End of training
Browse files
all_results.json
ADDED
|
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 6.909090909090909,
|
| 3 |
+
"eval_accuracy": 0.8358637669265491,
|
| 4 |
+
"eval_auc_class_0": 0.9637412706523591,
|
| 5 |
+
"eval_auc_class_1": 0.9464505145891209,
|
| 6 |
+
"eval_auc_class_2": 0.928635846283816,
|
| 7 |
+
"eval_auc_overall": 0.9462758771750988,
|
| 8 |
+
"eval_loss": 0.4069300889968872,
|
| 9 |
+
"eval_runtime": 280.1877,
|
| 10 |
+
"eval_samples_per_second": 8.698,
|
| 11 |
+
"eval_steps_per_second": 0.071,
|
| 12 |
+
"total_flos": 5.296065448002933e+18,
|
| 13 |
+
"train_loss": 0.5080686431182059,
|
| 14 |
+
"train_runtime": 15650.1833,
|
| 15 |
+
"train_samples_per_second": 4.371,
|
| 16 |
+
"train_steps_per_second": 0.008
|
| 17 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 6.909090909090909,
|
| 3 |
+
"eval_accuracy": 0.8358637669265491,
|
| 4 |
+
"eval_auc_class_0": 0.9637412706523591,
|
| 5 |
+
"eval_auc_class_1": 0.9464505145891209,
|
| 6 |
+
"eval_auc_class_2": 0.928635846283816,
|
| 7 |
+
"eval_auc_overall": 0.9462758771750988,
|
| 8 |
+
"eval_loss": 0.4069300889968872,
|
| 9 |
+
"eval_runtime": 280.1877,
|
| 10 |
+
"eval_samples_per_second": 8.698,
|
| 11 |
+
"eval_steps_per_second": 0.071
|
| 12 |
+
}
|
runs/Sep25_07-02-24_data-science-wbi/events.out.tfevents.1727263724.data-science-wbi
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7e78627528d39b464c37cbd5a5572e1f8610478d53ecb0d8e89f5788233dfd5a
|
| 3 |
+
size 250
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 6.909090909090909,
|
| 3 |
+
"total_flos": 5.296065448002933e+18,
|
| 4 |
+
"train_loss": 0.5080686431182059,
|
| 5 |
+
"train_runtime": 15650.1833,
|
| 6 |
+
"train_samples_per_second": 4.371,
|
| 7 |
+
"train_steps_per_second": 0.008
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,315 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.8358637669265491,
|
| 3 |
+
"best_model_checkpoint": "swin-base-patch4-window7-224-in22k-MM_NMM_Classification_base_V10/checkpoint-133",
|
| 4 |
+
"epoch": 6.909090909090909,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 133,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.5194805194805194,
|
| 13 |
+
"grad_norm": 3.6334409713745117,
|
| 14 |
+
"learning_rate": 3.571428571428572e-05,
|
| 15 |
+
"loss": 1.0502,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.987012987012987,
|
| 20 |
+
"step": 19,
|
| 21 |
+
"train_accuracy": 0.7569835260411337,
|
| 22 |
+
"train_auc_class_0": 0.9160739393649986,
|
| 23 |
+
"train_auc_class_1": 0.9059040692814828,
|
| 24 |
+
"train_auc_class_2": 0.8730912427450218,
|
| 25 |
+
"train_auc_overall": 0.8983564171305011,
|
| 26 |
+
"train_loss": 0.5773088932037354,
|
| 27 |
+
"train_runtime": 897.4347,
|
| 28 |
+
"train_samples_per_second": 10.89,
|
| 29 |
+
"train_steps_per_second": 0.086
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 0.987012987012987,
|
| 33 |
+
"eval_accuracy": 0.7911366434140337,
|
| 34 |
+
"eval_auc_class_0": 0.9403359734287176,
|
| 35 |
+
"eval_auc_class_1": 0.9235862442916344,
|
| 36 |
+
"eval_auc_class_2": 0.8963866320052807,
|
| 37 |
+
"eval_auc_overall": 0.9201029499085442,
|
| 38 |
+
"eval_loss": 0.5198014974594116,
|
| 39 |
+
"eval_runtime": 265.4844,
|
| 40 |
+
"eval_samples_per_second": 9.179,
|
| 41 |
+
"eval_steps_per_second": 0.075,
|
