End of training
Browse files- all_results.json +17 -0
- eval_results.json +12 -0
- train_results.json +8 -0
- trainer_state.json +283 -0
all_results.json
ADDED
|
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"eval_accuracy": 0.9639611008707811,
|
| 4 |
+
"eval_f1": 0.6654040404040403,
|
| 5 |
+
"eval_loss": 0.19381117820739746,
|
| 6 |
+
"eval_precision": 0.7045454545454546,
|
| 7 |
+
"eval_recall": 0.6303827751196173,
|
| 8 |
+
"eval_runtime": 1.7521,
|
| 9 |
+
"eval_samples": 1009,
|
| 10 |
+
"eval_samples_per_second": 575.867,
|
| 11 |
+
"eval_steps_per_second": 0.571,
|
| 12 |
+
"train_loss": 0.11085769158822519,
|
| 13 |
+
"train_runtime": 157.5154,
|
| 14 |
+
"train_samples": 3394,
|
| 15 |
+
"train_samples_per_second": 215.471,
|
| 16 |
+
"train_steps_per_second": 3.428
|
| 17 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"eval_accuracy": 0.9639611008707811,
|
| 4 |
+
"eval_f1": 0.6654040404040403,
|
| 5 |
+
"eval_loss": 0.19381117820739746,
|
| 6 |
+
"eval_precision": 0.7045454545454546,
|
| 7 |
+
"eval_recall": 0.6303827751196173,
|
| 8 |
+
"eval_runtime": 1.7521,
|
| 9 |
+
"eval_samples": 1009,
|
| 10 |
+
"eval_samples_per_second": 575.867,
|
| 11 |
+
"eval_steps_per_second": 0.571
|
| 12 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"train_loss": 0.11085769158822519,
|
| 4 |
+
"train_runtime": 157.5154,
|
| 5 |
+
"train_samples": 3394,
|
| 6 |
+
"train_samples_per_second": 215.471,
|
| 7 |
+
"train_steps_per_second": 3.428
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,283 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.6654040404040403,
|
| 3 |
+
"best_model_checkpoint": "twitter-roberta-base-WNUT/checkpoint-500",
|
| 4 |
+
"epoch": 10.0,
|
| 5 |
+
"global_step": 540,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.46,
|
| 12 |
+
"eval_accuracy": 0.9205491641772071,
|
| 13 |
+
"eval_f1": 0.0,
|
| 14 |
+
"eval_loss": 0.39121243357658386,
|
| 15 |
+
"eval_precision": 0.0,
|
| 16 |
+
"eval_recall": 0.0,
|
| 17 |
+
"eval_runtime": 1.5425,
|
| 18 |
+
"eval_samples_per_second": 654.138,
|
| 19 |
+
"eval_steps_per_second": 0.648,
|
| 20 |
+
"step": 25
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.93,
|
| 24 |
+
"eval_accuracy": 0.9209305281891565,
|
| 25 |
+
"eval_f1": 0.004739336492890995,
|
| 26 |
+
"eval_loss": 0.2846619784832001,
|
| 27 |
+
"eval_precision": 0.25,
|
| 28 |
+
"eval_recall": 0.0023923444976076554,
|
| 29 |
+
"eval_runtime": 1.5304,
|
| 30 |
+
"eval_samples_per_second": 659.288,
|
| 31 |
+
"eval_steps_per_second": 0.653,
|
| 32 |
+
"step": 50
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 1.39,
|
| 36 |
+
"eval_accuracy": 0.9426047162016145,
|
| 37 |
+
"eval_f1": 0.4239766081871345,
|
| 38 |
+
"eval_loss": 0.2449360191822052,
|
| 39 |
+
"eval_precision": 0.5451127819548872,
|
| 40 |
+
"eval_recall": 0.34688995215311,
|
| 41 |
+
"eval_runtime": 1.487,
|
| 42 |
+
"eval_samples_per_second": 678.556,
