End of training
Browse files- all_results.json +6 -0
- test_results.json +6 -0
- trainer_state.json +334 -0
all_results.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"accuracy": 0.971875,
|
| 3 |
+
"f1": 0.970599219660647,
|
| 4 |
+
"precision": 0.9766995157620159,
|
| 5 |
+
"recall": 0.971875
|
| 6 |
+
}
|
test_results.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"accuracy": 0.971875,
|
| 3 |
+
"f1": 0.970599219660647,
|
| 4 |
+
"precision": 0.9766995157620159,
|
| 5 |
+
"recall": 0.971875
|
| 6 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,334 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 1.0,
|
| 3 |
+
"best_model_checkpoint": "/media/cse/HDD/Shawon/shawon/MY DATA/ViViT_LSA64_SR_6/checkpoint-1152",
|
| 4 |
+
"epoch": 8.033333333333333,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 2592,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.011574074074074073,
|
| 13 |
+
"grad_norm": 44.73263931274414,
|
| 14 |
+
"learning_rate": 5.613425925925926e-06,
|
| 15 |
+
"loss": 17.0729,
|
| 16 |
+
"step": 100
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.023148148148148147,
|
| 20 |
+
"grad_norm": 47.833282470703125,
|
| 21 |
+
"learning_rate": 1.1400462962962963e-05,
|
| 22 |
+
"loss": 15.7817,
|
| 23 |
+
"step": 200
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.03333333333333333,
|
| 27 |
+
"eval_accuracy": 0.4609375,
|
| 28 |
+
"eval_f1": 0.43072370107622715,
|
| 29 |
+
"eval_loss": 2.8823623657226562,
|
| 30 |
+
"eval_precision": 0.5308730476699226,
|
| 31 |
+
"eval_recall": 0.4609375,
|
| 32 |
+
"eval_runtime": 294.5123,
|
| 33 |
+
"eval_samples_per_second": 0.869,
|
| 34 |
+
"eval_steps_per_second": 0.435,
|
| 35 |
+
"step": 288
|
| 36 |
+
},
|
| 37 |
+
{
|
| 38 |
+
"epoch": 1.0013888888888889,
|
| 39 |
+
"grad_norm": 49.69872283935547,
|
| 40 |
+
"learning_rate": 1.71875e-05,
|
| 41 |
+
"loss": 12.8142,
|
| 42 |
+
"step": 300
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 1.012962962962963,
|
| 46 |
+
"grad_norm": 53.043094635009766,
|
| 47 |
+
"learning_rate": 2.297453703703704e-05,
|
| 48 |
+
"loss": 8.4497,
|
| 49 |
+
"step": 400
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"epoch": 1.024537037037037,
|
| 53 |
+
"grad_norm": 30.541913986206055,
|
| 54 |
+
"learning_rate": 2.8761574074074076e-05,
|
| 55 |
+
"loss": 4.7558,
|
| 56 |
+
"step": 500
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 1.0333333333333334,
|
| 60 |
+
"eval_accuracy": 0.94921875,
|
| 61 |
+
"eval_f1": 0.9469866071428571,
|
| 62 |
+
"eval_loss": 0.5581986904144287,
|
| 63 |
+
"eval_precision": 0.9585937499999999,
|
| 64 |
+
"eval_recall": 0.94921875,
|
| 65 |
+
"eval_runtime": 294.5325,
|
| 66 |
+
"eval_samples_per_second": 0.869,
|
| 67 |
+
"eval_steps_per_second": 0.435,
|
| 68 |
+
"step": 576
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 2.0027777777777778,
|
| 72 |
+
"grad_norm": 16.023212432861328,
|
| 73 |
+
"learning_rate": 3.454861111111111e-05,
|
| 74 |
+
"loss": 2.1506,
|
| 75 |
+
"step": 600
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 2.0143518518518517,
|
| 79 |
+
"grad_norm": 9.642929077148438,
|
| 80 |
+
"learning_rate": 4.033564814814815e-05,
|
| 81 |
+
"loss": 0.968,
|
| 82 |
+
"step": 700
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 2.025925925925926,
|
| 86 |
+
"grad_norm": 2.5669755935668945,
|
| 87 |
+
"learning_rate": 4.612268518518519e-05,
|
| 88 |
+
"loss": 0.5173,
|
| 89 |
+
"step": 800
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 2.033333333333333,
|
| 93 |
+
"eval_accuracy": 0.98046875,
|
| 94 |
+
"eval_f1": 0.9797619047619047,
|
| 95 |
+
"eval_loss": 0.09987345337867737,
|
| 96 |
+
"eval_precision": 0.9854166666666667,
|
| 97 |
+
"eval_recall": 0.98046875,
|
| 98 |
+
"eval_runtime": 293.8692,
|
| 99 |
+
"eval_samples_per_second": 0.871,
|
| 100 |
+
"eval_steps_per_second": 0.436,
