Taiwan-ELM-270M / checkpoint-4000 /trainer_state.json
liswei's picture
Upload checkpoints (#1)
9e59354 verified
raw
history blame contribute delete
No virus
69.3 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.29428534642903126,
"eval_steps": 500,
"global_step": 4000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0007357133660725781,
"grad_norm": 223.60693359375,
"learning_rate": 1.0000000000000002e-06,
"loss": 20.4521,
"step": 10
},
{
"epoch": 0.0014714267321451562,
"grad_norm": 115.68708038330078,
"learning_rate": 2.0000000000000003e-06,
"loss": 17.0724,
"step": 20
},
{
"epoch": 0.0022071400982177345,
"grad_norm": 9.73855972290039,
"learning_rate": 3e-06,
"loss": 11.1765,
"step": 30
},
{
"epoch": 0.0029428534642903124,
"grad_norm": 4.239206314086914,
"learning_rate": 4.000000000000001e-06,
"loss": 9.9334,
"step": 40
},
{
"epoch": 0.0036785668303628907,
"grad_norm": 5.939801216125488,
"learning_rate": 5e-06,
"loss": 9.6538,
"step": 50
},
{
"epoch": 0.004414280196435469,
"grad_norm": 7.083678245544434,
"learning_rate": 6e-06,
"loss": 9.4877,
"step": 60
},
{
"epoch": 0.0051499935625080465,
"grad_norm": 4.155125617980957,
"learning_rate": 7.000000000000001e-06,
"loss": 9.2998,
"step": 70
},
{
"epoch": 0.005885706928580625,
"grad_norm": 8.080842018127441,
"learning_rate": 8.000000000000001e-06,
"loss": 9.1653,
"step": 80
},
{
"epoch": 0.006621420294653203,
"grad_norm": 5.2444353103637695,
"learning_rate": 9e-06,
"loss": 9.0503,
"step": 90
},
{
"epoch": 0.0073571336607257815,
"grad_norm": 5.591372966766357,
"learning_rate": 1e-05,
"loss": 8.9182,
"step": 100
},
{
"epoch": 0.008092847026798359,
"grad_norm": 6.641251564025879,
"learning_rate": 1.1000000000000001e-05,
"loss": 8.7308,
"step": 110
},
{
"epoch": 0.008828560392870938,
"grad_norm": 8.2617769241333,
"learning_rate": 1.2e-05,
"loss": 8.4667,
"step": 120
},
{
"epoch": 0.009564273758943516,
"grad_norm": 8.181135177612305,
"learning_rate": 1.3000000000000001e-05,
"loss": 8.1982,
"step": 130
},
{
"epoch": 0.010299987125016093,
"grad_norm": 5.930114269256592,
"learning_rate": 1.4000000000000001e-05,
"loss": 7.8692,
"step": 140
},
{
"epoch": 0.011035700491088672,
"grad_norm": 4.546728610992432,
"learning_rate": 1.5e-05,
"loss": 7.5773,
"step": 150
},
{
"epoch": 0.01177141385716125,
"grad_norm": 4.127258777618408,
"learning_rate": 1.6000000000000003e-05,
"loss": 7.3816,
"step": 160
},
{
"epoch": 0.012507127223233829,
"grad_norm": 4.3951849937438965,
"learning_rate": 1.7000000000000003e-05,
"loss": 7.2603,
"step": 170
},
{
"epoch": 0.013242840589306406,
"grad_norm": 2.085538625717163,
"learning_rate": 1.8e-05,
"loss": 7.16,
"step": 180
},
{
"epoch": 0.013978553955378984,
"grad_norm": 3.098052501678467,
"learning_rate": 1.9e-05,
"loss": 7.0236,
"step": 190
},
{
"epoch": 0.014714267321451563,
"grad_norm": 4.054460525512695,
"learning_rate": 2e-05,
"loss": 7.0169,
"step": 200
},
{
"epoch": 0.01544998068752414,
"grad_norm": 1.6470402479171753,
"learning_rate": 2.1e-05,
"loss": 6.9933,
"step": 210
},
{
"epoch": 0.016185694053596718,
"grad_norm": 1.3456400632858276,
"learning_rate": 2.2000000000000003e-05,
"loss": 6.9151,
"step": 220
},
{
"epoch": 0.016921407419669295,
"grad_norm": 1.3457653522491455,
"learning_rate": 2.3000000000000003e-05,
"loss": 6.9246,
"step": 230
},
{
"epoch": 0.017657120785741876,
"grad_norm": 2.5111804008483887,
"learning_rate": 2.4e-05,
"loss": 6.8615,
"step": 240
},
{
"epoch": 0.018392834151814454,
"grad_norm": 2.082517147064209,
"learning_rate": 2.5e-05,
"loss": 6.8109,
"step": 250
},
{
"epoch": 0.01912854751788703,
"grad_norm": 2.9603984355926514,
"learning_rate": 2.6000000000000002e-05,
"loss": 6.7036,
"step": 260
},
{
"epoch": 0.01986426088395961,
"grad_norm": 1.7493945360183716,
"learning_rate": 2.7000000000000002e-05,
"loss": 6.6403,
"step": 270
},
{
"epoch": 0.020599974250032186,
"grad_norm": 3.83150315284729,
"learning_rate": 2.8000000000000003e-05,
"loss": 6.6216,
"step": 280
},
{
"epoch": 0.021335687616104767,
"grad_norm": 2.9999842643737793,
"learning_rate": 2.9e-05,
"loss": 6.6013,
"step": 290
},
{
"epoch": 0.022071400982177344,
"grad_norm": 2.799868583679199,
"learning_rate": 3e-05,
"loss": 6.4751,
"step": 300
},
{
"epoch": 0.022807114348249922,
"grad_norm": 3.548393487930298,
"learning_rate": 3.1e-05,
"loss": 6.5082,
"step": 310
},
{
"epoch": 0.0235428277143225,
"grad_norm": 3.523336410522461,
"learning_rate": 3.2000000000000005e-05,
"loss": 6.4566,
"step": 320
},
{
"epoch": 0.024278541080395077,
"grad_norm": 2.0755739212036133,
"learning_rate": 3.3e-05,
"loss": 6.3776,
"step": 330
},
{
"epoch": 0.025014254446467658,
"grad_norm": 3.288764238357544,
"learning_rate": 3.4000000000000007e-05,
"loss": 6.3559,
"step": 340
},
{
"epoch": 0.025749967812540235,
"grad_norm": 3.3932132720947266,
"learning_rate": 3.5e-05,
"loss": 6.3234,
"step": 350
},
{
"epoch": 0.026485681178612813,
"grad_norm": 2.7775251865386963,
"learning_rate": 3.6e-05,
"loss": 6.2551,
"step": 360
},
{
"epoch": 0.02722139454468539,
"grad_norm": 2.6773834228515625,
"learning_rate": 3.7e-05,
"loss": 6.206,
"step": 370
},
{
"epoch": 0.027957107910757967,
"grad_norm": 2.556666612625122,
"learning_rate": 3.8e-05,
"loss": 6.1396,
"step": 380
},
{
"epoch": 0.02869282127683055,
"grad_norm": 3.2724132537841797,
"learning_rate": 3.9000000000000006e-05,
"loss": 6.106,
"step": 390
},
{
"epoch": 0.029428534642903126,
"grad_norm": 2.354327440261841,
"learning_rate": 4e-05,
"loss": 6.1258,
"step": 400
},
{
"epoch": 0.030164248008975703,
"grad_norm": 1.804317593574524,
"learning_rate": 4.1e-05,
"loss": 6.0516,
"step": 410
},
{
"epoch": 0.03089996137504828,
"grad_norm": 1.7134747505187988,
"learning_rate": 4.2e-05,
"loss": 5.9582,
"step": 420
},
{
"epoch": 0.03163567474112086,
"grad_norm": 1.4939428567886353,
"learning_rate": 4.3e-05,
"loss": 5.9328,
"step": 430
},
{
"epoch": 0.032371388107193436,
"grad_norm": 1.9662060737609863,
"learning_rate": 4.4000000000000006e-05,
"loss": 5.8578,
"step": 440
},
{
"epoch": 0.03310710147326602,
"grad_norm": 1.748353123664856,
"learning_rate": 4.5e-05,
"loss": 5.7874,
"step": 450
},
{
"epoch": 0.03384281483933859,
"grad_norm": 2.1945955753326416,
"learning_rate": 4.600000000000001e-05,
"loss": 5.7787,
"step": 460
},
{
"epoch": 0.03457852820541117,
"grad_norm": 2.1684770584106445,
"learning_rate": 4.7e-05,
"loss": 5.7138,
"step": 470
},
{
"epoch": 0.03531424157148375,
"grad_norm": 1.728945255279541,
"learning_rate": 4.8e-05,
"loss": 5.6774,
"step": 480
},
{
"epoch": 0.036049954937556326,
"grad_norm": 1.8206098079681396,
"learning_rate": 4.9e-05,
"loss": 5.6214,
"step": 490
},
{
"epoch": 0.03678566830362891,
"grad_norm": 1.5937659740447998,
"learning_rate": 5e-05,
"loss": 5.5198,
"step": 500
},
{
"epoch": 0.03752138166970148,
"grad_norm": 1.617659568786621,