|
| 43 |
+
"eval_steps_per_second": 0.673,
|
| 44 |
+
"step": 75
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 1.85,
|
| 48 |
+
"eval_accuracy": 0.9491514650734125,
|
| 49 |
+
"eval_f1": 0.5565455791638108,
|
| 50 |
+
"eval_loss": 0.19464540481567383,
|
| 51 |
+
"eval_precision": 0.651685393258427,
|
| 52 |
+
"eval_recall": 0.48564593301435405,
|
| 53 |
+
"eval_runtime": 1.5409,
|
| 54 |
+
"eval_samples_per_second": 654.812,
|
| 55 |
+
"eval_steps_per_second": 0.649,
|
| 56 |
+
"step": 100
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 2.31,
|
| 60 |
+
"eval_accuracy": 0.9581135193542236,
|
| 61 |
+
"eval_f1": 0.621870882740448,
|
| 62 |
+
"eval_loss": 0.1851097047328949,
|
| 63 |
+
"eval_precision": 0.6920821114369502,
|
| 64 |
+
"eval_recall": 0.5645933014354066,
|
| 65 |
+
"eval_runtime": 1.5283,
|
| 66 |
+
"eval_samples_per_second": 660.202,
|
| 67 |
+
"eval_steps_per_second": 0.654,
|
| 68 |
+
"step": 125
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 2.78,
|
| 72 |
+
"eval_accuracy": 0.9594482933960465,
|
| 73 |
+
"eval_f1": 0.6331399097356544,
|
| 74 |
+
"eval_loss": 0.1671772003173828,
|
| 75 |
+
"eval_precision": 0.6867132867132867,
|
| 76 |
+
"eval_recall": 0.5873205741626795,
|
| 77 |
+
"eval_runtime": 1.7364,
|
| 78 |
+
"eval_samples_per_second": 581.088,
|
| 79 |
+
"eval_steps_per_second": 0.576,
|
| 80 |
+
"step": 150
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 3.24,
|
| 84 |
+
"eval_accuracy": 0.9615457954617682,
|
| 85 |
+
"eval_f1": 0.6276527331189711,
|
| 86 |
+
"eval_loss": 0.16754180192947388,
|
| 87 |
+
"eval_precision": 0.6787204450625869,
|
| 88 |
+
"eval_recall": 0.583732057416268,
|
| 89 |
+
"eval_runtime": 1.522,
|
| 90 |
+
"eval_samples_per_second": 662.938,
|
| 91 |
+
"eval_steps_per_second": 0.657,
|
| 92 |
+
"step": 175
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 3.7,
|
| 96 |
+
"eval_accuracy": 0.9637704188648064,
|
| 97 |
+
"eval_f1": 0.65389369592089,
|
| 98 |
+
"eval_loss": 0.16441918909549713,
|
| 99 |
+
"eval_precision": 0.6764705882352942,
|
| 100 |
+
"eval_recall": 0.6327751196172249,
|
| 101 |
+
"eval_runtime": 1.5477,
|
| 102 |
+
"eval_samples_per_second": 651.939,
|
| 103 |
+
"eval_steps_per_second": 0.646,
|
| 104 |
+
"step": 200
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 4.17,
|
| 108 |
+
"eval_accuracy": 0.9640246615394394,
|
| 109 |
+
"eval_f1": 0.673697270471464,
|
| 110 |
+
"eval_loss": 0.1672356277704239,
|
| 111 |
+
"eval_precision": 0.6997422680412371,
|
| 112 |
+
"eval_recall": 0.6495215311004785,
|
| 113 |
+
"eval_runtime": 1.5668,
|
| 114 |
+
"eval_samples_per_second": 643.973,
|
| 115 |
+
"eval_steps_per_second": 0.638,
|
| 116 |
+
"step": 225
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 4.63,
|
| 120 |
+
"eval_accuracy": 0.9648509502319964,
|
| 121 |
+
"eval_f1": 0.6666666666666666,
|
| 122 |
+
"eval_loss": 0.16518081724643707,
|
| 123 |
+
