| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.1938677738741617, | |
| "eval_steps": 1000, | |
| "global_step": 5000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.015969338869370808, | |
| "grad_norm": 17.92350196838379, | |
| "learning_rate": 4.800000000000001e-07, | |
| "loss": 3.223, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.031938677738741615, | |
| "grad_norm": 11.101584434509277, | |
| "learning_rate": 9.800000000000001e-07, | |
| "loss": 2.5321, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.047908016608112426, | |
| "grad_norm": 9.936028480529785, | |
| "learning_rate": 1.48e-06, | |
| "loss": 2.0032, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.06387735547748323, | |
| "grad_norm": 10.770648956298828, | |
| "learning_rate": 1.98e-06, | |
| "loss": 1.6134, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.07984669434685404, | |
| "grad_norm": 10.68463134765625, | |
| "learning_rate": 2.4800000000000004e-06, | |
| "loss": 1.5694, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.09581603321622485, | |
| "grad_norm": 10.635124206542969, | |
| "learning_rate": 2.9800000000000003e-06, | |
| "loss": 1.4934, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.11178537208559565, | |
| "grad_norm": 9.225995063781738, | |
| "learning_rate": 3.48e-06, | |
| "loss": 1.518, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.12775471095496646, | |
| "grad_norm": 9.05696964263916, | |
| "learning_rate": 3.980000000000001e-06, | |
| "loss": 1.4258, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.14372404982433729, | |
| "grad_norm": 9.599803924560547, | |
| "learning_rate": 4.48e-06, | |
| "loss": 1.422, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.15969338869370808, | |
| "grad_norm": 9.442488670349121, | |
| "learning_rate": 4.980000000000001e-06, | |
| "loss": 1.3208, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.17566272756307888, | |
| "grad_norm": 10.746581077575684, | |
| "learning_rate": 5.480000000000001e-06, | |
| "loss": 1.3997, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.1916320664324497, | |
| "grad_norm": 9.297645568847656, | |
| "learning_rate": 5.98e-06, | |
| "loss": 1.3343, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.2076014053018205, | |
| "grad_norm": 10.026762962341309, | |
| "learning_rate": 6.480000000000001e-06, | |
| "loss": 1.3353, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.2235707441711913, | |
| "grad_norm": 9.392842292785645, | |
| "learning_rate": 6.98e-06, | |
| "loss": 1.3451, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.23954008304056212, | |
| "grad_norm": 7.376865386962891, | |
| "learning_rate": 7.48e-06, | |
| "loss": 1.2645, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.2555094219099329, | |
| "grad_norm": 10.001627922058105, | |
| "learning_rate": 7.980000000000002e-06, | |
| "loss": 1.271, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.2714787607793037, | |
| "grad_norm": 7.699875354766846, | |
| "learning_rate": 8.48e-06, | |
| "loss": 1.2116, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 0.28744809964867457, | |
| "grad_norm": 8.733208656311035, | |
| "learning_rate": 8.98e-06, | |
| "loss": 1.2222, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.30341743851804537, | |
| "grad_norm": 8.286600112915039, | |
| "learning_rate": 9.48e-06, | |
| "loss": 1.2134, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 0.31938677738741617, | |
| "grad_norm": 7.408142566680908, | |
| "learning_rate": 9.980000000000001e-06, | |
| "loss": 1.1662, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.33535611625678696, | |
| "grad_norm": 9.274364471435547, | |
| "learning_rate": 9.946666666666667e-06, | |
| "loss": 1.2752, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 0.35132545512615776, | |
| "grad_norm": 8.4090576171875, | |
| "learning_rate": 9.891111111111113e-06, | |
| "loss": 1.2137, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.3672947939955286, | |
| "grad_norm": 8.74751091003418, | |
| "learning_rate": 9.835555555555556e-06, | |
| "loss": 1.1794, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 0.3832641328648994, | |
| "grad_norm": 7.037300109863281, | |
| "learning_rate": 9.780000000000001e-06, | |
| "loss": 1.1806, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.3992334717342702, | |
| "grad_norm": 8.758708953857422, | |
| "learning_rate": 9.724444444444445e-06, | |
| "loss": 1.0997, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 0.415202810603641, | |
| "grad_norm": 7.583318710327148, | |
| "learning_rate": 9.66888888888889e-06, | |
| "loss": 1.1122, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.4311721494730118, | |
