File size: 5,227 Bytes
17f1dd8 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 |
{
"best_metric": 0.13781137764453888,
"best_model_checkpoint": "/data/jcanete/all_results/mldoc/distillbeto/epochs_3_bs_16_lr_2e-5/checkpoint-900",
"epoch": 3.0,
"global_step": 1776,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.17,
"eval_accuracy": 0.7329999804496765,
"eval_loss": 0.9082120656967163,
"eval_runtime": 2.085,
"eval_samples_per_second": 479.613,
"eval_steps_per_second": 30.216,
"step": 100
},
{
"epoch": 0.34,
"eval_accuracy": 0.8560000061988831,
"eval_loss": 0.47957685589790344,
"eval_runtime": 2.0816,
"eval_samples_per_second": 480.41,
"eval_steps_per_second": 30.266,
"step": 200
},
{
"epoch": 0.51,
"eval_accuracy": 0.9480000138282776,
"eval_loss": 0.23153278231620789,
"eval_runtime": 2.0846,
"eval_samples_per_second": 479.697,
"eval_steps_per_second": 30.221,
"step": 300
},
{
"epoch": 0.68,
"eval_accuracy": 0.9309999942779541,
"eval_loss": 0.25234749913215637,
"eval_runtime": 2.0857,
"eval_samples_per_second": 479.464,
"eval_steps_per_second": 30.206,
"step": 400
},
{
"epoch": 0.84,
"learning_rate": 1.4391891891891894e-05,
"loss": 0.1569,
"step": 500
},
{
"epoch": 0.84,
"eval_accuracy": 0.9539999961853027,
"eval_loss": 0.18860605359077454,
"eval_runtime": 2.0884,
"eval_samples_per_second": 478.832,
"eval_steps_per_second": 30.166,
"step": 500
},
{
"epoch": 1.01,
"eval_accuracy": 0.9020000100135803,
"eval_loss": 0.3387507200241089,
"eval_runtime": 2.0825,
"eval_samples_per_second": 480.196,
"eval_steps_per_second": 30.252,
"step": 600
},
{
"epoch": 1.18,
"eval_accuracy": 0.9610000252723694,
"eval_loss": 0.16218014061450958,
"eval_runtime": 2.0844,
"eval_samples_per_second": 479.763,
"eval_steps_per_second": 30.225,
"step": 700
},
{
"epoch": 1.35,
"eval_accuracy": 0.9509999752044678,
"eval_loss": 0.18978460133075714,
"eval_runtime": 2.0789,
"eval_samples_per_second": 481.026,
"eval_steps_per_second": 30.305,
"step": 800
},
{
"epoch": 1.52,
"eval_accuracy": 0.9710000157356262,
"eval_loss": 0.13781137764453888,
"eval_runtime": 2.0825,
"eval_samples_per_second": 480.201,
"eval_steps_per_second": 30.253,
"step": 900
},
{
"epoch": 1.69,
"learning_rate": 8.772522522522522e-06,
"loss": 0.0617,
"step": 1000
},
{
"epoch": 1.69,
"eval_accuracy": 0.9610000252723694,
"eval_loss": 0.1706898957490921,
"eval_runtime": 2.0817,
"eval_samples_per_second": 480.376,
"eval_steps_per_second": 30.264,
"step": 1000
},
{
"epoch": 1.86,
"eval_accuracy": 0.9599999785423279,
"eval_loss": 0.1884380429983139,
"eval_runtime": 2.08,
"eval_samples_per_second": 480.775,
"eval_steps_per_second": 30.289,
"step": 1100
},
{
"epoch": 2.03,
"eval_accuracy": 0.9570000171661377,
"eval_loss": 0.20238688588142395,
"eval_runtime": 2.0822,
"eval_samples_per_second": 480.271,
"eval_steps_per_second": 30.257,
"step": 1200
},
{
"epoch": 2.2,
"eval_accuracy": 0.9589999914169312,
"eval_loss": 0.1709979772567749,
"eval_runtime": 2.0789,
"eval_samples_per_second": 481.035,
"eval_steps_per_second": 30.305,
"step": 1300
},
{
"epoch": 2.36,
"eval_accuracy": 0.9610000252723694,
"eval_loss": 0.1705155074596405,
"eval_runtime": 2.0769,
"eval_samples_per_second": 481.48,
"eval_steps_per_second": 30.333,
"step": 1400
},
{
"epoch": 2.53,
"learning_rate": 3.141891891891892e-06,
"loss": 0.0353,
"step": 1500
},
{
"epoch": 2.53,
"eval_accuracy": 0.9570000171661377,
"eval_loss": 0.18021175265312195,
"eval_runtime": 2.0858,
"eval_samples_per_second": 479.427,
"eval_steps_per_second": 30.204,
"step": 1500
},
{
"epoch": 2.7,
"eval_accuracy": 0.9520000219345093,
"eval_loss": 0.19292205572128296,
"eval_runtime": 2.0769,
"eval_samples_per_second": 481.487,
"eval_steps_per_second": 30.334,
"step": 1600
},
{
"epoch": 2.87,
"eval_accuracy": 0.9570000171661377,
"eval_loss": 0.1787494271993637,
"eval_runtime": 2.0981,
"eval_samples_per_second": 476.617,
"eval_steps_per_second": 30.027,
"step": 1700
},
{
"epoch": 3.0,
"step": 1776,
"total_flos": 3142677580766976.0,
"train_loss": 0.077526035609546,
"train_runtime": 3451.0165,
"train_samples_per_second": 8.222,
"train_steps_per_second": 0.515
}
],
"max_steps": 1776,
"num_train_epochs": 3,
"total_flos": 3142677580766976.0,
"trial_name": null,
"trial_params": null
}
|