.8167,
"step": 300
},
{
"epoch": 0.33,
"learning_rate": 1.8476052249637157e-05,
"loss": 1.3269,
"step": 310
},
{
"epoch": 0.34,
"learning_rate": 1.840348330914369e-05,
"loss": 1.5738,
"step": 320
},
{
"epoch": 0.35,
"learning_rate": 1.833091436865022e-05,
"loss": 1.5026,
"step": 330
},
{
"epoch": 0.36,
"learning_rate": 1.825834542815675e-05,
"loss": 1.6312,
"step": 340
},
{
"epoch": 0.37,
"learning_rate": 1.8185776487663284e-05,
"loss": 1.8379,
"step": 350
},
{
"epoch": 0.38,
"learning_rate": 1.8113207547169813e-05,
"loss": 1.242,
"step": 360
},
{
"epoch": 0.39,
"learning_rate": 1.8040638606676342e-05,
"loss": 1.5145,
"step": 370
},
{
"epoch": 0.4,
"learning_rate": 1.7968069666182875e-05,
"loss": 1.326,
"step": 380
},
{
"epoch": 0.41,
"learning_rate": 1.7895500725689404e-05,
"loss": 1.2579,
"step": 390
},
{
"epoch": 0.42,
"learning_rate": 1.7822931785195937e-05,
"loss": 1.4427,
"step": 400
},
{
"epoch": 0.43,
"learning_rate": 1.775036284470247e-05,
"loss": 1.2246,
"step": 410
},
{
"epoch": 0.44,
"learning_rate": 1.7677793904209e-05,
"loss": 1.3649,
"step": 420
},
{
"epoch": 0.45,
"learning_rate": 1.760522496371553e-05,
"loss": 1.5865,
"step": 430
},
{
"epoch": 0.46,
"learning_rate": 1.7532656023222064e-05,
"loss": 1.0269,
"step": 440
},
{
"epoch": 0.47,
"learning_rate": 1.7460087082728593e-05,
"loss": 1.2287,
"step": 450
},
{
"epoch": 0.48,
"learning_rate": 1.7387518142235126e-05,
"loss": 1.231,
"step": 460
},
{
"epoch": 0.49,
"learning_rate": 1.7314949201741655e-05,
"loss": 1.4882,
"step": 470
},
{
"epoch": 0.5,
"learning_rate": 1.7242380261248185e-05,
"loss": 1.3311,
"step": 480
},
{
"epoch": 0.51,
"learning_rate": 1.716981132075472e-05,
"loss": 0.8074,
"step": 490
},
{
"epoch": 0.53,
"learning_rate": 1.709724238026125e-05,
"loss": 1.3885,
"step": 500
},
{
"epoch": 0.54,
"learning_rate": 1.702467343976778e-05,
"loss": 0.7269,
"step": 510
},
{
"epoch": 0.55,
"learning_rate": 1.6952104499274312e-05,
"loss": 1.0517,
"step": 520
},
{
"epoch": 0.56,
"learning_rate": 1.6879535558780844e-05,
"loss": 1.0979,
"step": 530
},
{
"epoch": 0.57,
"learning_rate": 1.6806966618287374e-05,
"loss": 1.2165,
"step": 540
},
{
"epoch": 0.58,
"learning_rate": 1.6734397677793906e-05,
"loss": 0.9271,
"step": 550
},
{
"epoch": 0.59,
"learning_rate": 1.6661828737300436e-05,
"loss": 1.1317,
"step": 560
},
{
"epoch": 0.6,
"learning_rate": 1.6589259796806968e-05,
"loss": 1.1018,
"step": 570
},
{
"epoch": 0.61,
"learning_rate": 1.65166908563135e-05,
"loss": 1.054,
"step": 580
},
{
"epoch": 0.62,
"learning_rate": 1.644412191582003e-05,
"loss": 1.0754,
"step": 590
},
{
"epoch": 0.63,
"learning_rate": 1.6371552975326563e-05,
"loss": 0.8159,
"step": 600
},
{
"epoch": 0.64,
"learning_rate": 1.6298984034833092e-05,
"loss": 0.929,
"step": 610
},
{
"epoch": 0.65,
"learning_rate": 1.6226415094339625e-05,
"loss": 1.1673,
"step": 620
},
{
"epoch": 0.66,
