Commit
•
c71d3b8
1
Parent(s):
a622e1b
Upload 11 files
Browse files- optimizer.pt +1 -1
- pytorch_model.bin +1 -1
- rng_state.pth +1 -1
- scheduler.pt +1 -1
- tokenizer.json +16 -2
- trainer_state.json +446 -188
- training_args.bin +1 -1
optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 884664069
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9d418320f9ee3f1dffca7832aecec7df759a80dada05861fc0afea3bec652bb9
|
| 3 |
size 884664069
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 442316593
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c52f18f3b87150eef81fabf3e5bbf077d3a640da74cebfb56afd87e7f4cc1786
|
| 3 |
size 442316593
|
rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14575
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6d5aca11c97f3a24aee2fd3a0e70898259f58b12fed8db72231afb4eb7278d66
|
| 3 |
size 14575
|
scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 627
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bfda1b9f02fbd3afeeb0a45c45d91917b2d9331eeaabde2bd2a0199143beeebf
|
| 3 |
size 627
|
tokenizer.json
CHANGED
|
@@ -1,7 +1,21 @@
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
-
"truncation":
|
| 4 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
"added_tokens": [
|
| 6 |
{
|
| 7 |
"id": 0,
|
|
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
+
"truncation": {
|
| 4 |
+
"direction": "Right",
|
| 5 |
+
"max_length": 384,
|
| 6 |
+
"strategy": "LongestFirst",
|
| 7 |
+
"stride": 0
|
| 8 |
+
},
|
| 9 |
+
"padding": {
|
| 10 |
+
"strategy": {
|
| 11 |
+
"Fixed": 384
|
| 12 |
+
},
|
| 13 |
+
"direction": "Right",
|
| 14 |
+
"pad_to_multiple_of": null,
|
| 15 |
+
"pad_id": 0,
|
| 16 |
+
"pad_type_id": 0,
|
| 17 |
+
"pad_token": "[PAD]"
|
| 18 |
+
},
|
| 19 |
"added_tokens": [
|
| 20 |
{
|
| 21 |
"id": 0,
|
trainer_state.json
CHANGED
|
@@ -1,337 +1,595 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
-
"best_model_checkpoint": "./indobertweet-review-rating/checkpoint-
|
| 4 |
"epoch": 6.0,
|
| 5 |
"eval_steps": 500,
|
| 6 |
-
"global_step":
|
| 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.
|
| 13 |
-
"learning_rate": 1.
|
| 14 |
-
"loss": 0.
|
| 15 |
"step": 500
|
| 16 |
},
|
| 17 |
{
|
| 18 |
-
"epoch": 0.
|
| 19 |
-
"learning_rate": 1.
|
| 20 |
-
"loss": 0.
|
| 21 |
"step": 1000
|
| 22 |
},
|
| 23 |
{
|
| 24 |
-
"epoch": 0.
|
| 25 |
-
"learning_rate": 1.
|
| 26 |
-
"loss": 0.
|
| 27 |
"step": 1500
|
| 28 |
},
|
| 29 |
{
|
| 30 |
-
"epoch": 0.
|
| 31 |
-
"learning_rate": 1.
|
| 32 |
-
"loss": 0.
|
| 33 |
"step": 2000
|
| 34 |
},
|
| 35 |
{
|
| 36 |
-
"epoch": 0.
|
| 37 |
-
"learning_rate": 1.
|
| 38 |
-
"loss": 0.
|
| 39 |
"step": 2500
|
| 40 |
},
|
| 41 |
{
|
| 42 |
-
"epoch": 0.
|
| 43 |
-
"learning_rate": 1.
|
| 44 |
-
"loss": 0.
|
| 45 |
"step": 3000
|
| 46 |
},
|
| 47 |
{
|
| 48 |
-
"epoch": 0.
|
| 49 |
-
"learning_rate": 1.
|
| 50 |
-
"loss": 0.
|
| 51 |
"step": 3500
|
| 52 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 53 |
{
|
| 54 |
"epoch": 1.0,
|
| 55 |
-
"eval_akurasi": 0.
|
| 56 |
-
"eval_f1": 0.
|
| 57 |
-
"eval_loss": 0.
|
| 58 |
-
"eval_roc_auc": 0.
|
| 59 |
-
"eval_runtime":
|
| 60 |
-
"eval_samples_per_second":
|
| 61 |
-
"eval_steps_per_second": 7.
|
| 62 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 63 |
},
|
| 64 |
{
|
| 65 |
"epoch": 1.12,
|
| 66 |
-
"learning_rate": 1.
|
| 67 |
-
"loss": 0.
|
| 68 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 69 |
},
|
| 70 |
{
|
| 71 |
"epoch": 1.26,
|
| 72 |
-
"learning_rate": 1.
|
| 73 |
-
"loss": 0.
