Commit
•
2ef3cb0
1
Parent(s):
eb19609
Training in progress, epoch 1
Browse files- all_results.json +8 -0
- pytorch_model.bin +1 -1
- train_results.json +8 -0
- trainer_state.json +244 -0
- training_args.bin +1 -1
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 15.0,
|
| 3 |
+
"total_flos": 1.16237984421888e+18,
|
| 4 |
+
"train_loss": 0.3610760450363159,
|
| 5 |
+
"train_runtime": 974.8105,
|
| 6 |
+
"train_samples_per_second": 15.388,
|
| 7 |
+
"train_steps_per_second": 0.062
|
| 8 |
+
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 343268717
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8365bd765d10703caedf7d6902cd1b017ac2ee0d2bcc45a6fbc3946358e0035d
|
| 3 |
size 343268717
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 15.0,
|
| 3 |
+
"total_flos": 1.16237984421888e+18,
|
| 4 |
+
"train_loss": 0.3610760450363159,
|
| 5 |
+
"train_runtime": 974.8105,
|
| 6 |
+
"train_samples_per_second": 15.388,
|
| 7 |
+
"train_steps_per_second": 0.062
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,244 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.9083333333333333,
|
| 3 |
+
"best_model_checkpoint": "vit-base-patch16-224/checkpoint-40",
|
| 4 |
+
"epoch": 15.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 60,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 1.0,
|
| 13 |
+
"eval_accuracy": 0.8666666666666667,
|
| 14 |
+
"eval_f1_score": 0.8224224224224224,
|
| 15 |
+
"eval_loss": 0.5036832094192505,
|
| 16 |
+
"eval_precision": 0.8150354609929079,
|
| 17 |
+
"eval_recall": 0.8666666666666667,
|
| 18 |
+
"eval_runtime": 4.0852,
|
| 19 |
+
"eval_samples_per_second": 58.748,
|
| 20 |
+
"eval_steps_per_second": 0.979,
|
| 21 |
+
"step": 4
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 2.0,
|
| 25 |
+
"eval_accuracy": 0.8708333333333333,
|
| 26 |
+
"eval_f1_score": 0.8107089829250185,
|
| 27 |
+
"eval_loss": 0.35003846883773804,
|
| 28 |
+
"eval_precision": 0.7583506944444445,
|
| 29 |
+
"eval_recall": 0.8708333333333333,
|
| 30 |
+
"eval_runtime": 4.1025,
|
| 31 |
+
"eval_samples_per_second": 58.501,
|
| 32 |
+
"eval_steps_per_second": 0.975,
|
| 33 |
+
"step": 8
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 3.0,
|
| 37 |
+
"eval_accuracy": 0.8708333333333333,
|
| 38 |
+
"eval_f1_score": 0.8107089829250185,
|
| 39 |
+
"eval_loss": 0.3154493272304535,
|
| 40 |
+
"eval_precision": 0.7583506944444445,
|
| 41 |
+
"eval_recall": 0.8708333333333333,
|
| 42 |
+
"eval_runtime": 3.9805,
|
| 43 |
+
"eval_samples_per_second": 60.295,
|
| 44 |
+
"eval_steps_per_second": 1.005,
|
| 45 |
+
"step": 12
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 3.75,
|
| 49 |
+
"learning_rate": 4.166666666666667e-05,
|
| 50 |
+
"loss": 0.5284,
|
| 51 |
+
"step": 15
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 4.0,
|
| 55 |
+
"eval_accuracy": 0.8833333333333333,
|
| 56 |
+
"eval_f1_score": 0.849658648884655,
|
| 57 |
+
"eval_loss": 0.2973836362361908,
|
| 58 |
+
"eval_precision": 0.8659207030451664,
|
| 59 |
+
"eval_recall": 0.8833333333333333,
|
| 60 |
+
"eval_runtime": 3.9445,
|
| 61 |
+
"eval_samples_per_second": 60.844,
|
| 62 |
+
"eval_steps_per_second": 1.014,
|
| 63 |
+
"step": 16
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 5.0,
