pakawadeep's picture
Training in progress, step 100, checkpoint
16cf945 verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.10982976386600769,
"eval_steps": 1000,
"global_step": 100,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"grad_norm": 11.704396157183714,
"learning_rate": 0.0,
"loss": 2.6917,
"step": 1
},
{
"epoch": 0.0,
"grad_norm": 14.261265634920543,
"learning_rate": 6.020599913279623e-05,
"loss": 2.0455,
"step": 2
},
{
"epoch": 0.0,
"grad_norm": 9.252464584699219,
"learning_rate": 9.542425094393248e-05,
"loss": 2.1024,
"step": 3
},
{
"epoch": 0.0,
"grad_norm": 7.478072090774749,
"learning_rate": 0.00012041199826559246,
"loss": 1.9419,
"step": 4
},
{
"epoch": 0.01,
"grad_norm": 6.996421444202911,
"learning_rate": 0.00013979400086720374,
"loss": 1.2142,
"step": 5
},
{
"epoch": 0.01,
"grad_norm": 9.62925923224712,
"learning_rate": 0.00015563025007672872,
"loss": 1.4192,
"step": 6
},
{
"epoch": 0.01,
"grad_norm": 5.9971192119861545,
"learning_rate": 0.00016901960800285134,
"loss": 1.1698,
"step": 7
},
{
"epoch": 0.01,
"grad_norm": 15.448410811680446,
"learning_rate": 0.00018061799739838867,
"loss": 1.0663,
"step": 8
},
{
"epoch": 0.01,
"grad_norm": 6.664012698560983,
"learning_rate": 0.00019084850188786495,
"loss": 1.0346,
"step": 9
},
{
"epoch": 0.01,
"grad_norm": 5.9872198688383325,
"learning_rate": 0.00019999999999999998,
"loss": 1.2899,
"step": 10
},
{
"epoch": 0.01,
"grad_norm": 5.492858411635369,
"learning_rate": 0.0002,
"loss": 0.733,
"step": 11
},
{
"epoch": 0.01,
"grad_norm": 4.117272508239465,
"learning_rate": 0.00019931271477663232,
"loss": 0.7529,
"step": 12
},
{
"epoch": 0.01,
"grad_norm": 4.57016142244955,
"learning_rate": 0.0001986254295532646,
"loss": 0.9221,
"step": 13
},
{
"epoch": 0.02,
"grad_norm": 5.106703686957636,
"learning_rate": 0.00019793814432989693,
"loss": 1.1292,
"step": 14
},
{
"epoch": 0.02,
"grad_norm": 4.4331559960790115,
"learning_rate": 0.00019725085910652924,
"loss": 0.9505,
"step": 15
},
{
"epoch": 0.02,
"grad_norm": 4.871898936371301,
"learning_rate": 0.0001965635738831615,
"loss": 1.0894,
"step": 16
},
{
"epoch": 0.02,
"grad_norm": 5.546128257668831,
"learning_rate": 0.00019587628865979381,
"loss": 1.0915,
"step": 17
},
{
"epoch": 0.02,
"grad_norm": 5.426135233570764,
"learning_rate": 0.00019518900343642613,
"loss": 1.2174,
"step": 18
},
{
"epoch": 0.02,
"grad_norm": 3.7481567939197316,
"learning_rate": 0.00019450171821305842,
"loss": 0.8281,
"step": 19
},
{
"epoch": 0.02,
"grad_norm": 6.264747615275931,
"learning_rate": 0.00019381443298969073,
"loss": 1.1069,
"step": 20
},
{
"epoch": 0.02,
"grad_norm": 4.850720515264914,
"learning_rate": 0.00019312714776632305,
"loss": 1.1216,
"step": 21
},
{
"epoch": 0.02,
"grad_norm": 4.583277384098615,
"learning_rate": 0.00019243986254295533,
"loss": 1.0751,
"step": 22
},
{
"epoch": 0.03,
"grad_norm": 4.923174586611154,
"learning_rate": 0.00019175257731958765,
"loss": 1.1915,
"step": 23
},
{
"epoch": 0.03,
"grad_norm": 4.21422328394722,
"learning_rate": 0.00019106529209621996,
"loss": 1.1412,
"step": 24
},
{
"epoch": 0.03,
