Erik W
commited on
Commit
•
4b9db3e
1
Parent(s):
9f8075d
End of training
Browse files- all_results.json +16 -0
- eval_results.json +11 -0
- runs/Sep25_00-45-06_08ff2b062b9b/events.out.tfevents.1664069668.08ff2b062b9b.67.14 +3 -0
- train_results.json +8 -0
- trainer_state.json +367 -0
all_results.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.0,
|
| 3 |
+
"eval_accuracy": 0.9888888888888889,
|
| 4 |
+
"eval_f1": 0.9888960568775346,
|
| 5 |
+
"eval_loss": 0.03830229118466377,
|
| 6 |
+
"eval_precision": 0.9889615535194125,
|
| 7 |
+
"eval_recall": 0.9888888888888889,
|
| 8 |
+
"eval_runtime": 22.9443,
|
| 9 |
+
"eval_samples_per_second": 117.676,
|
| 10 |
+
"eval_steps_per_second": 1.874,
|
| 11 |
+
"total_flos": 3.953802662903808e+18,
|
| 12 |
+
"train_loss": 0.33234748953267146,
|
| 13 |
+
"train_runtime": 2734.7444,
|
| 14 |
+
"train_samples_per_second": 44.428,
|
| 15 |
+
"train_steps_per_second": 0.174
|
| 16 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.0,
|
| 3 |
+
"eval_accuracy": 0.9888888888888889,
|
| 4 |
+
"eval_f1": 0.9888960568775346,
|
| 5 |
+
"eval_loss": 0.03830229118466377,
|
| 6 |
+
"eval_precision": 0.9889615535194125,
|
| 7 |
+
"eval_recall": 0.9888888888888889,
|
| 8 |
+
"eval_runtime": 22.9443,
|
| 9 |
+
"eval_samples_per_second": 117.676,
|
| 10 |
+
"eval_steps_per_second": 1.874
|
| 11 |
+
}
|
runs/Sep25_00-45-06_08ff2b062b9b/events.out.tfevents.1664069668.08ff2b062b9b.67.14
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4f96a72c42f5e20533e15dd4596544f4043b4fd7a780ca2bd243d38fd344aef8
|
| 3 |
+
size 512
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.0,
|
| 3 |
+
"total_flos": 3.953802662903808e+18,
|
| 4 |
+
"train_loss": 0.33234748953267146,
|
| 5 |
+
"train_runtime": 2734.7444,
|
| 6 |
+
"train_samples_per_second": 44.428,
|
| 7 |
+
"train_steps_per_second": 0.174
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,367 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.9888888888888889,
|
| 3 |
+
"best_model_checkpoint": "swinv2-tiny-patch4-window8-256-finetuned-eurosat/checkpoint-475",
|
| 4 |
+
"epoch": 5.0,
|
| 5 |
+
"global_step": 475,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.11,
|
| 12 |
+
"learning_rate": 1.0526315789473684e-05,
|
| 13 |
+
"loss": 2.2988,
|
| 14 |
+
"step": 10
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.21,
|
| 18 |
+
"learning_rate": 2.105263157894737e-05,
|
| 19 |
+
"loss": 2.096,
|
| 20 |
+
"step": 20
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.32,
|
| 24 |
+
"learning_rate": 3.157894736842105e-05,
|
| 25 |
+
"loss": 1.5718,
|
| 26 |
+
"step": 30
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.42,
|
| 30 |
+
"learning_rate": 4.210526315789474e-05,
|
| 31 |
+
"loss": 0.8586,
|
| 32 |
+
"step": 40
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.53,
|
| 36 |
+
"learning_rate": 5.2631578947368424e-05,
|
| 37 |
+
"loss": 0.5798,
|
| 38 |
+
"step": 50
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.63,
|
| 42 |
+
"learning_rate": 6.31578947368421e-05,
|
| 43 |
+
"loss": 0.46,
|
| 44 |
+
"step": 60
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.74,
|
| 48 |
+
"learning_rate": 7.368421052631579e-05,
|
| 49 |
+
"loss": 0.3742,
|
| 50 |
+
"step": 70
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.84,
|
| 54 |
+
"learning_rate": 8.421052631578948e-05,
|
| 55 |
+
"loss": 0.3674,
|
| 56 |
+
"step": 80
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.95,
|
| 60 |
+
"learning_rate": 9.473684210526316e-05,
|
| 61 |
+
"loss": 0.3514,
|
| 62 |
+
"step": 90
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 1.0,
|
| 66 |
+
"eval_accuracy": 0.9562962962962963,
|
| 67 |
+
"eval_f1": 0.9566096581797888,
|
| 68 |
+
"eval_loss": 0.12914273142814636,
|
| 69 |
+
"eval_precision": 0.9583681045676652,
|
| 70 |
+
"eval_recall": 0.9562962962962963,
|
| 71 |
+
"eval_runtime": 25.3036,
|
| 72 |
+
"eval_samples_per_second": 106.704,
|
| 73 |
+
"eval_steps_per_second": 1.699,
|
| 74 |
+
"step": 95
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 1.05,
|
| 78 |
+
"learning_rate": 9.868421052631579e-05,
|
| 79 |
+
"loss": 0.3315,
|
| 80 |
+
"step": 100
