nttx's picture
Training in progress, step 100, checkpoint
52ed1c6 verified
{
"best_metric": 1.4722347259521484,
"best_model_checkpoint": "miner_id_24/checkpoint-100",
"epoch": 0.5899705014749262,
"eval_steps": 50,
"global_step": 100,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0058997050147492625,
"grad_norm": 2.9862964153289795,
"learning_rate": 5.000000000000001e-07,
"loss": 11.9031,
"step": 1
},
{
"epoch": 0.0058997050147492625,
"eval_loss": 2.5443007946014404,
"eval_runtime": 32.2234,
"eval_samples_per_second": 8.876,
"eval_steps_per_second": 2.234,
"step": 1
},
{
"epoch": 0.011799410029498525,
"grad_norm": 3.709792137145996,
"learning_rate": 1.0000000000000002e-06,
"loss": 12.6814,
"step": 2
},
{
"epoch": 0.017699115044247787,
"grad_norm": 4.134566783905029,
"learning_rate": 1.5e-06,
"loss": 13.174,
"step": 3
},
{
"epoch": 0.02359882005899705,
"grad_norm": 4.506526470184326,
"learning_rate": 2.0000000000000003e-06,
"loss": 12.758,
"step": 4
},
{
"epoch": 0.029498525073746312,
"grad_norm": 4.452362537384033,
"learning_rate": 2.5e-06,
"loss": 10.6929,
"step": 5
},
{
"epoch": 0.035398230088495575,
"grad_norm": 5.046873092651367,
"learning_rate": 3e-06,
"loss": 10.9967,
"step": 6
},
{
"epoch": 0.04129793510324484,
"grad_norm": 6.876310348510742,
"learning_rate": 3.5e-06,
"loss": 12.946,
"step": 7
},
{
"epoch": 0.0471976401179941,
"grad_norm": 8.722047805786133,
"learning_rate": 4.000000000000001e-06,
"loss": 14.8323,
"step": 8
},
{
"epoch": 0.05309734513274336,
"grad_norm": 8.891469955444336,
"learning_rate": 4.5e-06,
"loss": 14.7489,
"step": 9
},
{
"epoch": 0.058997050147492625,
"grad_norm": 10.75536823272705,
"learning_rate": 5e-06,
"loss": 14.0431,
"step": 10
},
{
"epoch": 0.06489675516224189,
"grad_norm": 12.062834739685059,
"learning_rate": 4.99847706754774e-06,
"loss": 16.1985,
"step": 11
},
{
"epoch": 0.07079646017699115,
"grad_norm": 12.394959449768066,
"learning_rate": 4.993910125649561e-06,
"loss": 16.0138,
"step": 12
},
{
"epoch": 0.07669616519174041,
"grad_norm": 13.049904823303223,
"learning_rate": 4.986304738420684e-06,
"loss": 17.1506,
"step": 13
},
{
"epoch": 0.08259587020648967,
"grad_norm": 13.703821182250977,
"learning_rate": 4.975670171853926e-06,
"loss": 17.1909,
"step": 14
},
{
"epoch": 0.08849557522123894,
"grad_norm": 15.688636779785156,
"learning_rate": 4.962019382530521e-06,
"loss": 17.8761,
"step": 15
},
{
"epoch": 0.0943952802359882,
"grad_norm": 18.053247451782227,
"learning_rate": 4.9453690018345144e-06,
"loss": 19.2284,
"step": 16
},
{
"epoch": 0.10029498525073746,
"grad_norm": 18.931636810302734,
"learning_rate": 4.925739315689991e-06,
"loss": 20.131,
"step": 17
},
{
"epoch": 0.10619469026548672,
"grad_norm": 21.049278259277344,
"learning_rate": 4.903154239845798e-06,
"loss": 19.2567,
"step": 18
},
{
"epoch": 0.11209439528023599,
"grad_norm": 20.777387619018555,