"learning_rate": 1.6153846153846154e-05,
"loss": 0.8993,
"step": 630
},
{
"epoch": 0.67,
"learning_rate": 1.6081277213352687e-05,
"loss": 0.8426,
"step": 640
},
{
"epoch": 0.68,
"learning_rate": 1.6008708272859216e-05,
"loss": 0.9685,
"step": 650
},
{
"epoch": 0.69,
"learning_rate": 1.593613933236575e-05,
"loss": 0.7475,
"step": 660
},
{
"epoch": 0.7,
"learning_rate": 1.586357039187228e-05,
"loss": 0.4813,
"step": 670
},
{
"epoch": 0.71,
"learning_rate": 1.579100145137881e-05,
"loss": 0.8771,
"step": 680
},
{
"epoch": 0.72,
"learning_rate": 1.5718432510885343e-05,
"loss": 0.8842,
"step": 690
},
{
"epoch": 0.74,
"learning_rate": 1.5645863570391872e-05,
"loss": 1.0122,
"step": 700
},
{
"epoch": 0.75,
"learning_rate": 1.5573294629898405e-05,
"loss": 0.6247,
"step": 710
},
{
"epoch": 0.76,
"learning_rate": 1.5500725689404938e-05,
"loss": 0.9389,
"step": 720
},
{
"epoch": 0.77,
"learning_rate": 1.5428156748911467e-05,
"loss": 0.3921,
"step": 730
},
{
"epoch": 0.78,
"learning_rate": 1.5355587808417996e-05,
"loss": 0.695,
"step": 740
},
{
"epoch": 0.79,
"learning_rate": 1.5283018867924532e-05,
"loss": 0.4541,
"step": 750
},
{
"epoch": 0.8,
"learning_rate": 1.5210449927431061e-05,
"loss": 0.6469,
"step": 760
},
{
"epoch": 0.81,
"learning_rate": 1.5137880986937592e-05,
"loss": 0.6391,
"step": 770
},
{
"epoch": 0.82,
"learning_rate": 1.5065312046444123e-05,
"loss": 0.6501,
"step": 780
},
{
"epoch": 0.83,
"learning_rate": 1.4992743105950653e-05,
"loss": 0.9943,
"step": 790
},
{
"epoch": 0.84,
"learning_rate": 1.4920174165457187e-05,
"loss": 0.5541,
"step": 800
},
{
"epoch": 0.85,
"learning_rate": 1.4847605224963716e-05,
"loss": 0.7708,
"step": 810
},
{
"epoch": 0.86,
"learning_rate": 1.4775036284470247e-05,
"loss": 0.9068,
"step": 820
},
{
"epoch": 0.87,
"learning_rate": 1.4702467343976778e-05,
"loss": 0.8202,
"step": 830
},
{
"epoch": 0.88,
"learning_rate": 1.462989840348331e-05,
"loss": 0.6628,
"step": 840
},
{
"epoch": 0.89,
"learning_rate": 1.4557329462989842e-05,
"loss": 0.768,
"step": 850
},
{
"epoch": 0.9,
"learning_rate": 1.4484760522496373e-05,
"loss": 0.829,
"step": 860
},
{
"epoch": 0.91,
"learning_rate": 1.4412191582002904e-05,
"loss": 0.9561,
"step": 870
},
{
"epoch": 0.92,
"learning_rate": 1.4339622641509435e-05,
"loss": 0.6783,
"step": 880
},
{
"epoch": 0.93,
"learning_rate": 1.4267053701015967e-05,
"loss": 0.7017,
"step": 890
},
{
"epoch": 0.95,
"learning_rate": 1.4194484760522498e-05,
"loss": 0.6462,
"step": 900
},
{
"epoch": 0.96,
"learning_rate": 1.4121915820029029e-05,
"loss": 0.648,
"step": 910
},
{
"epoch": 0.97,
"learning_rate": 1.4049346879535558e-05,
"loss": 0.4731,
"step": 920
},
{
"epoch": 0.98,
"learning_rate": 1.3976777939042093e-05,
"loss": 0.6257,
"step": 930
},
{
"epoch": 0.99,
"learning_rate": 1.3904208998548622e-05,
"loss": 0.4245,
"step": 940
},
{
"epoch": 1.0,
"learning_rate": 1.3831640058055153e-05,
"loss": 0.687,
