bbytxt's picture
Training in progress, step 100, checkpoint
63e7582 verified
{
"best_metric": 2.4464058876037598,
"best_model_checkpoint": "miner_id_24/checkpoint-100",
"epoch": 0.0541895278737384,
"eval_steps": 50,
"global_step": 100,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.000541895278737384,
"grad_norm": 1.312487244606018,
"learning_rate": 5.000000000000001e-07,
"loss": 12.0843,
"step": 1
},
{
"epoch": 0.000541895278737384,
"eval_loss": 2.568927049636841,
"eval_runtime": 356.6215,
"eval_samples_per_second": 8.715,
"eval_steps_per_second": 2.179,
"step": 1
},
{
"epoch": 0.001083790557474768,
"grad_norm": 2.0385873317718506,
"learning_rate": 1.0000000000000002e-06,
"loss": 13.4083,
"step": 2
},
{
"epoch": 0.001625685836212152,
"grad_norm": 1.9277825355529785,
"learning_rate": 1.5e-06,
"loss": 13.6711,
"step": 3
},
{
"epoch": 0.002167581114949536,
"grad_norm": 2.5886740684509277,
"learning_rate": 2.0000000000000003e-06,
"loss": 14.1684,
"step": 4
},
{
"epoch": 0.00270947639368692,
"grad_norm": 2.3235366344451904,
"learning_rate": 2.5e-06,
"loss": 15.3074,
"step": 5
},
{
"epoch": 0.003251371672424304,
"grad_norm": 2.580097198486328,
"learning_rate": 3e-06,
"loss": 15.5703,
"step": 6
},
{
"epoch": 0.003793266951161688,
"grad_norm": 2.3437869548797607,
"learning_rate": 3.5e-06,
"loss": 15.6797,
"step": 7
},
{
"epoch": 0.004335162229899072,
"grad_norm": 2.1751561164855957,
"learning_rate": 4.000000000000001e-06,
"loss": 15.6452,
"step": 8
},
{
"epoch": 0.004877057508636456,
"grad_norm": 2.4562244415283203,
"learning_rate": 4.5e-06,
"loss": 16.0855,
"step": 9
},
{
"epoch": 0.00541895278737384,
"grad_norm": 2.959887981414795,
"learning_rate": 5e-06,
"loss": 16.5416,
"step": 10
},
{
"epoch": 0.005960848066111224,
"grad_norm": 2.9056694507598877,
"learning_rate": 4.99847706754774e-06,
"loss": 15.9268,
"step": 11
},
{
"epoch": 0.006502743344848608,
"grad_norm": 2.3838143348693848,
"learning_rate": 4.993910125649561e-06,
"loss": 17.0944,
"step": 12
},
{
"epoch": 0.007044638623585992,
"grad_norm": 3.266652822494507,
"learning_rate": 4.986304738420684e-06,
"loss": 17.1496,
"step": 13
},
{
"epoch": 0.007586533902323376,
"grad_norm": 3.1640474796295166,
"learning_rate": 4.975670171853926e-06,
"loss": 17.4364,
"step": 14
},
{
"epoch": 0.00812842918106076,
"grad_norm": 3.757476329803467,
"learning_rate": 4.962019382530521e-06,
"loss": 17.5002,
"step": 15
},
{
"epoch": 0.008670324459798144,
"grad_norm": 3.355529546737671,
"learning_rate": 4.9453690018345144e-06,
"loss": 16.9041,
"step": 16
},
{
"epoch": 0.009212219738535529,
"grad_norm": 3.3027448654174805,
"learning_rate": 4.925739315689991e-06,
"loss": 18.0518,
"step": 17
},
{
"epoch": 0.009754115017272911,
"grad_norm": 3.941869020462036,
"learning_rate": 4.903154239845798e-06,
"loss": 17.2925,
"step": 18
},
{
"epoch": 0.010296010296010296,
"grad_norm": 3.906616687774658,
