End of training
Browse files
all_results.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 20.0,
|
| 3 |
+
"eval_accuracy": 0.984313725490196,
|
| 4 |
+
"eval_loss": 0.07451473921537399,
|
| 5 |
+
"eval_runtime": 5.114,
|
| 6 |
+
"eval_samples_per_second": 49.863,
|
| 7 |
+
"eval_steps_per_second": 1.564,
|
| 8 |
+
"total_flos": 1.1677328181960376e+18,
|
| 9 |
+
"train_loss": 0.13230072516534064,
|
| 10 |
+
"train_runtime": 1894.9319,
|
| 11 |
+
"train_samples_per_second": 24.149,
|
| 12 |
+
"train_steps_per_second": 0.19
|
| 13 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 20.0,
|
| 3 |
+
"eval_accuracy": 0.984313725490196,
|
| 4 |
+
"eval_loss": 0.07451473921537399,
|
| 5 |
+
"eval_runtime": 5.114,
|
| 6 |
+
"eval_samples_per_second": 49.863,
|
| 7 |
+
"eval_steps_per_second": 1.564
|
| 8 |
+
}
|
runs/Oct09_03-55-26_f76b01336d31/events.out.tfevents.1696826334.f76b01336d31.1308.4
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e335db9ef36e905e26a44d07b90044caee9ab3409ec2240d4d5385b461e4f94c
|
| 3 |
+
size 411
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 20.0,
|
| 3 |
+
"total_flos": 1.1677328181960376e+18,
|
| 4 |
+
"train_loss": 0.13230072516534064,
|
| 5 |
+
"train_runtime": 1894.9319,
|
| 6 |
+
"train_samples_per_second": 24.149,
|
| 7 |
+
"train_steps_per_second": 0.19
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,421 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.984313725490196,
|
| 3 |
+
"best_model_checkpoint": "swin-tiny-patch4-window7-224-uploads-classifier-v2/checkpoint-54",
|
| 4 |
+
"epoch": 20.0,
|
| 5 |
+
"global_step": 360,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.56,
|
| 12 |
+
"learning_rate": 2.5e-05,
|
| 13 |
+
"loss": 1.2482,
|
| 14 |
+
"step": 10
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 1.0,
|
| 18 |
+
"eval_accuracy": 0.8823529411764706,
|
| 19 |
+
"eval_loss": 0.47807738184928894,
|
| 20 |
+
"eval_runtime": 128.4565,
|
| 21 |
+
"eval_samples_per_second": 1.985,
|
| 22 |
+
"eval_steps_per_second": 0.062,
|
| 23 |
+
"step": 18
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 1.11,
|
| 27 |
+
"learning_rate": 3.888888888888889e-05,
|
| 28 |
+
"loss": 0.6777,
|
| 29 |
+
"step": 20
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 1.67,
|
| 33 |
+
"learning_rate": 4.969135802469136e-05,
|
| 34 |
+
"loss": 0.3036,
|
| 35 |
+
"step": 30
|
| 36 |
+
},
|
| 37 |
+
{
|
| 38 |
+
"epoch": 2.0,
|
| 39 |
+
"eval_accuracy": 0.9803921568627451,
|
| 40 |
+
"eval_loss": 0.093613401055336,
|
| 41 |
+
"eval_runtime": 5.0974,
|
| 42 |
+
"eval_samples_per_second": 50.026,
|
| 43 |
+
"eval_steps_per_second": 1.569,
|
| 44 |
+
"step": 36
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 2.22,
|
| 48 |
+
"learning_rate": 4.814814814814815e-05,
|
| 49 |
+
"loss": 0.2274,
|
| 50 |
+
"step": 40
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 2.78,
|
| 54 |
+
"learning_rate": 4.6604938271604945e-05,
|
| 55 |
+
"loss": 0.1687,
|
| 56 |
+
"step": 50
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 3.0,
|
| 60 |
+
"eval_accuracy": 0.984313725490196,
|
| 61 |
+
"eval_loss": 0.07451473921537399,
|
| 62 |
+
"eval_runtime": 5.1553,
|
| 63 |
+
"eval_samples_per_second": 49.463,
|
| 64 |
+
"eval_steps_per_second": 1.552,
|
| 65 |
+
"step": 54
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 3.33,
|
| 69 |
+
"learning_rate": 4.506172839506173e-05,
|
| 70 |
+
"loss": 0.173,
|
| 71 |
+
"step": 60
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 3.89,
|
| 75 |
+