"learning_rate": 5.1000000000000006e-05,
"loss": 5.4818,
"step": 510
},
{
"epoch": 0.03825709503577406,
"grad_norm": 1.7942918539047241,
"learning_rate": 5.2000000000000004e-05,
"loss": 5.5156,
"step": 520
},
{
"epoch": 0.03899280840184664,
"grad_norm": 1.830945611000061,
"learning_rate": 5.300000000000001e-05,
"loss": 5.3836,
"step": 530
},
{
"epoch": 0.03972852176791922,
"grad_norm": 1.5295898914337158,
"learning_rate": 5.4000000000000005e-05,
"loss": 5.3989,
"step": 540
},
{
"epoch": 0.0404642351339918,
"grad_norm": 1.527603268623352,
"learning_rate": 5.500000000000001e-05,
"loss": 5.3724,
"step": 550
},
{
"epoch": 0.04119994850006437,
"grad_norm": 1.6225807666778564,
"learning_rate": 5.6000000000000006e-05,
"loss": 5.2788,
"step": 560
},
{
"epoch": 0.04193566186613695,
"grad_norm": 2.0076022148132324,
"learning_rate": 5.6999999999999996e-05,
"loss": 5.2227,
"step": 570
},
{
"epoch": 0.042671375232209534,
"grad_norm": 1.5891458988189697,
"learning_rate": 5.8e-05,
"loss": 5.2265,
"step": 580
},
{
"epoch": 0.04340708859828211,
"grad_norm": 1.5814419984817505,
"learning_rate": 5.9e-05,
"loss": 5.1948,
"step": 590
},
{
"epoch": 0.04414280196435469,
"grad_norm": 1.7139537334442139,
"learning_rate": 6e-05,
"loss": 5.1036,
"step": 600
},
{
"epoch": 0.04487851533042726,
"grad_norm": 1.2224972248077393,
"learning_rate": 6.1e-05,
"loss": 5.1932,
"step": 610
},
{
"epoch": 0.045614228696499844,
"grad_norm": 1.6268278360366821,
"learning_rate": 6.2e-05,
"loss": 5.068,
"step": 620
},
{
"epoch": 0.046349942062572425,
"grad_norm": 1.4944841861724854,
"learning_rate": 6.3e-05,
"loss": 5.032,
"step": 630
},
{
"epoch": 0.047085655428645,
"grad_norm": 1.442824363708496,
"learning_rate": 6.400000000000001e-05,
"loss": 5.0077,
"step": 640
},
{
"epoch": 0.04782136879471758,
"grad_norm": 1.6031944751739502,
"learning_rate": 6.500000000000001e-05,
"loss": 4.9808,
"step": 650
},
{
"epoch": 0.04855708216079015,
"grad_norm": 1.6006144285202026,
"learning_rate": 6.6e-05,
"loss": 4.9239,
"step": 660
},
{
"epoch": 0.049292795526862734,
"grad_norm": 1.3961182832717896,
"learning_rate": 6.7e-05,
"loss": 4.9158,
"step": 670
},
{
"epoch": 0.050028508892935315,
"grad_norm": 1.4314249753952026,
"learning_rate": 6.800000000000001e-05,
"loss": 4.8126,
"step": 680
},
{
"epoch": 0.05076422225900789,
"grad_norm": 1.4509848356246948,
"learning_rate": 6.9e-05,
"loss": 4.8713,
"step": 690
},
{
"epoch": 0.05149993562508047,
"grad_norm": 1.5618196725845337,
"learning_rate": 7e-05,
"loss": 4.7814,
"step": 700
},
{
"epoch": 0.052235648991153044,
"grad_norm": 1.5423110723495483,
"learning_rate": 7.1e-05,
"loss": 4.7409,
"step": 710
},
{
"epoch": 0.052971362357225625,
"grad_norm": 1.2559527158737183,
"learning_rate": 7.2e-05,
"loss": 4.73,
"step": 720
},
{
"epoch": 0.053707075723298206,
"grad_norm": 1.1119533777236938,
"learning_rate": 7.3e-05,
"loss": 4.7055,
"step": 730
},
{
"epoch": 0.05444278908937078,
"grad_norm": 1.2400840520858765,
"learning_rate": 7.4e-05,
"loss": 4.6501,
"step": 740
},
{
"epoch": 0.05517850245544336,
"grad_norm": 1.2191784381866455,
"learning_rate": 7.500000000000001e-05,
"loss": 4.6239,
"step": 750
},
{
"epoch": 0.055914215821515935,
"grad_norm": 1.269572377204895,
"learning_rate": 7.6e-05,
"loss": 4.6498,
"step": 760
},
{
"epoch": 0.056649929187588516,
"grad_norm": 1.275608777999878,
"learning_rate": 7.7e-05,
"loss": 4.6326,
"step": 770
},
{
"epoch": 0.0573856425536611,
"grad_norm": 1.3013856410980225,
"learning_rate": 7.800000000000001e-05,
"loss": 4.5869,
"step": 780
},
{
"epoch": 0.05812135591973367,
"grad_norm": 1.37381112575531,
"learning_rate": 7.900000000000001e-05,
"loss": 4.5785,
"step": 790
},
{
"epoch": 0.05885706928580625,
"grad_norm": 1.2166635990142822,
"learning_rate": 8e-05,
"loss": 4.5126,
"step": 800
},
{
"epoch": 0.059592782651878826,
"grad_norm": 1.4644134044647217,
"learning_rate": 8.1e-05,
"loss": 4.5228,
"step": 810
},
{
"epoch": 0.06032849601795141,
"grad_norm": 1.206525206565857,
"learning_rate": 8.2e-05,
"loss": 4.4874,
"step": 820
},
{
"epoch": 0.06106420938402399,
"grad_norm": 1.1188849210739136,
"learning_rate": 8.3e-05,
"loss": 4.4619,
"step": 830
},
{
"epoch": 0.06179992275009656,
"grad_norm": 1.2260874509811401,
"learning_rate": 8.4e-05,
"loss": 4.4118,
"step": 840
},
{
"epoch": 0.06253563611616914,
"grad_norm": 1.19864022731781,
"learning_rate": 8.5e-05,
"loss": 4.3522,
"step": 850
},
{
"epoch": 0.06327134948224172,
"grad_norm": 1.1710054874420166,
"learning_rate": 8.6e-05,
"loss": 4.4048,
"step": 860
},
{
"epoch": 0.0640070628483143,
"grad_norm": 0.8916666507720947,
"learning_rate": 8.7e-05,
"loss": 4.3865,
"step": 870
},
{
"epoch": 0.06474277621438687,
"grad_norm": 1.135651707649231,
"learning_rate": 8.800000000000001e-05,
"loss": 4.3554,
"step": 880
},
{
"epoch": 0.06547848958045946,
"grad_norm": 0.9037818312644958,
"learning_rate": 8.900000000000001e-05,
"loss": 4.4055,
"step": 890
},
{
"epoch": 0.06621420294653203,
"grad_norm": 1.1230660676956177,
"learning_rate": 9e-05,
"loss": 4.3131,
"step": 900
},
{
"epoch": 0.06694991631260461,
"grad_norm": 1.149318814277649,
"learning_rate": 9.1e-05,
"loss": 4.2923,
"step": 910
},
{
"epoch": 0.06768562967867718,
"grad_norm": 1.1154922246932983,
"learning_rate": 9.200000000000001e-05,
"loss": 4.2774,
"step": 920
},
{
"epoch": 0.06842134304474977,
"grad_norm": 1.0399177074432373,
"learning_rate": 9.300000000000001e-05,
"loss": 4.2766,
"step": 930
},
{
"epoch": 0.06915705641082234,
"grad_norm": 1.0165122747421265,
"learning_rate": 9.4e-05,
"loss": 4.2479,
"step": 940
},
{
"epoch": 0.06989276977689492,
"grad_norm": 1.3305314779281616,
"learning_rate": 9.5e-05,
"loss": 4.2443,
"step": 950
},
{
"epoch": 0.0706284831429675,
"grad_norm": 0.8728047609329224,
"learning_rate": 9.6e-05,
"loss": 4.3267,
"step": 960
},
{
"epoch": 0.07136419650904008,
"grad_norm": 1.117966890335083,
"learning_rate": 9.7e-05,
"loss": 4.2435,
"step": 970
},
{
"epoch": 0.07209990987511265,
"grad_norm": 0.934165894985199,
"learning_rate": 9.8e-05,
"loss": 4.2125,
"step": 980
},
{
"epoch": 0.07283562324118524,
"grad_norm": 1.0023953914642334,
"learning_rate": 9.900000000000001e-05,
"loss": 4.1705,
"step": 990
},
{
"epoch": 0.07357133660725781,
"grad_norm": 0.9707255959510803,
"learning_rate": 0.0001,
"loss": 4.202,
"step": 1000
},
{
"epoch": 0.07430704997333039,
"grad_norm": 0.988510012626648,
"learning_rate": 9.999998440456413e-05,
"loss": 4.1781,
"step": 1010
},
{
"epoch": 0.07504276333940296,
"grad_norm": 1.0348843336105347,
"learning_rate": 9.99999376182662e-05,
"loss": 4.1589,
"step": 1020
},
{
"epoch": 0.07577847670547555,
"grad_norm": 1.0255194902420044,
"learning_rate": 9.999985964113542e-05,
"loss": 4.1653,
"step": 1030
},
{
"epoch": 0.07651419007154812,
"grad_norm": 0.831902801990509,
"learning_rate": 9.999975047322044e-05,