|
| 74 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 75 |
},
|
| 76 |
{
|
| 77 |
"epoch": 1.4,
|
| 78 |
-
"learning_rate": 1.
|
| 79 |
-
"loss": 0.
|
| 80 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 81 |
},
|
| 82 |
{
|
| 83 |
"epoch": 1.54,
|
| 84 |
-
"learning_rate": 1.
|
| 85 |
-
"loss": 0.
|
| 86 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 87 |
},
|
| 88 |
{
|
| 89 |
"epoch": 1.68,
|
| 90 |
-
"learning_rate": 1.
|
| 91 |
-
"loss": 0.
|
| 92 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 93 |
},
|
| 94 |
{
|
| 95 |
"epoch": 1.82,
|
| 96 |
-
"learning_rate": 1.
|
| 97 |
-
"loss": 0.
|
| 98 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 99 |
},
|
| 100 |
{
|
| 101 |
"epoch": 1.96,
|
| 102 |
-
"learning_rate": 1.
|
| 103 |
-
"loss": 0.
|
| 104 |
-
"step":
|
| 105 |
},
|
| 106 |
{
|
| 107 |
"epoch": 2.0,
|
| 108 |
-
"eval_akurasi": 0.
|
| 109 |
-
"eval_f1": 0.
|
| 110 |
-
"eval_loss": 0.
|
| 111 |
-
"eval_roc_auc": 0.
|
| 112 |
-
"eval_runtime":
|
| 113 |
-
"eval_samples_per_second":
|
| 114 |
-
"eval_steps_per_second": 7.
|
| 115 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 116 |
},
|
| 117 |
{
|
| 118 |
"epoch": 2.1,
|
| 119 |
-
"learning_rate": 1.
|
| 120 |
-
"loss": 0.
|
| 121 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 122 |
},
|
| 123 |
{
|
| 124 |
"epoch": 2.24,
|
| 125 |
-
"learning_rate": 1.
|
| 126 |
-
"loss": 0.
|
| 127 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 128 |
},
|
| 129 |
{
|
| 130 |
"epoch": 2.38,
|
| 131 |
-
"learning_rate": 1.
|
| 132 |
-
"loss": 0.
|
| 133 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 134 |
},
|
| 135 |
{
|
| 136 |
"epoch": 2.52,
|
| 137 |
-
"learning_rate": 1.
|
| 138 |
-
"loss": 0.
|
| 139 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 140 |
},
|
| 141 |
{
|
| 142 |
"epoch": 2.66,
|
| 143 |
-
"learning_rate": 1.
|
| 144 |
-
"loss": 0.
|
| 145 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 146 |
},
|
| 147 |
{
|
| 148 |
"epoch": 2.8,
|
| 149 |
-
"learning_rate": 1.
|
| 150 |
-
"loss": 0.
|
| 151 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 152 |
},
|
| 153 |
{
|
| 154 |
"epoch": 2.94,
|
| 155 |
-
"learning_rate": 1.
|
| 156 |
-
"loss": 0.
|
| 157 |
-
"step":
|
| 158 |
},
|
| 159 |
{
|
| 160 |
"epoch": 3.0,
|
| 161 |
-
"eval_akurasi": 0.
|
| 162 |
-
"eval_f1": 0.
|
| 163 |
-
"eval_loss": 0.
|
| 164 |
-
"eval_roc_auc": 0.
|
| 165 |
-
"eval_runtime":
|
| 166 |
-
"eval_samples_per_second":
|
| 167 |
-
"eval_steps_per_second": 7.
|
| 168 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 169 |
},
|
| 170 |
{
|
| 171 |
"epoch": 3.08,
|
| 172 |
-
"learning_rate": 1.
|
| 173 |
-
"loss": 0.
|
| 174 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 175 |
},
|
| 176 |
{
|
| 177 |
"epoch": 3.22,
|
| 178 |
-
"learning_rate": 1.
|
| 179 |
-
"loss": 0.
|
| 180 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 181 |
},
|
| 182 |
{
|
| 183 |
"epoch": 3.36,
|
| 184 |
-
"learning_rate": 1.
|
| 185 |
-
"loss": 0.
|
| 186 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 187 |
},
|
| 188 |
{
|
| 189 |
"epoch": 3.5,
|
| 190 |
-
"learning_rate": 1.
|
| 191 |
-
"loss": 0.
|
| 192 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 193 |
},
|
| 194 |
{
|
| 195 |
"epoch": 3.64,
|
| 196 |
-
"learning_rate": 1.
|
| 197 |
-
"loss": 0.
|
| 198 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 199 |
},
|
| 200 |
{
|
| 201 |
"epoch": 3.78,
|
| 202 |
-
"learning_rate": 1.
|
| 203 |
-
"loss": 0.
|
| 204 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 205 |
},
|
| 206 |
{
|
| 207 |
"epoch": 3.92,
|
| 208 |
-
"learning_rate": 1.
