File size: 3,246 Bytes
35b297d |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 |
{
"best_metric": 0.19848246486644372,
"best_model_checkpoint": "esm2_t6_8M_qlora_binding_sites_2023-09-29_03-34-40/checkpoint-3939",
"epoch": 1.0,
"eval_steps": 500,
"global_step": 3939,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.05,
"learning_rate": 0.0003700096638060586,
"loss": 0.5009,
"step": 200
},
{
"epoch": 0.1,
"learning_rate": 0.0003695684724487918,
"loss": 0.3725,
"step": 400
},
{
"epoch": 0.15,
"learning_rate": 0.00036883393302294926,
"loss": 0.3363,
"step": 600
},
{
"epoch": 0.2,
"learning_rate": 0.0003678072134814851,
"loss": 0.3171,
"step": 800
},
{
"epoch": 0.25,
"learning_rate": 0.0003664899463577655,
"loss": 0.3041,
"step": 1000
},
{
"epoch": 0.3,
"learning_rate": 0.00036488422616976233,
"loss": 0.2954,
"step": 1200
},
{
"epoch": 0.36,
"learning_rate": 0.0003629926060896693,
"loss": 0.2872,
"step": 1400
},
{
"epoch": 0.41,
"learning_rate": 0.00036081809388423475,
"loss": 0.2804,
"step": 1600
},
{
"epoch": 0.46,
"learning_rate": 0.0003583641471322691,
"loss": 0.2754,
"step": 1800
},
{
"epoch": 0.51,
"learning_rate": 0.00035563466772692797,
"loss": 0.2696,
"step": 2000
},
{
"epoch": 0.56,
"learning_rate": 0.0003526339956715147,
"loss": 0.2675,
"step": 2200
},
{
"epoch": 0.61,
"learning_rate": 0.00034936690217866705,
"loss": 0.2642,
"step": 2400
},
{
"epoch": 0.66,
"learning_rate": 0.00034583858208389975,
"loss": 0.262,
"step": 2600
},
{
"epoch": 0.71,
"learning_rate": 0.0003420546455855667,
"loss": 0.2592,
"step": 2800
},
{
"epoch": 0.76,
"learning_rate": 0.00033802110932437625,
"loss": 0.2565,
"step": 3000
},
{
"epoch": 0.81,
"learning_rate": 0.0003337443868166437,
"loss": 0.2542,
"step": 3200
},
{
"epoch": 0.86,
"learning_rate": 0.00032923127825649205,
"loss": 0.2509,
"step": 3400
},
{
"epoch": 0.91,
"learning_rate": 0.00032448895970321745,
"loss": 0.2509,
"step": 3600
},
{
"epoch": 0.96,
"learning_rate": 0.0003195249716710097,
"loss": 0.2464,
"step": 3800
},
{
"epoch": 1.0,
"eval_accuracy": 0.8625347674451358,
"eval_auc": 0.8222331548742136,
"eval_f1": 0.19848246486644372,
"eval_loss": 0.41490185260772705,
"eval_mcc": 0.2639007297474409,
"eval_precision": 0.11370668247419904,
"eval_recall": 0.7800926533683039,
"eval_runtime": 1163.712,
"eval_samples_per_second": 109.693,
"eval_steps_per_second": 1.714,
"step": 3939
}
],
"logging_steps": 200,
"max_steps": 15756,
"num_train_epochs": 4,
"save_steps": 500,
"total_flos": 2.0257292207917116e+16,
"trial_name": null,
"trial_params": null
}
|