Model save
Browse files- all_results.json +6 -6
- pytorch_model.bin +1 -1
- runs/May23_21-58-26_project/events.out.tfevents.1684879118.project.44437.0 +2 -2
- train_results.json +6 -6
- trainer_state.json +658 -176
all_results.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
"eval_accuracy": 0.9265375854214123,
|
| 4 |
"eval_f1_score": 0.9252257576617917,
|
| 5 |
"eval_loss": 0.19247999787330627,
|
|
@@ -7,9 +7,9 @@
|
|
| 7 |
"eval_runtime": 96.8959,
|
| 8 |
"eval_samples_per_second": 18.123,
|
| 9 |
"eval_steps_per_second": 0.289,
|
| 10 |
-
"total_flos":
|
| 11 |
-
"train_loss": 0.
|
| 12 |
-
"train_runtime":
|
| 13 |
-
"train_samples_per_second": 5.
|
| 14 |
-
"train_steps_per_second": 0.
|
| 15 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 19.88,
|
| 3 |
"eval_accuracy": 0.9265375854214123,
|
| 4 |
"eval_f1_score": 0.9252257576617917,
|
| 5 |
"eval_loss": 0.19247999787330627,
|
|
|
|
| 7 |
"eval_runtime": 96.8959,
|
| 8 |
"eval_samples_per_second": 18.123,
|
| 9 |
"eval_steps_per_second": 0.289,
|
| 10 |
+
"total_flos": 8.203992042011222e+18,
|
| 11 |
+
"train_loss": 0.18675074555524965,
|
| 12 |
+
"train_runtime": 20102.5048,
|
| 13 |
+
"train_samples_per_second": 5.24,
|
| 14 |
+
"train_steps_per_second": 0.041
|
| 15 |
}
|
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 sha256:9069b6fc118f468b4306a25d0928f19afb8db914dbf5be8d6a0f4c0141cf69e4
|
| 3 |
size 347601681
|
runs/May23_21-58-26_project/events.out.tfevents.1684879118.project.44437.0
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:d664e488502c6ead12600c83b5e7062b30d6c2137ca77b7e6f04d61d5e8579fd
|
| 3 |
+
size 26347
|
train_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"total_flos":
|
| 4 |
-
"train_loss": 0.
|
| 5 |
-
"train_runtime":
|
| 6 |
-
"train_samples_per_second": 5.
|
| 7 |
-
"train_steps_per_second": 0.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 19.88,
|
| 3 |
+
"total_flos": 8.203992042011222e+18,
|
| 4 |
+
"train_loss": 0.18675074555524965,
|
| 5 |
+
"train_runtime": 20102.5048,
|
| 6 |
+
"train_samples_per_second": 5.24,
|
| 7 |
+
"train_steps_per_second": 0.041
|
| 8 |
}
|
trainer_state.json
CHANGED
|
@@ -1,255 +1,737 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
-
"best_model_checkpoint": "swin-base-patch4-window7-224-in22k-finetuned-brain-tumor-final/checkpoint-
|
| 4 |
-
"epoch":
|
| 5 |
-
"global_step":
|
| 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.
|
| 12 |
-
"learning_rate":
|
| 13 |
-
"loss": 1.
|
| 14 |
"step": 10
|
| 15 |
},
|
| 16 |
{
|
| 17 |
-
"epoch": 0.
|
| 18 |
-
"learning_rate":
|
| 19 |
-
"loss": 1.
|
| 20 |
-
"step": 20
|
| 21 |
-
},
|
| 22 |
-
{
|
| 23 |
-
"epoch": 0.96,
|
| 24 |
-
"eval_accuracy": 0.6429384965831435,
|
| 25 |
-
"eval_f1_score": 0.6225332030044981,
|
| 26 |
-
"eval_loss": 1.140669822692871,
|
| 27 |
-
"eval_precision": 0.6600729727071496,
|
| 28 |
-
"eval_runtime": 97.1469,
|
| 29 |
-
"eval_samples_per_second": 18.076,
|
| 30 |
-
"eval_steps_per_second": 0.288,
|
| 31 |
"step": 20
|
| 32 |
},
|
| 33 |
{
|
| 34 |
-
"epoch":
|
| 35 |
-
"learning_rate":
|
| 36 |
-
"loss":
|
| 37 |
"step": 30
|
| 38 |
},
|
| 39 |
{
|
| 40 |
-
"epoch":
|
| 41 |
-
"learning_rate":
|
| 42 |
-
"loss":
|
| 43 |
"step": 40
|
| 44 |
},
|
| 45 |
{
|
| 46 |
-
"epoch":
|
| 47 |
-
"eval_accuracy": 0.
|
| 48 |
-
"eval_f1_score": 0.
|
| 49 |
-
"eval_loss":
|
| 50 |
-
"eval_precision": 0.
|
| 51 |
-
"eval_runtime":
|
| 52 |
-
"eval_samples_per_second":
|
| 53 |
-
"eval_steps_per_second": 0.
|
| 54 |
"step": 41
|
| 55 |
},
|
| 56 |
{
|
| 57 |
-
"epoch":
|
| 58 |
-
"learning_rate":
|
| 59 |
-
"loss": 0.
|
| 60 |
"step": 50
|
| 61 |
},
|
| 62 |
{
|
| 63 |
-
"epoch":
|
| 64 |
-
"learning_rate": 7.
|
| 65 |
-
"loss": 0.