"step": 950
},
{
"epoch": 1.0,
"eval_Accuracy": 0.9114854517611026,
"eval_F1": 0.8950475194731157,
"eval_loss": 0.5604398846626282,
"eval_runtime": 98.5377,
"eval_samples_per_second": 33.135,
"eval_steps_per_second": 2.08,
"step": 952
},
{
"epoch": 1.01,
"learning_rate": 1.3759071117561684e-05,
"loss": 0.3493,
"step": 960
},
{
"epoch": 1.02,
"learning_rate": 1.3686502177068215e-05,
"loss": 0.9263,
"step": 970
},
{
"epoch": 1.03,
"learning_rate": 1.3613933236574748e-05,
"loss": 0.4981,
"step": 980
},
{
"epoch": 1.04,
"learning_rate": 1.3541364296081278e-05,
"loss": 0.4574,
"step": 990
},
{
"epoch": 1.05,
"learning_rate": 1.346879535558781e-05,
"loss": 0.6115,
"step": 1000
},
{
"epoch": 1.06,
"learning_rate": 1.339622641509434e-05,
"loss": 0.5973,
"step": 1010
},
{
"epoch": 1.07,
"learning_rate": 1.3323657474600873e-05,
"loss": 0.4881,
"step": 1020
},
{
"epoch": 1.08,
"learning_rate": 1.3251088534107404e-05,
"loss": 0.4824,
"step": 1030
},
{
"epoch": 1.09,
"learning_rate": 1.3178519593613935e-05,
"loss": 0.7372,
"step": 1040
},
{
"epoch": 1.1,
"learning_rate": 1.3105950653120464e-05,
"loss": 0.7515,
"step": 1050
},
{
"epoch": 1.11,
"learning_rate": 1.3033381712626995e-05,
"loss": 0.446,
"step": 1060
},
{
"epoch": 1.12,
"learning_rate": 1.2960812772133528e-05,
"loss": 0.6326,
"step": 1070
},
{
"epoch": 1.13,
"learning_rate": 1.2888243831640059e-05,
"loss": 0.7661,
"step": 1080
},
{
"epoch": 1.14,
"learning_rate": 1.281567489114659e-05,
"loss": 0.4974,
"step": 1090
},
{
"epoch": 1.16,
"learning_rate": 1.274310595065312e-05,
"loss": 0.7276,
"step": 1100
},
{
"epoch": 1.17,
"learning_rate": 1.2670537010159653e-05,
"loss": 0.3897,
"step": 1110
},
{
"epoch": 1.18,
"learning_rate": 1.2597968069666184e-05,
"loss": 0.7384,
"step": 1120
},
{
"epoch": 1.19,
"learning_rate": 1.2525399129172715e-05,
"loss": 0.7007,
"step": 1130
},
{
"epoch": 1.2,
"learning_rate": 1.2452830188679246e-05,
"loss": 0.6739,
"step": 1140
},
{
"epoch": 1.21,
"learning_rate": 1.2380261248185777e-05,
"loss": 0.5027,
"step": 1150
},
{
"epoch": 1.22,
"learning_rate": 1.230769230769231e-05,
"loss": 0.5931,
"step": 1160
},
{
"epoch": 1.23,
"learning_rate": 1.223512336719884e-05,
"loss": 0.3967,
"step": 1170
},
{
"epoch": 1.24,
"learning_rate": 1.216255442670537e-05,
"loss": 0.5215,
"step": 1180
},
{
"epoch": 1.25,
"learning_rate": 1.2089985486211901e-05,
"loss": 0.5034,
"step": 1190
},
{
"epoch": 1.26,
"learning_rate": 1.2017416545718435e-05,
"loss": 0.4521,
"step": 1200
},
{
"epoch": 1.27,
"learning_rate": 1.1944847605224965e-05,
"loss": 0.255,
"step": 1210
},
{
"epoch": 1.28,
"learning_rate": 1.1872278664731495e-05,
"loss": 0.2349,
"step": 1220
},
{
"epoch": 1.29,
"learning_rate": 1.1799709724238026e-05,
"loss": 0.6059,
"step": 1230
},
{
"epoch": 1.3,
"learning_rate": 1.1727140783744557e-05,
"loss": 0.3443,
"step": 1240
},
{
"epoch": 1.31,
"learning_rate": 1.165457184325109e-05,
