nttx's picture
Training in progress, step 100, checkpoint
a8be372 verified
raw
history blame
19 kB
{
"best_metric": 3.9525041580200195,
"best_model_checkpoint": "miner_id_24/checkpoint-100",
"epoch": 0.015006283881375326,
"eval_steps": 50,
"global_step": 100,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.00015006283881375325,
"grad_norm": 6.556857585906982,
"learning_rate": 5.000000000000001e-07,
"loss": 32.4793,
"step": 1
},
{
"epoch": 0.00015006283881375325,
"eval_loss": 4.422780513763428,
"eval_runtime": 1166.7634,
"eval_samples_per_second": 9.62,
"eval_steps_per_second": 2.405,
"step": 1
},
{
"epoch": 0.0003001256776275065,
"grad_norm": 6.7071757316589355,
"learning_rate": 1.0000000000000002e-06,
"loss": 33.3956,
"step": 2
},
{
"epoch": 0.0004501885164412598,
"grad_norm": 7.008890628814697,
"learning_rate": 1.5e-06,
"loss": 33.3792,
"step": 3
},
{
"epoch": 0.000600251355255013,
"grad_norm": 7.096307754516602,
"learning_rate": 2.0000000000000003e-06,
"loss": 35.099,
"step": 4
},
{
"epoch": 0.0007503141940687663,
"grad_norm": 7.1125569343566895,
"learning_rate": 2.5e-06,
"loss": 35.264,
"step": 5
},
{
"epoch": 0.0009003770328825196,
"grad_norm": 7.323802947998047,
"learning_rate": 3e-06,
"loss": 34.7285,
"step": 6
},
{
"epoch": 0.001050439871696273,
"grad_norm": 7.22035026550293,
"learning_rate": 3.5e-06,
"loss": 35.6589,
"step": 7
},
{
"epoch": 0.001200502710510026,
"grad_norm": 7.584096908569336,
"learning_rate": 4.000000000000001e-06,
"loss": 36.3612,
"step": 8
},
{
"epoch": 0.0013505655493237794,
"grad_norm": 8.085339546203613,
"learning_rate": 4.5e-06,
"loss": 35.9618,
"step": 9
},
{
"epoch": 0.0015006283881375327,
"grad_norm": 9.453437805175781,
"learning_rate": 5e-06,
"loss": 37.0509,
"step": 10
},
{
"epoch": 0.0016506912269512858,
"grad_norm": 10.464935302734375,
"learning_rate": 4.99847706754774e-06,
"loss": 39.5601,
"step": 11
},
{
"epoch": 0.0018007540657650391,
"grad_norm": 9.660285949707031,
"learning_rate": 4.993910125649561e-06,
"loss": 37.7704,
"step": 12
},
{
"epoch": 0.0019508169045787923,
"grad_norm": 11.434601783752441,
"learning_rate": 4.986304738420684e-06,
"loss": 39.5423,
"step": 13
},
{
"epoch": 0.002100879743392546,
"grad_norm": 12.925939559936523,
"learning_rate": 4.975670171853926e-06,
"loss": 40.1121,
"step": 14
},
{
"epoch": 0.002250942582206299,
"grad_norm": 13.035168647766113,
"learning_rate": 4.962019382530521e-06,
"loss": 39.6252,
"step": 15
},
{
"epoch": 0.002401005421020052,
"grad_norm": 11.976016998291016,
"learning_rate": 4.9453690018345144e-06,
"loss": 39.7855,
"step": 16
},
{
"epoch": 0.0025510682598338056,
"grad_norm": 14.432867050170898,
"learning_rate": 4.925739315689991e-06,
"loss": 43.1844,
"step": 17
},
{
"epoch": 0.0027011310986475587,
"grad_norm": 13.167061805725098,
"learning_rate": 4.903154239845798e-06,
"loss": 42.9399,
"step": 18
},
{
"epoch": 0.002851193937461312,
"grad_norm": 16.086027145385742,
"learning_rate": 4.8776412907378845e-06,