|
| 67 |
+
"eval_accuracy": 0.8875,
|
| 68 |
+
"eval_f1_score": 0.8768099547511312,
|
| 69 |
+
"eval_loss": 0.2953941226005554,
|
| 70 |
+
"eval_precision": 0.873125,
|
| 71 |
+
"eval_recall": 0.8875,
|
| 72 |
+
"eval_runtime": 4.0614,
|
| 73 |
+
"eval_samples_per_second": 59.092,
|
| 74 |
+
"eval_steps_per_second": 0.985,
|
| 75 |
+
"step": 20
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 6.0,
|
| 79 |
+
"eval_accuracy": 0.8958333333333334,
|
| 80 |
+
"eval_f1_score": 0.8716479619238106,
|
| 81 |
+
"eval_loss": 0.2720634639263153,
|
| 82 |
+
"eval_precision": 0.8870833333333333,
|
| 83 |
+
"eval_recall": 0.8958333333333334,
|
| 84 |
+
"eval_runtime": 4.0196,
|
| 85 |
+
"eval_samples_per_second": 59.708,
|
| 86 |
+
"eval_steps_per_second": 0.995,
|
| 87 |
+
"step": 24
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 7.0,
|
| 91 |
+
"eval_accuracy": 0.8875,
|
| 92 |
+
"eval_f1_score": 0.852667622475749,
|
| 93 |
+
"eval_loss": 0.26786690950393677,
|
| 94 |
+
"eval_precision": 0.881712962962963,
|
| 95 |
+
"eval_recall": 0.8875,
|
| 96 |
+
"eval_runtime": 4.2691,
|
| 97 |
+
"eval_samples_per_second": 56.218,
|
| 98 |
+
"eval_steps_per_second": 0.937,
|
| 99 |
+
"step": 28
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 7.5,
|
| 103 |
+
"learning_rate": 2.777777777777778e-05,
|
| 104 |
+
"loss": 0.3362,
|
| 105 |
+
"step": 30
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 8.0,
|
| 109 |
+
"eval_accuracy": 0.8875,
|
| 110 |
+
"eval_f1_score": 0.852667622475749,
|
| 111 |
+
"eval_loss": 0.26340213418006897,
|
| 112 |
+
"eval_precision": 0.881712962962963,
|
| 113 |
+
"eval_recall": 0.8875,
|
| 114 |
+
"eval_runtime": 4.2103,
|
| 115 |
+
"eval_samples_per_second": 57.002,
|
| 116 |
+
"eval_steps_per_second": 0.95,
|
| 117 |
+
"step": 32
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 9.0,
|
| 121 |
+
"eval_accuracy": 0.9041666666666667,
|
| 122 |
+
"eval_f1_score": 0.8879374201787995,
|
| 123 |
+
"eval_loss": 0.25068628787994385,
|
| 124 |
+
"eval_precision": 0.8952565318162663,
|
| 125 |
+
"eval_recall": 0.9041666666666667,
|
| 126 |
+
"eval_runtime": 3.9517,
|
| 127 |
+
"eval_samples_per_second": 60.733,
|
| 128 |
+
"eval_steps_per_second": 1.012,
|
| 129 |
+
"step": 36
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 10.0,
|
| 133 |
+
"eval_accuracy": 0.9083333333333333,
|
| 134 |
+
"eval_f1_score": 0.8940810124891471,
|
| 135 |
+
"eval_loss": 0.24386708438396454,
|
| 136 |
+
"eval_precision": 0.9006296296296298,
|
| 137 |
+
"eval_recall": 0.9083333333333333,
|
| 138 |
+
"eval_runtime": 3.9449,
|
| 139 |
+
"eval_samples_per_second": 60.839,
|
| 140 |
+
"eval_steps_per_second": 1.014,
|
| 141 |
+
"step": 40
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 11.0,
|
| 145 |
+
"eval_accuracy": 0.8916666666666667,
|
| 146 |
+
"eval_f1_score": 0.8884444626028217,
|
| 147 |
+
"eval_loss": 0.25889885425567627,
|
| 148 |
+
"eval_precision": 0.8860502521300643,
|
| 149 |
+
"eval_recall": 0.8916666666666667,
|
| 150 |
+
"eval_runtime": 4.1005,
|
| 151 |
+
"eval_samples_per_second": 58.529,
|
| 152 |
+
"eval_steps_per_second": 0.975,
|
| 153 |
+
"step": 44
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 11.25,
|
| 157 |
+
