Model save
Browse files- all_results.json +8 -0
- pytorch_model.bin +1 -1
- runs/Jun16_17-23-57_project/events.out.tfevents.1686936279.project.66927.0 +2 -2
- train_results.json +8 -0
- trainer_state.json +335 -0
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"total_flos": 5.983391481940132e+18,
|
| 4 |
+
"train_loss": 0.12369513756285111,
|
| 5 |
+
"train_runtime": 18018.3282,
|
| 6 |
+
"train_samples_per_second": 4.238,
|
| 7 |
+
"train_steps_per_second": 0.017
|
| 8 |
+
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 347601681
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7a982daf648323c0cb1fc09b0cead1a2fa43ce83f1fd8d81a0fdacbc40d48e90
|
| 3 |
size 347601681
|
runs/Jun16_17-23-57_project/events.out.tfevents.1686936279.project.66927.0
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b8ff86a4bb67ae76c362abbb381de7a08bc6fc8470b3168e6bfb3369c402d16f
|
| 3 |
+
size 14838
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"total_flos": 5.983391481940132e+18,
|
| 4 |
+
"train_loss": 0.12369513756285111,
|
| 5 |
+
"train_runtime": 18018.3282,
|
| 6 |
+
"train_samples_per_second": 4.238,
|
| 7 |
+
"train_steps_per_second": 0.017
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,335 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.9890023566378633,
|
| 3 |
+
"best_model_checkpoint": "finalProject/checkpoint-270",
|
| 4 |
+
"epoch": 10.0,
|
| 5 |
+
"global_step": 300,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.33,
|
| 12 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 13 |
+
"loss": 1.3112,
|
| 14 |
+
"step": 10
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.67,
|
| 18 |
+
"learning_rate": 6.666666666666667e-05,
|
| 19 |
+
"loss": 0.6741,
|
| 20 |
+
"step": 20
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 1.0,
|
| 24 |
+
"learning_rate": 0.0001,
|
| 25 |
+
"loss": 0.3384,
|
| 26 |
+
"step": 30
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 1.0,
|
| 30 |
+
"eval_accuracy": 0.9143754909662215,
|
| 31 |
+
"eval_f1_score": 0.9163479841895803,
|
| 32 |
+
"eval_loss": 0.23873452842235565,
|
| 33 |
+
"eval_precision": 0.9196515143456228,
|
| 34 |
+
"eval_runtime": 169.6465,
|
| 35 |
+
"eval_samples_per_second": 15.008,
|
| 36 |
+
"eval_sensitivity": 0.9146235660281107,
|
| 37 |
+
"eval_specificity": 0.9780923146558466,
|
| 38 |
+
"eval_steps_per_second": 0.236,
|
| 39 |
+
"step": 30
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 1.33,
|
| 43 |
+
"learning_rate": 9.62962962962963e-05,
|
| 44 |
+
"loss": 0.2174,
|
| 45 |
+
"step": 40
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 1.67,
|
| 49 |
+
"learning_rate": 9.25925925925926e-05,
|
| 50 |
+
"loss": 0.1765,
|
| 51 |
+
"step": 50
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 2.0,
|
| 55 |
+
"learning_rate": 8.888888888888889e-05,
|
| 56 |
+
"loss": 0.1608,
|
| 57 |
+
"step": 60
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 2.0,
|
| 61 |
+
"eval_accuracy": 0.9465828750981933,
|
| 62 |
+
"eval_f1_score": 0.9476010422638872,
|
| 63 |
+
"eval_loss": 0.16349805891513824,
|
| 64 |
+
"eval_precision": 0.9484564328540277,
|
| 65 |
+
"eval_runtime": 174.3047,
|
| 66 |
+
"eval_samples_per_second": 14.607,
|
| 67 |
+
"eval_sensitivity": 0.947446907765866,
|
| 68 |
+
"eval_specificity": 0.986469119173689,
|
| 69 |
+
"eval_steps_per_second": 0.229,
|
| 70 |
+
"step": 60
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"epoch": 2.33,
|
| 74 |
+
"learning_rate": 8.518518518518518e-05,
|
| 75 |
+
"loss": 0.1006,
|
| 76 |
+
"step": 70
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 2.67,
|
| 80 |
+
"learning_rate": 8.148148148148148e-05,
|
| 81 |
+
"loss": 0.1039,
|
| 82 |
+
"step": 80
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 3.0,
|
| 86 |
+
"learning_rate": 7.777777777777778e-05,
|
| 87 |
+
"loss": 0.0953,
|
| 88 |
+
"step": 90
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 3.0,
|
| 92 |
+
"eval_accuracy": 0.9697564807541241,
|
| 93 |
