End of training
Browse files
all_results.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.99,
|
| 3 |
+
"eval_accuracy": 0.9957828149710068,
|
| 4 |
+
"eval_loss": 0.01684400625526905,
|
| 5 |
+
"eval_runtime": 8.8295,
|
| 6 |
+
"eval_samples_per_second": 214.848,
|
| 7 |
+
"eval_steps_per_second": 6.795,
|
| 8 |
+
"total_flos": 3.954296686846206e+18,
|
| 9 |
+
"train_loss": 0.08411522551362675,
|
| 10 |
+
"train_runtime": 524.0438,
|
| 11 |
+
"train_samples_per_second": 97.698,
|
| 12 |
+
"train_steps_per_second": 0.761
|
| 13 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.99,
|
| 3 |
+
"eval_accuracy": 0.9957828149710068,
|
| 4 |
+
"eval_loss": 0.01684400625526905,
|
| 5 |
+
"eval_runtime": 8.8295,
|
| 6 |
+
"eval_samples_per_second": 214.848,
|
| 7 |
+
"eval_steps_per_second": 6.795
|
| 8 |
+
}
|
runs/Feb22_01-29-19_e0eba228dbb5/events.out.tfevents.1708565952.e0eba228dbb5.9867.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ff544a018ec4fbed2ac14c9ee46c82702f645835763fba4f2f379b2dfb6df310
|
| 3 |
+
size 411
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.99,
|
| 3 |
+
"total_flos": 3.954296686846206e+18,
|
| 4 |
+
"train_loss": 0.08411522551362675,
|
| 5 |
+
"train_runtime": 524.0438,
|
| 6 |
+
"train_samples_per_second": 97.698,
|
| 7 |
+
"train_steps_per_second": 0.761
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,330 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.9957828149710068,
|
| 3 |
+
"best_model_checkpoint": "vit-base-patch16-224-crochets-clothes-classification/checkpoint-399",
|
| 4 |
+
"epoch": 2.98876404494382,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 399,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.07,
|
| 13 |
+
"grad_norm": 4.591014385223389,
|
| 14 |
+
"learning_rate": 1.25e-05,
|
| 15 |
+
"loss": 1.1212,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.15,
|
| 20 |
+
"grad_norm": 2.8302791118621826,
|
| 21 |
+
"learning_rate": 2.5e-05,
|
| 22 |
+
"loss": 0.7817,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.22,
|
| 27 |
+
"grad_norm": 1.3665571212768555,
|
| 28 |
+
"learning_rate": 3.7500000000000003e-05,
|
| 29 |
+
"loss": 0.3726,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.3,
|
| 34 |
+
"grad_norm": 0.4955084025859833,
|
| 35 |
+
"learning_rate": 5e-05,
|
| 36 |
+
"loss": 0.1163,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.37,
|
| 41 |
+
"grad_norm": 0.4771425724029541,
|
| 42 |
+
"learning_rate": 4.860724233983287e-05,
|
| 43 |
+
"loss": 0.083,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.45,
|
| 48 |
+
"grad_norm": 0.48831480741500854,
|
| 49 |
+
"learning_rate": 4.721448467966574e-05,
|
| 50 |
+
"loss": 0.0505,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.52,
|
| 55 |
+
"grad_norm": 1.4589921236038208,
|
| 56 |
+
"learning_rate": 4.582172701949861e-05,
|
| 57 |
+
"loss": 0.0598,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.6,
|
| 62 |
+
"grad_norm": 0.9677128195762634,
|
| 63 |
+
"learning_rate": 4.442896935933148e-05,
|
| 64 |
+
"loss": 0.0551,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.67,
|
| 69 |
+
"grad_norm": 0.7934716939926147,
|
| 70 |
+
"learning_rate": 4.303621169916435e-05,
|
| 71 |
+
"loss": 0.0334,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.75,
|
| 76 |
+
"grad_norm": 0.7208961844444275,
|
| 77 |
+
"learning_rate": 4.164345403899722e-05,
|
| 78 |
+
"loss": 0.0548,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.82,
|
| 83 |
+
"grad_norm": 1.7045996189117432,
|
| 84 |
+
"learning_rate": 4.0250696378830085e-05,
|
| 85 |
+
"loss": 0.0325,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.9,
|
| 90 |
+
