BanglaBridge-Instruct / trainer_state.json
subhajitmahata84's picture
BanglaBridge-Instruct: LoRA adapter for Llama 3.3 70B (65% win rate)
536b39d verified
Raw
History Blame Contribute Delete
94.8 kB
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 4.0,
"eval_steps": 103,
"global_step": 516,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.007751937984496124,
"grad_norm": 0.18786276876926422,
"learning_rate": 0.0,
"loss": 1.5205078125,
"step": 1
},
{
"epoch": 0.015503875968992248,
"grad_norm": 0.19954028725624084,
"learning_rate": 9.375e-06,
"loss": 1.5380859375,
"step": 2
},
{
"epoch": 0.023255813953488372,
"grad_norm": 0.16636234521865845,
"learning_rate": 1.875e-05,
"loss": 1.4072265625,
"step": 3
},
{
"epoch": 0.031007751937984496,
"grad_norm": 0.1485351324081421,
"learning_rate": 2.8125e-05,
"loss": 1.4296875,
"step": 4
},
{
"epoch": 0.03875968992248062,
"grad_norm": 0.12388616800308228,
"learning_rate": 3.75e-05,
"loss": 1.466796875,
"step": 5
},
{
"epoch": 0.046511627906976744,
"grad_norm": 0.10179175436496735,
"learning_rate": 4.6874999999999994e-05,
"loss": 1.4150390625,
"step": 6
},
{
"epoch": 0.05426356589147287,
"grad_norm": 0.08314245194196701,
"learning_rate": 5.625e-05,
"loss": 1.3515625,
"step": 7
},
{
"epoch": 0.06201550387596899,
"grad_norm": 0.07605796307325363,
"learning_rate": 6.5625e-05,
"loss": 1.1748046875,
"step": 8
},
{
"epoch": 0.06976744186046512,
"grad_norm": 0.11161350458860397,
"learning_rate": 7.5e-05,
"loss": 1.2939453125,
"step": 9
},
{
"epoch": 0.07751937984496124,
"grad_norm": 0.1217145025730133,
"learning_rate": 8.437499999999999e-05,
"loss": 1.2294921875,
"step": 10
},
{
"epoch": 0.08527131782945736,
"grad_norm": 0.09762484580278397,
"learning_rate": 9.374999999999999e-05,
"loss": 1.2470703125,
"step": 11
},
{
"epoch": 0.09302325581395349,
"grad_norm": 0.06527552008628845,
"learning_rate": 0.00010312499999999999,
"loss": 1.2744140625,
"step": 12
},
{
"epoch": 0.10077519379844961,
"grad_norm": 0.04136033356189728,
"learning_rate": 0.0001125,
"loss": 1.185546875,
"step": 13
},
{
"epoch": 0.10852713178294573,
"grad_norm": 0.04345981031656265,
"learning_rate": 0.000121875,
"loss": 1.177734375,
"step": 14
},
{
"epoch": 0.11627906976744186,
"grad_norm": 0.04836779460310936,
"learning_rate": 0.00013125,
"loss": 1.2431640625,
"step": 15
},
{
"epoch": 0.12403100775193798,
"grad_norm": 0.04405202716588974,
"learning_rate": 0.000140625,
"loss": 1.1011962890625,
"step": 16
},
{
"epoch": 0.13178294573643412,
"grad_norm": 0.04624035581946373,
"learning_rate": 0.00015,
"loss": 1.021728515625,
"step": 17
},
{
"epoch": 0.13953488372093023,
"grad_norm": 0.038512423634529114,
"learning_rate": 0.00014999866760778924,
"loss": 1.15087890625,
"step": 18
},
{
"epoch": 0.14728682170542637,
"grad_norm": 0.04423275217413902,
"learning_rate": 0.00014999467048375757,
"loss": 1.1171875,
"step": 19
},
{
"epoch": 0.15503875968992248,
"grad_norm": 0.04338473826646805,
"learning_rate": 0.0001499880087857046,
"loss": 1.1572265625,
"step": 20
},
{
"epoch": 0.16279069767441862,
"grad_norm": 0.03963780775666237,
"learning_rate": 0.00014997868277662272,
"loss": 1.1611328125,
"step": 21
},
{
"epoch": 0.17054263565891473,
"grad_norm": 0.0381166934967041,
"learning_rate": 0.00014996669282468686,
"loss": 1.1103515625,
"step": 22
},
{
"epoch": 0.17829457364341086,
"grad_norm": 0.038508616387844086,
"learning_rate": 0.00014995203940323975,
"loss": 1.12841796875,
"step": 23
},
{
"epoch": 0.18604651162790697,
"grad_norm": 0.035543400794267654,
"learning_rate": 0.0001499347230907734,
"loss": 1.154296875,
"step": 24
},
{
"epoch": 0.1937984496124031,
"grad_norm": 0.04218472167849541,
"learning_rate": 0.00014991474457090617,
"loss": 1.1650390625,
"step": 25
},
{
"epoch": 0.20155038759689922,
"grad_norm": 0.03463132306933403,
"learning_rate": 0.0001498921046323558,
"loss": 1.0673828125,
"step": 26
},
{
"epoch": 0.20930232558139536,
"grad_norm": 0.036671627312898636,
"learning_rate": 0.00014986680416890832,
"loss": 1.10693359375,
"step": 27
},
{
"epoch": 0.21705426356589147,
"grad_norm": 0.033425938338041306,
"learning_rate": 0.00014983884417938269,
"loss": 1.11181640625,
"step": 28
},
{
"epoch": 0.2248062015503876,
"grad_norm": 0.032951440662145615,
"learning_rate": 0.00014980822576759142,
"loss": 1.13671875,
"step": 29
},
{
"epoch": 0.23255813953488372,
"grad_norm": 0.03474903851747513,
"learning_rate": 0.000149774950142297,
"loss": 1.13427734375,
"step": 30
},
{
"epoch": 0.24031007751937986,
"grad_norm": 0.0334058552980423,
"learning_rate": 0.00014973901861716412,
"loss": 1.001953125,
"step": 31
},
{
"epoch": 0.24806201550387597,
"grad_norm": 0.036706238985061646,
"learning_rate": 0.0001497004326107079,
"loss": 1.021484375,
"step": 32
},
{
"epoch": 0.2558139534883721,
"grad_norm": 0.03383168950676918,
"learning_rate": 0.00014965919364623776,
"loss": 1.0244140625,
"step": 33
},
{
"epoch": 0.26356589147286824,
"grad_norm": 0.03137823939323425,
"learning_rate": 0.0001496153033517974,
"loss": 1.1181640625,
"step": 34
},
{
"epoch": 0.2713178294573643,
"grad_norm": 0.030606389045715332,
"learning_rate": 0.00014956876346010055,
"loss": 1.03515625,
"step": 35
},
{
"epoch": 0.27906976744186046,
"grad_norm": 0.03193344920873642,
"learning_rate": 0.0001495195758084624,
"loss": 1.0791015625,
"step": 36
},
{
"epoch": 0.2868217054263566,
"grad_norm": 0.03284955397248268,
"learning_rate": 0.00014946774233872724,
"loss": 1.0546875,
"step": 37
},
{
"epoch": 0.29457364341085274,
"grad_norm": 0.02990698628127575,
"learning_rate": 0.0001494132650971917,
"loss": 0.990234375,
"step": 38
},
{
"epoch": 0.3023255813953488,
"grad_norm": 0.031072482466697693,
"learning_rate": 0.00014935614623452393,
"loss": 1.07421875,
"step": 39
},
{
"epoch": 0.31007751937984496,
"grad_norm": 0.0325331948697567,
"learning_rate": 0.00014929638800567893,
"loss": 1.0859375,
"step": 40
},
{
"epoch": 0.3178294573643411,
"grad_norm": 0.031455148011446,
"learning_rate": 0.00014923399276980918,
"loss": 1.07568359375,
"step": 41
},
{
"epoch": 0.32558139534883723,
"grad_norm": 0.03205735981464386,
"learning_rate": 0.0001491689629901718,
"loss": 0.8681640625,
"step": 42
},
{
"epoch": 0.3333333333333333,
"grad_norm": 0.036593612283468246,
"learning_rate": 0.00014910130123403108,
"loss": 1.09765625,
"step": 43
},
{
"epoch": 0.34108527131782945,
"grad_norm": 0.03448851406574249,
"learning_rate": 0.00014903101017255734,
"loss": 1.03759765625,
"step": 44
},
{
"epoch": 0.3488372093023256,
"grad_norm": 0.03364939987659454,
"learning_rate": 0.00014895809258072136,
"loss": 0.99951171875,
"step": 45
},
{
"epoch": 0.35658914728682173,
"grad_norm": 0.035791803151369095,
"learning_rate": 0.00014888255133718476,
"loss": 1.0458984375,
"step": 46
},
{
"epoch": 0.3643410852713178,
"grad_norm": 0.034536730498075485,
"learning_rate": 0.00014880438942418647,
"loss": 1.1064453125,
"step": 47
},
{
"epoch": 0.37209302325581395,
"grad_norm": 0.03306680545210838,
"learning_rate": 0.00014872360992742502,
"loss": 0.96728515625,
"step": 48
},
{
"epoch": 0.3798449612403101,
"grad_norm": 0.03216111660003662,
"learning_rate": 0.00014864021603593663,
"loss": 1.00341796875,
"step": 49
},
{
"epoch": 0.3875968992248062,
"grad_norm": 0.03700663149356842,
"learning_rate": 0.00014855421104196937,
"loss": 1.0478515625,
"step": 50
},
{
"epoch": 0.3953488372093023,
"grad_norm": 0.036067984998226166,
"learning_rate": 0.00014846559834085304,
"loss": 0.96435546875,
"step": 51
},
{
"epoch": 0.40310077519379844,
"grad_norm": 0.030266977846622467,
"learning_rate": 0.00014837438143086543,
"loss": 0.929229736328125,
"step": 52
},
{
"epoch": 0.4108527131782946,
"grad_norm": 0.03551589325070381,
"learning_rate": 0.00014828056391309394,
"loss": 1.0517578125,
"step": 53
},
{
"epoch": 0.4186046511627907,
"grad_norm": 0.03905569016933441,
"learning_rate": 0.00014818414949129355,
"loss": 1.06787109375,
"step": 54
},
{
"epoch": 0.4263565891472868,
"grad_norm": 0.03376009315252304,
"learning_rate": 0.0001480851419717405,
"loss": 0.7896728515625,
"step": 55
},
{
"epoch": 0.43410852713178294,
"grad_norm": 0.03881262615323067,
"learning_rate": 0.00014798354526308213,
"loss": 0.920654296875,
"step": 56
},
{
"epoch": 0.4418604651162791,
"grad_norm": 0.036101412028074265,
"learning_rate": 0.0001478793633761826,
"loss": 1.0380859375,
"step": 57
},
{
"epoch": 0.4496124031007752,
"grad_norm": 0.04050498083233833,
"learning_rate": 0.00014777260042396435,
"loss": 1.07275390625,
"step": 58
},
{
"epoch": 0.4573643410852713,
"grad_norm": 0.03470204025506973,
"learning_rate": 0.00014766326062124596,
"loss": 0.8338623046875,
"step": 59
},
{
"epoch": 0.46511627906976744,
"grad_norm": 0.043526601046323776,
"learning_rate": 0.00014755134828457566,
"loss": 0.94775390625,
"step": 60
},
{
"epoch": 0.4728682170542636,
"grad_norm": 0.03669349476695061,
"learning_rate": 0.00014743686783206077,
"loss": 0.946533203125,
"step": 61
},
{
"epoch": 0.4806201550387597,
"grad_norm": 0.039512187242507935,
"learning_rate": 0.00014731982378319363,
"loss": 1.0625,
"step": 62
},
{
"epoch": 0.4883720930232558,
"grad_norm": 0.035441990941762924,
"learning_rate": 0.00014720022075867284,
"loss": 1.0224609375,
"step": 63
},
{
"epoch": 0.49612403100775193,
"grad_norm": 0.038298629224300385,
"learning_rate": 0.00014707806348022103,
"loss": 0.96044921875,
"step": 64
},
{
"epoch": 0.5038759689922481,
"grad_norm": 0.04432480409741402,