| "grad_norm": 7.173635959625244, | |
| "learning_rate": 9.613333333333335e-06, | |
| "loss": 1.1167, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 0.4471414883423826, | |
| "grad_norm": 6.702845096588135, | |
| "learning_rate": 9.557777777777777e-06, | |
| "loss": 1.0873, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.46311082721175345, | |
| "grad_norm": 7.966395854949951, | |
| "learning_rate": 9.502222222222223e-06, | |
| "loss": 1.0764, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 0.47908016608112425, | |
| "grad_norm": 7.768787860870361, | |
| "learning_rate": 9.446666666666667e-06, | |
| "loss": 1.0985, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.49504950495049505, | |
| "grad_norm": 8.754780769348145, | |
| "learning_rate": 9.391111111111111e-06, | |
| "loss": 1.0646, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 0.5110188438198658, | |
| "grad_norm": 7.156813144683838, | |
| "learning_rate": 9.335555555555557e-06, | |
| "loss": 1.0149, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.5269881826892366, | |
| "grad_norm": 6.864979267120361, | |
| "learning_rate": 9.280000000000001e-06, | |
| "loss": 1.0514, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 0.5429575215586074, | |
| "grad_norm": 6.696143627166748, | |
| "learning_rate": 9.224444444444445e-06, | |
| "loss": 1.0376, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.5589268604279782, | |
| "grad_norm": 6.3973469734191895, | |
| "learning_rate": 9.168888888888889e-06, | |
| "loss": 0.992, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 0.5748961992973491, | |
| "grad_norm": 6.48210334777832, | |
| "learning_rate": 9.113333333333335e-06, | |
| "loss": 1.0463, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.5908655381667199, | |
| "grad_norm": 7.711927890777588, | |
| "learning_rate": 9.057777777777779e-06, | |
| "loss": 1.0023, | |
| "step": 925 | |
| }, | |
| { | |
| "epoch": 0.6068348770360907, | |
| "grad_norm": 7.2077250480651855, | |
| "learning_rate": 9.002222222222223e-06, | |
| "loss": 1.0283, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.6228042159054615, | |
| "grad_norm": 7.416881561279297, | |
| "learning_rate": 8.946666666666669e-06, | |
| "loss": 1.0249, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 0.6387735547748323, | |
| "grad_norm": 6.398010730743408, | |
| "learning_rate": 8.891111111111111e-06, | |
| "loss": 0.9546, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.6387735547748323, | |
| "eval_loss": 0.4855521023273468, | |
| "eval_runtime": 1667.9567, | |
| "eval_samples_per_second": 2.339, | |
| "eval_steps_per_second": 0.146, | |
| "eval_wer": 0.3615418266660186, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.6547428936442031, | |
| "grad_norm": 5.443120956420898, | |
| "learning_rate": 8.835555555555557e-06, | |
| "loss": 1.013, | |
| "step": 1025 | |
| }, | |
| { | |
| "epoch": 0.6707122325135739, | |
| "grad_norm": 7.361939907073975, | |
| "learning_rate": 8.78e-06, | |
| "loss": 0.946, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.6866815713829447, | |
| "grad_norm": 6.80987024307251, | |
| "learning_rate": 8.724444444444445e-06, | |
| "loss": 0.9945, | |
| "step": 1075 | |
| }, | |
| { | |
| "epoch": 0.7026509102523155, | |
| "grad_norm": 6.040420055389404, | |
| "learning_rate": 8.66888888888889e-06, | |
| "loss": 1.0078, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.7186202491216863, | |
| "grad_norm": 7.904597282409668, | |
| "learning_rate": 8.613333333333333e-06, | |
| "loss": 0.9707, | |
| "step": 1125 | |
| }, | |
| { | |
| "epoch": 0.7345895879910572, | |
| "grad_norm": 6.9557204246521, | |
| "learning_rate": 8.557777777777778e-06, | |
| "loss": 0.9712, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 0.750558926860428, | |
| "grad_norm": 5.4510178565979, | |
| "learning_rate": 8.502222222222223e-06, | |
| "loss": 0.9659, | |
| "step": 1175 | |
| }, | |
| { | |
| "epoch": 0.7665282657297988, | |
| "grad_norm": 5.72000789642334, | |
| "learning_rate": 8.446666666666668e-06, | |
| "loss": 0.9368, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.7824976045991696, | |
| "grad_norm": 5.816184043884277, | |
| "learning_rate": 8.391111111111112e-06, | |
| "loss": 0.9089, | |
| "step": 1225 | |
| }, | |
| { | |
| "epoch": 0.7984669434685404, | |
| "grad_norm": 6.033445835113525, | |
| "learning_rate": 8.335555555555556e-06, | |
| "loss": 0.9502, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 0.8144362823379112, | |
| "grad_norm": 5.273908615112305, | |
| "learning_rate": 8.28e-06, | |
| "loss": 0.9151, | |
| "step": 1275 | |
