1846 lines
36 KiB
JSON
1846 lines
36 KiB
JSON
{
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 0.1292824822236587,
|
|
"eval_steps": 100,
|
|
"global_step": 300,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"epoch": 0.0,
|
|
"learning_rate": 5e-05,
|
|
"loss": 1.5475,
|
|
"step": 1
|
|
},
|
|
{
|
|
"epoch": 0.0,
|
|
"learning_rate": 4.999997705921923e-05,
|
|
"loss": 1.4738,
|
|
"step": 2
|
|
},
|
|
{
|
|
"epoch": 0.0,
|
|
"learning_rate": 4.9999908236919016e-05,
|
|
"loss": 1.709,
|
|
"step": 3
|
|
},
|
|
{
|
|
"epoch": 0.0,
|
|
"learning_rate": 4.999979353322567e-05,
|
|
"loss": 1.3682,
|
|
"step": 4
|
|
},
|
|
{
|
|
"epoch": 0.0,
|
|
"learning_rate": 4.99996329483497e-05,
|
|
"loss": 1.4525,
|
|
"step": 5
|
|
},
|
|
{
|
|
"epoch": 0.0,
|
|
"learning_rate": 4.999942648258581e-05,
|
|
"loss": 1.2902,
|
|
"step": 6
|
|
},
|
|
{
|
|
"epoch": 0.0,
|
|
"learning_rate": 4.999917413631294e-05,
|
|
"loss": 1.2581,
|
|
"step": 7
|
|
},
|
|
{
|
|
"epoch": 0.0,
|
|
"learning_rate": 4.9998875909994206e-05,
|
|
"loss": 1.1363,
|
|
"step": 8
|
|
},
|
|
{
|
|
"epoch": 0.0,
|
|
"learning_rate": 4.9998531804176926e-05,
|
|
"loss": 1.0479,
|
|
"step": 9
|
|
},
|
|
{
|
|
"epoch": 0.0,
|
|
"learning_rate": 4.999814181949263e-05,
|
|
"loss": 1.0362,
|
|
"step": 10
|
|
},
|
|
{
|
|
"epoch": 0.0,
|
|
"learning_rate": 4.999770595665704e-05,
|
|
"loss": 0.9415,
|
|
"step": 11
|
|
},
|
|
{
|
|
"epoch": 0.01,
|
|
"learning_rate": 4.999722421647006e-05,
|
|
"loss": 1.0849,
|
|
"step": 12
|
|
},
|
|
{
|
|
"epoch": 0.01,
|
|
"learning_rate": 4.999669659981584e-05,
|
|
"loss": 0.8538,
|
|
"step": 13
|
|
},
|
|
{
|
|
"epoch": 0.01,
|
|
"learning_rate": 4.999612310766268e-05,
|
|
"loss": 0.9404,
|
|
"step": 14
|
|
},
|
|
{
|
|
"epoch": 0.01,
|
|
"learning_rate": 4.9995503741063096e-05,
|
|
"loss": 0.9645,
|
|
"step": 15
|
|
},
|
|
{
|
|
"epoch": 0.01,
|
|
"learning_rate": 4.999483850115379e-05,
|
|
"loss": 1.0898,
|
|
"step": 16
|
|
},
|
|
{
|
|
"epoch": 0.01,
|
|
"learning_rate": 4.9994127389155623e-05,
|
|
"loss": 0.9545,
|
|
"step": 17
|
|
},
|
|
{
|
|
"epoch": 0.01,
|
|
"learning_rate": 4.9993370406373705e-05,
|
|
"loss": 0.8432,
|
|
"step": 18
|
|
},
|
|
{
|
|
"epoch": 0.01,
|
|
"learning_rate": 4.999256755419729e-05,
|
|
"loss": 0.9946,
|
|
"step": 19
|
|
},
|
|
{
|
|
"epoch": 0.01,
|
|
"learning_rate": 4.999171883409982e-05,
|
|
"loss": 0.7908,
|
|
"step": 20
|
|
},
|
|
{
|
|
"epoch": 0.01,
|
|
"learning_rate": 4.999082424763891e-05,
|
|
"loss": 0.8971,
|
|
"step": 21
|
|
},
|
|
{
|
|
"epoch": 0.01,
|
|
"learning_rate": 4.998988379645638e-05,
|
|
"loss": 0.85,
|
|
"step": 22
|
|
},
|
|
{
|
|
"epoch": 0.01,
|
|
"learning_rate": 4.998889748227819e-05,
|
|
"loss": 0.8626,
|
|
"step": 23
|
|
},
|
|
{
|
|
"epoch": 0.01,
|
|
"learning_rate": 4.9987865306914495e-05,
|
|
"loss": 0.8335,
|
|
"step": 24
|
|
},
|
|
{
|
|
"epoch": 0.01,
|
|
"learning_rate": 4.9986787272259596e-05,
|
|
"loss": 0.9314,
|
|
"step": 25
|
|
},
|
|
{
|
|
"epoch": 0.01,
|
|
"learning_rate": 4.998566338029198e-05,
|
|
"loss": 0.8645,
|
|
"step": 26
|
|
},
|
|
{
|
|
"epoch": 0.01,
|
|
"learning_rate": 4.998449363307428e-05,
|
|
"loss": 0.9316,
|
|
"step": 27
|
|
},
|
|
{
|
|
"epoch": 0.01,
|
|
"learning_rate": 4.998327803275328e-05,
|
|
"loss": 0.805,
|
|
"step": 28
|
|
},
|
|
{
|
|
"epoch": 0.01,
|
|
"learning_rate": 4.998201658155994e-05,
|
|
"loss": 1.0418,
|
|
"step": 29
|
|
},
|
|
{
|
|
"epoch": 0.01,
|
|
"learning_rate": 4.998070928180935e-05,
|
|
"loss": 0.649,
|
|
"step": 30
|
|
},
|
|
{
|
|
"epoch": 0.01,
|
|
"learning_rate": 4.997935613590075e-05,
|
|
"loss": 0.8,
|
|
"step": 31
|
|
},
|
|
{
|
|
"epoch": 0.01,
|
|
"learning_rate": 4.997795714631751e-05,
|
|
"loss": 0.8014,
|
|
"step": 32
|
|
},
|
|
{
|
|
"epoch": 0.01,
|
|
"learning_rate": 4.997651231562715e-05,
|
|
"loss": 0.7854,
|
|
"step": 33
|
|
},
|
|
{
|
|
"epoch": 0.01,
|
|
"learning_rate": 4.9975021646481315e-05,
|
|
"loss": 0.8782,
|
|
"step": 34
|
|
},
|
|
{
|
|
"epoch": 0.02,
|
|
"learning_rate": 4.997348514161576e-05,
|
|
"loss": 0.7564,
|
|
"step": 35
|
|
},
|
|
{
|
|
"epoch": 0.02,
|
|
"learning_rate": 4.997190280385039e-05,
|
|
"loss": 0.9438,
|
|
"step": 36
|
|
},
|
|
{
|
|
"epoch": 0.02,
|
|
"learning_rate": 4.997027463608921e-05,
|
|
"loss": 0.9248,
|
|
"step": 37
|
|
},
|
|
{
|
|
"epoch": 0.02,
|
|