"learning_rate": 0.0001469533567703984,
"loss": 1.02587890625,
"step": 65
},
{
"epoch": 0.5116279069767442,
"grad_norm": 0.032273419201374054,
"learning_rate": 0.00014682610555241226,
"loss": 0.9384765625,
"step": 66
},
{
"epoch": 0.5193798449612403,
"grad_norm": 0.03732384368777275,
"learning_rate": 0.00014669631484992286,
"loss": 0.9461669921875,
"step": 67
},
{
"epoch": 0.5271317829457365,
"grad_norm": 0.03378031402826309,
"learning_rate": 0.00014656398978684488,
"loss": 1.00537109375,
"step": 68
},
{
"epoch": 0.5348837209302325,
"grad_norm": 0.03920016437768936,
"learning_rate": 0.00014642913558714525,
"loss": 1.0126953125,
"step": 69
},
{
"epoch": 0.5426356589147286,
"grad_norm": 0.03177313506603241,
"learning_rate": 0.0001462917575746368,
"loss": 0.8564453125,
"step": 70
},
{
"epoch": 0.5503875968992248,
"grad_norm": 0.035272154957056046,
"learning_rate": 0.00014615186117276834,
"loss": 0.96630859375,
"step": 71
},
{
"epoch": 0.5581395348837209,
"grad_norm": 0.03836892917752266,
"learning_rate": 0.00014600945190441022,
"loss": 1.0322265625,
"step": 72
},
{
"epoch": 0.5658914728682171,
"grad_norm": 0.030145496129989624,
"learning_rate": 0.00014586453539163649,
"loss": 0.789306640625,
"step": 73
},
{
"epoch": 0.5736434108527132,
"grad_norm": 0.0358957014977932,
"learning_rate": 0.00014571711735550296,
"loss": 0.886474609375,
"step": 74
},
{
"epoch": 0.5813953488372093,
"grad_norm": 0.04269283637404442,
"learning_rate": 0.00014556720361582132,
"loss": 1.0205078125,
"step": 75
},
{
"epoch": 0.5891472868217055,
"grad_norm": 0.03674475476145744,
"learning_rate": 0.0001454148000909292,
"loss": 1.04736328125,
"step": 76
},
{
"epoch": 0.5968992248062015,
"grad_norm": 0.03714277967810631,
"learning_rate": 0.00014525991279745696,
"loss": 0.97119140625,
"step": 77
},
{
"epoch": 0.6046511627906976,
"grad_norm": 0.03853367269039154,
"learning_rate": 0.00014510254785008963,
"loss": 1.06884765625,
"step": 78
},
{
"epoch": 0.6124031007751938,
"grad_norm": 0.03259620815515518,
"learning_rate": 0.0001449427114613259,
"loss": 0.90673828125,
"step": 79
},
{
"epoch": 0.6201550387596899,
"grad_norm": 0.029853660613298416,
"learning_rate": 0.00014478040994123274,
"loss": 0.899169921875,
"step": 80
},
{
"epoch": 0.627906976744186,
"grad_norm": 0.04663418233394623,
"learning_rate": 0.00014461564969719623,
"loss": 0.869140625,
"step": 81
},
{
"epoch": 0.6356589147286822,
"grad_norm": 0.03702740743756294,
"learning_rate": 0.00014444843723366871,
"loss": 1.03466796875,
"step": 82
},
{
"epoch": 0.6434108527131783,
"grad_norm": 0.03891228511929512,
"learning_rate": 0.00014427877915191192,
"loss": 0.9931640625,
"step": 83
},
{
"epoch": 0.6511627906976745,
"grad_norm": 0.03422516956925392,
"learning_rate": 0.00014410668214973643,
"loss": 0.9990234375,
"step": 84
},
{
"epoch": 0.6589147286821705,
"grad_norm": 0.03482131287455559,
"learning_rate": 0.0001439321530212372,
"loss": 0.9736328125,
"step": 85
},
{
"epoch": 0.6666666666666666,
"grad_norm": 0.05120984464883804,
"learning_rate": 0.00014375519865652536,
"loss": 0.9716796875,
"step": 86
},
{
"epoch": 0.6744186046511628,
"grad_norm": 0.03919104114174843,
"learning_rate": 0.00014357582604145633,
"loss": 1.0068359375,
"step": 87
},
{
"epoch": 0.6821705426356589,
"grad_norm": 0.03737185522913933,
"learning_rate": 0.00014339404225735368,
"loss": 0.97509765625,
"step": 88
},
{
"epoch": 0.689922480620155,
"grad_norm": 0.03514476865530014,
"learning_rate": 0.00014320985448073003,
"loss": 0.9755859375,
"step": 89
},
{
"epoch": 0.6976744186046512,
"grad_norm": 0.03411982208490372,
"learning_rate": 0.00014302326998300342,
"loss": 1.029296875,
"step": 90
},
{
"epoch": 0.7054263565891473,
"grad_norm": 0.037489742040634155,
"learning_rate": 0.0001428342961302103,
"loss": 0.9296875,
"step": 91
},
{
"epoch": 0.7131782945736435,
"grad_norm": 0.052215468138456345,
"learning_rate": 0.00014264294038271482,
"loss": 0.97705078125,
"step": 92
},
{
"epoch": 0.7209302325581395,
"grad_norm": 0.03588670864701271,
"learning_rate": 0.00014244921029491425,
"loss": 1.01611328125,
"step": 93
},
{
"epoch": 0.7286821705426356,
"grad_norm": 0.040395576506853104,
"learning_rate": 0.0001422531135149407,
"loss": 0.9638671875,
"step": 94
},
{
"epoch": 0.7364341085271318,
"grad_norm": 0.0333198606967926,
"learning_rate": 0.00014205465778435934,
"loss": 0.93994140625,
"step": 95
},
{
"epoch": 0.7441860465116279,
"grad_norm": 0.027959557250142097,
"learning_rate": 0.00014185385093786252,
"loss": 0.7498779296875,
"step": 96
},
{
"epoch": 0.751937984496124,
"grad_norm": 0.04139463230967522,
"learning_rate": 0.00014165070090296078,
"loss": 0.92724609375,
"step": 97
},
{
"epoch": 0.7596899224806202,
"grad_norm": 0.035497140139341354,
"learning_rate": 0.00014144521569966958,
"loss": 0.9853515625,
"step": 98
},
{
"epoch": 0.7674418604651163,
"grad_norm": 0.0334344319999218,
"learning_rate": 0.00014123740344019296,
"loss": 0.9033203125,
"step": 99
},
{
"epoch": 0.7751937984496124,
"grad_norm": 0.04021883383393288,
"learning_rate": 0.00014102727232860306,
"loss": 0.9814453125,
"step": 100
},
{
"epoch": 0.7829457364341085,
"grad_norm": 0.034049008041620255,
"learning_rate": 0.00014081483066051637,
"loss": 0.94287109375,
"step": 101
},
{
"epoch": 0.7906976744186046,
"grad_norm": 0.03493446484208107,
"learning_rate": 0.00014060008682276618,
"loss": 0.98779296875,
"step": 102
},
{
"epoch": 0.7984496124031008,
"grad_norm": 0.04007940739393234,
"learning_rate": 0.00014038304929307152,
"loss": 0.9609375,
"step": 103
},
{
"epoch": 0.8062015503875969,
"grad_norm": 0.035312455147504807,
"learning_rate": 0.0001401637266397024,
"loss": 1.01025390625,
"step": 104
},
{
"epoch": 0.8062015503875969,
"eval_loss": 0.91162109375,
"eval_runtime": 6.4937,
"eval_samples_per_second": 1.078,
"eval_steps_per_second": 0.154,
"step": 104
},
{
"epoch": 0.813953488372093,
"grad_norm": 0.03513696789741516,
"learning_rate": 0.0001399421275211417,
"loss": 0.98388671875,
"step": 105
},
{
"epoch": 0.8217054263565892,
"grad_norm": 0.0362546406686306,
"learning_rate": 0.0001397182606857431,
"loss": 1.001953125,
"step": 106
},
{
"epoch": 0.8294573643410853,
"grad_norm": 0.03439491614699364,
"learning_rate": 0.00013949213497138602,
"loss": 1.01025390625,
"step": 107
},
{
"epoch": 0.8372093023255814,
"grad_norm": 0.03678153082728386,
"learning_rate": 0.0001392637593051264,
"loss": 0.87353515625,
"step": 108
},
{
"epoch": 0.8449612403100775,
"grad_norm": 0.3193041682243347,
"learning_rate": 0.00013903314270284454,
"loss": 1.025390625,
"step": 109
},
{
"epoch": 0.8527131782945736,
"grad_norm": 0.03561978042125702,
"learning_rate": 0.00013880029426888905,
"loss": 0.9521484375,
"step": 110
},
{
"epoch": 0.8604651162790697,
"grad_norm": 0.042265113443136215,
"learning_rate": 0.00013856522319571733,
"loss": 0.96728515625,
"step": 111
},
{
"epoch": 0.8682170542635659,
"grad_norm": 0.035079870373010635,
"learning_rate": 0.00013832793876353288,
"loss": 0.9228515625,
"step": 112
},
{
"epoch": 0.875968992248062,
"grad_norm": 0.034565988928079605,
"learning_rate": 0.00013808845033991884,
"loss": 0.93212890625,
"step": 113
},
{
"epoch": 0.8837209302325582,
"grad_norm": 0.03750981390476227,
"learning_rate": 0.00013784676737946803,
"loss": 0.931640625,
"step": 114
},
{
"epoch": 0.8914728682170543,
"grad_norm": 0.03814476355910301,
"learning_rate": 0.00013760289942340992,
"loss": 0.9853515625,
"step": 115
},
{
"epoch": 0.8992248062015504,
"grad_norm": 0.03927535191178322,
"learning_rate": 0.0001373568560992338,
"loss": 0.92626953125,
"step": 116
},
{
"epoch": 0.9069767441860465,
"grad_norm": 0.06597933918237686,
"learning_rate": 0.00013710864712030893,
"loss": 0.92041015625,
"step": 117
},
{
"epoch": 0.9147286821705426,
"grad_norm": 0.03291847184300423,
"learning_rate": 0.0001368582822855007,
"loss": 0.89404296875,
"step": 118
},
{
"epoch": 0.9224806201550387,
"grad_norm": 0.038600772619247437,
"learning_rate": 0.00013660577147878416,
"loss": 0.99658203125,
"step": 119
},
{
"epoch": 0.9302325581395349,
"grad_norm": 0.035205889493227005,
"learning_rate": 0.00013635112466885352,
"loss": 0.95947265625,
"step": 120
},
{
"epoch": 0.937984496124031,
"grad_norm": 0.034847695380449295,
"learning_rate": 0.00013609435190872887,
"loss": 0.998046875,
"step": 121
},
{
"epoch": 0.9457364341085271,
"grad_norm": 0.038817476481199265,
"learning_rate": 0.0001358354633353591,
"loss": 0.93896484375,
"step": 122
},
{
"epoch": 0.9534883720930233,
"grad_norm": 0.03638102859258652,
"learning_rate": 0.00013557446916922177,
"loss": 0.85986328125,
"step": 123
},
{
"epoch": 0.9612403100775194,
"grad_norm": 0.03604152426123619,
"learning_rate": 0.00013531137971391967,
"loss": 0.95166015625,
"step": 124
},
{
"epoch": 0.9689922480620154,
"grad_norm": 0.04199523478746414,
"learning_rate": 0.00013504620535577407,
"loss": 0.98583984375,
"step": 125
},
{
"epoch": 0.9767441860465116,
"grad_norm": 0.038772206753492355,
"learning_rate": 0.00013477895656341453,
"loss": 0.94677734375,
"step": 126
},
{
"epoch": 0.9844961240310077,
"grad_norm": 0.09183433651924133,
"learning_rate": 0.00013450964388736576,
"loss": 0.9755859375,
"step": 127
},
{
"epoch": 0.9922480620155039,
"grad_norm": 0.035269711166620255,
"learning_rate": 0.0001342382779596311,
"loss": 0.95361328125,
"step": 128
},
{
"epoch": 1.0,
"grad_norm": 0.03634484484791756,
"learning_rate": 0.00013396486949327272,