|
| 209 |
-
"loss": 0.
|
| 210 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 211 |
},
|
| 212 |
{
|
| 213 |
"epoch": 4.0,
|
| 214 |
-
"eval_akurasi": 0.
|
| 215 |
-
"eval_f1": 0.
|
| 216 |
-
"eval_loss": 0.
|
| 217 |
-
"eval_roc_auc": 0.
|
| 218 |
-
"eval_runtime":
|
| 219 |
-
"eval_samples_per_second":
|
| 220 |
-
"eval_steps_per_second": 7.
|
| 221 |
-
"step":
|
| 222 |
},
|
| 223 |
{
|
| 224 |
"epoch": 4.06,
|
| 225 |
-
"learning_rate":
|
| 226 |
-
"loss": 0.
|
| 227 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 228 |
},
|
| 229 |
{
|
| 230 |
"epoch": 4.2,
|
| 231 |
-
"learning_rate":
|
| 232 |
-
"loss": 0.
|
| 233 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 234 |
},
|
| 235 |
{
|
| 236 |
"epoch": 4.34,
|
| 237 |
-
"learning_rate":
|
| 238 |
-
"loss": 0.
|
| 239 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 240 |
},
|
| 241 |
{
|
| 242 |
"epoch": 4.48,
|
| 243 |
-
"learning_rate":
|
| 244 |
-
"loss": 0.
|
| 245 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 246 |
},
|
| 247 |
{
|
| 248 |
"epoch": 4.62,
|
| 249 |
-
"learning_rate":
|
| 250 |
-
"loss": 0.
|
| 251 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 252 |
},
|
| 253 |
{
|
| 254 |
"epoch": 4.76,
|
| 255 |
-
"learning_rate":
|
| 256 |
-
"loss": 0.
|
| 257 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 258 |
},
|
| 259 |
{
|
| 260 |
"epoch": 4.9,
|
| 261 |
-
"learning_rate":
|
| 262 |
-
"loss": 0.
|
| 263 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 264 |
},
|
| 265 |
{
|
| 266 |
"epoch": 5.0,
|
| 267 |
-
"eval_akurasi": 0.
|
| 268 |
-
"eval_f1": 0.
|
| 269 |
-
"eval_loss": 0.
|
| 270 |
-
"eval_roc_auc": 0.
|
| 271 |
-
"eval_runtime":
|
| 272 |
-
"eval_samples_per_second":
|
| 273 |
-
"eval_steps_per_second": 7.
|
| 274 |
-
"step":
|
| 275 |
-
},
|
| 276 |
-
{
|
| 277 |
-
"epoch": 5.03,
|
| 278 |
-
"learning_rate": 1.3286713286713288e-05,
|
| 279 |
-
"loss": 0.2364,
|
| 280 |
-
"step": 18000
|
| 281 |
},
|
| 282 |
{
|
| 283 |
-
"epoch": 5.
|
| 284 |
-
"learning_rate":
|
| 285 |
-
"loss": 0.
|
| 286 |
-
"step":
|
| 287 |
},
|
| 288 |
{
|
| 289 |
-
"epoch": 5.
|
| 290 |
-
"learning_rate":
|
| 291 |
-
"loss": 0.
|
| 292 |
-
"step":
|
| 293 |
},
|
| 294 |
{
|
| 295 |
-
"epoch": 5.
|
| 296 |
-
"learning_rate":
|
| 297 |
-
"loss": 0.
|
| 298 |
-
"step":
|
| 299 |
},
|
| 300 |
{
|
| 301 |
-
"epoch": 5.
|
| 302 |
-
"learning_rate":
|
| 303 |
-
"loss": 0.
|
| 304 |
-
"step":
|
| 305 |
},
|
| 306 |
{
|
| 307 |
-
"epoch": 5.
|
| 308 |
-
"learning_rate":
|
| 309 |
-
"loss": 0.
|
| 310 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 311 |
},
|
| 312 |
{
|
| 313 |
"epoch": 5.87,
|
| 314 |
-
"learning_rate":
|
| 315 |
-
"loss": 0.
|
| 316 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 317 |
},
|
| 318 |
{
|
| 319 |
"epoch": 6.0,
|
| 320 |
-
"eval_akurasi": 0.
|
| 321 |
-
"eval_f1": 0.
|
| 322 |
-
"eval_loss": 0.
|
| 323 |
-
"eval_roc_auc": 0.
|
| 324 |
-
"eval_runtime":
|
| 325 |
-
"eval_samples_per_second":
|
| 326 |
-
"eval_steps_per_second": 7.