"learning_rate": 4.996860064132033e-05,
|
|
"loss": 0.76,
|
|
"step": 38
|
|
},
|
|
{
|
|
"epoch": 0.02,
|
|
"learning_rate": 4.9966880822615965e-05,
|
|
"loss": 0.8834,
|
|
"step": 39
|
|
},
|
|
{
|
|
"epoch": 0.02,
|
|
"learning_rate": 4.996511518313244e-05,
|
|
"loss": 0.8928,
|
|
"step": 40
|
|
},
|
|
{
|
|
"epoch": 0.02,
|
|
"learning_rate": 4.996330372611017e-05,
|
|
"loss": 0.8857,
|
|
"step": 41
|
|
},
|
|
{
|
|
"epoch": 0.02,
|
|
"learning_rate": 4.996144645487364e-05,
|
|
"loss": 0.7975,
|
|
"step": 42
|
|
},
|
|
{
|
|
"epoch": 0.02,
|
|
"learning_rate": 4.995954337283145e-05,
|
|
"loss": 0.7815,
|
|
"step": 43
|
|
},
|
|
{
|
|
"epoch": 0.02,
|
|
"learning_rate": 4.9957594483476236e-05,
|
|
"loss": 0.8869,
|
|
"step": 44
|
|
},
|
|
{
|
|
"epoch": 0.02,
|
|
"learning_rate": 4.995559979038474e-05,
|
|
"loss": 0.9173,
|
|
"step": 45
|
|
},
|
|
{
|
|
"epoch": 0.02,
|
|
"learning_rate": 4.995355929721773e-05,
|
|
"loss": 0.9258,
|
|
"step": 46
|
|
},
|
|
{
|
|
"epoch": 0.02,
|
|
"learning_rate": 4.995147300772006e-05,
|
|
"loss": 0.896,
|
|
"step": 47
|
|
},
|
|
{
|
|
"epoch": 0.02,
|
|
"learning_rate": 4.994934092572061e-05,
|
|
"loss": 0.893,
|
|
"step": 48
|
|
},
|
|
{
|
|
"epoch": 0.02,
|
|
"learning_rate": 4.994716305513232e-05,
|
|
"loss": 0.8257,
|
|
"step": 49
|
|
},
|
|
{
|
|
"epoch": 0.02,
|
|
"learning_rate": 4.994493939995214e-05,
|
|
"loss": 0.8759,
|
|
"step": 50
|
|
},
|
|
{
|
|
"epoch": 0.02,
|
|
"learning_rate": 4.994266996426107e-05,
|
|
"loss": 0.9216,
|
|
"step": 51
|
|
},
|
|
{
|
|
"epoch": 0.02,
|
|
"learning_rate": 4.994035475222412e-05,
|
|
"loss": 0.9097,
|
|
"step": 52
|
|
},
|
|
{
|
|
"epoch": 0.02,
|
|
"learning_rate": 4.9937993768090306e-05,
|
|
"loss": 1.015,
|
|
"step": 53
|
|
},
|
|
{
|
|
"epoch": 0.02,
|
|
"learning_rate": 4.993558701619266e-05,
|
|
"loss": 0.8633,
|
|
"step": 54
|
|
},
|
|
{
|
|
"epoch": 0.02,
|
|
"learning_rate": 4.9933134500948205e-05,
|
|
"loss": 0.928,
|
|
"step": 55
|
|
},
|
|
{
|
|
"epoch": 0.02,
|
|
"learning_rate": 4.993063622685794e-05,
|
|
"loss": 0.8069,
|
|
"step": 56
|
|
},
|
|
{
|
|
"epoch": 0.02,
|
|
"learning_rate": 4.9928092198506866e-05,
|
|
"loss": 0.885,
|
|
"step": 57
|
|
},
|
|
{
|
|
"epoch": 0.02,
|
|
"learning_rate": 4.992550242056393e-05,
|
|
"loss": 0.7342,
|
|
"step": 58
|
|
},
|
|
{
|
|
"epoch": 0.03,
|
|
"learning_rate": 4.992286689778207e-05,
|
|
"loss": 0.8593,
|
|
"step": 59
|
|
},
|
|
{
|
|
"epoch": 0.03,
|
|
"learning_rate": 4.992018563499814e-05,
|
|
"loss": 0.9458,
|
|
"step": 60
|
|
},
|
|
{
|
|
"epoch": 0.03,
|
|
"learning_rate": 4.991745863713299e-05,
|
|
"loss": 0.9511,
|
|
"step": 61
|
|
},
|
|
{
|
|
"epoch": 0.03,
|
|
"learning_rate": 4.991468590919135e-05,
|
|
"loss": 0.8605,
|
|
"step": 62
|
|
},
|
|
{
|
|
"epoch": 0.03,
|
|
"learning_rate": 4.9911867456261916e-05,
|
|
"loss": 0.76,
|
|
"step": 63
|
|
},
|
|
{
|
|
"epoch": 0.03,
|
|
"learning_rate": 4.9909003283517283e-05,
|
|
"loss": 0.8037,
|
|
"step": 64
|
|
},
|
|
{
|
|
"epoch": 0.03,
|
|
"learning_rate": 4.990609339621397e-05,
|
|
"loss": 0.8945,
|
|
"step": 65
|
|
},
|
|
{
|
|
"epoch": 0.03,
|
|
"learning_rate": 4.990313779969237e-05,
|
|
"loss": 0.7774,
|
|
"step": 66
|
|
},
|
|
{
|
|
"epoch": 0.03,
|
|
"learning_rate": 4.990013649937679e-05,
|
|
"loss": 0.8737,
|
|
"step": 67
|
|
},
|
|
{
|
|
"epoch": 0.03,
|
|
"learning_rate": 4.989708950077541e-05,
|
|
"loss": 0.8914,
|
|
"step": 68
|
|
},
|
|
{
|
|
"epoch": 0.03,
|
|
"learning_rate": 4.9893996809480246e-05,
|
|
"loss": 0.8682,
|
|
"step": 69
|
|
},
|
|
{
|
|
"epoch": 0.03,
|
|
"learning_rate": 4.9890858431167226e-05,
|
|
"loss": 0.7745,
|
|
"step": 70
|
|
},
|
|
{
|
|
"epoch": 0.03,
|
|
"learning_rate": 4.988767437159608e-05,
|
|
"loss": 1.0306,
|
|
"step": 71
|
|
},
|
|
{
|
|
"epoch": 0.03,
|
|
"learning_rate": 4.988444463661041e-05,
|
|
"loss": 0.904,
|
|
"step": 72
|
|
},
|
|
{
|
|
"epoch": 0.03,
|
|
"learning_rate": 4.98811692321376e-05,
|
|
"loss": 0.8478,
|
|
"step": 73
|
|
},
|
|
{
|
|
"epoch": 0.03,
|
|
"learning_rate": 4.9877848164188904e-05,
|
|
"loss": 0.7117,
|
|
"step": 74
|
|
},
|
|
{
|
|
"epoch": 0.03,
|
|
"learning_rate": 4.987448143885933e-05,
|
|
"loss": 0.6789,
|
|
"step": 75
|
|
},
|
|
{
|
|
"epoch": 0.03,
|
|
"learning_rate": 4.987106906232773e-05,
|
|
"loss": 0.9385,
|
|
"step": 76
|
|
},
|
|
{
|
|