| 42 |
+
"step": 19
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 1.0389610389610389,
|
| 46 |
+
"grad_norm": 3.133422374725342,
|
| 47 |
+
"learning_rate": 4.747899159663866e-05,
|
| 48 |
+
"loss": 0.6929,
|
| 49 |
+
"step": 20
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"epoch": 1.5584415584415585,
|
| 53 |
+
"grad_norm": 3.1555869579315186,
|
| 54 |
+
"learning_rate": 4.327731092436975e-05,
|
| 55 |
+
"loss": 0.5585,
|
| 56 |
+
"step": 30
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 1.974025974025974,
|
| 60 |
+
"step": 38,
|
| 61 |
+
"train_accuracy": 0.8060984344622941,
|
| 62 |
+
"train_auc_class_0": 0.9480363794091431,
|
| 63 |
+
"train_auc_class_1": 0.9353479593951236,
|
| 64 |
+
"train_auc_class_2": 0.9102701365313304,
|
| 65 |
+
"train_auc_overall": 0.9312181584451991,
|
| 66 |
+
"train_loss": 0.47007134556770325,
|
| 67 |
+
"train_runtime": 906.6059,
|
| 68 |
+
"train_samples_per_second": 10.78,
|
| 69 |
+
"train_steps_per_second": 0.085
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 1.974025974025974,
|
| 73 |
+
"eval_accuracy": 0.8104226508001642,
|
| 74 |
+
"eval_auc_class_0": 0.9510794583546245,
|
| 75 |
+
"eval_auc_class_1": 0.9375873639586919,
|
| 76 |
+
"eval_auc_class_2": 0.9143061067603285,
|
| 77 |
+
"eval_auc_overall": 0.9343243096912149,
|
| 78 |
+
"eval_loss": 0.4643743932247162,
|
| 79 |
+
"eval_runtime": 266.4476,
|
| 80 |
+
"eval_samples_per_second": 9.146,
|
| 81 |
+
"eval_steps_per_second": 0.075,
|
| 82 |
+
"step": 38
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 2.0779220779220777,
|
| 86 |
+
"grad_norm": 2.1339571475982666,
|
| 87 |
+
"learning_rate": 3.907563025210084e-05,
|
| 88 |
+
"loss": 0.5114,
|
| 89 |
+
"step": 40
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 2.5974025974025974,
|
| 93 |
+
"grad_norm": 2.0463883876800537,
|
| 94 |
+
"learning_rate": 3.487394957983193e-05,
|
| 95 |
+
"loss": 0.47,
|
| 96 |
+
"step": 50
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 2.961038961038961,
|
| 100 |
+
"step": 57,
|
| 101 |
+
"train_accuracy": 0.819093420648726,
|
| 102 |
+
"train_auc_class_0": 0.959281252652914,
|
| 103 |
+
"train_auc_class_1": 0.9451989583224498,
|
| 104 |
+
"train_auc_class_2": 0.9209859149104825,
|
| 105 |
+
"train_auc_overall": 0.9418220419619487,
|
| 106 |
+
"train_loss": 0.4309811294078827,
|
| 107 |
+
"train_runtime": 984.0694,
|
| 108 |
+
"train_samples_per_second": 9.931,
|
| 109 |
+
"train_steps_per_second": 0.078
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 2.961038961038961,
|
| 113 |
+
"eval_accuracy": 0.8276569552728765,
|
| 114 |
+
"eval_auc_class_0": 0.9621529552035428,
|
| 115 |
+
"eval_auc_class_1": 0.9414093721062062,
|
| 116 |
+
"eval_auc_class_2": 0.9226855511459174,
|
| 117 |
+
"eval_auc_overall": 0.9420826261518888,
|
| 118 |
+
"eval_loss": 0.4235168695449829,
|
| 119 |
+
"eval_runtime": 284.7667,
|
| 120 |
+
"eval_samples_per_second": 8.558,
|
| 121 |
+
"eval_steps_per_second": 0.07,
|
| 122 |
+
"step": 57
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 3.116883116883117,
|
| 126 |
+
"grad_norm": 2.500288963317871,
|
| 127 |
+
"learning_rate": 3.0672268907563026e-05,
|
| 128 |
+
"loss": 0.4485,
|
| 129 |
+
"step": 60
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 3.6363636363636362,
|
| 133 |
+
"grad_norm": 2.1541225910186768,
|
