pythia-exp / trainer_state.json
TinyPixel's picture
Upload folder using huggingface_hub
49c5b19
raw
history blame
12.5 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 2.9972041006523766,
"eval_steps": 500,
"global_step": 201,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.03,
"learning_rate": 5.714285714285714e-05,
"loss": 2.8134,
"step": 2
},
{
"epoch": 0.06,
"learning_rate": 0.00011428571428571428,
"loss": 2.4355,
"step": 4
},
{
"epoch": 0.09,
"learning_rate": 0.00017142857142857143,
"loss": 2.0049,
"step": 6
},
{
"epoch": 0.12,
"learning_rate": 0.00019998688836656323,
"loss": 1.9945,
"step": 8
},
{
"epoch": 0.15,
"learning_rate": 0.0001998820159279591,
"loss": 1.7738,
"step": 10
},
{
"epoch": 0.18,
"learning_rate": 0.00019967238104745696,
"loss": 2.0186,
"step": 12
},
{
"epoch": 0.21,
"learning_rate": 0.00019935820360309777,
"loss": 2.0048,
"step": 14
},
{
"epoch": 0.24,
"learning_rate": 0.00019893981312363562,
"loss": 1.9983,
"step": 16
},
{
"epoch": 0.27,
"learning_rate": 0.00019841764844290744,
"loss": 2.5312,
"step": 18
},
{
"epoch": 0.3,
"learning_rate": 0.00019779225723955707,
"loss": 1.7662,
"step": 20
},
{
"epoch": 0.33,
"learning_rate": 0.00019706429546259593,
"loss": 1.8439,
"step": 22
},
{
"epoch": 0.36,
"learning_rate": 0.00019623452664340306,
"loss": 1.7302,
"step": 24
},
{
"epoch": 0.39,
"learning_rate": 0.0001953038210948861,
"loss": 1.5975,
"step": 26
},
{
"epoch": 0.42,
"learning_rate": 0.00019427315499864344,
"loss": 1.5909,
"step": 28
},
{
"epoch": 0.45,
"learning_rate": 0.00019314360938108425,
"loss": 1.6737,
"step": 30
},
{
"epoch": 0.48,
"learning_rate": 0.00019191636897958122,
"loss": 1.7467,
"step": 32
},
{
"epoch": 0.51,
"learning_rate": 0.0001905927209998447,
"loss": 2.2383,
"step": 34
},
{
"epoch": 0.54,
"learning_rate": 0.00018917405376582145,
"loss": 1.7471,
"step": 36
},
{
"epoch": 0.57,
"learning_rate": 0.0001876618552635348,
"loss": 1.6543,
"step": 38
},
{
"epoch": 0.6,
"learning_rate": 0.00018605771158039253,
"loss": 1.7129,
"step": 40
},
{
"epoch": 0.63,
"learning_rate": 0.00018436330524160047,
"loss": 1.5638,
"step": 42
},
{
"epoch": 0.66,
"learning_rate": 0.00018258041344542566,
"loss": 1.4532,
"step": 44
},
{
"epoch": 0.69,
"learning_rate": 0.00018071090619916093,
"loss": 1.8129,
"step": 46
},
{
"epoch": 0.72,
"learning_rate": 0.00017875674435774547,
"loss": 1.5569,
"step": 48
},
{
"epoch": 0.75,
"learning_rate": 0.00017671997756709863,
"loss": 2.1262,
"step": 50
},
{
"epoch": 0.78,
"learning_rate": 0.0001746027421143246,
"loss": 1.7202,
"step": 52
},
{
"epoch": 0.81,
"learning_rate": 0.00017240725868704218,
"loss": 1.7062,
"step": 54
},
{
"epoch": 0.84,
"learning_rate": 0.00017013583004418993,
"loss": 1.7398,
"step": 56
},
{
"epoch": 0.86,
"learning_rate": 0.00016779083860075033,
"loss": 1.3817,
"step": 58
},
{
"epoch": 0.89,
"learning_rate": 0.00016537474392892528,
"loss": 1.6171,
"step": 60
},
{
"epoch": 0.92,
"learning_rate": 0.00016289008017838445,
"loss": 1.742,
"step": 62
},
{
"epoch": 0.95,
"learning_rate": 0.00016033945341829248,
"loss": 1.3789,
"step": 64
},
{