"learning_rate": 1.388888888888889e-05,
|
| 158 |
+
"loss": 0.3017,
|
| 159 |
+
"step": 45
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 12.0,
|
| 163 |
+
"eval_accuracy": 0.9083333333333333,
|
| 164 |
+
"eval_f1_score": 0.9024039297513475,
|
| 165 |
+
"eval_loss": 0.24283821880817413,
|
| 166 |
+
"eval_precision": 0.9004925532625392,
|
| 167 |
+
"eval_recall": 0.9083333333333333,
|
| 168 |
+
"eval_runtime": 4.2192,
|
| 169 |
+
"eval_samples_per_second": 56.883,
|
| 170 |
+
"eval_steps_per_second": 0.948,
|
| 171 |
+
"step": 48
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 13.0,
|
| 175 |
+
"eval_accuracy": 0.9,
|
| 176 |
+
"eval_f1_score": 0.8970256577872201,
|
| 177 |
+
"eval_loss": 0.2543129324913025,
|
| 178 |
+
"eval_precision": 0.894922622152669,
|
| 179 |
+
"eval_recall": 0.9,
|
| 180 |
+
"eval_runtime": 4.181,
|
| 181 |
+
"eval_samples_per_second": 57.402,
|
| 182 |
+
"eval_steps_per_second": 0.957,
|
| 183 |
+
"step": 52
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 14.0,
|
| 187 |
+
"eval_accuracy": 0.8958333333333334,
|
| 188 |
+
"eval_f1_score": 0.8951038120948916,
|
| 189 |
+
"eval_loss": 0.2651337683200836,
|
| 190 |
+
"eval_precision": 0.8944246031746032,
|
| 191 |
+
"eval_recall": 0.8958333333333334,
|
| 192 |
+
"eval_runtime": 3.9408,
|
| 193 |
+
"eval_samples_per_second": 60.902,
|
| 194 |
+
"eval_steps_per_second": 1.015,
|
| 195 |
+
"step": 56
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 15.0,
|
| 199 |
+
"learning_rate": 0.0,
|
| 200 |
+
"loss": 0.278,
|
| 201 |
+
"step": 60
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 15.0,
|
| 205 |
+
"eval_accuracy": 0.8958333333333334,
|
| 206 |
+
"eval_f1_score": 0.8951038120948916,
|
| 207 |
+
"eval_loss": 0.2636790871620178,
|
| 208 |
+
"eval_precision": 0.8944246031746032,
|
| 209 |
+
"eval_recall": 0.8958333333333334,
|
| 210 |
+
"eval_runtime": 4.1679,
|
| 211 |
+
"eval_samples_per_second": 57.584,
|
| 212 |
+
"eval_steps_per_second": 0.96,
|
| 213 |
+
"step": 60
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 15.0,
|
| 217 |
+
"step": 60,
|
| 218 |
+
"total_flos": 1.16237984421888e+18,
|
| 219 |
+
"train_loss": 0.3610760450363159,
|
| 220 |
+
"train_runtime": 974.8105,
|
| 221 |
+
"train_samples_per_second": 15.388,
|
| 222 |
+
"train_steps_per_second": 0.062
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 15.0,
|
| 226 |
+
"eval_accuracy": 0.9033333333333333,
|
| 227 |
+
"eval_f1_score": 0.888913443830571,
|
| 228 |
+
"eval_loss": 0.24460919201374054,
|
| 229 |
+
"eval_precision": 0.892075919335706,
|
| 230 |
+
"eval_recall": 0.9033333333333333,
|
| 231 |
+
"eval_runtime": 4.8461,
|
| 232 |
+
"eval_samples_per_second": 61.906,
|
| 233 |
+
"eval_steps_per_second": 1.032,
|
| 234 |
+
"step": 60
|
| 235 |
+
}
|
| 236 |
+
],
|
| 237 |
+
"logging_steps": 15,
|
| 238 |
+
"max_steps": 60,
|
| 239 |
+
"num_train_epochs": 15,
|
| 240 |
+
"save_steps": 500,
|
| 241 |
+
"total_flos": 1.16237984421888e+18,
|
| 242 |
+
"trial_name": null,
|
| 243 |
+
"trial_params": null
|
| 244 |
+
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4027
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7e3f28fa49c01ce58eb2cbd98f07b83111f96e4736164481dabe0c27dccfd18c
|
| 3 |
size 4027
|