Training in progress, epoch 0
Browse files- all_results.json +15 -11
- eval_results.json +10 -6
- model.safetensors +1 -1
- train_results.json +6 -6
- trainer_state.json +225 -55
- training_args.bin +1 -1
all_results.json
CHANGED
|
@@ -1,13 +1,17 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch": 4.
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"
|
| 5 |
-
"
|
| 6 |
-
"
|
| 7 |
-
"
|
| 8 |
-
"
|
| 9 |
-
"
|
| 10 |
-
"
|
| 11 |
-
"
|
| 12 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 4.95,
|
| 3 |
+
"eval_accuracy": 0.4166666666666667,
|
| 4 |
+
"eval_auc": 0.4313214285714286,
|
| 5 |
+
"eval_f1": 0.5882352941176471,
|
| 6 |
+
"eval_loss": 0.7166089415550232,
|
| 7 |
+
"eval_precision": 0.4166666666666667,
|
| 8 |
+
"eval_recall": 1.0,
|
| 9 |
+
"eval_runtime": 4.6416,
|
| 10 |
+
"eval_samples_per_second": 51.707,
|
| 11 |
+
"eval_steps_per_second": 6.463,
|
| 12 |
+
"total_flos": 3.4409368031831654e+17,
|
| 13 |
+
"train_loss": 0.6955731582641601,
|
| 14 |
+
"train_runtime": 190.8065,
|
| 15 |
+
"train_samples_per_second": 23.217,
|
| 16 |
+
"train_steps_per_second": 1.441
|
| 17 |
}
|
eval_results.json
CHANGED
|
@@ -1,8 +1,12 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch": 4.
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"
|
| 5 |
-
"
|
| 6 |
-
"
|
| 7 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 4.95,
|
| 3 |
+
"eval_accuracy": 0.4166666666666667,
|
| 4 |
+
"eval_auc": 0.4313214285714286,
|
| 5 |
+
"eval_f1": 0.5882352941176471,
|
| 6 |
+
"eval_loss": 0.7166089415550232,
|
| 7 |
+
"eval_precision": 0.4166666666666667,
|
| 8 |
+
"eval_recall": 1.0,
|
| 9 |
+
"eval_runtime": 4.6416,
|
| 10 |
+
"eval_samples_per_second": 51.707,
|
| 11 |
+
"eval_steps_per_second": 6.463
|
| 12 |
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 347498816
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:098d6205574a0bc5566e768b737a8414d1a9c400da70c067cb116757f918ae24
|
| 3 |
size 347498816
|
train_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch": 4.
|
| 3 |
-
"total_flos":
|
| 4 |
-
"train_loss": 0.
|
| 5 |
-
"train_runtime":
|
| 6 |
-
"train_samples_per_second":
|
| 7 |
-
"train_steps_per_second":
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 4.95,
|
| 3 |
+
"total_flos": 3.4409368031831654e+17,
|
| 4 |
+
"train_loss": 0.6955731582641601,
|
| 5 |
+
"train_runtime": 190.8065,
|
| 6 |
+
"train_samples_per_second": 23.217,
|
| 7 |
+
"train_steps_per_second": 1.441
|
| 8 |
}
|
trainer_state.json
CHANGED
|
@@ -1,87 +1,257 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
-
"best_model_checkpoint": "swin-finetuned-food101\\checkpoint-
|
| 4 |
-
"epoch": 4.
|
| 5 |
"eval_steps": 500,
|
| 6 |
-
"global_step":
|
| 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.
|
| 13 |
-
"
|
| 14 |
-
"
|
| 15 |
-
"
|
| 16 |
-
|
| 17 |
-
|
| 18 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 19 |
},
|
| 20 |
{
|
| 21 |
"epoch": 2.0,
|
| 22 |
-
"eval_accuracy": 0.
|
| 23 |
-
"
|
| 24 |
-
"
|
| 25 |
-
"
|
| 26 |
-
"
|
| 27 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
| 28 |
},
|
| 29 |
{
|
| 30 |
-
"epoch": 2.
