jeqcho's picture
Upload folder using huggingface_hub
d4fa1fa verified
Raw
History Blame Contribute Delete
18.8 kB
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.6923076923076923,
"eval_steps": 500,
"global_step": 105,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.006593406593406593,
"grad_norm": 1.02959144115448,
"learning_rate": 0.0,
"loss": 3.3348,
"step": 1
},
{
"epoch": 0.013186813186813187,
"grad_norm": 1.0243064165115356,
"learning_rate": 4e-05,
"loss": 3.3843,
"step": 2
},
{
"epoch": 0.01978021978021978,
"grad_norm": 0.9533873796463013,
"learning_rate": 8e-05,
"loss": 3.1602,
"step": 3
},
{
"epoch": 0.026373626373626374,
"grad_norm": 1.3778162002563477,
"learning_rate": 0.00012,
"loss": 3.8548,
"step": 4
},
{
"epoch": 0.03296703296703297,
"grad_norm": 1.5720551013946533,
"learning_rate": 0.00016,
"loss": 3.334,
"step": 5
},
{
"epoch": 0.03956043956043956,
"grad_norm": 2.0702953338623047,
"learning_rate": 0.0002,
"loss": 3.2436,
"step": 6
},
{
"epoch": 0.046153846153846156,
"grad_norm": 1.883508563041687,
"learning_rate": 0.00019955654101995565,
"loss": 2.4118,
"step": 7
},
{
"epoch": 0.05274725274725275,
"grad_norm": 1.8991221189498901,
"learning_rate": 0.00019911308203991133,
"loss": 1.7996,
"step": 8
},
{
"epoch": 0.05934065934065934,
"grad_norm": 1.943290114402771,
"learning_rate": 0.00019866962305986697,
"loss": 1.7992,
"step": 9
},
{
"epoch": 0.06593406593406594,
"grad_norm": 1.1848249435424805,
"learning_rate": 0.00019822616407982261,
"loss": 1.3218,
"step": 10
},
{
"epoch": 0.07252747252747253,
"grad_norm": 0.8290153741836548,
"learning_rate": 0.00019778270509977829,
"loss": 1.1483,
"step": 11
},
{
"epoch": 0.07912087912087912,
"grad_norm": 0.782597541809082,
"learning_rate": 0.00019733924611973393,
"loss": 1.1466,
"step": 12
},
{
"epoch": 0.08571428571428572,
"grad_norm": 1.070041537284851,
"learning_rate": 0.0001968957871396896,
"loss": 1.0435,
"step": 13
},
{
"epoch": 0.09230769230769231,
"grad_norm": 0.7890101671218872,
"learning_rate": 0.00019645232815964525,
"loss": 1.1189,
"step": 14
},
{
"epoch": 0.0989010989010989,
"grad_norm": 0.6797720789909363,
"learning_rate": 0.00019600886917960092,
"loss": 0.9294,
"step": 15
},
{
"epoch": 0.1054945054945055,
"grad_norm": 0.6561483144760132,
"learning_rate": 0.00019556541019955653,
"loss": 0.8717,
"step": 16
},
{
"epoch": 0.11208791208791209,
"grad_norm": 0.6154541969299316,
"learning_rate": 0.0001951219512195122,
"loss": 0.9475,
"step": 17
},
{
"epoch": 0.11868131868131868,
"grad_norm": 0.6936250925064087,
"learning_rate": 0.00019467849223946785,
"loss": 1.1112,
"step": 18
},
{
"epoch": 0.12527472527472527,
"grad_norm": 0.4830031096935272,
"learning_rate": 0.00019423503325942352,
"loss": 0.8719,
"step": 19
},
{
"epoch": 0.13186813186813187,
"grad_norm": 0.4977757930755615,
"learning_rate": 0.00019379157427937917,
"loss": 0.8456,
"step": 20
},
{
"epoch": 0.13846153846153847,
