Commit ·
b5d3343
1
Parent(s): 979557d
Training in progress, epoch 0
Browse files- all_results.json +7 -0
- pytorch_model.bin +1 -1
- runs/Sep21_18-25-55_hj/events.out.tfevents.1695288358.hj.6536.0 +3 -0
- train_results.json +7 -0
- trainer_state.json +529 -0
- training_args.bin +1 -1
all_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.98,
|
| 3 |
+
"train_loss": 0.14726725356690837,
|
| 4 |
+
"train_runtime": 5241.8792,
|
| 5 |
+
"train_samples_per_second": 72.911,
|
| 6 |
+
"train_steps_per_second": 0.142
|
| 7 |
+
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 343274861
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:80ac55cbd0cc3aac4ee3b4f451a2225877446d5673778d52508b643e3b0124e4
|
| 3 |
size 343274861
|
runs/Sep21_18-25-55_hj/events.out.tfevents.1695288358.hj.6536.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0c4c122883c4b3f52b6934644c5af95652e322e85f52ed6a5f50d43278172711
|
| 3 |
+
size 6721
|
train_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.98,
|
| 3 |
+
"train_loss": 0.14726725356690837,
|
| 4 |
+
"train_runtime": 5241.8792,
|
| 5 |
+
"train_samples_per_second": 72.911,
|
| 6 |
+
"train_steps_per_second": 0.142
|
| 7 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,529 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.9985872380503885,
|
| 3 |
+
"best_model_checkpoint": "vit_base_aihub_model_py/checkpoint-745",
|
| 4 |
+
"epoch": 4.983277591973244,
|
| 5 |
+
"global_step": 745,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.07,
|
| 12 |
+
"learning_rate": 6.666666666666667e-06,
|
| 13 |
+
"loss": 1.3773,
|
| 14 |
+
"step": 10
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.13,
|
| 18 |
+
"learning_rate": 1.3333333333333333e-05,
|
| 19 |
+
"loss": 1.2997,
|
| 20 |
+
"step": 20
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.2,
|
| 24 |
+
"learning_rate": 2e-05,
|
| 25 |
+
"loss": 1.134,
|
| 26 |
+
"step": 30
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.27,
|
| 30 |
+
"learning_rate": 2.6666666666666667e-05,
|
| 31 |
+
"loss": 0.9478,
|
| 32 |
+
"step": 40
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.33,
|
| 36 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 37 |
+
"loss": 0.7246,
|
| 38 |
+
"step": 50
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.4,
|
| 42 |
+
"learning_rate": 4e-05,
|
| 43 |
+
"loss": 0.5165,
|
| 44 |
+
"step": 60
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.47,
|
| 48 |
+
"learning_rate": 4.666666666666667e-05,
|
| 49 |
+
"loss": 0.3778,
|
| 50 |
+
"step": 70
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.54,
|
| 54 |
+
"learning_rate": 4.9626865671641794e-05,
|
| 55 |
+
"loss": 0.2721,
|
| 56 |
+
"step": 80
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.6,
|
| 60 |
+
"learning_rate": 4.888059701492538e-05,
|
| 61 |
+
"loss": 0.217,
|
| 62 |
+
"step": 90
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.67,
|
| 66 |
+
"learning_rate": 4.813432835820896e-05,
|
| 67 |
+
"loss": 0.186,
|
| 68 |
+
"step": 100
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.74,
|
| 72 |
+
"learning_rate": 4.738805970149254e-05,
|
| 73 |
+
"loss": 0.1654,
|
| 74 |
+
"step": 110
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.8,
|
| 78 |
+
"learning_rate": 4.664179104477612e-05,
|
| 79 |
+
"loss": 0.1533,
|
| 80 |
+
"step": 120
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.87,
|
| 84 |
+
"learning_rate": 4.58955223880597e-05,
|
| 85 |
+
"loss": 0.1389,
|
| 86 |
+
"step": 130
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.94,
|
| 90 |
+
"learning_rate": 4.5149253731343286e-05,
|
| 91 |
+
"loss": 0.1235,
|
| 92 |
+
"step": 140
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 1.0,
|
| 96 |
+
"eval_accuracy": 0.9857546503414175,
|
| 97 |
+
"eval_f1": 0.9829586496374041,
|
| 98 |
+
"eval_loss": 0.09358736127614975,
|
| 99 |
+
"eval_precision": 0.9845287058827537,
|
| 100 |
+
"eval_recall": 0.9814155430620309,
|
| 101 |
+
"eval_runtime": 111.262,
|
| 102 |
+
"eval_samples_per_second": 76.342,
|
| 103 |
+
"eval_steps_per_second": 0.602,
|
| 104 |
+
"step": 149