|
| 66 |
"step": 60
|
| 67 |
},
|
| 68 |
{
|
| 69 |
-
"epoch":
|
| 70 |
-
"
|
| 71 |
-
"
|
| 72 |
-
"eval_loss": 0.3265204429626465,
|
| 73 |
-
"eval_precision": 0.8843478014022281,
|
| 74 |
-
"eval_runtime": 94.9107,
|
| 75 |
-
"eval_samples_per_second": 18.502,
|
| 76 |
-
"eval_steps_per_second": 0.295,
|
| 77 |
-
"step": 62
|
| 78 |
-
},
|
| 79 |
-
{
|
| 80 |
-
"epoch": 3.37,
|
| 81 |
-
"learning_rate": 7.222222222222223e-06,
|
| 82 |
-
"loss": 0.2761,
|
| 83 |
"step": 70
|
| 84 |
},
|
| 85 |
{
|
| 86 |
-
"epoch":
|
| 87 |
-
"learning_rate":
|
| 88 |
-
"loss": 0.
|
| 89 |
"step": 80
|
| 90 |
},
|
| 91 |
{
|
| 92 |
-
"epoch":
|
| 93 |
-
"eval_accuracy": 0.
|
| 94 |
-
"eval_f1_score": 0.
|
| 95 |
-
"eval_loss": 0.
|
| 96 |
-
"eval_precision": 0.
|
| 97 |
-
"eval_runtime":
|
| 98 |
-
"eval_samples_per_second": 18.
|
| 99 |
-
"eval_steps_per_second": 0.
|
| 100 |
-
"step":
|
| 101 |
-
},
|
| 102 |
-
{
|
| 103 |
-
"epoch": 4.34,
|
| 104 |
-
"learning_rate": 6.111111111111112e-06,
|
| 105 |
-
"loss": 0.225,
|
| 106 |
-
"step": 90
|
| 107 |
},
|
| 108 |
{
|
| 109 |
-
"epoch":
|
| 110 |
-
"learning_rate":
|
| 111 |
-
"loss": 0.
|
| 112 |
-
"step":
|
| 113 |
},
|
| 114 |
{
|
| 115 |
-
"epoch":
|
| 116 |
-
"
|
| 117 |
-
"
|
| 118 |
-
"
|
| 119 |
-
"eval_precision": 0.899366339703112,
|
| 120 |
-
"eval_runtime": 95.1864,
|
| 121 |
-
"eval_samples_per_second": 18.448,
|
| 122 |
-
"eval_steps_per_second": 0.294,
|
| 123 |
-
"step": 103
|
| 124 |
},
|
| 125 |
{
|
| 126 |
-
"epoch":
|
| 127 |
-
"learning_rate":
|
| 128 |
-
"loss": 0.
|
| 129 |
"step": 110
|
| 130 |
},
|
| 131 |
{
|
| 132 |
-
"epoch":
|
| 133 |
-
"learning_rate":
|
| 134 |
-
"loss": 0.
|
| 135 |
"step": 120
|
| 136 |
},
|
| 137 |
{
|
| 138 |
-
"epoch":
|
| 139 |
-
"eval_accuracy": 0.
|
| 140 |
-
"eval_f1_score": 0.
|
| 141 |
-
"eval_loss": 0.
|
| 142 |
-
"eval_precision": 0.
|
| 143 |
-
"eval_runtime":
|
| 144 |
-
"eval_samples_per_second": 18.
|
| 145 |
-
"eval_steps_per_second": 0.
|
| 146 |
-
"step":
|
| 147 |
},
|
| 148 |
{
|
| 149 |
-
"epoch":
|
| 150 |
-
"learning_rate":
|
| 151 |
-
"loss": 0.
|
| 152 |
"step": 130
|
| 153 |
},
|
| 154 |
{
|
| 155 |
-
"epoch":
|
| 156 |
-
"learning_rate":
|
| 157 |
-
"loss": 0.
|
| 158 |
"step": 140
|
| 159 |
},
|
| 160 |
{
|
| 161 |
-
"epoch":
|
| 162 |
-
"
|
| 163 |
-
"
|
| 164 |
-
"eval_loss": 0.23449133336544037,
|
| 165 |
-
"eval_precision": 0.9129716383829837,
|
| 166 |
-
"eval_runtime": 94.2446,
|
| 167 |
-
"eval_samples_per_second": 18.632,
|
| 168 |
-
"eval_steps_per_second": 0.297,
|
| 169 |
-
"step": 145
|
| 170 |
-
},
|
| 171 |
-
{
|
| 172 |
-
"epoch": 7.23,
|
| 173 |
-
"learning_rate": 2.7777777777777783e-06,
|
| 174 |
-
"loss": 0.1487,
|
| 175 |
"step": 150
|
| 176 |
},
|
| 177 |
{
|
| 178 |
-
"epoch":
|
| 179 |
-
"learning_rate":
|
| 180 |
-
"loss": 0.
|
| 181 |
"step": 160
|
| 182 |
},
|
| 183 |
{
|
| 184 |
-
"epoch":
|
| 185 |
-
"eval_accuracy": 0.
|
| 186 |
-
"eval_f1_score": 0.
|
| 187 |
-
"eval_loss": 0.
|
| 188 |
-
"eval_precision": 0.
|
| 189 |
-
"eval_runtime":
|
| 190 |
-
"eval_samples_per_second": 18.
|
| 191 |
-
"eval_steps_per_second": 0.
