File size: 5,024 Bytes
00d7b7f |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 |
{
"best_metric": 0.3247086703777313,
"best_model_checkpoint": "outputs/electra-nli-efl/checkpoint-1050",
"epoch": 11.995555555555555,
"global_step": 2520,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"learning_rate": 9.499999999999999e-07,
"loss": 0.4175,
"step": 210
},
{
"epoch": 1.0,
"eval_accuracy": 0.7316666666666667,
"eval_f1": 0.7305281480923569,
"eval_loss": 0.4019607603549957,
"eval_runtime": 11.5986,
"eval_samples_per_second": 258.651,
"eval_steps_per_second": 32.331,
"step": 210
},
{
"epoch": 2.0,
"learning_rate": 9e-07,
"loss": 0.3061,
"step": 420
},
{
"epoch": 2.0,
"eval_accuracy": 0.768,
"eval_f1": 0.7674936528439713,
"eval_loss": 0.3519645631313324,
"eval_runtime": 11.6033,
"eval_samples_per_second": 258.548,
"eval_steps_per_second": 32.319,
"step": 420
},
{
"epoch": 3.0,
"learning_rate": 8.499999999999999e-07,
"loss": 0.2588,
"step": 630
},
{
"epoch": 3.0,
"eval_accuracy": 0.79,
"eval_f1": 0.7887799932409598,
"eval_loss": 0.32531991600990295,
"eval_runtime": 11.5951,
"eval_samples_per_second": 258.729,
"eval_steps_per_second": 32.341,
"step": 630
},
{
"epoch": 4.0,
"learning_rate": 8e-07,
"loss": 0.234,
"step": 840
},
{
"epoch": 4.0,
"eval_accuracy": 0.788,
"eval_f1": 0.7877041067016072,
"eval_loss": 0.33730262517929077,
"eval_runtime": 11.6935,
"eval_samples_per_second": 256.553,
"eval_steps_per_second": 32.069,
"step": 840
},
{
"epoch": 5.0,
"learning_rate": 7.5e-07,
"loss": 0.2116,
"step": 1050
},
{
"epoch": 5.0,
"eval_accuracy": 0.804,
"eval_f1": 0.8032759681298146,
"eval_loss": 0.3247086703777313,
"eval_runtime": 11.5938,
"eval_samples_per_second": 258.758,
"eval_steps_per_second": 32.345,
"step": 1050
},
{
"epoch": 6.0,
"learning_rate": 7e-07,
"loss": 0.1974,
"step": 1260
},
{
"epoch": 6.0,
"eval_accuracy": 0.793,
"eval_f1": 0.7928414316247181,
"eval_loss": 0.34000951051712036,
"eval_runtime": 11.6038,
"eval_samples_per_second": 258.537,
"eval_steps_per_second": 32.317,
"step": 1260
},
{
"epoch": 7.0,
"learning_rate": 6.5e-07,
"loss": 0.1807,
"step": 1470
},
{
"epoch": 7.0,
"eval_accuracy": 0.7973333333333333,
"eval_f1": 0.7969281824938732,
"eval_loss": 0.35112178325653076,
"eval_runtime": 11.589,
"eval_samples_per_second": 258.866,
"eval_steps_per_second": 32.358,
"step": 1470
},
{
"epoch": 8.0,
"learning_rate": 6e-07,
"loss": 0.1715,
"step": 1680
},
{
"epoch": 8.0,
"eval_accuracy": 0.7993333333333333,
"eval_f1": 0.79885693716362,
"eval_loss": 0.34963640570640564,
"eval_runtime": 11.6019,
"eval_samples_per_second": 258.579,
"eval_steps_per_second": 32.322,
"step": 1680
},
{
"epoch": 9.0,
"learning_rate": 5.5e-07,
"loss": 0.1577,
"step": 1890
},
{
"epoch": 9.0,
"eval_accuracy": 0.8043333333333333,
"eval_f1": 0.803166306363764,
"eval_loss": 0.3507426679134369,
"eval_runtime": 11.6051,
"eval_samples_per_second": 258.507,
"eval_steps_per_second": 32.313,
"step": 1890
},
{
"epoch": 10.0,
"learning_rate": 5e-07,
"loss": 0.1469,
"step": 2100
},
{
"epoch": 10.0,
"eval_accuracy": 0.798,
"eval_f1": 0.7970242731280681,
"eval_loss": 0.3604212701320648,
"eval_runtime": 11.7325,
"eval_samples_per_second": 255.699,
"eval_steps_per_second": 31.962,
"step": 2100
},
{
"epoch": 11.0,
"learning_rate": 4.5e-07,
"loss": 0.1394,
"step": 2310
},
{
"epoch": 11.0,
"eval_accuracy": 0.7966666666666666,
"eval_f1": 0.7957033854293423,
"eval_loss": 0.37343233823776245,
"eval_runtime": 11.6069,
"eval_samples_per_second": 258.468,
"eval_steps_per_second": 32.308,
"step": 2310
},
{
"epoch": 12.0,
"learning_rate": 4e-07,
"loss": 0.1322,
"step": 2520
},
{
"epoch": 12.0,
"eval_accuracy": 0.7913333333333333,
"eval_f1": 0.7905794192426068,
"eval_loss": 0.39285749197006226,
"eval_runtime": 11.6585,
"eval_samples_per_second": 257.322,
"eval_steps_per_second": 32.165,
"step": 2520
}
],
"max_steps": 4200,
"num_train_epochs": 20,
"total_flos": 4.992291637199885e+16,
"trial_name": null,
"trial_params": null
}
|