bbytxt's picture
Training in progress, step 100, checkpoint
c0979bb verified
{
"best_metric": 4.300358295440674,
"best_model_checkpoint": "miner_id_24/checkpoint-100",
"epoch": 2.830985915492958,
"eval_steps": 50,
"global_step": 100,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.028169014084507043,
"grad_norm": 5.68193244934082,
"learning_rate": 5.000000000000001e-07,
"loss": 6.4785,
"step": 1
},
{
"epoch": 0.028169014084507043,
"eval_loss": 6.220841884613037,
"eval_runtime": 1.6163,
"eval_samples_per_second": 37.121,
"eval_steps_per_second": 4.949,
"step": 1
},
{
"epoch": 0.056338028169014086,
"grad_norm": 5.4344162940979,
"learning_rate": 1.0000000000000002e-06,
"loss": 6.4907,
"step": 2
},
{
"epoch": 0.08450704225352113,
"grad_norm": 5.336536407470703,
"learning_rate": 1.5e-06,
"loss": 6.6291,
"step": 3
},
{
"epoch": 0.11267605633802817,
"grad_norm": 5.674023628234863,
"learning_rate": 2.0000000000000003e-06,
"loss": 6.5261,
"step": 4
},
{
"epoch": 0.14084507042253522,
"grad_norm": 6.0419111251831055,
"learning_rate": 2.5e-06,
"loss": 6.4708,
"step": 5
},
{
"epoch": 0.16901408450704225,
"grad_norm": 5.955847263336182,
"learning_rate": 3e-06,
"loss": 6.7497,
"step": 6
},
{
"epoch": 0.19718309859154928,
"grad_norm": 7.694795608520508,
"learning_rate": 3.5e-06,
"loss": 6.6166,
"step": 7
},
{
"epoch": 0.22535211267605634,
"grad_norm": 6.317434310913086,
"learning_rate": 4.000000000000001e-06,
"loss": 6.4985,
"step": 8
},
{
"epoch": 0.2535211267605634,
"grad_norm": 5.917690277099609,
"learning_rate": 4.5e-06,
"loss": 6.453,
"step": 9
},
{
"epoch": 0.28169014084507044,
"grad_norm": 5.736076831817627,
"learning_rate": 5e-06,
"loss": 6.7027,
"step": 10
},
{
"epoch": 0.30985915492957744,
"grad_norm": 5.613097190856934,
"learning_rate": 4.99847706754774e-06,
"loss": 5.9373,
"step": 11
},
{
"epoch": 0.3380281690140845,
"grad_norm": 5.329749584197998,
"learning_rate": 4.993910125649561e-06,
"loss": 6.6172,
"step": 12
},
{
"epoch": 0.36619718309859156,
"grad_norm": 6.5323333740234375,
"learning_rate": 4.986304738420684e-06,
"loss": 6.2915,
"step": 13
},
{
"epoch": 0.39436619718309857,
"grad_norm": 6.311445236206055,
"learning_rate": 4.975670171853926e-06,
"loss": 6.5675,
"step": 14
},
{
"epoch": 0.4225352112676056,
"grad_norm": 5.865750789642334,
"learning_rate": 4.962019382530521e-06,
"loss": 6.5465,
"step": 15
},
{
"epoch": 0.4507042253521127,
"grad_norm": 6.167825698852539,
"learning_rate": 4.9453690018345144e-06,
"loss": 6.3649,
"step": 16
},
{
"epoch": 0.4788732394366197,
"grad_norm": 6.63243293762207,
"learning_rate": 4.925739315689991e-06,
"loss": 6.3944,
"step": 17
},
{
"epoch": 0.5070422535211268,
"grad_norm": 5.555633544921875,
"learning_rate": 4.903154239845798e-06,
"loss": 6.3991,
"step": 18
},
{
"epoch": 0.5352112676056338,
"grad_norm": 5.7282867431640625,