"loss": 0.9521484375,
"step": 129
},
{
"epoch": 1.0077519379844961,
"grad_norm": 0.035050421953201294,
"learning_rate": 0.00013368942928198871,
"loss": 0.9619140625,
"step": 130
},
{
"epoch": 1.0155038759689923,
"grad_norm": 0.035989537835121155,
"learning_rate": 0.000133411968199687,
"loss": 0.9765625,
"step": 131
},
{
"epoch": 1.0232558139534884,
"grad_norm": 0.036197811365127563,
"learning_rate": 0.000133132497200056,
"loss": 0.9052734375,
"step": 132
},
{
"epoch": 1.0310077519379846,
"grad_norm": 0.037342485040426254,
"learning_rate": 0.00013285102731613229,
"loss": 0.94091796875,
"step": 133
},
{
"epoch": 1.0387596899224807,
"grad_norm": 0.04950591176748276,
"learning_rate": 0.00013256756965986487,
"loss": 0.99853515625,
"step": 134
},
{
"epoch": 1.0465116279069768,
"grad_norm": 0.046881064772605896,
"learning_rate": 0.00013228213542167673,
"loss": 0.98291015625,
"step": 135
},
{
"epoch": 1.054263565891473,
"grad_norm": 0.04122152552008629,
"learning_rate": 0.0001319947358700228,
"loss": 0.9794921875,
"step": 136
},
{
"epoch": 1.062015503875969,
"grad_norm": 0.03439309820532799,
"learning_rate": 0.00013170538235094526,
"loss": 0.859375,
"step": 137
},
{
"epoch": 1.069767441860465,
"grad_norm": 0.03992585465312004,
"learning_rate": 0.00013141408628762564,
"loss": 0.94873046875,
"step": 138
},
{
"epoch": 1.0775193798449612,
"grad_norm": 0.04098963364958763,
"learning_rate": 0.0001311208591799337,
"loss": 0.900390625,
"step": 139
},
{
"epoch": 1.0852713178294573,
"grad_norm": 0.035281822085380554,
"learning_rate": 0.00013082571260397357,
"loss": 0.9326171875,
"step": 140
},
{
"epoch": 1.0930232558139534,
"grad_norm": 0.038044273853302,
"learning_rate": 0.00013052865821162676,
"loss": 0.9794921875,
"step": 141
},
{
"epoch": 1.1007751937984496,
"grad_norm": 0.03448478877544403,
"learning_rate": 0.00013022970773009194,
"loss": 0.9072265625,
"step": 142
},
{
"epoch": 1.1085271317829457,
"grad_norm": 0.03594733402132988,
"learning_rate": 0.00012992887296142233,
"loss": 0.912109375,
"step": 143
},
{
"epoch": 1.1162790697674418,
"grad_norm": 0.036207329481840134,
"learning_rate": 0.0001296261657820594,
"loss": 0.9658203125,
"step": 144
},
{
"epoch": 1.124031007751938,
"grad_norm": 0.03591601550579071,
"learning_rate": 0.0001293215981423643,
"loss": 0.847412109375,
"step": 145
},
{
"epoch": 1.1317829457364341,
"grad_norm": 0.034314967691898346,
"learning_rate": 0.00012901518206614602,
"loss": 0.798583984375,
"step": 146
},
{
"epoch": 1.1395348837209303,
"grad_norm": 0.035597171634435654,
"learning_rate": 0.00012870692965018647,
"loss": 0.90576171875,
"step": 147
},
{
"epoch": 1.1472868217054264,
"grad_norm": 0.036420948803424835,
"learning_rate": 0.0001283968530637633,
"loss": 0.8740234375,
"step": 148
},
{
"epoch": 1.1550387596899225,
"grad_norm": 0.036359839141368866,
"learning_rate": 0.00012808496454816913,
"loss": 0.9208984375,
"step": 149
},
{
"epoch": 1.1627906976744187,
"grad_norm": 0.03531688079237938,
"learning_rate": 0.00012777127641622858,
"loss": 0.9208984375,
"step": 150
},
{
"epoch": 1.1705426356589148,
"grad_norm": 0.0392940379679203,
"learning_rate": 0.00012745580105181196,
"loss": 0.88427734375,
"step": 151
},
{
"epoch": 1.178294573643411,
"grad_norm": 0.03591623157262802,
"learning_rate": 0.0001271385509093465,
"loss": 0.90283203125,
"step": 152
},
{
"epoch": 1.1860465116279069,
"grad_norm": 0.0358872190117836,
"learning_rate": 0.00012681953851332456,
"loss": 0.92578125,
"step": 153
},
{
"epoch": 1.193798449612403,
"grad_norm": 0.044959183782339096,
"learning_rate": 0.00012649877645780932,
"loss": 0.9599609375,
"step": 154
},
{
"epoch": 1.2015503875968991,
"grad_norm": 0.0372597761452198,
"learning_rate": 0.0001261762774059375,
"loss": 0.8525390625,
"step": 155
},
{
"epoch": 1.2093023255813953,
"grad_norm": 0.03890680521726608,
"learning_rate": 0.00012585205408941944,
"loss": 0.89208984375,
"step": 156
},
{
"epoch": 1.2170542635658914,
"grad_norm": 0.041445646435022354,
"learning_rate": 0.00012552611930803653,
"loss": 0.89306640625,
"step": 157
},
{
"epoch": 1.2248062015503876,
"grad_norm": 0.03824222460389137,
"learning_rate": 0.00012519848592913588,
"loss": 0.9248046875,
"step": 158
},
{
"epoch": 1.2325581395348837,
"grad_norm": 0.04219675809144974,
"learning_rate": 0.00012486916688712229,
"loss": 0.9140625,
"step": 159
},
{
"epoch": 1.2403100775193798,
"grad_norm": 0.06856386363506317,
"learning_rate": 0.00012453817518294757,
"loss": 0.81005859375,
"step": 160
},
{
"epoch": 1.248062015503876,
"grad_norm": 0.042003314942121506,
"learning_rate": 0.00012420552388359756,
"loss": 0.822265625,
"step": 161
},
{
"epoch": 1.255813953488372,
"grad_norm": 0.03855019435286522,
"learning_rate": 0.0001238712261215759,
"loss": 0.8310546875,
"step": 162
},
{
"epoch": 1.2635658914728682,
"grad_norm": 0.040682099759578705,
"learning_rate": 0.00012353529509438586,
"loss": 0.912109375,
"step": 163
},
{
"epoch": 1.2713178294573644,
"grad_norm": 0.03906140476465225,
"learning_rate": 0.00012319774406400916,
"loss": 0.8447265625,
"step": 164
},
{
"epoch": 1.2790697674418605,
"grad_norm": 0.03948715329170227,
"learning_rate": 0.00012285858635638252,
"loss": 0.8798828125,
"step": 165
},
{
"epoch": 1.2868217054263567,
"grad_norm": 0.04061060771346092,
"learning_rate": 0.00012251783536087148,
"loss": 0.85400390625,
"step": 166
},
{
"epoch": 1.2945736434108528,
"grad_norm": 0.037617988884449005,
"learning_rate": 0.00012217550452974193,
"loss": 0.81005859375,
"step": 167
},
{
"epoch": 1.302325581395349,
"grad_norm": 0.03877709060907364,
"learning_rate": 0.00012183160737762887,
"loss": 0.87841796875,
"step": 168
},
{
"epoch": 1.310077519379845,
"grad_norm": 0.04214360937476158,
"learning_rate": 0.00012148615748100305,
"loss": 0.89013671875,
"step": 169
},
{
"epoch": 1.3178294573643412,
"grad_norm": 0.038744617253541946,
"learning_rate": 0.00012113916847763487,
"loss": 0.876953125,
"step": 170
},
{
"epoch": 1.3255813953488373,
"grad_norm": 0.03888416290283203,
"learning_rate": 0.00012079065406605606,
"loss": 0.71044921875,
"step": 171
},
{
"epoch": 1.3333333333333333,
"grad_norm": 0.03957424685359001,
"learning_rate": 0.0001204406280050188,
"loss": 0.8984375,
"step": 172
},
{
"epoch": 1.3410852713178294,
"grad_norm": 0.040746722370386124,
"learning_rate": 0.00012008910411295268,
"loss": 0.84912109375,
"step": 173
},
{
"epoch": 1.3488372093023255,
"grad_norm": 0.04713168367743492,
"learning_rate": 0.00011973609626741904,
"loss": 0.81298828125,
"step": 174
},
{
"epoch": 1.3565891472868217,
"grad_norm": 0.04117116332054138,
"learning_rate": 0.00011938161840456317,
"loss": 0.8564453125,
"step": 175
},
{
"epoch": 1.3643410852713178,
"grad_norm": 0.041082531213760376,
"learning_rate": 0.0001190256845185641,
"loss": 0.91064453125,
"step": 176
},
{
"epoch": 1.372093023255814,
"grad_norm": 0.036820586770772934,
"learning_rate": 0.00011866830866108226,
"loss": 0.801025390625,
"step": 177
},
{
"epoch": 1.37984496124031,
"grad_norm": 0.04114276170730591,
"learning_rate": 0.00011830950494070455,
"loss": 0.82275390625,
"step": 178
},
{
"epoch": 1.3875968992248062,
"grad_norm": 0.04060537740588188,
"learning_rate": 0.00011794928752238747,
"loss": 0.8603515625,
"step": 179
},
{
"epoch": 1.3953488372093024,
"grad_norm": 0.041201572865247726,
"learning_rate": 0.00011758767062689787,
"loss": 0.79150390625,
"step": 180
},
{
"epoch": 1.4031007751937985,
"grad_norm": 0.04132666066288948,
"learning_rate": 0.00011722466853025167,
"loss": 0.768890380859375,
"step": 181
},
{
"epoch": 1.4108527131782946,
"grad_norm": 0.042601559311151505,
"learning_rate": 0.00011686029556315005,
"loss": 0.86328125,
"step": 182
},
{
"epoch": 1.4186046511627908,
"grad_norm": 0.04839213192462921,
"learning_rate": 0.00011649456611041385,
"loss": 0.8798828125,
"step": 183
},
{
"epoch": 1.4263565891472867,
"grad_norm": 0.03969109058380127,
"learning_rate": 0.00011612749461041561,
"loss": 0.6427001953125,
"step": 184
},
{
"epoch": 1.4341085271317828,
"grad_norm": 0.04181140661239624,
"learning_rate": 0.00011575909555450966,
"loss": 0.756591796875,
"step": 185
},
{
"epoch": 1.441860465116279,
"grad_norm": 0.04716648533940315,
"learning_rate": 0.00011538938348645992,
"loss": 0.8515625,
"step": 186
},
{
"epoch": 1.449612403100775,
"grad_norm": 0.048337046056985855,
"learning_rate": 0.00011501837300186577,
"loss": 0.88330078125,
"step": 187
},
{
"epoch": 1.4573643410852712,
"grad_norm": 0.04053601995110512,
"learning_rate": 0.00011464607874758589,
"loss": 0.6898193359375,
"step": 188
},
{
"epoch": 1.4651162790697674,
"grad_norm": 0.055657759308815,
"learning_rate": 0.00011427251542115996,
"loss": 0.77880859375,
"step": 189
},
{
"epoch": 1.4728682170542635,
"grad_norm": 0.042166177183389664,
"learning_rate": 0.00011389769777022844,
"loss": 0.7822265625,
"step": 190
},
{
"epoch": 1.4806201550387597,
"grad_norm": 0.04735742136836052,
"learning_rate": 0.00011352164059195043,
"loss": 0.87890625,
"step": 191
},
{
"epoch": 1.4883720930232558,
"grad_norm": 0.045601736754179,
"learning_rate": 0.0001131443587324194,
"loss": 0.84130859375,
"step": 192
},
{
"epoch": 1.496124031007752,
"grad_norm": 0.04385631904006004,
"learning_rate": 0.00011276586708607718,
"loss": 0.79638671875,
"step": 193
},
{
"epoch": 1.503875968992248,
"grad_norm": 0.047408781945705414,
"learning_rate": 0.00011238618059512587,
"loss": 0.83984375,
"step": 194
},
{
"epoch": 1.5116279069767442,