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 1.0,
|
| 108 |
+
"learning_rate": 4.440298507462687e-05,
|
| 109 |
+
"loss": 0.1106,
|
| 110 |
+
"step": 150
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 1.07,
|
| 114 |
+
"learning_rate": 4.3656716417910446e-05,
|
| 115 |
+
"loss": 0.1162,
|
| 116 |
+
"step": 160
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 1.14,
|
| 120 |
+
"learning_rate": 4.2910447761194036e-05,
|
| 121 |
+
"loss": 0.1059,
|
| 122 |
+
"step": 170
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 1.2,
|
| 126 |
+
"learning_rate": 4.216417910447761e-05,
|
| 127 |
+
"loss": 0.1115,
|
| 128 |
+
"step": 180
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 1.27,
|
| 132 |
+
"learning_rate": 4.1417910447761195e-05,
|
| 133 |
+
"loss": 0.0924,
|
| 134 |
+
"step": 190
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 1.34,
|
| 138 |
+
"learning_rate": 4.067164179104478e-05,
|
| 139 |
+
"loss": 0.0972,
|
| 140 |
+
"step": 200
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 1.4,
|
| 144 |
+
"learning_rate": 3.992537313432836e-05,
|
| 145 |
+
"loss": 0.0909,
|
| 146 |
+
"step": 210
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 1.47,
|
| 150 |
+
"learning_rate": 3.9179104477611945e-05,
|
| 151 |
+
"loss": 0.0977,
|
| 152 |
+
"step": 220
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 1.54,
|
| 156 |
+
"learning_rate": 3.843283582089552e-05,
|
| 157 |
+
"loss": 0.0931,
|
| 158 |
+
"step": 230
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 1.61,
|
| 162 |
+
"learning_rate": 3.7686567164179104e-05,
|
| 163 |
+
"loss": 0.0756,
|
| 164 |
+
"step": 240
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 1.67,
|
| 168 |
+
"learning_rate": 3.694029850746269e-05,
|
| 169 |
+
"loss": 0.083,
|
| 170 |
+
"step": 250
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 1.74,
|
| 174 |
+
"learning_rate": 3.619402985074627e-05,
|
| 175 |
+
"loss": 0.0751,
|
| 176 |
+
"step": 260
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 1.81,
|
| 180 |
+
"learning_rate": 3.5447761194029854e-05,
|
| 181 |
+
"loss": 0.0666,
|
| 182 |
+
"step": 270
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 1.87,
|
| 186 |
+
"learning_rate": 3.470149253731344e-05,
|
| 187 |
+
"loss": 0.0673,
|
| 188 |
+
"step": 280
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 1.94,
|
| 192 |
+
"learning_rate": 3.395522388059701e-05,
|
| 193 |
+
"loss": 0.067,
|
| 194 |
+
"step": 290
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 2.0,
|
| 198 |
+
"eval_accuracy": 0.987756063103367,
|
| 199 |
+
"eval_f1": 0.9859294798786484,
|
| 200 |
+
"eval_loss": 0.06216855347156525,
|
| 201 |
+
"eval_precision": 0.990943040361106,
|
| 202 |
+
"eval_recall": 0.9812800326186175,
|
| 203 |
+
"eval_runtime": 108.9574,
|
| 204 |
+
"eval_samples_per_second": 77.957,
|
| 205 |
+
"eval_steps_per_second": 0.615,
|
| 206 |
+
"step": 299
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 2.01,
|
| 210 |
+
"learning_rate": 3.32089552238806e-05,
|
| 211 |
+
"loss": 0.0754,
|
| 212 |
+
"step": 300
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 2.07,
|
| 216 |
+
"learning_rate": 3.246268656716418e-05,
|
| 217 |
+
"loss": 0.0657,
|
| 218 |
+
"step": 310
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 2.14,
|
| 222 |
+
"learning_rate": 3.171641791044776e-05,
|
| 223 |
+
"loss": 0.0683,
|
| 224 |
+
"step": 320
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 2.21,
|
| 228 |
+
"learning_rate": 3.0970149253731346e-05,
|
| 229 |
+
"loss": 0.0569,
|
| 230 |
+
"step": 330
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 2.27,
|
| 234 |
+
"learning_rate": 3.0223880597014926e-05,
|
| 235 |
+
"loss": 0.0515,
|
| 236 |
+
"step": 340
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 2.34,
|
| 240 |
+
"learning_rate": 2.9477611940298512e-05,
|
| 241 |
+
"loss": 0.0557,
|
| 242 |
+
"step": 350
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 2.41,
|
| 246 |
+
"learning_rate": 2.8731343283582092e-05,
|
| 247 |
+
"loss": 0.0558,
|
| 248 |
+
"step": 360
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 2.47,