"loss": 4.1595,
"step": 1040
},
{
"epoch": 0.0772499034376207,
"grad_norm": 0.964509904384613,
"learning_rate": 9.999961011458933e-05,
"loss": 4.1414,
"step": 1050
},
{
"epoch": 0.07798561680369329,
"grad_norm": 0.796290397644043,
"learning_rate": 9.99994385653297e-05,
"loss": 4.0971,
"step": 1060
},
{
"epoch": 0.07872133016976586,
"grad_norm": 0.8830526471138,
"learning_rate": 9.99992358255485e-05,
"loss": 4.1182,
"step": 1070
},
{
"epoch": 0.07945704353583843,
"grad_norm": 1.0227144956588745,
"learning_rate": 9.999900189537226e-05,
"loss": 4.0917,
"step": 1080
},
{
"epoch": 0.08019275690191102,
"grad_norm": 1.0185173749923706,
"learning_rate": 9.999873677494689e-05,
"loss": 4.1066,
"step": 1090
},
{
"epoch": 0.0809284702679836,
"grad_norm": 0.8834981322288513,
"learning_rate": 9.999844046443776e-05,
"loss": 4.0413,
"step": 1100
},
{
"epoch": 0.08166418363405617,
"grad_norm": 0.9037182331085205,
"learning_rate": 9.999811296402975e-05,
"loss": 4.1012,
"step": 1110
},
{
"epoch": 0.08239989700012874,
"grad_norm": 0.9970824122428894,
"learning_rate": 9.99977542739271e-05,
"loss": 4.0548,
"step": 1120
},
{
"epoch": 0.08313561036620133,
"grad_norm": 0.9786319136619568,
"learning_rate": 9.999736439435364e-05,
"loss": 4.0613,
"step": 1130
},
{
"epoch": 0.0838713237322739,
"grad_norm": 0.8991515636444092,
"learning_rate": 9.999694332555253e-05,
"loss": 4.07,
"step": 1140
},
{
"epoch": 0.08460703709834648,
"grad_norm": 0.8191851377487183,
"learning_rate": 9.999649106778646e-05,
"loss": 4.0169,
"step": 1150
},
{
"epoch": 0.08534275046441907,
"grad_norm": 0.7964187860488892,
"learning_rate": 9.999600762133756e-05,
"loss": 4.0185,
"step": 1160
},
{
"epoch": 0.08607846383049164,
"grad_norm": 0.8330606818199158,
"learning_rate": 9.99954929865074e-05,
"loss": 4.0695,
"step": 1170
},
{
"epoch": 0.08681417719656422,
"grad_norm": 0.8456650376319885,
"learning_rate": 9.999494716361703e-05,
"loss": 3.971,
"step": 1180
},
{
"epoch": 0.0875498905626368,
"grad_norm": 0.7506271600723267,
"learning_rate": 9.999437015300694e-05,
"loss": 4.0053,
"step": 1190
},
{
"epoch": 0.08828560392870938,
"grad_norm": 0.7525317668914795,
"learning_rate": 9.999376195503709e-05,
"loss": 3.9699,
"step": 1200
},
{
"epoch": 0.08902131729478195,
"grad_norm": 0.7871759533882141,
"learning_rate": 9.999312257008685e-05,
"loss": 3.9137,
"step": 1210
},
{
"epoch": 0.08975703066085453,
"grad_norm": 0.8398749828338623,
"learning_rate": 9.999245199855512e-05,
"loss": 3.9667,
"step": 1220
},
{
"epoch": 0.09049274402692711,
"grad_norm": 0.7666105031967163,
"learning_rate": 9.99917502408602e-05,
"loss": 3.9273,
"step": 1230
},
{
"epoch": 0.09122845739299969,
"grad_norm": 0.8470506072044373,
"learning_rate": 9.999101729743985e-05,
"loss": 3.9694,
"step": 1240
},
{
"epoch": 0.09196417075907226,
"grad_norm": 0.7060391306877136,
"learning_rate": 9.999025316875129e-05,
"loss": 3.9618,
"step": 1250
},
{
"epoch": 0.09269988412514485,
"grad_norm": 0.7745850682258606,
"learning_rate": 9.99894578552712e-05,
"loss": 3.9252,
"step": 1260
},
{
"epoch": 0.09343559749121742,
"grad_norm": 0.8749181032180786,
"learning_rate": 9.998863135749575e-05,
"loss": 3.9104,
"step": 1270
},
{
"epoch": 0.09417131085729,
"grad_norm": 0.906620979309082,
"learning_rate": 9.998777367594046e-05,
"loss": 3.9174,
"step": 1280
},
{
"epoch": 0.09490702422336257,
"grad_norm": 0.7657135725021362,
"learning_rate": 9.998688481114039e-05,
"loss": 3.9238,
"step": 1290
},
{
"epoch": 0.09564273758943516,
"grad_norm": 0.6726455688476562,
"learning_rate": 9.998596476365006e-05,
"loss": 3.8952,
"step": 1300
},
{
"epoch": 0.09637845095550773,
"grad_norm": 0.7561966776847839,
"learning_rate": 9.998501353404336e-05,
"loss": 3.9123,
"step": 1310
},
{
"epoch": 0.0971141643215803,
"grad_norm": 0.8008501529693604,
"learning_rate": 9.998403112291372e-05,
"loss": 3.8617,
"step": 1320
},
{
"epoch": 0.0978498776876529,
"grad_norm": 0.7718631029129028,
"learning_rate": 9.998301753087398e-05,
"loss": 3.8859,
"step": 1330
},
{
"epoch": 0.09858559105372547,
"grad_norm": 0.8178690671920776,
"learning_rate": 9.998197275855644e-05,
"loss": 3.8473,
"step": 1340
},
{
"epoch": 0.09932130441979804,
"grad_norm": 0.7664726376533508,
"learning_rate": 9.998089680661282e-05,
"loss": 3.8305,
"step": 1350
},
{
"epoch": 0.10005701778587063,
"grad_norm": 0.8279010653495789,
"learning_rate": 9.997978967571436e-05,
"loss": 3.8802,
"step": 1360
},
{
"epoch": 0.1007927311519432,
"grad_norm": 0.7610680460929871,
"learning_rate": 9.997865136655166e-05,
"loss": 3.8869,
"step": 1370
},
{
"epoch": 0.10152844451801578,
"grad_norm": 0.7211320400238037,
"learning_rate": 9.997748187983487e-05,
"loss": 3.9122,
"step": 1380
},
{
"epoch": 0.10226415788408835,
"grad_norm": 0.7668148279190063,
"learning_rate": 9.997628121629349e-05,
"loss": 3.8238,
"step": 1390
},
{
"epoch": 0.10299987125016094,
"grad_norm": 0.6940723061561584,
"learning_rate": 9.997504937667654e-05,
"loss": 3.8464,
"step": 1400
},
{
"epoch": 0.10373558461623351,
"grad_norm": 0.681667149066925,
"learning_rate": 9.997378636175245e-05,
"loss": 3.8182,
"step": 1410
},
{
"epoch": 0.10447129798230609,
"grad_norm": 0.6430841684341431,
"learning_rate": 9.99724921723091e-05,
"loss": 3.8379,
"step": 1420
},
{
"epoch": 0.10520701134837868,
"grad_norm": 0.6482489705085754,
"learning_rate": 9.997116680915389e-05,
"loss": 3.8117,
"step": 1430
},
{
"epoch": 0.10594272471445125,
"grad_norm": 0.6649356484413147,
"learning_rate": 9.996981027311352e-05,
"loss": 3.8452,
"step": 1440
},
{
"epoch": 0.10667843808052382,
"grad_norm": 0.757146954536438,
"learning_rate": 9.996842256503428e-05,
"loss": 3.7886,
"step": 1450
},
{
"epoch": 0.10741415144659641,
"grad_norm": 0.6373863816261292,
"learning_rate": 9.99670036857818e-05,
"loss": 3.7975,
"step": 1460
},
{
"epoch": 0.10814986481266899,
"grad_norm": 0.6672409176826477,
"learning_rate": 9.996555363624124e-05,
"loss": 3.843,
"step": 1470
},
{
"epoch": 0.10888557817874156,
"grad_norm": 0.6595909595489502,
"learning_rate": 9.996407241731717e-05,
"loss": 3.8397,
"step": 1480
},
{
"epoch": 0.10962129154481413,
"grad_norm": 0.725779116153717,
"learning_rate": 9.996256002993358e-05,
"loss": 3.8264,
"step": 1490
},
{
"epoch": 0.11035700491088672,
"grad_norm": 0.6590442061424255,
"learning_rate": 9.99610164750339e-05,
"loss": 3.8375,
"step": 1500
},
{
"epoch": 0.1110927182769593,
"grad_norm": 0.707144558429718,
"learning_rate": 9.99594417535811e-05,
"loss": 3.7805,
"step": 1510
},
{
"epoch": 0.11182843164303187,
"grad_norm": 0.7135934233665466,
"learning_rate": 9.995783586655745e-05,
"loss": 3.7696,
"step": 1520
},
{
"epoch": 0.11256414500910446,
"grad_norm": 0.7143461108207703,
"learning_rate": 9.995619881496474e-05,
"loss": 3.7558,
"step": 1530
},
{
"epoch": 0.11329985837517703,
"grad_norm": 0.6768718957901001,
