End of training
Browse files
all_results.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"eval_accuracy": 0.8958333333333334,
|
| 4 |
+
"eval_loss": 0.4400902986526489,
|
| 5 |
+
"eval_runtime": 3.3735,
|
| 6 |
+
"eval_samples_per_second": 28.457,
|
| 7 |
+
"eval_steps_per_second": 3.557,
|
| 8 |
+
"total_flos": 9.499297468243968e+16,
|
| 9 |
+
"train_loss": 0.23564616565903027,
|
| 10 |
+
"train_runtime": 303.0343,
|
| 11 |
+
"train_samples_per_second": 12.474,
|
| 12 |
+
"train_steps_per_second": 1.584
|
| 13 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"eval_accuracy": 0.8958333333333334,
|
| 4 |
+
"eval_loss": 0.4400902986526489,
|
| 5 |
+
"eval_runtime": 3.3735,
|
| 6 |
+
"eval_samples_per_second": 28.457,
|
| 7 |
+
"eval_steps_per_second": 3.557
|
| 8 |
+
}
|
runs/Dec27_20-36-53_acc933989ffc/events.out.tfevents.1672173955.acc933989ffc.100.15
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d6390fe7ebe3d503b261168ae215b61f7be5c9b99dbab5542f6e3d84203141f1
|
| 3 |
+
size 363
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"total_flos": 9.499297468243968e+16,
|
| 4 |
+
"train_loss": 0.23564616565903027,
|
| 5 |
+
"train_runtime": 303.0343,
|
| 6 |
+
"train_samples_per_second": 12.474,
|
| 7 |
+
"train_steps_per_second": 1.584
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,403 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.8958333333333334,
|
| 3 |
+
"best_model_checkpoint": "convnext-tiny-224-klobasaniklobasa/checkpoint-288",
|
| 4 |
+
"epoch": 10.0,
|
| 5 |
+
"global_step": 480,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.21,
|
| 12 |
+
"learning_rate": 8.333333333333334e-06,
|
| 13 |
+
"loss": 0.608,
|
| 14 |
+
"step": 10
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.42,
|
| 18 |
+
"learning_rate": 1.6666666666666667e-05,
|
| 19 |
+
"loss": 0.6676,
|
| 20 |
+
"step": 20
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.62,
|
| 24 |
+
"learning_rate": 2.5e-05,
|
| 25 |
+
"loss": 0.6403,
|
| 26 |
+
"step": 30
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.83,
|
| 30 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 31 |
+
"loss": 0.7062,
|
| 32 |
+
"step": 40
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 1.0,
|
| 36 |
+
"eval_accuracy": 0.84375,
|
| 37 |
+
"eval_loss": 0.7115556597709656,
|
| 38 |
+
"eval_runtime": 3.3605,
|
| 39 |
+
"eval_samples_per_second": 28.567,
|
| 40 |
+
"eval_steps_per_second": 3.571,
|
| 41 |
+
"step": 48
|
| 42 |
+
},
|
| 43 |
+
{
|
| 44 |
+
"epoch": 1.04,
|
| 45 |
+
"learning_rate": 3.981481481481482e-05,
|
| 46 |
+
"loss": 0.5469,
|
| 47 |
+
"step": 50
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 1.25,
|
| 51 |
+
"learning_rate": 3.888888888888889e-05,
|
| 52 |
+
"loss": 0.5691,
|
| 53 |
+
"step": 60
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 1.46,
|
| 57 |
+
"learning_rate": 3.7962962962962964e-05,
|
| 58 |
+
"loss": 0.5161,
|
| 59 |
+
"step": 70
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 1.67,
|
| 63 |
+
"learning_rate": 3.703703703703704e-05,
|
| 64 |
+
"loss": 0.4157,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 1.88,
|
| 69 |
+
"learning_rate": 3.6111111111111116e-05,
|
| 70 |
+
"loss": 0.4831,
|
| 71 |
+
