Commit
•
fc25c1e
1
Parent(s):
c2013d5
End of training
Browse files
all_results.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 0.9991111111111111,
|
| 3 |
+
"eval_accuracy": 0.62025,
|
| 4 |
+
"eval_loss": 1.2218776941299438,
|
| 5 |
+
"eval_runtime": 57.2683,
|
| 6 |
+
"eval_samples_per_second": 69.847,
|
| 7 |
+
"eval_steps_per_second": 2.183,
|
| 8 |
+
"total_flos": 8.943699469318226e+17,
|
| 9 |
+
"train_loss": 1.6086162854768202,
|
| 10 |
+
"train_runtime": 797.2781,
|
| 11 |
+
"train_samples_per_second": 45.149,
|
| 12 |
+
"train_steps_per_second": 0.352
|
| 13 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 0.9991111111111111,
|
| 3 |
+
"eval_accuracy": 0.62025,
|
| 4 |
+
"eval_loss": 1.2218776941299438,
|
| 5 |
+
"eval_runtime": 57.2683,
|
| 6 |
+
"eval_samples_per_second": 69.847,
|
| 7 |
+
"eval_steps_per_second": 2.183
|
| 8 |
+
}
|
runs/Jun18_14-17-36_9f3187adc653/events.out.tfevents.1718721133.9f3187adc653.203.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7487cc815a1eeaeed984a4aae8fdca0994e71b21c6c07dfa08206e8d626aedec
|
| 3 |
+
size 411
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 0.9991111111111111,
|
| 3 |
+
"total_flos": 8.943699469318226e+17,
|
| 4 |
+
"train_loss": 1.6086162854768202,
|
| 5 |
+
"train_runtime": 797.2781,
|
| 6 |
+
"train_samples_per_second": 45.149,
|
| 7 |
+
"train_steps_per_second": 0.352
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,247 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.62025,
|
| 3 |
+
"best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-eurosat/checkpoint-281",
|
| 4 |
+
"epoch": 0.9991111111111111,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 281,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.035555555555555556,
|
| 13 |
+
"grad_norm": 7.3984904289245605,
|
| 14 |
+
"learning_rate": 1.7241379310344828e-05,
|
| 15 |
+
"loss": 2.7474,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.07111111111111111,
|
| 20 |
+
"grad_norm": 7.859865188598633,
|
| 21 |
+
"learning_rate": 3.4482758620689657e-05,
|
| 22 |
+
"loss": 2.6199,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.10666666666666667,
|
| 27 |
+
"grad_norm": 21.349201202392578,
|
| 28 |
+
"learning_rate": 4.9801587301587306e-05,
|
| 29 |
+
"loss": 2.2658,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.14222222222222222,
|
| 34 |
+
"grad_norm": 23.123310089111328,
|
| 35 |
+
"learning_rate": 4.781746031746032e-05,
|
| 36 |
+
"loss": 2.0242,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.17777777777777778,
|
| 41 |
+
"grad_norm": 10.755074501037598,
|
| 42 |
+
"learning_rate": 4.5833333333333334e-05,
|
| 43 |
+
"loss": 1.866,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.21333333333333335,
|
| 48 |
+
"grad_norm": 9.822580337524414,
|
| 49 |
+
"learning_rate": 4.384920634920635e-05,
|
| 50 |
+
"loss": 1.7276,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.24888888888888888,
|
| 55 |
+
"grad_norm": 11.387887001037598,
|
| 56 |
+
"learning_rate": 4.186507936507937e-05,
|
| 57 |
+
"loss": 1.6602,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.28444444444444444,
|
| 62 |
+
"grad_norm": 11.359118461608887,
|
| 63 |
+
"learning_rate": 3.9880952380952386e-05,
|
| 64 |
+
"loss": 1.6713,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.32,
|
| 69 |
+
"grad_norm": 10.438748359680176,
|
| 70 |
+
"learning_rate": 3.7896825396825396e-05,
|
| 71 |
+
"loss": 1.6469,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.35555555555555557,
|
| 76 |
+
"grad_norm": 10.260947227478027,
|
| 77 |
+
"learning_rate": 3.591269841269841e-05,
|
| 78 |
+
"loss": 1.5134,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.39111111111111113,
|
| 83 |
+
"grad_norm": 8.524605751037598,
|
| 84 |
+
"learning_rate": 3.392857142857143e-05,
|
| 85 |
+
"loss": 1.5694,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.4266666666666667,
|
| 90 |
+
"grad_norm": 10.703609466552734,
|
| 91 |
+
"learning_rate": 3.194444444444444e-05,
|
| 92 |
+
"loss": 1.597,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.4622222222222222,
|
| 97 |
+
"grad_norm": 10.19986629486084,
|
| 98 |
+
"learning_rate": 2.996031746031746e-05,
|
| 99 |
+
"loss": 1.4785,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.49777777777777776,
|
| 104 |
+
"grad_norm": 9.872143745422363,
|
| 105 |
+
"learning_rate": 2.797619047619048e-05,