"learning_rate": 4.8776412907378845e-06,
"loss": 18.6328,
"step": 19
},
{
"epoch": 0.11799410029498525,
"grad_norm": 22.106796264648438,
"learning_rate": 4.849231551964771e-06,
"loss": 19.1483,
"step": 20
},
{
"epoch": 0.12389380530973451,
"grad_norm": 22.35647201538086,
"learning_rate": 4.817959636416969e-06,
"loss": 19.4738,
"step": 21
},
{
"epoch": 0.12979351032448377,
"grad_norm": 22.263975143432617,
"learning_rate": 4.783863644106502e-06,
"loss": 20.9651,
"step": 22
},
{
"epoch": 0.13569321533923304,
"grad_norm": 23.579002380371094,
"learning_rate": 4.746985115747918e-06,
"loss": 20.4206,
"step": 23
},
{
"epoch": 0.1415929203539823,
"grad_norm": 22.080753326416016,
"learning_rate": 4.707368982147318e-06,
"loss": 18.6608,
"step": 24
},
{
"epoch": 0.14749262536873156,
"grad_norm": 27.090911865234375,
"learning_rate": 4.665063509461098e-06,
"loss": 21.1101,
"step": 25
},
{
"epoch": 0.15339233038348082,
"grad_norm": 24.73910903930664,
"learning_rate": 4.620120240391065e-06,
"loss": 21.0186,
"step": 26
},
{
"epoch": 0.1592920353982301,
"grad_norm": 29.831039428710938,
"learning_rate": 4.572593931387604e-06,
"loss": 18.9938,
"step": 27
},
{
"epoch": 0.16519174041297935,
"grad_norm": 28.281824111938477,
"learning_rate": 4.522542485937369e-06,
"loss": 21.8787,
"step": 28
},
{
"epoch": 0.1710914454277286,
"grad_norm": 22.166667938232422,
"learning_rate": 4.470026884016805e-06,
"loss": 19.2404,
"step": 29
},
{
"epoch": 0.17699115044247787,
"grad_norm": 27.089574813842773,
"learning_rate": 4.415111107797445e-06,
"loss": 20.9614,
"step": 30
},
{
"epoch": 0.18289085545722714,
"grad_norm": 27.603740692138672,
"learning_rate": 4.357862063693486e-06,
"loss": 20.543,
"step": 31
},
{
"epoch": 0.1887905604719764,
"grad_norm": 26.96535873413086,
"learning_rate": 4.2983495008466285e-06,
"loss": 19.2133,
"step": 32
},
{
"epoch": 0.19469026548672566,
"grad_norm": 24.52537727355957,
"learning_rate": 4.236645926147493e-06,
"loss": 19.1972,
"step": 33
},
{
"epoch": 0.20058997050147492,
"grad_norm": 30.096757888793945,
"learning_rate": 4.172826515897146e-06,
"loss": 20.1775,
"step": 34
},
{
"epoch": 0.20648967551622419,
"grad_norm": 25.8487606048584,
"learning_rate": 4.106969024216348e-06,
"loss": 19.8463,
"step": 35
},
{
"epoch": 0.21238938053097345,
"grad_norm": 27.982152938842773,
"learning_rate": 4.039153688314146e-06,
"loss": 24.0711,
"step": 36
},
{
"epoch": 0.2182890855457227,
"grad_norm": 31.729448318481445,
"learning_rate": 3.969463130731183e-06,
"loss": 20.8358,
"step": 37
},
{
"epoch": 0.22418879056047197,
"grad_norm": 33.05440139770508,
"learning_rate": 3.897982258676867e-06,
"loss": 20.9184,
"step": 38
},
{
"epoch": 0.23008849557522124,
"grad_norm": 33.20439147949219,
"learning_rate": 3.824798160583012e-06,
"loss": 22.1186,
"step": 39
},
{
"epoch": 0.2359882005899705,
"grad_norm": 35.490440368652344,
