farmery's picture
Upload folder using huggingface_hub
2ab7939 verified
{
"best_metric": 5.363029956817627,
"best_model_checkpoint": "miner_id_24/checkpoint-100",
"epoch": 0.4592422502870264,
"eval_steps": 50,
"global_step": 100,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.004592422502870264,
"grad_norm": 17.422351837158203,
"learning_rate": 5.000000000000001e-07,
"loss": 49.8036,
"step": 1
},
{
"epoch": 0.004592422502870264,
"eval_loss": 6.581690788269043,
"eval_runtime": 41.1686,
"eval_samples_per_second": 8.915,
"eval_steps_per_second": 2.235,
"step": 1
},
{
"epoch": 0.009184845005740528,
"grad_norm": 15.727997779846191,
"learning_rate": 1.0000000000000002e-06,
"loss": 50.5852,
"step": 2
},
{
"epoch": 0.013777267508610792,
"grad_norm": 15.347269058227539,
"learning_rate": 1.5e-06,
"loss": 51.7824,
"step": 3
},
{
"epoch": 0.018369690011481057,
"grad_norm": 16.722976684570312,
"learning_rate": 2.0000000000000003e-06,
"loss": 51.7411,
"step": 4
},
{
"epoch": 0.022962112514351322,
"grad_norm": 15.326921463012695,
"learning_rate": 2.5e-06,
"loss": 50.5851,
"step": 5
},
{
"epoch": 0.027554535017221583,
"grad_norm": 17.22072410583496,
"learning_rate": 3e-06,
"loss": 53.0931,
"step": 6
},
{
"epoch": 0.03214695752009185,
"grad_norm": 17.842632293701172,
"learning_rate": 3.5e-06,
"loss": 52.5499,
"step": 7
},
{
"epoch": 0.03673938002296211,
"grad_norm": 17.188825607299805,
"learning_rate": 4.000000000000001e-06,
"loss": 52.0334,
"step": 8
},
{
"epoch": 0.04133180252583238,
"grad_norm": 15.418607711791992,
"learning_rate": 4.5e-06,
"loss": 49.4726,
"step": 9
},
{
"epoch": 0.045924225028702644,
"grad_norm": 17.196287155151367,
"learning_rate": 5e-06,
"loss": 51.543,
"step": 10
},
{
"epoch": 0.0505166475315729,
"grad_norm": 16.128028869628906,
"learning_rate": 4.99847706754774e-06,
"loss": 50.8256,
"step": 11
},
{
"epoch": 0.05510907003444317,
"grad_norm": 17.322240829467773,
"learning_rate": 4.993910125649561e-06,
"loss": 52.4383,
"step": 12
},
{
"epoch": 0.05970149253731343,
"grad_norm": 17.042463302612305,
"learning_rate": 4.986304738420684e-06,
"loss": 50.8534,
"step": 13
},
{
"epoch": 0.0642939150401837,
"grad_norm": 18.691532135009766,
"learning_rate": 4.975670171853926e-06,
"loss": 53.126,
"step": 14
},
{
"epoch": 0.06888633754305395,
"grad_norm": 18.797557830810547,
"learning_rate": 4.962019382530521e-06,
"loss": 52.3491,
"step": 15
},
{
"epoch": 0.07347876004592423,
"grad_norm": 19.990497589111328,
"learning_rate": 4.9453690018345144e-06,
"loss": 55.9718,
"step": 16
},
{
"epoch": 0.07807118254879448,
"grad_norm": 18.329801559448242,
"learning_rate": 4.925739315689991e-06,
"loss": 51.4399,
"step": 17
},
{
"epoch": 0.08266360505166476,
"grad_norm": 19.932241439819336,
"learning_rate": 4.903154239845798e-06,
"loss": 51.7598,
"step": 18
},
{
"epoch": 0.08725602755453502,
"grad_norm": 19.305652618408203,