"grad_norm": 0.776774525642395,
|
| 91 |
+
"learning_rate": 3.885793871866296e-05,
|
| 92 |
+
"loss": 0.0203,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.97,
|
| 97 |
+
"grad_norm": 0.20739926397800446,
|
| 98 |
+
"learning_rate": 3.746518105849583e-05,
|
| 99 |
+
"loss": 0.037,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 1.0,
|
| 104 |
+
"eval_accuracy": 0.9910384818133896,
|
| 105 |
+
"eval_loss": 0.025993211194872856,
|
| 106 |
+
"eval_runtime": 8.9011,
|
| 107 |
+
"eval_samples_per_second": 213.121,
|
| 108 |
+
"eval_steps_per_second": 6.741,
|
| 109 |
+
"step": 133
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 1.05,
|
| 113 |
+
"grad_norm": 0.6267848014831543,
|
| 114 |
+
"learning_rate": 3.607242339832869e-05,
|
| 115 |
+
"loss": 0.0413,
|
| 116 |
+
"step": 140
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 1.12,
|
| 120 |
+
"grad_norm": 0.565723717212677,
|
| 121 |
+
"learning_rate": 3.4679665738161556e-05,
|
| 122 |
+
"loss": 0.0213,
|
| 123 |
+
"step": 150
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 1.2,
|
| 127 |
+
"grad_norm": 0.9837281107902527,
|
| 128 |
+
"learning_rate": 3.328690807799443e-05,
|
| 129 |
+
"loss": 0.0318,
|
| 130 |
+
"step": 160
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 1.27,
|
| 134 |
+
"grad_norm": 0.34034019708633423,
|
| 135 |
+
"learning_rate": 3.18941504178273e-05,
|
| 136 |
+
"loss": 0.0249,
|
| 137 |
+
"step": 170
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 1.35,
|
| 141 |
+
"grad_norm": 1.20231294631958,
|
| 142 |
+
"learning_rate": 3.050139275766017e-05,
|
| 143 |
+
"loss": 0.035,
|
| 144 |
+
"step": 180
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 1.42,
|
| 148 |
+
"grad_norm": 0.7923780679702759,
|
| 149 |
+
"learning_rate": 2.9108635097493035e-05,
|
| 150 |
+
"loss": 0.023,
|
| 151 |
+
"step": 190
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 1.5,
|
| 155 |
+
"grad_norm": 0.2982392907142639,
|
| 156 |
+
"learning_rate": 2.7715877437325903e-05,
|
| 157 |
+
"loss": 0.0226,
|
| 158 |
+
"step": 200
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 1.57,
|
| 162 |
+
"grad_norm": 1.0568493604660034,
|
| 163 |
+
"learning_rate": 2.6323119777158778e-05,
|
| 164 |
+
"loss": 0.013,
|
| 165 |
+
"step": 210
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 1.65,
|
| 169 |
+
"grad_norm": 0.593539834022522,
|
| 170 |
+
"learning_rate": 2.4930362116991646e-05,
|
| 171 |
+
"loss": 0.0277,
|
| 172 |
+
"step": 220
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 1.72,
|
| 176 |
+
"grad_norm": 0.1592184454202652,
|
| 177 |
+
"learning_rate": 2.3537604456824514e-05,
|
| 178 |
+
"loss": 0.0181,
|
| 179 |
+
"step": 230
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 1.8,
|
| 183 |
+
"grad_norm": 0.758721649646759,
|
| 184 |
+
"learning_rate": 2.214484679665738e-05,
|
| 185 |
+
"loss": 0.0286,
|
| 186 |
+
"step": 240
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 1.87,
|
| 190 |
+
"grad_norm": 0.1289820671081543,
|
| 191 |
+
"learning_rate": 2.0752089136490253e-05,
|
| 192 |
+
"loss": 0.0187,
|
| 193 |
+
"step": 250
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 1.95,
|
| 197 |
+
"grad_norm": 0.2615315616130829,
|
| 198 |
+
"learning_rate": 1.935933147632312e-05,
|
| 199 |
+
"loss": 0.0235,
|
| 200 |
+
"step": 260
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 2.0,
|
| 204 |
+
"eval_accuracy": 0.9942013705851345,
|
| 205 |
+
"eval_loss": 0.017579538747668266,
|
| 206 |
+
"eval_runtime": 8.8128,
|
| 207 |
+
"eval_samples_per_second": 215.255,
|
| 208 |
+
"eval_steps_per_second": 6.808,
|
| 209 |
+
"step": 267
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 2.02,