"loss": 0.3367,
"step": 1250
},
{
"epoch": 1.32,
"learning_rate": 1.1582002902757621e-05,
"loss": 0.4613,
"step": 1260
},
{
"epoch": 1.33,
"learning_rate": 1.1509433962264152e-05,
"loss": 0.3399,
"step": 1270
},
{
"epoch": 1.34,
"learning_rate": 1.1436865021770683e-05,
"loss": 0.5677,
"step": 1280
},
{
"epoch": 1.36,
"learning_rate": 1.1364296081277216e-05,
"loss": 0.8075,
"step": 1290
},
{
"epoch": 1.37,
"learning_rate": 1.1291727140783746e-05,
"loss": 0.4384,
"step": 1300
},
{
"epoch": 1.38,
"learning_rate": 1.1219158200290277e-05,
"loss": 0.3861,
"step": 1310
},
{
"epoch": 1.39,
"learning_rate": 1.1146589259796807e-05,
"loss": 0.1245,
"step": 1320
},
{
"epoch": 1.4,
"learning_rate": 1.1074020319303338e-05,
"loss": 0.6668,
"step": 1330
},
{
"epoch": 1.41,
"learning_rate": 1.100145137880987e-05,
"loss": 0.7036,
"step": 1340
},
{
"epoch": 1.42,
"learning_rate": 1.0928882438316401e-05,
"loss": 0.205,
"step": 1350
},
{
"epoch": 1.43,
"learning_rate": 1.0856313497822932e-05,
"loss": 0.588,
"step": 1360
},
{
"epoch": 1.44,
"learning_rate": 1.0783744557329463e-05,
"loss": 0.7293,
"step": 1370
},
{
"epoch": 1.45,
"learning_rate": 1.0711175616835996e-05,
"loss": 0.602,
"step": 1380
},
{
"epoch": 1.46,
"learning_rate": 1.0638606676342527e-05,
"loss": 0.3027,
"step": 1390
},
{
"epoch": 1.47,
"learning_rate": 1.0566037735849058e-05,
"loss": 0.4086,
"step": 1400
},
{
"epoch": 1.48,
"learning_rate": 1.0493468795355589e-05,
"loss": 0.4706,
"step": 1410
},
{
"epoch": 1.49,
"learning_rate": 1.0420899854862121e-05,
"loss": 0.2685,
"step": 1420
},
{
"epoch": 1.5,
"learning_rate": 1.0348330914368652e-05,
"loss": 0.4058,
"step": 1430
},
{
"epoch": 1.51,
"learning_rate": 1.0275761973875183e-05,
"loss": 0.4807,
"step": 1440
},
{
"epoch": 1.52,
"learning_rate": 1.0203193033381712e-05,
"loss": 0.3557,
"step": 1450
},
{
"epoch": 1.53,
"learning_rate": 1.0130624092888243e-05,
"loss": 0.3329,
"step": 1460
},
{
"epoch": 1.54,
"learning_rate": 1.0058055152394776e-05,
"loss": 0.2153,
"step": 1470
},
{
"epoch": 1.55,
"learning_rate": 9.985486211901307e-06,
"loss": 0.7515,
"step": 1480
},
{
"epoch": 1.57,
"learning_rate": 9.912917271407838e-06,
"loss": 0.3258,
"step": 1490
},
{
"epoch": 1.58,
"learning_rate": 9.84034833091437e-06,
"loss": 0.1792,
"step": 1500
},
{
"epoch": 1.59,
"learning_rate": 9.7677793904209e-06,
"loss": 0.5118,
"step": 1510
},
{
"epoch": 1.6,
"learning_rate": 9.69521044992743e-06,
"loss": 0.3737,
"step": 1520
},
{
"epoch": 1.61,
"learning_rate": 9.622641509433963e-06,
"loss": 0.3137,
"step": 1530
},
{
"epoch": 1.62,
"learning_rate": 9.550072568940494e-06,
"loss": 0.473,
"step": 1540
},
{
"epoch": 1.63,
"learning_rate": 9.477503628447025e-06,
"loss": 0.5268,
"step": 1550
},
{
"epoch": 1.64,
"learning_rate": 9.404934687953556e-06,
"loss": 0.4378,
"step": 1560
},
{
"epoch": 1.65,
"learning_rate": 9.332365747460089e-06,