| }, | |
| { | |
| "epoch": 0.830405621207282, | |
| "grad_norm": 6.122651100158691, | |
| "learning_rate": 8.224444444444444e-06, | |
| "loss": 0.9517, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.8463749600766528, | |
| "grad_norm": 6.673498630523682, | |
| "learning_rate": 8.16888888888889e-06, | |
| "loss": 1.0318, | |
| "step": 1325 | |
| }, | |
| { | |
| "epoch": 0.8623442989460236, | |
| "grad_norm": 7.197372913360596, | |
| "learning_rate": 8.113333333333334e-06, | |
| "loss": 0.937, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 0.8783136378153944, | |
| "grad_norm": 6.718713283538818, | |
| "learning_rate": 8.057777777777778e-06, | |
| "loss": 0.9325, | |
| "step": 1375 | |
| }, | |
| { | |
| "epoch": 0.8942829766847652, | |
| "grad_norm": 7.090008735656738, | |
| "learning_rate": 8.002222222222222e-06, | |
| "loss": 0.9044, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.9102523155541361, | |
| "grad_norm": 8.890588760375977, | |
| "learning_rate": 7.946666666666666e-06, | |
| "loss": 0.8935, | |
| "step": 1425 | |
| }, | |
| { | |
| "epoch": 0.9262216544235069, | |
| "grad_norm": 5.521778583526611, | |
| "learning_rate": 7.891111111111112e-06, | |
| "loss": 0.8857, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 0.9421909932928777, | |
| "grad_norm": 6.829771041870117, | |
| "learning_rate": 7.835555555555556e-06, | |
| "loss": 0.9411, | |
| "step": 1475 | |
| }, | |
| { | |
| "epoch": 0.9581603321622485, | |
| "grad_norm": 6.48971700668335, | |
| "learning_rate": 7.78e-06, | |
| "loss": 0.8616, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.9741296710316193, | |
| "grad_norm": 5.809508323669434, | |
| "learning_rate": 7.724444444444446e-06, | |
| "loss": 0.8976, | |
| "step": 1525 | |
| }, | |
| { | |
| "epoch": 0.9900990099009901, | |
| "grad_norm": 6.918030738830566, | |
| "learning_rate": 7.66888888888889e-06, | |
| "loss": 0.9213, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 1.006068348770361, | |
| "grad_norm": 5.847545623779297, | |
| "learning_rate": 7.613333333333334e-06, | |
| "loss": 0.813, | |
| "step": 1575 | |
| }, | |
| { | |
| "epoch": 1.0220376876397317, | |
| "grad_norm": 5.331517219543457, | |
| "learning_rate": 7.557777777777779e-06, | |
| "loss": 0.6469, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 1.0380070265091026, | |
| "grad_norm": 7.251556396484375, | |
| "learning_rate": 7.502222222222223e-06, | |
| "loss": 0.646, | |
| "step": 1625 | |
| }, | |
| { | |
| "epoch": 1.0539763653784733, | |
| "grad_norm": 5.755091667175293, | |
| "learning_rate": 7.446666666666668e-06, | |
| "loss": 0.6496, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 1.0699457042478442, | |
| "grad_norm": 5.709854602813721, | |
| "learning_rate": 7.3911111111111125e-06, | |
| "loss": 0.6459, | |
| "step": 1675 | |
| }, | |
| { | |
| "epoch": 1.0859150431172149, | |
| "grad_norm": 5.866008281707764, | |
| "learning_rate": 7.335555555555556e-06, | |
| "loss": 0.6629, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 1.1018843819865858, | |
| "grad_norm": 5.575136184692383, | |
| "learning_rate": 7.280000000000001e-06, | |
| "loss": 0.6724, | |
| "step": 1725 | |
| }, | |
| { | |
| "epoch": 1.1178537208559565, | |
| "grad_norm": 5.722553730010986, | |
| "learning_rate": 7.224444444444445e-06, | |
| "loss": 0.6946, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 1.1338230597253274, | |
| "grad_norm": 5.85053825378418, | |
| "learning_rate": 7.1688888888888895e-06, | |
| "loss": 0.6676, | |
| "step": 1775 | |
| }, | |
| { | |
| "epoch": 1.1497923985946983, | |
| "grad_norm": 6.432461261749268, | |
| "learning_rate": 7.113333333333334e-06, | |
| "loss": 0.6381, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 1.165761737464069, | |
| "grad_norm": 6.030885696411133, | |
| "learning_rate": 7.057777777777778e-06, | |
| "loss": 0.683, | |
| "step": 1825 | |
| }, | |
| { | |
| "epoch": 1.1817310763334399, | |
| "grad_norm": 5.215100288391113, | |
| "learning_rate": 7.0022222222222225e-06, | |
| "loss": 0.6623, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 1.1977004152028106, | |
| "grad_norm": 5.460089206695557, | |
| "learning_rate": 6.946666666666667e-06, | |
| "loss": 0.6519, | |
| "step": 1875 | |
| }, | |
| { | |
| "epoch": 1.2136697540721815, | |
| "grad_norm": 5.882613182067871, | |
| "learning_rate": 6.891111111111111e-06, | |
| "loss": 0.6788, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 1.2296390929415522, | |
| "grad_norm": 5.0330915451049805, | |
| "learning_rate": 6.835555555555556e-06, | |
| "loss": 0.6654, | |
| "step": 1925 | |
| }, | |
| { | |
| "epoch": 1.245608431810923, | |