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 1.16,
|
| 84 |
+
"learning_rate": 9.605263157894737e-05,
|
| 85 |
+
"loss": 0.2897,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 1.26,
|
| 90 |
+
"learning_rate": 9.342105263157896e-05,
|
| 91 |
+
"loss": 0.2712,
|
| 92 |
+
"step": 120
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 1.37,
|
| 96 |
+
"learning_rate": 9.078947368421054e-05,
|
| 97 |
+
"loss": 0.2586,
|
| 98 |
+
"step": 130
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 1.47,
|
| 102 |
+
"learning_rate": 8.81578947368421e-05,
|
| 103 |
+
"loss": 0.2557,
|
| 104 |
+
"step": 140
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 1.58,
|
| 108 |
+
"learning_rate": 8.552631578947369e-05,
|
| 109 |
+
"loss": 0.2354,
|
| 110 |
+
"step": 150
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 1.68,
|
| 114 |
+
"learning_rate": 8.289473684210527e-05,
|
| 115 |
+
"loss": 0.2386,
|
| 116 |
+
"step": 160
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 1.79,
|
| 120 |
+
"learning_rate": 8.026315789473685e-05,
|
| 121 |
+
"loss": 0.2084,
|
| 122 |
+
"step": 170
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 1.89,
|
| 126 |
+
"learning_rate": 7.763157894736843e-05,
|
| 127 |
+
"loss": 0.2225,
|
| 128 |
+
"step": 180
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 2.0,
|
| 132 |
+
"learning_rate": 7.500000000000001e-05,
|
| 133 |
+
"loss": 0.2514,
|
| 134 |
+
"step": 190
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 2.0,
|
| 138 |
+
"eval_accuracy": 0.9777777777777777,
|
| 139 |
+
"eval_f1": 0.9777845251783622,
|
| 140 |
+
"eval_loss": 0.06517087668180466,
|
| 141 |
+
"eval_precision": 0.9779939338043359,
|
| 142 |
+
"eval_recall": 0.9777777777777777,
|
| 143 |
+
"eval_runtime": 23.425,
|
| 144 |
+
"eval_samples_per_second": 115.262,
|
| 145 |
+
"eval_steps_per_second": 1.836,
|
| 146 |
+
"step": 190
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 2.11,
|
| 150 |
+
"learning_rate": 7.236842105263159e-05,
|
| 151 |
+
"loss": 0.1947,
|
| 152 |
+
"step": 200
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 2.21,
|
| 156 |
+
"learning_rate": 6.973684210526315e-05,
|
| 157 |
+
"loss": 0.1878,
|
| 158 |
+
"step": 210
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 2.32,
|
| 162 |
+
"learning_rate": 6.710526315789474e-05,
|
| 163 |
+
"loss": 0.1911,
|
| 164 |
+
"step": 220
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 2.42,
|
| 168 |
+
"learning_rate": 6.447368421052632e-05,
|
| 169 |
+
"loss": 0.1745,
|
| 170 |
+
"step": 230
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 2.53,
|
| 174 |
+
"learning_rate": 6.18421052631579e-05,
|
| 175 |
+
"loss": 0.2039,
|
| 176 |
+
"step": 240
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 2.63,
|
| 180 |
+
"learning_rate": 5.921052631578947e-05,
|
| 181 |
+
"loss": 0.1614,
|
| 182 |
+
"step": 250
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 2.74,
|
| 186 |
+
"learning_rate": 5.6578947368421056e-05,
|
| 187 |
+
"loss": 0.1518,
|
| 188 |
+
"step": 260
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 2.84,
|
| 192 |
+
"learning_rate": 5.3947368421052635e-05,
|
| 193 |
+
"loss": 0.1701,
|
| 194 |
+
"step": 270
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 2.95,
|
| 198 |
+
"learning_rate": 5.131578947368422e-05,
|
| 199 |
+
"loss": 0.1703,
|
| 200 |
+
"step": 280
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 3.0,
|
| 204 |
+
"eval_accuracy": 0.9840740740740741,
|
| 205 |
+
"eval_f1": 0.984082402812258,
|
| 206 |
+
"eval_loss": 0.0463990680873394,
|
| 207 |
+
"eval_precision": 0.9842341990848004,
|
| 208 |
+
"eval_recall": 0.9840740740740741,
|
| 209 |
+
"eval_runtime": 23.4447,
|
| 210 |
+
"eval_samples_per_second": 115.165,
|
| 211 |
+
"eval_steps_per_second": 1.834,
|
| 212 |
+
"step": 285
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 3.05,
|
| 216 |
+
"learning_rate": 4.868421052631579e-05,
|
| 217 |
+
"loss": 0.1533,
|
| 218 |
+
"step": 290
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 3.16,
|
| 222 |
+
"learning_rate": 4.605263157894737e-05,
|
| 223 |
+
"loss": 0.1435,
|
| 224 |
+
"step": 300
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 3.26,
