526 lines
10 KiB
JSON
526 lines
10 KiB
JSON
{
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 42.0,
|
|
"eval_steps": 5,
|
|
"global_step": 168,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"epoch": 0.5,
|
|
"learning_rate": 2.9999177540482684e-05,
|
|
"loss": 2.6428,
|
|
"step": 2
|
|
},
|
|
{
|
|
"epoch": 1.0,
|
|
"learning_rate": 2.9996710252122685e-05,
|
|
"loss": 2.1838,
|
|
"step": 4
|
|
},
|
|
{
|
|
"epoch": 1.5,
|
|
"learning_rate": 2.9992598405485974e-05,
|
|
"loss": 1.8524,
|
|
"step": 6
|
|
},
|
|
{
|
|
"epoch": 2.0,
|
|
"learning_rate": 2.9986842451482876e-05,
|
|
"loss": 1.59,
|
|
"step": 8
|
|
},
|
|
{
|
|
"epoch": 2.5,
|
|
"learning_rate": 2.9979443021318607e-05,
|
|
"loss": 1.4015,
|
|
"step": 10
|
|
},
|
|
{
|
|
"epoch": 3.0,
|
|
"learning_rate": 2.9970400926424075e-05,
|
|
"loss": 1.2128,
|
|
"step": 12
|
|
},
|
|
{
|
|
"epoch": 3.5,
|
|
"learning_rate": 2.995971715836687e-05,
|
|
"loss": 1.1418,
|
|
"step": 14
|
|
},
|
|
{
|
|
"epoch": 4.0,
|
|
"learning_rate": 2.9947392888742566e-05,
|
|
"loss": 1.0389,
|
|
"step": 16
|
|
},
|
|
{
|
|
"epoch": 4.5,
|
|
"learning_rate": 2.9933429469046202e-05,
|
|
"loss": 1.0268,
|
|
"step": 18
|
|
},
|
|
{
|
|
"epoch": 5.0,
|
|
"learning_rate": 2.99178284305241e-05,
|
|
"loss": 0.9734,
|
|
"step": 20
|
|
},
|
|
{
|
|
"epoch": 5.5,
|
|
"learning_rate": 2.9900591484005944e-05,
|
|
"loss": 0.9755,
|
|
"step": 22
|
|
},
|
|
{
|
|
"epoch": 6.0,
|
|
"learning_rate": 2.988172051971717e-05,
|
|
"loss": 0.9142,
|
|
"step": 24
|
|
},
|
|
{
|
|
"epoch": 6.5,
|
|
"learning_rate": 2.9861217607071655e-05,
|
|
"loss": 0.8872,
|
|
"step": 26
|
|
},
|
|
{
|
|
"epoch": 7.0,
|
|
"learning_rate": 2.983908499444483e-05,
|
|
"loss": 0.8633,
|
|
"step": 28
|
|
},
|
|
{
|
|
"epoch": 7.5,
|
|
"learning_rate": 2.981532510892707e-05,
|
|
"loss": 0.8248,
|
|
"step": 30
|
|
},
|
|
{
|
|
"epoch": 8.0,
|
|
"learning_rate": 2.9789940556057574e-05,
|
|
"loss": 0.8352,
|
|
"step": 32
|
|
},
|
|
{
|
|
"epoch": 8.5,
|
|
"learning_rate": 2.9762934119538628e-05,
|
|
"loss": 0.8017,
|
|
"step": 34
|
|
},
|
|
{
|
|
"epoch": 9.0,
|
|
"learning_rate": 2.9734308760930333e-05,
|
|
"loss": 0.7705,
|
|
"step": 36
|
|
},
|
|
{
|
|
"epoch": 9.5,
|
|
"learning_rate": 2.9704067619325828e-05,
|
|
"loss": 0.7619,
|
|
"step": 38
|
|
},
|
|
{
|
|
"epoch": 10.0,
|
|
"learning_rate": 2.9672214011007087e-05,
|
|
"loss": 0.7593,
|
|
"step": 40
|
|
},
|
|
{
|
|
"epoch": 10.5,
|
|
"learning_rate": 2.9638751429081213e-05,