"grad_norm": 3.9312652393524803,
"learning_rate": 0.00019037800687285222,
"loss": 0.9699,
"step": 25
},
{
"epoch": 0.03,
"grad_norm": 4.511161102577495,
"learning_rate": 0.00018969072164948454,
"loss": 1.1289,
"step": 26
},
{
"epoch": 0.03,
"grad_norm": 3.9233152624949454,
"learning_rate": 0.00018900343642611685,
"loss": 0.8803,
"step": 27
},
{
"epoch": 0.03,
"grad_norm": 5.413459689226915,
"learning_rate": 0.00018831615120274914,
"loss": 1.0594,
"step": 28
},
{
"epoch": 0.03,
"grad_norm": 4.2106489602848685,
"learning_rate": 0.00018762886597938145,
"loss": 1.1003,
"step": 29
},
{
"epoch": 0.03,
"grad_norm": 4.568263346040736,
"learning_rate": 0.00018694158075601377,
"loss": 1.0816,
"step": 30
},
{
"epoch": 0.03,
"grad_norm": 3.12202434010765,
"learning_rate": 0.00018625429553264605,
"loss": 0.9053,
"step": 31
},
{
"epoch": 0.04,
"grad_norm": 4.282623293516478,
"learning_rate": 0.00018556701030927837,
"loss": 1.206,
"step": 32
},
{
"epoch": 0.04,
"grad_norm": 6.45030819651884,
"learning_rate": 0.00018487972508591068,
"loss": 0.9049,
"step": 33
},
{
"epoch": 0.04,
"grad_norm": 4.871975082534186,
"learning_rate": 0.00018419243986254294,
"loss": 1.1436,
"step": 34
},
{
"epoch": 0.04,
"grad_norm": 4.715014058776802,
"learning_rate": 0.00018350515463917526,
"loss": 1.3847,
"step": 35
},
{
"epoch": 0.04,
"grad_norm": 3.3808462582338707,
"learning_rate": 0.00018281786941580757,
"loss": 0.7817,
"step": 36
},
{
"epoch": 0.04,
"grad_norm": 3.8976964456454866,
"learning_rate": 0.00018213058419243986,
"loss": 1.0001,
"step": 37
},
{
"epoch": 0.04,
"grad_norm": 5.355867444757705,
"learning_rate": 0.00018144329896907217,
"loss": 0.9259,
"step": 38
},
{
"epoch": 0.04,
"grad_norm": 5.178991855035252,
"learning_rate": 0.0001807560137457045,
"loss": 0.794,
"step": 39
},
{
"epoch": 0.04,
"grad_norm": 4.14441205427679,
"learning_rate": 0.00018006872852233677,
"loss": 1.0384,
"step": 40
},
{
"epoch": 0.05,
"grad_norm": 3.7176836552561974,
"learning_rate": 0.0001793814432989691,
"loss": 0.75,
"step": 41
},
{
"epoch": 0.05,
"grad_norm": 5.011588210132538,
"learning_rate": 0.0001786941580756014,
"loss": 1.3034,
"step": 42
},
{
"epoch": 0.05,
"grad_norm": 5.111725152950483,
"learning_rate": 0.00017800687285223366,
"loss": 1.3023,
"step": 43
},
{
"epoch": 0.05,
"grad_norm": 4.021959822322685,
"learning_rate": 0.00017731958762886598,
"loss": 0.9624,
"step": 44
},
{
"epoch": 0.05,
"grad_norm": 2.943541786297702,
"learning_rate": 0.0001766323024054983,
"loss": 0.6659,
"step": 45
},
{
"epoch": 0.05,
"grad_norm": 4.534002060279327,
"learning_rate": 0.00017594501718213058,
"loss": 1.1354,
"step": 46
},
{
"epoch": 0.05,
"grad_norm": 5.108426720583385,
"learning_rate": 0.0001752577319587629,
"loss": 1.4258,
"step": 47
},
{
"epoch": 0.05,
"grad_norm": 7.235810963301271,
"learning_rate": 0.0001745704467353952,
"loss": 1.3918,
"step": 48
},
{
"epoch": 0.05,
"grad_norm": 4.207791712185817,
"learning_rate": 0.0001738831615120275,
"loss": 1.2796,
"step": 49
},
{
"epoch": 0.05,
"grad_norm": 4.050243728273998,
"learning_rate": 0.0001731958762886598,
"loss": 1.244,
"step": 50
},