"learning_rate": 4.8776412907378845e-06,
"loss": 6.094,
"step": 19
},
{
"epoch": 0.5633802816901409,
"grad_norm": 6.097353935241699,
"learning_rate": 4.849231551964771e-06,
"loss": 6.2897,
"step": 20
},
{
"epoch": 0.5915492957746479,
"grad_norm": 6.4345197677612305,
"learning_rate": 4.817959636416969e-06,
"loss": 6.0746,
"step": 21
},
{
"epoch": 0.6197183098591549,
"grad_norm": 5.89772367477417,
"learning_rate": 4.783863644106502e-06,
"loss": 6.0027,
"step": 22
},
{
"epoch": 0.647887323943662,
"grad_norm": 6.29380989074707,
"learning_rate": 4.746985115747918e-06,
"loss": 5.7046,
"step": 23
},
{
"epoch": 0.676056338028169,
"grad_norm": 6.15521240234375,
"learning_rate": 4.707368982147318e-06,
"loss": 6.1176,
"step": 24
},
{
"epoch": 0.704225352112676,
"grad_norm": 5.841217517852783,
"learning_rate": 4.665063509461098e-06,
"loss": 6.0347,
"step": 25
},
{
"epoch": 0.7323943661971831,
"grad_norm": 5.708609580993652,
"learning_rate": 4.620120240391065e-06,
"loss": 5.7374,
"step": 26
},
{
"epoch": 0.7605633802816901,
"grad_norm": 6.486269474029541,
"learning_rate": 4.572593931387604e-06,
"loss": 5.9866,
"step": 27
},
{
"epoch": 0.7887323943661971,
"grad_norm": 6.278411388397217,
"learning_rate": 4.522542485937369e-06,
"loss": 6.0473,
"step": 28
},
{
"epoch": 0.8169014084507042,
"grad_norm": 6.592667102813721,
"learning_rate": 4.470026884016805e-06,
"loss": 6.0237,
"step": 29
},
{
"epoch": 0.8450704225352113,
"grad_norm": 6.2682414054870605,
"learning_rate": 4.415111107797445e-06,
"loss": 6.0611,
"step": 30
},
{
"epoch": 0.8732394366197183,
"grad_norm": 5.710134029388428,
"learning_rate": 4.357862063693486e-06,
"loss": 5.6585,
"step": 31
},
{
"epoch": 0.9014084507042254,
"grad_norm": 6.120304107666016,
"learning_rate": 4.2983495008466285e-06,
"loss": 6.3488,
"step": 32
},
{
"epoch": 0.9295774647887324,
"grad_norm": 5.738293170928955,
"learning_rate": 4.236645926147493e-06,
"loss": 5.5834,
"step": 33
},
{
"epoch": 0.9577464788732394,
"grad_norm": 6.664410591125488,
"learning_rate": 4.172826515897146e-06,
"loss": 5.7185,
"step": 34
},
{
"epoch": 0.9859154929577465,
"grad_norm": 6.02655553817749,
"learning_rate": 4.106969024216348e-06,
"loss": 5.4995,
"step": 35
},
{
"epoch": 1.0211267605633803,
"grad_norm": 10.034653663635254,
"learning_rate": 4.039153688314146e-06,
"loss": 9.6958,
"step": 36
},
{
"epoch": 1.0492957746478873,
"grad_norm": 6.114748001098633,
"learning_rate": 3.969463130731183e-06,
"loss": 5.6932,
"step": 37
},
{
"epoch": 1.0774647887323943,
"grad_norm": 5.394074440002441,
"learning_rate": 3.897982258676867e-06,
"loss": 5.4438,
"step": 38
},
{
"epoch": 1.1056338028169015,
"grad_norm": 5.475838661193848,
"learning_rate": 3.824798160583012e-06,
"loss": 5.1237,
"step": 39
},
{
"epoch": 1.1338028169014085,
"grad_norm": 5.955112934112549,
"learning_rate": 3.7500000000000005e-06,
"loss": 5.3704,