|
| 106 |
+
"loss": 1.4853,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.5333333333333333,
|
| 111 |
+
"grad_norm": 8.166397094726562,
|
| 112 |
+
"learning_rate": 2.5992063492063496e-05,
|
| 113 |
+
"loss": 1.4354,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.5688888888888889,
|
| 118 |
+
"grad_norm": 12.244831085205078,
|
| 119 |
+
"learning_rate": 2.400793650793651e-05,
|
| 120 |
+
"loss": 1.5286,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.6044444444444445,
|
| 125 |
+
"grad_norm": 9.033407211303711,
|
| 126 |
+
"learning_rate": 2.2023809523809524e-05,
|
| 127 |
+
"loss": 1.3584,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.64,
|
| 132 |
+
"grad_norm": 7.281382083892822,
|
| 133 |
+
"learning_rate": 2.003968253968254e-05,
|
| 134 |
+
"loss": 1.4626,
|
| 135 |
+
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.6755555555555556,
|
| 139 |
+
"grad_norm": 7.3251519203186035,
|
| 140 |
+
"learning_rate": 1.8055555555555555e-05,
|
| 141 |
+
"loss": 1.3453,
|
| 142 |
+
"step": 190
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.7111111111111111,
|
| 146 |
+
"grad_norm": 9.071359634399414,
|
| 147 |
+
"learning_rate": 1.6071428571428572e-05,
|
| 148 |
+
"loss": 1.3493,
|
| 149 |
+
"step": 200
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.7466666666666667,
|
| 153 |
+
"grad_norm": 11.566309928894043,
|
| 154 |
+
"learning_rate": 1.4087301587301587e-05,
|
| 155 |
+
"loss": 1.3759,
|
| 156 |
+
"step": 210
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.7822222222222223,
|
| 160 |
+
"grad_norm": 9.21988582611084,
|
| 161 |
+
"learning_rate": 1.2103174603174603e-05,
|
| 162 |
+
"loss": 1.365,
|
| 163 |
+
"step": 220
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.8177777777777778,
|
| 167 |
+
"grad_norm": 8.32099437713623,
|
| 168 |
+
"learning_rate": 1.011904761904762e-05,
|
| 169 |
+
"loss": 1.3049,
|
| 170 |
+
"step": 230
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.8533333333333334,
|
| 174 |
+
"grad_norm": 10.410431861877441,
|
| 175 |
+
"learning_rate": 8.134920634920636e-06,
|
| 176 |
+
"loss": 1.3583,
|
| 177 |
+
"step": 240
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.8888888888888888,
|
| 181 |
+
"grad_norm": 7.7621073722839355,
|
| 182 |
+
"learning_rate": 6.1507936507936505e-06,
|
| 183 |
+
"loss": 1.3066,
|
| 184 |
+
"step": 250
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.9244444444444444,
|
| 188 |
+
"grad_norm": 9.822245597839355,
|
| 189 |
+
"learning_rate": 4.166666666666667e-06,
|
| 190 |
+
"loss": 1.3564,
|
| 191 |
+
"step": 260
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.96,
|
| 195 |
+
"grad_norm": 11.113300323486328,
|
| 196 |
+
"learning_rate": 2.1825396825396824e-06,
|
| 197 |
+
"loss": 1.2959,
|
| 198 |
+
"step": 270
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.9955555555555555,
|
| 202 |
+
"grad_norm": 8.999974250793457,
|
| 203 |
+
"learning_rate": 1.9841269841269841e-07,
|
| 204 |
+
"loss": 1.3575,
|
| 205 |
+
"step": 280
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.9991111111111111,
|
| 209 |
+
"eval_accuracy": 0.62025,
|
| 210 |
+
"eval_loss": 1.2218776941299438,
|
| 211 |
+
"eval_runtime": 59.4645,
|
| 212 |
+
"eval_samples_per_second": 67.267,
|
| 213 |
+
"eval_steps_per_second": 2.102,
|
| 214 |
+
"step": 281
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 0.9991111111111111,
|
| 218 |
+
"step": 281,
|
| 219 |
+
"total_flos": 8.943699469318226e+17,
|
| 220 |
+
"train_loss": 1.6086162854768202,
|
| 221 |
+
"train_runtime": 797.2781,
|
| 222 |
+
"train_samples_per_second": 45.149,
|
| 223 |
+
"train_steps_per_second": 0.352
|
| 224 |
+
}
|
| 225 |
+
],
|
| 226 |
+
"logging_steps": 10,
|
| 227 |
+
"max_steps": 281,
|
| 228 |
+
"num_input_tokens_seen": 0,
|
| 229 |
+
"num_train_epochs": 1,
|
| 230 |
+
"save_steps": 500,
|
| 231 |
+
"stateful_callbacks": {
|
| 232 |
+
"TrainerControl": {
|
| 233 |
+
"args": {
|
| 234 |
+
"should_epoch_stop": false,
|
| 235 |
+
"should_evaluate": false,
|
| 236 |
+
"should_log": false,
|
| 237 |
+
"should_save": true,
|
| 238 |
+
"should_training_stop": true
|
| 239 |
+
},
|
| 240 |
+
"attributes": {}
|
| 241 |
+
}
|
| 242 |
+
},
|
| 243 |
+
"total_flos": 8.943699469318226e+17,
|
| 244 |
+
"train_batch_size": 32,
|
| 245 |
+
"trial_name": null,
|
| 246 |
+
"trial_params": null
|
| 247 |
+
}
|