"loss": 0.4031,
"step": 1570
},
{
"epoch": 1.66,
"learning_rate": 9.259796806966618e-06,
"loss": 0.7125,
"step": 1580
},
{
"epoch": 1.67,
"learning_rate": 9.187227866473151e-06,
"loss": 0.3404,
"step": 1590
},
{
"epoch": 1.68,
"learning_rate": 9.114658925979682e-06,
"loss": 0.4025,
"step": 1600
},
{
"epoch": 1.69,
"learning_rate": 9.042089985486213e-06,
"loss": 0.6217,
"step": 1610
},
{
"epoch": 1.7,
"learning_rate": 8.969521044992744e-06,
"loss": 0.4097,
"step": 1620
},
{
"epoch": 1.71,
"learning_rate": 8.896952104499275e-06,
"loss": 0.4337,
"step": 1630
},
{
"epoch": 1.72,
"learning_rate": 8.824383164005806e-06,
"loss": 0.2964,
"step": 1640
},
{
"epoch": 1.73,
"learning_rate": 8.751814223512337e-06,
"loss": 0.5013,
"step": 1650
},
{
"epoch": 1.74,
"learning_rate": 8.67924528301887e-06,
"loss": 0.6303,
"step": 1660
},
{
"epoch": 1.75,
"learning_rate": 8.6066763425254e-06,
"loss": 0.3938,
"step": 1670
},
{
"epoch": 1.76,
"learning_rate": 8.534107402031931e-06,
"loss": 0.1885,
"step": 1680
},
{
"epoch": 1.78,
"learning_rate": 8.461538461538462e-06,
"loss": 0.3159,
"step": 1690
},
{
"epoch": 1.79,
"learning_rate": 8.388969521044995e-06,
"loss": 0.5674,
"step": 1700
},
{
"epoch": 1.8,
"learning_rate": 8.316400580551524e-06,
"loss": 0.1875,
"step": 1710
},
{
"epoch": 1.81,
"learning_rate": 8.243831640058055e-06,
"loss": 0.4107,
"step": 1720
},
{
"epoch": 1.82,
"learning_rate": 8.171262699564588e-06,
"loss": 0.693,
"step": 1730
},
{
"epoch": 1.83,
"learning_rate": 8.098693759071119e-06,
"loss": 0.5109,
"step": 1740
},
{
"epoch": 1.84,
"learning_rate": 8.02612481857765e-06,
"loss": 0.3853,
"step": 1750
},
{
"epoch": 1.85,
"learning_rate": 7.95355587808418e-06,
"loss": 0.4673,
"step": 1760
},
{
"epoch": 1.86,
"learning_rate": 7.880986937590711e-06,
"loss": 0.2653,
"step": 1770
},
{
"epoch": 1.87,
"learning_rate": 7.808417997097242e-06,
"loss": 0.3816,
"step": 1780
},
{
"epoch": 1.88,
"learning_rate": 7.735849056603775e-06,
"loss": 0.2759,
"step": 1790
},
{
"epoch": 1.89,
"learning_rate": 7.663280116110306e-06,
"loss": 0.2267,
"step": 1800
},
{
"epoch": 1.9,
"learning_rate": 7.590711175616836e-06,
"loss": 0.3894,
"step": 1810
},
{
"epoch": 1.91,
"learning_rate": 7.518142235123368e-06,
"loss": 0.1902,
"step": 1820
},
{
"epoch": 1.92,
"learning_rate": 7.445573294629899e-06,
"loss": 0.3042,
"step": 1830
},
{
"epoch": 1.93,
"learning_rate": 7.373004354136431e-06,
"loss": 0.2981,
"step": 1840
},
{
"epoch": 1.94,
"learning_rate": 7.300435413642961e-06,
"loss": 0.2297,
"step": 1850
},
{
"epoch": 1.95,
"learning_rate": 7.227866473149493e-06,
"loss": 0.2528,
"step": 1860
},
{
"epoch": 1.96,
"learning_rate": 7.1552975326560235e-06,
"loss": 0.2361,
"step": 1870
},
{
"epoch": 1.97,
"learning_rate": 7.082728592162555e-06,
"loss": 0.327,
"step": 1880
},
{
"epoch": 1.99,
"learning_rate": 7.010159651669086e-06,
"loss": 0.2838,
"step": 1890
},
{
"epoch": 2.0,