|
|
"loss": 0.7469,
|
|
"step": 42
|
|
},
|
|
{
|
|
"epoch": 11.0,
|
|
"learning_rate": 2.9603683543097406e-05,
|
|
"loss": 0.7477,
|
|
"step": 44
|
|
},
|
|
{
|
|
"epoch": 11.5,
|
|
"learning_rate": 2.9567014198644542e-05,
|
|
"loss": 0.716,
|
|
"step": 46
|
|
},
|
|
{
|
|
"epoch": 12.0,
|
|
"learning_rate": 2.9528747416929467e-05,
|
|
"loss": 0.7351,
|
|
"step": 48
|
|
},
|
|
{
|
|
"epoch": 12.5,
|
|
"learning_rate": 2.9488887394336025e-05,
|
|
"loss": 0.72,
|
|
"step": 50
|
|
},
|
|
{
|
|
"epoch": 13.0,
|
|
"learning_rate": 2.9447438501964873e-05,
|
|
"loss": 0.714,
|
|
"step": 52
|
|
},
|
|
{
|
|
"epoch": 13.5,
|
|
"learning_rate": 2.9404405285154146e-05,
|
|
"loss": 0.6994,
|
|
"step": 54
|
|
},
|
|
{
|
|
"epoch": 14.0,
|
|
"learning_rate": 2.9359792462981007e-05,
|
|
"loss": 0.7064,
|
|
"step": 56
|
|
},
|
|
{
|
|
"epoch": 14.5,
|
|
"learning_rate": 2.9313604927744153e-05,
|
|
"loss": 0.6807,
|
|
"step": 58
|
|
},
|
|
{
|
|
"epoch": 15.0,
|
|
"learning_rate": 2.9265847744427305e-05,
|
|
"loss": 0.6969,
|
|
"step": 60
|
|
},
|
|
{
|
|
"epoch": 15.5,
|
|
"learning_rate": 2.9216526150143788e-05,
|
|
"loss": 0.6836,
|
|
"step": 62
|
|
},
|
|
{
|
|
"epoch": 16.0,
|
|
"learning_rate": 2.9165645553562215e-05,
|
|
"loss": 0.6557,
|
|
"step": 64
|
|
},
|
|
{
|
|
"epoch": 16.5,
|
|
"learning_rate": 2.9113211534313385e-05,
|
|
"loss": 0.6619,
|
|
"step": 66
|
|
},
|
|
{
|
|
"epoch": 17.0,
|
|
"learning_rate": 2.9059229842378373e-05,
|
|
"loss": 0.6496,
|
|
"step": 68
|
|
},
|
|
{
|
|
"epoch": 17.5,
|
|
"learning_rate": 2.9003706397458025e-05,
|
|
"loss": 0.6268,
|
|
"step": 70
|
|
},
|
|
{
|
|
"epoch": 18.0,
|
|
"learning_rate": 2.894664728832377e-05,
|
|
"loss": 0.6586,
|
|
"step": 72
|
|
},
|
|
{
|
|
"epoch": 18.5,
|
|
"learning_rate": 2.8888058772149923e-05,
|
|
"loss": 0.6197,
|
|
"step": 74
|
|
},
|
|
{
|
|
"epoch": 19.0,
|
|
"learning_rate": 2.8827947273827508e-05,
|
|
"loss": 0.638,
|
|
"step": 76
|
|
},
|
|
{
|
|
"epoch": 19.5,
|
|
"learning_rate": 2.8766319385259717e-05,
|
|
"loss": 0.6093,
|
|
"step": 78
|
|
},
|
|
{
|
|
"epoch": 20.0,
|
|
"learning_rate": 2.8703181864639013e-05,
|
|
"loss": 0.6089,
|
|
"step": 80
|
|
},
|
|
{
|
|
"epoch": 20.5,
|
|
"learning_rate": 2.863854163570603e-05,
|
|
"loss": 0.6108,
|
|
"step": 82
|
|
},
|
|
{
|
|
"epoch": 21.0,
|
|
"learning_rate": 2.8572405786990293e-05,
|
|
"loss": 0.5776,
|
|
"step": 84
|
|
},
|
|
{
|
|
"epoch": 21.5,
|
|
"learning_rate": 2.8504781571032906e-05,