|
| 101 |
+
"step": 864
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 3.004166666666667,
|
| 105 |
+
"grad_norm": 49.025569915771484,
|
| 106 |
+
"learning_rate": 4.978780864197531e-05,
|
| 107 |
+
"loss": 0.2348,
|
| 108 |
+
"step": 900
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 3.015740740740741,
|
| 112 |
+
"grad_norm": 4.306143283843994,
|
| 113 |
+
"learning_rate": 4.9144804526748975e-05,
|
| 114 |
+
"loss": 0.0649,
|
| 115 |
+
"step": 1000
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 3.027314814814815,
|
| 119 |
+
"grad_norm": 52.926971435546875,
|
| 120 |
+
"learning_rate": 4.850180041152263e-05,
|
| 121 |
+
"loss": 0.1244,
|
| 122 |
+
"step": 1100
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 3.033333333333333,
|
| 126 |
+
"eval_accuracy": 1.0,
|
| 127 |
+
"eval_f1": 1.0,
|
| 128 |
+
"eval_loss": 0.010159317404031754,
|
| 129 |
+
"eval_precision": 1.0,
|
| 130 |
+
"eval_recall": 1.0,
|
| 131 |
+
"eval_runtime": 358.4985,
|
| 132 |
+
"eval_samples_per_second": 0.714,
|
| 133 |
+
"eval_steps_per_second": 0.357,
|
| 134 |
+
"step": 1152
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 4.0055555555555555,
|
| 138 |
+
"grad_norm": 0.2205909937620163,
|
| 139 |
+
"learning_rate": 4.78587962962963e-05,
|
| 140 |
+
"loss": 0.0688,
|
| 141 |
+
"step": 1200
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 4.01712962962963,
|
| 145 |
+
"grad_norm": 0.06853680312633514,
|
| 146 |
+
"learning_rate": 4.721579218106996e-05,
|
| 147 |
+
"loss": 0.018,
|
| 148 |
+
"step": 1300
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 4.0287037037037035,
|
| 152 |
+
"grad_norm": 0.06609813868999481,
|
| 153 |
+
"learning_rate": 4.657278806584363e-05,
|
| 154 |
+
"loss": 0.0043,
|
| 155 |
+
"step": 1400
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 4.033333333333333,
|
| 159 |
+
"eval_accuracy": 0.9921875,
|
| 160 |
+
"eval_f1": 0.9920634920634921,
|
| 161 |
+
"eval_loss": 0.026480242609977722,
|
| 162 |
+
"eval_precision": 0.99375,
|
| 163 |
+
"eval_recall": 0.9921875,
|
| 164 |
+
"eval_runtime": 327.6241,
|
| 165 |
+
"eval_samples_per_second": 0.781,
|
| 166 |
+
"eval_steps_per_second": 0.391,
|
| 167 |
+
"step": 1440
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 5.006944444444445,
|
| 171 |
+
"grad_norm": 0.09487422555685043,
|
| 172 |
+
"learning_rate": 4.5929783950617286e-05,
|
| 173 |
+
"loss": 0.0178,
|
| 174 |
+
"step": 1500
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 5.018518518518518,
|
| 178 |
+
"grad_norm": 0.06308699399232864,
|
| 179 |
+
"learning_rate": 4.5286779835390944e-05,
|
| 180 |
+
"loss": 0.0033,
|
| 181 |
+
"step": 1600
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 5.030092592592593,
|
| 185 |
+
"grad_norm": 0.4189186692237854,
|
| 186 |
+
"learning_rate": 4.464377572016461e-05,
|
| 187 |
+
"loss": 0.021,
|
| 188 |
+
"step": 1700
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 5.033333333333333,
|
| 192 |
+
"eval_accuracy": 0.9921875,
|
| 193 |
+
"eval_f1": 0.9920634920634921,
|
| 194 |
+
"eval_loss": 0.019995149224996567,
|
| 195 |
+
"eval_precision": 0.99375,
|
| 196 |
+
"eval_recall": 0.9921875,
|
| 197 |
+
"eval_runtime": 314.0145,
|
| 198 |
+
"eval_samples_per_second": 0.815,
|
| 199 |
+
"eval_steps_per_second": 0.408,
|
| 200 |
+
"step": 1728
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 6.008333333333334,
|
| 204 |
+
"grad_norm": 0.022702256217598915,
|
| 205 |
+
"learning_rate": 4.4000771604938274e-05,
|
| 206 |
+
"loss": 0.0144,
|
| 207 |
+
"step": 1800
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 6.019907407407407,
|
| 211 |
+
"grad_norm": 0.019604824483394623,
|
| 212 |
+
"learning_rate": 4.335776748971194e-05,
|
| 213 |
+
"loss": 0.0016,
|
| 214 |
+
"step": 1900
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 6.031481481481482,
|
| 218 |
+