| "grad_norm": 4.624293804168701, | |
| "learning_rate": 6.780000000000001e-06, | |
| "loss": 0.6394, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 1.2615777706802938, | |
| "grad_norm": 5.252276420593262, | |
| "learning_rate": 6.724444444444444e-06, | |
| "loss": 0.6522, | |
| "step": 1975 | |
| }, | |
| { | |
| "epoch": 1.2775471095496647, | |
| "grad_norm": 5.393728733062744, | |
| "learning_rate": 6.668888888888889e-06, | |
| "loss": 0.6673, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.2775471095496647, | |
| "eval_loss": 0.41851192712783813, | |
| "eval_runtime": 1656.9911, | |
| "eval_samples_per_second": 2.354, | |
| "eval_steps_per_second": 0.147, | |
| "eval_wer": 0.31497593933796725, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.2935164484190356, | |
| "grad_norm": 7.740047454833984, | |
| "learning_rate": 6.613333333333334e-06, | |
| "loss": 0.643, | |
| "step": 2025 | |
| }, | |
| { | |
| "epoch": 1.3094857872884063, | |
| "grad_norm": 4.754881381988525, | |
| "learning_rate": 6.557777777777778e-06, | |
| "loss": 0.6545, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 1.325455126157777, | |
| "grad_norm": 5.5493693351745605, | |
| "learning_rate": 6.502222222222223e-06, | |
| "loss": 0.6741, | |
| "step": 2075 | |
| }, | |
| { | |
| "epoch": 1.3414244650271478, | |
| "grad_norm": 5.743963241577148, | |
| "learning_rate": 6.446666666666668e-06, | |
| "loss": 0.65, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 1.3573938038965188, | |
| "grad_norm": 6.479578495025635, | |
| "learning_rate": 6.391111111111111e-06, | |
| "loss": 0.6345, | |
| "step": 2125 | |
| }, | |
| { | |
| "epoch": 1.3733631427658894, | |
| "grad_norm": 5.8687286376953125, | |
| "learning_rate": 6.335555555555556e-06, | |
| "loss": 0.6612, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 1.3893324816352604, | |
| "grad_norm": 4.9471893310546875, | |
| "learning_rate": 6.280000000000001e-06, | |
| "loss": 0.6616, | |
| "step": 2175 | |
| }, | |
| { | |
| "epoch": 1.405301820504631, | |
| "grad_norm": 4.968109130859375, | |
| "learning_rate": 6.224444444444445e-06, | |
| "loss": 0.6405, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 1.421271159374002, | |
| "grad_norm": 6.063320159912109, | |
| "learning_rate": 6.16888888888889e-06, | |
| "loss": 0.6615, | |
| "step": 2225 | |
| }, | |
| { | |
| "epoch": 1.4372404982433729, | |
| "grad_norm": 5.78763484954834, | |
| "learning_rate": 6.113333333333333e-06, | |
| "loss": 0.6308, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 1.4532098371127435, | |
| "grad_norm": 5.714231014251709, | |
| "learning_rate": 6.057777777777778e-06, | |
| "loss": 0.6619, | |
| "step": 2275 | |
| }, | |
| { | |
| "epoch": 1.4691791759821142, | |
| "grad_norm": 7.075171947479248, | |
| "learning_rate": 6.002222222222223e-06, | |
| "loss": 0.6748, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 1.4851485148514851, | |
| "grad_norm": 6.3147969245910645, | |
| "learning_rate": 5.946666666666668e-06, | |
| "loss": 0.6441, | |
| "step": 2325 | |
| }, | |
| { | |
| "epoch": 1.501117853720856, | |
| "grad_norm": 6.079730033874512, | |
| "learning_rate": 5.891111111111112e-06, | |
| "loss": 0.6303, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 1.5170871925902267, | |
| "grad_norm": 5.132657527923584, | |
| "learning_rate": 5.8355555555555565e-06, | |
| "loss": 0.6718, | |
| "step": 2375 | |
| }, | |
| { | |
| "epoch": 1.5330565314595974, | |
| "grad_norm": 5.566254138946533, | |
| "learning_rate": 5.78e-06, | |
| "loss": 0.6686, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 1.5490258703289683, | |
| "grad_norm": 6.299161911010742, | |
| "learning_rate": 5.724444444444445e-06, | |
| "loss": 0.6485, | |
| "step": 2425 | |
| }, | |
| { | |
| "epoch": 1.5649952091983392, | |
| "grad_norm": 5.586335182189941, | |
| "learning_rate": 5.6688888888888895e-06, | |
| "loss": 0.6031, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 1.5809645480677101, | |
| "grad_norm": 5.396686553955078, | |
| "learning_rate": 5.613333333333334e-06, | |
| "loss": 0.6407, | |
| "step": 2475 | |
| }, | |
| { | |
| "epoch": 1.5969338869370808, | |
| "grad_norm": 6.483650207519531, | |
| "learning_rate": 5.557777777777778e-06, | |
| "loss": 0.6703, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 1.6129032258064515, | |
| "grad_norm": 5.946717739105225, | |
| "learning_rate": 5.5022222222222224e-06, | |
| "loss": 0.6079, | |
| "step": 2525 | |
| }, | |
| { | |
| "epoch": 1.6288725646758224, | |
| "grad_norm": 5.817110061645508, | |
| "learning_rate": 5.4466666666666665e-06, | |
| "loss": 0.6275, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 1.6448419035451933, | |