"grad_norm": 0.04731688275933266,
"learning_rate": 0.00011200531424893797,
"loss": 0.7763671875,
"step": 195
},
{
"epoch": 1.5193798449612403,
"grad_norm": 0.04579531028866768,
"learning_rate": 0.00011162328308346472,
"loss": 0.783935546875,
"step": 196
},
{
"epoch": 1.5271317829457365,
"grad_norm": 0.0453152172267437,
"learning_rate": 0.00011124010218064239,
"loss": 0.826171875,
"step": 197
},
{
"epoch": 1.5348837209302326,
"grad_norm": 0.050907932221889496,
"learning_rate": 0.00011085578666779693,
"loss": 0.8388671875,
"step": 198
},
{
"epoch": 1.5426356589147288,
"grad_norm": 0.041205476969480515,
"learning_rate": 0.00011047035171704669,
"loss": 0.712158203125,
"step": 199
},
{
"epoch": 1.550387596899225,
"grad_norm": 0.05009079724550247,
"learning_rate": 0.00011008381254470357,
"loss": 0.80029296875,
"step": 200
},
{
"epoch": 1.558139534883721,
"grad_norm": 0.04907772317528725,
"learning_rate": 0.00010969618441067223,
"loss": 0.85302734375,
"step": 201
},
{
"epoch": 1.5658914728682172,
"grad_norm": 0.04160582646727562,
"learning_rate": 0.00010930748261784768,
"loss": 0.651611328125,
"step": 202
},
{
"epoch": 1.5736434108527133,
"grad_norm": 0.04669788479804993,
"learning_rate": 0.00010891772251151116,
"loss": 0.733642578125,
"step": 203
},
{
"epoch": 1.5813953488372094,
"grad_norm": 0.046415988355875015,
"learning_rate": 0.00010852691947872426,
"loss": 0.845703125,
"step": 204
},
{
"epoch": 1.5891472868217056,
"grad_norm": 0.05536266416311264,
"learning_rate": 0.00010813508894772158,
"loss": 0.8720703125,
"step": 205
},
{
"epoch": 1.5968992248062015,
"grad_norm": 0.04646734520792961,
"learning_rate": 0.00010774224638730151,
"loss": 0.8056640625,
"step": 206
},
{
"epoch": 1.6046511627906976,
"grad_norm": 0.05074877664446831,
"learning_rate": 0.00010734840730621576,
"loss": 0.89306640625,
"step": 207
},
{
"epoch": 1.6046511627906976,
"eval_loss": 0.88916015625,
"eval_runtime": 6.4893,
"eval_samples_per_second": 1.079,
"eval_steps_per_second": 0.154,
"step": 207
},
{
"epoch": 1.6124031007751938,
"grad_norm": 0.045564450323581696,
"learning_rate": 0.00010695358725255682,
"loss": 0.754150390625,
"step": 208
},
{
"epoch": 1.62015503875969,
"grad_norm": 0.042502474039793015,
"learning_rate": 0.00010655780181314441,
"loss": 0.750732421875,
"step": 209
},
{
"epoch": 1.627906976744186,
"grad_norm": 0.04419833421707153,
"learning_rate": 0.00010616106661290997,
"loss": 0.7279052734375,
"step": 210
},
{
"epoch": 1.6356589147286822,
"grad_norm": 0.05234264209866524,
"learning_rate": 0.00010576339731427988,
"loss": 0.8544921875,
"step": 211
},
{
"epoch": 1.6434108527131783,
"grad_norm": 0.04661702737212181,
"learning_rate": 0.00010536480961655716,
"loss": 0.82568359375,
"step": 212
},
{
"epoch": 1.6511627906976745,
"grad_norm": 0.047514040023088455,
"learning_rate": 0.00010496531925530158,
"loss": 0.82763671875,
"step": 213
},
{
"epoch": 1.6589147286821704,
"grad_norm": 0.04733423516154289,
"learning_rate": 0.0001045649420017086,
"loss": 0.8095703125,
"step": 214
},
{
"epoch": 1.6666666666666665,
"grad_norm": 0.04783810302615166,
"learning_rate": 0.00010416369366198663,
"loss": 0.7978515625,
"step": 215
},
{
"epoch": 1.6744186046511627,
"grad_norm": 0.04815303534269333,
"learning_rate": 0.00010376159007673307,
"loss": 0.8427734375,
"step": 216
},
{
"epoch": 1.6821705426356588,
"grad_norm": 0.0529569648206234,
"learning_rate": 0.00010335864712030894,
"loss": 0.80908203125,
"step": 217
},
{
"epoch": 1.689922480620155,
"grad_norm": 0.04892537742853165,
"learning_rate": 0.00010295488070021224,
"loss": 0.81005859375,
"step": 218
},
{
"epoch": 1.697674418604651,
"grad_norm": 0.04687004163861275,
"learning_rate": 0.00010255030675644984,
"loss": 0.857421875,
"step": 219
},
{
"epoch": 1.7054263565891472,
"grad_norm": 0.049924347549676895,
"learning_rate": 0.00010214494126090833,
"loss": 0.76611328125,
"step": 220
},
{
"epoch": 1.7131782945736433,
"grad_norm": 0.04998449608683586,
"learning_rate": 0.00010173880021672338,
"loss": 0.81396484375,
"step": 221
},
{
"epoch": 1.7209302325581395,
"grad_norm": 0.0541192926466465,
"learning_rate": 0.00010133189965764798,
"loss": 0.84375,
"step": 222
},
{
"epoch": 1.7286821705426356,
"grad_norm": 0.050691869109869,
"learning_rate": 0.00010092425564741945,
"loss": 0.80126953125,
"step": 223
},
{
"epoch": 1.7364341085271318,
"grad_norm": 0.04845695197582245,
"learning_rate": 0.00010051588427912536,
"loss": 0.78466796875,
"step": 224
},
{
"epoch": 1.744186046511628,
"grad_norm": 0.03721952065825462,
"learning_rate": 0.00010010680167456804,
"loss": 0.631072998046875,
"step": 225
},
{
"epoch": 1.751937984496124,
"grad_norm": 0.04930705204606056,
"learning_rate": 9.969702398362828e-05,
"loss": 0.77490234375,
"step": 226
},
{
"epoch": 1.7596899224806202,
"grad_norm": 0.04764439910650253,
"learning_rate": 9.92865673836277e-05,
"loss": 0.8173828125,
"step": 227
},
{
"epoch": 1.7674418604651163,
"grad_norm": 0.044682808220386505,
"learning_rate": 9.887544807869e-05,
"loss": 0.75244140625,
"step": 228
},
{
"epoch": 1.7751937984496124,
"grad_norm": 0.04970500245690346,
"learning_rate": 9.846368229910141e-05,
"loss": 0.81640625,
"step": 229
},
{
"epoch": 1.7829457364341086,
"grad_norm": 0.04485026001930237,
"learning_rate": 9.805128630066986e-05,
"loss": 0.7822265625,
"step": 230
},
{
"epoch": 1.7906976744186047,
"grad_norm": 0.04685260355472565,
"learning_rate": 9.763827636408322e-05,
"loss": 0.828125,
"step": 231
},
{
"epoch": 1.7984496124031009,
"grad_norm": 0.04880339279770851,
"learning_rate": 9.722466879426662e-05,
"loss": 0.79638671875,
"step": 232
},
{
"epoch": 1.806201550387597,
"grad_norm": 0.04715869203209877,
"learning_rate": 9.681047991973869e-05,
"loss": 0.8427734375,
"step": 233
},
{
"epoch": 1.8139534883720931,
"grad_norm": 0.046799249947071075,
"learning_rate": 9.639572609196699e-05,
"loss": 0.814453125,
"step": 234
},
{
"epoch": 1.8217054263565893,
"grad_norm": 0.046375591307878494,
"learning_rate": 9.598042368472245e-05,
"loss": 0.83544921875,
"step": 235
},
{
"epoch": 1.8294573643410854,
"grad_norm": 0.04745873063802719,
"learning_rate": 9.556458909343307e-05,
"loss": 0.8447265625,
"step": 236
},
{
"epoch": 1.8372093023255816,
"grad_norm": 0.04402947798371315,
"learning_rate": 9.514823873453642e-05,
"loss": 0.7269287109375,
"step": 237
},
{
"epoch": 1.8449612403100775,
"grad_norm": 0.04808734729886055,
"learning_rate": 9.473138904483176e-05,
"loss": 0.86279296875,
"step": 238
},
{
"epoch": 1.8527131782945736,
"grad_norm": 0.0447438582777977,
"learning_rate": 9.431405648083114e-05,
"loss": 0.79150390625,
"step": 239
},
{
"epoch": 1.8604651162790697,
"grad_norm": 0.04795128479599953,
"learning_rate": 9.389625751810952e-05,
"loss": 0.8056640625,
"step": 240
},
{
"epoch": 1.8682170542635659,
"grad_norm": 0.049295589327812195,
"learning_rate": 9.347800865065463e-05,
"loss": 0.7607421875,
"step": 241
},
{
"epoch": 1.875968992248062,
"grad_norm": 0.047233305871486664,
"learning_rate": 9.305932639021559e-05,
"loss": 0.77734375,
"step": 242
},
{
"epoch": 1.8837209302325582,
"grad_norm": 0.047985710203647614,
"learning_rate": 9.264022726565109e-05,
"loss": 0.77001953125,
"step": 243
},
{
"epoch": 1.8914728682170543,
"grad_norm": 0.04906840622425079,
"learning_rate": 9.222072782227701e-05,
"loss": 0.82470703125,
"step": 244
},
{
"epoch": 1.8992248062015504,
"grad_norm": 0.04725610464811325,
"learning_rate": 9.180084462121307e-05,
"loss": 0.76806640625,
"step": 245
},
{
"epoch": 1.9069767441860463,
"grad_norm": 0.04630209505558014,
"learning_rate": 9.138059423872906e-05,
"loss": 0.763671875,
"step": 246
},
{
"epoch": 1.9147286821705425,
"grad_norm": 0.0477568581700325,
"learning_rate": 9.095999326559054e-05,
"loss": 0.75732421875,
"step": 247
},
{
"epoch": 1.9224806201550386,
"grad_norm": 0.052335675805807114,
"learning_rate": 9.053905830640371e-05,
"loss": 0.83349609375,
"step": 248
},
{
"epoch": 1.9302325581395348,
"grad_norm": 0.047090694308280945,
"learning_rate": 9.011780597896e-05,
"loss": 0.80078125,
"step": 249
},
{
"epoch": 1.937984496124031,
"grad_norm": 0.05373085290193558,
"learning_rate": 8.969625291358004e-05,
"loss": 0.83349609375,
"step": 250
},
{
"epoch": 1.945736434108527,
"grad_norm": 0.0480167455971241,
"learning_rate": 8.9274415752457e-05,
"loss": 0.78173828125,
"step": 251
},
{
"epoch": 1.9534883720930232,
"grad_norm": 0.04596777632832527,
"learning_rate": 8.885231114899972e-05,
"loss": 0.71728515625,
"step": 252
},
{
"epoch": 1.9612403100775193,
"grad_norm": 0.1261446177959442,
"learning_rate": 8.842995576717518e-05,
"loss": 0.79736328125,
"step": 253
},
{
"epoch": 1.9689922480620154,
"grad_norm": 0.04901716858148575,
"learning_rate": 8.800736628085063e-05,
"loss": 0.8271484375,
"step": 254
},
{
"epoch": 1.9767441860465116,
"grad_norm": 0.05226081609725952,
"learning_rate": 8.758455937313546e-05,
"loss": 0.7861328125,
"step": 255
},
{
"epoch": 1.9844961240310077,
"grad_norm": 0.0527765154838562,
"learning_rate": 8.71615517357224e-05,
"loss": 0.81494140625,
"step": 256
},
{
"epoch": 1.9922480620155039,
"grad_norm": 0.048730649054050446,
"learning_rate": 8.673836006822865e-05,
"loss": 0.79736328125,
"step": 257
},
{
"epoch": 2.0,
"grad_norm": 0.05379839986562729,
"learning_rate": 8.631500107753665e-05,
"loss": 0.74267578125,
"step": 258
},
{
"epoch": 2.007751937984496,
"grad_norm": 0.052472181618213654,
"learning_rate": 8.589149147713444e-05,
