Commit
•
7ca9fdf
1
Parent(s):
babc7bb
Fix bug and re-train
Browse files- optimizer.pt +2 -2
- pytorch_model.bin +1 -1
- rng_state.pth +1 -1
- scheduler.pt +1 -1
- trainer_state.json +120 -312
- 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
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9c118cfda620c1964f613cfb8931c4581d478025e9c79c7e24f99dbe541dfd37
|
| 3 |
+
size 2141757
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 891700799
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9d0f666892535d76135417a27d93995f91364e435ad002534fe9fed0a5782d52
|
| 3 |
size 891700799
|
rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14503
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5afd47c3d36d90a7c6e830e113baddf97d6f30cc8a8f13ef18c827cd5d6e383c
|
| 3 |
size 14503
|
scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 623
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:89ed9b1d2b8e897f9fed7bc2b4afe6f284caff5787c21247f285b0105a825905
|
| 3 |
size 623
|
trainer_state.json
CHANGED
|
@@ -1,388 +1,196 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 1.
|
| 3 |
-
"best_model_checkpoint": "./results/t5-bow-decoder-base\\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": 0.11,
|
| 12 |
-
"learning_rate":
|
| 13 |
-
"loss":
|
| 14 |
-
"step":
|
| 15 |
},
|
| 16 |
{
|
| 17 |
-
"epoch": 0.
|
| 18 |
-
"learning_rate": 0.
|
| 19 |
-
"loss":
|
| 20 |
-
"step":
|
| 21 |
},
|
| 22 |
{
|
| 23 |
-
"epoch": 0.
|
| 24 |
-
"learning_rate":
|
| 25 |
-
"loss":
|
| 26 |
-
"step":
|
| 27 |
},
|
| 28 |
{
|
| 29 |
-
"epoch": 0.
|
| 30 |
-
"learning_rate":
|
| 31 |
-
"loss":
|
| 32 |
-
"step":
|
| 33 |
},
|
| 34 |
{
|
| 35 |
-
"epoch": 0.
|
| 36 |
-
"learning_rate":
|
| 37 |
-
"loss": 1.
|
| 38 |
-
"step":
|
| 39 |
},
|
| 40 |
{
|
| 41 |
-
"epoch": 0.
|
| 42 |
-
"learning_rate":
|
| 43 |
-
"loss": 1.
|
| 44 |
-
"step":
|
| 45 |
},
|
| 46 |
{
|
| 47 |
-
"epoch": 0.
|
| 48 |
-
"learning_rate":
|
| 49 |
-
"loss": 1.
|
| 50 |
-
"step":
|
| 51 |
},
|
| 52 |
{
|
| 53 |
-
"epoch": 0.
|
| 54 |
-
"learning_rate":
|
| 55 |
-
"loss": 1.
|
| 56 |
-
"step":
|
| 57 |
},
|
| 58 |
{
|
| 59 |
"epoch": 1.0,
|
| 60 |
-
"
|
| 61 |
-
"
|
|
|
|
|
|
|
| 62 |
"step": 2250
|
| 63 |
},
|
| 64 |
{
|
| 65 |
-
"epoch": 1.
|
| 66 |
-
"
|
| 67 |
-
"
|
| 68 |
-
"
|
| 69 |
-
"eval_steps_per_second": 3.564,
|
| 70 |
-
"step": 2250
|
| 71 |
},
|
| 72 |
{
|
| 73 |
-
"epoch": 1.
|
| 74 |
-
"learning_rate":
|
| 75 |
-
"loss": 1.
|
| 76 |
-
"step":
|
| 77 |
},
|
| 78 |
{
|
| 79 |
-
"epoch": 1.
|
| 80 |
-
"learning_rate":
|
| 81 |
-
"loss": 1.
|
| 82 |
-
"step":
|
| 83 |
},
|
| 84 |
{
|
| 85 |
-
"epoch": 1.
|
| 86 |
-
"learning_rate":
|
| 87 |
-
"loss": 1.
|
| 88 |
-
"step":
|
| 89 |
},
|
| 90 |
{
|
| 91 |
-
"epoch": 1.
