Training in progress, epoch 1
Browse files- all_results.json +13 -0
- eval_results.json +8 -0
- model.safetensors +1 -1
- train_results.json +8 -0
- trainer_state.json +313 -0
all_results.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 30.0,
|
| 3 |
+
"eval_accuracy": 1.0,
|
| 4 |
+
"eval_loss": 0.0019323596497997642,
|
| 5 |
+
"eval_runtime": 0.4972,
|
| 6 |
+
"eval_samples_per_second": 20.114,
|
| 7 |
+
"eval_steps_per_second": 2.011,
|
| 8 |
+
"total_flos": 8918092191375360.0,
|
| 9 |
+
"train_loss": 0.0005863850936293602,
|
| 10 |
+
"train_runtime": 162.4577,
|
| 11 |
+
"train_samples_per_second": 2.585,
|
| 12 |
+
"train_steps_per_second": 0.185
|
| 13 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 30.0,
|
| 3 |
+
"eval_accuracy": 1.0,
|
| 4 |
+
"eval_loss": 0.0019323596497997642,
|
| 5 |
+
"eval_runtime": 0.4972,
|
| 6 |
+
"eval_samples_per_second": 20.114,
|
| 7 |
+
"eval_steps_per_second": 2.011
|
| 8 |
+
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 94294756
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e528fb14c305af83f68c4c19e3bf6e8d5b953440e2e4db2dffeec7a1fc6ec362
|
| 3 |
size 94294756
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 30.0,
|
| 3 |
+
"total_flos": 8918092191375360.0,
|
| 4 |
+
"train_loss": 0.0005863850936293602,
|
| 5 |
+
"train_runtime": 162.4577,
|
| 6 |
+
"train_samples_per_second": 2.585,
|
| 7 |
+
"train_steps_per_second": 0.185
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,313 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 1,
|
| 3 |
+
"best_metric": 1.0,
|
| 4 |
+
"best_model_checkpoint": "./resnet50-finetuned-coco/checkpoint-1",
|
| 5 |
+
"epoch": 30.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 30,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 1.0,
|
| 14 |
+
"eval_accuracy": 1.0,
|
| 15 |
+
"eval_loss": 0.0019323596497997642,
|
| 16 |
+
"eval_runtime": 4.4987,
|
| 17 |
+
"eval_samples_per_second": 2.223,
|
| 18 |
+
"eval_steps_per_second": 0.222,
|
| 19 |
+
"step": 1
|
| 20 |
+
},
|
| 21 |
+
{
|
| 22 |
+
"epoch": 2.0,
|
| 23 |
+
"eval_accuracy": 1.0,
|
| 24 |
+
"eval_loss": 0.0014340047491714358,
|
| 25 |
+
"eval_runtime": 0.5098,
|
| 26 |
+
"eval_samples_per_second": 19.614,
|
| 27 |
+
"eval_steps_per_second": 1.961,
|
| 28 |
+
"step": 2
|
| 29 |
+
},
|
| 30 |
+
{
|
| 31 |
+
"epoch": 3.0,
|
| 32 |
+
"eval_accuracy": 1.0,
|
| 33 |
+
"eval_loss": 0.0010718145640566945,
|
| 34 |
+
"eval_runtime": 0.5032,
|
| 35 |
+
"eval_samples_per_second": 19.874,
|
| 36 |
+
"eval_steps_per_second": 1.987,
|
| 37 |
+
"step": 3
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 4.0,
|
| 41 |
+
"eval_accuracy": 1.0,
|
| 42 |
+
"eval_loss": 0.0008249193197116256,
|
| 43 |
+
"eval_runtime": 0.6956,
|
| 44 |
+
"eval_samples_per_second": 14.377,
|
| 45 |
+
"eval_steps_per_second": 1.438,
|
| 46 |
+
"step": 4