"eval_precision": 0.6915167095115681,
|
| 124 |
+
"eval_recall": 0.6435406698564593,
|
| 125 |
+
"eval_runtime": 1.544,
|
| 126 |
+
"eval_samples_per_second": 653.501,
|
| 127 |
+
"eval_steps_per_second": 0.648,
|
| 128 |
+
"step": 250
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 5.09,
|
| 132 |
+
"eval_accuracy": 0.9629441301722494,
|
| 133 |
+
"eval_f1": 0.6520618556701031,
|
| 134 |
+
"eval_loss": 0.18820269405841827,
|
| 135 |
+
"eval_precision": 0.7067039106145251,
|
| 136 |
+
"eval_recall": 0.6052631578947368,
|
| 137 |
+
"eval_runtime": 1.5459,
|
| 138 |
+
"eval_samples_per_second": 652.688,
|
| 139 |
+
"eval_steps_per_second": 0.647,
|
| 140 |
+
"step": 275
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 5.56,
|
| 144 |
+
"eval_accuracy": 0.9644695862200471,
|
| 145 |
+
"eval_f1": 0.6717267552182163,
|
| 146 |
+
"eval_loss": 0.17831429839134216,
|
| 147 |
+
"eval_precision": 0.7127516778523489,
|
| 148 |
+
"eval_recall": 0.6351674641148325,
|
| 149 |
+
"eval_runtime": 1.5976,
|
| 150 |
+
"eval_samples_per_second": 631.564,
|
| 151 |
+
"eval_steps_per_second": 0.626,
|
| 152 |
+
"step": 300
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 6.02,
|
| 156 |
+
"eval_accuracy": 0.9638975402021229,
|
| 157 |
+
"eval_f1": 0.6564885496183207,
|
| 158 |
+
"eval_loss": 0.18128034472465515,
|
| 159 |
+
"eval_precision": 0.7010869565217391,
|
| 160 |
+
"eval_recall": 0.6172248803827751,
|
| 161 |
+
"eval_runtime": 1.5524,
|
| 162 |
+
"eval_samples_per_second": 649.966,
|
| 163 |
+
"eval_steps_per_second": 0.644,
|
| 164 |
+
"step": 325
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 6.48,
|
| 168 |
+
"eval_accuracy": 0.96472382889468,
|
| 169 |
+
"eval_f1": 0.677561282212445,
|
| 170 |
+
"eval_loss": 0.18036700785160065,
|
| 171 |
+
"eval_precision": 0.713907284768212,
|
| 172 |
+
"eval_recall": 0.6447368421052632,
|
| 173 |
+
"eval_runtime": 1.6249,
|
| 174 |
+
"eval_samples_per_second": 620.943,
|
| 175 |
+
"eval_steps_per_second": 0.615,
|
| 176 |
+
"step": 350
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 6.94,
|
| 180 |
+
"eval_accuracy": 0.9640882222080976,
|
| 181 |
+
"eval_f1": 0.6709346991037132,
|
| 182 |
+
"eval_loss": 0.19022008776664734,
|
| 183 |
+
"eval_precision": 0.721763085399449,
|
| 184 |
+
"eval_recall": 0.6267942583732058,
|
| 185 |
+
"eval_runtime": 1.8093,
|
| 186 |
+
"eval_samples_per_second": 557.663,
|
| 187 |
+
"eval_steps_per_second": 0.553,
|
| 188 |
+
"step": 375
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 7.41,
|
| 192 |
+
"eval_accuracy": 0.9640882222080976,
|
| 193 |
+
"eval_f1": 0.668777707409753,
|
| 194 |
+
"eval_loss": 0.1882619857788086,
|
| 195 |
+
"eval_precision": 0.7106325706594886,
|
| 196 |
+
"eval_recall": 0.631578947368421,
|
| 197 |
+
"eval_runtime": 1.62,
|
| 198 |
+
"eval_samples_per_second": 622.858,
|
| 199 |
+
"eval_steps_per_second": 0.617,
|
| 200 |
+
"step": 400