"loss": 0.74755859375,
"step": 259
},
{
"epoch": 2.0155038759689923,
"grad_norm": 0.06032218039035797,
"learning_rate": 8.546784798645588e-05,
"loss": 0.81298828125,
"step": 260
},
{
"epoch": 2.0232558139534884,
"grad_norm": 0.05505041033029556,
"learning_rate": 8.504408733022058e-05,
"loss": 0.7529296875,
"step": 261
},
{
"epoch": 2.0310077519379846,
"grad_norm": 0.05316637456417084,
"learning_rate": 8.462022623777365e-05,
"loss": 0.7734375,
"step": 262
},
{
"epoch": 2.0387596899224807,
"grad_norm": 0.056750357151031494,
"learning_rate": 8.419628144242528e-05,
"loss": 0.82568359375,
"step": 263
},
{
"epoch": 2.046511627906977,
"grad_norm": 0.05582032352685928,
"learning_rate": 8.377226968079005e-05,
"loss": 0.81494140625,
"step": 264
},
{
"epoch": 2.054263565891473,
"grad_norm": 0.0521075502038002,
"learning_rate": 8.33482076921263e-05,
"loss": 0.80810546875,
"step": 265
},
{
"epoch": 2.062015503875969,
"grad_norm": 0.04930770397186279,
"learning_rate": 8.292411221767524e-05,
"loss": 0.701904296875,
"step": 266
},
{
"epoch": 2.0697674418604652,
"grad_norm": 0.06509444117546082,
"learning_rate": 8.25e-05,
"loss": 0.7783203125,
"step": 267
},
{
"epoch": 2.0775193798449614,
"grad_norm": 0.05146259814500809,
"learning_rate": 8.207588778232476e-05,
"loss": 0.736328125,
"step": 268
},
{
"epoch": 2.0852713178294575,
"grad_norm": 0.05167889595031738,
"learning_rate": 8.16517923078737e-05,
"loss": 0.7646484375,
"step": 269
},
{
"epoch": 2.0930232558139537,
"grad_norm": 0.05263634771108627,
"learning_rate": 8.122773031920995e-05,
"loss": 0.80517578125,
"step": 270
},
{
"epoch": 2.10077519379845,
"grad_norm": 0.05087614431977272,
"learning_rate": 8.080371855757472e-05,
"loss": 0.73779296875,
"step": 271
},
{
"epoch": 2.108527131782946,
"grad_norm": 0.05077936872839928,
"learning_rate": 8.037977376222634e-05,
"loss": 0.73583984375,
"step": 272
},
{
"epoch": 2.116279069767442,
"grad_norm": 0.054750025272369385,
"learning_rate": 7.995591266977942e-05,
"loss": 0.78759765625,
"step": 273
},
{
"epoch": 2.124031007751938,
"grad_norm": 0.05173592269420624,
"learning_rate": 7.953215201354412e-05,
"loss": 0.67962646484375,
"step": 274
},
{
"epoch": 2.1317829457364343,
"grad_norm": 0.05042770877480507,
"learning_rate": 7.910850852286556e-05,
"loss": 0.653564453125,
"step": 275
},
{
"epoch": 2.13953488372093,
"grad_norm": 0.05418946221470833,
"learning_rate": 7.868499892246335e-05,
"loss": 0.73193359375,
"step": 276
},
{
"epoch": 2.147286821705426,
"grad_norm": 0.053501300513744354,
"learning_rate": 7.826163993177135e-05,
"loss": 0.706298828125,
"step": 277
},
{
"epoch": 2.1550387596899223,
"grad_norm": 0.05176064744591713,
"learning_rate": 7.78384482642776e-05,
"loss": 0.74658203125,
"step": 278
},
{
"epoch": 2.1627906976744184,
"grad_norm": 0.05234966054558754,
"learning_rate": 7.741544062686453e-05,
"loss": 0.751953125,
"step": 279
},
{
"epoch": 2.1705426356589146,
"grad_norm": 0.05013485997915268,
"learning_rate": 7.699263371914937e-05,
"loss": 0.716796875,
"step": 280
},
{
"epoch": 2.1782945736434107,
"grad_norm": 0.05255870148539543,
"learning_rate": 7.657004423282483e-05,
"loss": 0.7255859375,
"step": 281
},
{
"epoch": 2.186046511627907,
"grad_norm": 0.05105741694569588,
"learning_rate": 7.614768885100028e-05,
"loss": 0.7451171875,
"step": 282
},
{
"epoch": 2.193798449612403,
"grad_norm": 0.052115246653556824,
"learning_rate": 7.572558424754298e-05,
"loss": 0.7939453125,
"step": 283
},
{
"epoch": 2.201550387596899,
"grad_norm": 0.05337890610098839,
"learning_rate": 7.530374708641996e-05,
"loss": 0.6845703125,
"step": 284
},
{
"epoch": 2.2093023255813953,
"grad_norm": 0.05236468091607094,
"learning_rate": 7.488219402103999e-05,
"loss": 0.71337890625,
"step": 285
},
{
"epoch": 2.2170542635658914,
"grad_norm": 0.054926879703998566,
"learning_rate": 7.446094169359629e-05,
"loss": 0.71533203125,
"step": 286
},
{
"epoch": 2.2248062015503876,
"grad_norm": 0.06193400174379349,
"learning_rate": 7.404000673440945e-05,
"loss": 0.7451171875,
"step": 287
},
{
"epoch": 2.2325581395348837,
"grad_norm": 0.05470835417509079,
"learning_rate": 7.361940576127092e-05,
"loss": 0.73388671875,
"step": 288
},
{
"epoch": 2.24031007751938,
"grad_norm": 0.05230575427412987,
"learning_rate": 7.319915537878693e-05,
"loss": 0.64501953125,
"step": 289
},
{
"epoch": 2.248062015503876,
"grad_norm": 0.05716829374432564,
"learning_rate": 7.277927217772298e-05,
"loss": 0.6474609375,
"step": 290
},
{
"epoch": 2.255813953488372,
"grad_norm": 0.065622977912426,
"learning_rate": 7.235977273434888e-05,
"loss": 0.66015625,
"step": 291
},
{
"epoch": 2.2635658914728682,
"grad_norm": 0.057758916169404984,
"learning_rate": 7.19406736097844e-05,
"loss": 0.72509765625,
"step": 292
},
{
"epoch": 2.2713178294573644,
"grad_norm": 0.056422457098960876,
"learning_rate": 7.152199134934534e-05,
"loss": 0.6767578125,
"step": 293
},
{
"epoch": 2.2790697674418605,
"grad_norm": 0.06204810366034508,
"learning_rate": 7.110374248189046e-05,
"loss": 0.701171875,
"step": 294
},
{
"epoch": 2.2868217054263567,
"grad_norm": 0.05981920659542084,
"learning_rate": 7.068594351916886e-05,
"loss": 0.66748046875,
"step": 295
},
{
"epoch": 2.294573643410853,
"grad_norm": 0.0593731664121151,
"learning_rate": 7.026861095516821e-05,
"loss": 0.64599609375,
"step": 296
},
{
"epoch": 2.302325581395349,
"grad_norm": 0.06717907637357712,
"learning_rate": 6.985176126546357e-05,
"loss": 0.6953125,
"step": 297
},
{
"epoch": 2.310077519379845,
"grad_norm": 0.05741477012634277,
"learning_rate": 6.943541090656693e-05,
"loss": 0.7001953125,
"step": 298
},
{
"epoch": 2.317829457364341,
"grad_norm": 0.06018727645277977,
"learning_rate": 6.901957631527753e-05,
"loss": 0.690185546875,
"step": 299
},
{
"epoch": 2.3255813953488373,
"grad_norm": 0.056542541831731796,
"learning_rate": 6.860427390803304e-05,
"loss": 0.5599365234375,
"step": 300
},
{
"epoch": 2.3333333333333335,
"grad_norm": 0.059446174651384354,
"learning_rate": 6.818952008026134e-05,
"loss": 0.70947265625,
"step": 301
},
{
"epoch": 2.3410852713178296,
"grad_norm": 0.06016426160931587,
"learning_rate": 6.777533120573339e-05,
"loss": 0.66162109375,
"step": 302
},
{
"epoch": 2.3488372093023258,
"grad_norm": 0.06622719019651413,
"learning_rate": 6.736172363591678e-05,
"loss": 0.624755859375,
"step": 303
},
{
"epoch": 2.356589147286822,
"grad_norm": 0.06083570048213005,
"learning_rate": 6.694871369933015e-05,
"loss": 0.6611328125,
"step": 304
},
{
"epoch": 2.3643410852713176,
"grad_norm": 0.06764432787895203,
"learning_rate": 6.653631770089859e-05,
"loss": 0.71728515625,
"step": 305
},
{
"epoch": 2.3720930232558137,
"grad_norm": 0.05614745244383812,
"learning_rate": 6.612455192131e-05,
"loss": 0.631591796875,
"step": 306
},
{
"epoch": 2.37984496124031,
"grad_norm": 0.057795699685811996,
"learning_rate": 6.571343261637232e-05,
"loss": 0.63818359375,
"step": 307
},
{
"epoch": 2.387596899224806,
"grad_norm": 0.06633356213569641,
"learning_rate": 6.530297601637172e-05,
"loss": 0.67138671875,
"step": 308
},
{
"epoch": 2.395348837209302,
"grad_norm": 0.05835175886750221,
"learning_rate": 6.489319832543197e-05,
"loss": 0.615234375,
"step": 309
},
{
"epoch": 2.4031007751937983,
"grad_norm": 0.05563213303685188,
"learning_rate": 6.448411572087466e-05,
"loss": 0.60272216796875,
"step": 310
},
{
"epoch": 2.4031007751937983,
"eval_loss": 0.91650390625,
"eval_runtime": 6.4832,
"eval_samples_per_second": 1.08,
"eval_steps_per_second": 0.154,
"step": 310
},
{
"epoch": 2.4108527131782944,
"grad_norm": 0.06841554492712021,
"learning_rate": 6.407574435258055e-05,
"loss": 0.66748046875,
"step": 311
},
{
"epoch": 2.4186046511627906,
"grad_norm": 0.06703931838274002,
"learning_rate": 6.366810034235202e-05,
"loss": 0.68310546875,
"step": 312
},
{
"epoch": 2.4263565891472867,
"grad_norm": 0.05525091290473938,
"learning_rate": 6.326119978327662e-05,
"loss": 0.4915771484375,
"step": 313
},
{
"epoch": 2.434108527131783,
"grad_norm": 0.061299342662096024,
"learning_rate": 6.285505873909166e-05,
"loss": 0.585205078125,
"step": 314
},
{
"epoch": 2.441860465116279,
"grad_norm": 0.069545216858387,
"learning_rate": 6.244969324355016e-05,
"loss": 0.6513671875,
"step": 315
},
{
"epoch": 2.449612403100775,
"grad_norm": 0.06752844154834747,
"learning_rate": 6.204511929978777e-05,
"loss": 0.6826171875,
"step": 316
},
{
"epoch": 2.4573643410852712,
"grad_norm": 0.05634568631649017,
"learning_rate": 6.164135287969106e-05,
"loss": 0.5400390625,
"step": 317
},
{
"epoch": 2.4651162790697674,
"grad_norm": 0.06310458481311798,
"learning_rate": 6.123840992326695e-05,
"loss": 0.59716796875,
"step": 318
},
{
"epoch": 2.4728682170542635,
"grad_norm": 0.06880722939968109,
"learning_rate": 6.083630633801337e-05,
"loss": 0.6064453125,
"step": 319
},
{
"epoch": 2.4806201550387597,
"grad_norm": 0.06507935374975204,
"learning_rate": 6.0435057998291384e-05,
"loss": 0.68017578125,
"step": 320
},
{
"epoch": 2.488372093023256,
"grad_norm": 0.07064376771450043,
"learning_rate": 6.00346807446984e-05,
"loss": 0.6396484375,
"step": 321
},
{
"epoch": 2.496124031007752,
"grad_norm": 0.07107182592153549,
"learning_rate": 5.963519038344283e-05,
"loss": 0.614501953125,
"step": 322
},
{
"epoch": 2.503875968992248,
"grad_norm": 0.06816340237855911,
"learning_rate": 5.92366026857201e-05,
"loss": 0.642578125,
"step": 323
},
{
"epoch": 2.511627906976744,
"grad_norm": 0.07554891705513,