"learning_rate": 4.351851851851852e-05,
|
| 76 |
+
"loss": 0.1392,
|
| 77 |
+
"step": 70
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 4.0,
|
| 81 |
+
"eval_accuracy": 0.9725490196078431,
|
| 82 |
+
"eval_loss": 0.09800481051206589,
|
| 83 |
+
"eval_runtime": 5.0352,
|
| 84 |
+
"eval_samples_per_second": 50.643,
|
| 85 |
+
"eval_steps_per_second": 1.589,
|
| 86 |
+
"step": 72
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 4.44,
|
| 90 |
+
"learning_rate": 4.197530864197531e-05,
|
| 91 |
+
"loss": 0.1266,
|
| 92 |
+
"step": 80
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 5.0,
|
| 96 |
+
"learning_rate": 4.04320987654321e-05,
|
| 97 |
+
"loss": 0.14,
|
| 98 |
+
"step": 90
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 5.0,
|
| 102 |
+
"eval_accuracy": 0.9764705882352941,
|
| 103 |
+
"eval_loss": 0.07778824865818024,
|
| 104 |
+
"eval_runtime": 5.263,
|
| 105 |
+
"eval_samples_per_second": 48.451,
|
| 106 |
+
"eval_steps_per_second": 1.52,
|
| 107 |
+
"step": 90
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 5.56,
|
| 111 |
+
"learning_rate": 3.888888888888889e-05,
|
| 112 |
+
"loss": 0.1186,
|
| 113 |
+
"step": 100
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 6.0,
|
| 117 |
+
"eval_accuracy": 0.9725490196078431,
|
| 118 |
+
"eval_loss": 0.08367796242237091,
|
| 119 |
+
"eval_runtime": 5.0122,
|
| 120 |
+
"eval_samples_per_second": 50.876,
|
| 121 |
+
"eval_steps_per_second": 1.596,
|
| 122 |
+
"step": 108
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 6.11,
|
| 126 |
+
"learning_rate": 3.734567901234568e-05,
|
| 127 |
+
"loss": 0.0878,
|
| 128 |
+
"step": 110
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 6.67,
|
| 132 |
+
"learning_rate": 3.580246913580247e-05,
|
| 133 |
+
"loss": 0.1088,
|
| 134 |
+
"step": 120
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 7.0,
|
| 138 |
+
"eval_accuracy": 0.9803921568627451,
|
| 139 |
+
"eval_loss": 0.06448379158973694,
|
| 140 |
+
"eval_runtime": 5.145,
|
| 141 |
+
"eval_samples_per_second": 49.562,
|
| 142 |
+
"eval_steps_per_second": 1.555,
|
| 143 |
+
"step": 126
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 7.22,
|
| 147 |
+
"learning_rate": 3.425925925925926e-05,
|
| 148 |
+
"loss": 0.087,
|
| 149 |
+
"step": 130
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 7.78,
|
| 153 |
+
"learning_rate": 3.271604938271605e-05,
|
| 154 |
+
"loss": 0.0789,
|
| 155 |
+
"step": 140
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 8.0,
|
| 159 |
+
"eval_accuracy": 0.9764705882352941,
|
| 160 |
+
"eval_loss": 0.0674787312746048,
|
| 161 |
+
"eval_runtime": 5.0792,
|
| 162 |
+
"eval_samples_per_second": 50.204,
|
| 163 |
+
"eval_steps_per_second": 1.575,
|
| 164 |
+
"step": 144
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 8.33,
|
| 168 |
+
"learning_rate": 3.117283950617284e-05,
|
| 169 |
+
"loss": 0.0685,
|
| 170 |
+
"step": 150
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 8.89,
|
| 174 |
+
"learning_rate": 2.962962962962963e-05,
|
| 175 |
+
"loss": 0.0644,
|
| 176 |
+
"step": 160
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 9.0,
|
| 180 |
+
"eval_accuracy": 0.9686274509803922,
|
| 181 |
+
"eval_loss": 0.09402623027563095,
|
| 182 |
+
"eval_runtime": 5.1415,
|
| 183 |
+
"eval_samples_per_second": 49.597,
|
| 184 |
+
"eval_steps_per_second": 1.556,
|
| 185 |
+
"step": 162
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 9.44,
|
| 189 |
+
"learning_rate": 2.8086419753086424e-05,
|
| 190 |
+
"loss": 0.0731,
|