"grad_norm": 0.4251507520675659,
"learning_rate": 0.00019334811529933484,
"loss": 0.7946,
"step": 21
},
{
"epoch": 0.14505494505494507,
"grad_norm": 0.5000141263008118,
"learning_rate": 0.00019290465631929045,
"loss": 0.9003,
"step": 22
},
{
"epoch": 0.15164835164835164,
"grad_norm": 0.5055630803108215,
"learning_rate": 0.00019246119733924613,
"loss": 0.8483,
"step": 23
},
{
"epoch": 0.15824175824175823,
"grad_norm": 0.5189692378044128,
"learning_rate": 0.00019201773835920177,
"loss": 0.862,
"step": 24
},
{
"epoch": 0.16483516483516483,
"grad_norm": 0.39381036162376404,
"learning_rate": 0.00019157427937915744,
"loss": 0.73,
"step": 25
},
{
"epoch": 0.17142857142857143,
"grad_norm": 0.4727248549461365,
"learning_rate": 0.00019113082039911309,
"loss": 0.9574,
"step": 26
},
{
"epoch": 0.17802197802197803,
"grad_norm": 0.5471789836883545,
"learning_rate": 0.00019068736141906876,
"loss": 0.8291,
"step": 27
},
{
"epoch": 0.18461538461538463,
"grad_norm": 0.4908490777015686,
"learning_rate": 0.0001902439024390244,
"loss": 0.7855,
"step": 28
},
{
"epoch": 0.1912087912087912,
"grad_norm": 0.5352988243103027,
"learning_rate": 0.00018980044345898005,
"loss": 0.8019,
"step": 29
},
{
"epoch": 0.1978021978021978,
"grad_norm": 0.4222325384616852,
"learning_rate": 0.00018935698447893572,
"loss": 0.7782,
"step": 30
},
{
"epoch": 0.2043956043956044,
"grad_norm": 0.5250545740127563,
"learning_rate": 0.00018891352549889136,
"loss": 0.827,
"step": 31
},
{
"epoch": 0.210989010989011,
"grad_norm": 0.5112847685813904,
"learning_rate": 0.00018847006651884703,
"loss": 0.7717,
"step": 32
},
{
"epoch": 0.2175824175824176,
"grad_norm": 0.45085787773132324,
"learning_rate": 0.00018802660753880268,
"loss": 0.8548,
"step": 33
},
{
"epoch": 0.22417582417582418,
"grad_norm": 0.5169785618782043,
"learning_rate": 0.00018758314855875832,
"loss": 0.8469,
"step": 34
},
{
"epoch": 0.23076923076923078,
"grad_norm": 0.4831181466579437,
"learning_rate": 0.00018713968957871397,
"loss": 0.7138,
"step": 35
},
{
"epoch": 0.23736263736263735,
"grad_norm": 0.4298362731933594,
"learning_rate": 0.00018669623059866964,
"loss": 0.6416,
"step": 36
},
{
"epoch": 0.24395604395604395,
"grad_norm": 0.4677696228027344,
"learning_rate": 0.00018625277161862528,
"loss": 0.8296,
"step": 37
},
{
"epoch": 0.25054945054945055,
"grad_norm": 0.4513629376888275,
"learning_rate": 0.00018580931263858095,
"loss": 0.6803,
"step": 38
},
{
"epoch": 0.2571428571428571,
"grad_norm": 0.4796628952026367,
"learning_rate": 0.0001853658536585366,
"loss": 0.7778,
"step": 39
},
{
"epoch": 0.26373626373626374,
"grad_norm": 0.4168303906917572,
"learning_rate": 0.00018492239467849224,
"loss": 0.748,
"step": 40
},
{
"epoch": 0.2703296703296703,
"grad_norm": 0.3913823962211609,
"learning_rate": 0.0001844789356984479,
"loss": 0.8508,
"step": 41
},
{
"epoch": 0.27692307692307694,
"grad_norm": 0.46302542090415955,
"learning_rate": 0.00018403547671840356,
"loss": 0.86,