"learning_rate": 5.883893338709003e-05,
"loss": 0.599853515625,
"step": 324
},
{
"epoch": 2.5193798449612403,
"grad_norm": 0.06454700976610184,
"learning_rate": 5.844219818685558e-05,
"loss": 0.6109619140625,
"step": 325
},
{
"epoch": 2.5271317829457365,
"grad_norm": 0.06780916452407837,
"learning_rate": 5.8046412747443164e-05,
"loss": 0.629150390625,
"step": 326
},
{
"epoch": 2.5348837209302326,
"grad_norm": 0.0666443407535553,
"learning_rate": 5.765159269378423e-05,
"loss": 0.6455078125,
"step": 327
},
{
"epoch": 2.5426356589147288,
"grad_norm": 0.05940378084778786,
"learning_rate": 5.7257753612698474e-05,
"loss": 0.550537109375,
"step": 328
},
{
"epoch": 2.550387596899225,
"grad_norm": 0.06636858731508255,
"learning_rate": 5.686491105227842e-05,
"loss": 0.616943359375,
"step": 329
},
{
"epoch": 2.558139534883721,
"grad_norm": 0.06749380379915237,
"learning_rate": 5.6473080521275736e-05,
"loss": 0.65234375,
"step": 330
},
{
"epoch": 2.565891472868217,
"grad_norm": 0.05622634291648865,
"learning_rate": 5.608227748848883e-05,
"loss": 0.4979248046875,
"step": 331
},
{
"epoch": 2.5736434108527133,
"grad_norm": 0.06649996340274811,
"learning_rate": 5.5692517382152306e-05,
"loss": 0.56787109375,
"step": 332
},
{
"epoch": 2.5813953488372094,
"grad_norm": 0.06813498586416245,
"learning_rate": 5.530381558932778e-05,
"loss": 0.64453125,
"step": 333
},
{
"epoch": 2.5891472868217056,
"grad_norm": 0.06843607872724533,
"learning_rate": 5.491618745529645e-05,
"loss": 0.666015625,
"step": 334
},
{
"epoch": 2.5968992248062017,
"grad_norm": 0.061426661908626556,
"learning_rate": 5.452964828295331e-05,
"loss": 0.62060546875,
"step": 335
},
{
"epoch": 2.604651162790698,
"grad_norm": 0.07091527432203293,
"learning_rate": 5.4144213332203074e-05,
"loss": 0.69775390625,
"step": 336
},
{
"epoch": 2.612403100775194,
"grad_norm": 0.0639883354306221,
"learning_rate": 5.375989781935759e-05,
"loss": 0.583740234375,
"step": 337
},
{
"epoch": 2.62015503875969,
"grad_norm": 0.05846759304404259,
"learning_rate": 5.337671691653526e-05,
"loss": 0.5867919921875,
"step": 338
},
{
"epoch": 2.6279069767441863,
"grad_norm": 0.0625283271074295,
"learning_rate": 5.299468575106205e-05,
"loss": 0.560455322265625,
"step": 339
},
{
"epoch": 2.6356589147286824,
"grad_norm": 0.06804434955120087,
"learning_rate": 5.261381940487415e-05,
"loss": 0.65283203125,
"step": 340
},
{
"epoch": 2.6434108527131785,
"grad_norm": 0.06702367961406708,
"learning_rate": 5.223413291392283e-05,
"loss": 0.63818359375,
"step": 341
},
{
"epoch": 2.6511627906976747,
"grad_norm": 0.06705167144536972,
"learning_rate": 5.185564126758059e-05,
"loss": 0.63525390625,
"step": 342
},
{
"epoch": 2.6589147286821704,
"grad_norm": 0.06649189442396164,
"learning_rate": 5.147835940804957e-05,
"loss": 0.620361328125,
"step": 343
},
{
"epoch": 2.6666666666666665,
"grad_norm": 0.07073359936475754,
"learning_rate": 5.110230222977155e-05,
"loss": 0.595458984375,
"step": 344
},
{
"epoch": 2.6744186046511627,
"grad_norm": 0.06590575724840164,
"learning_rate": 5.0727484578840044e-05,
"loss": 0.650390625,
"step": 345
},
{
"epoch": 2.682170542635659,
"grad_norm": 0.06826666742563248,
"learning_rate": 5.03539212524141e-05,
"loss": 0.619384765625,
"step": 346
},
{
"epoch": 2.689922480620155,
"grad_norm": 0.06565766036510468,
"learning_rate": 4.9981626998134206e-05,
"loss": 0.6201171875,
"step": 347
},
{
"epoch": 2.697674418604651,
"grad_norm": 0.06565503031015396,
"learning_rate": 4.961061651354005e-05,
"loss": 0.6611328125,
"step": 348
},
{
"epoch": 2.705426356589147,
"grad_norm": 0.06592491269111633,
"learning_rate": 4.924090444549032e-05,
"loss": 0.58544921875,
"step": 349
},
{
"epoch": 2.7131782945736433,
"grad_norm": 0.06453471630811691,
"learning_rate": 4.887250538958437e-05,
"loss": 0.63037109375,
"step": 350
},
{
"epoch": 2.7209302325581395,
"grad_norm": 0.06422790139913559,
"learning_rate": 4.850543388958614e-05,
"loss": 0.6494140625,
"step": 351
},
{
"epoch": 2.7286821705426356,
"grad_norm": 0.06656038016080856,
"learning_rate": 4.813970443684994e-05,
"loss": 0.611083984375,
"step": 352
},
{
"epoch": 2.7364341085271318,
"grad_norm": 0.0709843710064888,
"learning_rate": 4.777533146974831e-05,
"loss": 0.603515625,
"step": 353
},
{
"epoch": 2.744186046511628,
"grad_norm": 0.06021834909915924,
"learning_rate": 4.74123293731021e-05,
"loss": 0.50115966796875,
"step": 354
},
{
"epoch": 2.751937984496124,
"grad_norm": 0.0715687945485115,
"learning_rate": 4.705071247761254e-05,
"loss": 0.60595703125,
"step": 355
},
{
"epoch": 2.75968992248062,
"grad_norm": 0.06411100178956985,
"learning_rate": 4.669049505929543e-05,
"loss": 0.62890625,
"step": 356
},
{
"epoch": 2.7674418604651163,
"grad_norm": 0.059254128485918045,
"learning_rate": 4.633169133891771e-05,
"loss": 0.584228515625,
"step": 357
},
{
"epoch": 2.7751937984496124,
"grad_norm": 0.0662040263414383,
"learning_rate": 4.597431548143588e-05,
"loss": 0.62841796875,
"step": 358
},
{
"epoch": 2.7829457364341086,
"grad_norm": 0.06599368900060654,
"learning_rate": 4.561838159543684e-05,
"loss": 0.599609375,
"step": 359
},
{
"epoch": 2.7906976744186047,
"grad_norm": 0.06215868145227432,
"learning_rate": 4.526390373258096e-05,
"loss": 0.6484375,
"step": 360
},
{
"epoch": 2.798449612403101,
"grad_norm": 0.06543800979852676,
"learning_rate": 4.4910895887047336e-05,
"loss": 0.609375,
"step": 361
},
{
"epoch": 2.806201550387597,
"grad_norm": 0.0680144876241684,
"learning_rate": 4.45593719949812e-05,
"loss": 0.65478515625,
"step": 362
},
{
"epoch": 2.813953488372093,
"grad_norm": 0.06762982159852982,
"learning_rate": 4.420934593394395e-05,
"loss": 0.62744140625,
"step": 363
},
{
"epoch": 2.8217054263565893,
"grad_norm": 0.06761243939399719,
"learning_rate": 4.386083152236513e-05,
"loss": 0.65625,
"step": 364
},
{
"epoch": 2.8294573643410854,
"grad_norm": 0.06615626066923141,
"learning_rate": 4.3513842518996946e-05,
"loss": 0.6533203125,
"step": 365
},
{
"epoch": 2.8372093023255816,
"grad_norm": 0.05982562154531479,
"learning_rate": 4.316839262237112e-05,
"loss": 0.563232421875,
"step": 366
},
{
"epoch": 2.8449612403100772,
"grad_norm": 0.06418420374393463,
"learning_rate": 4.282449547025807e-05,
"loss": 0.66845703125,
"step": 367
},
{
"epoch": 2.8527131782945734,
"grad_norm": 0.0631808415055275,
"learning_rate": 4.24821646391285e-05,
"loss": 0.61181640625,
"step": 368
},
{
"epoch": 2.8604651162790695,
"grad_norm": 0.06747371703386307,
"learning_rate": 4.21414136436175e-05,
"loss": 0.62109375,
"step": 369
},
{
"epoch": 2.8682170542635657,
"grad_norm": 0.06588835269212723,
"learning_rate": 4.180225593599085e-05,
"loss": 0.576904296875,
"step": 370
},
{
"epoch": 2.875968992248062,
"grad_norm": 0.06346820294857025,
"learning_rate": 4.1464704905614146e-05,
"loss": 0.60205078125,
"step": 371
},
{
"epoch": 2.883720930232558,
"grad_norm": 0.07391529530286789,
"learning_rate": 4.11287738784241e-05,
"loss": 0.58984375,
"step": 372
},
{
"epoch": 2.891472868217054,
"grad_norm": 0.06806578487157822,
"learning_rate": 4.079447611640244e-05,
"loss": 0.640625,
"step": 373
},
{
"epoch": 2.89922480620155,
"grad_norm": 0.06736227869987488,
"learning_rate": 4.046182481705242e-05,
"loss": 0.596923828125,
"step": 374
},
{
"epoch": 2.9069767441860463,
"grad_norm": 0.0699739083647728,
"learning_rate": 4.013083311287773e-05,
"loss": 0.585693359375,
"step": 375
},
{
"epoch": 2.9147286821705425,
"grad_norm": 0.059111256152391434,
"learning_rate": 3.980151407086409e-05,
"loss": 0.60888671875,
"step": 376
},
{
"epoch": 2.9224806201550386,
"grad_norm": 0.06356891244649887,
"learning_rate": 3.947388069196344e-05,
"loss": 0.65234375,
"step": 377
},
{
"epoch": 2.9302325581395348,
"grad_norm": 0.06365358829498291,
"learning_rate": 3.914794591058055e-05,
"loss": 0.627685546875,
"step": 378
},
{
"epoch": 2.937984496124031,
"grad_norm": 0.0656481608748436,
"learning_rate": 3.8823722594062525e-05,
"loss": 0.6533203125,
"step": 379
},
{
"epoch": 2.945736434108527,
"grad_norm": 0.07547803968191147,
"learning_rate": 3.8501223542190695e-05,
"loss": 0.61083984375,
"step": 380
},
{
"epoch": 2.953488372093023,
"grad_norm": 0.061364006251096725,
"learning_rate": 3.818046148667544e-05,
"loss": 0.56103515625,
"step": 381
},
{
"epoch": 2.9612403100775193,
"grad_norm": 0.06728404760360718,
"learning_rate": 3.786144909065351e-05,
"loss": 0.625244140625,
"step": 382
},
{
"epoch": 2.9689922480620154,
"grad_norm": 0.06856157630681992,
"learning_rate": 3.754419894818802e-05,
"loss": 0.65771484375,
"step": 383
},
{
"epoch": 2.9767441860465116,
"grad_norm": 0.07215557247400284,
"learning_rate": 3.7228723583771395e-05,
"loss": 0.609130859375,
"step": 384
},
{
"epoch": 2.9844961240310077,
"grad_norm": 0.06750628352165222,
"learning_rate": 3.6915035451830844e-05,
"loss": 0.64111328125,
"step": 385
},
{
"epoch": 2.992248062015504,
"grad_norm": 0.06516434252262115,
"learning_rate": 3.66031469362367e-05,
"loss": 0.63134765625,
"step": 386
},
{
"epoch": 3.0,
"grad_norm": 0.07094532996416092,
"learning_rate": 3.6293070349813505e-05,
"loss": 0.513916015625,
"step": 387
},
{
"epoch": 3.007751937984496,
"grad_norm": 0.06942681223154068,
"learning_rate": 3.5984817933853995e-05,
"loss": 0.51708984375,
"step": 388
},
{
"epoch": 3.0155038759689923,
"grad_norm": 0.06859709322452545,
"learning_rate": 3.5678401857635675e-05,
"loss": 0.623046875,
"step": 389
},
{
"epoch": 3.0232558139534884,