|
| 92 |
-
"learning_rate":
|
| 93 |
-
"loss": 1.
|
| 94 |
-
"step":
|
| 95 |
},
|
| 96 |
{
|
| 97 |
-
"epoch": 1.
|
| 98 |
-
"learning_rate":
|
| 99 |
-
"loss": 1.
|
| 100 |
-
"step":
|
| 101 |
},
|
| 102 |
{
|
| 103 |
-
"epoch": 1.
|
| 104 |
-
"learning_rate":
|
| 105 |
-
"loss": 1.
|
| 106 |
-
"step":
|
| 107 |
},
|
| 108 |
{
|
| 109 |
-
"epoch": 1.
|
| 110 |
-
"learning_rate":
|
| 111 |
-
"loss": 1.
|
| 112 |
-
"step":
|
| 113 |
},
|
| 114 |
{
|
| 115 |
-
"epoch": 1.
|
| 116 |
-
"learning_rate":
|
| 117 |
-
"loss": 1.
|
| 118 |
-
"step":
|
| 119 |
},
|
| 120 |
{
|
| 121 |
"epoch": 2.0,
|
| 122 |
-
"
|
| 123 |
-
"
|
|
|
|
|
|
|
| 124 |
"step": 4500
|
| 125 |
},
|
| 126 |
{
|
| 127 |
-
"epoch": 2.
|
| 128 |
-
"
|
| 129 |
-
"
|
| 130 |
-
"
|
| 131 |
-
"eval_steps_per_second": 3.698,
|
| 132 |
-
"step": 4500
|
| 133 |
},
|
| 134 |
{
|
| 135 |
-
"epoch": 2.
|
| 136 |
-
"learning_rate":
|
| 137 |
-
"loss": 1.
|
| 138 |
-
"step":
|
| 139 |
},
|
| 140 |
{
|
| 141 |
-
"epoch": 2.
|
| 142 |
-
"learning_rate":
|
| 143 |
-
"loss": 1.
|
| 144 |
-
"step":
|
| 145 |
},
|
| 146 |
{
|
| 147 |
-
"epoch": 2.
|
| 148 |
-
"learning_rate":
|
| 149 |
-
"loss": 1.
|
| 150 |
-
"step":
|
| 151 |
},
|
| 152 |
{
|
| 153 |
-
"epoch": 2.
|
| 154 |
-
"learning_rate":
|
| 155 |
-
"loss": 1.
|
| 156 |
-
"step":
|
| 157 |
},
|
| 158 |
{
|
| 159 |
-
"epoch": 2.
|
| 160 |
-
"learning_rate":
|
| 161 |
-
"loss": 1.
|
| 162 |
-
"step":
|
| 163 |
},
|
| 164 |
{
|
| 165 |
-
"epoch": 2.
|
| 166 |
-
"learning_rate":
|
| 167 |
-
"loss": 1.
|
| 168 |
-
"step":
|
| 169 |
},
|
| 170 |
{
|
| 171 |
-
"epoch": 2.
|
| 172 |
-
"learning_rate":
|
| 173 |
-
"loss": 1.
|
| 174 |
-
"step":
|
| 175 |
},
|
| 176 |
{
|
| 177 |
-
"epoch": 2.
|
| 178 |
-
"learning_rate":
|
| 179 |
-
"loss": 1.