"epoch": 0.03,
|
|
"learning_rate": 4.9867611040856695e-05,
|
|
"loss": 1.049,
|
|
"step": 77
|
|
},
|
|
{
|
|
"epoch": 0.03,
|
|
"learning_rate": 4.9864107380792594e-05,
|
|
"loss": 0.8914,
|
|
"step": 78
|
|
},
|
|
{
|
|
"epoch": 0.03,
|
|
"learning_rate": 4.986055808856558e-05,
|
|
"loss": 0.8211,
|
|
"step": 79
|
|
},
|
|
{
|
|
"epoch": 0.03,
|
|
"learning_rate": 4.9856963170689525e-05,
|
|
"loss": 0.9007,
|
|
"step": 80
|
|
},
|
|
{
|
|
"epoch": 0.03,
|
|
"learning_rate": 4.9853322633762045e-05,
|
|
"loss": 0.832,
|
|
"step": 81
|
|
},
|
|
{
|
|
"epoch": 0.04,
|
|
"learning_rate": 4.984963648446449e-05,
|
|
"loss": 0.807,
|
|
"step": 82
|
|
},
|
|
{
|
|
"epoch": 0.04,
|
|
"learning_rate": 4.984590472956191e-05,
|
|
"loss": 0.7031,
|
|
"step": 83
|
|
},
|
|
{
|
|
"epoch": 0.04,
|
|
"learning_rate": 4.984212737590304e-05,
|
|
"loss": 0.9261,
|
|
"step": 84
|
|
},
|
|
{
|
|
"epoch": 0.04,
|
|
"learning_rate": 4.983830443042033e-05,
|
|
"loss": 0.7759,
|
|
"step": 85
|
|
},
|
|
{
|
|
"epoch": 0.04,
|
|
"learning_rate": 4.983443590012989e-05,
|
|
"loss": 0.7147,
|
|
"step": 86
|
|
},
|
|
{
|
|
"epoch": 0.04,
|
|
"learning_rate": 4.9830521792131484e-05,
|
|
"loss": 0.8554,
|
|
"step": 87
|
|
},
|
|
{
|
|
"epoch": 0.04,
|
|
"learning_rate": 4.982656211360852e-05,
|
|
"loss": 0.8052,
|
|
"step": 88
|
|
},
|
|
{
|
|
"epoch": 0.04,
|
|
"learning_rate": 4.982255687182806e-05,
|
|
"loss": 0.8408,
|
|
"step": 89
|
|
},
|
|
{
|
|
"epoch": 0.04,
|
|
"learning_rate": 4.981850607414077e-05,
|
|
"loss": 0.7086,
|
|
"step": 90
|
|
},
|
|
{
|
|
"epoch": 0.04,
|
|
"learning_rate": 4.981440972798092e-05,
|
|
"loss": 0.7808,
|
|
"step": 91
|
|
},
|
|
{
|
|
"epoch": 0.04,
|
|
"learning_rate": 4.981026784086639e-05,
|
|
"loss": 0.8632,
|
|
"step": 92
|
|
},
|
|
{
|
|
"epoch": 0.04,
|
|
"learning_rate": 4.980608042039862e-05,
|
|
"loss": 0.8798,
|
|
"step": 93
|
|
},
|
|
{
|
|
"epoch": 0.04,
|
|
"learning_rate": 4.980184747426263e-05,
|
|
"loss": 0.9253,
|
|
"step": 94
|
|
},
|
|
{
|
|
"epoch": 0.04,
|
|
"learning_rate": 4.9797569010226995e-05,
|
|
"loss": 0.8305,
|
|
"step": 95
|
|
},
|
|
{
|
|
"epoch": 0.04,
|
|
"learning_rate": 4.979324503614381e-05,
|
|
"loss": 0.9474,
|
|
"step": 96
|
|
},
|
|
{
|
|
"epoch": 0.04,
|
|
"learning_rate": 4.97888755599487e-05,
|
|
"loss": 0.8102,
|
|
"step": 97
|
|
},
|
|
{
|
|
"epoch": 0.04,
|
|
"learning_rate": 4.978446058966081e-05,
|
|
"loss": 0.6445,
|
|
"step": 98
|
|
},
|
|
{
|
|
"epoch": 0.04,
|
|
"learning_rate": 4.978000013338277e-05,
|
|
"loss": 0.8123,
|
|
"step": 99
|
|
},
|
|
{
|
|
"epoch": 0.04,
|
|
"learning_rate": 4.977549419930067e-05,
|
|
"loss": 0.9368,
|
|
"step": 100
|
|
},
|
|
{
|
|
"epoch": 0.04,
|
|
"eval_loss": 0.8984958529472351,
|
|
"eval_runtime": 10.1685,
|
|
"eval_samples_per_second": 3.639,
|
|
"eval_steps_per_second": 0.492,
|
|
"step": 100
|
|
},
|
|
{
|
|
"epoch": 0.04,
|
|
"learning_rate": 4.97709427956841e-05,
|
|
"loss": 0.7673,
|
|
"step": 101
|
|
},
|
|
{
|
|
"epoch": 0.04,
|
|
"learning_rate": 4.976634593088608e-05,
|
|
"loss": 0.8571,
|
|
"step": 102
|
|
},
|
|
{
|
|
"epoch": 0.04,
|
|
"learning_rate": 4.9761703613343045e-05,
|
|
"loss": 0.9388,
|
|
"step": 103
|
|
},
|
|
{
|
|
"epoch": 0.04,
|
|
"learning_rate": 4.975701585157489e-05,
|
|
"loss": 0.7665,
|
|
"step": 104
|
|
},
|
|
{
|
|
"epoch": 0.05,
|
|
"learning_rate": 4.9752282654184876e-05,
|
|
"loss": 0.9379,
|
|
"step": 105
|
|
},
|
|
{
|
|
"epoch": 0.05,
|
|
"learning_rate": 4.974750402985966e-05,
|
|
"loss": 0.9475,
|
|
"step": 106
|
|
},
|
|
{
|
|
"epoch": 0.05,
|
|
"learning_rate": 4.974267998736928e-05,
|
|
"loss": 0.9757,
|
|
"step": 107
|
|
},
|
|
{
|
|
"epoch": 0.05,
|
|
"learning_rate": 4.973781053556711e-05,
|
|
"loss": 0.6865,
|
|
"step": 108
|
|
},
|
|
{
|
|
"epoch": 0.05,
|
|
"learning_rate": 4.973289568338989e-05,
|
|
"loss": 0.9761,
|
|
"step": 109
|
|
},
|
|
{
|
|
"epoch": 0.05,
|
|
"learning_rate": 4.9727935439857634e-05,
|
|
"loss": 0.9132,
|
|
"step": 110
|
|
},
|
|
{
|
|
"epoch": 0.05,
|
|
"learning_rate": 4.972292981407372e-05,
|
|
"loss": 0.774,
|
|
"step": 111
|
|
},
|
|
{
|
|
"epoch": 0.05,
|
|
"learning_rate": 4.971787881522477e-05,
|
|
"loss": 1.0217,
|
|
"step": 112
|
|
},
|
|
{
|
|
"epoch": 0.05,
|
|
"learning_rate": 4.9712782452580695e-05,
|
|
"loss": 0.9341,
|
|
"step": 113
|
|
},
|
|
{
|
|