"learning_rate": 9.995453059982422e-05,
"loss": 3.8221,
"step": 1540
},
{
"epoch": 0.1140355717412496,
"grad_norm": 0.6788365244865417,
"learning_rate": 9.995283122217653e-05,
"loss": 3.7792,
"step": 1550
},
{
"epoch": 0.1147712851073222,
"grad_norm": 0.6880599856376648,
"learning_rate": 9.995110068308179e-05,
"loss": 3.7191,
"step": 1560
},
{
"epoch": 0.11550699847339477,
"grad_norm": 0.6511822938919067,
"learning_rate": 9.994933898361951e-05,
"loss": 3.7585,
"step": 1570
},
{
"epoch": 0.11624271183946734,
"grad_norm": 0.6109036803245544,
"learning_rate": 9.99475461248887e-05,
"loss": 3.7555,
"step": 1580
},
{
"epoch": 0.11697842520553992,
"grad_norm": 0.6387907862663269,
"learning_rate": 9.994572210800777e-05,
"loss": 3.7283,
"step": 1590
},
{
"epoch": 0.1177141385716125,
"grad_norm": 0.6535074710845947,
"learning_rate": 9.994386693411455e-05,
"loss": 3.7781,
"step": 1600
},
{
"epoch": 0.11844985193768508,
"grad_norm": 0.6718204617500305,
"learning_rate": 9.994198060436637e-05,
"loss": 3.7622,
"step": 1610
},
{
"epoch": 0.11918556530375765,
"grad_norm": 0.75942063331604,
"learning_rate": 9.994006311993991e-05,
"loss": 3.6595,
"step": 1620
},
{
"epoch": 0.11992127866983024,
"grad_norm": 0.6169456243515015,
"learning_rate": 9.993811448203136e-05,
"loss": 3.6921,
"step": 1630
},
{
"epoch": 0.12065699203590281,
"grad_norm": 0.6598173379898071,
"learning_rate": 9.993613469185631e-05,
"loss": 3.6957,
"step": 1640
},
{
"epoch": 0.12139270540197539,
"grad_norm": 0.6640283465385437,
"learning_rate": 9.993412375064979e-05,
"loss": 3.7507,
"step": 1650
},
{
"epoch": 0.12212841876804797,
"grad_norm": 0.720782458782196,
"learning_rate": 9.993208165966623e-05,
"loss": 3.741,
"step": 1660
},
{
"epoch": 0.12286413213412055,
"grad_norm": 0.6343806385993958,
"learning_rate": 9.993000842017957e-05,
"loss": 3.7112,
"step": 1670
},
{
"epoch": 0.12359984550019312,
"grad_norm": 0.72925865650177,
"learning_rate": 9.99279040334831e-05,
"loss": 3.7455,
"step": 1680
},
{
"epoch": 0.1243355588662657,
"grad_norm": 0.7056775093078613,
"learning_rate": 9.99257685008896e-05,
"loss": 3.7007,
"step": 1690
},
{
"epoch": 0.12507127223233827,
"grad_norm": 0.6219266057014465,
"learning_rate": 9.992360182373122e-05,
"loss": 3.6704,
"step": 1700
},
{
"epoch": 0.12580698559841086,
"grad_norm": 0.8017805814743042,
"learning_rate": 9.992140400335958e-05,
"loss": 3.7098,
"step": 1710
},
{
"epoch": 0.12654269896448345,
"grad_norm": 0.6517687439918518,
"learning_rate": 9.991917504114574e-05,
"loss": 3.7145,
"step": 1720
},
{
"epoch": 0.127278412330556,
"grad_norm": 0.6560338735580444,
"learning_rate": 9.991691493848015e-05,
"loss": 3.7046,
"step": 1730
},
{
"epoch": 0.1280141256966286,
"grad_norm": 0.7055456638336182,
"learning_rate": 9.991462369677267e-05,
"loss": 3.6855,
"step": 1740
},
{
"epoch": 0.12874983906270118,
"grad_norm": 0.6441034078598022,
"learning_rate": 9.991230131745268e-05,
"loss": 3.7338,
"step": 1750
},
{
"epoch": 0.12948555242877374,
"grad_norm": 0.6746709942817688,
"learning_rate": 9.990994780196889e-05,
"loss": 3.7237,
"step": 1760
},
{
"epoch": 0.13022126579484633,
"grad_norm": 0.6609126925468445,
"learning_rate": 9.990756315178945e-05,
"loss": 3.7393,
"step": 1770
},
{
"epoch": 0.13095697916091892,
"grad_norm": 0.648073673248291,
"learning_rate": 9.990514736840197e-05,
"loss": 3.7057,
"step": 1780
},
{
"epoch": 0.13169269252699148,
"grad_norm": 0.6735105514526367,
"learning_rate": 9.990270045331344e-05,
"loss": 3.7574,
"step": 1790
},
{
"epoch": 0.13242840589306407,
"grad_norm": 0.6125868558883667,
"learning_rate": 9.99002224080503e-05,
"loss": 3.6548,
"step": 1800
},
{
"epoch": 0.13316411925913665,
"grad_norm": 0.5899696946144104,
"learning_rate": 9.98977132341584e-05,
"loss": 3.624,
"step": 1810
},
{
"epoch": 0.13389983262520921,
"grad_norm": 0.6936771273612976,
"learning_rate": 9.989517293320299e-05,
"loss": 3.7022,
"step": 1820
},
{
"epoch": 0.1346355459912818,
"grad_norm": 0.6176466345787048,
"learning_rate": 9.989260150676876e-05,
"loss": 3.697,
"step": 1830
},
{
"epoch": 0.13537125935735436,
"grad_norm": 0.6583747863769531,
"learning_rate": 9.988999895645981e-05,
"loss": 3.7048,
"step": 1840
},
{
"epoch": 0.13610697272342695,
"grad_norm": 0.6942030191421509,
"learning_rate": 9.988736528389969e-05,
"loss": 3.6784,
"step": 1850
},
{
"epoch": 0.13684268608949954,
"grad_norm": 0.6578043103218079,
"learning_rate": 9.988470049073126e-05,
"loss": 3.6411,
"step": 1860
},
{
"epoch": 0.1375783994555721,
"grad_norm": 0.648202657699585,
"learning_rate": 9.988200457861694e-05,
"loss": 3.6472,
"step": 1870
},
{
"epoch": 0.13831411282164469,
"grad_norm": 0.6567854285240173,
"learning_rate": 9.987927754923843e-05,
"loss": 3.6734,
"step": 1880
},
{
"epoch": 0.13904982618771727,
"grad_norm": 0.6515029668807983,
"learning_rate": 9.987651940429695e-05,
"loss": 3.6463,
"step": 1890
},
{
"epoch": 0.13978553955378983,
"grad_norm": 0.597316324710846,
"learning_rate": 9.987373014551302e-05,
"loss": 3.5951,
"step": 1900
},
{
"epoch": 0.14052125291986242,
"grad_norm": 0.6288499236106873,
"learning_rate": 9.987090977462668e-05,
"loss": 3.675,
"step": 1910
},
{
"epoch": 0.141256966285935,
"grad_norm": 0.6451112627983093,
"learning_rate": 9.986805829339729e-05,
"loss": 3.6552,
"step": 1920
},
{
"epoch": 0.14199267965200757,
"grad_norm": 0.6517444252967834,
"learning_rate": 9.986517570360368e-05,
"loss": 3.6206,
"step": 1930
},
{
"epoch": 0.14272839301808016,
"grad_norm": 0.6413518786430359,
"learning_rate": 9.986226200704404e-05,
"loss": 3.6848,
"step": 1940
},
{
"epoch": 0.14346410638415275,
"grad_norm": 0.6431183815002441,
"learning_rate": 9.9859317205536e-05,
"loss": 3.6339,
"step": 1950
},
{
"epoch": 0.1441998197502253,
"grad_norm": 0.7160407900810242,
"learning_rate": 9.985634130091657e-05,
"loss": 3.6306,
"step": 1960
},
{
"epoch": 0.1449355331162979,
"grad_norm": 0.602085292339325,
"learning_rate": 9.985333429504216e-05,
"loss": 3.6556,
"step": 1970
},
{
"epoch": 0.14567124648237048,
"grad_norm": 0.6392213702201843,
"learning_rate": 9.985029618978863e-05,
"loss": 3.6195,
"step": 1980
},
{
"epoch": 0.14640695984844304,
"grad_norm": 0.5774185657501221,
"learning_rate": 9.984722698705115e-05,
"loss": 3.6463,
"step": 1990
},
{
"epoch": 0.14714267321451563,
"grad_norm": 0.6097477674484253,
"learning_rate": 9.984412668874442e-05,
"loss": 3.6759,
"step": 2000
},
{
"epoch": 0.1478783865805882,
"grad_norm": 0.5511993765830994,
"learning_rate": 9.984099529680237e-05,
"loss": 3.6254,
"step": 2010
},
{
"epoch": 0.14861409994666078,
"grad_norm": 0.6293554306030273,
"learning_rate": 9.983783281317847e-05,
"loss": 3.6285,
"step": 2020
},
{
"epoch": 0.14934981331273336,
"grad_norm": 0.5784502625465393,
"learning_rate": 9.983463923984551e-05,
"loss": 3.5952,
"step": 2030
},
{