"step": 90
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 2.0,
|
| 75 |
+
"eval_accuracy": 0.8333333333333334,
|
| 76 |
+
"eval_loss": 0.5967997312545776,
|
| 77 |
+
"eval_runtime": 3.6773,
|
| 78 |
+
"eval_samples_per_second": 26.106,
|
| 79 |
+
"eval_steps_per_second": 3.263,
|
| 80 |
+
"step": 96
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 2.08,
|
| 84 |
+
"learning_rate": 3.518518518518519e-05,
|
| 85 |
+
"loss": 0.3808,
|
| 86 |
+
"step": 100
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 2.29,
|
| 90 |
+
"learning_rate": 3.425925925925926e-05,
|
| 91 |
+
"loss": 0.3956,
|
| 92 |
+
"step": 110
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 2.5,
|
| 96 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 97 |
+
"loss": 0.3992,
|
| 98 |
+
"step": 120
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 2.71,
|
| 102 |
+
"learning_rate": 3.2407407407407415e-05,
|
| 103 |
+
"loss": 0.3256,
|
| 104 |
+
"step": 130
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 2.92,
|
| 108 |
+
"learning_rate": 3.148148148148149e-05,
|
| 109 |
+
"loss": 0.2429,
|
| 110 |
+
"step": 140
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 3.0,
|
| 114 |
+
"eval_accuracy": 0.8541666666666666,
|
| 115 |
+
"eval_loss": 0.5383699536323547,
|
| 116 |
+
"eval_runtime": 3.5584,
|
| 117 |
+
"eval_samples_per_second": 26.979,
|
| 118 |
+
"eval_steps_per_second": 3.372,
|
| 119 |
+
"step": 144
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 3.12,
|
| 123 |
+
"learning_rate": 3.0555555555555554e-05,
|
| 124 |
+
"loss": 0.2586,
|
| 125 |
+
"step": 150
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 3.33,
|
| 129 |
+
"learning_rate": 2.962962962962963e-05,
|
| 130 |
+
"loss": 0.3041,
|
| 131 |
+
"step": 160
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 3.54,
|
| 135 |
+
"learning_rate": 2.8703703703703706e-05,
|
| 136 |
+
"loss": 0.2511,
|
| 137 |
+
"step": 170
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 3.75,
|
| 141 |
+
"learning_rate": 2.777777777777778e-05,
|
| 142 |
+
"loss": 0.2165,
|
| 143 |
+
"step": 180
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 3.96,
|
| 147 |
+
"learning_rate": 2.6851851851851852e-05,
|
| 148 |
+
"loss": 0.2292,
|
| 149 |
+
"step": 190
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 4.0,
|
| 153 |
+
"eval_accuracy": 0.84375,
|
| 154 |
+
"eval_loss": 0.4995401203632355,
|
| 155 |
+
"eval_runtime": 3.5701,
|
| 156 |
+
"eval_samples_per_second": 26.89,
|
| 157 |
+
"eval_steps_per_second": 3.361,
|
| 158 |
+
"step": 192
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 4.17,
|
| 162 |
+
"learning_rate": 2.5925925925925928e-05,
|
| 163 |
+
"loss": 0.2336,
|
| 164 |
+
"step": 200
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 4.38,
|
| 168 |
+
"learning_rate": 2.5e-05,
|
| 169 |
+
"loss": 0.1827,
|
| 170 |
+
"step": 210
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 4.58,
|
| 174 |
+
"learning_rate": 2.4074074074074077e-05,
|
| 175 |
+
"loss": 0.1918,
|
| 176 |
+
"step": 220
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 4.79,
|
| 180 |
+
"learning_rate": 2.314814814814815e-05,
|
| 181 |
+
"loss": 0.1316,
|
| 182 |
+
"step": 230