|
| 252 |
+
"learning_rate": 2.7985074626865672e-05,
|
| 253 |
+
"loss": 0.0592,
|
| 254 |
+
"step": 370
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 2.54,
|
| 258 |
+
"learning_rate": 2.7238805970149255e-05,
|
| 259 |
+
"loss": 0.0502,
|
| 260 |
+
"step": 380
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 2.61,
|
| 264 |
+
"learning_rate": 2.6492537313432835e-05,
|
| 265 |
+
"loss": 0.0567,
|
| 266 |
+
"step": 390
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 2.68,
|
| 270 |
+
"learning_rate": 2.574626865671642e-05,
|
| 271 |
+
"loss": 0.0539,
|
| 272 |
+
"step": 400
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 2.74,
|
| 276 |
+
"learning_rate": 2.5e-05,
|
| 277 |
+
"loss": 0.0512,
|
| 278 |
+
"step": 410
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 2.81,
|
| 282 |
+
"learning_rate": 2.4253731343283584e-05,
|
| 283 |
+
"loss": 0.0544,
|
| 284 |
+
"step": 420
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 2.88,
|
| 288 |
+
"learning_rate": 2.3507462686567168e-05,
|
| 289 |
+
"loss": 0.0561,
|
| 290 |
+
"step": 430
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 2.94,
|
| 294 |
+
"learning_rate": 2.2761194029850747e-05,
|
| 295 |
+
"loss": 0.049,
|
| 296 |
+
"step": 440
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 3.0,
|
| 300 |
+
"eval_accuracy": 0.9968212856133741,
|
| 301 |
+
"eval_f1": 0.9964206807723841,
|
| 302 |
+
"eval_loss": 0.03217490762472153,
|
| 303 |
+
"eval_precision": 0.9969469418365854,
|
| 304 |
+
"eval_recall": 0.99589824183686,
|
| 305 |
+
"eval_runtime": 106.3062,
|
| 306 |
+
"eval_samples_per_second": 79.901,
|
| 307 |
+
"eval_steps_per_second": 0.63,
|
| 308 |
+
"step": 448
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 3.01,
|
| 312 |
+
"learning_rate": 2.201492537313433e-05,
|
| 313 |
+
"loss": 0.0493,
|
| 314 |
+
"step": 450
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 3.08,
|
| 318 |
+
"learning_rate": 2.126865671641791e-05,
|
| 319 |
+
"loss": 0.0544,
|
| 320 |
+
"step": 460
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 3.14,
|
| 324 |
+
"learning_rate": 2.0522388059701493e-05,
|
| 325 |
+
"loss": 0.0495,
|
| 326 |
+
"step": 470
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 3.21,
|
| 330 |
+
"learning_rate": 1.9776119402985073e-05,
|
| 331 |
+
"loss": 0.044,
|
| 332 |
+
"step": 480
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 3.28,
|
| 336 |
+
"learning_rate": 1.9029850746268656e-05,
|
| 337 |
+
"loss": 0.0452,
|
| 338 |
+
"step": 490
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 3.34,
|
| 342 |
+
"learning_rate": 1.828358208955224e-05,
|
| 343 |
+
"loss": 0.0437,
|
| 344 |
+
"step": 500
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 3.41,
|
| 348 |
+
"learning_rate": 1.7537313432835823e-05,
|
| 349 |
+
"loss": 0.0374,
|
| 350 |
+
"step": 510
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 3.48,
|
| 354 |
+
"learning_rate": 1.6791044776119406e-05,
|
| 355 |
+
"loss": 0.0389,
|
| 356 |
+
"step": 520
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 3.55,
|
| 360 |
+
"learning_rate": 1.6044776119402986e-05,
|
| 361 |
+
"loss": 0.0321,
|
| 362 |
+
"step": 530
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 3.61,
|
| 366 |
+
"learning_rate": 1.529850746268657e-05,
|
| 367 |
+
"loss": 0.0347,
|
| 368 |
+
"step": 540
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 3.68,
|
| 372 |
+
"learning_rate": 1.455223880597015e-05,
|
| 373 |
+
"loss": 0.0359,
|
| 374 |
+
"step": 550
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 3.75,
|
| 378 |
+
"learning_rate": 1.3805970149253733e-05,
|
| 379 |
+
"loss": 0.0369,
|
| 380 |
+
"step": 560
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 3.81,
|
| 384 |
+
"learning_rate": 1.3059701492537313e-05,
|
| 385 |
+
"loss": 0.0367,
|
| 386 |
+
"step": 570
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 3.88,
|
| 390 |
+
"learning_rate": 1.2313432835820896e-05,
|
| 391 |
+
"loss": 0.0353,
|
| 392 |
+
"step": 580
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 3.95,
|
| 396 |
+
"learning_rate": 1.1567164179104478e-05,