"epoch": 0.05,
|
|
"learning_rate": 4.970764073549467e-05,
|
|
"loss": 0.7135,
|
|
"step": 114
|
|
},
|
|
{
|
|
"epoch": 0.05,
|
|
"learning_rate": 4.970245367340307e-05,
|
|
"loss": 0.7177,
|
|
"step": 115
|
|
},
|
|
{
|
|
"epoch": 0.05,
|
|
"learning_rate": 4.969722127582553e-05,
|
|
"loss": 0.9312,
|
|
"step": 116
|
|
},
|
|
{
|
|
"epoch": 0.05,
|
|
"learning_rate": 4.9691943552364885e-05,
|
|
"loss": 0.8677,
|
|
"step": 117
|
|
},
|
|
{
|
|
"epoch": 0.05,
|
|
"learning_rate": 4.968662051270711e-05,
|
|
"loss": 0.7371,
|
|
"step": 118
|
|
},
|
|
{
|
|
"epoch": 0.05,
|
|
"learning_rate": 4.968125216662142e-05,
|
|
"loss": 0.7248,
|
|
"step": 119
|
|
},
|
|
{
|
|
"epoch": 0.05,
|
|
"learning_rate": 4.9675838523960114e-05,
|
|
"loss": 0.7281,
|
|
"step": 120
|
|
},
|
|
{
|
|
"epoch": 0.05,
|
|
"learning_rate": 4.967037959465865e-05,
|
|
"loss": 0.8678,
|
|
"step": 121
|
|
},
|
|
{
|
|
"epoch": 0.05,
|
|
"learning_rate": 4.96648753887356e-05,
|
|
"loss": 0.8477,
|
|
"step": 122
|
|
},
|
|
{
|
|
"epoch": 0.05,
|
|
"learning_rate": 4.965932591629262e-05,
|
|
"loss": 0.7801,
|
|
"step": 123
|
|
},
|
|
{
|
|
"epoch": 0.05,
|
|
"learning_rate": 4.965373118751446e-05,
|
|
"loss": 0.8289,
|
|
"step": 124
|
|
},
|
|
{
|
|
"epoch": 0.05,
|
|
"learning_rate": 4.9648091212668904e-05,
|
|
"loss": 0.7771,
|
|
"step": 125
|
|
},
|
|
{
|
|
"epoch": 0.05,
|
|
"learning_rate": 4.964240600210679e-05,
|
|
"loss": 0.7933,
|
|
"step": 126
|
|
},
|
|
{
|
|
"epoch": 0.05,
|
|
"learning_rate": 4.963667556626198e-05,
|
|
"loss": 0.8119,
|
|
"step": 127
|
|
},
|
|
{
|
|
"epoch": 0.06,
|
|
"learning_rate": 4.963089991565131e-05,
|
|
"loss": 0.9761,
|
|
"step": 128
|
|
},
|
|
{
|
|
"epoch": 0.06,
|
|
"learning_rate": 4.9625079060874634e-05,
|
|
"loss": 0.7456,
|
|
"step": 129
|
|
},
|
|
{
|
|
"epoch": 0.06,
|
|
"learning_rate": 4.961921301261474e-05,
|
|
"loss": 0.7955,
|
|
"step": 130
|
|
},
|
|
{
|
|
"epoch": 0.06,
|
|
"learning_rate": 4.961330178163736e-05,
|
|
"loss": 0.8379,
|
|
"step": 131
|
|
},
|
|
{
|
|
"epoch": 0.06,
|
|
"learning_rate": 4.960734537879117e-05,
|
|
"loss": 0.793,
|
|
"step": 132
|
|
},
|
|
{
|
|
"epoch": 0.06,
|
|
"learning_rate": 4.960134381500771e-05,
|
|
"loss": 0.8465,
|
|
"step": 133
|
|
},
|
|
{
|
|
"epoch": 0.06,
|
|
"learning_rate": 4.959529710130144e-05,
|
|
"loss": 0.8813,
|
|
"step": 134
|
|
},
|
|
{
|
|
"epoch": 0.06,
|
|
"learning_rate": 4.958920524876967e-05,
|
|
"loss": 0.8148,
|
|
"step": 135
|
|
},
|
|
{
|
|
"epoch": 0.06,
|
|
"learning_rate": 4.9583068268592544e-05,
|
|
"loss": 0.8524,
|
|
"step": 136
|
|
},
|
|
{
|
|
"epoch": 0.06,
|
|
"learning_rate": 4.957688617203302e-05,
|
|
"loss": 0.6524,
|
|
"step": 137
|
|
},
|
|
{
|
|
"epoch": 0.06,
|
|
"learning_rate": 4.957065897043689e-05,
|
|
"loss": 0.8021,
|
|
"step": 138
|
|
},
|
|
{
|
|
"epoch": 0.06,
|
|
"learning_rate": 4.9564386675232674e-05,
|
|
"loss": 0.9442,
|
|
"step": 139
|
|
},
|
|
{
|
|
"epoch": 0.06,
|
|
"learning_rate": 4.955806929793171e-05,
|
|
"loss": 0.8701,
|
|
"step": 140
|
|
},
|
|
{
|
|
"epoch": 0.06,
|
|
"learning_rate": 4.9551706850128024e-05,
|
|
"loss": 0.9975,
|
|
"step": 141
|
|
},
|
|
{
|
|
"epoch": 0.06,
|
|
"learning_rate": 4.954529934349839e-05,
|
|
"loss": 0.7725,
|
|
"step": 142
|
|
},
|
|
{
|
|
"epoch": 0.06,
|
|
"learning_rate": 4.953884678980225e-05,
|
|
"loss": 0.7544,
|
|
"step": 143
|
|
},
|
|
{
|
|
"epoch": 0.06,
|
|
"learning_rate": 4.9532349200881745e-05,
|
|
"loss": 0.6881,
|
|
"step": 144
|
|
},
|
|
{
|
|
"epoch": 0.06,
|
|
"learning_rate": 4.9525806588661656e-05,
|
|
"loss": 0.8211,
|
|
"step": 145
|
|
},
|
|
{
|
|
"epoch": 0.06,
|
|
"learning_rate": 4.951921896514938e-05,
|
|
"loss": 0.7736,
|
|
"step": 146
|
|
},
|
|
{
|
|
"epoch": 0.06,
|
|
"learning_rate": 4.9512586342434956e-05,
|
|
"loss": 0.9176,
|
|
"step": 147
|
|
},
|
|
{
|
|
"epoch": 0.06,
|
|
"learning_rate": 4.950590873269098e-05,
|
|
"loss": 0.7639,
|
|
"step": 148
|
|
},
|
|
{
|
|
"epoch": 0.06,
|
|
"learning_rate": 4.94991861481726e-05,
|
|
"loss": 0.8447,
|
|
"step": 149
|
|
},
|
|
{
|
|
"epoch": 0.06,
|
|
"learning_rate": 4.949241860121755e-05,
|
|
"loss": 0.7537,
|
|
"step": 150
|
|
},
|
|
{
|
|
"epoch": 0.07,
|
|
"learning_rate": 4.948560610424604e-05,
|
|
"loss": 0.7948,
|
|
"step": 151
|
|
},
|
|
{
|
|
"epoch": 0.07,
|
|
"learning_rate": 4.94787486697608e-05,
