File size: 4,341 Bytes
9280b93 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 |
{
"best_metric": 0.9461009174311926,
"best_model_checkpoint": "./electra-base-discriminator/fine_tuned_models/checkpoint-8420",
"epoch": 10.0,
"global_step": 21050,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"learning_rate": 1.8398562688161604e-05,
"loss": 0.2346,
"step": 2105
},
{
"epoch": 1.0,
"eval_accuracy": 0.9426605504587156,
"eval_loss": 0.21175895631313324,
"eval_runtime": 2.2043,
"eval_samples_per_second": 395.593,
"eval_steps_per_second": 49.449,
"step": 2105
},
{
"epoch": 2.0,
"learning_rate": 1.6354277945032536e-05,
"loss": 0.1204,
"step": 4210
},
{
"epoch": 2.0,
"eval_accuracy": 0.9438073394495413,
"eval_loss": 0.19780370593070984,
"eval_runtime": 2.1909,
"eval_samples_per_second": 398.006,
"eval_steps_per_second": 49.751,
"step": 4210
},
{
"epoch": 3.0,
"learning_rate": 1.4309993201903469e-05,
"loss": 0.0893,
"step": 6315
},
{
"epoch": 3.0,
"eval_accuracy": 0.9415137614678899,
"eval_loss": 0.2090323567390442,
"eval_runtime": 2.2098,
"eval_samples_per_second": 394.601,
"eval_steps_per_second": 49.325,
"step": 6315
},
{
"epoch": 4.0,
"learning_rate": 1.2265708458774402e-05,
"loss": 0.0708,
"step": 8420
},
{
"epoch": 4.0,
"eval_accuracy": 0.9461009174311926,
"eval_loss": 0.22068844735622406,
"eval_runtime": 2.1815,
"eval_samples_per_second": 399.725,
"eval_steps_per_second": 49.966,
"step": 8420
},
{
"epoch": 5.0,
"learning_rate": 1.0221423715645335e-05,
"loss": 0.0539,
"step": 10525
},
{
"epoch": 5.0,
"eval_accuracy": 0.9461009174311926,
"eval_loss": 0.21388141810894012,
"eval_runtime": 2.1881,
"eval_samples_per_second": 398.521,
"eval_steps_per_second": 49.815,
"step": 10525
},
{
"epoch": 6.0,
"learning_rate": 8.177138972516268e-06,
"loss": 0.0424,
"step": 12630
},
{
"epoch": 6.0,
"eval_accuracy": 0.9438073394495413,
"eval_loss": 0.23279055953025818,
"eval_runtime": 2.1898,
"eval_samples_per_second": 398.209,
"eval_steps_per_second": 49.776,
"step": 12630
},
{
"epoch": 7.0,
"learning_rate": 6.132854229387201e-06,
"loss": 0.0316,
"step": 14735
},
{
"epoch": 7.0,
"eval_accuracy": 0.9392201834862385,
"eval_loss": 0.27414366602897644,
"eval_runtime": 2.1831,
"eval_samples_per_second": 399.423,
"eval_steps_per_second": 49.928,
"step": 14735
},
{
"epoch": 8.0,
"learning_rate": 4.088569486258134e-06,
"loss": 0.0259,
"step": 16840
},
{
"epoch": 8.0,
"eval_accuracy": 0.9369266055045872,
"eval_loss": 0.3532903790473938,
"eval_runtime": 2.1863,
"eval_samples_per_second": 398.847,
"eval_steps_per_second": 49.856,
"step": 16840
},
{
"epoch": 9.0,
"learning_rate": 2.044284743129067e-06,
"loss": 0.0184,
"step": 18945
},
{
"epoch": 9.0,
"eval_accuracy": 0.9369266055045872,
"eval_loss": 0.3735915720462799,
"eval_runtime": 2.1998,
"eval_samples_per_second": 396.399,
"eval_steps_per_second": 49.55,
"step": 18945
},
{
"epoch": 10.0,
"learning_rate": 0.0,
"loss": 0.0137,
"step": 21050
},
{
"epoch": 10.0,
"eval_accuracy": 0.9357798165137615,
"eval_loss": 0.39657318592071533,
"eval_runtime": 2.1994,
"eval_samples_per_second": 396.467,
"eval_steps_per_second": 49.558,
"step": 21050
},
{
"epoch": 10.0,
"step": 21050,
"total_flos": 2.831471218376448e+16,
"train_loss": 0.07010283381808682,
"train_runtime": 4415.7756,
"train_samples_per_second": 152.519,
"train_steps_per_second": 4.767
}
],
"max_steps": 21050,
"num_train_epochs": 10,
"total_flos": 2.831471218376448e+16,
"trial_name": null,
"trial_params": null
}
|