Training in progress, epoch 0
Browse files- all_results.json +7 -0
- pytorch_model.bin +1 -1
- train_results.json +7 -0
- trainer_state.json +250 -0
- training_args.bin +1 -1
all_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.99,
|
| 3 |
+
"train_loss": 0.9869003245780418,
|
| 4 |
+
"train_runtime": 506.9873,
|
| 5 |
+
"train_samples_per_second": 21.107,
|
| 6 |
+
"train_steps_per_second": 0.657
|
| 7 |
+
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 94383181
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8f4fc548c3b4c71a79913df3579d859b1b8e89a651aabcde74fdfd5898a3aacd
|
| 3 |
size 94383181
|
train_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.99,
|
| 3 |
+
"train_loss": 0.9869003245780418,
|
| 4 |
+
"train_runtime": 506.9873,
|
| 5 |
+
"train_samples_per_second": 21.107,
|
| 6 |
+
"train_steps_per_second": 0.657
|
| 7 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,250 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.5768261964735516,
|
| 3 |
+
"best_model_checkpoint": "resnet-50-finetuned-omar/checkpoint-333",
|
| 4 |
+
"epoch": 2.986547085201794,
|
| 5 |
+
"global_step": 333,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.09,
|
| 12 |
+
"learning_rate": 1.4705882352941177e-05,
|
| 13 |
+
"loss": 1.0992,
|
| 14 |
+
"step": 10
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.18,
|
| 18 |
+
"learning_rate": 2.9411764705882354e-05,
|
| 19 |
+
"loss": 1.0937,
|
| 20 |
+
"step": 20
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.27,
|
| 24 |
+
"learning_rate": 4.411764705882353e-05,
|
| 25 |
+
"loss": 1.089,
|
| 26 |
+
"step": 30
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.36,
|
| 30 |
+
"learning_rate": 4.8996655518394655e-05,
|
| 31 |
+
"loss": 1.0776,
|
| 32 |
+
"step": 40
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.45,
|
| 36 |
+
"learning_rate": 4.7324414715719065e-05,
|
| 37 |
+
"loss": 1.0506,
|
| 38 |
+
"step": 50
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.54,
|
| 42 |
+
"learning_rate": 4.565217391304348e-05,
|
| 43 |
+
"loss": 1.0407,
|
| 44 |
+
"step": 60
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.63,
|
| 48 |
+
"learning_rate": 4.397993311036789e-05,
|
| 49 |
+
"loss": 1.0425,
|
| 50 |
+
"step": 70
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.72,
|
| 54 |
+
"learning_rate": 4.230769230769231e-05,
|
| 55 |
+
"loss": 1.0591,
|
| 56 |
+
"step": 80
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.81,
|
| 60 |
+
"learning_rate": 4.0635451505016724e-05,
|
| 61 |
+
"loss": 1.0361,
|
| 62 |
+
"step": 90
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.9,
|
| 66 |
+
"learning_rate": 3.896321070234114e-05,
|
| 67 |
+
"loss": 1.0337,
|
| 68 |
+
"step": 100
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.99,
|
| 72 |
+
"learning_rate": 3.729096989966555e-05,
|
| 73 |
+
"loss": 0.9977,
|
| 74 |
+
"step": 110
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 1.0,
|
| 78 |
+
"eval_accuracy": 0.5214105793450882,
|
| 79 |
+
"eval_loss": 0.993331253528595,
|
| 80 |
+
"eval_runtime": 9.0682,
|
| 81 |
+
"eval_samples_per_second": 43.779,
|
| 82 |
+
"eval_steps_per_second": 5.514,
|
| 83 |
+
"step": 111
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 1.08,
|
| 87 |
+
"learning_rate": 3.5618729096989966e-05,
|
| 88 |
+
"loss": 1.0008,
|
| 89 |
+
"step": 120
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 1.17,
|
| 93 |
+
"learning_rate": 3.394648829431438e-05,
|
| 94 |
+
"loss": 0.9833,
|
| 95 |
+
"step": 130
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 1.26,
|
| 99 |
+
"learning_rate": 3.22742474916388e-05,
|
| 100 |
+
"loss": 0.9977,
|
| 101 |
+
"step": 140
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 1.35,
|
| 105 |
+
"learning_rate": 3.0602006688963215e-05,
|
| 106 |
+
"loss": 1.0122,
|
| 107 |
+
"step": 150
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 1.43,
|
| 111 |
+
"learning_rate": 2.8929765886287625e-05,
|
| 112 |
+
"loss": 0.9786,
|
| 113 |
+
"step": 160
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 1.52,
|
| 117 |