"loss": 43.4687,
"step": 19
},
{
"epoch": 0.0030012567762750654,
"grad_norm": 16.82833480834961,
"learning_rate": 4.849231551964771e-06,
"loss": 43.5851,
"step": 20
},
{
"epoch": 0.0031513196150888185,
"grad_norm": 16.73269271850586,
"learning_rate": 4.817959636416969e-06,
"loss": 44.3198,
"step": 21
},
{
"epoch": 0.0033013824539025716,
"grad_norm": 22.951553344726562,
"learning_rate": 4.783863644106502e-06,
"loss": 45.8731,
"step": 22
},
{
"epoch": 0.003451445292716325,
"grad_norm": 19.36189842224121,
"learning_rate": 4.746985115747918e-06,
"loss": 45.582,
"step": 23
},
{
"epoch": 0.0036015081315300783,
"grad_norm": 20.003419876098633,
"learning_rate": 4.707368982147318e-06,
"loss": 46.9365,
"step": 24
},
{
"epoch": 0.0037515709703438314,
"grad_norm": 13.010815620422363,
"learning_rate": 4.665063509461098e-06,
"loss": 35.3997,
"step": 25
},
{
"epoch": 0.0039016338091575845,
"grad_norm": 12.633563995361328,
"learning_rate": 4.620120240391065e-06,
"loss": 33.8044,
"step": 26
},
{
"epoch": 0.004051696647971338,
"grad_norm": 12.934494972229004,
"learning_rate": 4.572593931387604e-06,
"loss": 34.0807,
"step": 27
},
{
"epoch": 0.004201759486785092,
"grad_norm": 12.416427612304688,
"learning_rate": 4.522542485937369e-06,
"loss": 31.6505,
"step": 28
},
{
"epoch": 0.004351822325598845,
"grad_norm": 12.711592674255371,
"learning_rate": 4.470026884016805e-06,
"loss": 33.807,
"step": 29
},
{
"epoch": 0.004501885164412598,
"grad_norm": 13.012476921081543,
"learning_rate": 4.415111107797445e-06,
"loss": 33.2907,
"step": 30
},
{
"epoch": 0.004651948003226351,
"grad_norm": 13.100297927856445,
"learning_rate": 4.357862063693486e-06,
"loss": 32.955,
"step": 31
},
{
"epoch": 0.004802010842040104,
"grad_norm": 12.629734992980957,
"learning_rate": 4.2983495008466285e-06,
"loss": 33.4184,
"step": 32
},
{
"epoch": 0.004952073680853857,
"grad_norm": 13.031803131103516,
"learning_rate": 4.236645926147493e-06,
"loss": 32.4434,
"step": 33
},
{
"epoch": 0.005102136519667611,
"grad_norm": 13.07551383972168,
"learning_rate": 4.172826515897146e-06,
"loss": 31.8428,
"step": 34
},
{
"epoch": 0.005252199358481364,
"grad_norm": 13.340009689331055,
"learning_rate": 4.106969024216348e-06,
"loss": 30.6754,
"step": 35
},
{
"epoch": 0.005402262197295117,
"grad_norm": 13.459136962890625,
"learning_rate": 4.039153688314146e-06,
"loss": 32.3325,
"step": 36
},
{
"epoch": 0.0055523250361088705,
"grad_norm": 13.509114265441895,
"learning_rate": 3.969463130731183e-06,
"loss": 30.3527,
"step": 37
},
{
"epoch": 0.005702387874922624,
"grad_norm": 14.133980751037598,
"learning_rate": 3.897982258676867e-06,
"loss": 29.5306,
"step": 38
},
{
"epoch": 0.005852450713736377,
"grad_norm": 13.122635841369629,
"learning_rate": 3.824798160583012e-06,
"loss": 27.8162,
"step": 39
},
{
"epoch": 0.006002513552550131,
"grad_norm": 13.173026084899902,
"learning_rate": 3.7500000000000005e-06,
"loss": 28.7461,
"step": 40
},
{
"epoch": 0.006152576391363884,
"grad_norm": 15.021635055541992,