"learning_rate": 4.8776412907378845e-06,
"loss": 18.5134,
"step": 19
},
{
"epoch": 0.01083790557474768,
"grad_norm": 4.283662796020508,
"learning_rate": 4.849231551964771e-06,
"loss": 17.6599,
"step": 20
},
{
"epoch": 0.011379800853485065,
"grad_norm": 3.5966744422912598,
"learning_rate": 4.817959636416969e-06,
"loss": 17.765,
"step": 21
},
{
"epoch": 0.011921696132222447,
"grad_norm": 3.567039966583252,
"learning_rate": 4.783863644106502e-06,
"loss": 20.5735,
"step": 22
},
{
"epoch": 0.012463591410959832,
"grad_norm": 4.263599395751953,
"learning_rate": 4.746985115747918e-06,
"loss": 18.9028,
"step": 23
},
{
"epoch": 0.013005486689697216,
"grad_norm": 3.6329641342163086,
"learning_rate": 4.707368982147318e-06,
"loss": 18.6384,
"step": 24
},
{
"epoch": 0.0135473819684346,
"grad_norm": 5.154904365539551,
"learning_rate": 4.665063509461098e-06,
"loss": 19.6976,
"step": 25
},
{
"epoch": 0.014089277247171983,
"grad_norm": 4.175611972808838,
"learning_rate": 4.620120240391065e-06,
"loss": 18.8855,
"step": 26
},
{
"epoch": 0.014631172525909368,
"grad_norm": 5.684014797210693,
"learning_rate": 4.572593931387604e-06,
"loss": 17.9151,
"step": 27
},
{
"epoch": 0.015173067804646752,
"grad_norm": 3.9782209396362305,
"learning_rate": 4.522542485937369e-06,
"loss": 18.1362,
"step": 28
},
{
"epoch": 0.015714963083384135,
"grad_norm": 5.732182025909424,
"learning_rate": 4.470026884016805e-06,
"loss": 20.7214,
"step": 29
},
{
"epoch": 0.01625685836212152,
"grad_norm": 5.507081031799316,
"learning_rate": 4.415111107797445e-06,
"loss": 19.7423,
"step": 30
},
{
"epoch": 0.016798753640858904,
"grad_norm": 5.731754779815674,
"learning_rate": 4.357862063693486e-06,
"loss": 22.4296,
"step": 31
},
{
"epoch": 0.017340648919596288,
"grad_norm": 4.9393463134765625,
"learning_rate": 4.2983495008466285e-06,
"loss": 19.3488,
"step": 32
},
{
"epoch": 0.017882544198333673,
"grad_norm": 4.795718669891357,
"learning_rate": 4.236645926147493e-06,
"loss": 19.5817,
"step": 33
},
{
"epoch": 0.018424439477071057,
"grad_norm": 5.4530463218688965,
"learning_rate": 4.172826515897146e-06,
"loss": 20.7245,
"step": 34
},
{
"epoch": 0.01896633475580844,
"grad_norm": 5.843173980712891,
"learning_rate": 4.106969024216348e-06,
"loss": 22.3009,
"step": 35
},
{
"epoch": 0.019508230034545822,
"grad_norm": 6.191988945007324,
"learning_rate": 4.039153688314146e-06,
"loss": 19.8796,
"step": 36
},
{
"epoch": 0.020050125313283207,
"grad_norm": 6.448052883148193,
"learning_rate": 3.969463130731183e-06,
"loss": 21.6479,
"step": 37
},
{
"epoch": 0.02059202059202059,
"grad_norm": 11.463981628417969,
"learning_rate": 3.897982258676867e-06,
"loss": 21.8738,
"step": 38
},
{
"epoch": 0.021133915870757976,
"grad_norm": 6.69301700592041,
"learning_rate": 3.824798160583012e-06,
"loss": 21.8778,
"step": 39
},
{
"epoch": 0.02167581114949536,
"grad_norm": 6.770164489746094,
"learning_rate": 3.7500000000000005e-06,