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 5.0,
|
| 50 |
+
"eval_accuracy": 1.0,
|
| 51 |
+
"eval_loss": 0.0011749675031751394,
|
| 52 |
+
"eval_runtime": 0.7554,
|
| 53 |
+
"eval_samples_per_second": 13.237,
|
| 54 |
+
"eval_steps_per_second": 1.324,
|
| 55 |
+
"step": 5
|
| 56 |
+
},
|
| 57 |
+
{
|
| 58 |
+
"epoch": 6.0,
|
| 59 |
+
"eval_accuracy": 1.0,
|
| 60 |
+
"eval_loss": 0.0019186580320820212,
|
| 61 |
+
"eval_runtime": 0.4856,
|
| 62 |
+
"eval_samples_per_second": 20.595,
|
| 63 |
+
"eval_steps_per_second": 2.06,
|
| 64 |
+
"step": 6
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 7.0,
|
| 68 |
+
"eval_accuracy": 1.0,
|
| 69 |
+
"eval_loss": 0.002705862745642662,
|
| 70 |
+
"eval_runtime": 0.4973,
|
| 71 |
+
"eval_samples_per_second": 20.11,
|
| 72 |
+
"eval_steps_per_second": 2.011,
|
| 73 |
+
"step": 7
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 8.0,
|
| 77 |
+
"eval_accuracy": 1.0,
|
| 78 |
+
"eval_loss": 0.00382140651345253,
|
| 79 |
+
"eval_runtime": 0.802,
|
| 80 |
+
"eval_samples_per_second": 12.47,
|
| 81 |
+
"eval_steps_per_second": 1.247,
|
| 82 |
+
"step": 8
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 9.0,
|
| 86 |
+
"eval_accuracy": 1.0,
|
| 87 |
+
"eval_loss": 0.005335311871021986,
|
| 88 |
+
"eval_runtime": 0.502,
|
| 89 |
+
"eval_samples_per_second": 19.922,
|
| 90 |
+
"eval_steps_per_second": 1.992,
|
| 91 |
+
"step": 9
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 10.0,
|
| 95 |
+
"eval_accuracy": 1.0,
|
| 96 |
+
"eval_loss": 0.006471132393926382,
|
| 97 |
+
"eval_runtime": 0.4806,
|
| 98 |
+
"eval_samples_per_second": 20.808,
|
| 99 |
+
"eval_steps_per_second": 2.081,
|
| 100 |
+
"step": 10
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 11.0,
|
| 104 |
+
"eval_accuracy": 1.0,
|
| 105 |
+
"eval_loss": 0.007191370241343975,
|
| 106 |
+
"eval_runtime": 0.898,
|
| 107 |
+
"eval_samples_per_second": 11.135,
|
| 108 |
+
"eval_steps_per_second": 1.114,
|
| 109 |
+
"step": 11
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 12.0,
|
| 113 |
+
"eval_accuracy": 1.0,
|
| 114 |
+
"eval_loss": 0.007900777272880077,
|
| 115 |
+
"eval_runtime": 0.4922,
|
| 116 |
+
"eval_samples_per_second": 20.316,
|
| 117 |
+
"eval_steps_per_second": 2.032,
|
| 118 |
+
"step": 12
|
| 119 |
+
},
|
| 120 |
+
{
|
| 121 |
+
"epoch": 13.0,
|
| 122 |
+
"eval_accuracy": 1.0,
|
| 123 |
+
"eval_loss": 0.00863733608275652,
|
| 124 |
+
"eval_runtime": 0.4715,
|
| 125 |
+
"eval_samples_per_second": 21.209,
|
| 126 |
+
"eval_steps_per_second": 2.121,
|
| 127 |
+
"step": 13
|
| 128 |
+
},
|
| 129 |
+
{
|
| 130 |
+
"epoch": 14.0,
|
| 131 |
+
"eval_accuracy": 1.0,
|
| 132 |
+
"eval_loss": 0.010232715867459774,
|
| 133 |
+
"eval_runtime": 0.505,
|
| 134 |
+
"eval_samples_per_second": 19.802,
|
| 135 |
+
"eval_steps_per_second": 1.98,
|
| 136 |
+
"step": 14