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 5.0,
|
| 186 |
+
"learning_rate": 2.2222222222222227e-05,
|
| 187 |
+
"loss": 0.1549,
|
| 188 |
+
"step": 240
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 5.0,
|
| 192 |
+
"eval_accuracy": 0.8854166666666666,
|
| 193 |
+
"eval_loss": 0.45076122879981995,
|
| 194 |
+
"eval_runtime": 3.3498,
|
| 195 |
+
"eval_samples_per_second": 28.658,
|
| 196 |
+
"eval_steps_per_second": 3.582,
|
| 197 |
+
"step": 240
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 5.21,
|
| 201 |
+
"learning_rate": 2.12962962962963e-05,
|
| 202 |
+
"loss": 0.0792,
|
| 203 |
+
"step": 250
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 5.42,
|
| 207 |
+
"learning_rate": 2.0370370370370372e-05,
|
| 208 |
+
"loss": 0.1449,
|
| 209 |
+
"step": 260
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 5.62,
|
| 213 |
+
"learning_rate": 1.9444444444444445e-05,
|
| 214 |
+
"loss": 0.0869,
|
| 215 |
+
"step": 270
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 5.83,
|
| 219 |
+
"learning_rate": 1.851851851851852e-05,
|
| 220 |
+
"loss": 0.1682,
|
| 221 |
+
"step": 280
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 6.0,
|
| 225 |
+
"eval_accuracy": 0.8958333333333334,
|
| 226 |
+
"eval_loss": 0.4400902986526489,
|
| 227 |
+
"eval_runtime": 3.566,
|
| 228 |
+
"eval_samples_per_second": 26.921,
|
| 229 |
+
"eval_steps_per_second": 3.365,
|
| 230 |
+
"step": 288
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 6.04,
|
| 234 |
+
"learning_rate": 1.7592592592592595e-05,
|
| 235 |
+
"loss": 0.1264,
|
| 236 |
+
"step": 290
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 6.25,
|
| 240 |
+
"learning_rate": 1.6666666666666667e-05,
|
| 241 |
+
"loss": 0.1211,
|
| 242 |
+
"step": 300
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 6.46,
|
| 246 |
+
"learning_rate": 1.5740740740740744e-05,
|
| 247 |
+
"loss": 0.0649,
|
| 248 |
+
"step": 310
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 6.67,
|
| 252 |
+
"learning_rate": 1.4814814814814815e-05,
|
| 253 |
+
"loss": 0.1159,
|
| 254 |
+
"step": 320
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 6.88,
|
| 258 |
+
"learning_rate": 1.388888888888889e-05,
|
| 259 |
+
"loss": 0.1736,
|
| 260 |
+
"step": 330
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 7.0,
|
| 264 |
+
"eval_accuracy": 0.8958333333333334,
|
| 265 |
+
"eval_loss": 0.4440065622329712,
|
| 266 |
+
"eval_runtime": 3.5045,
|
| 267 |
+
"eval_samples_per_second": 27.393,
|
| 268 |
+
"eval_steps_per_second": 3.424,
|
| 269 |
+
"step": 336
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 7.08,
|
| 273 |
+
"learning_rate": 1.2962962962962964e-05,
|
| 274 |
+
"loss": 0.0679,
|
| 275 |
+
"step": 340
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 7.29,
|
| 279 |
+
"learning_rate": 1.2037037037037039e-05,
|
| 280 |
+
"loss": 0.0915,
|
| 281 |
+
"step": 350
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 7.5,
|
| 285 |
+
"learning_rate": 1.1111111111111113e-05,
|
| 286 |
+
"loss": 0.1254,
|
| 287 |
+
"step": 360
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 7.71,
|
| 291 |
+
"learning_rate": 1.0185185185185186e-05,
|
| 292 |
+
"loss": 0.0588,
|
| 293 |
+
"step": 370
