End of training
Browse files
all_results.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.99,
|
| 3 |
+
"eval_accuracy": 0.7812061711079944,
|
| 4 |
+
"eval_loss": 0.5785719156265259,
|
| 5 |
+
"eval_runtime": 39.667,
|
| 6 |
+
"eval_samples_per_second": 71.899,
|
| 7 |
+
"eval_steps_per_second": 1.134,
|
| 8 |
+
"total_flos": 1.9092599963910144e+18,
|
| 9 |
+
"train_loss": 0.8440527868270874,
|
| 10 |
+
"train_runtime": 1489.601,
|
| 11 |
+
"train_samples_per_second": 51.686,
|
| 12 |
+
"train_steps_per_second": 0.201
|
| 13 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.99,
|
| 3 |
+
"eval_accuracy": 0.7812061711079944,
|
| 4 |
+
"eval_loss": 0.5785719156265259,
|
| 5 |
+
"eval_runtime": 39.667,
|
| 6 |
+
"eval_samples_per_second": 71.899,
|
| 7 |
+
"eval_steps_per_second": 1.134
|
| 8 |
+
}
|
runs/Apr22_17-14-25_822cc979178f/events.out.tfevents.1713807754.822cc979178f.35.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dd2145ac948ecd293e7cb0004acc2d4235dc2c5ae4c5982359b6c3d3a28c658a
|
| 3 |
+
size 411
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.99,
|
| 3 |
+
"total_flos": 1.9092599963910144e+18,
|
| 4 |
+
"train_loss": 0.8440527868270874,
|
| 5 |
+
"train_runtime": 1489.601,
|
| 6 |
+
"train_samples_per_second": 51.686,
|
| 7 |
+
"train_steps_per_second": 0.201
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,267 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.7812061711079944,
|
| 3 |
+
"best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-eurosat/checkpoint-300",
|
| 4 |
+
"epoch": 2.9925187032418954,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 300,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.1,
|
| 13 |
+
"grad_norm": 5.978888988494873,
|
| 14 |
+
"learning_rate": 1.6666666666666667e-05,
|
| 15 |
+
"loss": 2.0615,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.2,
|
| 20 |
+
"grad_norm": 5.561241149902344,
|
| 21 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 22 |
+
"loss": 1.7164,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.3,
|
| 27 |
+
"grad_norm": 4.879634857177734,
|
| 28 |
+
"learning_rate": 5e-05,
|
| 29 |
+
"loss": 1.3532,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.4,
|
| 34 |
+
"grad_norm": 8.15771198272705,
|
| 35 |
+
"learning_rate": 4.814814814814815e-05,
|
| 36 |
+
"loss": 1.1296,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.5,
|
| 41 |
+
"grad_norm": 5.303676128387451,
|
| 42 |
+
"learning_rate": 4.62962962962963e-05,
|
| 43 |
+
"loss": 1.0239,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.6,
|
| 48 |
+
"grad_norm": 6.73429536819458,
|
| 49 |
+
"learning_rate": 4.4444444444444447e-05,
|
| 50 |
+
"loss": 0.9523,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.7,
|
| 55 |
+
"grad_norm": 5.433155059814453,
|
| 56 |
+
"learning_rate": 4.259259259259259e-05,
|
| 57 |
+
"loss": 0.931,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.8,
|
| 62 |
+
"grad_norm": 5.7002854347229,
|
| 63 |
+
"learning_rate": 4.074074074074074e-05,
|
| 64 |
+
"loss": 0.86,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.9,
|
| 69 |
+
"grad_norm": 7.802429676055908,
|
| 70 |
+
"learning_rate": 3.888888888888889e-05,
|
| 71 |
+
"loss": 0.8574,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 1.0,
|
| 76 |
+
"grad_norm": 5.270522117614746,
|
| 77 |
+
"learning_rate": 3.7037037037037037e-05,
|
| 78 |
+
"loss": 0.8284,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 1.0,
|
| 83 |
+
"eval_accuracy": 0.7166900420757363,
|
| 84 |
+
"eval_loss": 0.7453354597091675,
|
| 85 |
+
"eval_runtime": 39.771,
|
| 86 |
+
"eval_samples_per_second": 71.711,
|
| 87 |
+
"eval_steps_per_second": 1.131,
|
| 88 |
+
"step": 100
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 1.1,
|
| 92 |
+
"grad_norm": 5.239772796630859,
|
| 93 |
+
"learning_rate": 3.518518518518519e-05,
|
| 94 |
+
"loss": 0.8073,
|
| 95 |
+
"step": 110
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 1.2,
|
| 99 |
+
"grad_norm": 7.129805088043213,
|
| 100 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 101 |
+
"loss": 0.7591,
|
| 102 |
+
"step": 120
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 1.3,
|
| 106 |
+
"grad_norm": 5.309109687805176,
|
| 107 |
+
"learning_rate": 3.148148148148148e-05,
|
| 108 |
+
"loss": 0.7565,
|
| 109 |
+
"step": 130
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 1.4,
|
| 113 |
+
"grad_norm": 6.846292972564697,
|
| 114 |
+
"learning_rate": 2.962962962962963e-05,
|
| 115 |
+
"loss": 0.7205,
|
| 116 |
+
"step": 140
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 1.5,