{
"epoch": 0.06,
"grad_norm": 4.657182228931627,
"learning_rate": 0.00017250859106529212,
"loss": 1.2068,
"step": 51
},
{
"epoch": 0.06,
"grad_norm": 3.5652582299228643,
"learning_rate": 0.00017182130584192438,
"loss": 0.8897,
"step": 52
},
{
"epoch": 0.06,
"grad_norm": 4.529701968193304,
"learning_rate": 0.0001711340206185567,
"loss": 1.1582,
"step": 53
},
{
"epoch": 0.06,
"grad_norm": 4.49586529984068,
"learning_rate": 0.000170446735395189,
"loss": 1.1379,
"step": 54
},
{
"epoch": 0.06,
"grad_norm": 5.845994813972232,
"learning_rate": 0.0001697594501718213,
"loss": 1.4724,
"step": 55
},
{
"epoch": 0.06,
"grad_norm": 4.732950229095352,
"learning_rate": 0.00016907216494845361,
"loss": 0.886,
"step": 56
},
{
"epoch": 0.06,
"grad_norm": 3.8567901480339426,
"learning_rate": 0.00016838487972508593,
"loss": 0.7763,
"step": 57
},
{
"epoch": 0.06,
"grad_norm": 4.931804800794497,
"learning_rate": 0.00016769759450171822,
"loss": 1.1761,
"step": 58
},
{
"epoch": 0.06,
"grad_norm": 3.7294788904744625,
"learning_rate": 0.00016701030927835053,
"loss": 0.6722,
"step": 59
},
{
"epoch": 0.07,
"grad_norm": 3.688890615204965,
"learning_rate": 0.00016632302405498285,
"loss": 0.9642,
"step": 60
},
{
"epoch": 0.07,
"grad_norm": 4.022317141495382,
"learning_rate": 0.00016563573883161513,
"loss": 0.8865,
"step": 61
},
{
"epoch": 0.07,
"grad_norm": 6.55573614414137,
"learning_rate": 0.00016494845360824742,
"loss": 1.217,
"step": 62
},
{
"epoch": 0.07,
"grad_norm": 4.5890564068710615,
"learning_rate": 0.00016426116838487973,
"loss": 1.0791,
"step": 63
},
{
"epoch": 0.07,
"grad_norm": 5.435288078022071,
"learning_rate": 0.00016357388316151202,
"loss": 1.1501,
"step": 64
},
{
"epoch": 0.07,
"grad_norm": 4.965664463354534,
"learning_rate": 0.00016288659793814434,
"loss": 1.4109,
"step": 65
},
{
"epoch": 0.07,
"grad_norm": 7.483997056692371,
"learning_rate": 0.00016219931271477665,
"loss": 1.0735,
"step": 66
},
{
"epoch": 0.07,
"grad_norm": 4.9923544603584915,
"learning_rate": 0.00016151202749140894,
"loss": 0.9927,
"step": 67
},
{
"epoch": 0.07,
"grad_norm": 5.143678077389599,
"learning_rate": 0.00016082474226804125,
"loss": 1.1299,
"step": 68
},
{
"epoch": 0.08,
"grad_norm": 4.420855401236021,
"learning_rate": 0.00016013745704467357,
"loss": 1.0263,
"step": 69
},
{
"epoch": 0.08,
"grad_norm": 5.02485050719212,
"learning_rate": 0.00015945017182130585,
"loss": 1.1168,
"step": 70
},
{
"epoch": 0.08,
"grad_norm": 4.524608717382107,
"learning_rate": 0.00015876288659793814,
"loss": 1.1015,
"step": 71
},
{
"epoch": 0.08,
"grad_norm": 3.9028726855074054,
"learning_rate": 0.00015807560137457046,
"loss": 1.091,
"step": 72
},
{
"epoch": 0.08,
"grad_norm": 3.271315148375007,
"learning_rate": 0.00015738831615120274,
"loss": 0.9397,
"step": 73
},
{
"epoch": 0.08,
"grad_norm": 4.5227145076761515,
"learning_rate": 0.00015670103092783506,
"loss": 1.0062,
"step": 74
},
{
"epoch": 0.08,
"grad_norm": 3.344752651586208,
"learning_rate": 0.00015601374570446737,
"loss": 1.0027,
"step": 75
},
{
"epoch": 0.08,
"grad_norm": 4.102353206893142,
"learning_rate": 0.00015532646048109966,