"epoch": 0.98,
"learning_rate": 0.00015772553890390197,
"loss": 1.6184,
"step": 66
},
{
"epoch": 1.01,
"learning_rate": 0.00015505107827058036,
"loss": 1.9795,
"step": 68
},
{
"epoch": 1.04,
"learning_rate": 0.000152318876658213,
"loss": 2.1623,
"step": 70
},
{
"epoch": 1.07,
"learning_rate": 0.00014953179976899878,
"loss": 1.6021,
"step": 72
},
{
"epoch": 1.1,
"learning_rate": 0.00014669277086172406,
"loss": 1.6685,
"step": 74
},
{
"epoch": 1.13,
"learning_rate": 0.00014380476768566824,
"loss": 1.5446,
"step": 76
},
{
"epoch": 1.16,
"learning_rate": 0.00014087081935735564,
"loss": 1.416,
"step": 78
},
{
"epoch": 1.19,
"learning_rate": 0.00013789400318343068,
"loss": 1.444,
"step": 80
},
{
"epoch": 1.22,
"learning_rate": 0.00013487744143298822,
"loss": 1.6077,
"step": 82
},
{
"epoch": 1.25,
"learning_rate": 0.0001318242980627444,
"loss": 1.6088,
"step": 84
},
{
"epoch": 1.28,
"learning_rate": 0.00012873777539848283,
"loss": 2.1679,
"step": 86
},
{
"epoch": 1.31,
"learning_rate": 0.00012562111077625722,
"loss": 1.6029,
"step": 88
},
{
"epoch": 1.34,
"learning_rate": 0.00012247757314687297,
"loss": 1.6147,
"step": 90
},
{
"epoch": 1.37,
"learning_rate": 0.00011931045964720881,
"loss": 1.5484,
"step": 92
},
{
"epoch": 1.4,
"learning_rate": 0.00011612309214197599,
"loss": 1.209,
"step": 94
},
{
"epoch": 1.43,
"learning_rate": 0.00011291881373954065,
"loss": 1.4836,
"step": 96
},
{
"epoch": 1.46,
"learning_rate": 0.00010970098528546481,
"loss": 1.6123,
"step": 98
},
{
"epoch": 1.49,
"learning_rate": 0.00010647298183744359,
"loss": 1.5941,
"step": 100
},
{
"epoch": 1.52,
"learning_rate": 0.00010323818912533561,
"loss": 1.6742,
"step": 102
},
{
"epoch": 1.55,
"learning_rate": 0.0001,
"loss": 1.6694,
"step": 104
},
{
"epoch": 1.58,
"learning_rate": 9.676181087466444e-05,
"loss": 1.6093,
"step": 106
},
{
"epoch": 1.61,
"learning_rate": 9.352701816255643e-05,
"loss": 1.523,
"step": 108
},
{
"epoch": 1.64,
"learning_rate": 9.02990147145352e-05,
"loss": 1.3713,
"step": 110
},
{
"epoch": 1.67,
"learning_rate": 8.70811862604594e-05,
"loss": 1.353,
"step": 112
},
{
"epoch": 1.7,
"learning_rate": 8.387690785802402e-05,
"loss": 1.6161,
"step": 114
},
{
"epoch": 1.73,
"learning_rate": 8.068954035279121e-05,
"loss": 1.4482,
"step": 116
},
{
"epoch": 1.76,
"learning_rate": 7.75224268531271e-05,
"loss": 2.2994,
"step": 118
},
{
"epoch": 1.79,
"learning_rate": 7.437888922374276e-05,
"loss": 1.6135,
"step": 120
},
{
"epoch": 1.82,
"learning_rate": 7.126222460151719e-05,
"loss": 1.6165,
"step": 122
},
{
"epoch": 1.85,
"learning_rate": 6.817570193725564e-05,
"loss": 1.5075,
"step": 124
},
{
"epoch": 1.88,
"learning_rate": 6.512255856701177e-05,
"loss": 1.3746,
"step": 126
},
{
"epoch": 1.91,
"learning_rate": 6.210599681656933e-05,
"loss": 1.636,
"step": 128
},
{
"epoch": 1.94,
"learning_rate": 5.9129180642644414e-05,
"loss": 1.543,
"step": 130
},
{
"epoch": 1.97,
"learning_rate": 5.6195232314331766e-05,
"loss": 1.8575,
"step": 132
},
{
"epoch": 2.0,
"learning_rate": 5.3307229138275936e-05,
"loss": 1.5399,
"step": 134
},
{
"epoch": 2.03,