+
"learning_rate": 2.725752508361204e-05,
|
| 118 |
+
"loss": 0.9888,
|
| 119 |
+
"step": 170
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 1.61,
|
| 123 |
+
"learning_rate": 2.5585284280936454e-05,
|
| 124 |
+
"loss": 0.9688,
|
| 125 |
+
"step": 180
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 1.7,
|
| 129 |
+
"learning_rate": 2.391304347826087e-05,
|
| 130 |
+
"loss": 0.9591,
|
| 131 |
+
"step": 190
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 1.79,
|
| 135 |
+
"learning_rate": 2.2240802675585284e-05,
|
| 136 |
+
"loss": 0.9611,
|
| 137 |
+
"step": 200
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 1.88,
|
| 141 |
+
"learning_rate": 2.05685618729097e-05,
|
| 142 |
+
"loss": 0.9273,
|
| 143 |
+
"step": 210
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 1.97,
|
| 147 |
+
"learning_rate": 1.8896321070234117e-05,
|
| 148 |
+
"loss": 0.9814,
|
| 149 |
+
"step": 220
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 2.0,
|
| 153 |
+
"eval_accuracy": 0.5340050377833753,
|
| 154 |
+
"eval_loss": 0.9008849263191223,
|
| 155 |
+
"eval_runtime": 8.9706,
|
| 156 |
+
"eval_samples_per_second": 44.256,
|
| 157 |
+
"eval_steps_per_second": 5.574,
|
| 158 |
+
"step": 223
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 2.06,
|
| 162 |
+
"learning_rate": 1.722408026755853e-05,
|
| 163 |
+
"loss": 0.9379,
|
| 164 |
+
"step": 230
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 2.15,
|
| 168 |
+
"learning_rate": 1.5551839464882946e-05,
|
| 169 |
+
"loss": 0.9327,
|
| 170 |
+
"step": 240
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 2.24,
|
| 174 |
+
"learning_rate": 1.3879598662207358e-05,
|
| 175 |
+
"loss": 0.9464,
|
| 176 |
+
"step": 250
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 2.33,
|
| 180 |
+
"learning_rate": 1.2207357859531774e-05,
|
| 181 |
+
"loss": 0.8991,
|
| 182 |
+
"step": 260
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 2.42,
|
| 186 |
+
"learning_rate": 1.0535117056856187e-05,
|
| 187 |
+
"loss": 0.9211,
|
| 188 |
+
"step": 270
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 2.51,
|
| 192 |
+
"learning_rate": 8.862876254180602e-06,
|
| 193 |
+
"loss": 0.9617,
|
| 194 |
+
"step": 280
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 2.6,
|
| 198 |
+
"learning_rate": 7.1906354515050165e-06,
|
| 199 |
+
"loss": 0.9298,
|
| 200 |
+
"step": 290
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 2.69,
|
| 204 |
+
"learning_rate": 5.518394648829431e-06,
|
| 205 |
+
"loss": 0.9174,
|
| 206 |
+
"step": 300
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 2.78,
|
| 210 |
+
"learning_rate": 3.846153846153847e-06,
|
| 211 |
+
"loss": 0.9123,
|
| 212 |
+
"step": 310
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 2.87,
|
| 216 |
+
"learning_rate": 2.173913043478261e-06,
|
| 217 |
+
"loss": 0.9272,
|
| 218 |
+
"step": 320
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 2.96,
|
| 222 |
+
"learning_rate": 5.016722408026756e-07,
|
| 223 |
+
"loss": 0.9463,
|
| 224 |
+
"step": 330
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 2.99,
|
| 228 |
+
"eval_accuracy": 0.5768261964735516,
|
| 229 |
+
"eval_loss": 0.8737264275550842,
|
| 230 |
+
"eval_runtime": 8.7069,
|
| 231 |
+
"eval_samples_per_second": 45.596,
|
| 232 |
+
"eval_steps_per_second": 5.743,
|
| 233 |
+
"step": 333
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 2.99,
|
| 237 |
+
"step": 333,
|
| 238 |
+
"total_flos": 2.262617043191931e+17,
|
| 239 |
+
"train_loss": 0.9869003245780418,
|
| 240 |
+
"train_runtime": 506.9873,
|
| 241 |
+
"train_samples_per_second": 21.107,
|
| 242 |
+
"train_steps_per_second": 0.657
|
| 243 |
+
}
|
| 244 |
+
],
|
| 245 |
+
"max_steps": 333,
|
| 246 |
+
"num_train_epochs": 3,
|
| 247 |
+
"total_flos": 2.262617043191931e+17,
|
| 248 |
+
"trial_name": null,
|
| 249 |
+
"trial_params": null
|
| 250 |
+
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3963
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:587698c7370a3eb8049f2f714d3df709848aa23b9ff3f9bc2fde08cce9f1bb21
|
| 3 |
size 3963
|