|
| 397 |
+
"loss": 0.0477,
|
| 398 |
+
"step": 590
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 4.0,
|
| 402 |
+
"eval_accuracy": 0.9977631269131152,
|
| 403 |
+
"eval_f1": 0.997511338692231,
|
| 404 |
+
"eval_loss": 0.024851497262716293,
|
| 405 |
+
"eval_precision": 0.9985286326587551,
|
| 406 |
+
"eval_recall": 0.9965020764725261,
|
| 407 |
+
"eval_runtime": 103.7864,
|
| 408 |
+
"eval_samples_per_second": 81.841,
|
| 409 |
+
"eval_steps_per_second": 0.646,
|
| 410 |
+
"step": 598
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 4.01,
|
| 414 |
+
"learning_rate": 1.082089552238806e-05,
|
| 415 |
+
"loss": 0.0382,
|
| 416 |
+
"step": 600
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 4.08,
|
| 420 |
+
"learning_rate": 1.0074626865671643e-05,
|
| 421 |
+
"loss": 0.0347,
|
| 422 |
+
"step": 610
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 4.15,
|
| 426 |
+
"learning_rate": 9.328358208955226e-06,
|
| 427 |
+
"loss": 0.0304,
|
| 428 |
+
"step": 620
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 4.21,
|
| 432 |
+
"learning_rate": 8.582089552238805e-06,
|
| 433 |
+
"loss": 0.0373,
|
| 434 |
+
"step": 630
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 4.28,
|
| 438 |
+
"learning_rate": 7.835820895522389e-06,
|
| 439 |
+
"loss": 0.0311,
|
| 440 |
+
"step": 640
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 4.35,
|
| 444 |
+
"learning_rate": 7.08955223880597e-06,
|
| 445 |
+
"loss": 0.0332,
|
| 446 |
+
"step": 650
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 4.41,
|
| 450 |
+
"learning_rate": 6.343283582089552e-06,
|
| 451 |
+
"loss": 0.0334,
|
| 452 |
+
"step": 660
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 4.48,
|
| 456 |
+
"learning_rate": 5.597014925373135e-06,
|
| 457 |
+
"loss": 0.0329,
|
| 458 |
+
"step": 670
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 4.55,
|
| 462 |
+
"learning_rate": 4.850746268656717e-06,
|
| 463 |
+
"loss": 0.0332,
|
| 464 |
+
"step": 680
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 4.62,
|
| 468 |
+
"learning_rate": 4.1044776119402985e-06,
|
| 469 |
+
"loss": 0.0303,
|
| 470 |
+
"step": 690
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 4.68,
|
| 474 |
+
"learning_rate": 3.358208955223881e-06,
|
| 475 |
+
"loss": 0.0276,
|
| 476 |
+
"step": 700
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 4.75,
|
| 480 |
+
"learning_rate": 2.6119402985074627e-06,
|
| 481 |
+
"loss": 0.0332,
|
| 482 |
+
"step": 710
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 4.82,
|
| 486 |
+
"learning_rate": 1.8656716417910446e-06,
|
| 487 |
+
"loss": 0.0317,
|
| 488 |
+
"step": 720
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 4.88,
|
| 492 |
+
"learning_rate": 1.119402985074627e-06,
|
| 493 |
+
"loss": 0.0315,
|
| 494 |
+
"step": 730
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 4.95,
|
| 498 |
+
"learning_rate": 3.7313432835820895e-07,
|
| 499 |
+
"loss": 0.0336,
|
| 500 |
+
"step": 740
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 4.98,
|
| 504 |
+
"eval_accuracy": 0.9985872380503885,
|
| 505 |
+
"eval_f1": 0.9985770990024514,
|
| 506 |
+
"eval_loss": 0.021681277081370354,
|
| 507 |
+
"eval_precision": 0.9989954885489135,
|
| 508 |
+
"eval_recall": 0.998161142953993,
|
| 509 |
+
"eval_runtime": 106.6587,
|
| 510 |
+
"eval_samples_per_second": 79.637,
|
| 511 |
+
"eval_steps_per_second": 0.628,
|
| 512 |
+
"step": 745
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 4.98,
|
| 516 |
+
"step": 745,
|
| 517 |
+
"total_flos": 2.9526217173796848e+19,
|
| 518 |
+
"train_loss": 0.14726725356690837,
|
| 519 |
+
"train_runtime": 5241.8792,
|
| 520 |
+
"train_samples_per_second": 72.911,
|
| 521 |
+
"train_steps_per_second": 0.142
|
| 522 |
+
}
|
| 523 |
+
],
|
| 524 |
+
"max_steps": 745,
|
| 525 |
+
"num_train_epochs": 5,
|
| 526 |
+
"total_flos": 2.9526217173796848e+19,
|
| 527 |
+
"trial_name": null,
|
| 528 |
+
"trial_params": null
|
| 529 |
+
}
|
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 sha256:13356b6157d75c25db2c03ce43f34eb86fca619f4815efc577fc211676d3f7f9
|
| 3 |
size 3963
|