| 191 |
+
"step": 170
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 10.0,
|
| 195 |
+
"learning_rate": 2.654320987654321e-05,
|
| 196 |
+
"loss": 0.0582,
|
| 197 |
+
"step": 180
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 10.0,
|
| 201 |
+
"eval_accuracy": 0.9725490196078431,
|
| 202 |
+
"eval_loss": 0.08792443573474884,
|
| 203 |
+
"eval_runtime": 5.0234,
|
| 204 |
+
"eval_samples_per_second": 50.762,
|
| 205 |
+
"eval_steps_per_second": 1.593,
|
| 206 |
+
"step": 180
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 10.56,
|
| 210 |
+
"learning_rate": 2.5e-05,
|
| 211 |
+
"loss": 0.0591,
|
| 212 |
+
"step": 190
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 11.0,
|
| 216 |
+
"eval_accuracy": 0.9686274509803922,
|
| 217 |
+
"eval_loss": 0.09348892420530319,
|
| 218 |
+
"eval_runtime": 4.9609,
|
| 219 |
+
"eval_samples_per_second": 51.402,
|
| 220 |
+
"eval_steps_per_second": 1.613,
|
| 221 |
+
"step": 198
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 11.11,
|
| 225 |
+
"learning_rate": 2.345679012345679e-05,
|
| 226 |
+
"loss": 0.0432,
|
| 227 |
+
"step": 200
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 11.67,
|
| 231 |
+
"learning_rate": 2.1913580246913582e-05,
|
| 232 |
+
"loss": 0.0538,
|
| 233 |
+
"step": 210
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 12.0,
|
| 237 |
+
"eval_accuracy": 0.9803921568627451,
|
| 238 |
+
"eval_loss": 0.054012518376111984,
|
| 239 |
+
"eval_runtime": 4.9341,
|
| 240 |
+
"eval_samples_per_second": 51.681,
|
| 241 |
+
"eval_steps_per_second": 1.621,
|
| 242 |
+
"step": 216
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 12.22,
|
| 246 |
+
"learning_rate": 2.037037037037037e-05,
|
| 247 |
+
"loss": 0.0471,
|
| 248 |
+
"step": 220
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 12.78,
|
| 252 |
+
"learning_rate": 1.8827160493827163e-05,
|
| 253 |
+
"loss": 0.0588,
|
| 254 |
+
"step": 230
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 13.0,
|
| 258 |
+
"eval_accuracy": 0.9686274509803922,
|
| 259 |
+
"eval_loss": 0.0725012868642807,
|
| 260 |
+
"eval_runtime": 5.0522,
|
| 261 |
+
"eval_samples_per_second": 50.473,
|
| 262 |
+
"eval_steps_per_second": 1.583,
|
| 263 |
+
"step": 234
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 13.33,
|
| 267 |
+
"learning_rate": 1.728395061728395e-05,
|
| 268 |
+
"loss": 0.0508,
|
| 269 |
+
"step": 240
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 13.89,
|
| 273 |
+
"learning_rate": 1.574074074074074e-05,
|
| 274 |
+
"loss": 0.0538,
|
| 275 |
+
"step": 250
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 14.0,
|
| 279 |
+
"eval_accuracy": 0.9764705882352941,
|
| 280 |
+
"eval_loss": 0.0636754184961319,
|
| 281 |
+
"eval_runtime": 5.0696,
|
| 282 |
+
"eval_samples_per_second": 50.3,
|
| 283 |
+
"eval_steps_per_second": 1.578,
|
| 284 |
+
"step": 252
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 14.44,
|
| 288 |
+
"learning_rate": 1.419753086419753e-05,
|
| 289 |
+
"loss": 0.056,
|
| 290 |
+
"step": 260
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 15.0,
|
| 294 |
+
"learning_rate": 1.2654320987654323e-05,
|
| 295 |
+
"loss": 0.0462,
|
| 296 |
+
"step": 270
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 15.0,
|
| 300 |
+
"eval_accuracy": 0.9725490196078431,
|
| 301 |
+
"eval_loss": 0.06937408447265625,
|
| 302 |
+
"eval_runtime": 5.0454,
|
| 303 |
+
"eval_samples_per_second": 50.541,
|
| 304 |
+
"eval_steps_per_second": 1.586,
|
| 305 |
+
"step": 270