"epoch": 0.15008552667880593,
"grad_norm": 0.5587512254714966,
"learning_rate": 9.983141457879572e-05,
"loss": 3.5877,
"step": 2040
},
{
"epoch": 0.1508212400448785,
"grad_norm": 0.5835023522377014,
"learning_rate": 9.982815883204068e-05,
"loss": 3.6139,
"step": 2050
},
{
"epoch": 0.1515569534109511,
"grad_norm": 0.6096065044403076,
"learning_rate": 9.982487200161139e-05,
"loss": 3.6261,
"step": 2060
},
{
"epoch": 0.15229266677702366,
"grad_norm": 0.6385859847068787,
"learning_rate": 9.982155408955822e-05,
"loss": 3.6228,
"step": 2070
},
{
"epoch": 0.15302838014309625,
"grad_norm": 0.6276549100875854,
"learning_rate": 9.981820509795096e-05,
"loss": 3.6525,
"step": 2080
},
{
"epoch": 0.15376409350916884,
"grad_norm": 0.5835126638412476,
"learning_rate": 9.981482502887878e-05,
"loss": 3.6081,
"step": 2090
},
{
"epoch": 0.1544998068752414,
"grad_norm": 0.6056969165802002,
"learning_rate": 9.981141388445019e-05,
"loss": 3.6241,
"step": 2100
},
{
"epoch": 0.15523552024131398,
"grad_norm": 0.6270286440849304,
"learning_rate": 9.980797166679314e-05,
"loss": 3.6231,
"step": 2110
},
{
"epoch": 0.15597123360738657,
"grad_norm": 0.6744200587272644,
"learning_rate": 9.980449837805494e-05,
"loss": 3.5789,
"step": 2120
},
{
"epoch": 0.15670694697345913,
"grad_norm": 0.5492793321609497,
"learning_rate": 9.98009940204023e-05,
"loss": 3.58,
"step": 2130
},
{
"epoch": 0.15744266033953172,
"grad_norm": 0.601390540599823,
"learning_rate": 9.979745859602129e-05,
"loss": 3.6059,
"step": 2140
},
{
"epoch": 0.1581783737056043,
"grad_norm": 0.6107606887817383,
"learning_rate": 9.979389210711737e-05,
"loss": 3.5928,
"step": 2150
},
{
"epoch": 0.15891408707167687,
"grad_norm": 0.6118071675300598,
"learning_rate": 9.979029455591538e-05,
"loss": 3.5771,
"step": 2160
},
{
"epoch": 0.15964980043774946,
"grad_norm": 0.6007488369941711,
"learning_rate": 9.978666594465953e-05,
"loss": 3.5729,
"step": 2170
},
{
"epoch": 0.16038551380382204,
"grad_norm": 0.5910535454750061,
"learning_rate": 9.978300627561343e-05,
"loss": 3.5953,
"step": 2180
},
{
"epoch": 0.1611212271698946,
"grad_norm": 0.5529370903968811,
"learning_rate": 9.977931555106002e-05,
"loss": 3.6167,
"step": 2190
},
{
"epoch": 0.1618569405359672,
"grad_norm": 0.6961104273796082,
"learning_rate": 9.977559377330163e-05,
"loss": 3.5541,
"step": 2200
},
{
"epoch": 0.16259265390203975,
"grad_norm": 0.5334804654121399,
"learning_rate": 9.977184094466001e-05,
"loss": 3.6368,
"step": 2210
},
{
"epoch": 0.16332836726811234,
"grad_norm": 0.6472899913787842,
"learning_rate": 9.976805706747622e-05,
"loss": 3.5896,
"step": 2220
},
{
"epoch": 0.16406408063418493,
"grad_norm": 0.6276665329933167,
"learning_rate": 9.976424214411071e-05,
"loss": 3.5907,
"step": 2230
},
{
"epoch": 0.1647997940002575,
"grad_norm": 0.5503706932067871,
"learning_rate": 9.976039617694328e-05,
"loss": 3.6037,
"step": 2240
},
{
"epoch": 0.16553550736633008,
"grad_norm": 0.5655608773231506,
"learning_rate": 9.975651916837313e-05,
"loss": 3.6157,
"step": 2250
},
{
"epoch": 0.16627122073240266,
"grad_norm": 0.5357344746589661,
"learning_rate": 9.975261112081879e-05,
"loss": 3.583,
"step": 2260
},
{
"epoch": 0.16700693409847522,
"grad_norm": 0.5251188278198242,
"learning_rate": 9.974867203671819e-05,
"loss": 3.5705,
"step": 2270
},
{
"epoch": 0.1677426474645478,
"grad_norm": 0.5895013809204102,
"learning_rate": 9.974470191852858e-05,
"loss": 3.5648,
"step": 2280
},
{
"epoch": 0.1684783608306204,
"grad_norm": 0.5837428569793701,
"learning_rate": 9.974070076872662e-05,
"loss": 3.5607,
"step": 2290
},
{
"epoch": 0.16921407419669296,
"grad_norm": 0.5866957306861877,
"learning_rate": 9.973666858980824e-05,
"loss": 3.5689,
"step": 2300
},
{
"epoch": 0.16994978756276555,
"grad_norm": 0.5927156209945679,
"learning_rate": 9.973260538428884e-05,
"loss": 3.5806,
"step": 2310
},
{
"epoch": 0.17068550092883814,
"grad_norm": 0.5668119788169861,
"learning_rate": 9.972851115470307e-05,
"loss": 3.5247,
"step": 2320
},
{
"epoch": 0.1714212142949107,
"grad_norm": 0.5907779335975647,
"learning_rate": 9.972438590360503e-05,
"loss": 3.5757,
"step": 2330
},
{
"epoch": 0.17215692766098328,
"grad_norm": 0.5702281594276428,
"learning_rate": 9.97202296335681e-05,
"loss": 3.5698,
"step": 2340
},
{
"epoch": 0.17289264102705587,
"grad_norm": 0.5785143375396729,
"learning_rate": 9.971604234718504e-05,
"loss": 3.5547,
"step": 2350
},
{
"epoch": 0.17362835439312843,
"grad_norm": 0.5959532856941223,
"learning_rate": 9.971182404706792e-05,
"loss": 3.4787,
"step": 2360
},
{
"epoch": 0.17436406775920102,
"grad_norm": 0.5923709869384766,
"learning_rate": 9.970757473584824e-05,
"loss": 3.5127,
"step": 2370
},
{
"epoch": 0.1750997811252736,
"grad_norm": 0.6314843893051147,
"learning_rate": 9.970329441617676e-05,
"loss": 3.5123,
"step": 2380
},
{
"epoch": 0.17583549449134617,
"grad_norm": 0.6579912304878235,
"learning_rate": 9.969898309072363e-05,
"loss": 3.5295,
"step": 2390
},
{
"epoch": 0.17657120785741875,
"grad_norm": 0.5852422118186951,
"learning_rate": 9.969464076217831e-05,
"loss": 3.5761,
"step": 2400
},
{
"epoch": 0.17730692122349132,
"grad_norm": 0.5590935945510864,
"learning_rate": 9.969026743324967e-05,
"loss": 3.5697,
"step": 2410
},
{
"epoch": 0.1780426345895639,
"grad_norm": 0.5512566566467285,
"learning_rate": 9.968586310666583e-05,
"loss": 3.5069,
"step": 2420
},
{
"epoch": 0.1787783479556365,
"grad_norm": 0.6014286279678345,
"learning_rate": 9.968142778517429e-05,
"loss": 3.5985,
"step": 2430
},
{
"epoch": 0.17951406132170905,
"grad_norm": 0.5852993726730347,
"learning_rate": 9.967696147154187e-05,
"loss": 3.4978,
"step": 2440
},
{
"epoch": 0.18024977468778164,
"grad_norm": 0.5915689468383789,
"learning_rate": 9.967246416855475e-05,
"loss": 3.5926,
"step": 2450
},
{
"epoch": 0.18098548805385423,
"grad_norm": 0.5336611866950989,
"learning_rate": 9.966793587901844e-05,
"loss": 3.5764,
"step": 2460
},
{
"epoch": 0.1817212014199268,
"grad_norm": 0.6106781959533691,
"learning_rate": 9.966337660575775e-05,
"loss": 3.5095,
"step": 2470
},
{
"epoch": 0.18245691478599937,
"grad_norm": 0.5323026180267334,
"learning_rate": 9.965878635161682e-05,
"loss": 3.4732,
"step": 2480
},
{
"epoch": 0.18319262815207196,
"grad_norm": 0.5882947444915771,
"learning_rate": 9.965416511945915e-05,
"loss": 3.56,
"step": 2490
},
{
"epoch": 0.18392834151814452,
"grad_norm": 0.5978416800498962,
"learning_rate": 9.964951291216755e-05,
"loss": 3.4982,
"step": 2500
},
{
"epoch": 0.1846640548842171,
"grad_norm": 0.5574873089790344,
"learning_rate": 9.964482973264413e-05,
"loss": 3.5024,
"step": 2510
},
{
"epoch": 0.1853997682502897,
"grad_norm": 0.6445927023887634,
"learning_rate": 9.964011558381035e-05,
"loss": 3.4935,
"step": 2520
},
{
"epoch": 0.18613548161636226,
"grad_norm": 0.5893427729606628,