|
| 120 |
+
"grad_norm": 4.7191572189331055,
|
| 121 |
+
"learning_rate": 2.777777777777778e-05,
|
| 122 |
+
"loss": 0.7412,
|
| 123 |
+
"step": 150
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 1.6,
|
| 127 |
+
"grad_norm": 6.145421981811523,
|
| 128 |
+
"learning_rate": 2.5925925925925925e-05,
|
| 129 |
+
"loss": 0.7029,
|
| 130 |
+
"step": 160
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 1.7,
|
| 134 |
+
"grad_norm": 6.272791385650635,
|
| 135 |
+
"learning_rate": 2.4074074074074074e-05,
|
| 136 |
+
"loss": 0.7253,
|
| 137 |
+
"step": 170
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 1.8,
|
| 141 |
+
"grad_norm": 5.79164457321167,
|
| 142 |
+
"learning_rate": 2.2222222222222223e-05,
|
| 143 |
+
"loss": 0.7195,
|
| 144 |
+
"step": 180
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 1.9,
|
| 148 |
+
"grad_norm": 5.050856590270996,
|
| 149 |
+
"learning_rate": 2.037037037037037e-05,
|
| 150 |
+
"loss": 0.6927,
|
| 151 |
+
"step": 190
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 2.0,
|
| 155 |
+
"grad_norm": 4.7087554931640625,
|
| 156 |
+
"learning_rate": 1.8518518518518518e-05,
|
| 157 |
+
"loss": 0.6807,
|
| 158 |
+
"step": 200
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 2.0,
|
| 162 |
+
"eval_accuracy": 0.7622720897615708,
|
| 163 |
+
"eval_loss": 0.6100432872772217,
|
| 164 |
+
"eval_runtime": 39.0846,
|
| 165 |
+
"eval_samples_per_second": 72.97,
|
| 166 |
+
"eval_steps_per_second": 1.151,
|
| 167 |
+
"step": 200
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 2.09,
|
| 171 |
+
"grad_norm": 4.873398780822754,
|
| 172 |
+
"learning_rate": 1.6666666666666667e-05,
|
| 173 |
+
"loss": 0.6583,
|
| 174 |
+
"step": 210
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 2.19,
|
| 178 |
+
"grad_norm": 5.965737342834473,
|
| 179 |
+
"learning_rate": 1.4814814814814815e-05,
|
| 180 |
+
"loss": 0.5997,
|
| 181 |
+
"step": 220
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 2.29,
|
| 185 |
+
"grad_norm": 5.910747051239014,
|
| 186 |
+
"learning_rate": 1.2962962962962962e-05,
|
| 187 |
+
"loss": 0.6797,
|
| 188 |
+
"step": 230
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 2.39,
|
| 192 |
+
"grad_norm": 5.015042781829834,
|
| 193 |
+
"learning_rate": 1.1111111111111112e-05,
|
| 194 |
+
"loss": 0.6473,
|
| 195 |
+
"step": 240
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 2.49,
|
| 199 |
+
"grad_norm": 4.869871616363525,
|
| 200 |
+
"learning_rate": 9.259259259259259e-06,
|
| 201 |
+
"loss": 0.6486,
|
| 202 |
+
"step": 250
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 2.59,
|
| 206 |
+
"grad_norm": 5.467216491699219,
|
| 207 |
+
"learning_rate": 7.4074074074074075e-06,
|
| 208 |
+
"loss": 0.611,
|
| 209 |
+
"step": 260
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 2.69,
|
| 213 |
+
"grad_norm": 4.853744983673096,
|
| 214 |
+
"learning_rate": 5.555555555555556e-06,
|
| 215 |
+
"loss": 0.6041,
|
| 216 |
+
"step": 270
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 2.79,
|
| 220 |
+
"grad_norm": 5.990160942077637,
|
| 221 |
+
"learning_rate": 3.7037037037037037e-06,
|
| 222 |
+
"loss": 0.6201,
|
| 223 |
+
"step": 280
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 2.89,
|
| 227 |
+
"grad_norm": 5.613973140716553,
|
| 228 |
+
"learning_rate": 1.8518518518518519e-06,
|
| 229 |
+
"loss": 0.5962,
|
| 230 |
+
"step": 290
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 2.99,
|
| 234 |
+
"grad_norm": 6.6730828285217285,
|
| 235 |
+
"learning_rate": 0.0,
|
| 236 |
+
"loss": 0.6372,
|
| 237 |
+
"step": 300
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 2.99,
|
| 241 |
+
"eval_accuracy": 0.7812061711079944,
|
| 242 |
+
"eval_loss": 0.5785719156265259,
|
| 243 |
+
"eval_runtime": 39.5945,
|
| 244 |
+
"eval_samples_per_second": 72.03,
|
| 245 |
+
"eval_steps_per_second": 1.137,
|
| 246 |
+
"step": 300
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 2.99,
|
| 250 |
+
"step": 300,
|
| 251 |
+
"total_flos": 1.9092599963910144e+18,
|
| 252 |
+
"train_loss": 0.8440527868270874,
|
| 253 |
+
"train_runtime": 1489.601,
|
| 254 |
+
"train_samples_per_second": 51.686,
|
| 255 |
+
"train_steps_per_second": 0.201
|
| 256 |
+
}
|
| 257 |
+
],
|
| 258 |
+
"logging_steps": 10,
|
| 259 |
+
"max_steps": 300,
|
| 260 |
+
"num_input_tokens_seen": 0,
|
| 261 |
+
"num_train_epochs": 3,
|
| 262 |
+
"save_steps": 500,
|
| 263 |
+
"total_flos": 1.9092599963910144e+18,
|
| 264 |
+
"train_batch_size": 64,
|
| 265 |
+
"trial_name": null,
|
| 266 |
+
"trial_params": null
|
| 267 |
+
}
|