|
| 327 |
-
"step":
|
| 328 |
}
|
| 329 |
],
|
| 330 |
"logging_steps": 500,
|
| 331 |
-
"max_steps":
|
| 332 |
-
"num_train_epochs":
|
| 333 |
"save_steps": 500,
|
| 334 |
-
"total_flos":
|
| 335 |
"trial_name": null,
|
| 336 |
"trial_params": null
|
| 337 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.49651709628372404,
|
| 3 |
+
"best_model_checkpoint": "./indobertweet-review-rating/checkpoint-28596",
|
| 4 |
"epoch": 6.0,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 42894,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
+
"epoch": 0.07,
|
| 13 |
+
"learning_rate": 1.9825150370681216e-05,
|
| 14 |
+
"loss": 0.43,
|
| 15 |
"step": 500
|
| 16 |
},
|
| 17 |
{
|
| 18 |
+
"epoch": 0.14,
|
| 19 |
+
"learning_rate": 1.965030074136243e-05,
|
| 20 |
+
"loss": 0.3942,
|
| 21 |
"step": 1000
|
| 22 |
},
|
| 23 |
{
|
| 24 |
+
"epoch": 0.21,
|
| 25 |
+
"learning_rate": 1.9475451112043644e-05,
|
| 26 |
+
"loss": 0.3869,
|
| 27 |
"step": 1500
|
| 28 |
},
|
| 29 |
{
|
| 30 |
+
"epoch": 0.28,
|
| 31 |
+
"learning_rate": 1.9300601482724858e-05,
|
| 32 |
+
"loss": 0.389,
|
| 33 |
"step": 2000
|
| 34 |
},
|
| 35 |
{
|
| 36 |
+
"epoch": 0.35,
|
| 37 |
+
"learning_rate": 1.9125751853406072e-05,
|
| 38 |
+
"loss": 0.3822,
|
| 39 |
"step": 2500
|
| 40 |
},
|
| 41 |
{
|
| 42 |
+
"epoch": 0.42,
|
| 43 |
+
"learning_rate": 1.8950902224087286e-05,
|
| 44 |
+
"loss": 0.3766,
|
| 45 |
"step": 3000
|
| 46 |
},
|
| 47 |
{
|
| 48 |
+
"epoch": 0.49,
|
| 49 |
+
"learning_rate": 1.87760525947685e-05,
|
| 50 |
+
"loss": 0.382,
|
| 51 |
"step": 3500
|
| 52 |
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.56,
|
| 55 |
+
"learning_rate": 1.8601202965449715e-05,
|
| 56 |
+
"loss": 0.3849,
|
| 57 |
+
"step": 4000
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.63,
|
| 61 |
+
"learning_rate": 1.842635333613093e-05,
|
| 62 |
+
"loss": 0.3761,
|
| 63 |
+
"step": 4500
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.7,
|
| 67 |
+
"learning_rate": 1.8251503706812143e-05,
|
| 68 |
+
"loss": 0.376,
|
| 69 |
+
"step": 5000
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.77,
|
| 73 |
+
"learning_rate": 1.8076654077493357e-05,
|
| 74 |
+
"loss": 0.3789,
|
| 75 |
+
"step": 5500
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.84,
|
| 79 |
+
"learning_rate": 1.790180444817457e-05,
|
| 80 |
+
"loss": 0.3677,
|
| 81 |
+
"step": 6000
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.91,
|
| 85 |
+
"learning_rate": 1.7726954818855785e-05,
|
| 86 |
+
"loss": 0.3728,
|
| 87 |
+
"step": 6500
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.98,
|
| 91 |
+
"learning_rate": 1.7552105189537e-05,
|
| 92 |
+
"loss": 0.3748,
|
| 93 |
+
"step": 7000
|
| 94 |
+
},
|
| 95 |
{
|
| 96 |
"epoch": 1.0,
|
| 97 |
+
"eval_akurasi": 0.3444364303980067,
|
| 98 |
+
"eval_f1": 0.4382533261041832,
|
| 99 |
+
"eval_loss": 0.37478938698768616,
|
| 100 |
+
"eval_roc_auc": 0.6437938495836338,
|
| 101 |
+
"eval_runtime": 259.2098,
|
| 102 |
+
"eval_samples_per_second": 58.837,
|
| 103 |
+
"eval_steps_per_second": 7.357,
|
| 104 |
+
"step": 7149
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 1.05,
|
| 108 |
+
"learning_rate": 1.7377255560218214e-05,
|
| 109 |
+
"loss": 0.356,
|
| 110 |
+
"step": 7500
|
| 111 |
},
|
| 112 |
{
|
| 113 |
"epoch": 1.12,
|
| 114 |
+
"learning_rate": 1.7202405930899428e-05,
|
| 115 |
+
"loss": 0.3519,
|
| 116 |
+
"step": 8000