| "grad_norm": 5.888713836669922, | |
| "learning_rate": 5.391111111111111e-06, | |
| "loss": 0.64, | |
| "step": 2575 | |
| }, | |
| { | |
| "epoch": 1.660811242414564, | |
| "grad_norm": 5.296940803527832, | |
| "learning_rate": 5.335555555555556e-06, | |
| "loss": 0.6278, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 1.6767805812839347, | |
| "grad_norm": 5.4542388916015625, | |
| "learning_rate": 5.28e-06, | |
| "loss": 0.6236, | |
| "step": 2625 | |
| }, | |
| { | |
| "epoch": 1.6927499201533056, | |
| "grad_norm": 5.980891227722168, | |
| "learning_rate": 5.224444444444445e-06, | |
| "loss": 0.6607, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 1.7087192590226765, | |
| "grad_norm": 7.3297014236450195, | |
| "learning_rate": 5.168888888888889e-06, | |
| "loss": 0.673, | |
| "step": 2675 | |
| }, | |
| { | |
| "epoch": 1.7246885978920474, | |
| "grad_norm": 4.739117622375488, | |
| "learning_rate": 5.113333333333333e-06, | |
| "loss": 0.5893, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 1.7406579367614181, | |
| "grad_norm": 4.754851818084717, | |
| "learning_rate": 5.057777777777778e-06, | |
| "loss": 0.6459, | |
| "step": 2725 | |
| }, | |
| { | |
| "epoch": 1.7566272756307888, | |
| "grad_norm": 4.72427225112915, | |
| "learning_rate": 5.002222222222223e-06, | |
| "loss": 0.6093, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 1.7725966145001597, | |
| "grad_norm": 5.871730327606201, | |
| "learning_rate": 4.946666666666667e-06, | |
| "loss": 0.6088, | |
| "step": 2775 | |
| }, | |
| { | |
| "epoch": 1.7885659533695306, | |
| "grad_norm": 5.640221118927002, | |
| "learning_rate": 4.891111111111111e-06, | |
| "loss": 0.6214, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 1.8045352922389013, | |
| "grad_norm": 5.749293327331543, | |
| "learning_rate": 4.835555555555556e-06, | |
| "loss": 0.6105, | |
| "step": 2825 | |
| }, | |
| { | |
| "epoch": 1.820504631108272, | |
| "grad_norm": 6.414817810058594, | |
| "learning_rate": 4.78e-06, | |
| "loss": 0.6523, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 1.836473969977643, | |
| "grad_norm": 5.655066967010498, | |
| "learning_rate": 4.724444444444445e-06, | |
| "loss": 0.6348, | |
| "step": 2875 | |
| }, | |
| { | |
| "epoch": 1.8524433088470138, | |
| "grad_norm": 5.395172119140625, | |
| "learning_rate": 4.66888888888889e-06, | |
| "loss": 0.634, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 1.8684126477163845, | |
| "grad_norm": 4.894425868988037, | |
| "learning_rate": 4.613333333333334e-06, | |
| "loss": 0.595, | |
| "step": 2925 | |
| }, | |
| { | |
| "epoch": 1.8843819865857554, | |
| "grad_norm": 5.686845779418945, | |
| "learning_rate": 4.557777777777778e-06, | |
| "loss": 0.6113, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 1.900351325455126, | |
| "grad_norm": 5.444372177124023, | |
| "learning_rate": 4.502222222222223e-06, | |
| "loss": 0.6277, | |
| "step": 2975 | |
| }, | |
| { | |
| "epoch": 1.916320664324497, | |
| "grad_norm": 5.224650859832764, | |
| "learning_rate": 4.446666666666667e-06, | |
| "loss": 0.6601, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.916320664324497, | |
| "eval_loss": 0.389792263507843, | |
| "eval_runtime": 1666.4367, | |
| "eval_samples_per_second": 2.341, | |
| "eval_steps_per_second": 0.146, | |
| "eval_wer": 0.2912798327905507, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.932290003193868, | |
| "grad_norm": 4.736299514770508, | |
| "learning_rate": 4.391111111111112e-06, | |
| "loss": 0.6351, | |
| "step": 3025 | |
| }, | |
| { | |
| "epoch": 1.9482593420632386, | |
| "grad_norm": 4.797982692718506, | |
| "learning_rate": 4.3355555555555565e-06, | |
| "loss": 0.6017, | |
| "step": 3050 | |
| }, | |
| { | |
| "epoch": 1.9642286809326093, | |
| "grad_norm": 5.4142022132873535, | |
| "learning_rate": 4.2800000000000005e-06, | |
| "loss": 0.6124, | |
| "step": 3075 | |
| }, | |
| { | |
| "epoch": 1.9801980198019802, | |
| "grad_norm": 5.374582767486572, | |
| "learning_rate": 4.2244444444444446e-06, | |
| "loss": 0.6243, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 1.996167358671351, | |
| "grad_norm": 4.480958938598633, | |
| "learning_rate": 4.168888888888889e-06, | |
| "loss": 0.5981, | |
| "step": 3125 | |
| }, | |
| { | |
| "epoch": 2.012136697540722, | |
| "grad_norm": 5.1775736808776855, | |
| "learning_rate": 4.1133333333333335e-06, | |
| "loss": 0.4607, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 2.0281060364100925, | |
| "grad_norm": 4.18350887298584, | |
| "learning_rate": 4.057777777777778e-06, | |
| "loss": 0.3907, | |
| "step": 3175 | |