"learning_rate": 4.8776412907378845e-06,
"loss": 51.3118,
"step": 19
},
{
"epoch": 0.09184845005740529,
"grad_norm": 20.77489471435547,
"learning_rate": 4.849231551964771e-06,
"loss": 52.1306,
"step": 20
},
{
"epoch": 0.09644087256027555,
"grad_norm": 19.153535842895508,
"learning_rate": 4.817959636416969e-06,
"loss": 51.4403,
"step": 21
},
{
"epoch": 0.1010332950631458,
"grad_norm": 19.786102294921875,
"learning_rate": 4.783863644106502e-06,
"loss": 51.161,
"step": 22
},
{
"epoch": 0.10562571756601608,
"grad_norm": 18.834474563598633,
"learning_rate": 4.746985115747918e-06,
"loss": 49.2061,
"step": 23
},
{
"epoch": 0.11021814006888633,
"grad_norm": 20.738544464111328,
"learning_rate": 4.707368982147318e-06,
"loss": 51.229,
"step": 24
},
{
"epoch": 0.1148105625717566,
"grad_norm": 20.025314331054688,
"learning_rate": 4.665063509461098e-06,
"loss": 51.0834,
"step": 25
},
{
"epoch": 0.11940298507462686,
"grad_norm": 22.799274444580078,
"learning_rate": 4.620120240391065e-06,
"loss": 51.7177,
"step": 26
},
{
"epoch": 0.12399540757749714,
"grad_norm": 21.667531967163086,
"learning_rate": 4.572593931387604e-06,
"loss": 52.6204,
"step": 27
},
{
"epoch": 0.1285878300803674,
"grad_norm": 22.614103317260742,
"learning_rate": 4.522542485937369e-06,
"loss": 50.8502,
"step": 28
},
{
"epoch": 0.13318025258323765,
"grad_norm": 19.7918758392334,
"learning_rate": 4.470026884016805e-06,
"loss": 49.1687,
"step": 29
},
{
"epoch": 0.1377726750861079,
"grad_norm": 23.40234375,
"learning_rate": 4.415111107797445e-06,
"loss": 52.8214,
"step": 30
},
{
"epoch": 0.1423650975889782,
"grad_norm": 24.31424903869629,
"learning_rate": 4.357862063693486e-06,
"loss": 50.4354,
"step": 31
},
{
"epoch": 0.14695752009184845,
"grad_norm": 23.1087646484375,
"learning_rate": 4.2983495008466285e-06,
"loss": 50.5401,
"step": 32
},
{
"epoch": 0.1515499425947187,
"grad_norm": 24.652694702148438,
"learning_rate": 4.236645926147493e-06,
"loss": 51.1058,
"step": 33
},
{
"epoch": 0.15614236509758897,
"grad_norm": 24.83074951171875,
"learning_rate": 4.172826515897146e-06,
"loss": 52.2553,
"step": 34
},
{
"epoch": 0.16073478760045926,
"grad_norm": 24.135053634643555,
"learning_rate": 4.106969024216348e-06,
"loss": 50.662,
"step": 35
},
{
"epoch": 0.1653272101033295,
"grad_norm": 24.16924476623535,
"learning_rate": 4.039153688314146e-06,
"loss": 48.2732,
"step": 36
},
{
"epoch": 0.16991963260619977,
"grad_norm": 26.378135681152344,
"learning_rate": 3.969463130731183e-06,
"loss": 50.8932,
"step": 37
},
{
"epoch": 0.17451205510907003,
"grad_norm": 25.19991111755371,
"learning_rate": 3.897982258676867e-06,
"loss": 49.9703,
"step": 38
},
{
"epoch": 0.1791044776119403,
"grad_norm": 28.445180892944336,
"learning_rate": 3.824798160583012e-06,
"loss": 51.1727,
"step": 39
},
{
"epoch": 0.18369690011481057,
"grad_norm": 24.99131965637207,
"learning_rate": 3.7500000000000005e-06,