"step": 40
},
{
"epoch": 1.1619718309859155,
"grad_norm": 6.310902118682861,
"learning_rate": 3.6736789069647273e-06,
"loss": 5.5419,
"step": 41
},
{
"epoch": 1.1901408450704225,
"grad_norm": 6.074863910675049,
"learning_rate": 3.595927866972694e-06,
"loss": 5.2662,
"step": 42
},
{
"epoch": 1.2183098591549295,
"grad_norm": 5.811051845550537,
"learning_rate": 3.516841607689501e-06,
"loss": 5.256,
"step": 43
},
{
"epoch": 1.2464788732394365,
"grad_norm": 6.148581504821777,
"learning_rate": 3.436516483539781e-06,
"loss": 5.0733,
"step": 44
},
{
"epoch": 1.2746478873239437,
"grad_norm": 6.256888389587402,
"learning_rate": 3.3550503583141726e-06,
"loss": 5.1171,
"step": 45
},
{
"epoch": 1.3028169014084507,
"grad_norm": 5.250644683837891,
"learning_rate": 3.272542485937369e-06,
"loss": 5.2975,
"step": 46
},
{
"epoch": 1.3309859154929577,
"grad_norm": 5.596186637878418,
"learning_rate": 3.189093389542498e-06,
"loss": 5.3599,
"step": 47
},
{
"epoch": 1.3591549295774648,
"grad_norm": 5.674249649047852,
"learning_rate": 3.1048047389991693e-06,
"loss": 5.2093,
"step": 48
},
{
"epoch": 1.3873239436619718,
"grad_norm": 6.155755996704102,
"learning_rate": 3.019779227044398e-06,
"loss": 5.1566,
"step": 49
},
{
"epoch": 1.415492957746479,
"grad_norm": 6.356016635894775,
"learning_rate": 2.9341204441673267e-06,
"loss": 5.0461,
"step": 50
},
{
"epoch": 1.415492957746479,
"eval_loss": 4.852181434631348,
"eval_runtime": 1.229,
"eval_samples_per_second": 48.819,
"eval_steps_per_second": 6.509,
"step": 50
},
{
"epoch": 1.443661971830986,
"grad_norm": 5.88961124420166,
"learning_rate": 2.847932752400164e-06,
"loss": 5.3644,
"step": 51
},
{
"epoch": 1.471830985915493,
"grad_norm": 4.989941120147705,
"learning_rate": 2.761321158169134e-06,
"loss": 5.3129,
"step": 52
},
{
"epoch": 1.5,
"grad_norm": 5.352567672729492,
"learning_rate": 2.6743911843603134e-06,
"loss": 5.1404,
"step": 53
},
{
"epoch": 1.528169014084507,
"grad_norm": 5.720556259155273,
"learning_rate": 2.587248741756253e-06,
"loss": 4.8448,
"step": 54
},
{
"epoch": 1.556338028169014,
"grad_norm": 5.738869667053223,
"learning_rate": 2.5e-06,
"loss": 5.2918,
"step": 55
},
{
"epoch": 1.584507042253521,
"grad_norm": 5.720866680145264,
"learning_rate": 2.4127512582437486e-06,
"loss": 4.7,
"step": 56
},
{
"epoch": 1.612676056338028,
"grad_norm": 5.672741413116455,
"learning_rate": 2.325608815639687e-06,
"loss": 5.124,
"step": 57
},
{
"epoch": 1.6408450704225352,
"grad_norm": 5.708094120025635,
"learning_rate": 2.238678841830867e-06,
"loss": 5.3825,
"step": 58
},
{
"epoch": 1.6690140845070423,
"grad_norm": 4.969758033752441,
"learning_rate": 2.1520672475998374e-06,
"loss": 5.2906,
"step": 59
},
{
"epoch": 1.6971830985915493,
"grad_norm": 4.994139194488525,
"learning_rate": 2.0658795558326745e-06,
"loss": 5.1099,
"step": 60
},
{
"epoch": 1.7253521126760565,