|
| 180 |
-
"step":
|
| 181 |
},
|
| 182 |
{
|
| 183 |
"epoch": 3.0,
|
| 184 |
-
"
|
| 185 |
-
"
|
|
|
|
|
|
|
| 186 |
"step": 6750
|
| 187 |
-
},
|
| 188 |
-
{
|
| 189 |
-
"epoch": 3.0,
|
| 190 |
-
"eval_loss": 1.593631386756897,
|
| 191 |
-
"eval_runtime": 19.1501,
|
| 192 |
-
"eval_samples_per_second": 52.219,
|
| 193 |
-
"eval_steps_per_second": 3.29,
|
| 194 |
-
"step": 6750
|
| 195 |
-
},
|
| 196 |
-
{
|
| 197 |
-
"epoch": 3.11,
|
| 198 |
-
"learning_rate": 8.53932584269663e-05,
|
| 199 |
-
"loss": 1.5611,
|
| 200 |
-
"step": 7000
|
| 201 |
-
},
|
| 202 |
-
{
|
| 203 |
-
"epoch": 3.22,
|
| 204 |
-
"learning_rate": 8.483146067415731e-05,
|
| 205 |
-
"loss": 1.5177,
|
| 206 |
-
"step": 7250
|
| 207 |
-
},
|
| 208 |
-
{
|
| 209 |
-
"epoch": 3.33,
|
| 210 |
-
"learning_rate": 8.426966292134831e-05,
|
| 211 |
-
"loss": 1.5332,
|
| 212 |
-
"step": 7500
|
| 213 |
-
},
|
| 214 |
-
{
|
| 215 |
-
"epoch": 3.44,
|
| 216 |
-
"learning_rate": 8.370786516853934e-05,
|
| 217 |
-
"loss": 1.6529,
|
| 218 |
-
"step": 7750
|
| 219 |
-
},
|
| 220 |
-
{
|
| 221 |
-
"epoch": 3.56,
|
| 222 |
-
"learning_rate": 8.314606741573034e-05,
|
| 223 |
-
"loss": 1.5575,
|
| 224 |
-
"step": 8000
|
| 225 |
-
},
|
| 226 |
-
{
|
| 227 |
-
"epoch": 3.67,
|
| 228 |
-
"learning_rate": 8.258426966292135e-05,
|
| 229 |
-
"loss": 1.5424,
|
| 230 |
-
"step": 8250
|
| 231 |
-
},
|
| 232 |
-
{
|
| 233 |
-
"epoch": 3.78,
|
| 234 |
-
"learning_rate": 8.202247191011237e-05,
|
| 235 |
-
"loss": 1.5496,
|
| 236 |
-
"step": 8500
|
| 237 |
-
},
|
| 238 |
-
{
|
| 239 |
-
"epoch": 3.89,
|
| 240 |
-
"learning_rate": 8.146067415730337e-05,
|
| 241 |
-
"loss": 1.5465,
|
| 242 |
-
"step": 8750
|
| 243 |
-
},
|
| 244 |
-
{
|
| 245 |
-
"epoch": 4.0,
|
| 246 |
-
"learning_rate": 8.089887640449438e-05,
|
| 247 |
-
"loss": 1.5903,
|
| 248 |
-
"step": 9000
|
| 249 |
-
},
|
| 250 |
-
{
|
| 251 |
-
"epoch": 4.0,
|
| 252 |
-
"eval_loss": 1.5624333620071411,
|
| 253 |
-
"eval_runtime": 19.0571,
|
| 254 |
-
"eval_samples_per_second": 52.474,
|
| 255 |
-
"eval_steps_per_second": 3.306,
|
| 256 |
-
"step": 9000
|
| 257 |
-
},
|
| 258 |
-
{
|
| 259 |
-
"epoch": 4.11,
|
| 260 |
-
"learning_rate": 8.03370786516854e-05,
|
| 261 |
-
"loss": 1.4976,
|
| 262 |
-
"step": 9250
|
| 263 |
-
},
|
| 264 |
-
{
|
| 265 |
-
"epoch": 4.22,
|
| 266 |
-
"learning_rate": 7.97752808988764e-05,
|
| 267 |
-
"loss": 1.4719,
|
| 268 |
-
"step": 9500
|
| 269 |
-
},
|
| 270 |
-
{
|
| 271 |
-
"epoch": 4.33,
|
| 272 |
-