|
| 192 |
-
"step":
|
| 193 |
-
},
|
| 194 |
-
{
|
| 195 |
-
"epoch":
|
| 196 |
-
"learning_rate":
|
| 197 |
-
"loss": 0.
|
| 198 |
"step": 170
|
| 199 |
},
|
| 200 |
{
|
| 201 |
-
"epoch":
|
| 202 |
-
"learning_rate":
|
| 203 |
-
"loss": 0.
|
| 204 |
"step": 180
|
| 205 |
},
|
| 206 |
{
|
| 207 |
-
"epoch":
|
| 208 |
-
"
|
| 209 |
-
"
|
| 210 |
-
"eval_loss": 0.19247999787330627,
|
| 211 |
-
"eval_precision": 0.9269521372101541,
|
| 212 |
-
"eval_runtime": 95.6309,
|
| 213 |
-
"eval_samples_per_second": 18.362,
|
| 214 |
-
"eval_steps_per_second": 0.293,
|
| 215 |
-
"step": 186
|
| 216 |
-
},
|
| 217 |
-
{
|
| 218 |
-
"epoch": 9.16,
|
| 219 |
-
"learning_rate": 5.555555555555555e-07,
|
| 220 |
-
"loss": 0.1361,
|
| 221 |
"step": 190
|
| 222 |
},
|
| 223 |
{
|
| 224 |
-
"epoch":
|
| 225 |
-
"learning_rate":
|
| 226 |
-
"loss": 0.
|
| 227 |
"step": 200
|
| 228 |
},
|
| 229 |
{
|
| 230 |
-
"epoch":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 231 |
"eval_accuracy": 0.9219817767653758,
|
| 232 |
-
"eval_f1_score": 0.
|
| 233 |
-
"eval_loss": 0.
|
| 234 |
-
"eval_precision": 0.
|
| 235 |
-
"eval_runtime":
|
| 236 |
-
"eval_samples_per_second": 18.
|
| 237 |
-
"eval_steps_per_second": 0.
|
| 238 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 239 |
},
|
| 240 |
{
|
| 241 |
-
"epoch":
|
| 242 |
-
"step":
|
| 243 |
-
"total_flos":
|
| 244 |
-
"train_loss": 0.
|
| 245 |
-
"train_runtime":
|
| 246 |
-
"train_samples_per_second": 5.
|
| 247 |
-
"train_steps_per_second": 0.
|
| 248 |
}
|
| 249 |
],
|
| 250 |
-
"max_steps":
|
| 251 |
-
"num_train_epochs":
|
| 252 |
-
"total_flos":
|
| 253 |
"trial_name": null,
|
| 254 |
"trial_params": null
|
| 255 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.9396355353075171,
|
| 3 |
+
"best_model_checkpoint": "swin-base-patch4-window7-224-in22k-finetuned-brain-tumor-final/checkpoint-495",
|
| 4 |
+
"epoch": 19.87878787878788,
|
| 5 |
+
"global_step": 820,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
| 9 |
"log_history": [
|
| 10 |
{
|
| 11 |
+
"epoch": 0.24,
|
| 12 |
+
"learning_rate": 1.2195121951219514e-06,
|
| 13 |
+
"loss": 1.4212,
|
| 14 |
"step": 10
|
| 15 |
},
|
| 16 |
{
|
| 17 |
+
"epoch": 0.48,
|
| 18 |
+
"learning_rate": 2.4390243902439027e-06,
|
| 19 |
+
"loss": 1.3801,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 20 |
"step": 20
|
| 21 |
},
|
| 22 |
{
|
| 23 |
+
"epoch": 0.73,
|
| 24 |
+
"learning_rate": 3.6585365853658537e-06,
|
| 25 |
+
"loss": 1.2755,
|
| 26 |
"step": 30
|
| 27 |
},
|
| 28 |
{
|
| 29 |
+
"epoch": 0.97,
|
| 30 |
+
"learning_rate": 4.8780487804878055e-06,
|
| 31 |
+
"loss": 1.1562,
|
| 32 |
"step": 40
|
| 33 |
},
|
| 34 |
{
|
| 35 |
+
"epoch": 0.99,
|
| 36 |
+
"eval_accuracy": 0.6378132118451025,
|
| 37 |
+
"eval_f1_score": 0.6190569285283298,
|
| 38 |
+
"eval_loss": 1.1378333568572998,
|
| 39 |
+
"eval_precision": 0.6536626392431208,
|
| 40 |
+
"eval_runtime": 96.8359,
|
| 41 |
+
"eval_samples_per_second": 18.134,
|
| 42 |
+
"eval_steps_per_second": 0.568,
|
| 43 |
"step": 41
|
| 44 |
},
|
| 45 |
{
|
| 46 |
+
"epoch": 1.21,
|
| 47 |
+
"learning_rate": 6.0975609756097564e-06,
|
| 48 |
+
"loss": 0.9839,
|
| 49 |
"step": 50
|
| 50 |
},
|
| 51 |
{
|
| 52 |
+
"epoch": 1.45,
|
| 53 |
+
"learning_rate": 7.317073170731707e-06,
|
| 54 |
+
"loss": 0.7914,
|
| 55 |
"step": 60
|
| 56 |
},
|
| 57 |
{
|
| 58 |
+
"epoch": 1.7,
|
| 59 |
+
"learning_rate": 8.536585365853658e-06,
|
| 60 |
+
"loss": 0.6245,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 61 |
"step": 70
|
| 62 |
},
|
| 63 |
{
|
| 64 |
+
"epoch": 1.94,
|
| 65 |
+
"learning_rate": 9.756097560975611e-06,
|
| 66 |
+
"loss": 0.4878,
|
| 67 |
"step": 80
|
| 68 |
},
|
| 69 |
{
|
| 70 |
+
"epoch": 1.99,
|
| 71 |
+
"eval_accuracy": 0.7591116173120729,
|
| 72 |
+
"eval_f1_score": 0.7498580587869668,
|
| 73 |
+
"eval_loss": 0.6476529836654663,
|
| 74 |
+
"eval_precision": 0.7873955323748831,
|
| 75 |
+
"eval_runtime": 96.8155,
|
| 76 |
+
"eval_samples_per_second": 18.138,
|
| 77 |
+
"eval_steps_per_second": 0.568,