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 1.19,
|
| 120 |
+
"learning_rate": 1.7027556301580642e-05,
|
| 121 |
+
"loss": 0.3475,
|
| 122 |
+
"step": 8500
|
| 123 |
},
|
| 124 |
{
|
| 125 |
"epoch": 1.26,
|
| 126 |
+
"learning_rate": 1.6852706672261856e-05,
|
| 127 |
+
"loss": 0.3497,
|
| 128 |
+
"step": 9000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 1.33,
|
| 132 |
+
"learning_rate": 1.667785704294307e-05,
|
| 133 |
+
"loss": 0.3467,
|
| 134 |
+
"step": 9500
|
| 135 |
},
|
| 136 |
{
|
| 137 |
"epoch": 1.4,
|
| 138 |
+
"learning_rate": 1.6503007413624284e-05,
|
| 139 |
+
"loss": 0.3518,
|
| 140 |
+
"step": 10000
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 1.47,
|
| 144 |
+
"learning_rate": 1.63281577843055e-05,
|
| 145 |
+
"loss": 0.345,
|
| 146 |
+
"step": 10500
|
| 147 |
},
|
| 148 |
{
|
| 149 |
"epoch": 1.54,
|
| 150 |
+
"learning_rate": 1.6153308154986713e-05,
|
| 151 |
+
"loss": 0.3461,
|
| 152 |
+
"step": 11000
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 1.61,
|
| 156 |
+
"learning_rate": 1.5978458525667927e-05,
|
| 157 |
+
"loss": 0.3439,
|
| 158 |
+
"step": 11500
|
| 159 |
},
|
| 160 |
{
|
| 161 |
"epoch": 1.68,
|
| 162 |
+
"learning_rate": 1.580360889634914e-05,
|
| 163 |
+
"loss": 0.3465,
|
| 164 |
+
"step": 12000
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 1.75,
|
| 168 |
+
"learning_rate": 1.5628759267030355e-05,
|
| 169 |
+
"loss": 0.3478,
|
| 170 |
+
"step": 12500
|
| 171 |
},
|
| 172 |
{
|
| 173 |
"epoch": 1.82,
|
| 174 |
+
"learning_rate": 1.545390963771157e-05,
|
| 175 |
+
"loss": 0.3393,
|
| 176 |
+
"step": 13000
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 1.89,
|
| 180 |
+
"learning_rate": 1.5279060008392783e-05,
|
| 181 |
+
"loss": 0.3432,
|
| 182 |
+
"step": 13500
|
| 183 |
},
|
| 184 |
{
|
| 185 |
"epoch": 1.96,
|
| 186 |
+
"learning_rate": 1.5104210379073997e-05,
|
| 187 |
+
"loss": 0.3463,
|
| 188 |
+
"step": 14000
|
| 189 |
},
|
| 190 |
{
|
| 191 |
"epoch": 2.0,
|
| 192 |
+
"eval_akurasi": 0.38469608550259,
|
| 193 |
+
"eval_f1": 0.46908843863645444,
|
| 194 |
+
"eval_loss": 0.36731091141700745,
|
| 195 |
+
"eval_roc_auc": 0.6604239066290736,
|
| 196 |
+
"eval_runtime": 259.0823,
|
| 197 |
+
"eval_samples_per_second": 58.865,
|
| 198 |
+
"eval_steps_per_second": 7.361,
|
| 199 |
+
"step": 14298
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 2.03,
|
| 203 |
+
"learning_rate": 1.492936074975521e-05,
|
| 204 |
+
"loss": 0.3333,
|
| 205 |
+
"step": 14500
|
| 206 |
},
|
| 207 |
{
|
| 208 |
"epoch": 2.1,
|
| 209 |
+
"learning_rate": 1.4754511120436426e-05,
|
| 210 |
+
"loss": 0.3077,
|
| 211 |
+
"step": 15000
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 2.17,
|
| 215 |
+
"learning_rate": 1.457966149111764e-05,
|
| 216 |
+
"loss": 0.3109,
|
| 217 |
+
"step": 15500
|
| 218 |
},
|
| 219 |
{
|
| 220 |
"epoch": 2.24,
|
| 221 |
+
"learning_rate": 1.4404811861798856e-05,
|
| 222 |
+
"loss": 0.31,
|
| 223 |
+
"step": 16000
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 2.31,
|
| 227 |
+
"learning_rate": 1.4229962232480068e-05,
|
| 228 |
+
"loss": 0.3054,
|
| 229 |
+
"step": 16500
|
| 230 |
},
|
| 231 |
{
|
| 232 |
"epoch": 2.38,
|
| 233 |
+
"learning_rate": 1.4055112603161282e-05,
|
| 234 |
+
"loss": 0.3105,
|
| 235 |
+
"step": 17000
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"epoch": 2.45,
|
| 239 |
+
"learning_rate": 1.3880262973842498e-05,