|
|
"loss": 0.7734,
|
|
"step": 152
|
|
},
|
|
{
|
|
"epoch": 0.07,
|
|
"learning_rate": 4.9471846310347006e-05,
|
|
"loss": 0.8796,
|
|
"step": 153
|
|
},
|
|
{
|
|
"epoch": 0.07,
|
|
"learning_rate": 4.946489903867231e-05,
|
|
"loss": 0.7196,
|
|
"step": 154
|
|
},
|
|
{
|
|
"epoch": 0.07,
|
|
"learning_rate": 4.945790686748678e-05,
|
|
"loss": 0.7676,
|
|
"step": 155
|
|
},
|
|
{
|
|
"epoch": 0.07,
|
|
"learning_rate": 4.945086980962288e-05,
|
|
"loss": 0.7697,
|
|
"step": 156
|
|
},
|
|
{
|
|
"epoch": 0.07,
|
|
"learning_rate": 4.9443787877995464e-05,
|
|
"loss": 0.8223,
|
|
"step": 157
|
|
},
|
|
{
|
|
"epoch": 0.07,
|
|
"learning_rate": 4.943666108560173e-05,
|
|
"loss": 0.8416,
|
|
"step": 158
|
|
},
|
|
{
|
|
"epoch": 0.07,
|
|
"learning_rate": 4.942948944552122e-05,
|
|
"loss": 0.8536,
|
|
"step": 159
|
|
},
|
|
{
|
|
"epoch": 0.07,
|
|
"learning_rate": 4.942227297091577e-05,
|
|
"loss": 1.0185,
|
|
"step": 160
|
|
},
|
|
{
|
|
"epoch": 0.07,
|
|
"learning_rate": 4.94150116750295e-05,
|
|
"loss": 0.8932,
|
|
"step": 161
|
|
},
|
|
{
|
|
"epoch": 0.07,
|
|
"learning_rate": 4.94077055711888e-05,
|
|
"loss": 0.8254,
|
|
"step": 162
|
|
},
|
|
{
|
|
"epoch": 0.07,
|
|
"learning_rate": 4.940035467280229e-05,
|
|
"loss": 0.7546,
|
|
"step": 163
|
|
},
|
|
{
|
|
"epoch": 0.07,
|
|
"learning_rate": 4.9392958993360794e-05,
|
|
"loss": 0.8746,
|
|
"step": 164
|
|
},
|
|
{
|
|
"epoch": 0.07,
|
|
"learning_rate": 4.9385518546437325e-05,
|
|
"loss": 0.9356,
|
|
"step": 165
|
|
},
|
|
{
|
|
"epoch": 0.07,
|
|
"learning_rate": 4.937803334568706e-05,
|
|
"loss": 0.8459,
|
|
"step": 166
|
|
},
|
|
{
|
|
"epoch": 0.07,
|
|
"learning_rate": 4.9370503404847304e-05,
|
|
"loss": 0.7772,
|
|
"step": 167
|
|
},
|
|
{
|
|
"epoch": 0.07,
|
|
"learning_rate": 4.9362928737737465e-05,
|
|
"loss": 0.9711,
|
|
"step": 168
|
|
},
|
|
{
|
|
"epoch": 0.07,
|
|
"learning_rate": 4.935530935825907e-05,
|
|
"loss": 0.849,
|
|
"step": 169
|
|
},
|
|
{
|
|
"epoch": 0.07,
|
|
"learning_rate": 4.934764528039566e-05,
|
|
"loss": 0.759,
|
|
"step": 170
|
|
},
|
|
{
|
|
"epoch": 0.07,
|
|
"learning_rate": 4.933993651821282e-05,
|
|
"loss": 0.7088,
|
|
"step": 171
|
|
},
|
|
{
|
|
"epoch": 0.07,
|
|
"learning_rate": 4.933218308585819e-05,
|
|
"loss": 0.6487,
|
|
"step": 172
|
|
},
|
|
{
|
|
"epoch": 0.07,
|
|
"learning_rate": 4.9324384997561315e-05,
|
|
"loss": 0.7925,
|
|
"step": 173
|
|
},
|
|
{
|
|
"epoch": 0.07,
|
|
"learning_rate": 4.931654226763375e-05,
|
|
"loss": 0.922,
|
|
"step": 174
|
|
},
|
|
{
|
|
"epoch": 0.08,
|
|
"learning_rate": 4.9308654910468964e-05,
|
|
"loss": 0.8621,
|
|
"step": 175
|
|
},
|
|
{
|
|
"epoch": 0.08,
|
|
"learning_rate": 4.930072294054233e-05,
|
|
"loss": 0.8429,
|
|
"step": 176
|
|
},
|
|
{
|
|
"epoch": 0.08,
|
|
"learning_rate": 4.929274637241108e-05,
|
|
"loss": 0.7388,
|
|
"step": 177
|
|
},
|
|
{
|
|
"epoch": 0.08,
|
|
"learning_rate": 4.9284725220714324e-05,
|
|
"loss": 0.8557,
|
|
"step": 178
|
|
},
|
|
{
|
|
"epoch": 0.08,
|
|
"learning_rate": 4.927665950017297e-05,
|
|
"loss": 0.8447,
|
|
"step": 179
|
|
},
|
|
{
|
|
"epoch": 0.08,
|
|
"learning_rate": 4.926854922558975e-05,
|
|
"loss": 0.8104,
|
|
"step": 180
|
|
},
|
|
{
|
|
"epoch": 0.08,
|
|
"learning_rate": 4.9260394411849134e-05,
|
|
"loss": 0.9483,
|
|
"step": 181
|
|
},
|
|
{
|
|
"epoch": 0.08,
|
|
"learning_rate": 4.9252195073917335e-05,
|
|
"loss": 0.7172,
|
|
"step": 182
|
|
},
|
|
{
|
|
"epoch": 0.08,
|
|
"learning_rate": 4.9243951226842305e-05,
|
|
"loss": 0.7127,
|
|
"step": 183
|
|
},
|
|
{
|
|
"epoch": 0.08,
|
|
"learning_rate": 4.9235662885753666e-05,
|
|
"loss": 0.7191,
|
|
"step": 184
|
|
},
|
|
{
|
|
"epoch": 0.08,
|
|
"learning_rate": 4.92273300658627e-05,
|
|
"loss": 0.7975,
|
|
"step": 185
|
|
},
|
|
{
|
|
"epoch": 0.08,
|
|
"learning_rate": 4.921895278246231e-05,
|
|
"loss": 0.7981,
|
|
"step": 186
|
|
},
|
|
{
|
|
"epoch": 0.08,
|
|
"learning_rate": 4.921053105092701e-05,
|
|
"loss": 0.7595,
|
|
"step": 187
|
|
},
|
|
{
|
|
"epoch": 0.08,
|
|
"learning_rate": 4.9202064886712906e-05,
|
|
"loss": 0.7376,
|
|
"step": 188
|
|
},
|
|
{
|
|
"epoch": 0.08,
|
|
"learning_rate": 4.919355430535761e-05,
|
|
"loss": 0.8999,
|
|
"step": 189
|
|
},
|
|
{
|
|
"epoch": 0.08,
|
|
"learning_rate": 4.9184999322480285e-05,
|
|
"loss": 0.8945,
|
|
"step": 190
|
|
},
|
|