"learning_rate": 5.0468200231001286e-05,
"loss": 2.0868,
"step": 136
},
{
"epoch": 2.06,
"learning_rate": 4.768112334178699e-05,
"loss": 1.6908,
"step": 138
},
{
"epoch": 2.09,
"learning_rate": 4.494892172941965e-05,
"loss": 1.6114,
"step": 140
},
{
"epoch": 2.12,
"learning_rate": 4.227446109609809e-05,
"loss": 1.6339,
"step": 142
},
{
"epoch": 2.15,
"learning_rate": 3.966054658170754e-05,
"loss": 1.2812,
"step": 144
},
{
"epoch": 2.18,
"learning_rate": 3.710991982161555e-05,
"loss": 1.2917,
"step": 146
},
{
"epoch": 2.21,
"learning_rate": 3.4625256071074773e-05,
"loss": 1.4585,
"step": 148
},
{
"epoch": 2.24,
"learning_rate": 3.2209161399249674e-05,
"loss": 1.2756,
"step": 150
},
{
"epoch": 2.27,
"learning_rate": 2.9864169955810084e-05,
"loss": 2.3198,
"step": 152
},
{
"epoch": 2.3,
"learning_rate": 2.759274131295787e-05,
"loss": 1.5796,
"step": 154
},
{
"epoch": 2.33,
"learning_rate": 2.5397257885675397e-05,
"loss": 1.5894,
"step": 156
},
{
"epoch": 2.36,
"learning_rate": 2.3280022432901383e-05,
"loss": 1.5756,
"step": 158
},
{
"epoch": 2.39,
"learning_rate": 2.1243255642254578e-05,
"loss": 1.4533,
"step": 160
},
{
"epoch": 2.42,
"learning_rate": 1.9289093800839066e-05,
"loss": 1.438,
"step": 162
},
{
"epoch": 2.45,
"learning_rate": 1.741958655457436e-05,
"loss": 1.3457,
"step": 164
},
{
"epoch": 2.48,
"learning_rate": 1.563669475839956e-05,
"loss": 1.1468,
"step": 166
},
{
"epoch": 2.51,
"learning_rate": 1.3942288419607475e-05,
"loss": 2.2085,
"step": 168
},
{
"epoch": 2.53,
"learning_rate": 1.233814473646524e-05,
"loss": 1.9171,
"step": 170
},
{
"epoch": 2.56,
"learning_rate": 1.0825946234178574e-05,
"loss": 1.6193,
"step": 172
},
{
"epoch": 2.59,
"learning_rate": 9.407279000155312e-06,
"loss": 1.47,
"step": 174
},
{
"epoch": 2.62,
"learning_rate": 8.083631020418791e-06,
"loss": 1.4138,
"step": 176
},
{
"epoch": 2.65,
"learning_rate": 6.856390618915775e-06,
"loss": 1.2043,
"step": 178
},
{
"epoch": 2.68,
"learning_rate": 5.726845001356573e-06,
"loss": 1.4215,
"step": 180
},
{
"epoch": 2.71,
"learning_rate": 4.6961789051139124e-06,
"loss": 1.0938,
"step": 182
},
{
"epoch": 2.74,
"learning_rate": 3.7654733565969826e-06,
"loss": 2.0156,
"step": 184
},
{
"epoch": 2.77,
"learning_rate": 2.9357045374040825e-06,
"loss": 2.0088,
"step": 186
},
{
"epoch": 2.8,
"learning_rate": 2.2077427604429433e-06,
"loss": 1.5032,
"step": 188
},
{
"epoch": 2.83,
"learning_rate": 1.5823515570925763e-06,
"loss": 1.5842,
"step": 190
},
{
"epoch": 2.86,
"learning_rate": 1.0601868763643996e-06,
"loss": 1.3561,
"step": 192
},
{
"epoch": 2.89,
"learning_rate": 6.41796396902239e-07,
"loss": 1.296,
"step": 194
},
{
"epoch": 2.92,
"learning_rate": 3.2761895254306287e-07,
"loss": 1.3239,
"step": 196
},
{
"epoch": 2.95,
"learning_rate": 1.179840720409331e-07,
"loss": 1.2131,
"step": 198
},
{
"epoch": 2.98,
"learning_rate": 1.3111633436779791e-08,
"loss": 1.7555,
"step": 200
}
],
"logging_steps": 2,
"max_steps": 201,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"save_steps": 500,
"total_flos": 8968581547376640.0,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}