"grad_norm": 5.776417255401611,
"learning_rate": 1.9802207729556023e-06,
"loss": 4.8853,
"step": 61
},
{
"epoch": 1.7535211267605635,
"grad_norm": 5.504635334014893,
"learning_rate": 1.895195261000831e-06,
"loss": 4.8793,
"step": 62
},
{
"epoch": 1.7816901408450705,
"grad_norm": 5.382895469665527,
"learning_rate": 1.8109066104575023e-06,
"loss": 4.9927,
"step": 63
},
{
"epoch": 1.8098591549295775,
"grad_norm": 5.304967403411865,
"learning_rate": 1.7274575140626318e-06,
"loss": 4.8314,
"step": 64
},
{
"epoch": 1.8380281690140845,
"grad_norm": 5.1869893074035645,
"learning_rate": 1.6449496416858285e-06,
"loss": 5.233,
"step": 65
},
{
"epoch": 1.8661971830985915,
"grad_norm": 6.1123366355896,
"learning_rate": 1.56348351646022e-06,
"loss": 4.9092,
"step": 66
},
{
"epoch": 1.8943661971830985,
"grad_norm": 5.411812782287598,
"learning_rate": 1.4831583923105e-06,
"loss": 5.1397,
"step": 67
},
{
"epoch": 1.9225352112676055,
"grad_norm": 5.654954433441162,
"learning_rate": 1.4040721330273063e-06,
"loss": 4.6659,
"step": 68
},
{
"epoch": 1.9507042253521125,
"grad_norm": 5.411698341369629,
"learning_rate": 1.3263210930352737e-06,
"loss": 4.8395,
"step": 69
},
{
"epoch": 1.9788732394366197,
"grad_norm": 5.4398064613342285,
"learning_rate": 1.2500000000000007e-06,
"loss": 5.1385,
"step": 70
},
{
"epoch": 2.0140845070422535,
"grad_norm": 10.192140579223633,
"learning_rate": 1.1752018394169882e-06,
"loss": 7.7338,
"step": 71
},
{
"epoch": 2.0422535211267605,
"grad_norm": 5.421514511108398,
"learning_rate": 1.1020177413231334e-06,
"loss": 4.567,
"step": 72
},
{
"epoch": 2.0704225352112675,
"grad_norm": 5.557625770568848,
"learning_rate": 1.0305368692688175e-06,
"loss": 4.3131,
"step": 73
},
{
"epoch": 2.0985915492957745,
"grad_norm": 5.216914653778076,
"learning_rate": 9.608463116858544e-07,
"loss": 4.5585,
"step": 74
},
{
"epoch": 2.1267605633802815,
"grad_norm": 5.993343830108643,
"learning_rate": 8.930309757836517e-07,
"loss": 4.6337,
"step": 75
},
{
"epoch": 2.1549295774647885,
"grad_norm": 5.094235420227051,
"learning_rate": 8.271734841028553e-07,
"loss": 4.8541,
"step": 76
},
{
"epoch": 2.183098591549296,
"grad_norm": 5.717433929443359,
"learning_rate": 7.633540738525066e-07,
"loss": 5.2967,
"step": 77
},
{
"epoch": 2.211267605633803,
"grad_norm": 5.293563365936279,
"learning_rate": 7.016504991533727e-07,
"loss": 4.8659,
"step": 78
},
{
"epoch": 2.23943661971831,
"grad_norm": 5.073064804077148,
"learning_rate": 6.421379363065142e-07,
"loss": 4.9172,
"step": 79
},
{
"epoch": 2.267605633802817,
"grad_norm": 5.354030609130859,
"learning_rate": 5.848888922025553e-07,
"loss": 4.6161,
"step": 80
},
{
"epoch": 2.295774647887324,
"grad_norm": 5.201179504394531,
"learning_rate": 5.299731159831953e-07,
"loss": 4.7591,
"step": 81
},
{
"epoch": 2.323943661971831,
"grad_norm": 5.040406227111816,
"learning_rate": 4.774575140626317e-07,
"loss": 4.7533,
"step": 82
},
{
"epoch": 2.352112676056338,
"grad_norm": 5.279065132141113,
"learning_rate": 4.27406068612396e-07,
"loss": 4.6149,
"step": 83
},
{
"epoch": 2.380281690140845,
"grad_norm": 5.657581329345703,
"learning_rate": 3.798797596089351e-07,
"loss": 4.4146,
"step": 84
},
{
"epoch": 2.408450704225352,
"grad_norm": 5.0008931159973145,
"learning_rate": 3.3493649053890325e-07,
"loss": 4.374,
"step": 85
},
{
"epoch": 2.436619718309859,
"grad_norm": 5.283320426940918,
"learning_rate": 2.9263101785268253e-07,
"loss": 4.5699,
"step": 86
},
{
"epoch": 2.464788732394366,
"grad_norm": 5.353503704071045,
"learning_rate": 2.53014884252083e-07,
"loss": 4.6215,
"step": 87
},
{
"epoch": 2.492957746478873,
"grad_norm": 5.431240081787109,
"learning_rate": 2.1613635589349756e-07,
"loss": 4.5881,
"step": 88
},
{
"epoch": 2.52112676056338,
"grad_norm": 5.6447858810424805,
"learning_rate": 1.8204036358303173e-07,
"loss": 4.2597,
"step": 89
},
{
"epoch": 2.5492957746478875,
"grad_norm": 5.344186305999756,
"learning_rate": 1.507684480352292e-07,
"loss": 4.4999,
"step": 90
},
{
"epoch": 2.5774647887323945,
"grad_norm": 5.2609477043151855,
"learning_rate": 1.223587092621162e-07,
"loss": 4.5457,
"step": 91
},
{
"epoch": 2.6056338028169015,
"grad_norm": 5.623130798339844,
"learning_rate": 9.684576015420277e-08,
"loss": 4.4276,
"step": 92
},
{
"epoch": 2.6338028169014085,
"grad_norm": 5.679134845733643,
"learning_rate": 7.426068431000883e-08,
"loss": 4.7285,
"step": 93
},
{
"epoch": 2.6619718309859155,
"grad_norm": 5.343556880950928,
"learning_rate": 5.463099816548578e-08,
"loss": 4.7053,
"step": 94
},
{
"epoch": 2.6901408450704225,
"grad_norm": 4.940552711486816,
"learning_rate": 3.798061746947995e-08,
"loss": 4.4612,
"step": 95
},
{
"epoch": 2.7183098591549295,
"grad_norm": 5.611880779266357,
"learning_rate": 2.4329828146074096e-08,
"loss": 4.37,
"step": 96
},
{
"epoch": 2.7464788732394365,
"grad_norm": 5.197037220001221,
"learning_rate": 1.3695261579316776e-08,
"loss": 4.5959,
"step": 97
},
{
"epoch": 2.7746478873239435,
"grad_norm": 5.572286605834961,
"learning_rate": 6.089874350439507e-09,
"loss": 4.5331,
"step": 98
},
{
"epoch": 2.802816901408451,
"grad_norm": 5.335962772369385,
"learning_rate": 1.5229324522605949e-09,
"loss": 4.3457,
"step": 99
},
{
"epoch": 2.830985915492958,
"grad_norm": 5.259434223175049,
"learning_rate": 0.0,
"loss": 4.7794,
"step": 100
},
{
"epoch": 2.830985915492958,
"eval_loss": 4.300358295440674,
"eval_runtime": 1.2256,
"eval_samples_per_second": 48.955,
"eval_steps_per_second": 6.527,
"step": 100
}
],
"logging_steps": 1,
"max_steps": 100,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"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": 2.13314785247232e+16,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}