|
| 240 |
+
"loss": 0.3142,
|
| 241 |
+
"step": 17500
|
| 242 |
},
|
| 243 |
{
|
| 244 |
"epoch": 2.52,
|
| 245 |
+
"learning_rate": 1.370541334452371e-05,
|
| 246 |
+
"loss": 0.3097,
|
| 247 |
+
"step": 18000
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 2.59,
|
| 251 |
+
"learning_rate": 1.3530563715204925e-05,
|
| 252 |
+
"loss": 0.3145,
|
| 253 |
+
"step": 18500
|
| 254 |
},
|
| 255 |
{
|
| 256 |
"epoch": 2.66,
|
| 257 |
+
"learning_rate": 1.335571408588614e-05,
|
| 258 |
+
"loss": 0.3153,
|
| 259 |
+
"step": 19000
|
| 260 |
+
},
|
| 261 |
+
{
|
| 262 |
+
"epoch": 2.73,
|
| 263 |
+
"learning_rate": 1.3180864456567353e-05,
|
| 264 |
+
"loss": 0.3163,
|
| 265 |
+
"step": 19500
|
| 266 |
},
|
| 267 |
{
|
| 268 |
"epoch": 2.8,
|
| 269 |
+
"learning_rate": 1.3006014827248567e-05,
|
| 270 |
+
"loss": 0.3044,
|
| 271 |
+
"step": 20000
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 2.87,
|
| 275 |
+
"learning_rate": 1.2831165197929783e-05,
|
| 276 |
+
"loss": 0.3118,
|
| 277 |
+
"step": 20500
|
| 278 |
},
|
| 279 |
{
|
| 280 |
"epoch": 2.94,
|
| 281 |
+
"learning_rate": 1.2656315568610995e-05,
|
| 282 |
+
"loss": 0.3115,
|
| 283 |
+
"step": 21000
|
| 284 |
},
|
| 285 |
{
|
| 286 |
"epoch": 3.0,
|
| 287 |
+
"eval_akurasi": 0.4235787817192315,
|
| 288 |
+
"eval_f1": 0.4809589398056807,
|
| 289 |
+
"eval_loss": 0.3863948583602905,
|
| 290 |
+
"eval_roc_auc": 0.6695626516294014,
|
| 291 |
+
"eval_runtime": 258.9039,
|
| 292 |
+
"eval_samples_per_second": 58.906,
|
| 293 |
+
"eval_steps_per_second": 7.366,
|
| 294 |
+
"step": 21447
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 3.01,
|
| 298 |
+
"learning_rate": 1.248146593929221e-05,
|
| 299 |
+
"loss": 0.3029,
|
| 300 |
+
"step": 21500
|
| 301 |
},
|
| 302 |
{
|
| 303 |
"epoch": 3.08,
|
| 304 |
+
"learning_rate": 1.2306616309973425e-05,
|
| 305 |
+
"loss": 0.2587,
|
| 306 |
+
"step": 22000
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 3.15,
|
| 310 |
+
"learning_rate": 1.2131766680654638e-05,
|
| 311 |
+
"loss": 0.2592,
|
| 312 |
+
"step": 22500
|
| 313 |
},
|
| 314 |
{
|
| 315 |
"epoch": 3.22,
|
| 316 |
+
"learning_rate": 1.1956917051335852e-05,
|
| 317 |
+
"loss": 0.2679,
|
| 318 |
+
"step": 23000
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 3.29,
|
| 322 |
+
"learning_rate": 1.1782067422017068e-05,
|
| 323 |
+
"loss": 0.2645,
|
| 324 |
+
"step": 23500
|
| 325 |
},
|
| 326 |
{
|
| 327 |
"epoch": 3.36,
|
| 328 |
+
"learning_rate": 1.160721779269828e-05,
|
| 329 |
+
"loss": 0.2669,
|
| 330 |
+
"step": 24000
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 3.43,
|
| 334 |
+
"learning_rate": 1.1432368163379494e-05,
|
| 335 |
+
"loss": 0.2676,
|
| 336 |
+
"step": 24500
|
| 337 |
},
|
| 338 |
{
|
| 339 |
"epoch": 3.5,
|
| 340 |
+
"learning_rate": 1.125751853406071e-05,
|
| 341 |
+
"loss": 0.2683,
|
| 342 |
+
"step": 25000
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 3.57,
|
| 346 |
+
"learning_rate": 1.1082668904741923e-05,
|
| 347 |
+
"loss": 0.272,
|
| 348 |
+
"step": 25500
|
| 349 |
},
|
| 350 |
{
|
| 351 |
"epoch": 3.64,
|
| 352 |
+
"learning_rate": 1.0907819275423137e-05,
|
| 353 |
+
"loss": 0.2718,
|
| 354 |
+
"step": 26000
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 3.71,
|
| 358 |
+
"learning_rate": 1.0732969646104353e-05,
|
| 359 |
+
"loss": 0.2731,
|
| 360 |
+
"step": 26500
|
| 361 |
},
|
| 362 |
{
|
| 363 |
"epoch": 3.78,