|
| 31 |
-
"learning_rate": 0.
|
| 32 |
-
"loss": 0.
|
| 33 |
-
"step":
|
| 34 |
},
|
| 35 |
{
|
| 36 |
-
"epoch": 2.
|
| 37 |
-
"
|
| 38 |
-
"
|
| 39 |
-
"
|
| 40 |
-
|
| 41 |
-
|
| 42 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 43 |
},
|
| 44 |
{
|
| 45 |
"epoch": 4.0,
|
| 46 |
-
"eval_accuracy": 0.
|
| 47 |
-
"
|
| 48 |
-
"
|
| 49 |
-
"
|
| 50 |
-
"
|
| 51 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
| 52 |
},
|
| 53 |
{
|
| 54 |
-
"epoch": 4.
|
| 55 |
-
"learning_rate": 0.
|
| 56 |
-
"loss": 0.
|
| 57 |
-
"step":
|
| 58 |
},
|
| 59 |
{
|
| 60 |
-
"epoch": 4.
|
| 61 |
-
"
|
| 62 |
-
"
|
| 63 |
-
"
|
| 64 |
-
|
| 65 |
-
|
| 66 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 67 |
},
|
| 68 |
{
|
| 69 |
-
"epoch": 4.
|
| 70 |
-
"step":
|
| 71 |
-
"total_flos":
|
| 72 |
-
"train_loss": 0.
|
| 73 |
-
"train_runtime":
|
| 74 |
-
"train_samples_per_second":
|
| 75 |
-
"train_steps_per_second":
|
| 76 |
}
|
| 77 |
],
|
| 78 |
"logging_steps": 10,
|
| 79 |
-
"max_steps":
|
| 80 |
"num_input_tokens_seen": 0,
|
| 81 |
"num_train_epochs": 5,
|
| 82 |
"save_steps": 500,
|
| 83 |
-
"total_flos":
|
| 84 |
-
"train_batch_size":
|
| 85 |
"trial_name": null,
|
| 86 |
"trial_params": null
|
| 87 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.5189873417721519,
|
| 3 |
+
"best_model_checkpoint": "swin-finetuned-food101\\checkpoint-111",
|
| 4 |
+
"epoch": 4.954954954954955,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 275,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
+
"epoch": 0.18,
|
| 13 |
+
"learning_rate": 0.0005882352941176471,
|
| 14 |
+
"loss": 0.6928,
|
| 15 |
+
"step": 10
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.36,
|
| 19 |
+
"learning_rate": 0.0009883720930232557,
|
| 20 |
+
"loss": 0.7119,
|
| 21 |
+
"step": 20
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.54,
|
| 25 |
+
"learning_rate": 0.0009496124031007753,
|
| 26 |
+
"loss": 0.701,
|
| 27 |
+
"step": 30
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.72,
|
| 31 |
+
"learning_rate": 0.0009108527131782945,
|
| 32 |
+
"loss": 0.6967,
|
| 33 |
+
"step": 40
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.9,
|
| 37 |
+
"learning_rate": 0.0008720930232558139,
|
| 38 |
+
"loss": 0.7016,
|
| 39 |
+
"step": 50
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.99,
|
| 43 |
+
"eval_accuracy": 0.4810126582278481,
|
| 44 |
+
"eval_auc": 0.47442875481386393,
|
| 45 |
+
"eval_f1": 0.0,
|
| 46 |
+
"eval_loss": 0.7054013609886169,
|
| 47 |
+
"eval_precision": 0.0,
|
| 48 |
+
"eval_recall": 0.0,
|
| 49 |
+
"eval_runtime": 7.2267,
|
| 50 |
+
"eval_samples_per_second": 54.658,
|
| 51 |
+
"eval_steps_per_second": 6.919,
|
| 52 |
+
"step": 55
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 1.08,
|
| 56 |
+
"learning_rate": 0.0008333333333333334,
|
| 57 |
+
"loss": 0.7091,
|
| 58 |
+
"step": 60
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 1.26,
|
| 62 |
+
"learning_rate": 0.0007945736434108527,
|
| 63 |
+