"loss": 48.2178,
"step": 40
},
{
"epoch": 0.18828932261768083,
"grad_norm": 26.75794219970703,
"learning_rate": 3.6736789069647273e-06,
"loss": 48.9569,
"step": 41
},
{
"epoch": 0.1928817451205511,
"grad_norm": 28.006494522094727,
"learning_rate": 3.595927866972694e-06,
"loss": 48.6871,
"step": 42
},
{
"epoch": 0.19747416762342135,
"grad_norm": 28.05718994140625,
"learning_rate": 3.516841607689501e-06,
"loss": 51.0425,
"step": 43
},
{
"epoch": 0.2020665901262916,
"grad_norm": 28.426515579223633,
"learning_rate": 3.436516483539781e-06,
"loss": 49.6784,
"step": 44
},
{
"epoch": 0.2066590126291619,
"grad_norm": 29.402090072631836,
"learning_rate": 3.3550503583141726e-06,
"loss": 50.3752,
"step": 45
},
{
"epoch": 0.21125143513203215,
"grad_norm": 28.24565887451172,
"learning_rate": 3.272542485937369e-06,
"loss": 48.4813,
"step": 46
},
{
"epoch": 0.2158438576349024,
"grad_norm": 27.259733200073242,
"learning_rate": 3.189093389542498e-06,
"loss": 47.8943,
"step": 47
},
{
"epoch": 0.22043628013777267,
"grad_norm": 30.925739288330078,
"learning_rate": 3.1048047389991693e-06,
"loss": 51.9337,
"step": 48
},
{
"epoch": 0.22502870264064295,
"grad_norm": 29.552427291870117,
"learning_rate": 3.019779227044398e-06,
"loss": 51.5688,
"step": 49
},
{
"epoch": 0.2296211251435132,
"grad_norm": 28.672847747802734,
"learning_rate": 2.9341204441673267e-06,
"loss": 51.1267,
"step": 50
},
{
"epoch": 0.2296211251435132,
"eval_loss": 5.869631767272949,
"eval_runtime": 41.6165,
"eval_samples_per_second": 8.819,
"eval_steps_per_second": 2.211,
"step": 50
},
{
"epoch": 0.23421354764638347,
"grad_norm": 26.808902740478516,
"learning_rate": 2.847932752400164e-06,
"loss": 47.6216,
"step": 51
},
{
"epoch": 0.23880597014925373,
"grad_norm": 26.181222915649414,
"learning_rate": 2.761321158169134e-06,
"loss": 45.5904,
"step": 52
},
{
"epoch": 0.24339839265212398,
"grad_norm": 24.47733497619629,
"learning_rate": 2.6743911843603134e-06,
"loss": 44.2045,
"step": 53
},
{
"epoch": 0.24799081515499427,
"grad_norm": 27.00351905822754,
"learning_rate": 2.587248741756253e-06,
"loss": 46.1095,
"step": 54
},
{
"epoch": 0.2525832376578645,
"grad_norm": 25.429462432861328,
"learning_rate": 2.5e-06,
"loss": 45.1595,
"step": 55
},
{
"epoch": 0.2571756601607348,
"grad_norm": 27.074621200561523,
"learning_rate": 2.4127512582437486e-06,
"loss": 46.2527,
"step": 56
},
{
"epoch": 0.2617680826636051,
"grad_norm": 28.328506469726562,
"learning_rate": 2.325608815639687e-06,
"loss": 44.0381,
"step": 57
},
{
"epoch": 0.2663605051664753,
"grad_norm": 27.414587020874023,
"learning_rate": 2.238678841830867e-06,
"loss": 44.427,
"step": 58
},
{
"epoch": 0.2709529276693456,
"grad_norm": 27.592138290405273,
"learning_rate": 2.1520672475998374e-06,
"loss": 45.2812,
"step": 59
},
{
"epoch": 0.2755453501722158,
"grad_norm": 26.86080551147461,
"learning_rate": 2.0658795558326745e-06,