|
| 364 |
+
"learning_rate": 1.0558120016785565e-05,
|
| 365 |
+
"loss": 0.2641,
|
| 366 |
+
"step": 27000
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 3.85,
|
| 370 |
+
"learning_rate": 1.0383270387466779e-05,
|
| 371 |
+
"loss": 0.2795,
|
| 372 |
+
"step": 27500
|
| 373 |
},
|
| 374 |
{
|
| 375 |
"epoch": 3.92,
|
| 376 |
+
"learning_rate": 1.0208420758147995e-05,
|
| 377 |
+
"loss": 0.2715,
|
| 378 |
+
"step": 28000
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 3.99,
|
| 382 |
+
"learning_rate": 1.0033571128829207e-05,
|
| 383 |
+
"loss": 0.2618,
|
| 384 |
+
"step": 28500
|
| 385 |
},
|
| 386 |
{
|
| 387 |
"epoch": 4.0,
|
| 388 |
+
"eval_akurasi": 0.45898629598059143,
|
| 389 |
+
"eval_f1": 0.49651709628372404,
|
| 390 |
+
"eval_loss": 0.43184059858322144,
|
| 391 |
+
"eval_roc_auc": 0.6809307586387777,
|
| 392 |
+
"eval_runtime": 259.0229,
|
| 393 |
+
"eval_samples_per_second": 58.879,
|
| 394 |
+
"eval_steps_per_second": 7.362,
|
| 395 |
+
"step": 28596
|
| 396 |
},
|
| 397 |
{
|
| 398 |
"epoch": 4.06,
|
| 399 |
+
"learning_rate": 9.858721499510422e-06,
|
| 400 |
+
"loss": 0.2317,
|
| 401 |
+
"step": 29000
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 4.13,
|
| 405 |
+
"learning_rate": 9.683871870191636e-06,
|
| 406 |
+
"loss": 0.2289,
|
| 407 |
+
"step": 29500
|
| 408 |
},
|
| 409 |
{
|
| 410 |
"epoch": 4.2,
|
| 411 |
+
"learning_rate": 9.50902224087285e-06,
|
| 412 |
+
"loss": 0.2273,
|
| 413 |
+
"step": 30000
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 4.27,
|
| 417 |
+
"learning_rate": 9.334172611554064e-06,
|
| 418 |
+
"loss": 0.2344,
|
| 419 |
+
"step": 30500
|
| 420 |
},
|
| 421 |
{
|
| 422 |
"epoch": 4.34,
|
| 423 |
+
"learning_rate": 9.159322982235278e-06,
|
| 424 |
+
"loss": 0.2256,
|
| 425 |
+
"step": 31000
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 4.41,
|
| 429 |
+
"learning_rate": 8.984473352916492e-06,
|
| 430 |
+
"loss": 0.2265,
|
| 431 |
+
"step": 31500
|
| 432 |
},
|
| 433 |
{
|
| 434 |
"epoch": 4.48,
|
| 435 |
+
"learning_rate": 8.809623723597706e-06,
|
| 436 |
+
"loss": 0.2274,
|
| 437 |
+
"step": 32000
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 4.55,
|
| 441 |
+
"learning_rate": 8.63477409427892e-06,
|
| 442 |
+
"loss": 0.2315,
|
| 443 |
+
"step": 32500
|
| 444 |
},
|
| 445 |
{
|
| 446 |
"epoch": 4.62,
|
| 447 |
+
"learning_rate": 8.459924464960135e-06,
|
| 448 |
+
"loss": 0.2231,
|
| 449 |
+
"step": 33000
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 4.69,
|
| 453 |
+
"learning_rate": 8.285074835641349e-06,
|
| 454 |
+
"loss": 0.233,
|
| 455 |
+
"step": 33500
|
| 456 |
},
|
| 457 |
{
|
| 458 |
"epoch": 4.76,
|
| 459 |
+
"learning_rate": 8.110225206322563e-06,
|
| 460 |
+
"loss": 0.234,
|
| 461 |
+
"step": 34000
|
| 462 |
+
},
|
| 463 |
+
{
|
| 464 |
+
"epoch": 4.83,
|
| 465 |
+
"learning_rate": 7.935375577003777e-06,
|
| 466 |
+
"loss": 0.2237,
|
| 467 |
+
"step": 34500
|
| 468 |
},
|
| 469 |
{
|
| 470 |
"epoch": 4.9,
|
| 471 |
+
"learning_rate": 7.760525947684991e-06,
|
| 472 |
+
"loss": 0.2316,
|
| 473 |
+
"step": 35000
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 4.97,
|
| 477 |
+
"learning_rate": 7.585676318366205e-06,
|
| 478 |
+
"loss": 0.2223,
|
| 479 |
+
"step": 35500
|
| 480 |
},
|
| 481 |
{
|
| 482 |
"epoch": 5.0,
|
| 483 |
+
"eval_akurasi": 0.46829716084191203,
|
| 484 |
+
"eval_f1": 0.49530800928009977,
|
| 485 |
+