|
| 78 |
+
"step": 82
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 79 |
},
|
| 80 |
{
|
| 81 |
+
"epoch": 2.18,
|
| 82 |
+
"learning_rate": 9.89159891598916e-06,
|
| 83 |
+
"loss": 0.3834,
|
| 84 |
+
"step": 90
|
| 85 |
},
|
| 86 |
{
|
| 87 |
+
"epoch": 2.42,
|
| 88 |
+
"learning_rate": 9.756097560975611e-06,
|
| 89 |
+
"loss": 0.3288,
|
| 90 |
+
"step": 100
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 91 |
},
|
| 92 |
{
|
| 93 |
+
"epoch": 2.67,
|
| 94 |
+
"learning_rate": 9.620596205962061e-06,
|
| 95 |
+
"loss": 0.3111,
|
| 96 |
"step": 110
|
| 97 |
},
|
| 98 |
{
|
| 99 |
+
"epoch": 2.91,
|
| 100 |
+
"learning_rate": 9.485094850948512e-06,
|
| 101 |
+
"loss": 0.2623,
|
| 102 |
"step": 120
|
| 103 |
},
|
| 104 |
{
|
| 105 |
+
"epoch": 2.98,
|
| 106 |
+
"eval_accuracy": 0.8337129840546698,
|
| 107 |
+
"eval_f1_score": 0.8310652064326258,
|
| 108 |
+
"eval_loss": 0.44103795289993286,
|
| 109 |
+
"eval_precision": 0.8487545531816145,
|
| 110 |
+
"eval_runtime": 95.5234,
|
| 111 |
+
"eval_samples_per_second": 18.383,
|
| 112 |
+
"eval_steps_per_second": 0.576,
|
| 113 |
+
"step": 123
|
| 114 |
},
|
| 115 |
{
|
| 116 |
+
"epoch": 3.15,
|
| 117 |
+
"learning_rate": 9.34959349593496e-06,
|
| 118 |
+
"loss": 0.2449,
|
| 119 |
"step": 130
|
| 120 |
},
|
| 121 |
{
|
| 122 |
+
"epoch": 3.39,
|
| 123 |
+
"learning_rate": 9.21409214092141e-06,
|
| 124 |
+
"loss": 0.2058,
|
| 125 |
"step": 140
|
| 126 |
},
|
| 127 |
{
|
| 128 |
+
"epoch": 3.64,
|
| 129 |
+
"learning_rate": 9.07859078590786e-06,
|
| 130 |
+
"loss": 0.2426,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 131 |
"step": 150
|
| 132 |
},
|
| 133 |
{
|
| 134 |
+
"epoch": 3.88,
|
| 135 |
+
"learning_rate": 8.94308943089431e-06,
|
| 136 |
+
"loss": 0.1985,
|
| 137 |
"step": 160
|
| 138 |
},
|
| 139 |
{
|
| 140 |
+
"epoch": 4.0,
|
| 141 |
+
"eval_accuracy": 0.8143507972665148,
|
| 142 |
+
"eval_f1_score": 0.8114988597034715,
|
| 143 |
+
"eval_loss": 0.465999573469162,
|
| 144 |
+
"eval_precision": 0.8455116716314306,
|
| 145 |
+
"eval_runtime": 95.3707,
|
| 146 |
+
"eval_samples_per_second": 18.412,
|
| 147 |
+
"eval_steps_per_second": 0.577,
|
| 148 |
+
"step": 165
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 4.12,
|
| 152 |
+
"learning_rate": 8.80758807588076e-06,
|
| 153 |
+
"loss": 0.1852,
|
| 154 |
"step": 170
|
| 155 |
},
|
| 156 |
{
|
| 157 |
+
"epoch": 4.36,
|
| 158 |
+
"learning_rate": 8.67208672086721e-06,
|
| 159 |
+
"loss": 0.1738,
|
| 160 |
"step": 180
|
| 161 |
},
|
| 162 |
{
|
| 163 |
+
"epoch": 4.61,
|
| 164 |
+
"learning_rate": 8.536585365853658e-06,
|
| 165 |
+
"loss": 0.1806,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 166 |
"step": 190
|
| 167 |
},
|
| 168 |
{
|
| 169 |
+
"epoch": 4.85,
|
| 170 |
+
"learning_rate": 8.401084010840109e-06,
|
| 171 |
+
"loss": 0.1736,
|
| 172 |
"step": 200
|
| 173 |
},
|
| 174 |
{
|
| 175 |
+
"epoch": 4.99,
|
| 176 |
+
"eval_accuracy": 0.8775626423690205,
|
| 177 |
+
"eval_f1_score": 0.8759706154432891,
|
| 178 |
+
"eval_loss": 0.3229566812515259,
|
| 179 |
+
"eval_precision": 0.8894198873971897,
|
| 180 |
+
"eval_runtime": 96.4712,
|
| 181 |
+
"eval_samples_per_second": 18.202,
|
| 182 |
+
"eval_steps_per_second": 0.57,
|
| 183 |
+
"step": 206
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 5.09,
|
| 187 |
+
"learning_rate": 8.265582655826559e-06,
|
| 188 |
+
"loss": 0.1677,
|
| 189 |
+
"step": 210
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 5.33,
|
| 193 |
+
"learning_rate": 8.130081300813009e-06,
|
| 194 |
+
"loss": 0.1384,
|
| 195 |
+
"step": 220
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 5.58,
|
| 199 |
+
"learning_rate": 7.99457994579946e-06,
|
| 200 |
+
"loss": 0.1319,
|
| 201 |
+
"step": 230
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 5.82,
|
| 205 |
+
"learning_rate": 7.859078590785908e-06,
|
| 206 |
+
"loss": 0.124,
|
| 207 |
+
"step": 240
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 5.99,
|
| 211 |
+
"eval_accuracy": 0.9026195899772209,