"loss": 22.1602,
"step": 40
},
{
"epoch": 0.022217706428232745,
"grad_norm": 7.03548002243042,
"learning_rate": 3.6736789069647273e-06,
"loss": 22.7901,
"step": 41
},
{
"epoch": 0.02275960170697013,
"grad_norm": 9.729033470153809,
"learning_rate": 3.595927866972694e-06,
"loss": 24.2832,
"step": 42
},
{
"epoch": 0.023301496985707514,
"grad_norm": 7.9464335441589355,
"learning_rate": 3.516841607689501e-06,
"loss": 25.8137,
"step": 43
},
{
"epoch": 0.023843392264444895,
"grad_norm": 8.11252212524414,
"learning_rate": 3.436516483539781e-06,
"loss": 28.7299,
"step": 44
},
{
"epoch": 0.02438528754318228,
"grad_norm": 9.726422309875488,
"learning_rate": 3.3550503583141726e-06,
"loss": 26.6308,
"step": 45
},
{
"epoch": 0.024927182821919663,
"grad_norm": 11.935210227966309,
"learning_rate": 3.272542485937369e-06,
"loss": 30.5609,
"step": 46
},
{
"epoch": 0.025469078100657048,
"grad_norm": 10.29076099395752,
"learning_rate": 3.189093389542498e-06,
"loss": 28.0565,
"step": 47
},
{
"epoch": 0.026010973379394432,
"grad_norm": 13.732169151306152,
"learning_rate": 3.1048047389991693e-06,
"loss": 33.951,
"step": 48
},
{
"epoch": 0.026552868658131817,
"grad_norm": 12.743755340576172,
"learning_rate": 3.019779227044398e-06,
"loss": 35.0371,
"step": 49
},
{
"epoch": 0.0270947639368692,
"grad_norm": 19.506738662719727,
"learning_rate": 2.9341204441673267e-06,
"loss": 42.8953,
"step": 50
},
{
"epoch": 0.0270947639368692,
"eval_loss": 2.4954833984375,
"eval_runtime": 358.0494,
"eval_samples_per_second": 8.68,
"eval_steps_per_second": 2.17,
"step": 50
},
{
"epoch": 0.027636659215606586,
"grad_norm": 1.6957308053970337,
"learning_rate": 2.847932752400164e-06,
"loss": 12.6216,
"step": 51
},
{
"epoch": 0.028178554494343967,
"grad_norm": 2.395599842071533,
"learning_rate": 2.761321158169134e-06,
"loss": 13.6985,
"step": 52
},
{
"epoch": 0.02872044977308135,
"grad_norm": 2.4453835487365723,
"learning_rate": 2.6743911843603134e-06,
"loss": 13.4491,
"step": 53
},
{
"epoch": 0.029262345051818735,
"grad_norm": 4.068036079406738,
"learning_rate": 2.587248741756253e-06,
"loss": 13.1798,
"step": 54
},
{
"epoch": 0.02980424033055612,
"grad_norm": 3.4825592041015625,
"learning_rate": 2.5e-06,
"loss": 14.8378,
"step": 55
},
{
"epoch": 0.030346135609293504,
"grad_norm": 3.283317804336548,
"learning_rate": 2.4127512582437486e-06,
"loss": 14.6238,
"step": 56
},
{
"epoch": 0.03088803088803089,
"grad_norm": 2.9764211177825928,
"learning_rate": 2.325608815639687e-06,
"loss": 15.7249,
"step": 57
},
{
"epoch": 0.03142992616676827,
"grad_norm": 2.89556622505188,
"learning_rate": 2.238678841830867e-06,
"loss": 14.5268,
"step": 58
},
{
"epoch": 0.03197182144550566,
"grad_norm": 4.53331995010376,
"learning_rate": 2.1520672475998374e-06,
"loss": 15.1174,
"step": 59
},
{
"epoch": 0.03251371672424304,
"grad_norm": 3.2078773975372314,
"learning_rate": 2.0658795558326745e-06,