"grad_norm": 0.07105369865894318,
"learning_rate": 3.5373834217940605e-05,
"loss": 0.58203125,
"step": 390
},
{
"epoch": 3.0310077519379846,
"grad_norm": 0.07783112674951553,
"learning_rate": 3.5071127038577686e-05,
"loss": 0.59130859375,
"step": 391
},
{
"epoch": 3.0387596899224807,
"grad_norm": 0.07641559839248657,
"learning_rate": 3.4770292269908044e-05,
"loss": 0.640869140625,
"step": 392
},
{
"epoch": 3.046511627906977,
"grad_norm": 0.07343966513872147,
"learning_rate": 3.4471341788373234e-05,
"loss": 0.63916015625,
"step": 393
},
{
"epoch": 3.054263565891473,
"grad_norm": 0.07169951498508453,
"learning_rate": 3.417428739602639e-05,
"loss": 0.623779296875,
"step": 394
},
{
"epoch": 3.062015503875969,
"grad_norm": 0.06770291924476624,
"learning_rate": 3.387914082006628e-05,
"loss": 0.533447265625,
"step": 395
},
{
"epoch": 3.0697674418604652,
"grad_norm": 0.06953474879264832,
"learning_rate": 3.358591371237435e-05,
"loss": 0.59521484375,
"step": 396
},
{
"epoch": 3.0775193798449614,
"grad_norm": 0.07055654376745224,
"learning_rate": 3.329461764905473e-05,
"loss": 0.559814453125,
"step": 397
},
{
"epoch": 3.0852713178294575,
"grad_norm": 0.06619474291801453,
"learning_rate": 3.300526412997721e-05,
"loss": 0.58642578125,
"step": 398
},
{
"epoch": 3.0930232558139537,
"grad_norm": 0.07193581759929657,
"learning_rate": 3.2717864578323267e-05,
"loss": 0.61865234375,
"step": 399
},
{
"epoch": 3.10077519379845,
"grad_norm": 0.06734154373407364,
"learning_rate": 3.243243034013511e-05,
"loss": 0.559814453125,
"step": 400
},
{
"epoch": 3.108527131782946,
"grad_norm": 0.06870515644550323,
"learning_rate": 3.2148972683867707e-05,
"loss": 0.556396484375,
"step": 401
},
{
"epoch": 3.116279069767442,
"grad_norm": 0.07094790786504745,
"learning_rate": 3.186750279994398e-05,
"loss": 0.60400390625,
"step": 402
},
{
"epoch": 3.124031007751938,
"grad_norm": 0.06578138470649719,
"learning_rate": 3.158803180031298e-05,
"loss": 0.5087890625,
"step": 403
},
{
"epoch": 3.1317829457364343,
"grad_norm": 0.06036490574479103,
"learning_rate": 3.131057071801127e-05,
"loss": 0.50390625,
"step": 404
},
{
"epoch": 3.13953488372093,
"grad_norm": 0.0690043643116951,
"learning_rate": 3.103513050672726e-05,
"loss": 0.54931640625,
"step": 405
},
{
"epoch": 3.147286821705426,
"grad_norm": 0.06643012166023254,
"learning_rate": 3.076172204036889e-05,
"loss": 0.528076171875,
"step": 406
},
{
"epoch": 3.1550387596899223,
"grad_norm": 0.06908755004405975,
"learning_rate": 3.0490356112634235e-05,
"loss": 0.56201171875,
"step": 407
},
{
"epoch": 3.1627906976744184,
"grad_norm": 0.06997007131576538,
"learning_rate": 3.0221043436585472e-05,
"loss": 0.57470703125,
"step": 408
},
{
"epoch": 3.1705426356589146,
"grad_norm": 0.06872081011533737,
"learning_rate": 2.995379464422592e-05,
"loss": 0.545166015625,
"step": 409
},
{
"epoch": 3.1782945736434107,
"grad_norm": 0.06880426406860352,
"learning_rate": 2.9688620286080303e-05,
"loss": 0.545166015625,
"step": 410
},
{
"epoch": 3.186046511627907,
"grad_norm": 0.07061348855495453,
"learning_rate": 2.9425530830778223e-05,
"loss": 0.5673828125,
"step": 411
},
{
"epoch": 3.193798449612403,
"grad_norm": 0.06754624098539352,
"learning_rate": 2.9164536664640896e-05,
"loss": 0.631591796875,
"step": 412
},
{
"epoch": 3.201550387596899,
"grad_norm": 0.08922949433326721,
"learning_rate": 2.890564809127111e-05,
"loss": 0.51611328125,
"step": 413
},
{
"epoch": 3.201550387596899,
"eval_loss": 0.9375,
"eval_runtime": 6.5061,
"eval_samples_per_second": 1.076,
"eval_steps_per_second": 0.154,
"step": 413
},
{
"epoch": 3.2093023255813953,
"grad_norm": 0.07229218631982803,
"learning_rate": 2.864887533114645e-05,
"loss": 0.5322265625,
"step": 414
},
{
"epoch": 3.2170542635658914,
"grad_norm": 0.08055881410837173,
"learning_rate": 2.839422852121582e-05,
"loss": 0.53857421875,
"step": 415
},
{
"epoch": 3.2248062015503876,
"grad_norm": 0.08100420981645584,
"learning_rate": 2.8141717714499273e-05,
"loss": 0.563232421875,
"step": 416
},
{
"epoch": 3.2325581395348837,
"grad_norm": 0.07434435188770294,
"learning_rate": 2.7891352879691055e-05,
"loss": 0.55224609375,
"step": 417
},
{
"epoch": 3.24031007751938,
"grad_norm": 0.07508531957864761,
"learning_rate": 2.7643143900766157e-05,
"loss": 0.48291015625,
"step": 418
},
{
"epoch": 3.248062015503876,
"grad_norm": 0.07350693643093109,
"learning_rate": 2.739710057659008e-05,
"loss": 0.47900390625,
"step": 419
},
{
"epoch": 3.255813953488372,
"grad_norm": 0.07112405449151993,
"learning_rate": 2.715323262053196e-05,
"loss": 0.4951171875,
"step": 420
},
{
"epoch": 3.2635658914728682,
"grad_norm": 0.07355426251888275,
"learning_rate": 2.6911549660081147e-05,
"loss": 0.54248046875,
"step": 421
},
{
"epoch": 3.2713178294573644,
"grad_norm": 0.07093562930822372,
"learning_rate": 2.6672061236467067e-05,
"loss": 0.508056640625,
"step": 422
},
{
"epoch": 3.2790697674418605,
"grad_norm": 0.07659183442592621,
"learning_rate": 2.6434776804282633e-05,
"loss": 0.524658203125,
"step": 423
},
{
"epoch": 3.2868217054263567,
"grad_norm": 0.07301755249500275,
"learning_rate": 2.6199705731110945e-05,
"loss": 0.4892578125,
"step": 424
},
{
"epoch": 3.294573643410853,
"grad_norm": 0.07013290375471115,
"learning_rate": 2.5966857297155437e-05,
"loss": 0.483154296875,
"step": 425
},
{
"epoch": 3.302325581395349,
"grad_norm": 0.0757346972823143,
"learning_rate": 2.573624069487359e-05,
"loss": 0.514404296875,
"step": 426
},
{
"epoch": 3.310077519379845,
"grad_norm": 0.08032671362161636,
"learning_rate": 2.5507865028613997e-05,
"loss": 0.52099609375,
"step": 427
},
{
"epoch": 3.317829457364341,
"grad_norm": 0.08637872338294983,
"learning_rate": 2.5281739314256896e-05,
"loss": 0.51806640625,
"step": 428
},
{
"epoch": 3.3255813953488373,
"grad_norm": 0.06795325875282288,
"learning_rate": 2.505787247885831e-05,
"loss": 0.4205322265625,
"step": 429
},
{
"epoch": 3.3333333333333335,
"grad_norm": 0.07763935625553131,
"learning_rate": 2.483627336029758e-05,
"loss": 0.533447265625,
"step": 430
},
{
"epoch": 3.3410852713178296,
"grad_norm": 0.07631447166204453,
"learning_rate": 2.461695070692848e-05,
"loss": 0.4873046875,
"step": 431
},
{
"epoch": 3.3488372093023258,
"grad_norm": 0.07747241109609604,
"learning_rate": 2.439991317723381e-05,
"loss": 0.442626953125,
"step": 432
},
{
"epoch": 3.356589147286822,
"grad_norm": 0.07769514620304108,
"learning_rate": 2.4185169339483618e-05,
"loss": 0.478515625,
"step": 433
},
{
"epoch": 3.3643410852713176,
"grad_norm": 0.08305241912603378,
"learning_rate": 2.3972727671396924e-05,
"loss": 0.535888671875,
"step": 434
},
{
"epoch": 3.3720930232558137,
"grad_norm": 0.07428973913192749,
"learning_rate": 2.3762596559807017e-05,
"loss": 0.4754638671875,
"step": 435
},
{
"epoch": 3.37984496124031,
"grad_norm": 0.08149438351392746,
"learning_rate": 2.3554784300330405e-05,
"loss": 0.470703125,
"step": 436
},
{
"epoch": 3.387596899224806,
"grad_norm": 0.08471261709928513,
"learning_rate": 2.334929909703922e-05,
"loss": 0.50048828125,
"step": 437
},
{
"epoch": 3.395348837209302,
"grad_norm": 0.07583427429199219,
"learning_rate": 2.3146149062137462e-05,
"loss": 0.45703125,
"step": 438
},
{
"epoch": 3.4031007751937983,
"grad_norm": 0.07008874416351318,
"learning_rate": 2.294534221564066e-05,
"loss": 0.4544830322265625,
"step": 439
},
{
"epoch": 3.4108527131782944,
"grad_norm": 0.08026977628469467,
"learning_rate": 2.2746886485059278e-05,
"loss": 0.48681640625,
"step": 440
},
{
"epoch": 3.4186046511627906,
"grad_norm": 0.07984422147274017,
"learning_rate": 2.2550789705085744e-05,
"loss": 0.50732421875,
"step": 441
},
{
"epoch": 3.4263565891472867,
"grad_norm": 0.09029471129179001,
"learning_rate": 2.235705961728517e-05,
"loss": 0.361083984375,
"step": 442
},
{
"epoch": 3.434108527131783,
"grad_norm": 0.07068944722414017,
"learning_rate": 2.2165703869789695e-05,
"loss": 0.4365234375,
"step": 443
},
{
"epoch": 3.441860465116279,
"grad_norm": 0.07630511373281479,
"learning_rate": 2.1976730016996578e-05,
"loss": 0.4755859375,
"step": 444
},
{
"epoch": 3.449612403100775,
"grad_norm": 0.07964383065700531,
"learning_rate": 2.179014551926995e-05,
"loss": 0.502197265625,
"step": 445
},
{
"epoch": 3.4573643410852712,
"grad_norm": 0.06727761775255203,
"learning_rate": 2.1605957742646316e-05,
"loss": 0.4046630859375,
"step": 446
},
{
"epoch": 3.4651162790697674,
"grad_norm": 0.07407158613204956,
"learning_rate": 2.1424173958543693e-05,
"loss": 0.435302734375,
"step": 447
},
{
"epoch": 3.4728682170542635,
"grad_norm": 0.07212996482849121,
"learning_rate": 2.124480134347461e-05,
"loss": 0.4476318359375,
"step": 448
},
{
"epoch": 3.4806201550387597,
"grad_norm": 0.08215648680925369,
"learning_rate": 2.1067846978762794e-05,
"loss": 0.51171875,
"step": 449
},
{
"epoch": 3.488372093023256,
"grad_norm": 0.08030379563570023,
"learning_rate": 2.0893317850263563e-05,
"loss": 0.46484375,
"step": 450
},
{
"epoch": 3.496124031007752,
"grad_norm": 0.074031762778759,
"learning_rate": 2.0721220848088068e-05,
"loss": 0.455078125,
"step": 451
},
{
"epoch": 3.503875968992248,
"grad_norm": 0.08028865605592728,
"learning_rate": 2.055156276633127e-05,
"loss": 0.47021484375,
"step": 452
},
{
"epoch": 3.511627906976744,
"grad_norm": 0.07204830646514893,
"learning_rate": 2.0384350302803752e-05,
"loss": 0.44287109375,
"step": 453
},
{
"epoch": 3.5193798449612403,
"grad_norm": 0.07277313619852066,