|
| 212 |
+
"eval_f1_score": 0.9013627262353661,
|
| 213 |
+
"eval_loss": 0.2684251368045807,
|
| 214 |
+
"eval_precision": 0.9089527019800868,
|
| 215 |
+
"eval_runtime": 94.5477,
|
| 216 |
+
"eval_samples_per_second": 18.573,
|
| 217 |
+
"eval_steps_per_second": 0.582,
|
| 218 |
+
"step": 247
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 6.06,
|
| 222 |
+
"learning_rate": 7.723577235772358e-06,
|
| 223 |
+
"loss": 0.1508,
|
| 224 |
+
"step": 250
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 6.3,
|
| 228 |
+
"learning_rate": 7.5880758807588085e-06,
|
| 229 |
+
"loss": 0.1168,
|
| 230 |
+
"step": 260
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 6.55,
|
| 234 |
+
"learning_rate": 7.452574525745257e-06,
|
| 235 |
+
"loss": 0.1043,
|
| 236 |
+
"step": 270
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 6.79,
|
| 240 |
+
"learning_rate": 7.317073170731707e-06,
|
| 241 |
+
"loss": 0.1278,
|
| 242 |
+
"step": 280
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 6.98,
|
| 246 |
+
"eval_accuracy": 0.9179954441913439,
|
| 247 |
+
"eval_f1_score": 0.9166179163753916,
|
| 248 |
+
"eval_loss": 0.22102278470993042,
|
| 249 |
+
"eval_precision": 0.9210303187193152,
|
| 250 |
+
"eval_runtime": 95.7688,
|
| 251 |
+
"eval_samples_per_second": 18.336,
|
| 252 |
+
"eval_steps_per_second": 0.574,
|
| 253 |
+
"step": 288
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 7.03,
|
| 257 |
+
"learning_rate": 7.181571815718158e-06,
|
| 258 |
+
"loss": 0.1122,
|
| 259 |
+
"step": 290
|
| 260 |
+
},
|
| 261 |
+
{
|
| 262 |
+
"epoch": 7.27,
|
| 263 |
+
"learning_rate": 7.046070460704607e-06,
|
| 264 |
+
"loss": 0.1052,
|
| 265 |
+
"step": 300
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 7.52,
|
| 269 |
+
"learning_rate": 6.910569105691057e-06,
|
| 270 |
+
"loss": 0.0965,
|
| 271 |
+
"step": 310
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 7.76,
|
| 275 |
+
"learning_rate": 6.775067750677508e-06,
|
| 276 |
+
"loss": 0.1072,
|
| 277 |
+
"step": 320
|
| 278 |
+
},
|
| 279 |
+
{
|
| 280 |
+
"epoch": 8.0,
|
| 281 |
+
"learning_rate": 6.639566395663957e-06,
|
| 282 |
+
"loss": 0.0959,
|
| 283 |
+
"step": 330
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 8.0,
|
| 287 |
+
"eval_accuracy": 0.9208428246013668,
|
| 288 |
+
"eval_f1_score": 0.9195432105337242,
|
| 289 |
+
"eval_loss": 0.21511134505271912,
|
| 290 |
+
"eval_precision": 0.9259948741044411,
|
| 291 |
+
"eval_runtime": 94.727,
|
| 292 |
+
"eval_samples_per_second": 18.537,
|
| 293 |
+
"eval_steps_per_second": 0.581,
|
| 294 |
+
"step": 330
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 8.24,
|
| 298 |
+
"learning_rate": 6.504065040650407e-06,
|
| 299 |
+
"loss": 0.087,
|
| 300 |
+
"step": 340
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 8.48,
|
| 304 |
+
"learning_rate": 6.368563685636857e-06,
|
| 305 |
+
"loss": 0.0788,
|
| 306 |
+
"step": 350
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 8.73,
|
| 310 |
+
"learning_rate": 6.233062330623306e-06,
|
| 311 |
+
"loss": 0.0952,
|
| 312 |
+
"step": 360
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 8.97,
|
| 316 |
+
"learning_rate": 6.0975609756097564e-06,
|
| 317 |
+
"loss": 0.0849,
|
| 318 |
+
"step": 370
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 8.99,
|
| 322 |
"eval_accuracy": 0.9219817767653758,
|
| 323 |
+
"eval_f1_score": 0.9205449523633584,
|
| 324 |
+
"eval_loss": 0.21544188261032104,
|
| 325 |
+
"eval_precision": 0.9290889598643586,
|
| 326 |
+
"eval_runtime": 95.0804,
|
| 327 |
+
"eval_samples_per_second": 18.469,
|
| 328 |
+
"eval_steps_per_second": 0.578,
|
| 329 |
+
"step": 371
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 9.21,
|
| 333 |
+
"learning_rate": 5.962059620596207e-06,
|
| 334 |
+
"loss": 0.0954,
|
| 335 |
+
"step": 380
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 9.45,
|
| 339 |
+
"learning_rate": 5.826558265582656e-06,
|
| 340 |
+
"loss": 0.0808,
|
| 341 |
+
"step": 390
|
| 342 |
+
},
|
| 343 |
+
{
|
| 344 |
+