"loss": 0.6942,
|
| 64 |
+
"step": 70
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 1.44,
|
| 68 |
+
"learning_rate": 0.0007558139534883722,
|
| 69 |
+
"loss": 0.703,
|
| 70 |
+
"step": 80
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"epoch": 1.62,
|
| 74 |
+
"learning_rate": 0.0007170542635658915,
|
| 75 |
+
"loss": 0.6974,
|
| 76 |
+
"step": 90
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 1.8,
|
| 80 |
+
"learning_rate": 0.0006782945736434108,
|
| 81 |
+
"loss": 0.6947,
|
| 82 |
+
"step": 100
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 1.98,
|
| 86 |
+
"learning_rate": 0.0006395348837209303,
|
| 87 |
+
"loss": 0.6894,
|
| 88 |
+
"step": 110
|
| 89 |
},
|
| 90 |
{
|
| 91 |
"epoch": 2.0,
|
| 92 |
+
"eval_accuracy": 0.5189873417721519,
|
| 93 |
+
"eval_auc": 0.4473812580231065,
|
| 94 |
+
"eval_f1": 0.6833333333333332,
|
| 95 |
+
"eval_loss": 0.6947762370109558,
|
| 96 |
+
"eval_precision": 0.5189873417721519,
|
| 97 |
+
"eval_recall": 1.0,
|
| 98 |
+
"eval_runtime": 6.9385,
|
| 99 |
+
"eval_samples_per_second": 56.928,
|
| 100 |
+
"eval_steps_per_second": 7.206,
|
| 101 |
+
"step": 111
|
| 102 |
},
|
| 103 |
{
|
| 104 |
+
"epoch": 2.16,
|
| 105 |
+
"learning_rate": 0.0006007751937984496,
|
| 106 |
+
"loss": 0.6918,
|
| 107 |
+
"step": 120
|
| 108 |
},
|
| 109 |
{
|
| 110 |
+
"epoch": 2.34,
|
| 111 |
+
"learning_rate": 0.000562015503875969,
|
| 112 |
+
"loss": 0.6962,
|
| 113 |
+
"step": 130
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 2.52,
|
| 117 |
+
"learning_rate": 0.0005232558139534884,
|
| 118 |
+
"loss": 0.6935,
|
| 119 |
+
"step": 140
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 2.7,
|
| 123 |
+
"learning_rate": 0.00048449612403100775,
|
| 124 |
+
"loss": 0.6913,
|
| 125 |
+
"step": 150
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 2.88,
|
| 129 |
+
"learning_rate": 0.00044573643410852714,
|
| 130 |
+
"loss": 0.6905,
|
| 131 |
+
"step": 160
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 2.99,
|
| 135 |
+
"eval_accuracy": 0.5189873417721519,
|
| 136 |
+
"eval_auc": 0.6049550706033376,
|
| 137 |
+
"eval_f1": 0.6833333333333332,
|
| 138 |
+
"eval_loss": 0.6924389600753784,
|
| 139 |
+
"eval_precision": 0.5189873417721519,
|
| 140 |
+
"eval_recall": 1.0,
|
| 141 |
+
"eval_runtime": 6.8681,
|
| 142 |
+
"eval_samples_per_second": 57.512,
|
| 143 |
+
"eval_steps_per_second": 7.28,
|
| 144 |
+
"step": 166
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 3.06,
|
| 148 |
+
"learning_rate": 0.00040697674418604653,
|
| 149 |
+
"loss": 0.6962,
|
| 150 |
+
"step": 170
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 3.24,
|
| 154 |
+
"learning_rate": 0.00036821705426356586,
|
| 155 |
+
"loss": 0.695,
|
| 156 |
+
"step": 180
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 3.42,
|
| 160 |
+
"learning_rate": 0.00032945736434108526,
|
| 161 |
+
"loss": 0.693,
|
| 162 |
+
"step": 190
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 3.6,
|
| 166 |
+