"loss": 1.3915,
"step": 76
},
{
"epoch": 0.08,
"grad_norm": 4.722343844673861,
"learning_rate": 0.00015463917525773197,
"loss": 1.1678,
"step": 77
},
{
"epoch": 0.09,
"grad_norm": 6.017428516681286,
"learning_rate": 0.0001539518900343643,
"loss": 1.329,
"step": 78
},
{
"epoch": 0.09,
"grad_norm": 3.7313811619387516,
"learning_rate": 0.00015326460481099657,
"loss": 0.887,
"step": 79
},
{
"epoch": 0.09,
"grad_norm": 3.7179924970759406,
"learning_rate": 0.00015257731958762886,
"loss": 1.0153,
"step": 80
},
{
"epoch": 0.09,
"grad_norm": 4.499981774187266,
"learning_rate": 0.00015189003436426118,
"loss": 1.3911,
"step": 81
},
{
"epoch": 0.09,
"grad_norm": 5.955286629774712,
"learning_rate": 0.00015120274914089346,
"loss": 1.215,
"step": 82
},
{
"epoch": 0.09,
"grad_norm": 3.5953610996772984,
"learning_rate": 0.00015051546391752578,
"loss": 0.9343,
"step": 83
},
{
"epoch": 0.09,
"grad_norm": 3.8040779769157687,
"learning_rate": 0.0001498281786941581,
"loss": 1.062,
"step": 84
},
{
"epoch": 0.09,
"grad_norm": 5.755142565965664,
"learning_rate": 0.00014914089347079038,
"loss": 1.2539,
"step": 85
},
{
"epoch": 0.09,
"grad_norm": 3.7550494212874264,
"learning_rate": 0.0001484536082474227,
"loss": 0.8594,
"step": 86
},
{
"epoch": 0.1,
"grad_norm": 6.7330159455584635,
"learning_rate": 0.000147766323024055,
"loss": 0.9157,
"step": 87
},
{
"epoch": 0.1,
"grad_norm": 4.438479463179745,
"learning_rate": 0.0001470790378006873,
"loss": 1.1235,
"step": 88
},
{
"epoch": 0.1,
"grad_norm": 3.87421384650703,
"learning_rate": 0.00014639175257731958,
"loss": 0.9763,
"step": 89
},
{
"epoch": 0.1,
"grad_norm": 2.4000323333151683,
"learning_rate": 0.0001457044673539519,
"loss": 0.5867,
"step": 90
},
{
"epoch": 0.1,
"grad_norm": 5.866412115354472,
"learning_rate": 0.00014501718213058418,
"loss": 1.5134,
"step": 91
},
{
"epoch": 0.1,
"grad_norm": 3.023945137404242,
"learning_rate": 0.0001443298969072165,
"loss": 0.7887,
"step": 92
},
{
"epoch": 0.1,
"grad_norm": 3.7174822786238435,
"learning_rate": 0.00014364261168384881,
"loss": 0.925,
"step": 93
},
{
"epoch": 0.1,
"grad_norm": 4.007705895268358,
"learning_rate": 0.0001429553264604811,
"loss": 0.9114,
"step": 94
},
{
"epoch": 0.1,
"grad_norm": 3.852559484855566,
"learning_rate": 0.00014226804123711342,
"loss": 1.2322,
"step": 95
},
{
"epoch": 0.11,
"grad_norm": 3.9331976985714006,
"learning_rate": 0.00014158075601374573,
"loss": 1.021,
"step": 96
},
{
"epoch": 0.11,
"grad_norm": 3.7472774795317676,
"learning_rate": 0.00014089347079037802,
"loss": 0.9222,
"step": 97
},
{
"epoch": 0.11,
"grad_norm": 5.430655545449399,
"learning_rate": 0.0001402061855670103,
"loss": 1.0648,
"step": 98
},
{
"epoch": 0.11,
"grad_norm": 3.8259440534841365,
"learning_rate": 0.00013951890034364262,
"loss": 0.9769,
"step": 99
},
{
"epoch": 0.11,
"grad_norm": 4.784794509604932,
"learning_rate": 0.0001388316151202749,
"loss": 1.0134,
"step": 100
}
],
"logging_steps": 1,
"max_steps": 301,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 25,
"total_flos": 1192784269148160.0,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}