"epoch": 9.7,
|
| 345 |
+
"learning_rate": 5.691056910569106e-06,
|
| 346 |
+
"loss": 0.0703,
|
| 347 |
+
"step": 400
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"epoch": 9.94,
|
| 351 |
+
"learning_rate": 5.555555555555557e-06,
|
| 352 |
+
"loss": 0.0805,
|
| 353 |
+
"step": 410
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 9.99,
|
| 357 |
+
"eval_accuracy": 0.9191343963553531,
|
| 358 |
+
"eval_f1_score": 0.9178865857712233,
|
| 359 |
+
"eval_loss": 0.21121914684772491,
|
| 360 |
+
"eval_precision": 0.9250862844253733,
|
| 361 |
+
"eval_runtime": 94.2987,
|
| 362 |
+
"eval_samples_per_second": 18.622,
|
| 363 |
+
"eval_steps_per_second": 0.583,
|
| 364 |
+
"step": 412
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
"epoch": 10.18,
|
| 368 |
+
"learning_rate": 5.420054200542005e-06,
|
| 369 |
+
"loss": 0.0521,
|
| 370 |
+
"step": 420
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 10.42,
|
| 374 |
+
"learning_rate": 5.2845528455284555e-06,
|
| 375 |
+
"loss": 0.0681,
|
| 376 |
+
"step": 430
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 10.67,
|
| 380 |
+
"learning_rate": 5.149051490514906e-06,
|
| 381 |
+
"loss": 0.0769,
|
| 382 |
+
"step": 440
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 10.91,
|
| 386 |
+
"learning_rate": 5.013550135501355e-06,
|
| 387 |
+
"loss": 0.0682,
|
| 388 |
+
"step": 450
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 10.98,
|
| 392 |
+
"eval_accuracy": 0.9384965831435079,
|
| 393 |
+
"eval_f1_score": 0.9369393287065592,
|
| 394 |
+
"eval_loss": 0.15628309547901154,
|
| 395 |
+
"eval_precision": 0.9402176891312171,
|
| 396 |
+
"eval_runtime": 96.028,
|
| 397 |
+
"eval_samples_per_second": 18.286,
|
| 398 |
+
"eval_steps_per_second": 0.573,
|
| 399 |
+
"step": 453
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 11.15,
|
| 403 |
+
"learning_rate": 4.8780487804878055e-06,
|
| 404 |
+
"loss": 0.0668,
|
| 405 |
+
"step": 460
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 11.39,
|
| 409 |
+
"learning_rate": 4.742547425474256e-06,
|
| 410 |
+
"loss": 0.0657,
|
| 411 |
+
"step": 470
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 11.64,
|
| 415 |
+
"learning_rate": 4.607046070460705e-06,
|
| 416 |
+
"loss": 0.0703,
|
| 417 |
+
"step": 480
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 11.88,
|
| 421 |
+
"learning_rate": 4.471544715447155e-06,
|
| 422 |
+
"loss": 0.0624,
|
| 423 |
+
"step": 490
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 12.0,
|
| 427 |
+
"eval_accuracy": 0.9396355353075171,
|
| 428 |
+
"eval_f1_score": 0.9384678994386635,
|
| 429 |
+
"eval_loss": 0.1576806604862213,
|
| 430 |
+
"eval_precision": 0.9408448811333167,
|
| 431 |
+
"eval_runtime": 95.9898,
|
| 432 |
+
"eval_samples_per_second": 18.294,
|
| 433 |
+
"eval_steps_per_second": 0.573,
|
| 434 |
+
"step": 495
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 12.12,
|
| 438 |
+
"learning_rate": 4.336043360433605e-06,
|
| 439 |
+
"loss": 0.0531,
|
| 440 |
+
"step": 500
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 12.36,
|
| 444 |
+
"learning_rate": 4.200542005420054e-06,
|
| 445 |
+
"loss": 0.0579,
|
| 446 |
+
"step": 510
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 12.61,
|
| 450 |
+
"learning_rate": 4.0650406504065046e-06,
|
| 451 |
+
"loss": 0.0657,
|
| 452 |
+
"step": 520
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 12.85,
|
| 456 |
+
"learning_rate": 3.929539295392954e-06,
|
| 457 |
+
"loss": 0.0415,
|
| 458 |
+
"step": 530
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 12.99,
|
| 462 |
+
"eval_accuracy": 0.9305239179954442,
|
| 463 |
+
"eval_f1_score": 0.9294348170687547,
|
| 464 |
+
"eval_loss": 0.1836157888174057,
|
| 465 |
+
"eval_precision": 0.9332309174336554,
|
| 466 |
+
"eval_runtime": 99.8745,
|
| 467 |
+
"eval_samples_per_second": 17.582,
|
| 468 |
+
"eval_steps_per_second": 0.551,
|
| 469 |
+
"step": 536
|
| 470 |
+
},
|
| 471 |
+
{
|
| 472 |
+
"epoch": 13.09,
|
| 473 |
+
"learning_rate": 3.7940379403794043e-06,
|