"learning_rate": 3.7500000000000005e-06,
"loss": 22.7667,
"step": 40
},
{
"epoch": 0.24188790560471976,
"grad_norm": 36.88962173461914,
"learning_rate": 3.6736789069647273e-06,
"loss": 23.1779,
"step": 41
},
{
"epoch": 0.24778761061946902,
"grad_norm": 50.72957229614258,
"learning_rate": 3.595927866972694e-06,
"loss": 24.7407,
"step": 42
},
{
"epoch": 0.2536873156342183,
"grad_norm": 3.6904404163360596,
"learning_rate": 3.516841607689501e-06,
"loss": 10.9707,
"step": 43
},
{
"epoch": 0.25958702064896755,
"grad_norm": 5.453059196472168,
"learning_rate": 3.436516483539781e-06,
"loss": 13.0506,
"step": 44
},
{
"epoch": 0.26548672566371684,
"grad_norm": 4.847866535186768,
"learning_rate": 3.3550503583141726e-06,
"loss": 11.3953,
"step": 45
},
{
"epoch": 0.2713864306784661,
"grad_norm": 5.430877685546875,
"learning_rate": 3.272542485937369e-06,
"loss": 9.8737,
"step": 46
},
{
"epoch": 0.27728613569321536,
"grad_norm": 8.19796085357666,
"learning_rate": 3.189093389542498e-06,
"loss": 10.3856,
"step": 47
},
{
"epoch": 0.2831858407079646,
"grad_norm": 8.586030006408691,
"learning_rate": 3.1048047389991693e-06,
"loss": 11.5376,
"step": 48
},
{
"epoch": 0.2890855457227139,
"grad_norm": 8.650554656982422,
"learning_rate": 3.019779227044398e-06,
"loss": 11.1728,
"step": 49
},
{
"epoch": 0.2949852507374631,
"grad_norm": 11.194820404052734,
"learning_rate": 2.9341204441673267e-06,
"loss": 12.0976,
"step": 50
},
{
"epoch": 0.2949852507374631,
"eval_loss": 1.8799346685409546,
"eval_runtime": 32.683,
"eval_samples_per_second": 8.751,
"eval_steps_per_second": 2.203,
"step": 50
},
{
"epoch": 0.3008849557522124,
"grad_norm": 14.157112121582031,
"learning_rate": 2.847932752400164e-06,
"loss": 11.7297,
"step": 51
},
{
"epoch": 0.30678466076696165,
"grad_norm": 13.268279075622559,
"learning_rate": 2.761321158169134e-06,
"loss": 11.9854,
"step": 52
},
{
"epoch": 0.31268436578171094,
"grad_norm": 14.777017593383789,
"learning_rate": 2.6743911843603134e-06,
"loss": 11.6982,
"step": 53
},
{
"epoch": 0.3185840707964602,
"grad_norm": 15.651505470275879,
"learning_rate": 2.587248741756253e-06,
"loss": 12.7209,
"step": 54
},
{
"epoch": 0.32448377581120946,
"grad_norm": 16.862051010131836,
"learning_rate": 2.5e-06,
"loss": 12.7352,
"step": 55
},
{
"epoch": 0.3303834808259587,
"grad_norm": 16.122634887695312,
"learning_rate": 2.4127512582437486e-06,
"loss": 12.8166,
"step": 56
},
{
"epoch": 0.336283185840708,
"grad_norm": 20.204120635986328,
"learning_rate": 2.325608815639687e-06,
"loss": 13.0973,
"step": 57
},
{
"epoch": 0.3421828908554572,
"grad_norm": 15.840360641479492,
"learning_rate": 2.238678841830867e-06,
"loss": 13.2673,
"step": 58
},
{
"epoch": 0.3480825958702065,
"grad_norm": 27.855974197387695,
"learning_rate": 2.1520672475998374e-06,
"loss": 13.2521,
"step": 59
},
{
"epoch": 0.35398230088495575,
"grad_norm": 21.352693557739258,
