🍻 cheers
Browse files
all_results.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.0,
|
| 3 |
+
"eval_accuracy": 0.9918582375478927,
|
| 4 |
+
"eval_loss": 0.026852501556277275,
|
| 5 |
+
"eval_runtime": 14.6756,
|
| 6 |
+
"eval_samples_per_second": 142.277,
|
| 7 |
+
"eval_steps_per_second": 17.785,
|
| 8 |
+
"total_flos": 3.522751306056622e+18,
|
| 9 |
+
"train_loss": 0.05303763715957088,
|
| 10 |
+
"train_runtime": 404.1694,
|
| 11 |
+
"train_samples_per_second": 110.201,
|
| 12 |
+
"train_steps_per_second": 0.861
|
| 13 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.0,
|
| 3 |
+
"eval_accuracy": 0.9918582375478927,
|
| 4 |
+
"eval_loss": 0.026852501556277275,
|
| 5 |
+
"eval_runtime": 14.6756,
|
| 6 |
+
"eval_samples_per_second": 142.277,
|
| 7 |
+
"eval_steps_per_second": 17.785
|
| 8 |
+
}
|
runs/Nov19_15-25-15_12fd5a028bd4/events.out.tfevents.1668872454.12fd5a028bd4.107.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e6205bb939f8c553c3fdce5e1422d8f98602a9132f2f5b2d3b9d2c28eb27b4b8
|
| 3 |
+
size 363
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.0,
|
| 3 |
+
"total_flos": 3.522751306056622e+18,
|
| 4 |
+
"train_loss": 0.05303763715957088,
|
| 5 |
+
"train_runtime": 404.1694,
|
| 6 |
+
"train_samples_per_second": 110.201,
|
| 7 |
+
"train_steps_per_second": 0.861
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,238 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.026852501556277275,
|
| 3 |
+
"best_model_checkpoint": "./ConvNext-base-chesapeake-land-cover-v0/checkpoint-300",
|
| 4 |
+
"epoch": 4.0,
|
| 5 |
+
"global_step": 348,
|
| 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": 0.0001942528735632184,
|
| 13 |
+
"loss": 0.8419,
|
| 14 |
+
"step": 10
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.23,
|
| 18 |
+
"learning_rate": 0.00018850574712643678,
|
| 19 |
+
"loss": 0.1669,
|
| 20 |
+
"step": 20
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.34,
|
| 24 |
+
"learning_rate": 0.00018275862068965518,
|
| 25 |
+
"loss": 0.1106,
|
| 26 |
+
"step": 30
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.46,
|
| 30 |
+
"learning_rate": 0.00017701149425287358,
|
| 31 |
+
"loss": 0.0916,
|
| 32 |
+
"step": 40
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.57,
|
| 36 |
+
"learning_rate": 0.00017126436781609197,
|
| 37 |
+
"loss": 0.0701,
|
| 38 |
+
"step": 50
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.69,
|
| 42 |
+
"learning_rate": 0.00016551724137931035,
|
| 43 |
+
"loss": 0.0838,
|
| 44 |
+
"step": 60
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.8,
|
| 48 |
+
"learning_rate": 0.00015977011494252874,
|
| 49 |
+
"loss": 0.0533,
|
| 50 |
+
"step": 70
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.92,
|
| 54 |
+
"learning_rate": 0.00015402298850574712,
|
| 55 |
+
"loss": 0.0329,
|
| 56 |
+
"step": 80
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 1.03,
|
| 60 |
+
"learning_rate": 0.00014827586206896554,
|
| 61 |
+
"loss": 0.0548,
|
| 62 |
+
"step": 90
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 1.15,
|
| 66 |
+
"learning_rate": 0.0001425287356321839,
|
| 67 |
+
"loss": 0.0341,
|
| 68 |
+
"step": 100
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 1.26,
|
| 72 |
+
"learning_rate": 0.0001367816091954023,
|
| 73 |
+
"loss": 0.0346,
|
| 74 |
+
"step": 110
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 1.38,
|
| 78 |
+
"learning_rate": 0.00013103448275862068,
|
| 79 |
+
"loss": 0.0279,
|
| 80 |
+
"step": 120
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 1.49,
|
| 84 |
+
"learning_rate": 0.00012528735632183908,
|
| 85 |
+
"loss": 0.0207,
|
| 86 |
+
"step": 130
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 1.61,
|
| 90 |
+
"learning_rate": 0.00011954022988505748,
|
| 91 |
+
"loss": 0.0157,
|
| 92 |
+
"step": 140
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 1.72,
|
| 96 |
+
"learning_rate": 0.00011379310344827588,
|
| 97 |
+
"loss": 0.0254,
|
| 98 |
+
"step": 150