"learning_rate": 9.963537046860697e-05,
"loss": 3.5344,
"step": 2530
},
{
"epoch": 0.18687119498243485,
"grad_norm": 0.5860798954963684,
"learning_rate": 9.963059438999409e-05,
"loss": 3.5498,
"step": 2540
},
{
"epoch": 0.18760690834850743,
"grad_norm": 0.5362831950187683,
"learning_rate": 9.962578735095109e-05,
"loss": 3.4655,
"step": 2550
},
{
"epoch": 0.18834262171458,
"grad_norm": 0.5293241143226624,
"learning_rate": 9.96209493544767e-05,
"loss": 3.5236,
"step": 2560
},
{
"epoch": 0.18907833508065258,
"grad_norm": 0.6069090366363525,
"learning_rate": 9.961608040358894e-05,
"loss": 3.5332,
"step": 2570
},
{
"epoch": 0.18981404844672514,
"grad_norm": 0.5620616674423218,
"learning_rate": 9.961118050132517e-05,
"loss": 3.4838,
"step": 2580
},
{
"epoch": 0.19054976181279773,
"grad_norm": 0.5729257464408875,
"learning_rate": 9.9606249650742e-05,
"loss": 3.4809,
"step": 2590
},
{
"epoch": 0.19128547517887032,
"grad_norm": 0.5876139998435974,
"learning_rate": 9.96012878549154e-05,
"loss": 3.4935,
"step": 2600
},
{
"epoch": 0.19202118854494288,
"grad_norm": 0.5324752330780029,
"learning_rate": 9.959629511694061e-05,
"loss": 3.5621,
"step": 2610
},
{
"epoch": 0.19275690191101547,
"grad_norm": 0.5787373781204224,
"learning_rate": 9.959127143993219e-05,
"loss": 3.4896,
"step": 2620
},
{
"epoch": 0.19349261527708805,
"grad_norm": 0.5609232783317566,
"learning_rate": 9.958621682702403e-05,
"loss": 3.4973,
"step": 2630
},
{
"epoch": 0.1942283286431606,
"grad_norm": 0.5869426131248474,
"learning_rate": 9.958113128136923e-05,
"loss": 3.5203,
"step": 2640
},
{
"epoch": 0.1949640420092332,
"grad_norm": 0.609747052192688,
"learning_rate": 9.957601480614029e-05,
"loss": 3.5297,
"step": 2650
},
{
"epoch": 0.1956997553753058,
"grad_norm": 0.5092261433601379,
"learning_rate": 9.957086740452894e-05,
"loss": 3.4951,
"step": 2660
},
{
"epoch": 0.19643546874137835,
"grad_norm": 0.5409265756607056,
"learning_rate": 9.956568907974621e-05,
"loss": 3.528,
"step": 2670
},
{
"epoch": 0.19717118210745094,
"grad_norm": 0.5979306101799011,
"learning_rate": 9.956047983502245e-05,
"loss": 3.5356,
"step": 2680
},
{
"epoch": 0.19790689547352353,
"grad_norm": 0.5668174624443054,
"learning_rate": 9.955523967360725e-05,
"loss": 3.5797,
"step": 2690
},
{
"epoch": 0.19864260883959609,
"grad_norm": 0.5992650389671326,
"learning_rate": 9.954996859876953e-05,
"loss": 3.5107,
"step": 2700
},
{
"epoch": 0.19937832220566867,
"grad_norm": 0.5725685358047485,
"learning_rate": 9.954466661379748e-05,
"loss": 3.5161,
"step": 2710
},
{
"epoch": 0.20011403557174126,
"grad_norm": 0.5398104786872864,
"learning_rate": 9.953933372199855e-05,
"loss": 3.5191,
"step": 2720
},
{
"epoch": 0.20084974893781382,
"grad_norm": 0.5120781064033508,
"learning_rate": 9.953396992669953e-05,
"loss": 3.4936,
"step": 2730
},
{
"epoch": 0.2015854623038864,
"grad_norm": 0.5185467004776001,
"learning_rate": 9.952857523124641e-05,
"loss": 3.4757,
"step": 2740
},
{
"epoch": 0.202321175669959,
"grad_norm": 0.6107959747314453,
"learning_rate": 9.952314963900453e-05,
"loss": 3.4972,
"step": 2750
},
{
"epoch": 0.20305688903603156,
"grad_norm": 0.5769765377044678,
"learning_rate": 9.951769315335844e-05,
"loss": 3.4983,
"step": 2760
},
{
"epoch": 0.20379260240210414,
"grad_norm": 0.5694507956504822,
"learning_rate": 9.951220577771201e-05,
"loss": 3.5063,
"step": 2770
},
{
"epoch": 0.2045283157681767,
"grad_norm": 0.5544769763946533,
"learning_rate": 9.950668751548835e-05,
"loss": 3.507,
"step": 2780
},
{
"epoch": 0.2052640291342493,
"grad_norm": 0.5395680665969849,
"learning_rate": 9.950113837012984e-05,
"loss": 3.5315,
"step": 2790
},
{
"epoch": 0.20599974250032188,
"grad_norm": 0.575812816619873,
"learning_rate": 9.949555834509817e-05,
"loss": 3.4873,
"step": 2800
},
{
"epoch": 0.20673545586639444,
"grad_norm": 0.5248579978942871,
"learning_rate": 9.948994744387419e-05,
"loss": 3.4849,
"step": 2810
},
{
"epoch": 0.20747116923246703,
"grad_norm": 0.5287348031997681,
"learning_rate": 9.948430566995816e-05,
"loss": 3.5028,
"step": 2820
},
{
"epoch": 0.20820688259853962,
"grad_norm": 0.5448064804077148,
"learning_rate": 9.947863302686945e-05,
"loss": 3.4801,
"step": 2830
},
{
"epoch": 0.20894259596461218,
"grad_norm": 0.583583652973175,
"learning_rate": 9.947292951814679e-05,
"loss": 3.4899,
"step": 2840
},
{
"epoch": 0.20967830933068476,
"grad_norm": 0.5897386074066162,
"learning_rate": 9.946719514734813e-05,
"loss": 3.5659,
"step": 2850
},
{
"epoch": 0.21041402269675735,
"grad_norm": 0.5261275172233582,
"learning_rate": 9.946142991805062e-05,
"loss": 3.4662,
"step": 2860
},
{
"epoch": 0.2111497360628299,
"grad_norm": 0.5870264768600464,
"learning_rate": 9.945563383385079e-05,
"loss": 3.5123,
"step": 2870
},
{
"epoch": 0.2118854494289025,
"grad_norm": 0.5746486186981201,
"learning_rate": 9.944980689836429e-05,
"loss": 3.4351,
"step": 2880
},
{
"epoch": 0.2126211627949751,
"grad_norm": 0.6177893877029419,
"learning_rate": 9.944394911522606e-05,
"loss": 3.5206,
"step": 2890
},
{
"epoch": 0.21335687616104765,
"grad_norm": 0.5619845390319824,
"learning_rate": 9.94380604880903e-05,
"loss": 3.4801,
"step": 2900
},
{
"epoch": 0.21409258952712024,
"grad_norm": 0.5628277063369751,
"learning_rate": 9.943214102063043e-05,
"loss": 3.5564,
"step": 2910
},
{
"epoch": 0.21482830289319282,
"grad_norm": 0.5306517481803894,
"learning_rate": 9.942619071653914e-05,
"loss": 3.5094,
"step": 2920
},
{
"epoch": 0.21556401625926538,
"grad_norm": 0.6212943196296692,
"learning_rate": 9.942020957952831e-05,
"loss": 3.5182,
"step": 2930
},
{
"epoch": 0.21629972962533797,
"grad_norm": 0.5883834362030029,
"learning_rate": 9.941419761332908e-05,
"loss": 3.4715,
"step": 2940
},
{
"epoch": 0.21703544299141056,
"grad_norm": 0.5104158520698547,
"learning_rate": 9.940815482169184e-05,
"loss": 3.4712,
"step": 2950
},
{
"epoch": 0.21777115635748312,
"grad_norm": 0.5349141955375671,
"learning_rate": 9.940208120838616e-05,
"loss": 3.4517,
"step": 2960
},
{
"epoch": 0.2185068697235557,
"grad_norm": 0.555456280708313,
"learning_rate": 9.939597677720089e-05,
"loss": 3.4984,
"step": 2970
},
{
"epoch": 0.21924258308962827,
"grad_norm": 0.5867215991020203,
"learning_rate": 9.938984153194406e-05,
"loss": 3.4821,
"step": 2980
},
{
"epoch": 0.21997829645570086,
"grad_norm": 0.5781378149986267,
"learning_rate": 9.938367547644296e-05,
"loss": 3.4437,
"step": 2990
},
{
"epoch": 0.22071400982177344,
"grad_norm": 0.5571138858795166,
"learning_rate": 9.937747861454407e-05,
"loss": 3.4935,
"step": 3000
},
{
"epoch": 0.221449723187846,
"grad_norm": 0.47858932614326477,
"learning_rate": 9.93712509501131e-05,
"loss": 3.499,
"step": 3010
},
{
"epoch": 0.2221854365539186,
"grad_norm": 0.500126838684082,
"learning_rate": 9.936499248703499e-05,
"loss": 3.4822,
"step": 3020
},
{
"epoch": 0.22292114991999118,