+
"eval_f1_score": 0.9702895103028133,
|
| 94 |
+
"eval_loss": 0.09146171808242798,
|
| 95 |
+
"eval_precision": 0.9706239633752509,
|
| 96 |
+
"eval_runtime": 174.9345,
|
| 97 |
+
"eval_samples_per_second": 14.554,
|
| 98 |
+
"eval_sensitivity": 0.9706195571306373,
|
| 99 |
+
"eval_specificity": 0.9923940549463361,
|
| 100 |
+
"eval_steps_per_second": 0.229,
|
| 101 |
+
"step": 90
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 3.33,
|
| 105 |
+
"learning_rate": 7.407407407407407e-05,
|
| 106 |
+
"loss": 0.0575,
|
| 107 |
+
"step": 100
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 3.67,
|
| 111 |
+
"learning_rate": 7.037037037037038e-05,
|
| 112 |
+
"loss": 0.0646,
|
| 113 |
+
"step": 110
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 4.0,
|
| 117 |
+
"learning_rate": 6.666666666666667e-05,
|
| 118 |
+
"loss": 0.0573,
|
| 119 |
+
"step": 120
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 4.0,
|
| 123 |
+
"eval_accuracy": 0.9607227022780833,
|
| 124 |
+
"eval_f1_score": 0.961737628945878,
|
| 125 |
+
"eval_loss": 0.11249902099370956,
|
| 126 |
+
"eval_precision": 0.9634002942489603,
|
| 127 |
+
"eval_runtime": 174.353,
|
| 128 |
+
"eval_samples_per_second": 14.603,
|
| 129 |
+
"eval_sensitivity": 0.962087628091487,
|
| 130 |
+
"eval_specificity": 0.9901301133433245,
|
| 131 |
+
"eval_steps_per_second": 0.229,
|
| 132 |
+
"step": 120
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 4.33,
|
| 136 |
+
"learning_rate": 6.296296296296296e-05,
|
| 137 |
+
"loss": 0.0444,
|
| 138 |
+
"step": 130
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 4.67,
|
| 142 |
+
"learning_rate": 5.925925925925926e-05,
|
| 143 |
+
"loss": 0.038,
|
| 144 |
+
"step": 140
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 5.0,
|
| 148 |
+
"learning_rate": 5.555555555555556e-05,
|
| 149 |
+
"loss": 0.0335,
|
| 150 |
+
"step": 150
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 5.0,
|
| 154 |
+
"eval_accuracy": 0.9827179890023566,
|
| 155 |
+
"eval_f1_score": 0.9830979182543695,
|
| 156 |
+
"eval_loss": 0.05359521508216858,
|
| 157 |
+
"eval_precision": 0.9837394543276896,
|
| 158 |
+
"eval_runtime": 177.7345,
|
| 159 |
+
"eval_samples_per_second": 14.325,
|
| 160 |
+
"eval_sensitivity": 0.9826194561417916,
|
| 161 |
+
"eval_specificity": 0.9956624203306454,
|
| 162 |
+
"eval_steps_per_second": 0.225,
|
| 163 |
+
"step": 150
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 5.33,
|
| 167 |
+
"learning_rate": 5.185185185185185e-05,
|
| 168 |
+
"loss": 0.03,
|
| 169 |
+
"step": 160
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 5.67,
|
| 173 |
+
"learning_rate": 4.814814814814815e-05,
|
| 174 |
+
"loss": 0.0288,
|
| 175 |
+
"step": 170
|
| 176 |
+
},
|
| 177 |
+
{
|
| 178 |
+
"epoch": 6.0,
|
| 179 |
+
"learning_rate": 4.4444444444444447e-05,
|
| 180 |
+
"loss": 0.0185,
|
| 181 |
+
"step": 180
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 6.0,
|
| 185 |
+
"eval_accuracy": 0.9827179890023566,
|
| 186 |
+
"eval_f1_score": 0.9830165407869904,
|
| 187 |
+
"eval_loss": 0.054298341274261475,
|
| 188 |
+
"eval_precision": 0.9836641999516438,
|
| 189 |
+
"eval_runtime": 174.6458,
|
| 190 |
+
"eval_samples_per_second": 14.578,
|
| 191 |
+
"eval_sensitivity": 0.982531934982829,
|
| 192 |
+
"eval_specificity": 0.9956626426606766,
|
| 193 |
+
"eval_steps_per_second": 0.229,
|
| 194 |
+
"step": 180
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 6.33,
|
| 198 |
+
"learning_rate": 4.074074074074074e-05,
|
| 199 |
+
"loss": 0.0195,
|
| 200 |
+
"step": 190
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 6.67,
|
| 204 |
+
"learning_rate": 3.7037037037037037e-05,
|
| 205 |
+
"loss": 0.0243,
|
| 206 |
+
"step": 200
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 7.0,
|
| 210 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 211 |
+
"loss": 0.0226,
|
| 212 |
+
"step": 210
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 7.0,
|
| 216 |
+