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 7.92,
|
| 297 |
+
"learning_rate": 9.25925925925926e-06,
|
| 298 |
+
"loss": 0.0633,
|
| 299 |
+
"step": 380
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 8.0,
|
| 303 |
+
"eval_accuracy": 0.8958333333333334,
|
| 304 |
+
"eval_loss": 0.44057992100715637,
|
| 305 |
+
"eval_runtime": 3.5708,
|
| 306 |
+
"eval_samples_per_second": 26.885,
|
| 307 |
+
"eval_steps_per_second": 3.361,
|
| 308 |
+
"step": 384
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 8.12,
|
| 312 |
+
"learning_rate": 8.333333333333334e-06,
|
| 313 |
+
"loss": 0.0512,
|
| 314 |
+
"step": 390
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 8.33,
|
| 318 |
+
"learning_rate": 7.4074074074074075e-06,
|
| 319 |
+
"loss": 0.129,
|
| 320 |
+
"step": 400
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 8.54,
|
| 324 |
+
"learning_rate": 6.481481481481482e-06,
|
| 325 |
+
"loss": 0.0776,
|
| 326 |
+
"step": 410
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 8.75,
|
| 330 |
+
"learning_rate": 5.555555555555557e-06,
|
| 331 |
+
"loss": 0.0628,
|
| 332 |
+
"step": 420
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 8.96,
|
| 336 |
+
"learning_rate": 4.62962962962963e-06,
|
| 337 |
+
"loss": 0.0689,
|
| 338 |
+
"step": 430
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 9.0,
|
| 342 |
+
"eval_accuracy": 0.8958333333333334,
|
| 343 |
+
"eval_loss": 0.4371330738067627,
|
| 344 |
+
"eval_runtime": 3.3898,
|
| 345 |
+
"eval_samples_per_second": 28.32,
|
| 346 |
+
"eval_steps_per_second": 3.54,
|
| 347 |
+
"step": 432
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"epoch": 9.17,
|
| 351 |
+
"learning_rate": 3.7037037037037037e-06,
|
| 352 |
+
"loss": 0.0947,
|
| 353 |
+
"step": 440
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 9.38,
|
| 357 |
+
"learning_rate": 2.7777777777777783e-06,
|
| 358 |
+
"loss": 0.1003,
|
| 359 |
+
"step": 450
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 9.58,
|
| 363 |
+
"learning_rate": 1.8518518518518519e-06,
|
| 364 |
+
"loss": 0.0593,
|
| 365 |
+
"step": 460
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 9.79,
|
| 369 |
+
"learning_rate": 9.259259259259259e-07,
|
| 370 |
+
"loss": 0.0722,
|
| 371 |
+
"step": 470
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 10.0,
|
| 375 |
+
"learning_rate": 0.0,
|
| 376 |
+
"loss": 0.0558,
|
| 377 |
+
"step": 480
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 10.0,
|
| 381 |
+
"eval_accuracy": 0.8958333333333334,
|
| 382 |
+
"eval_loss": 0.43337997794151306,
|
| 383 |
+
"eval_runtime": 4.6987,
|
| 384 |
+
"eval_samples_per_second": 20.431,
|
| 385 |
+
"eval_steps_per_second": 2.554,
|
| 386 |
+
"step": 480
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 10.0,
|
| 390 |
+
"step": 480,
|
| 391 |
+
"total_flos": 9.499297468243968e+16,
|
| 392 |
+
"train_loss": 0.23564616565903027,
|
| 393 |
+
"train_runtime": 303.0343,
|
| 394 |
+
"train_samples_per_second": 12.474,
|
| 395 |
+
"train_steps_per_second": 1.584
|
| 396 |
+
}
|
| 397 |
+
],
|
| 398 |
+
"max_steps": 480,
|
| 399 |
+
"num_train_epochs": 10,
|
| 400 |
+
"total_flos": 9.499297468243968e+16,
|
| 401 |
+
"trial_name": null,
|
| 402 |
+
"trial_params": null
|
| 403 |
+
}
|