|
|
"loss": 0.5776,
|
|
"step": 86
|
|
},
|
|
{
|
|
"epoch": 22.0,
|
|
"learning_rate": 2.8435676403591193e-05,
|
|
"loss": 0.5997,
|
|
"step": 88
|
|
},
|
|
{
|
|
"epoch": 22.5,
|
|
"learning_rate": 2.8365097862825516e-05,
|
|
"loss": 0.5579,
|
|
"step": 90
|
|
},
|
|
{
|
|
"epoch": 23.0,
|
|
"learning_rate": 2.829305368846822e-05,
|
|
"loss": 0.579,
|
|
"step": 92
|
|
},
|
|
{
|
|
"epoch": 23.5,
|
|
"learning_rate": 2.821955178097488e-05,
|
|
"loss": 0.5689,
|
|
"step": 94
|
|
},
|
|
{
|
|
"epoch": 24.0,
|
|
"learning_rate": 2.8144600200657953e-05,
|
|
"loss": 0.5278,
|
|
"step": 96
|
|
},
|
|
{
|
|
"epoch": 24.5,
|
|
"learning_rate": 2.8068207166802843e-05,
|
|
"loss": 0.55,
|
|
"step": 98
|
|
},
|
|
{
|
|
"epoch": 25.0,
|
|
"learning_rate": 2.7990381056766583e-05,
|
|
"loss": 0.516,
|
|
"step": 100
|
|
},
|
|
{
|
|
"epoch": 25.5,
|
|
"learning_rate": 2.7911130405059155e-05,
|
|
"loss": 0.5342,
|
|
"step": 102
|
|
},
|
|
{
|
|
"epoch": 26.0,
|
|
"learning_rate": 2.78304639024076e-05,
|
|
"loss": 0.5021,
|
|
"step": 104
|
|
},
|
|
{
|
|
"epoch": 26.5,
|
|
"learning_rate": 2.774839039480296e-05,
|
|
"loss": 0.5042,
|
|
"step": 106
|
|
},
|
|
{
|
|
"epoch": 27.0,
|
|
"learning_rate": 2.7664918882530227e-05,
|
|
"loss": 0.4999,
|
|
"step": 108
|
|
},
|
|
{
|
|
"epoch": 27.5,
|
|
"learning_rate": 2.7580058519181363e-05,
|
|
"loss": 0.4847,
|
|
"step": 110
|
|
},
|
|
{
|
|
"epoch": 28.0,
|
|
"learning_rate": 2.7493818610651493e-05,
|
|
"loss": 0.467,
|
|
"step": 112
|
|
},
|
|
{
|
|
"epoch": 28.5,
|
|
"learning_rate": 2.7406208614118427e-05,
|
|
"loss": 0.462,
|
|
"step": 114
|
|
},
|
|
{
|
|
"epoch": 29.0,
|
|
"learning_rate": 2.731723813700556e-05,
|
|
"loss": 0.4576,
|
|
"step": 116
|
|
},
|
|
{
|
|
"epoch": 29.5,
|
|
"learning_rate": 2.7226916935928312e-05,
|
|
"loss": 0.45,
|
|
"step": 118
|
|
},
|
|
{
|
|
"epoch": 30.0,
|
|
"learning_rate": 2.7135254915624213e-05,
|
|
"loss": 0.4045,
|
|
"step": 120
|
|
},
|
|
{
|
|
"epoch": 30.5,
|
|
"learning_rate": 2.7042262127866718e-05,
|
|
"loss": 0.424,
|
|
"step": 122
|
|
},
|
|
{
|
|
"epoch": 31.0,
|
|
"learning_rate": 2.6947948770362945e-05,
|
|
"loss": 0.3926,
|
|
"step": 124
|
|
},
|
|
{
|
|
"epoch": 31.5,
|
|
"learning_rate": 2.6852325185635357e-05,
|
|
"loss": 0.3923,
|
|
"step": 126
|
|
},
|
|
{
|
|
"epoch": 32.0,
|
|
"learning_rate": 2.6755401859887598e-05,
|
|
"loss": 0.3652,
|
|
"step": 128
|
|
},
|
|
{
|
|
"epoch": 32.5,
|
|