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 1.84,
|
| 102 |
+
"learning_rate": 0.00010804597701149426,
|
| 103 |
+
"loss": 0.0286,
|
| 104 |
+
"step": 160
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 1.95,
|
| 108 |
+
"learning_rate": 0.00010229885057471265,
|
| 109 |
+
"loss": 0.028,
|
| 110 |
+
"step": 170
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 2.07,
|
| 114 |
+
"learning_rate": 9.655172413793105e-05,
|
| 115 |
+
"loss": 0.0158,
|
| 116 |
+
"step": 180
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 2.18,
|
| 120 |
+
"learning_rate": 9.080459770114943e-05,
|
| 121 |
+
"loss": 0.0126,
|
| 122 |
+
"step": 190
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 2.3,
|
| 126 |
+
"learning_rate": 8.505747126436782e-05,
|
| 127 |
+
"loss": 0.013,
|
| 128 |
+
"step": 200
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 2.41,
|
| 132 |
+
"learning_rate": 7.931034482758621e-05,
|
| 133 |
+
"loss": 0.0113,
|
| 134 |
+
"step": 210
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 2.53,
|
| 138 |
+
"learning_rate": 7.35632183908046e-05,
|
| 139 |
+
"loss": 0.0153,
|
| 140 |
+
"step": 220
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 2.64,
|
| 144 |
+
"learning_rate": 6.781609195402298e-05,
|
| 145 |
+
"loss": 0.0083,
|
| 146 |
+
"step": 230
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 2.76,
|
| 150 |
+
"learning_rate": 6.206896551724138e-05,
|
| 151 |
+
"loss": 0.008,
|
| 152 |
+
"step": 240
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 2.87,
|
| 156 |
+
"learning_rate": 5.632183908045977e-05,
|
| 157 |
+
"loss": 0.0056,
|
| 158 |
+
"step": 250
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 2.99,
|
| 162 |
+
"learning_rate": 5.057471264367817e-05,
|
| 163 |
+
"loss": 0.0076,
|
| 164 |
+
"step": 260
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 3.1,
|
| 168 |
+
"learning_rate": 4.482758620689655e-05,
|
| 169 |
+
"loss": 0.0038,
|
| 170 |
+
"step": 270
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 3.22,
|
| 174 |
+
"learning_rate": 3.908045977011495e-05,
|
| 175 |
+
"loss": 0.0023,
|
| 176 |
+
"step": 280
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 3.33,
|
| 180 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 181 |
+
"loss": 0.0032,
|
| 182 |
+
"step": 290
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 3.45,
|
| 186 |
+
"learning_rate": 2.7586206896551727e-05,
|
| 187 |
+
"loss": 0.0076,
|
| 188 |
+
"step": 300
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 3.45,
|
| 192 |
+
"eval_accuracy": 0.9918582375478927,
|
| 193 |
+
"eval_loss": 0.026852501556277275,
|
| 194 |
+
"eval_runtime": 14.7576,
|
| 195 |
+
"eval_samples_per_second": 141.486,
|
| 196 |
+
"eval_steps_per_second": 17.686,
|
| 197 |
+
"step": 300
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 3.56,
|
| 201 |
+
"learning_rate": 2.183908045977012e-05,
|
| 202 |
+
"loss": 0.0028,
|
| 203 |
+
"step": 310
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 3.68,
|
| 207 |
+
"learning_rate": 1.6091954022988507e-05,
|
| 208 |
+
"loss": 0.0022,
|
| 209 |
+
"step": 320
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 3.79,
|
| 213 |
+
"learning_rate": 1.0344827586206897e-05,
|
| 214 |
+
"loss": 0.0023,
|
| 215 |
+
"step": 330
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 3.91,
|
| 219 |
+
"learning_rate": 4.5977011494252875e-06,
|
| 220 |
+
"loss": 0.0017,
|
| 221 |
+
"step": 340
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 4.0,
|
| 225 |
+
"step": 348,
|
| 226 |
+
"total_flos": 3.522751306056622e+18,
|
| 227 |
+
"train_loss": 0.05303763715957088,
|
| 228 |
+
"train_runtime": 404.1694,
|
| 229 |
+
"train_samples_per_second": 110.201,
|
| 230 |
+
"train_steps_per_second": 0.861
|
| 231 |
+
}
|
| 232 |
+
],
|
| 233 |
+
"max_steps": 348,
|
| 234 |
+
"num_train_epochs": 4,
|
| 235 |
+
"total_flos": 3.522751306056622e+18,
|
| 236 |
+
"trial_name": null,
|
| 237 |
+
"trial_params": null
|
| 238 |
+
}
|