| 134 |
+
"learning_rate": 2.647058823529412e-05,
|
| 135 |
+
"loss": 0.4487,
|
| 136 |
+
"step": 70
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 4.0,
|
| 140 |
+
"step": 77,
|
| 141 |
+
"train_accuracy": 0.8312698250281387,
|
| 142 |
+
"train_auc_class_0": 0.9636362430493655,
|
| 143 |
+
"train_auc_class_1": 0.9487531692630246,
|
| 144 |
+
"train_auc_class_2": 0.928211332215209,
|
| 145 |
+
"train_auc_overall": 0.9468669148425329,
|
| 146 |
+
"train_loss": 0.41109779477119446,
|
| 147 |
+
"train_runtime": 958.2523,
|
| 148 |
+
"train_samples_per_second": 10.199,
|
| 149 |
+
"train_steps_per_second": 0.08
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 4.0,
|
| 153 |
+
"eval_accuracy": 0.826015592942142,
|
| 154 |
+
"eval_auc_class_0": 0.9611033043774485,
|
| 155 |
+
"eval_auc_class_1": 0.9434057595955114,
|
| 156 |
+
"eval_auc_class_2": 0.9248328729019133,
|
| 157 |
+
"eval_auc_overall": 0.9431139789582911,
|
| 158 |
+
"eval_loss": 0.4228733479976654,
|
| 159 |
+
"eval_runtime": 284.7186,
|
| 160 |
+
"eval_samples_per_second": 8.559,
|
| 161 |
+
"eval_steps_per_second": 0.07,
|
| 162 |
+
"step": 77
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 4.1558441558441555,
|
| 166 |
+
"grad_norm": 2.5099682807922363,
|
| 167 |
+
"learning_rate": 2.226890756302521e-05,
|
| 168 |
+
"loss": 0.4217,
|
| 169 |
+
"step": 80
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 4.675324675324675,
|
| 173 |
+
"grad_norm": 2.6273367404937744,
|
| 174 |
+
"learning_rate": 1.8067226890756303e-05,
|
| 175 |
+
"loss": 0.4076,
|
| 176 |
+
"step": 90
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 4.987012987012987,
|
| 180 |
+
"step": 96,
|
| 181 |
+
"train_accuracy": 0.8339302159009516,
|
| 182 |
+
"train_auc_class_0": 0.9658112345600407,
|
| 183 |
+
"train_auc_class_1": 0.9512605003604601,
|
| 184 |
+
"train_auc_class_2": 0.931225975691603,
|
| 185 |
+
"train_auc_overall": 0.9494325702040346,
|
| 186 |
+
"train_loss": 0.4025966227054596,
|
| 187 |
+
"train_runtime": 991.1294,
|
| 188 |
+
"train_samples_per_second": 9.86,
|
| 189 |
+
"train_steps_per_second": 0.078
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 4.987012987012987,
|
| 193 |
+
"eval_accuracy": 0.8297086581862946,
|
| 194 |
+
"eval_auc_class_0": 0.9624020609776871,
|
| 195 |
+
"eval_auc_class_1": 0.9453678176703179,
|
| 196 |
+
"eval_auc_class_2": 0.9253326922606775,
|
| 197 |
+
"eval_auc_overall": 0.9443675236362274,
|
| 198 |
+
"eval_loss": 0.41654419898986816,
|
| 199 |
+
"eval_runtime": 281.0044,
|
| 200 |
+
"eval_samples_per_second": 8.672,
|
| 201 |
+
"eval_steps_per_second": 0.071,
|
| 202 |
+
"step": 96
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 5.194805194805195,
|
| 206 |
+
"grad_norm": 2.5981998443603516,
|
| 207 |
+
"learning_rate": 1.3865546218487396e-05,
|
| 208 |
+
"loss": 0.4229,
|
| 209 |
+
"step": 100
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 5.714285714285714,
|
| 213 |
+
"grad_norm": 2.4040989875793457,
|
| 214 |
+
"learning_rate": 9.663865546218488e-06,
|
| 215 |
+
"loss": 0.4182,
|
| 216 |
+
"step": 110
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 5.974025974025974,
|
| 220 |
+
"step": 115,
|
| 221 |
+
"train_accuracy": 0.8407858385347385,
|
| 222 |
+
"train_auc_class_0": 0.9691956895453967,
|
| 223 |
+
"train_auc_class_1": 0.9539528502470981,
|
| 224 |