{
|
|
"epoch": 0.08,
|
|
"learning_rate": 4.917639995378156e-05,
|
|
"loss": 0.7347,
|
|
"step": 191
|
|
},
|
|
{
|
|
"epoch": 0.08,
|
|
"learning_rate": 4.916775621504354e-05,
|
|
"loss": 0.8662,
|
|
"step": 192
|
|
},
|
|
{
|
|
"epoch": 0.08,
|
|
"learning_rate": 4.915906812212976e-05,
|
|
"loss": 0.6963,
|
|
"step": 193
|
|
},
|
|
{
|
|
"epoch": 0.08,
|
|
"learning_rate": 4.9150335690985136e-05,
|
|
"loss": 0.7317,
|
|
"step": 194
|
|
},
|
|
{
|
|
"epoch": 0.08,
|
|
"learning_rate": 4.9141558937635985e-05,
|
|
"loss": 0.8358,
|
|
"step": 195
|
|
},
|
|
{
|
|
"epoch": 0.08,
|
|
"learning_rate": 4.913273787818995e-05,
|
|
"loss": 0.7879,
|
|
"step": 196
|
|
},
|
|
{
|
|
"epoch": 0.08,
|
|
"learning_rate": 4.912387252883598e-05,
|
|
"loss": 0.8523,
|
|
"step": 197
|
|
},
|
|
{
|
|
"epoch": 0.09,
|
|
"learning_rate": 4.911496290584433e-05,
|
|
"loss": 0.8389,
|
|
"step": 198
|
|
},
|
|
{
|
|
"epoch": 0.09,
|
|
"learning_rate": 4.910600902556649e-05,
|
|
"loss": 0.7412,
|
|
"step": 199
|
|
},
|
|
{
|
|
"epoch": 0.09,
|
|
"learning_rate": 4.909701090443518e-05,
|
|
"loss": 0.8253,
|
|
"step": 200
|
|
},
|
|
{
|
|
"epoch": 0.09,
|
|
"eval_loss": 0.8050532341003418,
|
|
"eval_runtime": 10.2691,
|
|
"eval_samples_per_second": 3.603,
|
|
"eval_steps_per_second": 0.487,
|
|
"step": 200
|
|
},
|
|
{
|
|
"epoch": 0.09,
|
|
"learning_rate": 4.908796855896432e-05,
|
|
"loss": 0.7399,
|
|
"step": 201
|
|
},
|
|
{
|
|
"epoch": 0.09,
|
|
"learning_rate": 4.907888200574898e-05,
|
|
"loss": 0.9344,
|
|
"step": 202
|
|
},
|
|
{
|
|
"epoch": 0.09,
|
|
"learning_rate": 4.906975126146538e-05,
|
|
"loss": 0.8562,
|
|
"step": 203
|
|
},
|
|
{
|
|
"epoch": 0.09,
|
|
"learning_rate": 4.906057634287082e-05,
|
|
"loss": 0.7759,
|
|
"step": 204
|
|
},
|
|
{
|
|
"epoch": 0.09,
|
|
"learning_rate": 4.905135726680369e-05,
|
|
"loss": 0.7058,
|
|
"step": 205
|
|
},
|
|
{
|
|
"epoch": 0.09,
|
|
"learning_rate": 4.9042094050183415e-05,
|
|
"loss": 0.9686,
|
|
"step": 206
|
|
},
|
|
{
|
|
"epoch": 0.09,
|
|
"learning_rate": 4.9032786710010424e-05,
|
|
"loss": 0.9007,
|
|
"step": 207
|
|
},
|
|
{
|
|
"epoch": 0.09,
|
|
"learning_rate": 4.902343526336614e-05,
|
|
"loss": 0.8106,
|
|
"step": 208
|
|
},
|
|
{
|
|
"epoch": 0.09,
|
|
"learning_rate": 4.901403972741291e-05,
|
|
"loss": 0.8317,
|
|
"step": 209
|
|
},
|
|
{
|
|
"epoch": 0.09,
|
|
"learning_rate": 4.900460011939402e-05,
|
|
"loss": 0.9889,
|
|
"step": 210
|
|
},
|
|
{
|
|
"epoch": 0.09,
|
|
"learning_rate": 4.899511645663361e-05,
|
|
"loss": 0.7061,
|
|
"step": 211
|
|
},
|
|
{
|
|
"epoch": 0.09,
|
|
"learning_rate": 4.898558875653671e-05,
|
|
"loss": 0.9084,
|
|
"step": 212
|
|
},
|
|
{
|
|
"epoch": 0.09,
|
|
"learning_rate": 4.897601703658914e-05,
|
|
"loss": 0.8296,
|
|
"step": 213
|
|
},
|
|
{
|
|
"epoch": 0.09,
|
|
"learning_rate": 4.896640131435751e-05,
|
|
"loss": 0.7512,
|
|
"step": 214
|
|
},
|
|
{
|
|
"epoch": 0.09,
|
|
"learning_rate": 4.8956741607489215e-05,
|
|
"loss": 0.7808,
|
|
"step": 215
|
|
},
|
|
{
|
|
"epoch": 0.09,
|
|
"learning_rate": 4.8947037933712335e-05,
|
|
"loss": 0.8168,
|
|
"step": 216
|
|
},
|
|
{
|
|
"epoch": 0.09,
|
|
"learning_rate": 4.893729031083567e-05,
|
|
"loss": 0.6904,
|
|
"step": 217
|
|
},
|
|
{
|
|
"epoch": 0.09,
|
|
"learning_rate": 4.8927498756748664e-05,
|
|
"loss": 0.8154,
|
|
"step": 218
|
|
},
|
|
{
|
|
"epoch": 0.09,
|
|
"learning_rate": 4.891766328942138e-05,
|
|
"loss": 0.732,
|
|
"step": 219
|
|
},
|
|
{
|
|
"epoch": 0.09,
|
|
"learning_rate": 4.8907783926904495e-05,
|
|
"loss": 0.833,
|
|
"step": 220
|
|
},
|
|
{
|
|
"epoch": 0.1,
|
|
"learning_rate": 4.889786068732921e-05,
|
|
"loss": 0.7308,
|
|
"step": 221
|
|
},
|
|
{
|
|
"epoch": 0.1,
|
|
"learning_rate": 4.8887893588907304e-05,
|
|
"loss": 0.8428,
|
|
"step": 222
|
|
},
|
|
{
|
|
"epoch": 0.1,
|
|
"learning_rate": 4.8877882649930995e-05,
|
|
"loss": 0.735,
|
|
"step": 223
|
|
},
|
|
{
|
|
"epoch": 0.1,
|
|
"learning_rate": 4.8867827888773e-05,
|
|
"loss": 0.6815,
|
|
"step": 224
|
|
},
|
|
{
|
|
"epoch": 0.1,
|
|
"learning_rate": 4.885772932388642e-05,
|
|
"loss": 0.8329,
|
|
"step": 225
|
|
},
|
|
{
|
|
"epoch": 0.1,
|
|
"learning_rate": 4.884758697380481e-05,
|
|
"loss": 0.7601,
|
|
"step": 226
|
|
},
|
|
{
|
|
"epoch": 0.1,
|
|
"learning_rate": 4.8837400857142015e-05,
|
|
"loss": 0.7283,
|
|
"step": 227