"loss": 15.0038,
"step": 60
},
{
"epoch": 0.033055612002980427,
"grad_norm": 3.0406272411346436,
"learning_rate": 1.9802207729556023e-06,
"loss": 15.8146,
"step": 61
},
{
"epoch": 0.03359750728171781,
"grad_norm": 3.8402979373931885,
"learning_rate": 1.895195261000831e-06,
"loss": 16.1639,
"step": 62
},
{
"epoch": 0.034139402560455195,
"grad_norm": 3.454057455062866,
"learning_rate": 1.8109066104575023e-06,
"loss": 15.6871,
"step": 63
},
{
"epoch": 0.034681297839192576,
"grad_norm": 3.8209731578826904,
"learning_rate": 1.7274575140626318e-06,
"loss": 17.064,
"step": 64
},
{
"epoch": 0.03522319311792996,
"grad_norm": 3.635895252227783,
"learning_rate": 1.6449496416858285e-06,
"loss": 15.6606,
"step": 65
},
{
"epoch": 0.035765088396667345,
"grad_norm": 4.060421466827393,
"learning_rate": 1.56348351646022e-06,
"loss": 17.5466,
"step": 66
},
{
"epoch": 0.036306983675404726,
"grad_norm": 4.730147361755371,
"learning_rate": 1.4831583923105e-06,
"loss": 17.1693,
"step": 67
},
{
"epoch": 0.036848878954142114,
"grad_norm": 9.351218223571777,
"learning_rate": 1.4040721330273063e-06,
"loss": 15.6337,
"step": 68
},
{
"epoch": 0.037390774232879495,
"grad_norm": 4.0762128829956055,
"learning_rate": 1.3263210930352737e-06,
"loss": 15.6759,
"step": 69
},
{
"epoch": 0.03793266951161688,
"grad_norm": 4.4134907722473145,
"learning_rate": 1.2500000000000007e-06,
"loss": 16.9798,
"step": 70
},
{
"epoch": 0.038474564790354264,
"grad_norm": 4.037068843841553,
"learning_rate": 1.1752018394169882e-06,
"loss": 18.4723,
"step": 71
},
{
"epoch": 0.039016460069091645,
"grad_norm": 4.869369983673096,
"learning_rate": 1.1020177413231334e-06,
"loss": 16.1792,
"step": 72
},
{
"epoch": 0.03955835534782903,
"grad_norm": 4.059152126312256,
"learning_rate": 1.0305368692688175e-06,
"loss": 18.025,
"step": 73
},
{
"epoch": 0.040100250626566414,
"grad_norm": 6.198925971984863,
"learning_rate": 9.608463116858544e-07,
"loss": 17.3643,
"step": 74
},
{
"epoch": 0.0406421459053038,
"grad_norm": 4.602997303009033,
"learning_rate": 8.930309757836517e-07,
"loss": 18.4931,
"step": 75
},
{
"epoch": 0.04118404118404118,
"grad_norm": 5.112064838409424,
"learning_rate": 8.271734841028553e-07,
"loss": 18.2432,
"step": 76
},
{
"epoch": 0.04172593646277857,
"grad_norm": 5.037693977355957,
"learning_rate": 7.633540738525066e-07,
"loss": 19.7166,
"step": 77
},
{
"epoch": 0.04226783174151595,
"grad_norm": 6.0072550773620605,
"learning_rate": 7.016504991533727e-07,
"loss": 19.2431,
"step": 78
},
{
"epoch": 0.04280972702025334,
"grad_norm": 5.383151054382324,
"learning_rate": 6.421379363065142e-07,
"loss": 19.4844,
"step": 79
},
{
"epoch": 0.04335162229899072,
"grad_norm": 6.218992233276367,
"learning_rate": 5.848888922025553e-07,
"loss": 18.2424,
"step": 80
},
{
"epoch": 0.0438935175777281,
"grad_norm": 5.023440837860107,
"learning_rate": 5.299731159831953e-07,