"learning_rate": 3.6736789069647273e-06,
"loss": 29.4984,
"step": 41
},
{
"epoch": 0.006302639230177637,
"grad_norm": 14.209413528442383,
"learning_rate": 3.595927866972694e-06,
"loss": 30.0559,
"step": 42
},
{
"epoch": 0.00645270206899139,
"grad_norm": 14.6431884765625,
"learning_rate": 3.516841607689501e-06,
"loss": 29.7791,
"step": 43
},
{
"epoch": 0.006602764907805143,
"grad_norm": 12.084189414978027,
"learning_rate": 3.436516483539781e-06,
"loss": 28.6705,
"step": 44
},
{
"epoch": 0.006752827746618896,
"grad_norm": 13.18972396850586,
"learning_rate": 3.3550503583141726e-06,
"loss": 28.7666,
"step": 45
},
{
"epoch": 0.00690289058543265,
"grad_norm": 13.173684120178223,
"learning_rate": 3.272542485937369e-06,
"loss": 27.7091,
"step": 46
},
{
"epoch": 0.0070529534242464035,
"grad_norm": 14.174872398376465,
"learning_rate": 3.189093389542498e-06,
"loss": 28.4409,
"step": 47
},
{
"epoch": 0.007203016263060157,
"grad_norm": 13.488956451416016,
"learning_rate": 3.1048047389991693e-06,
"loss": 25.6084,
"step": 48
},
{
"epoch": 0.00735307910187391,
"grad_norm": 15.413603782653809,
"learning_rate": 3.019779227044398e-06,
"loss": 26.7375,
"step": 49
},
{
"epoch": 0.007503141940687663,
"grad_norm": 14.66285228729248,
"learning_rate": 2.9341204441673267e-06,
"loss": 28.3319,
"step": 50
},
{
"epoch": 0.007503141940687663,
"eval_loss": 4.124388217926025,
"eval_runtime": 1172.9983,
"eval_samples_per_second": 9.569,
"eval_steps_per_second": 2.392,
"step": 50
},
{
"epoch": 0.007653204779501416,
"grad_norm": 9.979507446289062,
"learning_rate": 2.847932752400164e-06,
"loss": 30.6154,
"step": 51
},
{
"epoch": 0.007803267618315169,
"grad_norm": 10.939770698547363,
"learning_rate": 2.761321158169134e-06,
"loss": 31.6489,
"step": 52
},
{
"epoch": 0.007953330457128923,
"grad_norm": 11.191797256469727,
"learning_rate": 2.6743911843603134e-06,
"loss": 30.9841,
"step": 53
},
{
"epoch": 0.008103393295942675,
"grad_norm": 11.720529556274414,
"learning_rate": 2.587248741756253e-06,
"loss": 32.4647,
"step": 54
},
{
"epoch": 0.00825345613475643,
"grad_norm": 13.322903633117676,
"learning_rate": 2.5e-06,
"loss": 33.2152,
"step": 55
},
{
"epoch": 0.008403518973570183,
"grad_norm": 12.972123146057129,
"learning_rate": 2.4127512582437486e-06,
"loss": 32.6633,
"step": 56
},
{
"epoch": 0.008553581812383936,
"grad_norm": 12.695440292358398,
"learning_rate": 2.325608815639687e-06,
"loss": 33.9742,
"step": 57
},
{
"epoch": 0.00870364465119769,
"grad_norm": 13.083794593811035,
"learning_rate": 2.238678841830867e-06,
"loss": 34.3758,
"step": 58
},
{
"epoch": 0.008853707490011442,
"grad_norm": 14.709982872009277,
"learning_rate": 2.1520672475998374e-06,
"loss": 33.0617,
"step": 59
},
{
"epoch": 0.009003770328825196,
"grad_norm": 15.33502197265625,
"learning_rate": 2.0658795558326745e-06,
"loss": 32.3498,
"step": 60
},
{
"epoch": 0.009153833167638948,
"grad_norm": 16.43514060974121,
"learning_rate": 1.9802207729556023e-06,
"loss": 35.4804,