"loss": 44.7676,
"step": 60
},
{
"epoch": 0.2801377726750861,
"grad_norm": 27.480749130249023,
"learning_rate": 1.9802207729556023e-06,
"loss": 44.6694,
"step": 61
},
{
"epoch": 0.2847301951779564,
"grad_norm": 27.362363815307617,
"learning_rate": 1.895195261000831e-06,
"loss": 44.9002,
"step": 62
},
{
"epoch": 0.2893226176808266,
"grad_norm": 28.51040267944336,
"learning_rate": 1.8109066104575023e-06,
"loss": 45.6995,
"step": 63
},
{
"epoch": 0.2939150401836969,
"grad_norm": 29.854806900024414,
"learning_rate": 1.7274575140626318e-06,
"loss": 46.2855,
"step": 64
},
{
"epoch": 0.29850746268656714,
"grad_norm": 26.63895606994629,
"learning_rate": 1.6449496416858285e-06,
"loss": 42.679,
"step": 65
},
{
"epoch": 0.3030998851894374,
"grad_norm": 26.914358139038086,
"learning_rate": 1.56348351646022e-06,
"loss": 43.8516,
"step": 66
},
{
"epoch": 0.3076923076923077,
"grad_norm": 25.817581176757812,
"learning_rate": 1.4831583923105e-06,
"loss": 43.8709,
"step": 67
},
{
"epoch": 0.31228473019517794,
"grad_norm": 28.417312622070312,
"learning_rate": 1.4040721330273063e-06,
"loss": 44.2127,
"step": 68
},
{
"epoch": 0.3168771526980482,
"grad_norm": 27.355661392211914,
"learning_rate": 1.3263210930352737e-06,
"loss": 44.3729,
"step": 69
},
{
"epoch": 0.3214695752009185,
"grad_norm": 27.43345832824707,
"learning_rate": 1.2500000000000007e-06,
"loss": 43.7944,
"step": 70
},
{
"epoch": 0.32606199770378874,
"grad_norm": 29.279691696166992,
"learning_rate": 1.1752018394169882e-06,
"loss": 44.0171,
"step": 71
},
{
"epoch": 0.330654420206659,
"grad_norm": 27.410545349121094,
"learning_rate": 1.1020177413231334e-06,
"loss": 43.095,
"step": 72
},
{
"epoch": 0.33524684270952926,
"grad_norm": 29.67399024963379,
"learning_rate": 1.0305368692688175e-06,
"loss": 45.0487,
"step": 73
},
{
"epoch": 0.33983926521239954,
"grad_norm": 30.19101333618164,
"learning_rate": 9.608463116858544e-07,
"loss": 44.676,
"step": 74
},
{
"epoch": 0.34443168771526983,
"grad_norm": 27.907899856567383,
"learning_rate": 8.930309757836517e-07,
"loss": 43.2354,
"step": 75
},
{
"epoch": 0.34902411021814006,
"grad_norm": 28.882566452026367,
"learning_rate": 8.271734841028553e-07,
"loss": 43.4213,
"step": 76
},
{
"epoch": 0.35361653272101035,
"grad_norm": 30.828548431396484,
"learning_rate": 7.633540738525066e-07,
"loss": 45.3045,
"step": 77
},
{
"epoch": 0.3582089552238806,
"grad_norm": 29.114967346191406,
"learning_rate": 7.016504991533727e-07,
"loss": 43.4449,
"step": 78
},
{
"epoch": 0.36280137772675086,
"grad_norm": 29.279699325561523,
"learning_rate": 6.421379363065142e-07,
"loss": 42.7139,
"step": 79
},
{
"epoch": 0.36739380022962115,
"grad_norm": 29.65679931640625,
"learning_rate": 5.848888922025553e-07,
"loss": 43.0745,
"step": 80
},
{
"epoch": 0.3719862227324914,
"grad_norm": 29.90504264831543,
"learning_rate": 5.299731159831953e-07,