"learning_rate": 2.0658795558326745e-06,
"loss": 13.3141,
"step": 60
},
{
"epoch": 0.35988200589970504,
"grad_norm": 24.652055740356445,
"learning_rate": 1.9802207729556023e-06,
"loss": 13.715,
"step": 61
},
{
"epoch": 0.36578171091445427,
"grad_norm": 24.22166633605957,
"learning_rate": 1.895195261000831e-06,
"loss": 12.7998,
"step": 62
},
{
"epoch": 0.37168141592920356,
"grad_norm": 22.723926544189453,
"learning_rate": 1.8109066104575023e-06,
"loss": 14.2915,
"step": 63
},
{
"epoch": 0.3775811209439528,
"grad_norm": 25.48423194885254,
"learning_rate": 1.7274575140626318e-06,
"loss": 13.0007,
"step": 64
},
{
"epoch": 0.3834808259587021,
"grad_norm": 23.430404663085938,
"learning_rate": 1.6449496416858285e-06,
"loss": 14.1499,
"step": 65
},
{
"epoch": 0.3893805309734513,
"grad_norm": 25.634765625,
"learning_rate": 1.56348351646022e-06,
"loss": 12.2943,
"step": 66
},
{
"epoch": 0.3952802359882006,
"grad_norm": 29.16959571838379,
"learning_rate": 1.4831583923105e-06,
"loss": 15.9917,
"step": 67
},
{
"epoch": 0.40117994100294985,
"grad_norm": 26.52433204650879,
"learning_rate": 1.4040721330273063e-06,
"loss": 13.1748,
"step": 68
},
{
"epoch": 0.40707964601769914,
"grad_norm": 23.716463088989258,
"learning_rate": 1.3263210930352737e-06,
"loss": 13.5076,
"step": 69
},
{
"epoch": 0.41297935103244837,
"grad_norm": 25.928203582763672,
"learning_rate": 1.2500000000000007e-06,
"loss": 13.0781,
"step": 70
},
{
"epoch": 0.41887905604719766,
"grad_norm": 25.973100662231445,
"learning_rate": 1.1752018394169882e-06,
"loss": 12.7629,
"step": 71
},
{
"epoch": 0.4247787610619469,
"grad_norm": 26.729578018188477,
"learning_rate": 1.1020177413231334e-06,
"loss": 13.0884,
"step": 72
},
{
"epoch": 0.4306784660766962,
"grad_norm": 28.534502029418945,
"learning_rate": 1.0305368692688175e-06,
"loss": 14.8765,
"step": 73
},
{
"epoch": 0.4365781710914454,
"grad_norm": 27.88771629333496,
"learning_rate": 9.608463116858544e-07,
"loss": 16.3264,
"step": 74
},
{
"epoch": 0.4424778761061947,
"grad_norm": 35.43700408935547,
"learning_rate": 8.930309757836517e-07,
"loss": 13.3003,
"step": 75
},
{
"epoch": 0.44837758112094395,
"grad_norm": 31.386333465576172,
"learning_rate": 8.271734841028553e-07,
"loss": 16.0848,
"step": 76
},
{
"epoch": 0.45427728613569324,
"grad_norm": 33.588722229003906,
"learning_rate": 7.633540738525066e-07,
"loss": 14.6917,
"step": 77
},
{
"epoch": 0.46017699115044247,
"grad_norm": 31.54501724243164,
"learning_rate": 7.016504991533727e-07,
"loss": 12.2341,
"step": 78
},
{
"epoch": 0.46607669616519176,
"grad_norm": 39.24992370605469,
"learning_rate": 6.421379363065142e-07,
"loss": 14.9348,
"step": 79
},
{
"epoch": 0.471976401179941,
"grad_norm": 38.33148193359375,
"learning_rate": 5.848888922025553e-07,
"loss": 11.4804,
"step": 80
},
{
"epoch": 0.4778761061946903,
"grad_norm": 39.474124908447266,
"learning_rate": 5.299731159831953e-07,