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 15.0,
|
| 140 |
+
"eval_accuracy": 1.0,
|
| 141 |
+
"eval_loss": 0.011720546521246433,
|
| 142 |
+
"eval_runtime": 0.5554,
|
| 143 |
+
"eval_samples_per_second": 18.005,
|
| 144 |
+
"eval_steps_per_second": 1.801,
|
| 145 |
+
"step": 15
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 16.0,
|
| 149 |
+
"eval_accuracy": 1.0,
|
| 150 |
+
"eval_loss": 0.012477124109864235,
|
| 151 |
+
"eval_runtime": 0.5068,
|
| 152 |
+
"eval_samples_per_second": 19.732,
|
| 153 |
+
"eval_steps_per_second": 1.973,
|
| 154 |
+
"step": 16
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 17.0,
|
| 158 |
+
"eval_accuracy": 1.0,
|
| 159 |
+
"eval_loss": 0.01326531171798706,
|
| 160 |
+
"eval_runtime": 0.4999,
|
| 161 |
+
"eval_samples_per_second": 20.005,
|
| 162 |
+
"eval_steps_per_second": 2.001,
|
| 163 |
+
"step": 17
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 18.0,
|
| 167 |
+
"eval_accuracy": 1.0,
|
| 168 |
+
"eval_loss": 0.012465937063097954,
|
| 169 |
+
"eval_runtime": 0.4736,
|
| 170 |
+
"eval_samples_per_second": 21.114,
|
| 171 |
+
"eval_steps_per_second": 2.111,
|
| 172 |
+
"step": 18
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 19.0,
|
| 176 |
+
"eval_accuracy": 1.0,
|
| 177 |
+
"eval_loss": 0.011286773718893528,
|
| 178 |
+
"eval_runtime": 0.4807,
|
| 179 |
+
"eval_samples_per_second": 20.805,
|
| 180 |
+
"eval_steps_per_second": 2.08,
|
| 181 |
+
"step": 19
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 20.0,
|
| 185 |
+
"eval_accuracy": 1.0,
|
| 186 |
+
"eval_loss": 0.010712802410125732,
|
| 187 |
+
"eval_runtime": 0.4988,
|
| 188 |
+
"eval_samples_per_second": 20.049,
|
| 189 |
+
"eval_steps_per_second": 2.005,
|
| 190 |
+
"step": 20
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 21.0,
|
| 194 |
+
"eval_accuracy": 1.0,
|
| 195 |
+
"eval_loss": 0.00999603420495987,
|
| 196 |
+
"eval_runtime": 0.4827,
|
| 197 |
+
"eval_samples_per_second": 20.719,
|
| 198 |
+
"eval_steps_per_second": 2.072,
|
| 199 |
+
"step": 21
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 22.0,
|
| 203 |
+
"eval_accuracy": 1.0,
|
| 204 |
+
"eval_loss": 0.009599635377526283,
|
| 205 |
+
"eval_runtime": 0.7185,
|
| 206 |
+
"eval_samples_per_second": 13.918,
|
| 207 |
+
"eval_steps_per_second": 1.392,
|
| 208 |
+
"step": 22
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 23.0,
|
| 212 |
+
"eval_accuracy": 1.0,
|
| 213 |
+
"eval_loss": 0.009064934216439724,
|
| 214 |
+
"eval_runtime": 0.4758,
|
| 215 |
+
"eval_samples_per_second": 21.016,
|
| 216 |
+
"eval_steps_per_second": 2.102,
|
| 217 |
+
"step": 23
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 24.0,
|
| 221 |
+
"eval_accuracy": 1.0,
|
| 222 |
+
"eval_loss": 0.00888894684612751,
|
| 223 |
+
"eval_runtime": 0.5421,
|
| 224 |
+
"eval_samples_per_second": 18.446,