"learning_rate": 2.6657189421854564e-05,
|
|
"loss": 0.3541,
|
|
"step": 130
|
|
},
|
|
{
|
|
"epoch": 33.0,
|
|
"learning_rate": 2.655769864163684e-05,
|
|
"loss": 0.3451,
|
|
"step": 132
|
|
},
|
|
{
|
|
"epoch": 33.5,
|
|
"learning_rate": 2.6456940429519637e-05,
|
|
"loss": 0.3235,
|
|
"step": 134
|
|
},
|
|
{
|
|
"epoch": 34.0,
|
|
"learning_rate": 2.6354925834776346e-05,
|
|
"loss": 0.3221,
|
|
"step": 136
|
|
},
|
|
{
|
|
"epoch": 34.5,
|
|
"learning_rate": 2.6251666044456895e-05,
|
|
"loss": 0.3058,
|
|
"step": 138
|
|
},
|
|
{
|
|
"epoch": 35.0,
|
|
"learning_rate": 2.6147172382160913e-05,
|
|
"loss": 0.2797,
|
|
"step": 140
|
|
},
|
|
{
|
|
"epoch": 35.5,
|
|
"learning_rate": 2.604145630679602e-05,
|
|
"loss": 0.2611,
|
|
"step": 142
|
|
},
|
|
{
|
|
"epoch": 36.0,
|
|
"learning_rate": 2.5934529411321174e-05,
|
|
"loss": 0.2706,
|
|
"step": 144
|
|
},
|
|
{
|
|
"epoch": 36.5,
|
|
"learning_rate": 2.582640342147543e-05,
|
|
"loss": 0.245,
|
|
"step": 146
|
|
},
|
|
{
|
|
"epoch": 37.0,
|
|
"learning_rate": 2.571709019449205e-05,
|
|
"loss": 0.2134,
|
|
"step": 148
|
|
},
|
|
{
|
|
"epoch": 37.5,
|
|
"learning_rate": 2.5606601717798212e-05,
|
|
"loss": 0.2031,
|
|
"step": 150
|
|
},
|
|
{
|
|
"epoch": 38.0,
|
|
"learning_rate": 2.5494950107700482e-05,
|
|
"loss": 0.1988,
|
|
"step": 152
|
|
},
|
|
{
|
|
"epoch": 38.5,
|
|
"learning_rate": 2.5382147608056104e-05,
|
|
"loss": 0.1801,
|
|
"step": 154
|
|
},
|
|
{
|
|
"epoch": 39.0,
|
|
"learning_rate": 2.5268206588930332e-05,
|
|
"loss": 0.1731,
|
|
"step": 156
|
|
},
|
|
{
|
|
"epoch": 39.5,
|
|
"learning_rate": 2.515313954523991e-05,
|
|
"loss": 0.1585,
|
|
"step": 158
|
|
},
|
|
{
|
|
"epoch": 40.0,
|
|
"learning_rate": 2.5036959095382875e-05,
|
|
"loss": 0.1464,
|
|
"step": 160
|
|
},
|
|
{
|
|
"epoch": 40.5,
|
|
"learning_rate": 2.491967797985478e-05,
|
|
"loss": 0.1372,
|
|
"step": 162
|
|
},
|
|
{
|
|
"epoch": 41.0,
|
|
"learning_rate": 2.4801309059851586e-05,
|
|
"loss": 0.1254,
|
|
"step": 164
|
|
},
|
|
{
|
|
"epoch": 41.5,
|
|
"learning_rate": 2.468186531585926e-05,
|
|
"loss": 0.1204,
|
|
"step": 166
|
|
},
|
|
{
|
|
"epoch": 42.0,
|
|
"learning_rate": 2.4561359846230346e-05,
|
|
"loss": 0.1099,
|
|
"step": 168
|
|
}
|
|
],
|
|
"logging_steps": 2,
|
|
"max_steps": 600,
|
|
"num_input_tokens_seen": 0,
|
|
"num_train_epochs": 150,
|
|
"save_steps": 500,
|
|
"total_flos": 8003964905717760.0,
|
|
"train_batch_size": 52,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|