"learning_rate": 6.937590711175617e-06,
"loss": 0.3027,
"step": 1900
},
{
"epoch": 2.0,
"eval_Accuracy": 0.935375191424196,
"eval_F1": 0.9231380335717158,
"eval_loss": 0.42070162296295166,
"eval_runtime": 98.699,
"eval_samples_per_second": 33.08,
"eval_steps_per_second": 2.077,
"step": 1904
},
{
"epoch": 2.01,
"learning_rate": 6.865021770682149e-06,
"loss": 0.3852,
"step": 1910
},
{
"epoch": 2.02,
"learning_rate": 6.792452830188679e-06,
"loss": 0.4178,
"step": 1920
},
{
"epoch": 2.03,
"learning_rate": 6.719883889695211e-06,
"loss": 0.4089,
"step": 1930
},
{
"epoch": 2.04,
"learning_rate": 6.647314949201742e-06,
"loss": 0.3711,
"step": 1940
},
{
"epoch": 2.05,
"learning_rate": 6.574746008708274e-06,
"loss": 0.4505,
"step": 1950
},
{
"epoch": 2.06,
"learning_rate": 6.502177068214805e-06,
"loss": 0.2162,
"step": 1960
},
{
"epoch": 2.07,
"learning_rate": 6.429608127721336e-06,
"loss": 0.2023,
"step": 1970
},
{
"epoch": 2.08,
"learning_rate": 6.357039187227867e-06,
"loss": 0.2912,
"step": 1980
},
{
"epoch": 2.09,
"learning_rate": 6.2844702467343975e-06,
"loss": 0.4556,
"step": 1990
},
{
"epoch": 2.1,
"learning_rate": 6.211901306240929e-06,
"loss": 0.3712,
"step": 2000
},
{
"epoch": 2.11,
"learning_rate": 6.13933236574746e-06,
"loss": 0.407,
"step": 2010
},
{
"epoch": 2.12,
"learning_rate": 6.066763425253992e-06,
"loss": 0.3238,
"step": 2020
},
{
"epoch": 2.13,
"learning_rate": 5.994194484760523e-06,
"loss": 0.118,
"step": 2030
},
{
"epoch": 2.14,
"learning_rate": 5.921625544267055e-06,
"loss": 0.1698,
"step": 2040
},
{
"epoch": 2.15,
"learning_rate": 5.849056603773585e-06,
"loss": 0.3557,
"step": 2050
},
{
"epoch": 2.16,
"learning_rate": 5.776487663280117e-06,
"loss": 0.2857,
"step": 2060
},
{
"epoch": 2.17,
"learning_rate": 5.703918722786648e-06,
"loss": 0.6379,
"step": 2070
},
{
"epoch": 2.18,
"learning_rate": 5.6313497822931794e-06,
"loss": 0.7017,
"step": 2080
},
{
"epoch": 2.2,
"learning_rate": 5.55878084179971e-06,
"loss": 0.2319,
"step": 2090
},
{
"epoch": 2.21,
"learning_rate": 5.486211901306241e-06,
"loss": 0.2963,
"step": 2100
},
{
"epoch": 2.22,
"learning_rate": 5.413642960812773e-06,
"loss": 0.284,
"step": 2110
},
{
"epoch": 2.23,
"learning_rate": 5.341074020319303e-06,
"loss": 0.2335,
"step": 2120
},
{
"epoch": 2.24,
"learning_rate": 5.268505079825835e-06,
"loss": 0.3575,
"step": 2130
},
{
"epoch": 2.25,
"learning_rate": 5.195936139332366e-06,
"loss": 0.3061,
"step": 2140
},
{
"epoch": 2.26,
"learning_rate": 5.123367198838898e-06,
"loss": 0.2509,
"step": 2150
},
{
"epoch": 2.27,
"learning_rate": 5.050798258345429e-06,
"loss": 0.669,
"step": 2160
},
{
"epoch": 2.28,
"learning_rate": 4.97822931785196e-06,
"loss": 0.3276,
"step": 2170
},
{
"epoch": 2.29,
"learning_rate": 4.905660377358491e-06,
"loss": 0.2792,
"step": 2180
},
{
"epoch": 2.3,
"learning_rate": 4.8330914368650224e-06,
"loss": 0.3574,
"step": 2190
},
{
