File size: 6,200 Bytes
2c85068 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 |
{
"best_metric": 0.5068484544754028,
"best_model_checkpoint": "/mnt/beegfs/farid/mlora/outputs/xnli/aya-101/zh/rank4_lr5e-5/checkpoint-4000",
"epoch": 0.24445893089960888,
"eval_steps": 500,
"global_step": 6000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.020371577574967405,
"grad_norm": 2.87671160697937,
"learning_rate": 4.166666666666667e-05,
"loss": 1.201,
"step": 500
},
{
"epoch": 0.020371577574967405,
"eval_accuracy": 0.3718875502008032,
"eval_f1": 0.3144388665500335,
"eval_loss": 1.0995594263076782,
"eval_runtime": 413.743,
"eval_samples_per_second": 6.018,
"eval_steps_per_second": 0.377,
"step": 500
},
{
"epoch": 0.04074315514993481,
"grad_norm": 9.780874252319336,
"learning_rate": 4.62962962962963e-05,
"loss": 1.0225,
"step": 1000
},
{
"epoch": 0.04074315514993481,
"eval_accuracy": 0.6277108433734939,
"eval_f1": 0.6294051779002606,
"eval_loss": 0.9010089039802551,
"eval_runtime": 411.7026,
"eval_samples_per_second": 6.048,
"eval_steps_per_second": 0.379,
"step": 1000
},
{
"epoch": 0.06111473272490222,
"grad_norm": 54.40706253051758,
"learning_rate": 4.166666666666667e-05,
"loss": 0.7434,
"step": 1500
},
{
"epoch": 0.06111473272490222,
"eval_accuracy": 0.748995983935743,
"eval_f1": 0.7514237869702255,
"eval_loss": 0.6406136155128479,
"eval_runtime": 411.3183,
"eval_samples_per_second": 6.054,
"eval_steps_per_second": 0.379,
"step": 1500
},
{
"epoch": 0.08148631029986962,
"grad_norm": 11.607203483581543,
"learning_rate": 3.7037037037037037e-05,
"loss": 0.6288,
"step": 2000
},
{
"epoch": 0.08148631029986962,
"eval_accuracy": 0.7738955823293173,
"eval_f1": 0.7758546821907705,
"eval_loss": 0.5777280926704407,
"eval_runtime": 411.4602,
"eval_samples_per_second": 6.052,
"eval_steps_per_second": 0.379,
"step": 2000
},
{
"epoch": 0.10185788787483703,
"grad_norm": 5.107800483703613,
"learning_rate": 3.240740740740741e-05,
"loss": 0.6186,
"step": 2500
},
{
"epoch": 0.10185788787483703,
"eval_accuracy": 0.7847389558232932,
"eval_f1": 0.7871483289805999,
"eval_loss": 0.5597745180130005,
"eval_runtime": 411.7146,
"eval_samples_per_second": 6.048,
"eval_steps_per_second": 0.379,
"step": 2500
},
{
"epoch": 0.12222946544980444,
"grad_norm": 7.775627136230469,
"learning_rate": 2.777777777777778e-05,
"loss": 0.5909,
"step": 3000
},
{
"epoch": 0.12222946544980444,
"eval_accuracy": 0.7963855421686747,
"eval_f1": 0.7956904592219637,
"eval_loss": 0.5284361839294434,
"eval_runtime": 411.1781,
"eval_samples_per_second": 6.056,
"eval_steps_per_second": 0.379,
"step": 3000
},
{
"epoch": 0.14260104302477183,
"grad_norm": 18.797571182250977,
"learning_rate": 2.314814814814815e-05,
"loss": 0.58,
"step": 3500
},
{
"epoch": 0.14260104302477183,
"eval_accuracy": 0.7891566265060241,
"eval_f1": 0.7909172071907363,
"eval_loss": 0.5231069922447205,
"eval_runtime": 412.124,
"eval_samples_per_second": 6.042,
"eval_steps_per_second": 0.379,
"step": 3500
},
{
"epoch": 0.16297262059973924,
"grad_norm": 5.233774185180664,
"learning_rate": 1.8518518518518518e-05,
"loss": 0.5752,
"step": 4000
},
{
"epoch": 0.16297262059973924,
"eval_accuracy": 0.8028112449799196,
"eval_f1": 0.8033343776283127,
"eval_loss": 0.5068484544754028,
"eval_runtime": 411.2741,
"eval_samples_per_second": 6.054,
"eval_steps_per_second": 0.379,
"step": 4000
},
{
"epoch": 0.18334419817470665,
"grad_norm": 5.612044334411621,
"learning_rate": 1.388888888888889e-05,
"loss": 0.5495,
"step": 4500
},
{
"epoch": 0.18334419817470665,
"eval_accuracy": 0.8016064257028113,
"eval_f1": 0.8027178095880526,
"eval_loss": 0.5132325887680054,
"eval_runtime": 411.4311,
"eval_samples_per_second": 6.052,
"eval_steps_per_second": 0.379,
"step": 4500
},
{
"epoch": 0.20371577574967406,
"grad_norm": 5.75107479095459,
"learning_rate": 9.259259259259259e-06,
"loss": 0.5594,
"step": 5000
},
{
"epoch": 0.20371577574967406,
"eval_accuracy": 0.8016064257028113,
"eval_f1": 0.802067784242174,
"eval_loss": 0.52597576379776,
"eval_runtime": 412.0059,
"eval_samples_per_second": 6.044,
"eval_steps_per_second": 0.379,
"step": 5000
},
{
"epoch": 0.22408735332464147,
"grad_norm": 4.854472637176514,
"learning_rate": 4.6296296296296296e-06,
"loss": 0.5561,
"step": 5500
},
{
"epoch": 0.22408735332464147,
"eval_accuracy": 0.8016064257028113,
"eval_f1": 0.8025734250007549,
"eval_loss": 0.5094338059425354,
"eval_runtime": 411.5334,
"eval_samples_per_second": 6.051,
"eval_steps_per_second": 0.379,
"step": 5500
},
{
"epoch": 0.24445893089960888,
"grad_norm": 6.345026016235352,
"learning_rate": 0.0,
"loss": 0.5454,
"step": 6000
},
{
"epoch": 0.24445893089960888,
"eval_accuracy": 0.804417670682731,
"eval_f1": 0.8051855538804084,
"eval_loss": 0.5121804475784302,
"eval_runtime": 411.4571,
"eval_samples_per_second": 6.052,
"eval_steps_per_second": 0.379,
"step": 6000
}
],
"logging_steps": 500,
"max_steps": 6000,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 500,
"total_flos": 8.03166870528e+17,
"train_batch_size": 16,
"trial_name": null,
"trial_params": null
}
|