"eval_accuracy": 0.98586017282011,
|
| 217 |
+
"eval_f1_score": 0.9860564452647325,
|
| 218 |
+
"eval_loss": 0.04783537611365318,
|
| 219 |
+
"eval_precision": 0.9866235023223676,
|
| 220 |
+
"eval_runtime": 173.1051,
|
| 221 |
+
"eval_samples_per_second": 14.708,
|
| 222 |
+
"eval_sensitivity": 0.9856112737545305,
|
| 223 |
+
"eval_specificity": 0.9964541699537246,
|
| 224 |
+
"eval_steps_per_second": 0.231,
|
| 225 |
+
"step": 210
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 7.33,
|
| 229 |
+
"learning_rate": 2.962962962962963e-05,
|
| 230 |
+
"loss": 0.0152,
|
| 231 |
+
"step": 220
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 7.67,
|
| 235 |
+
"learning_rate": 2.5925925925925925e-05,
|
| 236 |
+
"loss": 0.0144,
|
| 237 |
+
"step": 230
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 8.0,
|
| 241 |
+
"learning_rate": 2.2222222222222223e-05,
|
| 242 |
+
"loss": 0.0131,
|
| 243 |
+
"step": 240
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 8.0,
|
| 247 |
+
"eval_accuracy": 0.9842890809112333,
|
| 248 |
+
"eval_f1_score": 0.9846202402489282,
|
| 249 |
+
"eval_loss": 0.04676336422562599,
|
| 250 |
+
"eval_precision": 0.9847490680324253,
|
| 251 |
+
"eval_runtime": 168.3745,
|
| 252 |
+
"eval_samples_per_second": 15.121,
|
| 253 |
+
"eval_sensitivity": 0.9845709444874553,
|
| 254 |
+
"eval_specificity": 0.9960560509519609,
|
| 255 |
+
"eval_steps_per_second": 0.238,
|
| 256 |
+
"step": 240
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 8.33,
|
| 260 |
+
"learning_rate": 1.8518518518518518e-05,
|
| 261 |
+
"loss": 0.013,
|
| 262 |
+
"step": 250
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 8.67,
|
| 266 |
+
"learning_rate": 1.4814814814814815e-05,
|
| 267 |
+
"loss": 0.0064,
|
| 268 |
+
"step": 260
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 9.0,
|
| 272 |
+
"learning_rate": 1.1111111111111112e-05,
|
| 273 |
+
"loss": 0.0087,
|
| 274 |
+
"step": 270
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 9.0,
|
| 278 |
+
"eval_accuracy": 0.9890023566378633,
|
| 279 |
+
"eval_f1_score": 0.9892464690962157,
|
| 280 |
+
"eval_loss": 0.04106396436691284,
|
| 281 |
+
"eval_precision": 0.9894345375382527,
|
| 282 |
+
"eval_runtime": 167.0678,
|
| 283 |
+
"eval_samples_per_second": 15.239,
|
| 284 |
+
"eval_sensitivity": 0.9891044356825909,
|
| 285 |
+
"eval_specificity": 0.9972424629484078,
|
| 286 |
+
"eval_steps_per_second": 0.239,
|
| 287 |
+
"step": 270
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 9.33,
|
| 291 |
+
"learning_rate": 7.4074074074074075e-06,
|
| 292 |
+
"loss": 0.0062,
|
| 293 |
+
"step": 280
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 9.67,
|
| 297 |
+
"learning_rate": 3.7037037037037037e-06,
|
| 298 |
+
"loss": 0.0123,
|
| 299 |
+
"step": 290
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 10.0,
|
| 303 |
+
"learning_rate": 0.0,
|
| 304 |
+
"loss": 0.0043,
|
| 305 |
+
"step": 300
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 10.0,
|
| 309 |
+
"eval_accuracy": 0.9886095836606441,
|
| 310 |
+
"eval_f1_score": 0.9888168771772841,
|
| 311 |
+
"eval_loss": 0.03755420818924904,
|
| 312 |
+
"eval_precision": 0.9890037194336745,
|
| 313 |
+
"eval_runtime": 166.1033,
|
| 314 |
+
"eval_samples_per_second": 15.328,
|
| 315 |
+
"eval_sensitivity": 0.9886508238847711,
|
| 316 |
+
"eval_specificity": 0.9971433026494437,
|
| 317 |
+
"eval_steps_per_second": 0.241,
|
| 318 |
+
"step": 300
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 10.0,
|
| 322 |
+
"step": 300,
|
| 323 |
+
"total_flos": 5.983391481940132e+18,
|
| 324 |
+
"train_loss": 0.12369513756285111,
|
| 325 |
+
"train_runtime": 18018.3282,
|
| 326 |
+
"train_samples_per_second": 4.238,
|
| 327 |
+
"train_steps_per_second": 0.017
|
| 328 |
+
}
|
| 329 |
+
],
|
| 330 |
+
"max_steps": 300,
|
| 331 |
+
"num_train_epochs": 10,
|
| 332 |
+
"total_flos": 5.983391481940132e+18,
|
| 333 |
+
"trial_name": null,
|
| 334 |
+
"trial_params": null
|
| 335 |
+
}
|