| }, | |
| { | |
| "epoch": 2.0440753752794634, | |
| "grad_norm": 4.902673721313477, | |
| "learning_rate": 4.002222222222222e-06, | |
| "loss": 0.4004, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 2.0600447141488343, | |
| "grad_norm": 4.528185844421387, | |
| "learning_rate": 3.946666666666667e-06, | |
| "loss": 0.3936, | |
| "step": 3225 | |
| }, | |
| { | |
| "epoch": 2.076014053018205, | |
| "grad_norm": 5.0421061515808105, | |
| "learning_rate": 3.891111111111111e-06, | |
| "loss": 0.4242, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 2.0919833918875756, | |
| "grad_norm": 4.861361026763916, | |
| "learning_rate": 3.835555555555555e-06, | |
| "loss": 0.3916, | |
| "step": 3275 | |
| }, | |
| { | |
| "epoch": 2.1079527307569466, | |
| "grad_norm": 6.367924213409424, | |
| "learning_rate": 3.7800000000000002e-06, | |
| "loss": 0.413, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 2.1239220696263175, | |
| "grad_norm": 3.6156017780303955, | |
| "learning_rate": 3.724444444444445e-06, | |
| "loss": 0.4103, | |
| "step": 3325 | |
| }, | |
| { | |
| "epoch": 2.1398914084956884, | |
| "grad_norm": 5.132371425628662, | |
| "learning_rate": 3.668888888888889e-06, | |
| "loss": 0.407, | |
| "step": 3350 | |
| }, | |
| { | |
| "epoch": 2.1558607473650593, | |
| "grad_norm": 4.446967601776123, | |
| "learning_rate": 3.6133333333333336e-06, | |
| "loss": 0.4082, | |
| "step": 3375 | |
| }, | |
| { | |
| "epoch": 2.1718300862344297, | |
| "grad_norm": 5.18086576461792, | |
| "learning_rate": 3.5577777777777785e-06, | |
| "loss": 0.4053, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 2.1877994251038007, | |
| "grad_norm": 4.955840587615967, | |
| "learning_rate": 3.5022222222222225e-06, | |
| "loss": 0.3995, | |
| "step": 3425 | |
| }, | |
| { | |
| "epoch": 2.2037687639731716, | |
| "grad_norm": 4.59506368637085, | |
| "learning_rate": 3.446666666666667e-06, | |
| "loss": 0.4064, | |
| "step": 3450 | |
| }, | |
| { | |
| "epoch": 2.2197381028425425, | |
| "grad_norm": 5.527169227600098, | |
| "learning_rate": 3.391111111111111e-06, | |
| "loss": 0.3946, | |
| "step": 3475 | |
| }, | |
| { | |
| "epoch": 2.235707441711913, | |
| "grad_norm": 5.034458637237549, | |
| "learning_rate": 3.335555555555556e-06, | |
| "loss": 0.4088, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 2.251676780581284, | |
| "grad_norm": 4.814046382904053, | |
| "learning_rate": 3.2800000000000004e-06, | |
| "loss": 0.4032, | |
| "step": 3525 | |
| }, | |
| { | |
| "epoch": 2.2676461194506548, | |
| "grad_norm": 5.115776062011719, | |
| "learning_rate": 3.2244444444444444e-06, | |
| "loss": 0.4009, | |
| "step": 3550 | |
| }, | |
| { | |
| "epoch": 2.2836154583200257, | |
| "grad_norm": 4.4629130363464355, | |
| "learning_rate": 3.1688888888888893e-06, | |
| "loss": 0.408, | |
| "step": 3575 | |
| }, | |
| { | |
| "epoch": 2.2995847971893966, | |
| "grad_norm": 4.914193153381348, | |
| "learning_rate": 3.1133333333333337e-06, | |
| "loss": 0.3867, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 2.315554136058767, | |
| "grad_norm": 4.358288288116455, | |
| "learning_rate": 3.0577777777777778e-06, | |
| "loss": 0.4485, | |
| "step": 3625 | |
| }, | |
| { | |
| "epoch": 2.331523474928138, | |
| "grad_norm": 4.8634161949157715, | |
| "learning_rate": 3.0022222222222227e-06, | |
| "loss": 0.389, | |
| "step": 3650 | |
| }, | |
| { | |
| "epoch": 2.347492813797509, | |
| "grad_norm": 5.283102989196777, | |
| "learning_rate": 2.946666666666667e-06, | |
| "loss": 0.395, | |
| "step": 3675 | |
| }, | |
| { | |
| "epoch": 2.3634621526668798, | |
| "grad_norm": 4.393892765045166, | |
| "learning_rate": 2.891111111111111e-06, | |
| "loss": 0.4047, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 2.37943149153625, | |
| "grad_norm": 5.246931552886963, | |
| "learning_rate": 2.835555555555556e-06, | |
| "loss": 0.3957, | |
| "step": 3725 | |
| }, | |
| { | |
| "epoch": 2.395400830405621, | |
| "grad_norm": 4.599190711975098, | |
| "learning_rate": 2.7800000000000005e-06, | |
| "loss": 0.3829, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 2.411370169274992, | |
| "grad_norm": 5.136366367340088, | |
| "learning_rate": 2.7244444444444445e-06, | |
| "loss": 0.4029, | |
| "step": 3775 | |
| }, | |
| { | |
| "epoch": 2.427339508144363, | |
| "grad_norm": 4.448164463043213, | |
| "learning_rate": 2.6688888888888894e-06, | |
| "loss": 0.3869, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 2.443308847013734, | |
| "grad_norm": 5.434977054595947, | |
| "learning_rate": 2.6133333333333334e-06, | |
| "loss": 0.3871, | |
| "step": 3825 | |
| }, | |
| { | |