"step": 42
},
{
"epoch": 0.2835164835164835,
"grad_norm": 0.43823087215423584,
"learning_rate": 0.0001835920177383592,
"loss": 0.7062,
"step": 43
},
{
"epoch": 0.29010989010989013,
"grad_norm": 0.4874539375305176,
"learning_rate": 0.00018314855875831487,
"loss": 0.7632,
"step": 44
},
{
"epoch": 0.2967032967032967,
"grad_norm": 0.44593605399131775,
"learning_rate": 0.00018270509977827052,
"loss": 0.8815,
"step": 45
},
{
"epoch": 0.3032967032967033,
"grad_norm": 0.4195469915866852,
"learning_rate": 0.00018226164079822616,
"loss": 0.7796,
"step": 46
},
{
"epoch": 0.3098901098901099,
"grad_norm": 0.40345215797424316,
"learning_rate": 0.00018181818181818183,
"loss": 0.6468,
"step": 47
},
{
"epoch": 0.31648351648351647,
"grad_norm": 0.4226957857608795,
"learning_rate": 0.00018137472283813748,
"loss": 0.6274,
"step": 48
},
{
"epoch": 0.3230769230769231,
"grad_norm": 0.477471262216568,
"learning_rate": 0.00018093126385809312,
"loss": 0.7629,
"step": 49
},
{
"epoch": 0.32967032967032966,
"grad_norm": 0.39429357647895813,
"learning_rate": 0.0001804878048780488,
"loss": 0.6709,
"step": 50
},
{
"epoch": 0.3362637362637363,
"grad_norm": 0.4581214189529419,
"learning_rate": 0.00018004434589800444,
"loss": 0.7036,
"step": 51
},
{
"epoch": 0.34285714285714286,
"grad_norm": 0.4935621917247772,
"learning_rate": 0.00017960088691796008,
"loss": 0.6878,
"step": 52
},
{
"epoch": 0.34945054945054943,
"grad_norm": 0.45704221725463867,
"learning_rate": 0.00017915742793791575,
"loss": 0.7126,
"step": 53
},
{
"epoch": 0.35604395604395606,
"grad_norm": 0.4570856988430023,
"learning_rate": 0.0001787139689578714,
"loss": 0.7569,
"step": 54
},
{
"epoch": 0.3626373626373626,
"grad_norm": 0.4568769037723541,
"learning_rate": 0.00017827050997782707,
"loss": 0.7162,
"step": 55
},
{
"epoch": 0.36923076923076925,
"grad_norm": 0.4904540181159973,
"learning_rate": 0.00017782705099778271,
"loss": 0.7308,
"step": 56
},
{
"epoch": 0.3758241758241758,
"grad_norm": 0.4313798248767853,
"learning_rate": 0.00017738359201773839,
"loss": 0.635,
"step": 57
},
{
"epoch": 0.3824175824175824,
"grad_norm": 0.5561969876289368,
"learning_rate": 0.000176940133037694,
"loss": 0.7838,
"step": 58
},
{
"epoch": 0.389010989010989,
"grad_norm": 0.44863128662109375,
"learning_rate": 0.00017649667405764967,
"loss": 0.6366,
"step": 59
},
{
"epoch": 0.3956043956043956,
"grad_norm": 0.4197455048561096,
"learning_rate": 0.00017605321507760532,
"loss": 0.7589,
"step": 60
},
{
"epoch": 0.4021978021978022,
"grad_norm": 0.4661950170993805,
"learning_rate": 0.000175609756097561,
"loss": 0.725,
"step": 61
},
{
"epoch": 0.4087912087912088,
"grad_norm": 0.46837183833122253,
"learning_rate": 0.00017516629711751663,
"loss": 0.64,
"step": 62
},
{
"epoch": 0.4153846153846154,
"grad_norm": 0.5886682868003845,
"learning_rate": 0.0001747228381374723,
"loss": 0.5071,
"step": 63
},
{
"epoch": 0.421978021978022,
"grad_norm": 0.5030215978622437,