| 474 |
+
"loss": 0.0569,
|
| 475 |
+
"step": 540
|
| 476 |
+
},
|
| 477 |
+
{
|
| 478 |
+
"epoch": 13.33,
|
| 479 |
+
"learning_rate": 3.6585365853658537e-06,
|
| 480 |
+
"loss": 0.0707,
|
| 481 |
+
"step": 550
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 13.58,
|
| 485 |
+
"learning_rate": 3.5230352303523035e-06,
|
| 486 |
+
"loss": 0.0424,
|
| 487 |
+
"step": 560
|
| 488 |
+
},
|
| 489 |
+
{
|
| 490 |
+
"epoch": 13.82,
|
| 491 |
+
"learning_rate": 3.387533875338754e-06,
|
| 492 |
+
"loss": 0.0465,
|
| 493 |
+
"step": 570
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 13.99,
|
| 497 |
+
"eval_accuracy": 0.9202733485193622,
|
| 498 |
+
"eval_f1_score": 0.9191914508633344,
|
| 499 |
+
"eval_loss": 0.2144739031791687,
|
| 500 |
+
"eval_precision": 0.9251966092567651,
|
| 501 |
+
"eval_runtime": 96.9873,
|
| 502 |
+
"eval_samples_per_second": 18.105,
|
| 503 |
+
"eval_steps_per_second": 0.567,
|
| 504 |
+
"step": 577
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 14.06,
|
| 508 |
+
"learning_rate": 3.2520325203252037e-06,
|
| 509 |
+
"loss": 0.0483,
|
| 510 |
+
"step": 580
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"epoch": 14.3,
|
| 514 |
+
"learning_rate": 3.116531165311653e-06,
|
| 515 |
+
"loss": 0.0432,
|
| 516 |
+
"step": 590
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"epoch": 14.55,
|
| 520 |
+
"learning_rate": 2.9810298102981034e-06,
|
| 521 |
+
"loss": 0.046,
|
| 522 |
+
"step": 600
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 14.79,
|
| 526 |
+
"learning_rate": 2.845528455284553e-06,
|
| 527 |
+
"loss": 0.056,
|
| 528 |
+
"step": 610
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 14.98,
|
| 532 |
+
"eval_accuracy": 0.9339407744874715,
|
| 533 |
+
"eval_f1_score": 0.9324607544046006,
|
| 534 |
+
"eval_loss": 0.17098096013069153,
|
| 535 |
+
"eval_precision": 0.9369044224464911,
|
| 536 |
+
"eval_runtime": 96.6806,
|
| 537 |
+
"eval_samples_per_second": 18.163,
|
| 538 |
+
"eval_steps_per_second": 0.569,
|
| 539 |
+
"step": 618
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 15.03,
|
| 543 |
+
"learning_rate": 2.7100271002710026e-06,
|
| 544 |
+
"loss": 0.0447,
|
| 545 |
+
"step": 620
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 15.27,
|
| 549 |
+
"learning_rate": 2.574525745257453e-06,
|
| 550 |
+
"loss": 0.0441,
|
| 551 |
+
"step": 630
|
| 552 |
+
},
|
| 553 |
+
{
|
| 554 |
+
"epoch": 15.52,
|
| 555 |
+
"learning_rate": 2.4390243902439027e-06,
|
| 556 |
+
"loss": 0.0515,
|
| 557 |
+
"step": 640
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 15.76,
|
| 561 |
+
"learning_rate": 2.3035230352303526e-06,
|
| 562 |
+
"loss": 0.0435,
|
| 563 |
+
"step": 650
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 16.0,
|
| 567 |
+
"learning_rate": 2.1680216802168024e-06,
|
| 568 |
+
"loss": 0.0545,
|
| 569 |
+
"step": 660
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 16.0,
|
| 573 |
+
"eval_accuracy": 0.9248291571753986,
|
| 574 |
+
"eval_f1_score": 0.9235589091910614,
|
| 575 |
+
"eval_loss": 0.20944343507289886,
|
| 576 |
+
"eval_precision": 0.929753616084827,
|
| 577 |
+
"eval_runtime": 97.9348,
|
| 578 |
+
"eval_samples_per_second": 17.93,
|
| 579 |
+
"eval_steps_per_second": 0.562,
|
| 580 |
+
"step": 660
|
| 581 |
+
},
|
| 582 |
+
{
|
| 583 |
+
"epoch": 16.24,
|
| 584 |
+
"learning_rate": 2.0325203252032523e-06,
|
| 585 |
+
"loss": 0.0477,
|
| 586 |
+
"step": 670
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 16.48,
|
| 590 |
+
"learning_rate": 1.8970189701897021e-06,
|
| 591 |
+
"loss": 0.0424,
|
| 592 |
+
"step": 680
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 16.73,
|
| 596 |
+
"learning_rate": 1.7615176151761518e-06,
|
| 597 |
+
"loss": 0.0377,
|
| 598 |
+
"step": 690
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 16.97,
|
| 602 |
+
"learning_rate": 1.6260162601626018e-06,
|
| 603 |
+
"loss": 0.0591,
|
| 604 |
+
"step": 700
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 16.99,
|
| 608 |
+
"eval_accuracy": 0.9316628701594533,