|
| 225 |
+
"eval_steps_per_second": 1.845,
|
| 226 |
+
"step": 24
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 25.0,
|
| 230 |
+
"eval_accuracy": 1.0,
|
| 231 |
+
"eval_loss": 0.008358614519238472,
|
| 232 |
+
"eval_runtime": 0.4808,
|
| 233 |
+
"eval_samples_per_second": 20.8,
|
| 234 |
+
"eval_steps_per_second": 2.08,
|
| 235 |
+
"step": 25
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"epoch": 26.0,
|
| 239 |
+
"eval_accuracy": 1.0,
|
| 240 |
+
"eval_loss": 0.007842540740966797,
|
| 241 |
+
"eval_runtime": 0.5519,
|
| 242 |
+
"eval_samples_per_second": 18.12,
|
| 243 |
+
"eval_steps_per_second": 1.812,
|
| 244 |
+
"step": 26
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 27.0,
|
| 248 |
+
"eval_accuracy": 1.0,
|
| 249 |
+
"eval_loss": 0.007688184734433889,
|
| 250 |
+
"eval_runtime": 0.4658,
|
| 251 |
+
"eval_samples_per_second": 21.469,
|
| 252 |
+
"eval_steps_per_second": 2.147,
|
| 253 |
+
"step": 27
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 28.0,
|
| 257 |
+
"eval_accuracy": 1.0,
|
| 258 |
+
"eval_loss": 0.007302085869014263,
|
| 259 |
+
"eval_runtime": 0.4838,
|
| 260 |
+
"eval_samples_per_second": 20.671,
|
| 261 |
+
"eval_steps_per_second": 2.067,
|
| 262 |
+
"step": 28
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 29.0,
|
| 266 |
+
"eval_accuracy": 1.0,
|
| 267 |
+
"eval_loss": 0.006760203279554844,
|
| 268 |
+
"eval_runtime": 0.4878,
|
| 269 |
+
"eval_samples_per_second": 20.498,
|
| 270 |
+
"eval_steps_per_second": 2.05,
|
| 271 |
+
"step": 29
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 30.0,
|
| 275 |
+
"eval_accuracy": 1.0,
|
| 276 |
+
"eval_loss": 0.005953826941549778,
|
| 277 |
+
"eval_runtime": 0.8908,
|
| 278 |
+
"eval_samples_per_second": 11.225,
|
| 279 |
+
"eval_steps_per_second": 1.123,
|
| 280 |
+
"step": 30
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 30.0,
|
| 284 |
+
"step": 30,
|
| 285 |
+
"total_flos": 8918092191375360.0,
|
| 286 |
+
"train_loss": 0.0005863850936293602,
|
| 287 |
+
"train_runtime": 162.4577,
|
| 288 |
+
"train_samples_per_second": 2.585,
|
| 289 |
+
"train_steps_per_second": 0.185
|
| 290 |
+
}
|
| 291 |
+
],
|
| 292 |
+
"logging_steps": 50,
|
| 293 |
+
"max_steps": 30,
|
| 294 |
+
"num_input_tokens_seen": 0,
|
| 295 |
+
"num_train_epochs": 30,
|
| 296 |
+
"save_steps": 500,
|
| 297 |
+
"stateful_callbacks": {
|
| 298 |
+
"TrainerControl": {
|
| 299 |
+
"args": {
|
| 300 |
+
"should_epoch_stop": false,
|
| 301 |
+
"should_evaluate": false,
|
| 302 |
+
"should_log": false,
|
| 303 |
+
"should_save": true,
|
| 304 |
+
"should_training_stop": true
|
| 305 |
+
},
|
| 306 |
+
"attributes": {}
|
| 307 |
+
}
|
| 308 |
+
},
|
| 309 |
+
"total_flos": 8918092191375360.0,
|
| 310 |
+
"train_batch_size": 32,
|
| 311 |
+
"trial_name": null,
|
| 312 |
+
"trial_params": null
|
| 313 |
+
}
|