"learning_rate": 7.921348314606743e-05,
|
| 273 |
-
"loss": 1.4781,
|
| 274 |
-
"step": 9750
|
| 275 |
-
},
|
| 276 |
-
{
|
| 277 |
-
"epoch": 4.44,
|
| 278 |
-
"learning_rate": 7.865168539325843e-05,
|
| 279 |
-
"loss": 1.4652,
|
| 280 |
-
"step": 10000
|
| 281 |
-
},
|
| 282 |
-
{
|
| 283 |
-
"epoch": 4.56,
|
| 284 |
-
"learning_rate": 7.808988764044944e-05,
|
| 285 |
-
"loss": 1.4997,
|
| 286 |
-
"step": 10250
|
| 287 |
-
},
|
| 288 |
-
{
|
| 289 |
-
"epoch": 4.67,
|
| 290 |
-
"learning_rate": 7.752808988764046e-05,
|
| 291 |
-
"loss": 1.5537,
|
| 292 |
-
"step": 10500
|
| 293 |
-
},
|
| 294 |
-
{
|
| 295 |
-
"epoch": 4.78,
|
| 296 |
-
"learning_rate": 7.696629213483147e-05,
|
| 297 |
-
"loss": 1.5558,
|
| 298 |
-
"step": 10750
|
| 299 |
-
},
|
| 300 |
-
{
|
| 301 |
-
"epoch": 4.89,
|
| 302 |
-
"learning_rate": 7.640449438202247e-05,
|
| 303 |
-
"loss": 1.4763,
|
| 304 |
-
"step": 11000
|
| 305 |
-
},
|
| 306 |
-
{
|
| 307 |
-
"epoch": 5.0,
|
| 308 |
-
"learning_rate": 7.584269662921349e-05,
|
| 309 |
-
"loss": 1.5011,
|
| 310 |
-
"step": 11250
|
| 311 |
-
},
|
| 312 |
-
{
|
| 313 |
-
"epoch": 5.0,
|
| 314 |
-
"eval_loss": 1.5619711875915527,
|
| 315 |
-
"eval_runtime": 19.201,
|
| 316 |
-
"eval_samples_per_second": 52.081,
|
| 317 |
-
"eval_steps_per_second": 3.281,
|
| 318 |
-
"step": 11250
|
| 319 |
-
},
|
| 320 |
-
{
|
| 321 |
-
"epoch": 5.11,
|
| 322 |
-
"learning_rate": 7.52808988764045e-05,
|
| 323 |
-
"loss": 1.4501,
|
| 324 |
-
"step": 11500
|
| 325 |
-
},
|
| 326 |
-
{
|
| 327 |
-
"epoch": 5.22,
|
| 328 |
-
"learning_rate": 7.471910112359551e-05,
|
| 329 |
-
"loss": 1.434,
|
| 330 |
-
"step": 11750
|
| 331 |
-
},
|
| 332 |
-
{
|
| 333 |
-
"epoch": 5.33,
|
| 334 |
-
"learning_rate": 7.415730337078653e-05,
|
| 335 |
-
"loss": 1.3839,
|
| 336 |
-
"step": 12000
|
| 337 |
-
},
|
| 338 |
-
{
|
| 339 |
-
"epoch": 5.44,
|
| 340 |
-
"learning_rate": 7.359550561797753e-05,
|
| 341 |
-
"loss": 1.4426,
|
| 342 |
-
"step": 12250
|
| 343 |
-
},
|
| 344 |
-
{
|
| 345 |
-
"epoch": 5.56,
|
| 346 |
-
"learning_rate": 7.303370786516854e-05,
|
| 347 |
-
"loss": 1.4481,
|
| 348 |
-
"step": 12500
|
| 349 |
-
},
|
| 350 |
-
{
|
| 351 |
-
"epoch": 5.67,
|
| 352 |
-
"learning_rate": 7.247191011235956e-05,
|
| 353 |
-
"loss": 1.452,
|
| 354 |
-
"step": 12750
|
| 355 |
-
},
|
| 356 |
-
{
|
| 357 |
-
"epoch": 5.78,
|
| 358 |
-
"learning_rate": 7.191011235955056e-05,
|
| 359 |
-
"loss": 1.485,
|
| 360 |
-
"step": 13000
|
| 361 |
-
},
|
| 362 |
-
{
|
| 363 |