|
| 228 |
+
"learning_rate": 4.342105263157895e-05,
|
| 229 |
+
"loss": 0.1481,
|
| 230 |
+
"step": 310
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 3.37,
|
| 234 |
+
"learning_rate": 4.078947368421053e-05,
|
| 235 |
+
"loss": 0.1544,
|
| 236 |
+
"step": 320
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 3.47,
|
| 240 |
+
"learning_rate": 3.815789473684211e-05,
|
| 241 |
+
"loss": 0.1488,
|
| 242 |
+
"step": 330
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 3.58,
|
| 246 |
+
"learning_rate": 3.5526315789473684e-05,
|
| 247 |
+
"loss": 0.1307,
|
| 248 |
+
"step": 340
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 3.68,
|
| 252 |
+
"learning_rate": 3.289473684210527e-05,
|
| 253 |
+
"loss": 0.1328,
|
| 254 |
+
"step": 350
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 3.79,
|
| 258 |
+
"learning_rate": 3.0263157894736844e-05,
|
| 259 |
+
"loss": 0.1436,
|
| 260 |
+
"step": 360
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 3.89,
|
| 264 |
+
"learning_rate": 2.7631578947368426e-05,
|
| 265 |
+
"loss": 0.1457,
|
| 266 |
+
"step": 370
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 4.0,
|
| 270 |
+
"learning_rate": 2.5e-05,
|
| 271 |
+
"loss": 0.1449,
|
| 272 |
+
"step": 380
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 4.0,
|
| 276 |
+
"eval_accuracy": 0.9862962962962963,
|
| 277 |
+
"eval_f1": 0.9862788078879426,
|
| 278 |
+
"eval_loss": 0.042202528566122055,
|
| 279 |
+
"eval_precision": 0.9863517695170958,
|
| 280 |
+
"eval_recall": 0.9862962962962963,
|
| 281 |
+
"eval_runtime": 23.3925,
|
| 282 |
+
"eval_samples_per_second": 115.421,
|
| 283 |
+
"eval_steps_per_second": 1.838,
|
| 284 |
+
"step": 380
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 4.11,
|
| 288 |
+
"learning_rate": 2.236842105263158e-05,
|
| 289 |
+
"loss": 0.1208,
|
| 290 |
+
"step": 390
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 4.21,
|
| 294 |
+
"learning_rate": 1.9736842105263158e-05,
|
| 295 |
+
"loss": 0.148,
|
| 296 |
+
"step": 400
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 4.32,
|
| 300 |
+
"learning_rate": 1.7105263157894737e-05,
|
| 301 |
+
"loss": 0.1311,
|
| 302 |
+
"step": 410
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 4.42,
|
| 306 |
+
"learning_rate": 1.4473684210526317e-05,
|
| 307 |
+
"loss": 0.1327,
|
| 308 |
+
"step": 420
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 4.53,
|
| 312 |
+
"learning_rate": 1.1842105263157895e-05,
|
| 313 |
+
"loss": 0.1253,
|
| 314 |
+
"step": 430
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 4.63,
|
| 318 |
+
"learning_rate": 9.210526315789474e-06,
|
| 319 |
+
"loss": 0.1268,
|
| 320 |
+
"step": 440
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 4.74,
|
| 324 |
+
"learning_rate": 6.578947368421053e-06,
|
| 325 |
+
"loss": 0.1232,
|
| 326 |
+
"step": 450
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 4.84,
|
| 330 |
+
"learning_rate": 3.9473684210526315e-06,
|
| 331 |
+
"loss": 0.1102,
|
| 332 |
+
"step": 460
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 4.95,
|
| 336 |
+
"learning_rate": 1.3157894736842106e-06,
|
| 337 |
+
"loss": 0.1303,
|
| 338 |
+
"step": 470
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 5.0,
|
| 342 |
+
"eval_accuracy": 0.9888888888888889,
|
| 343 |
+
"eval_f1": 0.9888960568775346,
|
| 344 |
+
"eval_loss": 0.03830229118466377,
|
| 345 |
+
"eval_precision": 0.9889615535194125,
|
| 346 |
+
"eval_recall": 0.9888888888888889,
|
| 347 |
+
"eval_runtime": 23.3358,
|
| 348 |
+
"eval_samples_per_second": 115.702,
|
| 349 |
+
"eval_steps_per_second": 1.843,
|
| 350 |
+
"step": 475
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 5.0,
|
| 354 |
+
"step": 475,
|
| 355 |
+
"total_flos": 3.953802662903808e+18,
|
| 356 |
+
"train_loss": 0.33234748953267146,
|
| 357 |
+
"train_runtime": 2734.7444,
|
| 358 |
+
"train_samples_per_second": 44.428,
|
| 359 |
+
"train_steps_per_second": 0.174
|
| 360 |
+
}
|
| 361 |
+
],
|
| 362 |
+
"max_steps": 475,
|
| 363 |
+
"num_train_epochs": 5,
|
| 364 |
+
"total_flos": 3.953802662903808e+18,
|
| 365 |
+
"trial_name": null,
|
| 366 |
+
"trial_params": null
|
| 367 |
+
}
|