"grad_norm": 0.5339503288269043,
"learning_rate": 9.935870322921387e-05,
"loss": 3.5028,
"step": 3030
},
{
"epoch": 0.22365686328606374,
"grad_norm": 0.5465017557144165,
"learning_rate": 9.93523831805731e-05,
"loss": 3.4338,
"step": 3040
},
{
"epoch": 0.22439257665213633,
"grad_norm": 0.5432729125022888,
"learning_rate": 9.934603234505519e-05,
"loss": 3.4831,
"step": 3050
},
{
"epoch": 0.22512829001820892,
"grad_norm": 0.5051527619361877,
"learning_rate": 9.933965072662197e-05,
"loss": 3.4473,
"step": 3060
},
{
"epoch": 0.22586400338428148,
"grad_norm": 0.5150954127311707,
"learning_rate": 9.933323832925437e-05,
"loss": 3.4755,
"step": 3070
},
{
"epoch": 0.22659971675035406,
"grad_norm": 0.5967200398445129,
"learning_rate": 9.932679515695253e-05,
"loss": 3.4938,
"step": 3080
},
{
"epoch": 0.22733543011642665,
"grad_norm": 0.5499495267868042,
"learning_rate": 9.932032121373587e-05,
"loss": 3.5033,
"step": 3090
},
{
"epoch": 0.2280711434824992,
"grad_norm": 0.502854585647583,
"learning_rate": 9.931381650364291e-05,
"loss": 3.3716,
"step": 3100
},
{
"epoch": 0.2288068568485718,
"grad_norm": 0.5126801133155823,
"learning_rate": 9.93072810307314e-05,
"loss": 3.4727,
"step": 3110
},
{
"epoch": 0.2295425702146444,
"grad_norm": 0.48045796155929565,
"learning_rate": 9.930071479907831e-05,
"loss": 3.4312,
"step": 3120
},
{
"epoch": 0.23027828358071695,
"grad_norm": 0.5664313435554504,
"learning_rate": 9.929411781277974e-05,
"loss": 3.4225,
"step": 3130
},
{
"epoch": 0.23101399694678953,
"grad_norm": 0.5236510634422302,
"learning_rate": 9.928749007595101e-05,
"loss": 3.4255,
"step": 3140
},
{
"epoch": 0.23174971031286212,
"grad_norm": 0.5875115990638733,
"learning_rate": 9.928083159272666e-05,
"loss": 3.4699,
"step": 3150
},
{
"epoch": 0.23248542367893468,
"grad_norm": 0.5420896410942078,
"learning_rate": 9.92741423672603e-05,
"loss": 3.3887,
"step": 3160
},
{
"epoch": 0.23322113704500727,
"grad_norm": 0.5325738191604614,
"learning_rate": 9.926742240372483e-05,
"loss": 3.4807,
"step": 3170
},
{
"epoch": 0.23395685041107983,
"grad_norm": 0.5513830780982971,
"learning_rate": 9.926067170631227e-05,
"loss": 3.4647,
"step": 3180
},
{
"epoch": 0.23469256377715242,
"grad_norm": 0.5124702453613281,
"learning_rate": 9.925389027923382e-05,
"loss": 3.4392,
"step": 3190
},
{
"epoch": 0.235428277143225,
"grad_norm": 0.532706081867218,
"learning_rate": 9.924707812671985e-05,
"loss": 3.4456,
"step": 3200
},
{
"epoch": 0.23616399050929757,
"grad_norm": 0.5108603835105896,
"learning_rate": 9.924023525301991e-05,
"loss": 3.4621,
"step": 3210
},
{
"epoch": 0.23689970387537015,
"grad_norm": 0.5478849411010742,
"learning_rate": 9.92333616624027e-05,
"loss": 3.4602,
"step": 3220
},
{
"epoch": 0.23763541724144274,
"grad_norm": 0.481143057346344,
"learning_rate": 9.922645735915608e-05,
"loss": 3.4647,
"step": 3230
},
{
"epoch": 0.2383711306075153,
"grad_norm": 0.5544288754463196,
"learning_rate": 9.921952234758709e-05,
"loss": 3.4312,
"step": 3240
},
{
"epoch": 0.2391068439735879,
"grad_norm": 0.5568479299545288,
"learning_rate": 9.921255663202189e-05,
"loss": 3.4306,
"step": 3250
},
{
"epoch": 0.23984255733966048,
"grad_norm": 0.5197471380233765,
"learning_rate": 9.92055602168058e-05,
"loss": 3.4488,
"step": 3260
},
{
"epoch": 0.24057827070573304,
"grad_norm": 0.5361900329589844,
"learning_rate": 9.919853310630336e-05,
"loss": 3.395,
"step": 3270
},
{
"epoch": 0.24131398407180563,
"grad_norm": 0.5017499327659607,
"learning_rate": 9.919147530489816e-05,
"loss": 3.4654,
"step": 3280
},
{
"epoch": 0.24204969743787821,
"grad_norm": 0.5076097846031189,
"learning_rate": 9.9184386816993e-05,
"loss": 3.3991,
"step": 3290
},
{
"epoch": 0.24278541080395077,
"grad_norm": 0.5834246873855591,
"learning_rate": 9.917726764700981e-05,
"loss": 3.4058,
"step": 3300
},
{
"epoch": 0.24352112417002336,
"grad_norm": 0.5632571578025818,
"learning_rate": 9.917011779938961e-05,
"loss": 3.4442,
"step": 3310
},
{
"epoch": 0.24425683753609595,
"grad_norm": 0.5473082065582275,
"learning_rate": 9.916293727859265e-05,
"loss": 3.4536,
"step": 3320
},
{
"epoch": 0.2449925509021685,
"grad_norm": 0.5029418468475342,
"learning_rate": 9.915572608909824e-05,
"loss": 3.4263,
"step": 3330
},
{
"epoch": 0.2457282642682411,
"grad_norm": 0.5429378151893616,
"learning_rate": 9.914848423540483e-05,
"loss": 3.4652,
"step": 3340
},
{
"epoch": 0.24646397763431366,
"grad_norm": 0.5347001552581787,
"learning_rate": 9.914121172203005e-05,
"loss": 3.4009,
"step": 3350
},
{
"epoch": 0.24719969100038625,
"grad_norm": 0.538618266582489,
"learning_rate": 9.913390855351058e-05,
"loss": 3.457,
"step": 3360
},
{
"epoch": 0.24793540436645883,
"grad_norm": 0.5618345141410828,
"learning_rate": 9.912657473440232e-05,
"loss": 3.4588,
"step": 3370
},
{
"epoch": 0.2486711177325314,
"grad_norm": 0.5444225072860718,
"learning_rate": 9.911921026928019e-05,
"loss": 3.4401,
"step": 3380
},
{
"epoch": 0.24940683109860398,
"grad_norm": 0.5804809927940369,
"learning_rate": 9.911181516273826e-05,
"loss": 3.3904,
"step": 3390
},
{
"epoch": 0.25014254446467654,
"grad_norm": 0.5047810673713684,
"learning_rate": 9.910438941938978e-05,
"loss": 3.42,
"step": 3400
},
{
"epoch": 0.25087825783074913,
"grad_norm": 0.5213153958320618,
"learning_rate": 9.9096933043867e-05,
"loss": 3.4572,
"step": 3410
},
{
"epoch": 0.2516139711968217,
"grad_norm": 0.49462226033210754,
"learning_rate": 9.908944604082138e-05,
"loss": 3.432,
"step": 3420
},
{
"epoch": 0.2523496845628943,
"grad_norm": 0.5353688597679138,
"learning_rate": 9.908192841492343e-05,
"loss": 3.4174,
"step": 3430
},
{
"epoch": 0.2530853979289669,
"grad_norm": 0.4931166470050812,
"learning_rate": 9.907438017086277e-05,
"loss": 3.4175,
"step": 3440
},
{
"epoch": 0.2538211112950394,
"grad_norm": 0.5079531669616699,
"learning_rate": 9.906680131334813e-05,
"loss": 3.478,
"step": 3450
},
{
"epoch": 0.254556824661112,
"grad_norm": 0.5377930402755737,
"learning_rate": 9.905919184710733e-05,
"loss": 3.4353,
"step": 3460
},
{
"epoch": 0.2552925380271846,
"grad_norm": 0.5525156855583191,
"learning_rate": 9.90515517768873e-05,
"loss": 3.4084,
"step": 3470
},
{
"epoch": 0.2560282513932572,
"grad_norm": 0.5057874321937561,
"learning_rate": 9.904388110745403e-05,
"loss": 3.4503,
"step": 3480
},
{
"epoch": 0.2567639647593298,
"grad_norm": 0.5415982007980347,
"learning_rate": 9.903617984359263e-05,
"loss": 3.412,
"step": 3490
},
{
"epoch": 0.25749967812540236,
"grad_norm": 0.5116530656814575,
"learning_rate": 9.902844799010729e-05,
"loss": 3.3947,
"step": 3500
},
{
"epoch": 0.2582353914914749,
"grad_norm": 0.49354326725006104,
"learning_rate": 9.902068555182124e-05,
"loss": 3.4183,
"step": 3510
},
{
"epoch": 0.2589711048575475,
"grad_norm": 0.5207719206809998,
"learning_rate": 9.901289253357688e-05,
"loss": 3.4225,