"loss": 18.9336,
"step": 81
},
{
"epoch": 0.04443541285646549,
"grad_norm": 5.840432167053223,
"learning_rate": 4.774575140626317e-07,
"loss": 18.8547,
"step": 82
},
{
"epoch": 0.04497730813520287,
"grad_norm": 6.296828269958496,
"learning_rate": 4.27406068612396e-07,
"loss": 20.1747,
"step": 83
},
{
"epoch": 0.04551920341394026,
"grad_norm": 6.640228748321533,
"learning_rate": 3.798797596089351e-07,
"loss": 20.2483,
"step": 84
},
{
"epoch": 0.04606109869267764,
"grad_norm": 7.213305950164795,
"learning_rate": 3.3493649053890325e-07,
"loss": 21.2069,
"step": 85
},
{
"epoch": 0.04660299397141503,
"grad_norm": 6.3729567527771,
"learning_rate": 2.9263101785268253e-07,
"loss": 19.7627,
"step": 86
},
{
"epoch": 0.04714488925015241,
"grad_norm": 7.3160600662231445,
"learning_rate": 2.53014884252083e-07,
"loss": 20.9435,
"step": 87
},
{
"epoch": 0.04768678452888979,
"grad_norm": 7.332363605499268,
"learning_rate": 2.1613635589349756e-07,
"loss": 20.6377,
"step": 88
},
{
"epoch": 0.04822867980762718,
"grad_norm": 7.867956161499023,
"learning_rate": 1.8204036358303173e-07,
"loss": 20.0944,
"step": 89
},
{
"epoch": 0.04877057508636456,
"grad_norm": 7.888767242431641,
"learning_rate": 1.507684480352292e-07,
"loss": 22.6835,
"step": 90
},
{
"epoch": 0.049312470365101946,
"grad_norm": 9.607979774475098,
"learning_rate": 1.223587092621162e-07,
"loss": 22.9416,
"step": 91
},
{
"epoch": 0.04985436564383933,
"grad_norm": 8.894455909729004,
"learning_rate": 9.684576015420277e-08,
"loss": 24.3503,
"step": 92
},
{
"epoch": 0.050396260922576715,
"grad_norm": 8.218143463134766,
"learning_rate": 7.426068431000883e-08,
"loss": 23.8572,
"step": 93
},
{
"epoch": 0.050938156201314096,
"grad_norm": 9.763501167297363,
"learning_rate": 5.463099816548578e-08,
"loss": 25.768,
"step": 94
},
{
"epoch": 0.05148005148005148,
"grad_norm": 10.202559471130371,
"learning_rate": 3.798061746947995e-08,
"loss": 26.5671,
"step": 95
},
{
"epoch": 0.052021946758788865,
"grad_norm": 10.504480361938477,
"learning_rate": 2.4329828146074096e-08,
"loss": 25.8313,
"step": 96
},
{
"epoch": 0.052563842037526246,
"grad_norm": 11.200603485107422,
"learning_rate": 1.3695261579316776e-08,
"loss": 27.4676,
"step": 97
},
{
"epoch": 0.05310573731626363,
"grad_norm": 10.476430892944336,
"learning_rate": 6.089874350439507e-09,
"loss": 29.916,
"step": 98
},
{
"epoch": 0.053647632595001014,
"grad_norm": 13.919726371765137,
"learning_rate": 1.5229324522605949e-09,
"loss": 35.1479,
"step": 99
},
{
"epoch": 0.0541895278737384,
"grad_norm": 17.542753219604492,
"learning_rate": 0.0,
"loss": 38.8144,
"step": 100
},
{
"epoch": 0.0541895278737384,
"eval_loss": 2.4464058876037598,
"eval_runtime": 357.9028,
"eval_samples_per_second": 8.684,
"eval_steps_per_second": 2.171,
"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": 2.5486537298804736e+17,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}