| "epoch": 2.4592781858831043, | |
| "grad_norm": 5.272222518920898, | |
| "learning_rate": 2.557777777777778e-06, | |
| "loss": 0.388, | |
| "step": 3850 | |
| }, | |
| { | |
| "epoch": 2.4752475247524752, | |
| "grad_norm": 5.163560390472412, | |
| "learning_rate": 2.5022222222222224e-06, | |
| "loss": 0.4156, | |
| "step": 3875 | |
| }, | |
| { | |
| "epoch": 2.491216863621846, | |
| "grad_norm": 4.091150283813477, | |
| "learning_rate": 2.446666666666667e-06, | |
| "loss": 0.4093, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 2.5071862024912166, | |
| "grad_norm": 4.858378887176514, | |
| "learning_rate": 2.3911111111111113e-06, | |
| "loss": 0.4068, | |
| "step": 3925 | |
| }, | |
| { | |
| "epoch": 2.5231555413605875, | |
| "grad_norm": 5.535120487213135, | |
| "learning_rate": 2.3355555555555557e-06, | |
| "loss": 0.3992, | |
| "step": 3950 | |
| }, | |
| { | |
| "epoch": 2.5391248802299584, | |
| "grad_norm": 4.70937442779541, | |
| "learning_rate": 2.28e-06, | |
| "loss": 0.4009, | |
| "step": 3975 | |
| }, | |
| { | |
| "epoch": 2.5550942190993293, | |
| "grad_norm": 5.273413181304932, | |
| "learning_rate": 2.2244444444444447e-06, | |
| "loss": 0.3887, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 2.5550942190993293, | |
| "eval_loss": 0.3953465223312378, | |
| "eval_runtime": 1634.3629, | |
| "eval_samples_per_second": 2.387, | |
| "eval_steps_per_second": 0.149, | |
| "eval_wer": 0.2815826568803772, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 2.5710635579687002, | |
| "grad_norm": 5.2189483642578125, | |
| "learning_rate": 2.168888888888889e-06, | |
| "loss": 0.3789, | |
| "step": 4025 | |
| }, | |
| { | |
| "epoch": 2.587032896838071, | |
| "grad_norm": 5.335792064666748, | |
| "learning_rate": 2.1133333333333336e-06, | |
| "loss": 0.3911, | |
| "step": 4050 | |
| }, | |
| { | |
| "epoch": 2.6030022357074416, | |
| "grad_norm": 4.469089508056641, | |
| "learning_rate": 2.057777777777778e-06, | |
| "loss": 0.388, | |
| "step": 4075 | |
| }, | |
| { | |
| "epoch": 2.6189715745768125, | |
| "grad_norm": 4.454526424407959, | |
| "learning_rate": 2.0022222222222225e-06, | |
| "loss": 0.3829, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 2.6349409134461834, | |
| "grad_norm": 5.536740303039551, | |
| "learning_rate": 1.9466666666666665e-06, | |
| "loss": 0.3846, | |
| "step": 4125 | |
| }, | |
| { | |
| "epoch": 2.650910252315554, | |
| "grad_norm": 4.877845764160156, | |
| "learning_rate": 1.8911111111111114e-06, | |
| "loss": 0.4116, | |
| "step": 4150 | |
| }, | |
| { | |
| "epoch": 2.666879591184925, | |
| "grad_norm": 5.3322014808654785, | |
| "learning_rate": 1.8355555555555557e-06, | |
| "loss": 0.3857, | |
| "step": 4175 | |
| }, | |
| { | |
| "epoch": 2.6828489300542957, | |
| "grad_norm": 4.9132866859436035, | |
| "learning_rate": 1.7800000000000001e-06, | |
| "loss": 0.3922, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 2.6988182689236666, | |
| "grad_norm": 5.380650043487549, | |
| "learning_rate": 1.7244444444444448e-06, | |
| "loss": 0.3757, | |
| "step": 4225 | |
| }, | |
| { | |
| "epoch": 2.7147876077930375, | |
| "grad_norm": 4.5387282371521, | |
| "learning_rate": 1.668888888888889e-06, | |
| "loss": 0.3919, | |
| "step": 4250 | |
| }, | |
| { | |
| "epoch": 2.7307569466624084, | |
| "grad_norm": 5.215519428253174, | |
| "learning_rate": 1.6133333333333335e-06, | |
| "loss": 0.4104, | |
| "step": 4275 | |
| }, | |
| { | |
| "epoch": 2.746726285531779, | |
| "grad_norm": 6.126536846160889, | |
| "learning_rate": 1.5577777777777777e-06, | |
| "loss": 0.3792, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 2.76269562440115, | |
| "grad_norm": 5.707647323608398, | |
| "learning_rate": 1.5022222222222224e-06, | |
| "loss": 0.4041, | |
| "step": 4325 | |
| }, | |
| { | |
| "epoch": 2.7786649632705207, | |
| "grad_norm": 5.024244785308838, | |
| "learning_rate": 1.4466666666666669e-06, | |
| "loss": 0.4045, | |
| "step": 4350 | |
| }, | |
| { | |
| "epoch": 2.794634302139891, | |
| "grad_norm": 5.240878105163574, | |
| "learning_rate": 1.3911111111111111e-06, | |
| "loss": 0.4022, | |
| "step": 4375 | |
| }, | |
| { | |
| "epoch": 2.810603641009262, | |
| "grad_norm": 5.824533939361572, | |
| "learning_rate": 1.3355555555555558e-06, | |
| "loss": 0.3947, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 2.826572979878633, | |
| "grad_norm": 4.228843688964844, | |
| "learning_rate": 1.28e-06, | |
| "loss": 0.3725, | |
| "step": 4425 | |
| }, | |
| { | |
| "epoch": 2.842542318748004, | |
| "grad_norm": 4.704908847808838, | |
| "learning_rate": 1.2244444444444445e-06, | |
| "loss": 0.4001, | |
| "step": 4450 | |
| }, | |