"step": 61
},
{
"epoch": 0.009303896006452702,
"grad_norm": 16.312402725219727,
"learning_rate": 1.895195261000831e-06,
"loss": 36.8484,
"step": 62
},
{
"epoch": 0.009453958845266456,
"grad_norm": 18.906774520874023,
"learning_rate": 1.8109066104575023e-06,
"loss": 37.3672,
"step": 63
},
{
"epoch": 0.009604021684080208,
"grad_norm": 17.955244064331055,
"learning_rate": 1.7274575140626318e-06,
"loss": 38.5029,
"step": 64
},
{
"epoch": 0.009754084522893962,
"grad_norm": 20.66045379638672,
"learning_rate": 1.6449496416858285e-06,
"loss": 35.5722,
"step": 65
},
{
"epoch": 0.009904147361707714,
"grad_norm": 20.17714500427246,
"learning_rate": 1.56348351646022e-06,
"loss": 37.8927,
"step": 66
},
{
"epoch": 0.010054210200521468,
"grad_norm": 22.08597755432129,
"learning_rate": 1.4831583923105e-06,
"loss": 38.4573,
"step": 67
},
{
"epoch": 0.010204273039335222,
"grad_norm": 24.34529685974121,
"learning_rate": 1.4040721330273063e-06,
"loss": 40.1156,
"step": 68
},
{
"epoch": 0.010354335878148975,
"grad_norm": 22.071252822875977,
"learning_rate": 1.3263210930352737e-06,
"loss": 40.0515,
"step": 69
},
{
"epoch": 0.010504398716962729,
"grad_norm": 23.233043670654297,
"learning_rate": 1.2500000000000007e-06,
"loss": 38.8181,
"step": 70
},
{
"epoch": 0.010654461555776481,
"grad_norm": 24.044532775878906,
"learning_rate": 1.1752018394169882e-06,
"loss": 38.3733,
"step": 71
},
{
"epoch": 0.010804524394590235,
"grad_norm": 28.727855682373047,
"learning_rate": 1.1020177413231334e-06,
"loss": 38.9866,
"step": 72
},
{
"epoch": 0.010954587233403987,
"grad_norm": 31.710817337036133,
"learning_rate": 1.0305368692688175e-06,
"loss": 43.0757,
"step": 73
},
{
"epoch": 0.011104650072217741,
"grad_norm": 29.618091583251953,
"learning_rate": 9.608463116858544e-07,
"loss": 40.1635,
"step": 74
},
{
"epoch": 0.011254712911031495,
"grad_norm": 15.594468116760254,
"learning_rate": 8.930309757836517e-07,
"loss": 31.7493,
"step": 75
},
{
"epoch": 0.011404775749845247,
"grad_norm": 16.501638412475586,
"learning_rate": 8.271734841028553e-07,
"loss": 30.6078,
"step": 76
},
{
"epoch": 0.011554838588659001,
"grad_norm": 16.97194480895996,
"learning_rate": 7.633540738525066e-07,
"loss": 30.2159,
"step": 77
},
{
"epoch": 0.011704901427472754,
"grad_norm": 17.44843864440918,
"learning_rate": 7.016504991533727e-07,
"loss": 29.8036,
"step": 78
},
{
"epoch": 0.011854964266286508,
"grad_norm": 15.254544258117676,
"learning_rate": 6.421379363065142e-07,
"loss": 28.1706,
"step": 79
},
{
"epoch": 0.012005027105100262,
"grad_norm": 18.066022872924805,
"learning_rate": 5.848888922025553e-07,
"loss": 29.3522,
"step": 80
},
{
"epoch": 0.012155089943914014,
"grad_norm": 17.23478126525879,
"learning_rate": 5.299731159831953e-07,
"loss": 30.1829,
"step": 81
},
{
"epoch": 0.012305152782727768,
"grad_norm": 16.398849487304688,
"learning_rate": 4.774575140626317e-07,
"loss": 28.8294,
"step": 82
},
{
"epoch": 0.01245521562154152,
"grad_norm": 16.836814880371094,