"learning_rate": 0.00017427937915742792,
"loss": 0.692,
"step": 64
},
{
"epoch": 0.42857142857142855,
"grad_norm": 0.5501147508621216,
"learning_rate": 0.0001738359201773836,
"loss": 0.8112,
"step": 65
},
{
"epoch": 0.4351648351648352,
"grad_norm": 0.4744016230106354,
"learning_rate": 0.00017339246119733924,
"loss": 0.6571,
"step": 66
},
{
"epoch": 0.44175824175824174,
"grad_norm": 0.4610467553138733,
"learning_rate": 0.0001729490022172949,
"loss": 0.6737,
"step": 67
},
{
"epoch": 0.44835164835164837,
"grad_norm": 0.495379239320755,
"learning_rate": 0.00017250554323725056,
"loss": 0.7577,
"step": 68
},
{
"epoch": 0.45494505494505494,
"grad_norm": 0.4832289516925812,
"learning_rate": 0.00017206208425720623,
"loss": 0.6387,
"step": 69
},
{
"epoch": 0.46153846153846156,
"grad_norm": 0.5150049924850464,
"learning_rate": 0.00017161862527716187,
"loss": 0.8346,
"step": 70
},
{
"epoch": 0.46813186813186813,
"grad_norm": 0.4854123294353485,
"learning_rate": 0.00017117516629711752,
"loss": 0.6864,
"step": 71
},
{
"epoch": 0.4747252747252747,
"grad_norm": 0.45552781224250793,
"learning_rate": 0.0001707317073170732,
"loss": 0.6789,
"step": 72
},
{
"epoch": 0.48131868131868133,
"grad_norm": 0.4643484652042389,
"learning_rate": 0.00017028824833702883,
"loss": 0.6516,
"step": 73
},
{
"epoch": 0.4879120879120879,
"grad_norm": 0.4445684254169464,
"learning_rate": 0.0001698447893569845,
"loss": 0.6762,
"step": 74
},
{
"epoch": 0.4945054945054945,
"grad_norm": 0.5563467741012573,
"learning_rate": 0.00016940133037694015,
"loss": 0.7624,
"step": 75
},
{
"epoch": 0.5010989010989011,
"grad_norm": 0.4668287932872772,
"learning_rate": 0.00016895787139689582,
"loss": 0.5379,
"step": 76
},
{
"epoch": 0.5076923076923077,
"grad_norm": 0.424448698759079,
"learning_rate": 0.00016851441241685144,
"loss": 0.6594,
"step": 77
},
{
"epoch": 0.5142857142857142,
"grad_norm": 0.47027847170829773,
"learning_rate": 0.0001680709534368071,
"loss": 0.6288,
"step": 78
},
{
"epoch": 0.5208791208791209,
"grad_norm": 0.4704686403274536,
"learning_rate": 0.00016762749445676275,
"loss": 0.7025,
"step": 79
},
{
"epoch": 0.5274725274725275,
"grad_norm": 0.5712776184082031,
"learning_rate": 0.00016718403547671842,
"loss": 0.6923,
"step": 80
},
{
"epoch": 0.5340659340659341,
"grad_norm": 0.5098185539245605,
"learning_rate": 0.00016674057649667407,
"loss": 0.6952,
"step": 81
},
{
"epoch": 0.5406593406593406,
"grad_norm": 0.5409852266311646,
"learning_rate": 0.00016629711751662974,
"loss": 0.6023,
"step": 82
},
{
"epoch": 0.5472527472527473,
"grad_norm": 0.6706210374832153,
"learning_rate": 0.00016585365853658536,
"loss": 0.713,
"step": 83
},
{
"epoch": 0.5538461538461539,
"grad_norm": 0.34992656111717224,
"learning_rate": 0.00016541019955654103,
"loss": 0.7375,
"step": 84
},
{
"epoch": 0.5604395604395604,
"grad_norm": 0.6524062156677246,
"learning_rate": 0.00016496674057649667,
"loss": 0.739,
"step": 85
},
{