"epoch": 2.31,
"learning_rate": 4.760522496371553e-06,
"loss": 0.1847,
"step": 2200
},
{
"epoch": 2.32,
"learning_rate": 4.687953555878084e-06,
"loss": 0.3664,
"step": 2210
},
{
"epoch": 2.33,
"learning_rate": 4.615384615384616e-06,
"loss": 0.313,
"step": 2220
},
{
"epoch": 2.34,
"learning_rate": 4.542815674891147e-06,
"loss": 0.4165,
"step": 2230
},
{
"epoch": 2.35,
"learning_rate": 4.470246734397678e-06,
"loss": 0.2627,
"step": 2240
},
{
"epoch": 2.36,
"learning_rate": 4.397677793904209e-06,
"loss": 0.4678,
"step": 2250
},
{
"epoch": 2.37,
"learning_rate": 4.325108853410741e-06,
"loss": 0.4254,
"step": 2260
},
{
"epoch": 2.38,
"learning_rate": 4.252539912917272e-06,
"loss": 0.2166,
"step": 2270
},
{
"epoch": 2.39,
"learning_rate": 4.179970972423803e-06,
"loss": 0.2313,
"step": 2280
},
{
"epoch": 2.41,
"learning_rate": 4.1074020319303345e-06,
"loss": 0.2503,
"step": 2290
},
{
"epoch": 2.42,
"learning_rate": 4.0348330914368655e-06,
"loss": 0.2127,
"step": 2300
},
{
"epoch": 2.43,
"learning_rate": 3.962264150943396e-06,
"loss": 0.1339,
"step": 2310
},
{
"epoch": 2.44,
"learning_rate": 3.889695210449927e-06,
"loss": 0.1467,
"step": 2320
},
{
"epoch": 2.45,
"learning_rate": 3.817126269956458e-06,
"loss": 0.3517,
"step": 2330
},
{
"epoch": 2.46,
"learning_rate": 3.74455732946299e-06,
"loss": 0.1513,
"step": 2340
},
{
"epoch": 2.47,
"learning_rate": 3.671988388969521e-06,
"loss": 0.1561,
"step": 2350
},
{
"epoch": 2.48,
"learning_rate": 3.5994194484760525e-06,
"loss": 0.2388,
"step": 2360
},
{
"epoch": 2.49,
"learning_rate": 3.526850507982584e-06,
"loss": 0.5018,
"step": 2370
},
{
"epoch": 2.5,
"learning_rate": 3.454281567489115e-06,
"loss": 0.3328,
"step": 2380
},
{
"epoch": 2.51,
"learning_rate": 3.381712626995646e-06,
"loss": 0.4347,
"step": 2390
},
{
"epoch": 2.52,
"learning_rate": 3.3091436865021775e-06,
"loss": 0.3993,
"step": 2400
},
{
"epoch": 2.53,
"learning_rate": 3.236574746008709e-06,
"loss": 0.4217,
"step": 2410
},
{
"epoch": 2.54,
"learning_rate": 3.1640058055152394e-06,
"loss": 0.651,
"step": 2420
},
{
"epoch": 2.55,
"learning_rate": 3.091436865021771e-06,
"loss": 0.3912,
"step": 2430
},
{
"epoch": 2.56,
"learning_rate": 3.018867924528302e-06,
"loss": 0.2198,
"step": 2440
},
{
"epoch": 2.57,
"learning_rate": 2.946298984034833e-06,
"loss": 0.1841,
"step": 2450
},
{
"epoch": 2.58,
"learning_rate": 2.8737300435413645e-06,
"loss": 0.2908,
"step": 2460
},
{
"epoch": 2.59,
"learning_rate": 2.801161103047896e-06,
"loss": 0.2179,
"step": 2470
},
{
"epoch": 2.61,
"learning_rate": 2.728592162554427e-06,
"loss": 0.1909,
"step": 2480
},
{
"epoch": 2.62,
"learning_rate": 2.6560232220609582e-06,
"loss": 0.4162,
"step": 2490
},
{
"epoch": 2.63,
"learning_rate": 2.5834542815674896e-06,
"loss": 0.3347,
"step": 2500
}
],
"max_steps": 2856,
"num_train_epochs": 3,
"total_flos": 5266095390720000.0,
"trial_name": null,
"trial_params": null
}