"step": 3520
},
{
"epoch": 0.2597068182236201,
"grad_norm": 0.5140487551689148,
"learning_rate": 9.900506894023558e-05,
"loss": 3.4375,
"step": 3530
},
{
"epoch": 0.26044253158969266,
"grad_norm": 0.5068781971931458,
"learning_rate": 9.899721477667785e-05,
"loss": 3.3917,
"step": 3540
},
{
"epoch": 0.26117824495576525,
"grad_norm": 0.5903786420822144,
"learning_rate": 9.898933004780328e-05,
"loss": 3.4376,
"step": 3550
},
{
"epoch": 0.26191395832183784,
"grad_norm": 0.5345304012298584,
"learning_rate": 9.898141475853046e-05,
"loss": 3.4211,
"step": 3560
},
{
"epoch": 0.26264967168791037,
"grad_norm": 0.5153301954269409,
"learning_rate": 9.89734689137971e-05,
"loss": 3.4378,
"step": 3570
},
{
"epoch": 0.26338538505398296,
"grad_norm": 0.48121339082717896,
"learning_rate": 9.896549251855998e-05,
"loss": 3.4369,
"step": 3580
},
{
"epoch": 0.26412109842005554,
"grad_norm": 0.49092957377433777,
"learning_rate": 9.89574855777949e-05,
"loss": 3.3808,
"step": 3590
},
{
"epoch": 0.26485681178612813,
"grad_norm": 0.49230051040649414,
"learning_rate": 9.894944809649671e-05,
"loss": 3.4153,
"step": 3600
},
{
"epoch": 0.2655925251522007,
"grad_norm": 0.542644739151001,
"learning_rate": 9.894138007967935e-05,
"loss": 3.4127,
"step": 3610
},
{
"epoch": 0.2663282385182733,
"grad_norm": 0.49647256731987,
"learning_rate": 9.893328153237578e-05,
"loss": 3.3944,
"step": 3620
},
{
"epoch": 0.26706395188434584,
"grad_norm": 0.4804913103580475,
"learning_rate": 9.892515245963803e-05,
"loss": 3.4299,
"step": 3630
},
{
"epoch": 0.26779966525041843,
"grad_norm": 0.5026209354400635,
"learning_rate": 9.891699286653714e-05,
"loss": 3.4199,
"step": 3640
},
{
"epoch": 0.268535378616491,
"grad_norm": 0.5007442235946655,
"learning_rate": 9.890880275816322e-05,
"loss": 3.4058,
"step": 3650
},
{
"epoch": 0.2692710919825636,
"grad_norm": 0.49342918395996094,
"learning_rate": 9.890058213962538e-05,
"loss": 3.408,
"step": 3660
},
{
"epoch": 0.2700068053486362,
"grad_norm": 0.48717033863067627,
"learning_rate": 9.889233101605184e-05,
"loss": 3.3731,
"step": 3670
},
{
"epoch": 0.2707425187147087,
"grad_norm": 0.5098682045936584,
"learning_rate": 9.888404939258973e-05,
"loss": 3.3768,
"step": 3680
},
{
"epoch": 0.2714782320807813,
"grad_norm": 0.48432040214538574,
"learning_rate": 9.88757372744053e-05,
"loss": 3.4547,
"step": 3690
},
{
"epoch": 0.2722139454468539,
"grad_norm": 0.487289160490036,
"learning_rate": 9.886739466668379e-05,
"loss": 3.4094,
"step": 3700
},
{
"epoch": 0.2729496588129265,
"grad_norm": 0.5253422260284424,
"learning_rate": 9.885902157462948e-05,
"loss": 3.445,
"step": 3710
},
{
"epoch": 0.2736853721789991,
"grad_norm": 0.5656958222389221,
"learning_rate": 9.885061800346563e-05,
"loss": 3.3925,
"step": 3720
},
{
"epoch": 0.27442108554507166,
"grad_norm": 0.5607571601867676,
"learning_rate": 9.884218395843452e-05,
"loss": 3.386,
"step": 3730
},
{
"epoch": 0.2751567989111442,
"grad_norm": 0.48992305994033813,
"learning_rate": 9.883371944479749e-05,
"loss": 3.4261,
"step": 3740
},
{
"epoch": 0.2758925122772168,
"grad_norm": 0.5179588794708252,
"learning_rate": 9.882522446783484e-05,
"loss": 3.3555,
"step": 3750
},
{
"epoch": 0.27662822564328937,
"grad_norm": 0.5124242305755615,
"learning_rate": 9.88166990328459e-05,
"loss": 3.4095,
"step": 3760
},
{
"epoch": 0.27736393900936196,
"grad_norm": 0.5088645815849304,
"learning_rate": 9.880814314514894e-05,
"loss": 3.4152,
"step": 3770
},
{
"epoch": 0.27809965237543455,
"grad_norm": 0.5194174647331238,
"learning_rate": 9.87995568100813e-05,
"loss": 3.3998,
"step": 3780
},
{
"epoch": 0.27883536574150714,
"grad_norm": 0.5403995513916016,
"learning_rate": 9.879094003299928e-05,
"loss": 3.3553,
"step": 3790
},
{
"epoch": 0.27957107910757967,
"grad_norm": 0.5247926712036133,
"learning_rate": 9.87822928192782e-05,
"loss": 3.4321,
"step": 3800
},
{
"epoch": 0.28030679247365226,
"grad_norm": 0.5156255960464478,
"learning_rate": 9.877361517431231e-05,
"loss": 3.3851,
"step": 3810
},
{
"epoch": 0.28104250583972484,
"grad_norm": 0.4857509732246399,
"learning_rate": 9.876490710351489e-05,
"loss": 3.3663,
"step": 3820
},
{
"epoch": 0.28177821920579743,
"grad_norm": 0.5125151872634888,
"learning_rate": 9.875616861231819e-05,
"loss": 3.3637,
"step": 3830
},
{
"epoch": 0.28251393257187,
"grad_norm": 0.47020360827445984,
"learning_rate": 9.874739970617341e-05,
"loss": 3.4038,
"step": 3840
},
{
"epoch": 0.28324964593794255,
"grad_norm": 0.48255953192710876,
"learning_rate": 9.87386003905508e-05,
"loss": 3.3459,
"step": 3850
},
{
"epoch": 0.28398535930401514,
"grad_norm": 0.47846198081970215,
"learning_rate": 9.872977067093947e-05,
"loss": 3.376,
"step": 3860
},
{
"epoch": 0.2847210726700877,
"grad_norm": 0.5100752115249634,
"learning_rate": 9.872091055284756e-05,
"loss": 3.3609,
"step": 3870
},
{
"epoch": 0.2854567860361603,
"grad_norm": 0.5000672936439514,
"learning_rate": 9.87120200418022e-05,
"loss": 3.4512,
"step": 3880
},
{
"epoch": 0.2861924994022329,
"grad_norm": 0.5057271718978882,
"learning_rate": 9.870309914334942e-05,
"loss": 3.3253,
"step": 3890
},
{
"epoch": 0.2869282127683055,
"grad_norm": 0.5031580328941345,
"learning_rate": 9.869414786305424e-05,
"loss": 3.3809,
"step": 3900
},
{
"epoch": 0.287663926134378,
"grad_norm": 0.49000057578086853,
"learning_rate": 9.868516620650062e-05,
"loss": 3.4302,
"step": 3910
},
{
"epoch": 0.2883996395004506,
"grad_norm": 0.4677979052066803,
"learning_rate": 9.867615417929147e-05,
"loss": 3.3782,
"step": 3920
},
{
"epoch": 0.2891353528665232,
"grad_norm": 0.4826011061668396,
"learning_rate": 9.866711178704869e-05,
"loss": 3.3509,
"step": 3930
},
{
"epoch": 0.2898710662325958,
"grad_norm": 0.5133295655250549,
"learning_rate": 9.865803903541301e-05,
"loss": 3.4039,
"step": 3940
},
{
"epoch": 0.2906067795986684,
"grad_norm": 0.5011733174324036,
"learning_rate": 9.864893593004422e-05,
"loss": 3.3433,
"step": 3950
},
{
"epoch": 0.29134249296474096,
"grad_norm": 0.49504631757736206,
"learning_rate": 9.863980247662099e-05,
"loss": 3.3795,
"step": 3960
},
{
"epoch": 0.2920782063308135,
"grad_norm": 0.5216391682624817,
"learning_rate": 9.863063868084093e-05,
"loss": 3.4249,
"step": 3970
},
{
"epoch": 0.2928139196968861,
"grad_norm": 0.5909170508384705,
"learning_rate": 9.862144454842055e-05,
"loss": 3.341,
"step": 3980
},
{
"epoch": 0.29354963306295867,
"grad_norm": 0.5585739016532898,
"learning_rate": 9.861222008509534e-05,
"loss": 3.4334,
"step": 3990
},
{
"epoch": 0.29428534642903126,
"grad_norm": 0.5350683927536011,
"learning_rate": 9.860296529661966e-05,
"loss": 3.4152,
"step": 4000
}
],
"logging_steps": 10,
"max_steps": 40776,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"save_steps": 4000,
"total_flos": 3.62650798129152e+17,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}