"epoch": 0.567032967032967,
"grad_norm": 0.5203568935394287,
"learning_rate": 0.00016452328159645234,
"loss": 0.7482,
"step": 86
},
{
"epoch": 0.5736263736263736,
"grad_norm": 0.6416592597961426,
"learning_rate": 0.000164079822616408,
"loss": 0.7033,
"step": 87
},
{
"epoch": 0.5802197802197803,
"grad_norm": 0.4666348695755005,
"learning_rate": 0.00016363636363636366,
"loss": 0.6811,
"step": 88
},
{
"epoch": 0.5868131868131868,
"grad_norm": 0.6599462628364563,
"learning_rate": 0.0001631929046563193,
"loss": 0.7908,
"step": 89
},
{
"epoch": 0.5934065934065934,
"grad_norm": 0.551964521408081,
"learning_rate": 0.00016274944567627495,
"loss": 0.6226,
"step": 90
},
{
"epoch": 0.6,
"grad_norm": 0.429592490196228,
"learning_rate": 0.0001623059866962306,
"loss": 0.6602,
"step": 91
},
{
"epoch": 0.6065934065934065,
"grad_norm": 0.5001062750816345,
"learning_rate": 0.00016186252771618626,
"loss": 0.6884,
"step": 92
},
{
"epoch": 0.6131868131868132,
"grad_norm": 0.4265173375606537,
"learning_rate": 0.0001614190687361419,
"loss": 0.6613,
"step": 93
},
{
"epoch": 0.6197802197802198,
"grad_norm": 0.4387926757335663,
"learning_rate": 0.00016097560975609758,
"loss": 0.6829,
"step": 94
},
{
"epoch": 0.6263736263736264,
"grad_norm": 0.5375656485557556,
"learning_rate": 0.00016053215077605322,
"loss": 0.6584,
"step": 95
},
{
"epoch": 0.6329670329670329,
"grad_norm": 0.511247992515564,
"learning_rate": 0.00016008869179600887,
"loss": 0.6725,
"step": 96
},
{
"epoch": 0.6395604395604395,
"grad_norm": 0.49439311027526855,
"learning_rate": 0.00015964523281596454,
"loss": 0.7958,
"step": 97
},
{
"epoch": 0.6461538461538462,
"grad_norm": 0.521442174911499,
"learning_rate": 0.00015920177383592018,
"loss": 0.6591,
"step": 98
},
{
"epoch": 0.6527472527472528,
"grad_norm": 0.5001063942909241,
"learning_rate": 0.00015875831485587586,
"loss": 0.7915,
"step": 99
},
{
"epoch": 0.6593406593406593,
"grad_norm": 0.741524338722229,
"learning_rate": 0.0001583148558758315,
"loss": 0.6201,
"step": 100
},
{
"epoch": 0.6659340659340659,
"grad_norm": 0.49745646119117737,
"learning_rate": 0.00015787139689578714,
"loss": 0.915,
"step": 101
},
{
"epoch": 0.6725274725274726,
"grad_norm": 0.5976807475090027,
"learning_rate": 0.0001574279379157428,
"loss": 0.7476,
"step": 102
},
{
"epoch": 0.6791208791208792,
"grad_norm": 0.47543030977249146,
"learning_rate": 0.00015698447893569846,
"loss": 0.8067,
"step": 103
},
{
"epoch": 0.6857142857142857,
"grad_norm": 0.5175777673721313,
"learning_rate": 0.0001565410199556541,
"loss": 0.618,
"step": 104
},
{
"epoch": 0.6923076923076923,
"grad_norm": 0.5875190496444702,
"learning_rate": 0.00015609756097560978,
"loss": 0.6178,
"step": 105
}
],
"logging_steps": 1,
"max_steps": 456,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"save_steps": 15,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 4.217460027385651e+16,
"train_batch_size": 22,
"trial_name": null,
"trial_params": null
}