"eval_loss": 0.47835299372673035,
|
| 486 |
+
"eval_roc_auc": 0.6813979411186152,
|
| 487 |
+
"eval_runtime": 258.995,
|
| 488 |
+
"eval_samples_per_second": 58.885,
|
| 489 |
+
"eval_steps_per_second": 7.363,
|
| 490 |
+
"step": 35745
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 491 |
},
|
| 492 |
{
|
| 493 |
+
"epoch": 5.04,
|
| 494 |
+
"learning_rate": 7.41082668904742e-06,
|
| 495 |
+
"loss": 0.2077,
|
| 496 |
+
"step": 36000
|
| 497 |
},
|
| 498 |
{
|
| 499 |
+
"epoch": 5.11,
|
| 500 |
+
"learning_rate": 7.2359770597286336e-06,
|
| 501 |
+
"loss": 0.1861,
|
| 502 |
+
"step": 36500
|
| 503 |
},
|
| 504 |
{
|
| 505 |
+
"epoch": 5.18,
|
| 506 |
+
"learning_rate": 7.061127430409848e-06,
|
| 507 |
+
"loss": 0.1971,
|
| 508 |
+
"step": 37000
|
| 509 |
},
|
| 510 |
{
|
| 511 |
+
"epoch": 5.25,
|
| 512 |
+
"learning_rate": 6.886277801091063e-06,
|
| 513 |
+
"loss": 0.196,
|
| 514 |
+
"step": 37500
|
| 515 |
},
|
| 516 |
{
|
| 517 |
+
"epoch": 5.32,
|
| 518 |
+
"learning_rate": 6.711428171772276e-06,
|
| 519 |
+
"loss": 0.1908,
|
| 520 |
+
"step": 38000
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 5.39,
|
| 524 |
+
"learning_rate": 6.53657854245349e-06,
|
| 525 |
+
"loss": 0.1911,
|
| 526 |
+
"step": 38500
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 5.46,
|
| 530 |
+
"learning_rate": 6.361728913134705e-06,
|
| 531 |
+
"loss": 0.1903,
|
| 532 |
+
"step": 39000
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 5.53,
|
| 536 |
+
"learning_rate": 6.186879283815918e-06,
|
| 537 |
+
"loss": 0.1976,
|
| 538 |
+
"step": 39500
|
| 539 |
+
},
|
| 540 |
+
{
|
| 541 |
+
"epoch": 5.6,
|
| 542 |
+
"learning_rate": 6.012029654497133e-06,
|
| 543 |
+
"loss": 0.1971,
|
| 544 |
+
"step": 40000
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 5.67,
|
| 548 |
+
"learning_rate": 5.8371800251783475e-06,
|
| 549 |
+
"loss": 0.1928,
|
| 550 |
+
"step": 40500
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 5.74,
|
| 554 |
+
"learning_rate": 5.662330395859561e-06,
|
| 555 |
+
"loss": 0.1927,
|
| 556 |
+
"step": 41000
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 5.81,
|
| 560 |
+
"learning_rate": 5.487480766540776e-06,
|
| 561 |
+
"loss": 0.1917,
|
| 562 |
+
"step": 41500
|
| 563 |
},
|
| 564 |
{
|
| 565 |
"epoch": 5.87,
|
| 566 |
+
"learning_rate": 5.31263113722199e-06,
|
| 567 |
+
"loss": 0.2022,
|
| 568 |
+
"step": 42000
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 5.94,
|
| 572 |
+
"learning_rate": 5.137781507903203e-06,
|
| 573 |
+
"loss": 0.1988,
|
| 574 |
+
"step": 42500
|
| 575 |
},
|
| 576 |
{
|
| 577 |
"epoch": 6.0,
|
| 578 |
+
"eval_akurasi": 0.4731493016851354,
|
| 579 |
+
"eval_f1": 0.496174038362557,
|
| 580 |
+
"eval_loss": 0.5363304018974304,
|
| 581 |
+
"eval_roc_auc": 0.6824306602845714,
|
| 582 |
+
"eval_runtime": 259.1769,
|
| 583 |
+
"eval_samples_per_second": 58.844,
|
| 584 |
+
"eval_steps_per_second": 7.358,
|
| 585 |
+
"step": 42894
|
| 586 |
}
|
| 587 |
],
|
| 588 |
"logging_steps": 500,
|
| 589 |
+
"max_steps": 57192,
|
| 590 |
+
"num_train_epochs": 8,
|
| 591 |
"save_steps": 500,
|
| 592 |
+
"total_flos": 6.77171376171049e+16,
|
| 593 |
"trial_name": null,
|
| 594 |
"trial_params": null
|
| 595 |
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4091
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b9a439502e64b076bc34244bcf4c6cc9e5e81fb300921726e1d8aa752c17d504
|
| 3 |
size 4091
|