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 7.87,
|
| 204 |
+
"eval_accuracy": 0.9642789042140724,
|
| 205 |
+
"eval_f1": 0.6683480453972257,
|
| 206 |
+
"eval_loss": 0.18618735671043396,
|
| 207 |
+
"eval_precision": 0.7066666666666667,
|
| 208 |
+
"eval_recall": 0.6339712918660287,
|
| 209 |
+
"eval_runtime": 1.5944,
|
| 210 |
+
"eval_samples_per_second": 632.853,
|
| 211 |
+
"eval_steps_per_second": 0.627,
|
| 212 |
+
"step": 425
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 8.33,
|
| 216 |
+
"eval_accuracy": 0.9638975402021229,
|
| 217 |
+
"eval_f1": 0.6670870113493064,
|
| 218 |
+
"eval_loss": 0.1881590634584427,
|
| 219 |
+
"eval_precision": 0.7053333333333334,
|
| 220 |
+
"eval_recall": 0.6327751196172249,
|
| 221 |
+
"eval_runtime": 1.7003,
|
| 222 |
+
"eval_samples_per_second": 593.415,
|
| 223 |
+
"eval_steps_per_second": 0.588,
|
| 224 |
+
"step": 450
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 8.8,
|
| 228 |
+
"eval_accuracy": 0.9638339795334647,
|
| 229 |
+
"eval_f1": 0.6658243840808591,
|
| 230 |
+
"eval_loss": 0.19190868735313416,
|
| 231 |
+
"eval_precision": 0.7054886211512718,
|
| 232 |
+
"eval_recall": 0.6303827751196173,
|
| 233 |
+
"eval_runtime": 1.543,
|
| 234 |
+
"eval_samples_per_second": 653.928,
|
| 235 |
+
"eval_steps_per_second": 0.648,
|
| 236 |
+
"step": 475
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 9.26,
|
| 240 |
+
"learning_rate": 1.4814814814814815e-06,
|
| 241 |
+
"loss": 0.1175,
|
| 242 |
+
"step": 500
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 9.26,
|
| 246 |
+
"eval_accuracy": 0.9639611008707811,
|
| 247 |
+
"eval_f1": 0.6654040404040403,
|
| 248 |
+
"eval_loss": 0.19381117820739746,
|
| 249 |
+
"eval_precision": 0.7045454545454546,
|
| 250 |
+
"eval_recall": 0.6303827751196173,
|
| 251 |
+
"eval_runtime": 1.541,
|
| 252 |
+
"eval_samples_per_second": 654.789,
|
| 253 |
+
"eval_steps_per_second": 0.649,
|
| 254 |
+
"step": 500
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 9.72,
|
| 258 |
+
"eval_accuracy": 0.9645967075573635,
|
| 259 |
+
"eval_f1": 0.6704190118824266,
|
| 260 |
+
"eval_loss": 0.18799594044685364,
|
| 261 |
+
"eval_precision": 0.7024901703800787,
|
| 262 |
+
"eval_recall": 0.6411483253588517,
|
| 263 |
+
"eval_runtime": 1.6071,
|
| 264 |
+
"eval_samples_per_second": 627.849,
|
| 265 |
+
"eval_steps_per_second": 0.622,
|
| 266 |
+
"step": 525
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 10.0,
|
| 270 |
+
"step": 540,
|
| 271 |
+
"total_flos": 1009327449452316.0,
|
| 272 |
+
"train_loss": 0.11085769158822519,
|
| 273 |
+
"train_runtime": 157.5154,
|
| 274 |
+
"train_samples_per_second": 215.471,
|
| 275 |
+
"train_steps_per_second": 3.428
|
| 276 |
+
}
|
| 277 |
+
],
|
| 278 |
+
"max_steps": 540,
|
| 279 |
+
"num_train_epochs": 10,
|
| 280 |
+
"total_flos": 1009327449452316.0,
|
| 281 |
+
"trial_name": null,
|
| 282 |
+
"trial_params": null
|
| 283 |
+
}
|