+
"train_auc_class_2": 0.9353985798608017,
|
| 225 |
+
"train_auc_overall": 0.9528490398844321,
|
| 226 |
+
"train_loss": 0.3878542184829712,
|
| 227 |
+
"train_runtime": 964.3964,
|
| 228 |
+
"train_samples_per_second": 10.134,
|
| 229 |
+
"train_steps_per_second": 0.08
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 5.974025974025974,
|
| 233 |
+
"eval_accuracy": 0.83258104226508,
|
| 234 |
+
"eval_auc_class_0": 0.9633271589167093,
|
| 235 |
+
"eval_auc_class_1": 0.9464734008654533,
|
| 236 |
+
"eval_auc_class_2": 0.9275261929791678,
|
| 237 |
+
"eval_auc_overall": 0.9457755842537768,
|
| 238 |
+
"eval_loss": 0.4134509563446045,
|
| 239 |
+
"eval_runtime": 281.0951,
|
| 240 |
+
"eval_samples_per_second": 8.67,
|
| 241 |
+
"eval_steps_per_second": 0.071,
|
| 242 |
+
"step": 115
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 6.233766233766234,
|
| 246 |
+
"grad_norm": 1.9785808324813843,
|
| 247 |
+
"learning_rate": 5.46218487394958e-06,
|
| 248 |
+
"loss": 0.396,
|
| 249 |
+
"step": 120
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 6.753246753246753,
|
| 253 |
+
"grad_norm": 1.799540400505066,
|
| 254 |
+
"learning_rate": 1.2605042016806724e-06,
|
| 255 |
+
"loss": 0.3874,
|
| 256 |
+
"step": 130
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 6.909090909090909,
|
| 260 |
+
"step": 133,
|
| 261 |
+
"train_accuracy": 0.8431392612299191,
|
| 262 |
+
"train_auc_class_0": 0.9683630724988327,
|
| 263 |
+
"train_auc_class_1": 0.9514347173174106,
|
| 264 |
+
"train_auc_class_2": 0.9349089785503817,
|
| 265 |
+
"train_auc_overall": 0.951568922788875,
|
| 266 |
+
"train_loss": 0.39069029688835144,
|
| 267 |
+
"train_runtime": 970.3934,
|
| 268 |
+
"train_samples_per_second": 10.071,
|
| 269 |
+
"train_steps_per_second": 0.079
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 6.909090909090909,
|
| 273 |
+
"eval_accuracy": 0.8358637669265491,
|
| 274 |
+
"eval_auc_class_0": 0.9637412706523591,
|
| 275 |
+
"eval_auc_class_1": 0.9464505145891209,
|
| 276 |
+
"eval_auc_class_2": 0.928635846283816,
|
| 277 |
+
"eval_auc_overall": 0.9462758771750988,
|
| 278 |
+
"eval_loss": 0.4069300889968872,
|
| 279 |
+
"eval_runtime": 282.2427,
|
| 280 |
+
"eval_samples_per_second": 8.634,
|
| 281 |
+
"eval_steps_per_second": 0.071,
|
| 282 |
+
"step": 133
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 6.909090909090909,
|
| 286 |
+
"step": 133,
|
| 287 |
+
"total_flos": 5.296065448002933e+18,
|
| 288 |
+
"train_loss": 0.5080686431182059,
|
| 289 |
+
"train_runtime": 15650.1833,
|
| 290 |
+
"train_samples_per_second": 4.371,
|
| 291 |
+
"train_steps_per_second": 0.008
|
| 292 |
+
}
|
| 293 |
+
],
|
| 294 |
+
"logging_steps": 10,
|
| 295 |
+
"max_steps": 133,
|
| 296 |
+
"num_input_tokens_seen": 0,
|
| 297 |
+
"num_train_epochs": 7,
|
| 298 |
+
"save_steps": 500,
|
| 299 |
+
"stateful_callbacks": {
|
| 300 |
+
"TrainerControl": {
|
| 301 |
+
"args": {
|
| 302 |
+
"should_epoch_stop": false,
|
| 303 |
+
"should_evaluate": false,
|
| 304 |
+
"should_log": false,
|
| 305 |
+
"should_save": true,
|
| 306 |
+
"should_training_stop": true
|
| 307 |
+
},
|
| 308 |
+
"attributes": {}
|
| 309 |
+
}
|
| 310 |
+
},
|
| 311 |
+
"total_flos": 5.296065448002933e+18,
|
| 312 |
+
"train_batch_size": 128,
|
| 313 |
+
"trial_name": null,
|
| 314 |
+
"trial_params": null
|
| 315 |
+
}
|