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 15.56,
|
| 309 |
+
"learning_rate": 1.1111111111111112e-05,
|
| 310 |
+
"loss": 0.0352,
|
| 311 |
+
"step": 280
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 16.0,
|
| 315 |
+
"eval_accuracy": 0.9686274509803922,
|
| 316 |
+
"eval_loss": 0.07712557911872864,
|
| 317 |
+
"eval_runtime": 5.0258,
|
| 318 |
+
"eval_samples_per_second": 50.738,
|
| 319 |
+
"eval_steps_per_second": 1.592,
|
| 320 |
+
"step": 288
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 16.11,
|
| 324 |
+
"learning_rate": 9.5679012345679e-06,
|
| 325 |
+
"loss": 0.0469,
|
| 326 |
+
"step": 290
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 16.67,
|
| 330 |
+
"learning_rate": 8.02469135802469e-06,
|
| 331 |
+
"loss": 0.0536,
|
| 332 |
+
"step": 300
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 17.0,
|
| 336 |
+
"eval_accuracy": 0.9803921568627451,
|
| 337 |
+
"eval_loss": 0.06293778121471405,
|
| 338 |
+
"eval_runtime": 4.9305,
|
| 339 |
+
"eval_samples_per_second": 51.719,
|
| 340 |
+
"eval_steps_per_second": 1.623,
|
| 341 |
+
"step": 306
|
| 342 |
+
},
|
| 343 |
+
{
|
| 344 |
+
"epoch": 17.22,
|
| 345 |
+
"learning_rate": 6.481481481481481e-06,
|
| 346 |
+
"loss": 0.0317,
|
| 347 |
+
"step": 310
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"epoch": 17.78,
|
| 351 |
+
"learning_rate": 4.938271604938272e-06,
|
| 352 |
+
"loss": 0.0403,
|
| 353 |
+
"step": 320
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 18.0,
|
| 357 |
+
"eval_accuracy": 0.9686274509803922,
|
| 358 |
+
"eval_loss": 0.09334510564804077,
|
| 359 |
+
"eval_runtime": 5.0623,
|
| 360 |
+
"eval_samples_per_second": 50.373,
|
| 361 |
+
"eval_steps_per_second": 1.58,
|
| 362 |
+
"step": 324
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 18.33,
|
| 366 |
+
"learning_rate": 3.3950617283950617e-06,
|
| 367 |
+
"loss": 0.036,
|
| 368 |
+
"step": 330
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 18.89,
|
| 372 |
+
"learning_rate": 1.8518518518518519e-06,
|
| 373 |
+
"loss": 0.0412,
|
| 374 |
+
"step": 340
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 19.0,
|
| 378 |
+
"eval_accuracy": 0.9725490196078431,
|
| 379 |
+
"eval_loss": 0.08482151478528976,
|
| 380 |
+
"eval_runtime": 4.9192,
|
| 381 |
+
"eval_samples_per_second": 51.838,
|
| 382 |
+
"eval_steps_per_second": 1.626,
|
| 383 |
+
"step": 342
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 19.44,
|
| 387 |
+
"learning_rate": 3.08641975308642e-07,
|
| 388 |
+
"loss": 0.029,
|
| 389 |
+
"step": 350
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 20.0,
|
| 393 |
+
"learning_rate": 0.0,
|
| 394 |
+
"loss": 0.0305,
|
| 395 |
+
"step": 360
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 20.0,
|
| 399 |
+
"eval_accuracy": 0.9725490196078431,
|
| 400 |
+
"eval_loss": 0.08195191621780396,
|
| 401 |
+
"eval_runtime": 5.0318,
|
| 402 |
+
"eval_samples_per_second": 50.677,
|
| 403 |
+
"eval_steps_per_second": 1.59,
|
| 404 |
+
"step": 360
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 20.0,
|
| 408 |
+
"step": 360,
|
| 409 |
+
"total_flos": 1.1677328181960376e+18,
|
| 410 |
+
"train_loss": 0.13230072516534064,
|
| 411 |
+
"train_runtime": 1894.9319,
|
| 412 |
+
"train_samples_per_second": 24.149,
|
| 413 |
+
"train_steps_per_second": 0.19
|
| 414 |
+
}
|
| 415 |
+
],
|
| 416 |
+
"max_steps": 360,
|
| 417 |
+
"num_train_epochs": 20,
|
| 418 |
+
"total_flos": 1.1677328181960376e+18,
|
| 419 |
+
"trial_name": null,
|
| 420 |
+
"trial_params": null
|
| 421 |
+
}
|