-
"epoch": 5.89,
|
| 364 |
-
"learning_rate": 7.134831460674157e-05,
|
| 365 |
-
"loss": 1.5027,
|
| 366 |
-
"step": 13250
|
| 367 |
-
},
|
| 368 |
-
{
|
| 369 |
-
"epoch": 6.0,
|
| 370 |
-
"learning_rate": 7.078651685393259e-05,
|
| 371 |
-
"loss": 1.4556,
|
| 372 |
-
"step": 13500
|
| 373 |
-
},
|
| 374 |
-
{
|
| 375 |
-
"epoch": 6.0,
|
| 376 |
-
"eval_loss": 1.5397371053695679,
|
| 377 |
-
"eval_runtime": 22.8085,
|
| 378 |
-
"eval_samples_per_second": 43.843,
|
| 379 |
-
"eval_steps_per_second": 2.762,
|
| 380 |
-
"step": 13500
|
| 381 |
}
|
| 382 |
],
|
| 383 |
"max_steps": 45000,
|
| 384 |
"num_train_epochs": 20,
|
| 385 |
-
"total_flos":
|
| 386 |
"trial_name": null,
|
| 387 |
"trial_params": null
|
| 388 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 1.6302473545074463,
|
| 3 |
+
"best_model_checkpoint": "./results/t5-bow-decoder-base\\checkpoint-6750",
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"global_step": 6750,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
| 9 |
"log_history": [
|
| 10 |
{
|
| 11 |
"epoch": 0.11,
|
| 12 |
+
"learning_rate": 0.0005,
|
| 13 |
+
"loss": 3.0243,
|
| 14 |
+
"step": 256
|
| 15 |
},
|
| 16 |
{
|
| 17 |
+
"epoch": 0.23,
|
| 18 |
+
"learning_rate": 0.001,
|
| 19 |
+
"loss": 1.9017,
|
| 20 |
+
"step": 512
|
| 21 |
},
|
| 22 |
{
|
| 23 |
+
"epoch": 0.34,
|
| 24 |
+
"learning_rate": 0.0009942456392735119,
|
| 25 |
+
"loss": 1.8801,
|
| 26 |
+
"step": 768
|
| 27 |
},
|
| 28 |
{
|
| 29 |
+
"epoch": 0.46,
|
| 30 |
+
"learning_rate": 0.000988491278547024,
|
| 31 |
+
"loss": 1.875,
|
| 32 |
+
"step": 1024
|
| 33 |
},
|
| 34 |
{
|
| 35 |
+
"epoch": 0.57,
|
| 36 |
+
"learning_rate": 0.0009827369178205358,
|
| 37 |
+
"loss": 1.7517,
|
| 38 |
+
"step": 1280
|
| 39 |
},
|
| 40 |
{
|
| 41 |
+
"epoch": 0.68,
|
| 42 |
+
"learning_rate": 0.000976982557094048,
|
| 43 |
+
"loss": 1.8016,
|
| 44 |
+
"step": 1536
|
| 45 |
},
|
| 46 |
{
|
| 47 |
+
"epoch": 0.8,
|
| 48 |
+
"learning_rate": 0.0009712281963675598,
|
| 49 |
+
"loss": 1.7453,
|
| 50 |
+
"step": 1792
|
| 51 |
},
|
| 52 |
{
|
| 53 |
+
"epoch": 0.91,
|
| 54 |
+
"learning_rate": 0.0009654738356410718,
|
| 55 |
+
"loss": 1.7931,
|
| 56 |
+
"step": 2048
|
| 57 |
},
|
| 58 |
{
|
| 59 |
"epoch": 1.0,
|
| 60 |
+
"eval_loss": 1.6831984519958496,
|
| 61 |
+
"eval_runtime": 18.9287,
|
| 62 |
+
"eval_samples_per_second": 52.83,
|
| 63 |
+
"eval_steps_per_second": 6.604,
|
| 64 |
"step": 2250
|
| 65 |
},
|
| 66 |
{
|
| 67 |
+
"epoch": 1.02,
|
| 68 |