"grad_norm": 0.017143510282039642,
|
| 219 |
+
"learning_rate": 4.27147633744856e-05,
|
| 220 |
+
"loss": 0.0014,
|
| 221 |
+
"step": 2000
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 6.033333333333333,
|
| 225 |
+
"eval_accuracy": 1.0,
|
| 226 |
+
"eval_f1": 1.0,
|
| 227 |
+
"eval_loss": 0.0011858218349516392,
|
| 228 |
+
"eval_precision": 1.0,
|
| 229 |
+
"eval_recall": 1.0,
|
| 230 |
+
"eval_runtime": 318.1849,
|
| 231 |
+
"eval_samples_per_second": 0.805,
|
| 232 |
+
"eval_steps_per_second": 0.402,
|
| 233 |
+
"step": 2016
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 7.009722222222222,
|
| 237 |
+
"grad_norm": 0.1380627602338791,
|
| 238 |
+
"learning_rate": 4.207175925925926e-05,
|
| 239 |
+
"loss": 0.0017,
|
| 240 |
+
"step": 2100
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 7.021296296296296,
|
| 244 |
+
"grad_norm": 0.02778031677007675,
|
| 245 |
+
"learning_rate": 4.142875514403292e-05,
|
| 246 |
+
"loss": 0.0251,
|
| 247 |
+
"step": 2200
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 7.032870370370371,
|
| 251 |
+
"grad_norm": 0.0441974513232708,
|
| 252 |
+
"learning_rate": 4.0785751028806585e-05,
|
| 253 |
+
"loss": 0.0414,
|
| 254 |
+
"step": 2300
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 7.033333333333333,
|
| 258 |
+
"eval_accuracy": 0.99609375,
|
| 259 |
+
"eval_f1": 0.996031746031746,
|
| 260 |
+
"eval_loss": 0.007463962305337191,
|
| 261 |
+
"eval_precision": 0.996875,
|
| 262 |
+
"eval_recall": 0.99609375,
|
| 263 |
+
"eval_runtime": 362.0912,
|
| 264 |
+
"eval_samples_per_second": 0.707,
|
| 265 |
+
"eval_steps_per_second": 0.354,
|
| 266 |
+
"step": 2304
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 8.011111111111111,
|
| 270 |
+
"grad_norm": 0.018177902325987816,
|
| 271 |
+
"learning_rate": 4.0149176954732515e-05,
|
| 272 |
+
"loss": 0.0836,
|
| 273 |
+
"step": 2400
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 8.022685185185185,
|
| 277 |
+
"grad_norm": 0.04126301780343056,
|
| 278 |
+
"learning_rate": 3.950617283950617e-05,
|
| 279 |
+
"loss": 0.0386,
|
| 280 |
+
"step": 2500
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 8.033333333333333,
|
| 284 |
+
"eval_accuracy": 0.99609375,
|
| 285 |
+
"eval_f1": 0.996031746031746,
|
| 286 |
+
"eval_loss": 0.018984569236636162,
|
| 287 |
+
"eval_precision": 0.996875,
|
| 288 |
+
"eval_recall": 0.99609375,
|
| 289 |
+
"eval_runtime": 313.7776,
|
| 290 |
+
"eval_samples_per_second": 0.816,
|
| 291 |
+
"eval_steps_per_second": 0.408,
|
| 292 |
+
"step": 2592
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"epoch": 8.033333333333333,
|
| 296 |
+
"step": 2592,
|
| 297 |
+
"total_flos": 5.3155188007162085e+19,
|
| 298 |
+
"train_loss": 2.444476819677669,
|
| 299 |
+
"train_runtime": 29887.626,
|
| 300 |
+
"train_samples_per_second": 2.313,
|
| 301 |
+
"train_steps_per_second": 0.289
|
| 302 |
+
}
|
| 303 |
+
],
|
| 304 |
+
"logging_steps": 100,
|
| 305 |
+
"max_steps": 8640,
|
| 306 |
+
"num_input_tokens_seen": 0,
|
| 307 |
+
"num_train_epochs": 9223372036854775807,
|
| 308 |
+
"save_steps": 500,
|
| 309 |
+
"stateful_callbacks": {
|
| 310 |
+
"EarlyStoppingCallback": {
|
| 311 |
+
"args": {
|
| 312 |
+
"early_stopping_patience": 5,
|
| 313 |
+
"early_stopping_threshold": 0.0
|
| 314 |
+
},
|
| 315 |
+
"attributes": {
|
| 316 |
+
"early_stopping_patience_counter": 5
|
| 317 |
+
}
|
| 318 |
+
},
|
| 319 |
+
"TrainerControl": {
|
| 320 |
+
"args": {
|
| 321 |
+
"should_epoch_stop": false,
|
| 322 |
+
"should_evaluate": false,
|
| 323 |
+
"should_log": false,
|
| 324 |
+
"should_save": true,
|
| 325 |
+
"should_training_stop": true
|
| 326 |
+
},
|
| 327 |
+
"attributes": {}
|
| 328 |
+
}
|
| 329 |
+
},
|
| 330 |
+
"total_flos": 5.3155188007162085e+19,
|
| 331 |
+
"train_batch_size": 2,
|
| 332 |
+
"trial_name": null,
|
| 333 |
+
"trial_params": null
|
| 334 |
+
}
|