"loss": 44.1824,
"step": 81
},
{
"epoch": 0.37657864523536166,
"grad_norm": 30.5111083984375,
"learning_rate": 4.774575140626317e-07,
"loss": 44.0602,
"step": 82
},
{
"epoch": 0.3811710677382319,
"grad_norm": 28.713394165039062,
"learning_rate": 4.27406068612396e-07,
"loss": 43.8557,
"step": 83
},
{
"epoch": 0.3857634902411022,
"grad_norm": 28.297386169433594,
"learning_rate": 3.798797596089351e-07,
"loss": 42.6137,
"step": 84
},
{
"epoch": 0.39035591274397247,
"grad_norm": 28.568580627441406,
"learning_rate": 3.3493649053890325e-07,
"loss": 43.4909,
"step": 85
},
{
"epoch": 0.3949483352468427,
"grad_norm": 29.288326263427734,
"learning_rate": 2.9263101785268253e-07,
"loss": 42.8888,
"step": 86
},
{
"epoch": 0.399540757749713,
"grad_norm": 28.4726619720459,
"learning_rate": 2.53014884252083e-07,
"loss": 43.0369,
"step": 87
},
{
"epoch": 0.4041331802525832,
"grad_norm": 29.91521644592285,
"learning_rate": 2.1613635589349756e-07,
"loss": 41.9991,
"step": 88
},
{
"epoch": 0.4087256027554535,
"grad_norm": 30.32415008544922,
"learning_rate": 1.8204036358303173e-07,
"loss": 42.7265,
"step": 89
},
{
"epoch": 0.4133180252583238,
"grad_norm": 30.52402114868164,
"learning_rate": 1.507684480352292e-07,
"loss": 43.7341,
"step": 90
},
{
"epoch": 0.417910447761194,
"grad_norm": 29.194290161132812,
"learning_rate": 1.223587092621162e-07,
"loss": 44.0457,
"step": 91
},
{
"epoch": 0.4225028702640643,
"grad_norm": 30.200559616088867,
"learning_rate": 9.684576015420277e-08,
"loss": 44.1988,
"step": 92
},
{
"epoch": 0.42709529276693453,
"grad_norm": 30.448226928710938,
"learning_rate": 7.426068431000883e-08,
"loss": 43.5972,
"step": 93
},
{
"epoch": 0.4316877152698048,
"grad_norm": 31.17372703552246,
"learning_rate": 5.463099816548578e-08,
"loss": 45.4866,
"step": 94
},
{
"epoch": 0.4362801377726751,
"grad_norm": 30.126811981201172,
"learning_rate": 3.798061746947995e-08,
"loss": 43.0588,
"step": 95
},
{
"epoch": 0.44087256027554533,
"grad_norm": 31.021615982055664,
"learning_rate": 2.4329828146074096e-08,
"loss": 43.662,
"step": 96
},
{
"epoch": 0.4454649827784156,
"grad_norm": 31.53817367553711,
"learning_rate": 1.3695261579316776e-08,
"loss": 45.2449,
"step": 97
},
{
"epoch": 0.4500574052812859,
"grad_norm": 33.527503967285156,
"learning_rate": 6.089874350439507e-09,
"loss": 45.0926,
"step": 98
},
{
"epoch": 0.45464982778415614,
"grad_norm": 30.129289627075195,
"learning_rate": 1.5229324522605949e-09,
"loss": 44.7906,
"step": 99
},
{
"epoch": 0.4592422502870264,
"grad_norm": 31.717391967773438,
"learning_rate": 0.0,
"loss": 46.6076,
"step": 100
},
{
"epoch": 0.4592422502870264,
"eval_loss": 5.363029956817627,
"eval_runtime": 41.6293,
"eval_samples_per_second": 8.816,
"eval_steps_per_second": 2.21,
"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": 2.53913198493696e+17,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}