|
| 213 |
+
"grad_norm": 0.3360155522823334,
|
| 214 |
+
"learning_rate": 1.7966573816155992e-05,
|
| 215 |
+
"loss": 0.0192,
|
| 216 |
+
"step": 270
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 2.1,
|
| 220 |
+
"grad_norm": 0.3642173409461975,
|
| 221 |
+
"learning_rate": 1.6573816155988857e-05,
|
| 222 |
+
"loss": 0.0095,
|
| 223 |
+
"step": 280
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 2.17,
|
| 227 |
+
"grad_norm": 0.2768695652484894,
|
| 228 |
+
"learning_rate": 1.518105849582173e-05,
|
| 229 |
+
"loss": 0.024,
|
| 230 |
+
"step": 290
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 2.25,
|
| 234 |
+
"grad_norm": 0.45118042826652527,
|
| 235 |
+
"learning_rate": 1.3788300835654596e-05,
|
| 236 |
+
"loss": 0.0168,
|
| 237 |
+
"step": 300
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 2.32,
|
| 241 |
+
"grad_norm": 0.7551447749137878,
|
| 242 |
+
"learning_rate": 1.2395543175487466e-05,
|
| 243 |
+
"loss": 0.0145,
|
| 244 |
+
"step": 310
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 2.4,
|
| 248 |
+
"grad_norm": 0.5245360732078552,
|
| 249 |
+
"learning_rate": 1.1002785515320335e-05,
|
| 250 |
+
"loss": 0.0192,
|
| 251 |
+
"step": 320
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 2.47,
|
| 255 |
+
"grad_norm": 0.0511808916926384,
|
| 256 |
+
"learning_rate": 9.610027855153205e-06,
|
| 257 |
+
"loss": 0.017,
|
| 258 |
+
"step": 330
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 2.55,
|
| 262 |
+
"grad_norm": 0.40286481380462646,
|
| 263 |
+
"learning_rate": 8.217270194986073e-06,
|
| 264 |
+
"loss": 0.0113,
|
| 265 |
+
"step": 340
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 2.62,
|
| 269 |
+
"grad_norm": 0.8864955306053162,
|
| 270 |
+
"learning_rate": 6.8245125348189415e-06,
|
| 271 |
+
"loss": 0.0124,
|
| 272 |
+
"step": 350
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 2.7,
|
| 276 |
+
"grad_norm": 0.10564003139734268,
|
| 277 |
+
"learning_rate": 5.43175487465181e-06,
|
| 278 |
+
"loss": 0.0091,
|
| 279 |
+
"step": 360
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 2.77,
|
| 283 |
+
"grad_norm": 0.37896963953971863,
|
| 284 |
+
"learning_rate": 4.03899721448468e-06,
|
| 285 |
+
"loss": 0.0136,
|
| 286 |
+
"step": 370
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 2.85,
|
| 290 |
+
"grad_norm": 0.09369711577892303,
|
| 291 |
+
"learning_rate": 2.6462395543175487e-06,
|
| 292 |
+
"loss": 0.0106,
|
| 293 |
+
"step": 380
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 2.92,
|
| 297 |
+
"grad_norm": 0.3972206711769104,
|
| 298 |
+
"learning_rate": 1.253481894150418e-06,
|
| 299 |
+
"loss": 0.0167,
|
| 300 |
+
"step": 390
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 2.99,
|
| 304 |
+
"eval_accuracy": 0.9957828149710068,
|
| 305 |
+
"eval_loss": 0.01684400625526905,
|
| 306 |
+
"eval_runtime": 8.7926,
|
| 307 |
+
"eval_samples_per_second": 215.75,
|
| 308 |
+
"eval_steps_per_second": 6.824,
|
| 309 |
+
"step": 399
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 2.99,
|
| 313 |
+
"step": 399,
|
| 314 |
+
"total_flos": 3.954296686846206e+18,
|
| 315 |
+
"train_loss": 0.08411522551362675,
|
| 316 |
+
"train_runtime": 524.0438,
|
| 317 |
+
"train_samples_per_second": 97.698,
|
| 318 |
+
"train_steps_per_second": 0.761
|
| 319 |
+
}
|
| 320 |
+
],
|
| 321 |
+
"logging_steps": 10,
|
| 322 |
+
"max_steps": 399,
|
| 323 |
+
"num_input_tokens_seen": 0,
|
| 324 |
+
"num_train_epochs": 3,
|
| 325 |
+
"save_steps": 500,
|
| 326 |
+
"total_flos": 3.954296686846206e+18,
|
| 327 |
+
"train_batch_size": 32,
|
| 328 |
+
"trial_name": null,
|
| 329 |
+
"trial_params": null
|
| 330 |
+
}
|