| { | |
| "epoch": 2.858511657617375, | |
| "grad_norm": 4.397124767303467, | |
| "learning_rate": 1.168888888888889e-06, | |
| "loss": 0.381, | |
| "step": 4475 | |
| }, | |
| { | |
| "epoch": 2.8744809964867457, | |
| "grad_norm": 4.7757062911987305, | |
| "learning_rate": 1.1133333333333334e-06, | |
| "loss": 0.3689, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 2.890450335356116, | |
| "grad_norm": 4.855478763580322, | |
| "learning_rate": 1.0577777777777779e-06, | |
| "loss": 0.373, | |
| "step": 4525 | |
| }, | |
| { | |
| "epoch": 2.906419674225487, | |
| "grad_norm": 5.458982467651367, | |
| "learning_rate": 1.0022222222222223e-06, | |
| "loss": 0.3919, | |
| "step": 4550 | |
| }, | |
| { | |
| "epoch": 2.922389013094858, | |
| "grad_norm": 3.9116828441619873, | |
| "learning_rate": 9.466666666666667e-07, | |
| "loss": 0.4143, | |
| "step": 4575 | |
| }, | |
| { | |
| "epoch": 2.9383583519642285, | |
| "grad_norm": 4.8182878494262695, | |
| "learning_rate": 8.911111111111112e-07, | |
| "loss": 0.3726, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 2.9543276908335994, | |
| "grad_norm": 5.018452167510986, | |
| "learning_rate": 8.355555555555556e-07, | |
| "loss": 0.4018, | |
| "step": 4625 | |
| }, | |
| { | |
| "epoch": 2.9702970297029703, | |
| "grad_norm": 5.315720081329346, | |
| "learning_rate": 7.8e-07, | |
| "loss": 0.3648, | |
| "step": 4650 | |
| }, | |
| { | |
| "epoch": 2.986266368572341, | |
| "grad_norm": 4.65333890914917, | |
| "learning_rate": 7.266666666666668e-07, | |
| "loss": 0.3865, | |
| "step": 4675 | |
| }, | |
| { | |
| "epoch": 3.002235707441712, | |
| "grad_norm": 2.9384920597076416, | |
| "learning_rate": 6.711111111111111e-07, | |
| "loss": 0.3793, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 3.0182050463110826, | |
| "grad_norm": 4.572001934051514, | |
| "learning_rate": 6.155555555555556e-07, | |
| "loss": 0.2557, | |
| "step": 4725 | |
| }, | |
| { | |
| "epoch": 3.0341743851804535, | |
| "grad_norm": 3.237912654876709, | |
| "learning_rate": 5.6e-07, | |
| "loss": 0.252, | |
| "step": 4750 | |
| }, | |
| { | |
| "epoch": 3.0501437240498244, | |
| "grad_norm": 3.8456506729125977, | |
| "learning_rate": 5.044444444444445e-07, | |
| "loss": 0.2556, | |
| "step": 4775 | |
| }, | |
| { | |
| "epoch": 3.0661130629191953, | |
| "grad_norm": 4.627549171447754, | |
| "learning_rate": 4.488888888888889e-07, | |
| "loss": 0.2618, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 3.0820824017885657, | |
| "grad_norm": 4.322127342224121, | |
| "learning_rate": 3.9333333333333336e-07, | |
| "loss": 0.2715, | |
| "step": 4825 | |
| }, | |
| { | |
| "epoch": 3.0980517406579366, | |
| "grad_norm": 4.883068084716797, | |
| "learning_rate": 3.3777777777777777e-07, | |
| "loss": 0.2585, | |
| "step": 4850 | |
| }, | |
| { | |
| "epoch": 3.1140210795273076, | |
| "grad_norm": 4.687808513641357, | |
| "learning_rate": 2.822222222222222e-07, | |
| "loss": 0.2593, | |
| "step": 4875 | |
| }, | |
| { | |
| "epoch": 3.1299904183966785, | |
| "grad_norm": 4.111570835113525, | |
| "learning_rate": 2.266666666666667e-07, | |
| "loss": 0.2645, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 3.1459597572660494, | |
| "grad_norm": 4.777975082397461, | |
| "learning_rate": 1.7111111111111114e-07, | |
| "loss": 0.2594, | |
| "step": 4925 | |
| }, | |
| { | |
| "epoch": 3.16192909613542, | |
| "grad_norm": 4.395523548126221, | |
| "learning_rate": 1.1555555555555556e-07, | |
| "loss": 0.2665, | |
| "step": 4950 | |
| }, | |
| { | |
| "epoch": 3.1778984350047907, | |
| "grad_norm": 5.332032203674316, | |
| "learning_rate": 6.000000000000001e-08, | |
| "loss": 0.2772, | |
| "step": 4975 | |
| }, | |
| { | |
| "epoch": 3.1938677738741617, | |
| "grad_norm": 4.1832733154296875, | |
| "learning_rate": 4.444444444444445e-09, | |
| "loss": 0.2637, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 3.1938677738741617, | |
| "eval_loss": 0.4074931740760803, | |
| "eval_runtime": 1670.4337, | |
| "eval_samples_per_second": 2.335, | |
| "eval_steps_per_second": 0.146, | |
| "eval_wer": 0.2823846789481359, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 3.1938677738741617, | |
| "step": 5000, | |
| "total_flos": 5.435895365546803e+20, | |
| "train_loss": 0.7105956988334656, | |
| "train_runtime": 59674.9515, | |
| "train_samples_per_second": 2.681, | |
| "train_steps_per_second": 0.084 | |
| } | |
| ], | |
| "logging_steps": 25, | |
| "max_steps": 5000, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 1000, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5.435895365546803e+20, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |