bbytxt's picture
Training in progress, step 100, checkpoint
8802571 verified
{
"best_metric": 11.10726547241211,
"best_model_checkpoint": "miner_id_24/checkpoint-50",
"epoch": 1.5594541910331383,
"eval_steps": 50,
"global_step": 100,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.015594541910331383,
"grad_norm": 1.3553541898727417,
"learning_rate": 5.000000000000001e-07,
"loss": 88.9667,
"step": 1
},
{
"epoch": 0.015594541910331383,
"eval_loss": 11.111183166503906,
"eval_runtime": 0.2874,
"eval_samples_per_second": 375.846,
"eval_steps_per_second": 93.962,
"step": 1
},
{
"epoch": 0.031189083820662766,
"grad_norm": 1.4310979843139648,
"learning_rate": 1.0000000000000002e-06,
"loss": 88.9521,
"step": 2
},
{
"epoch": 0.04678362573099415,
"grad_norm": 1.448810338973999,
"learning_rate": 1.5e-06,
"loss": 88.9224,
"step": 3
},
{
"epoch": 0.06237816764132553,
"grad_norm": 1.4280792474746704,
"learning_rate": 2.0000000000000003e-06,
"loss": 88.9165,
"step": 4
},
{
"epoch": 0.07797270955165692,
"grad_norm": 1.5008811950683594,
"learning_rate": 2.5e-06,
"loss": 88.9208,
"step": 5
},
{
"epoch": 0.0935672514619883,
"grad_norm": 1.6087157726287842,
"learning_rate": 3e-06,
"loss": 88.9012,
"step": 6
},
{
"epoch": 0.10916179337231968,
"grad_norm": 1.6683207750320435,
"learning_rate": 3.5e-06,
"loss": 88.9475,
"step": 7
},
{
"epoch": 0.12475633528265107,
"grad_norm": 1.747448444366455,
"learning_rate": 4.000000000000001e-06,
"loss": 88.9432,
"step": 8
},
{
"epoch": 0.14035087719298245,
"grad_norm": 1.678775668144226,
"learning_rate": 4.5e-06,
"loss": 88.9057,
"step": 9
},
{
"epoch": 0.15594541910331383,
"grad_norm": 1.823146104812622,
"learning_rate": 5e-06,
"loss": 88.8821,
"step": 10
},
{
"epoch": 0.17153996101364521,
"grad_norm": 1.9624767303466797,
"learning_rate": 4.99847706754774e-06,
"loss": 88.9016,
"step": 11
},
{
"epoch": 0.1871345029239766,
"grad_norm": 1.9462685585021973,
"learning_rate": 4.993910125649561e-06,
"loss": 88.9103,
"step": 12
},
{
"epoch": 0.20272904483430798,
"grad_norm": 2.1563684940338135,
"learning_rate": 4.986304738420684e-06,
"loss": 88.9475,
"step": 13
},
{
"epoch": 0.21832358674463936,
"grad_norm": 2.48010516166687,
"learning_rate": 4.975670171853926e-06,
"loss": 88.932,
"step": 14
},
{
"epoch": 0.23391812865497075,
"grad_norm": 3.1107337474823,
"learning_rate": 4.962019382530521e-06,
"loss": 88.8091,
"step": 15
},
{
"epoch": 0.24951267056530213,
"grad_norm": 5.877386569976807,
"learning_rate": 4.9453690018345144e-06,
"loss": 88.589,
"step": 16
},
{
"epoch": 0.2651072124756335,
"grad_norm": 1.4020336866378784,
"learning_rate": 4.925739315689991e-06,
"loss": 88.9679,
"step": 17
},
{
"epoch": 0.2807017543859649,
"grad_norm": 1.4191652536392212,
"learning_rate": 4.903154239845798e-06,
"loss": 88.9306,
"step": 18
},
{
"epoch": 0.2962962962962963,
"grad_norm": 1.4291287660598755,
"learning_rate": 4.8776412907378845e-06,
"loss": 88.9514,
"step": 19
},
{
"epoch": 0.31189083820662766,
"grad_norm": 1.5101865530014038,
"learning_rate": 4.849231551964771e-06,
"loss": 88.9267,
"step": 20
},
{
"epoch": 0.32748538011695905,
"grad_norm": 1.5891046524047852,
"learning_rate": 4.817959636416969e-06,
"loss": 88.9252,
"step": 21
},
{
"epoch": 0.34307992202729043,
"grad_norm": 1.5987111330032349,
"learning_rate": 4.783863644106502e-06,
"loss": 88.9014,
"step": 22
},
{
"epoch": 0.3586744639376218,
"grad_norm": 1.6611799001693726,
"learning_rate": 4.746985115747918e-06,
"loss": 88.9222,
"step": 23
},
{
"epoch": 0.3742690058479532,
"grad_norm": 1.675337314605713,
"learning_rate": 4.707368982147318e-06,
"loss": 88.9076,
"step": 24
},
{
"epoch": 0.3898635477582846,
"grad_norm": 1.729783058166504,
"learning_rate": 4.665063509461098e-06,
"loss": 88.9013,
"step": 25
},
{
"epoch": 0.40545808966861596,
"grad_norm": 1.9155665636062622,
"learning_rate": 4.620120240391065e-06,
"loss": 88.8678,
"step": 26
},
{
"epoch": 0.42105263157894735,
"grad_norm": 1.9021366834640503,
"learning_rate": 4.572593931387604e-06,
"loss": 88.9318,
"step": 27
},
{
"epoch": 0.43664717348927873,
"grad_norm": 2.0137956142425537,
"learning_rate": 4.522542485937369e-06,
"loss": 88.8439,
"step": 28
},
{
"epoch": 0.4522417153996101,
"grad_norm": 2.1356048583984375,
"learning_rate": 4.470026884016805e-06,
"loss": 88.9014,
"step": 29
},
{
"epoch": 0.4678362573099415,
"grad_norm": 2.3856770992279053,
"learning_rate": 4.415111107797445e-06,
"loss": 88.8764,
"step": 30
},
{
"epoch": 0.4834307992202729,
"grad_norm": 2.872187852859497,
"learning_rate": 4.357862063693486e-06,
"loss": 88.8898,
"step": 31
},
{
"epoch": 0.49902534113060426,
"grad_norm": 4.954247951507568,
"learning_rate": 4.2983495008466285e-06,
"loss": 88.7124,
"step": 32
},
{
"epoch": 0.5146198830409356,
"grad_norm": 1.4366636276245117,
"learning_rate": 4.236645926147493e-06,
"loss": 88.9227,
"step": 33
},
{
"epoch": 0.530214424951267,
"grad_norm": 1.502366304397583,
"learning_rate": 4.172826515897146e-06,
"loss": 88.9448,
"step": 34
},
{
"epoch": 0.5458089668615984,
"grad_norm": 1.4580628871917725,
"learning_rate": 4.106969024216348e-06,
"loss": 88.904,
"step": 35
},
{
"epoch": 0.5614035087719298,
"grad_norm": 1.4254974126815796,
"learning_rate": 4.039153688314146e-06,
"loss": 88.9466,
"step": 36
},
{
"epoch": 0.5769980506822612,
"grad_norm": 1.559779405593872,
"learning_rate": 3.969463130731183e-06,
"loss": 88.8986,
"step": 37
},
{
"epoch": 0.5925925925925926,
"grad_norm": 1.6463968753814697,
"learning_rate": 3.897982258676867e-06,
"loss": 88.915,
"step": 38
},
{
"epoch": 0.6081871345029239,
"grad_norm": 1.7474920749664307,
"learning_rate": 3.824798160583012e-06,
"loss": 88.9155,
"step": 39
},
{
"epoch": 0.6237816764132553,
"grad_norm": 1.8197089433670044,
"learning_rate": 3.7500000000000005e-06,
"loss": 88.871,
"step": 40
},
{
"epoch": 0.6393762183235867,
"grad_norm": 1.8057571649551392,
"learning_rate": 3.6736789069647273e-06,
"loss": 88.9049,
"step": 41
},
{
"epoch": 0.6549707602339181,
"grad_norm": 1.847694754600525,
"learning_rate": 3.595927866972694e-06,
"loss": 88.8932,
"step": 42
},
{
"epoch": 0.6705653021442495,
"grad_norm": 1.9483572244644165,
"learning_rate": 3.516841607689501e-06,
"loss": 88.8755,
"step": 43
},
{
"epoch": 0.6861598440545809,
"grad_norm": 2.0147557258605957,
"learning_rate": 3.436516483539781e-06,
"loss": 88.9301,
"step": 44
},
{
"epoch": 0.7017543859649122,
"grad_norm": 2.302340269088745,
"learning_rate": 3.3550503583141726e-06,
"loss": 88.7964,
"step": 45
},
{
"epoch": 0.7173489278752436,
"grad_norm": 2.700557231903076,
"learning_rate": 3.272542485937369e-06,
"loss": 88.7984,
"step": 46
},
{
"epoch": 0.732943469785575,
"grad_norm": 3.645312547683716,
"learning_rate": 3.189093389542498e-06,
"loss": 88.781,
"step": 47
},
{
"epoch": 0.7485380116959064,
"grad_norm": 5.459611892700195,
"learning_rate": 3.1048047389991693e-06,
"loss": 88.6414,
"step": 48
},
{
"epoch": 0.7641325536062378,
"grad_norm": 1.5512522459030151,
"learning_rate": 3.019779227044398e-06,
"loss": 88.9102,
"step": 49
},
{
"epoch": 0.7797270955165692,
"grad_norm": 1.5456151962280273,
"learning_rate": 2.9341204441673267e-06,
"loss": 88.9206,
"step": 50
},
{
"epoch": 0.7797270955165692,
"eval_loss": 11.10726547241211,
"eval_runtime": 0.2974,
"eval_samples_per_second": 363.086,
"eval_steps_per_second": 90.772,
"step": 50
},
{
"epoch": 0.7953216374269005,
"grad_norm": 1.4868738651275635,
"learning_rate": 2.847932752400164e-06,
"loss": 88.9165,
"step": 51
},
{
"epoch": 0.8109161793372319,
"grad_norm": 1.5754703283309937,
"learning_rate": 2.761321158169134e-06,
"loss": 88.8994,
"step": 52
},
{
"epoch": 0.8265107212475633,
"grad_norm": 1.521441102027893,
"learning_rate": 2.6743911843603134e-06,
"loss": 88.8922,
"step": 53
},
{
"epoch": 0.8421052631578947,
"grad_norm": 1.5741850137710571,
"learning_rate": 2.587248741756253e-06,
"loss": 88.9125,
"step": 54
},
{
"epoch": 0.8576998050682261,
"grad_norm": 1.6995844841003418,
"learning_rate": 2.5e-06,
"loss": 88.8839,
"step": 55
},
{
"epoch": 0.8732943469785575,
"grad_norm": 1.7483824491500854,
"learning_rate": 2.4127512582437486e-06,
"loss": 88.8931,
"step": 56
},
{
"epoch": 0.8888888888888888,
"grad_norm": 1.6258654594421387,
"learning_rate": 2.325608815639687e-06,
"loss": 88.9227,
"step": 57
},
{
"epoch": 0.9044834307992202,
"grad_norm": 1.6917520761489868,
"learning_rate": 2.238678841830867e-06,
"loss": 88.8958,
"step": 58
},
{
"epoch": 0.9200779727095516,
"grad_norm": 1.9397125244140625,
"learning_rate": 2.1520672475998374e-06,
"loss": 88.8976,
"step": 59
},
{
"epoch": 0.935672514619883,
"grad_norm": 2.0061938762664795,
"learning_rate": 2.0658795558326745e-06,
"loss": 88.8821,
"step": 60
},
{
"epoch": 0.9512670565302144,
"grad_norm": 2.2613093852996826,
"learning_rate": 1.9802207729556023e-06,
"loss": 88.9129,
"step": 61
},
{
"epoch": 0.9668615984405458,
"grad_norm": 2.683389186859131,
"learning_rate": 1.895195261000831e-06,
"loss": 88.7381,
"step": 62
},
{
"epoch": 0.9824561403508771,
"grad_norm": 3.433419704437256,
"learning_rate": 1.8109066104575023e-06,
"loss": 88.8607,
"step": 63
},
{
"epoch": 0.9980506822612085,
"grad_norm": 6.409455299377441,
"learning_rate": 1.7274575140626318e-06,
"loss": 88.5442,
"step": 64
},
{
"epoch": 1.01364522417154,
"grad_norm": 1.4463061094284058,
"learning_rate": 1.6449496416858285e-06,
"loss": 88.9063,
"step": 65
},
{
"epoch": 1.0292397660818713,
"grad_norm": 1.4709982872009277,
"learning_rate": 1.56348351646022e-06,
"loss": 88.9036,
"step": 66
},
{
"epoch": 1.0448343079922027,
"grad_norm": 1.5933891534805298,
"learning_rate": 1.4831583923105e-06,
"loss": 88.9131,
"step": 67
},
{
"epoch": 1.060428849902534,
"grad_norm": 1.418686032295227,
"learning_rate": 1.4040721330273063e-06,
"loss": 88.8879,
"step": 68
},
{
"epoch": 1.0760233918128654,
"grad_norm": 1.5968884229660034,
"learning_rate": 1.3263210930352737e-06,
"loss": 88.8766,
"step": 69
},
{
"epoch": 1.0916179337231968,
"grad_norm": 1.7474418878555298,
"learning_rate": 1.2500000000000007e-06,
"loss": 88.9008,
"step": 70
},
{
"epoch": 1.1072124756335282,
"grad_norm": 1.7670066356658936,
"learning_rate": 1.1752018394169882e-06,
"loss": 88.9295,
"step": 71
},
{
"epoch": 1.1228070175438596,
"grad_norm": 1.739268183708191,
"learning_rate": 1.1020177413231334e-06,
"loss": 88.8783,
"step": 72
},
{
"epoch": 1.138401559454191,
"grad_norm": 1.924734354019165,
"learning_rate": 1.0305368692688175e-06,
"loss": 88.9094,
"step": 73
},
{
"epoch": 1.1539961013645224,
"grad_norm": 1.8002381324768066,
"learning_rate": 9.608463116858544e-07,
"loss": 88.9047,
"step": 74
},
{
"epoch": 1.1695906432748537,
"grad_norm": 1.9778398275375366,
"learning_rate": 8.930309757836517e-07,
"loss": 88.8734,
"step": 75
},
{
"epoch": 1.1851851851851851,
"grad_norm": 2.0487163066864014,
"learning_rate": 8.271734841028553e-07,
"loss": 88.8375,
"step": 76
},
{
"epoch": 1.2007797270955165,
"grad_norm": 2.143615484237671,
"learning_rate": 7.633540738525066e-07,
"loss": 88.8514,
"step": 77
},
{
"epoch": 1.2163742690058479,
"grad_norm": 2.540370225906372,
"learning_rate": 7.016504991533727e-07,
"loss": 88.7744,
"step": 78
},
{
"epoch": 1.2319688109161793,
"grad_norm": 3.210033416748047,
"learning_rate": 6.421379363065142e-07,
"loss": 88.7798,
"step": 79
},
{
"epoch": 1.2475633528265107,
"grad_norm": 5.062490463256836,
"learning_rate": 5.848888922025553e-07,
"loss": 88.712,
"step": 80
},
{
"epoch": 1.263157894736842,
"grad_norm": 2.2439610958099365,
"learning_rate": 5.299731159831953e-07,
"loss": 88.918,
"step": 81
},
{
"epoch": 1.2787524366471734,
"grad_norm": 1.4683839082717896,
"learning_rate": 4.774575140626317e-07,
"loss": 88.9326,
"step": 82
},
{
"epoch": 1.2943469785575048,
"grad_norm": 1.4734752178192139,
"learning_rate": 4.27406068612396e-07,
"loss": 88.9029,
"step": 83
},
{
"epoch": 1.3099415204678362,
"grad_norm": 1.5223207473754883,
"learning_rate": 3.798797596089351e-07,
"loss": 88.9191,
"step": 84
},
{
"epoch": 1.3255360623781676,
"grad_norm": 1.5164719820022583,
"learning_rate": 3.3493649053890325e-07,
"loss": 88.8715,
"step": 85
},
{
"epoch": 1.341130604288499,
"grad_norm": 1.6114667654037476,
"learning_rate": 2.9263101785268253e-07,
"loss": 88.8649,
"step": 86
},
{
"epoch": 1.3567251461988303,
"grad_norm": 1.7107863426208496,
"learning_rate": 2.53014884252083e-07,
"loss": 88.8973,
"step": 87
},
{
"epoch": 1.3723196881091617,
"grad_norm": 1.7419860363006592,
"learning_rate": 2.1613635589349756e-07,
"loss": 88.8746,
"step": 88
},
{
"epoch": 1.387914230019493,
"grad_norm": 1.6827164888381958,
"learning_rate": 1.8204036358303173e-07,
"loss": 88.8891,
"step": 89
},
{
"epoch": 1.4035087719298245,
"grad_norm": 1.8386940956115723,
"learning_rate": 1.507684480352292e-07,
"loss": 88.8503,
"step": 90
},
{
"epoch": 1.4191033138401559,
"grad_norm": 1.9322350025177002,
"learning_rate": 1.223587092621162e-07,
"loss": 88.8244,
"step": 91
},
{
"epoch": 1.4346978557504872,
"grad_norm": 1.968429684638977,
"learning_rate": 9.684576015420277e-08,
"loss": 88.882,
"step": 92
},
{
"epoch": 1.4502923976608186,
"grad_norm": 2.1462831497192383,
"learning_rate": 7.426068431000883e-08,
"loss": 88.8721,
"step": 93
},
{
"epoch": 1.46588693957115,
"grad_norm": 2.4528849124908447,
"learning_rate": 5.463099816548578e-08,
"loss": 88.8235,
"step": 94
},
{
"epoch": 1.4814814814814814,
"grad_norm": 2.8609659671783447,
"learning_rate": 3.798061746947995e-08,
"loss": 88.7827,
"step": 95
},
{
"epoch": 1.4970760233918128,
"grad_norm": 4.6707563400268555,
"learning_rate": 2.4329828146074096e-08,
"loss": 88.6615,
"step": 96
},
{
"epoch": 1.5126705653021442,
"grad_norm": 2.532287120819092,
"learning_rate": 1.3695261579316776e-08,
"loss": 88.8792,
"step": 97
},
{
"epoch": 1.5282651072124755,
"grad_norm": 1.508450984954834,
"learning_rate": 6.089874350439507e-09,
"loss": 88.9139,
"step": 98
},
{
"epoch": 1.543859649122807,
"grad_norm": 1.4835156202316284,
"learning_rate": 1.5229324522605949e-09,
"loss": 88.9422,
"step": 99
},
{
"epoch": 1.5594541910331383,
"grad_norm": 1.498764991760254,
"learning_rate": 0.0,
"loss": 88.9188,
"step": 100
},
{
"epoch": 1.5594541910331383,
"eval_loss": 11.107521057128906,
"eval_runtime": 0.3045,
"eval_samples_per_second": 354.702,
"eval_steps_per_second": 88.675,
"step": 100
}
],
"logging_steps": 1,
"max_steps": 100,
"num_input_tokens_seen": 0,
"num_train_epochs": 2,
"save_steps": 50,
"stateful_callbacks": {
"EarlyStoppingCallback": {
"args": {
"early_stopping_patience": 5,
"early_stopping_threshold": 0.0
},
"attributes": {
"early_stopping_patience_counter": 1
}
},
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 8592815554560.0,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}