"loss": 12.2075,
"step": 81
},
{
"epoch": 0.4837758112094395,
"grad_norm": 40.61744689941406,
"learning_rate": 4.774575140626317e-07,
"loss": 15.4732,
"step": 82
},
{
"epoch": 0.4896755162241888,
"grad_norm": 43.01291275024414,
"learning_rate": 4.27406068612396e-07,
"loss": 13.508,
"step": 83
},
{
"epoch": 0.49557522123893805,
"grad_norm": 53.99359893798828,
"learning_rate": 3.798797596089351e-07,
"loss": 17.6752,
"step": 84
},
{
"epoch": 0.5014749262536873,
"grad_norm": 4.3658342361450195,
"learning_rate": 3.3493649053890325e-07,
"loss": 9.9121,
"step": 85
},
{
"epoch": 0.5073746312684366,
"grad_norm": 4.73631477355957,
"learning_rate": 2.9263101785268253e-07,
"loss": 12.0327,
"step": 86
},
{
"epoch": 0.5132743362831859,
"grad_norm": 5.241606712341309,
"learning_rate": 2.53014884252083e-07,
"loss": 10.5648,
"step": 87
},
{
"epoch": 0.5191740412979351,
"grad_norm": 6.079821586608887,
"learning_rate": 2.1613635589349756e-07,
"loss": 11.1205,
"step": 88
},
{
"epoch": 0.5250737463126843,
"grad_norm": 6.707623481750488,
"learning_rate": 1.8204036358303173e-07,
"loss": 9.6277,
"step": 89
},
{
"epoch": 0.5309734513274337,
"grad_norm": 7.61404275894165,
"learning_rate": 1.507684480352292e-07,
"loss": 7.6849,
"step": 90
},
{
"epoch": 0.5368731563421829,
"grad_norm": 9.975937843322754,
"learning_rate": 1.223587092621162e-07,
"loss": 10.2248,
"step": 91
},
{
"epoch": 0.5427728613569321,
"grad_norm": 11.2512845993042,
"learning_rate": 9.684576015420277e-08,
"loss": 9.7481,
"step": 92
},
{
"epoch": 0.5486725663716814,
"grad_norm": 12.412166595458984,
"learning_rate": 7.426068431000883e-08,
"loss": 9.6559,
"step": 93
},
{
"epoch": 0.5545722713864307,
"grad_norm": 13.59131145477295,
"learning_rate": 5.463099816548578e-08,
"loss": 10.219,
"step": 94
},
{
"epoch": 0.56047197640118,
"grad_norm": 12.337257385253906,
"learning_rate": 3.798061746947995e-08,
"loss": 10.9511,
"step": 95
},
{
"epoch": 0.5663716814159292,
"grad_norm": 14.506831169128418,
"learning_rate": 2.4329828146074096e-08,
"loss": 9.9813,
"step": 96
},
{
"epoch": 0.5722713864306784,
"grad_norm": 16.134977340698242,
"learning_rate": 1.3695261579316776e-08,
"loss": 10.8139,
"step": 97
},
{
"epoch": 0.5781710914454278,
"grad_norm": 16.2382755279541,
"learning_rate": 6.089874350439507e-09,
"loss": 11.4754,
"step": 98
},
{
"epoch": 0.584070796460177,
"grad_norm": 16.110279083251953,
"learning_rate": 1.5229324522605949e-09,
"loss": 10.8895,
"step": 99
},
{
"epoch": 0.5899705014749262,
"grad_norm": 19.847707748413086,
"learning_rate": 0.0,
"loss": 11.8983,
"step": 100
},
{
"epoch": 0.5899705014749262,
"eval_loss": 1.4722347259521484,
"eval_runtime": 32.6234,
"eval_samples_per_second": 8.767,
"eval_steps_per_second": 2.207,
"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": 2.5391158788096e+17,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}