"learning_rate": 4.27406068612396e-07,
"loss": 29.5157,
"step": 83
},
{
"epoch": 0.012605278460355274,
"grad_norm": 14.805627822875977,
"learning_rate": 3.798797596089351e-07,
"loss": 30.2987,
"step": 84
},
{
"epoch": 0.012755341299169026,
"grad_norm": 16.60382080078125,
"learning_rate": 3.3493649053890325e-07,
"loss": 30.1055,
"step": 85
},
{
"epoch": 0.01290540413798278,
"grad_norm": 14.74989128112793,
"learning_rate": 2.9263101785268253e-07,
"loss": 28.499,
"step": 86
},
{
"epoch": 0.013055466976796534,
"grad_norm": 18.09991455078125,
"learning_rate": 2.53014884252083e-07,
"loss": 31.4409,
"step": 87
},
{
"epoch": 0.013205529815610286,
"grad_norm": 15.617703437805176,
"learning_rate": 2.1613635589349756e-07,
"loss": 29.3455,
"step": 88
},
{
"epoch": 0.01335559265442404,
"grad_norm": 17.055313110351562,
"learning_rate": 1.8204036358303173e-07,
"loss": 26.5924,
"step": 89
},
{
"epoch": 0.013505655493237793,
"grad_norm": 15.88111686706543,
"learning_rate": 1.507684480352292e-07,
"loss": 26.878,
"step": 90
},
{
"epoch": 0.013655718332051547,
"grad_norm": 16.348384857177734,
"learning_rate": 1.223587092621162e-07,
"loss": 28.8989,
"step": 91
},
{
"epoch": 0.0138057811708653,
"grad_norm": 15.886968612670898,
"learning_rate": 9.684576015420277e-08,
"loss": 26.7125,
"step": 92
},
{
"epoch": 0.013955844009679053,
"grad_norm": 16.663654327392578,
"learning_rate": 7.426068431000883e-08,
"loss": 27.2911,
"step": 93
},
{
"epoch": 0.014105906848492807,
"grad_norm": 17.79175567626953,
"learning_rate": 5.463099816548578e-08,
"loss": 27.798,
"step": 94
},
{
"epoch": 0.01425596968730656,
"grad_norm": 15.905275344848633,
"learning_rate": 3.798061746947995e-08,
"loss": 26.0851,
"step": 95
},
{
"epoch": 0.014406032526120313,
"grad_norm": 16.322898864746094,
"learning_rate": 2.4329828146074096e-08,
"loss": 27.9597,
"step": 96
},
{
"epoch": 0.014556095364934065,
"grad_norm": 16.844186782836914,
"learning_rate": 1.3695261579316776e-08,
"loss": 25.2095,
"step": 97
},
{
"epoch": 0.01470615820374782,
"grad_norm": 16.607568740844727,
"learning_rate": 6.089874350439507e-09,
"loss": 24.5913,
"step": 98
},
{
"epoch": 0.014856221042561573,
"grad_norm": 15.835559844970703,
"learning_rate": 1.5229324522605949e-09,
"loss": 24.0955,
"step": 99
},
{
"epoch": 0.015006283881375326,
"grad_norm": 18.256946563720703,
"learning_rate": 0.0,
"loss": 25.9992,
"step": 100
},
{
"epoch": 0.015006283881375326,
"eval_loss": 3.9525041580200195,
"eval_runtime": 1173.1028,
"eval_samples_per_second": 9.568,
"eval_steps_per_second": 2.392,
"step": 100
}
],
"logging_steps": 1,
"max_steps": 100,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 50,
"stateful_callbacks": {
"EarlyStoppingCallback": {
"args": {
"early_stopping_patience": 5,
"early_stopping_threshold": 0.0
},
"attributes": {
"early_stopping_patience_counter": 0
}
},
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 1.9392388208787456e+17,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}