|
|
},
|
|
{
|
|
"epoch": 0.1,
|
|
"learning_rate": 4.882717099259224e-05,
|
|
"loss": 0.7835,
|
|
"step": 228
|
|
},
|
|
{
|
|
"epoch": 0.1,
|
|
"learning_rate": 4.8816897398929975e-05,
|
|
"loss": 0.7538,
|
|
"step": 229
|
|
},
|
|
{
|
|
"epoch": 0.1,
|
|
"learning_rate": 4.880658009500995e-05,
|
|
"loss": 0.6243,
|
|
"step": 230
|
|
},
|
|
{
|
|
"epoch": 0.1,
|
|
"learning_rate": 4.8796219099767136e-05,
|
|
"loss": 0.7844,
|
|
"step": 231
|
|
},
|
|
{
|
|
"epoch": 0.1,
|
|
"learning_rate": 4.878581443221668e-05,
|
|
"loss": 0.8362,
|
|
"step": 232
|
|
},
|
|
{
|
|
"epoch": 0.1,
|
|
"learning_rate": 4.877536611145388e-05,
|
|
"loss": 0.7069,
|
|
"step": 233
|
|
},
|
|
{
|
|
"epoch": 0.1,
|
|
"learning_rate": 4.876487415665413e-05,
|
|
"loss": 0.7603,
|
|
"step": 234
|
|
},
|
|
{
|
|
"epoch": 0.1,
|
|
"learning_rate": 4.875433858707293e-05,
|
|
"loss": 0.8936,
|
|
"step": 235
|
|
},
|
|
{
|
|
"epoch": 0.1,
|
|
"learning_rate": 4.874375942204583e-05,
|
|
"loss": 0.7754,
|
|
"step": 236
|
|
},
|
|
{
|
|
"epoch": 0.1,
|
|
"learning_rate": 4.8733136680988355e-05,
|
|
"loss": 0.7515,
|
|
"step": 237
|
|
},
|
|
{
|
|
"epoch": 0.1,
|
|
"learning_rate": 4.8722470383396024e-05,
|
|
"loss": 0.7706,
|
|
"step": 238
|
|
},
|
|
{
|
|
"epoch": 0.1,
|
|
"learning_rate": 4.871176054884431e-05,
|
|
"loss": 0.7938,
|
|
"step": 239
|
|
},
|
|
{
|
|
"epoch": 0.1,
|
|
"learning_rate": 4.870100719698854e-05,
|
|
"loss": 0.7918,
|
|
"step": 240
|
|
},
|
|
{
|
|
"epoch": 0.1,
|
|
"learning_rate": 4.8690210347563975e-05,
|
|
"loss": 0.9421,
|
|
"step": 241
|
|
},
|
|
{
|
|
"epoch": 0.1,
|
|
"learning_rate": 4.867937002038564e-05,
|
|
"loss": 0.7249,
|
|
"step": 242
|
|
},
|
|
{
|
|
"epoch": 0.1,
|
|
"learning_rate": 4.866848623534839e-05,
|
|
"loss": 0.7552,
|
|
"step": 243
|
|
},
|
|
{
|
|
"epoch": 0.11,
|
|
"learning_rate": 4.865755901242682e-05,
|
|
"loss": 0.7415,
|
|
"step": 244
|
|
},
|
|
{
|
|
"epoch": 0.11,
|
|
"learning_rate": 4.864658837167526e-05,
|
|
"loss": 0.7475,
|
|
"step": 245
|
|
},
|
|
{
|
|
"epoch": 0.11,
|
|
"learning_rate": 4.863557433322771e-05,
|
|
"loss": 0.8791,
|
|
"step": 246
|
|
},
|
|
{
|
|
"epoch": 0.11,
|
|
"learning_rate": 4.862451691729783e-05,
|
|
"loss": 0.8837,
|
|
"step": 247
|
|
},
|
|
{
|
|
"epoch": 0.11,
|
|
"learning_rate": 4.861341614417887e-05,
|
|
"loss": 0.7218,
|
|
"step": 248
|
|
},
|
|
{
|
|
"epoch": 0.11,
|
|
"learning_rate": 4.860227203424367e-05,
|
|
"loss": 0.8089,
|
|
"step": 249
|
|
},
|
|
{
|
|
"epoch": 0.11,
|
|
"learning_rate": 4.8591084607944595e-05,
|
|
"loss": 0.9958,
|
|
"step": 250
|
|
},
|
|
{
|
|
"epoch": 0.11,
|
|
"learning_rate": 4.85798538858135e-05,
|
|
"loss": 0.861,
|
|
"step": 251
|
|
},
|
|
{
|
|
"epoch": 0.11,
|
|
"learning_rate": 4.856857988846172e-05,
|
|
"loss": 0.783,
|
|
"step": 252
|
|
},
|
|
{
|
|
"epoch": 0.11,
|
|
"learning_rate": 4.855726263657999e-05,
|
|
"loss": 0.8853,
|
|
"step": 253
|
|
},
|
|
{
|
|
"epoch": 0.11,
|
|
"learning_rate": 4.8545902150938436e-05,
|
|
"loss": 0.7947,
|
|
"step": 254
|
|
},
|
|
{
|
|
"epoch": 0.11,
|
|
"learning_rate": 4.8534498452386543e-05,
|
|
"loss": 0.7206,
|
|
"step": 255
|
|
},
|
|
{
|
|
"epoch": 0.11,
|
|
"learning_rate": 4.8523051561853084e-05,
|
|
"loss": 0.8859,
|
|
"step": 256
|
|
},
|
|
{
|
|
"epoch": 0.11,
|
|
"learning_rate": 4.851156150034611e-05,
|
|
"loss": 0.745,
|
|
"step": 257
|
|
},
|
|
{
|
|
"epoch": 0.11,
|
|
"learning_rate": 4.850002828895289e-05,
|
|
"loss": 0.9045,
|
|
"step": 258
|
|
},
|
|
{
|
|
"epoch": 0.11,
|
|
"learning_rate": 4.8488451948839905e-05,
|
|
"loss": 0.6362,
|
|
"step": 259
|
|
},
|
|
{
|
|
"epoch": 0.11,
|
|
"learning_rate": 4.847683250125277e-05,
|
|
"loss": 0.8622,
|
|
"step": 260
|
|
},
|
|
{
|
|
"epoch": 0.11,
|
|
"learning_rate": 4.8465169967516235e-05,
|
|
"loss": 0.7037,
|
|
"step": 261
|
|
},
|
|
{
|
|
"epoch": 0.11,
|
|
"learning_rate": 4.845346436903408e-05,
|
|
"loss": 0.9182,
|
|
"step": 262
|
|
},
|
|
{
|
|
"epoch": 0.11,
|
|
"learning_rate": 4.844171572728919e-05,
|
|
"loss": 1.0684,
|
|
"step": 263
|
|
},
|
|
{
|
|
"epoch": 0.11,
|
|
"learning_rate": 4.842992406384338e-05,
|
|
"loss": 0.7909,
|
|
"step": 264
|
|
},
|
|
{
|
|
"epoch": 0.11,
|
|
"learning_rate": 4.8418089400337444e-05,
|
|
"loss": 0.8534,
|
|
"step": 265
|
|
},
|
|
{
|
|
"epoch": 0.11,
|
|
"learning_rate": 4.840621175849112e-05,