"learning_rate": 0.00029069767441860465,
|
| 167 |
+
"loss": 0.6939,
|
| 168 |
+
"step": 200
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 3.78,
|
| 172 |
+
"learning_rate": 0.00025193798449612404,
|
| 173 |
+
"loss": 0.6882,
|
| 174 |
+
"step": 210
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 3.96,
|
| 178 |
+
"learning_rate": 0.0002131782945736434,
|
| 179 |
+
"loss": 0.6956,
|
| 180 |
+
"step": 220
|
| 181 |
},
|
| 182 |
{
|
| 183 |
"epoch": 4.0,
|
| 184 |
+
"eval_accuracy": 0.5189873417721519,
|
| 185 |
+
"eval_auc": 0.38290115532734276,
|
| 186 |
+
"eval_f1": 0.6833333333333332,
|
| 187 |
+
"eval_loss": 0.6925024390220642,
|
| 188 |
+
"eval_precision": 0.5189873417721519,
|
| 189 |
+
"eval_recall": 1.0,
|
| 190 |
+
"eval_runtime": 6.9643,
|
| 191 |
+
"eval_samples_per_second": 56.718,
|
| 192 |
+
"eval_steps_per_second": 7.179,
|
| 193 |
+
"step": 222
|
| 194 |
},
|
| 195 |
{
|
| 196 |
+
"epoch": 4.14,
|
| 197 |
+
"learning_rate": 0.0001744186046511628,
|
| 198 |
+
"loss": 0.6877,
|
| 199 |
+
"step": 230
|
| 200 |
},
|
| 201 |
{
|
| 202 |
+
"epoch": 4.32,
|
| 203 |
+
"learning_rate": 0.00013565891472868216,
|
| 204 |
+
"loss": 0.6963,
|
| 205 |
+
"step": 240
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 4.5,
|
| 209 |
+
"learning_rate": 9.689922480620156e-05,
|
| 210 |
+
"loss": 0.6979,
|
| 211 |
+
"step": 250
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 4.68,
|
| 215 |
+
"learning_rate": 5.8139534883720933e-05,
|
| 216 |
+
"loss": 0.6926,
|
| 217 |
+
"step": 260
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 4.86,
|
| 221 |
+
"learning_rate": 1.937984496124031e-05,
|
| 222 |
+
"loss": 0.6909,
|
| 223 |
+
"step": 270
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 4.95,
|
| 227 |
+
"eval_accuracy": 0.5189873417721519,
|
| 228 |
+
"eval_auc": 0.3773170731707318,
|
| 229 |
+
"eval_f1": 0.6833333333333332,
|
| 230 |
+
"eval_loss": 0.6924667954444885,
|
| 231 |
+
"eval_precision": 0.5189873417721519,
|
| 232 |
+
"eval_recall": 1.0,
|
| 233 |
+
"eval_runtime": 6.8651,
|
| 234 |
+
"eval_samples_per_second": 57.537,
|
| 235 |
+
"eval_steps_per_second": 7.283,
|
| 236 |
+
"step": 275
|
| 237 |
},
|
| 238 |
{
|
| 239 |
+
"epoch": 4.95,
|
| 240 |
+
"step": 275,
|
| 241 |
+
"total_flos": 3.4409368031831654e+17,
|
| 242 |
+
"train_loss": 0.6955731582641601,
|
| 243 |
+
"train_runtime": 190.8065,
|
| 244 |
+
"train_samples_per_second": 23.217,
|
| 245 |
+
"train_steps_per_second": 1.441
|
| 246 |
}
|
| 247 |
],
|
| 248 |
"logging_steps": 10,
|
| 249 |
+
"max_steps": 275,
|
| 250 |
"num_input_tokens_seen": 0,
|
| 251 |
"num_train_epochs": 5,
|
| 252 |
"save_steps": 500,
|
| 253 |
+
"total_flos": 3.4409368031831654e+17,
|
| 254 |
+
"train_batch_size": 8,
|
| 255 |
"trial_name": null,
|
| 256 |
"trial_params": null
|
| 257 |
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4728
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:276be73dfb225923e866d3e4cffd53ad7519404788c78c1a640e4f289028e777
|
| 3 |
size 4728
|