|
| 609 |
+
"eval_f1_score": 0.930292082850388,
|
| 610 |
+
"eval_loss": 0.1752157062292099,
|
| 611 |
+
"eval_precision": 0.934052681687829,
|
| 612 |
+
"eval_runtime": 98.3671,
|
| 613 |
+
"eval_samples_per_second": 17.852,
|
| 614 |
+
"eval_steps_per_second": 0.559,
|
| 615 |
+
"step": 701
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 17.21,
|
| 619 |
+
"learning_rate": 1.4905149051490517e-06,
|
| 620 |
+
"loss": 0.0425,
|
| 621 |
+
"step": 710
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 17.45,
|
| 625 |
+
"learning_rate": 1.3550135501355013e-06,
|
| 626 |
+
"loss": 0.0394,
|
| 627 |
+
"step": 720
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 17.7,
|
| 631 |
+
"learning_rate": 1.2195121951219514e-06,
|
| 632 |
+
"loss": 0.0323,
|
| 633 |
+
"step": 730
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 17.94,
|
| 637 |
+
"learning_rate": 1.0840108401084012e-06,
|
| 638 |
+
"loss": 0.0512,
|
| 639 |
+
"step": 740
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 17.99,
|
| 643 |
+
"eval_accuracy": 0.9310933940774487,
|
| 644 |
+
"eval_f1_score": 0.9297072356118401,
|
| 645 |
+
"eval_loss": 0.17810992896556854,
|
| 646 |
+
"eval_precision": 0.9341920124235589,
|
| 647 |
+
"eval_runtime": 99.187,
|
| 648 |
+
"eval_samples_per_second": 17.704,
|
| 649 |
+
"eval_steps_per_second": 0.555,
|
| 650 |
+
"step": 742
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 18.18,
|
| 654 |
+
"learning_rate": 9.485094850948511e-07,
|
| 655 |
+
"loss": 0.0278,
|
| 656 |
+
"step": 750
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"epoch": 18.42,
|
| 660 |
+
"learning_rate": 8.130081300813009e-07,
|
| 661 |
+
"loss": 0.0338,
|
| 662 |
+
"step": 760
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 18.67,
|
| 666 |
+
"learning_rate": 6.775067750677507e-07,
|
| 667 |
+
"loss": 0.0467,
|
| 668 |
+
"step": 770
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 18.91,
|
| 672 |
+
"learning_rate": 5.420054200542006e-07,
|
| 673 |
+
"loss": 0.0424,
|
| 674 |
+
"step": 780
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 18.98,
|
| 678 |
+
"eval_accuracy": 0.9305239179954442,
|
| 679 |
+
"eval_f1_score": 0.9292526869769537,
|
| 680 |
+
"eval_loss": 0.18729418516159058,
|
| 681 |
+
"eval_precision": 0.9338045676207426,
|
| 682 |
+
"eval_runtime": 97.3576,
|
| 683 |
+
"eval_samples_per_second": 18.037,
|
| 684 |
+
"eval_steps_per_second": 0.565,
|
| 685 |
+
"step": 783
|
| 686 |
+
},
|
| 687 |
+
{
|
| 688 |
+
"epoch": 19.15,
|
| 689 |
+
"learning_rate": 4.0650406504065046e-07,
|
| 690 |
+
"loss": 0.0333,
|
| 691 |
+
"step": 790
|
| 692 |
+
},
|
| 693 |
+
{
|
| 694 |
+
"epoch": 19.39,
|
| 695 |
+
"learning_rate": 2.710027100271003e-07,
|
| 696 |
+
"loss": 0.039,
|
| 697 |
+
"step": 800
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 19.64,
|
| 701 |
+
"learning_rate": 1.3550135501355015e-07,
|
| 702 |
+
"loss": 0.0344,
|
| 703 |
+
"step": 810
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 19.88,
|
| 707 |
+
"learning_rate": 0.0,
|
| 708 |
+
"loss": 0.0438,
|
| 709 |
+
"step": 820
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 19.88,
|
| 713 |
+
"eval_accuracy": 0.9265375854214123,
|
| 714 |
+
"eval_f1_score": 0.9252094972625854,
|
| 715 |
+
"eval_loss": 0.19554641842842102,
|
| 716 |
+
"eval_precision": 0.9307429809120586,
|
| 717 |
+
"eval_runtime": 100.1651,
|
| 718 |
+
"eval_samples_per_second": 17.531,
|
| 719 |
+
"eval_steps_per_second": 0.549,
|
| 720 |
+
"step": 820
|
| 721 |
},
|
| 722 |
{
|
| 723 |
+
"epoch": 19.88,
|
| 724 |
+
"step": 820,
|
| 725 |
+
"total_flos": 8.203992042011222e+18,
|
| 726 |
+
"train_loss": 0.18675074555524965,
|
| 727 |
+
"train_runtime": 20102.5048,
|
| 728 |
+
"train_samples_per_second": 5.24,
|
| 729 |
+
"train_steps_per_second": 0.041
|
| 730 |
}
|
| 731 |
],
|
| 732 |
+
"max_steps": 820,
|
| 733 |
+
"num_train_epochs": 20,
|
| 734 |
+
"total_flos": 8.203992042011222e+18,
|
| 735 |
"trial_name": null,
|
| 736 |
"trial_params": null
|
| 737 |
}
|