|
|
"loss": 0.8092,
|
|
"step": 266
|
|
},
|
|
{
|
|
"epoch": 0.12,
|
|
"learning_rate": 4.839429116010297e-05,
|
|
"loss": 0.7109,
|
|
"step": 267
|
|
},
|
|
{
|
|
"epoch": 0.12,
|
|
"learning_rate": 4.838232762705044e-05,
|
|
"loss": 0.5593,
|
|
"step": 268
|
|
},
|
|
{
|
|
"epoch": 0.12,
|
|
"learning_rate": 4.8370321181289754e-05,
|
|
"loss": 0.6169,
|
|
"step": 269
|
|
},
|
|
{
|
|
"epoch": 0.12,
|
|
"learning_rate": 4.835827184485587e-05,
|
|
"loss": 0.7919,
|
|
"step": 270
|
|
},
|
|
{
|
|
"epoch": 0.12,
|
|
"learning_rate": 4.834617963986251e-05,
|
|
"loss": 0.8294,
|
|
"step": 271
|
|
},
|
|
{
|
|
"epoch": 0.12,
|
|
"learning_rate": 4.833404458850203e-05,
|
|
"loss": 0.9067,
|
|
"step": 272
|
|
},
|
|
{
|
|
"epoch": 0.12,
|
|
"learning_rate": 4.832186671304543e-05,
|
|
"loss": 0.8037,
|
|
"step": 273
|
|
},
|
|
{
|
|
"epoch": 0.12,
|
|
"learning_rate": 4.8309646035842316e-05,
|
|
"loss": 0.7649,
|
|
"step": 274
|
|
},
|
|
{
|
|
"epoch": 0.12,
|
|
"learning_rate": 4.829738257932084e-05,
|
|
"loss": 0.736,
|
|
"step": 275
|
|
},
|
|
{
|
|
"epoch": 0.12,
|
|
"learning_rate": 4.8285076365987646e-05,
|
|
"loss": 0.6717,
|
|
"step": 276
|
|
},
|
|
{
|
|
"epoch": 0.12,
|
|
"learning_rate": 4.827272741842789e-05,
|
|
"loss": 0.8744,
|
|
"step": 277
|
|
},
|
|
{
|
|
"epoch": 0.12,
|
|
"learning_rate": 4.826033575930512e-05,
|
|
"loss": 0.8303,
|
|
"step": 278
|
|
},
|
|
{
|
|
"epoch": 0.12,
|
|
"learning_rate": 4.824790141136127e-05,
|
|
"loss": 0.8506,
|
|
"step": 279
|
|
},
|
|
{
|
|
"epoch": 0.12,
|
|
"learning_rate": 4.823542439741666e-05,
|
|
"loss": 0.7496,
|
|
"step": 280
|
|
},
|
|
{
|
|
"epoch": 0.12,
|
|
"learning_rate": 4.822290474036987e-05,
|
|
"loss": 0.8215,
|
|
"step": 281
|
|
},
|
|
{
|
|
"epoch": 0.12,
|
|
"learning_rate": 4.821034246319774e-05,
|
|
"loss": 0.8849,
|
|
"step": 282
|
|
},
|
|
{
|
|
"epoch": 0.12,
|
|
"learning_rate": 4.819773758895538e-05,
|
|
"loss": 0.7652,
|
|
"step": 283
|
|
},
|
|
{
|
|
"epoch": 0.12,
|
|
"learning_rate": 4.818509014077602e-05,
|
|
"loss": 0.7457,
|
|
"step": 284
|
|
},
|
|
{
|
|
"epoch": 0.12,
|
|
"learning_rate": 4.817240014187105e-05,
|
|
"loss": 0.7701,
|
|
"step": 285
|
|
},
|
|
{
|
|
"epoch": 0.12,
|
|
"learning_rate": 4.8159667615529954e-05,
|
|
"loss": 0.7975,
|
|
"step": 286
|
|
},
|
|
{
|
|
"epoch": 0.12,
|
|
"learning_rate": 4.814689258512025e-05,
|
|
"loss": 0.7421,
|
|
"step": 287
|
|
},
|
|
{
|
|
"epoch": 0.12,
|
|
"learning_rate": 4.813407507408748e-05,
|
|
"loss": 0.771,
|
|
"step": 288
|
|
},
|
|
{
|
|
"epoch": 0.12,
|
|
"learning_rate": 4.8121215105955145e-05,
|
|
"loss": 0.7896,
|
|
"step": 289
|
|
},
|
|
{
|
|
"epoch": 0.12,
|
|
"learning_rate": 4.8108312704324654e-05,
|
|
"loss": 0.6527,
|
|
"step": 290
|
|
},
|
|
{
|
|
"epoch": 0.13,
|
|
"learning_rate": 4.8095367892875295e-05,
|
|
"loss": 0.7029,
|
|
"step": 291
|
|
},
|
|
{
|
|
"epoch": 0.13,
|
|
"learning_rate": 4.80823806953642e-05,
|
|
"loss": 0.7148,
|
|
"step": 292
|
|
},
|
|
{
|
|
"epoch": 0.13,
|
|
"learning_rate": 4.80693511356263e-05,
|
|
"loss": 0.7192,
|
|
"step": 293
|
|
},
|
|
{
|
|
"epoch": 0.13,
|
|
"learning_rate": 4.8056279237574234e-05,
|
|
"loss": 0.8897,
|
|
"step": 294
|
|
},
|
|
{
|
|
"epoch": 0.13,
|
|
"learning_rate": 4.8043165025198375e-05,
|
|
"loss": 0.9168,
|
|
"step": 295
|
|
},
|
|
{
|
|
"epoch": 0.13,
|
|
"learning_rate": 4.803000852256675e-05,
|
|
"loss": 0.6315,
|
|
"step": 296
|
|
},
|
|
{
|
|
"epoch": 0.13,
|
|
"learning_rate": 4.801680975382499e-05,
|
|
"loss": 0.8135,
|
|
"step": 297
|
|
},
|
|
{
|
|
"epoch": 0.13,
|
|
"learning_rate": 4.800356874319629e-05,
|
|
"loss": 0.8978,
|
|
"step": 298
|
|
},
|
|
{
|
|
"epoch": 0.13,
|
|
"learning_rate": 4.79902855149814e-05,
|
|
"loss": 0.8826,
|
|
"step": 299
|
|
},
|
|
{
|
|
"epoch": 0.13,
|
|
"learning_rate": 4.797696009355851e-05,
|
|
"loss": 0.8169,
|
|
"step": 300
|
|
},
|
|
{
|
|
"epoch": 0.13,
|
|
"eval_loss": 0.795865535736084,
|
|
"eval_runtime": 10.328,
|
|
"eval_samples_per_second": 3.582,
|
|
"eval_steps_per_second": 0.484,
|
|
"step": 300
|
|
}
|
|
],
|
|
"logging_steps": 1,
|
|
"max_steps": 2320,
|
|
"num_input_tokens_seen": 0,
|
|
"num_train_epochs": 1,
|
|
"save_steps": 100,
|
|
"total_flos": 4.218776992088064e+17,
|
|
"train_batch_size": 4,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|