"learning_rate": 2.0219590058767242e-05,
"loss": 0.45819091796875,
"step": 454
},
{
"epoch": 3.5271317829457365,
"grad_norm": 0.0787966251373291,
"learning_rate": 2.0057288538674088e-05,
"loss": 0.456298828125,
"step": 455
},
{
"epoch": 3.5348837209302326,
"grad_norm": 0.07700956612825394,
"learning_rate": 1.9897452149910364e-05,
"loss": 0.479248046875,
"step": 456
},
{
"epoch": 3.5426356589147288,
"grad_norm": 0.07119468599557877,
"learning_rate": 1.9740087202543035e-05,
"loss": 0.4141845703125,
"step": 457
},
{
"epoch": 3.550387596899225,
"grad_norm": 0.0764649286866188,
"learning_rate": 1.9585199909070763e-05,
"loss": 0.460693359375,
"step": 458
},
{
"epoch": 3.558139534883721,
"grad_norm": 0.0787726417183876,
"learning_rate": 1.943279638417869e-05,
"loss": 0.48486328125,
"step": 459
},
{
"epoch": 3.565891472868217,
"grad_norm": 0.06715036183595657,
"learning_rate": 1.9282882644497018e-05,
"loss": 0.3721923828125,
"step": 460
},
{
"epoch": 3.5736434108527133,
"grad_norm": 0.07189641892910004,
"learning_rate": 1.91354646083635e-05,
"loss": 0.4287109375,
"step": 461
},
{
"epoch": 3.5813953488372094,
"grad_norm": 0.0780823677778244,
"learning_rate": 1.899054809558978e-05,
"loss": 0.474609375,
"step": 462
},
{
"epoch": 3.5891472868217056,
"grad_norm": 0.07662241905927658,
"learning_rate": 1.8848138827231642e-05,
"loss": 0.496337890625,
"step": 463
},
{
"epoch": 3.5968992248062017,
"grad_norm": 0.07655166834592819,
"learning_rate": 1.870824242536318e-05,
"loss": 0.470947265625,
"step": 464
},
{
"epoch": 3.604651162790698,
"grad_norm": 0.08279549330472946,
"learning_rate": 1.8570864412854765e-05,
"loss": 0.532958984375,
"step": 465
},
{
"epoch": 3.612403100775194,
"grad_norm": 0.07830751687288284,
"learning_rate": 1.843601021315512e-05,
"loss": 0.440673828125,
"step": 466
},
{
"epoch": 3.62015503875969,
"grad_norm": 0.07219333201646805,
"learning_rate": 1.8303685150077136e-05,
"loss": 0.4556884765625,
"step": 467
},
{
"epoch": 3.6279069767441863,
"grad_norm": 0.07164263725280762,
"learning_rate": 1.8173894447587733e-05,
"loss": 0.427947998046875,
"step": 468
},
{
"epoch": 3.6356589147286824,
"grad_norm": 0.0806884765625,
"learning_rate": 1.80466432296016e-05,
"loss": 0.4912109375,
"step": 469
},
{
"epoch": 3.6434108527131785,
"grad_norm": 0.07723332941532135,
"learning_rate": 1.792193651977894e-05,
"loss": 0.485595703125,
"step": 470
},
{
"epoch": 3.6511627906976747,
"grad_norm": 0.07822735607624054,
"learning_rate": 1.7799779241327125e-05,
"loss": 0.47705078125,
"step": 471
},
{
"epoch": 3.6589147286821704,
"grad_norm": 0.08420364558696747,
"learning_rate": 1.768017621680634e-05,
"loss": 0.470947265625,
"step": 472
},
{
"epoch": 3.6666666666666665,
"grad_norm": 0.08089973032474518,
"learning_rate": 1.75631321679392e-05,
"loss": 0.43701171875,
"step": 473
},
{
"epoch": 3.6744186046511627,
"grad_norm": 0.07639868557453156,
"learning_rate": 1.7448651715424343e-05,
"loss": 0.500244140625,
"step": 474
},
{
"epoch": 3.682170542635659,
"grad_norm": 0.07755531370639801,
"learning_rate": 1.733673937875401e-05,
"loss": 0.4736328125,
"step": 475
},
{
"epoch": 3.689922480620155,
"grad_norm": 0.08167009055614471,
"learning_rate": 1.7227399576035636e-05,
"loss": 0.469970703125,
"step": 476
},
{
"epoch": 3.697674418604651,
"grad_norm": 0.08117778599262238,
"learning_rate": 1.7120636623817402e-05,
"loss": 0.509033203125,
"step": 477
},
{
"epoch": 3.705426356589147,
"grad_norm": 0.07648774236440659,
"learning_rate": 1.7016454736917857e-05,
"loss": 0.446533203125,
"step": 478
},
{
"epoch": 3.7131782945736433,
"grad_norm": 0.08431831747293472,
"learning_rate": 1.6914858028259504e-05,
"loss": 0.48974609375,
"step": 479
},
{
"epoch": 3.7209302325581395,
"grad_norm": 0.07815668731927872,
"learning_rate": 1.6815850508706452e-05,
"loss": 0.501708984375,
"step": 480
},
{
"epoch": 3.7286821705426356,
"grad_norm": 0.0762772262096405,
"learning_rate": 1.6719436086906034e-05,
"loss": 0.465576171875,
"step": 481
},
{
"epoch": 3.7364341085271318,
"grad_norm": 0.07828109711408615,
"learning_rate": 1.6625618569134547e-05,
"loss": 0.4580078125,
"step": 482
},
{
"epoch": 3.744186046511628,
"grad_norm": 0.06441089510917664,
"learning_rate": 1.653440165914694e-05,
"loss": 0.392425537109375,
"step": 483
},
{
"epoch": 3.751937984496124,
"grad_norm": 0.07554791122674942,
"learning_rate": 1.6445788958030633e-05,
"loss": 0.465576171875,
"step": 484
},
{
"epoch": 3.75968992248062,
"grad_norm": 0.07720019668340683,
"learning_rate": 1.6359783964063338e-05,
"loss": 0.484375,
"step": 485
},
{
"epoch": 3.7674418604651163,
"grad_norm": 0.07605230063199997,
"learning_rate": 1.6276390072574957e-05,
"loss": 0.4639892578125,
"step": 486
},
{
"epoch": 3.7751937984496124,
"grad_norm": 0.07766040414571762,
"learning_rate": 1.6195610575813518e-05,
"loss": 0.49560546875,
"step": 487
},
{
"epoch": 3.7829457364341086,
"grad_norm": 0.07689350843429565,
"learning_rate": 1.611744866281525e-05,
"loss": 0.471435546875,
"step": 488
},
{
"epoch": 3.7906976744186047,
"grad_norm": 0.07278704643249512,
"learning_rate": 1.604190741927864e-05,
"loss": 0.5166015625,
"step": 489
},
{
"epoch": 3.798449612403101,
"grad_norm": 0.07505790144205093,
"learning_rate": 1.5968989827442633e-05,
"loss": 0.468994140625,
"step": 490
},
{
"epoch": 3.806201550387597,
"grad_norm": 0.07847912609577179,
"learning_rate": 1.5898698765968908e-05,
"loss": 0.510009765625,
"step": 491
},
{
"epoch": 3.813953488372093,
"grad_norm": 0.07862749695777893,
"learning_rate": 1.5831037009828207e-05,
"loss": 0.482421875,
"step": 492
},
{
"epoch": 3.8217054263565893,
"grad_norm": 0.07740738242864609,
"learning_rate": 1.5766007230190806e-05,
"loss": 0.5146484375,
"step": 493
},
{
"epoch": 3.8294573643410854,
"grad_norm": 0.08023978769779205,
"learning_rate": 1.5703611994321064e-05,
"loss": 0.50927734375,
"step": 494
},
{
"epoch": 3.8372093023255816,
"grad_norm": 0.07485775649547577,
"learning_rate": 1.5643853765476044e-05,
"loss": 0.443115234375,
"step": 495
},
{
"epoch": 3.8449612403100772,
"grad_norm": 0.08099298924207687,
"learning_rate": 1.5586734902808312e-05,
"loss": 0.5302734375,
"step": 496
},
{
"epoch": 3.8527131782945734,
"grad_norm": 0.07868078351020813,
"learning_rate": 1.553225766127275e-05,
"loss": 0.48095703125,
"step": 497
},
{
"epoch": 3.8604651162790695,
"grad_norm": 0.08307386934757233,
"learning_rate": 1.5480424191537582e-05,
"loss": 0.487548828125,
"step": 498
},
{
"epoch": 3.8682170542635657,
"grad_norm": 0.07793569564819336,
"learning_rate": 1.543123653989943e-05,
"loss": 0.4443359375,
"step": 499
},
{
"epoch": 3.875968992248062,
"grad_norm": 0.078414186835289,
"learning_rate": 1.5384696648202572e-05,
"loss": 0.473876953125,
"step": 500
},
{
"epoch": 3.883720930232558,
"grad_norm": 0.07785522192716599,
"learning_rate": 1.5340806353762237e-05,
"loss": 0.456298828125,
"step": 501
},
{
"epoch": 3.891472868217054,
"grad_norm": 0.07686799764633179,
"learning_rate": 1.52995673892921e-05,
"loss": 0.50341796875,
"step": 502
},
{
"epoch": 3.89922480620155,
"grad_norm": 0.07719577848911285,
"learning_rate": 1.5260981382835856e-05,
"loss": 0.46826171875,
"step": 503
},
{
"epoch": 3.9069767441860463,
"grad_norm": 0.07671701908111572,
"learning_rate": 1.5225049857702982e-05,
"loss": 0.459716796875,
"step": 504
},
{
"epoch": 3.9147286821705425,
"grad_norm": 0.07271593064069748,
"learning_rate": 1.519177423240856e-05,
"loss": 0.499755859375,
"step": 505
},
{
"epoch": 3.9224806201550386,
"grad_norm": 0.08233615756034851,
"learning_rate": 1.5161155820617298e-05,
"loss": 0.527587890625,
"step": 506
},
{
"epoch": 3.9302325581395348,
"grad_norm": 0.07872453331947327,
"learning_rate": 1.5133195831091668e-05,
"loss": 0.506103515625,
"step": 507
},
{
"epoch": 3.937984496124031,
"grad_norm": 0.07894981652498245,
"learning_rate": 1.5107895367644186e-05,
"loss": 0.52978515625,
"step": 508
},
{
"epoch": 3.945736434108527,
"grad_norm": 0.3182094991207123,
"learning_rate": 1.5085255429093821e-05,
"loss": 0.493896484375,
"step": 509
},
{
"epoch": 3.953488372093023,
"grad_norm": 0.07412038743495941,
"learning_rate": 1.5065276909226583e-05,
"loss": 0.454345703125,
"step": 510
},
{
"epoch": 3.9612403100775193,
"grad_norm": 0.07970291376113892,
"learning_rate": 1.5047960596760229e-05,
"loss": 0.505615234375,
"step": 511
},
{
"epoch": 3.9689922480620154,
"grad_norm": 0.08109211176633835,
"learning_rate": 1.5033307175313116e-05,
"loss": 0.536865234375,
"step": 512
},
{
"epoch": 3.9767441860465116,
"grad_norm": 0.078403539955616,
"learning_rate": 1.5021317223377253e-05,
"loss": 0.485107421875,
"step": 513
},
{
"epoch": 3.9844961240310077,
"grad_norm": 0.07839163392782211,
"learning_rate": 1.5011991214295394e-05,
"loss": 0.517578125,
"step": 514
},
{
"epoch": 3.992248062015504,
"grad_norm": 0.07636582851409912,
"learning_rate": 1.5005329516242412e-05,
"loss": 0.51708984375,
"step": 515
},
{
"epoch": 4.0,
"grad_norm": 0.08016166090965271,
"learning_rate": 1.5001332392210745e-05,
"loss": 0.37939453125,
"step": 516
},
{
"epoch": 4.0,
"eval_loss": 0.96484375,
"eval_runtime": 6.4728,
"eval_samples_per_second": 1.081,
"eval_steps_per_second": 0.154,
"step": 516
}
],
"logging_steps": 1.0,
"max_steps": 516,
"num_input_tokens_seen": 0,
"num_train_epochs": 4,
"save_steps": 0,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 4.279527187500604e+19,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}