+
"learning_rate": 0.0009597194749145838,
|
| 69 |
+
"loss": 1.7622,
|
| 70 |
+
"step": 2304
|
|
|
|
|
|
|
| 71 |
},
|
| 72 |
{
|
| 73 |
+
"epoch": 1.14,
|
| 74 |
+
"learning_rate": 0.0009539651141880957,
|
| 75 |
+
"loss": 1.5755,
|
| 76 |
+
"step": 2560
|
| 77 |
},
|
| 78 |
{
|
| 79 |
+
"epoch": 1.25,
|
| 80 |
+
"learning_rate": 0.0009482107534616077,
|
| 81 |
+
"loss": 1.6284,
|
| 82 |
+
"step": 2816
|
| 83 |
},
|
| 84 |
{
|
| 85 |
+
"epoch": 1.37,
|
| 86 |
+
"learning_rate": 0.0009424563927351196,
|
| 87 |
+
"loss": 1.6671,
|
| 88 |
+
"step": 3072
|
| 89 |
},
|
| 90 |
{
|
| 91 |
+
"epoch": 1.48,
|
| 92 |
+
"learning_rate": 0.0009367020320086316,
|
| 93 |
+
"loss": 1.5683,
|
| 94 |
+
"step": 3328
|
| 95 |
},
|
| 96 |
{
|
| 97 |
+
"epoch": 1.59,
|
| 98 |
+
"learning_rate": 0.0009309476712821435,
|
| 99 |
+
"loss": 1.618,
|
| 100 |
+
"step": 3584
|
| 101 |
},
|
| 102 |
{
|
| 103 |
+
"epoch": 1.71,
|
| 104 |
+
"learning_rate": 0.0009251933105556555,
|
| 105 |
+
"loss": 1.6381,
|
| 106 |
+
"step": 3840
|
| 107 |
},
|
| 108 |
{
|
| 109 |
+
"epoch": 1.82,
|
| 110 |
+
"learning_rate": 0.0009194389498291674,
|
| 111 |
+
"loss": 1.6486,
|
| 112 |
+
"step": 4096
|
| 113 |
},
|
| 114 |
{
|
| 115 |
+
"epoch": 1.93,
|
| 116 |
+
"learning_rate": 0.0009136845891026794,
|
| 117 |
+
"loss": 1.6367,
|
| 118 |
+
"step": 4352
|
| 119 |
},
|
| 120 |
{
|
| 121 |
"epoch": 2.0,
|
| 122 |
+
"eval_loss": 1.6470595598220825,
|
| 123 |
+
"eval_runtime": 19.0654,
|
| 124 |
+
"eval_samples_per_second": 52.451,
|
| 125 |
+
"eval_steps_per_second": 6.556,
|
| 126 |
"step": 4500
|
| 127 |
},
|
| 128 |
{
|
| 129 |
+
"epoch": 2.05,
|
| 130 |
+
"learning_rate": 0.0009079302283761914,
|
| 131 |
+
"loss": 1.527,
|
| 132 |
+
"step": 4608
|
|
|
|
|
|
|
| 133 |
},
|
| 134 |
{
|
| 135 |
+
"epoch": 2.16,
|
| 136 |
+
"learning_rate": 0.0009021758676497032,
|
| 137 |
+
"loss": 1.4307,
|
| 138 |
+
"step": 4864
|
| 139 |
},
|
| 140 |
{
|
| 141 |
+
"epoch": 2.28,
|
| 142 |
+
"learning_rate": 0.0008964215069232152,
|
| 143 |
+
"loss": 1.4458,
|
| 144 |
+
"step": 5120
|
| 145 |
},
|
| 146 |
{
|
| 147 |
+
"epoch": 2.39,
|
| 148 |
+
"learning_rate": 0.0008906671461967272,
|
| 149 |
+
"loss": 1.4737,
|
| 150 |
+
"step": 5376
|
| 151 |
},
|
| 152 |
{
|
| 153 |
+
"epoch": 2.5,
|
| 154 |
+
"learning_rate": 0.0008849127854702393,
|
| 155 |
+
"loss": 1.4935,
|
| 156 |
+
"step": 5632
|
| 157 |
},
|
| 158 |
{
|
| 159 |
+
"epoch": 2.62,
|
| 160 |
+
"learning_rate": 0.0008791584247437511,
|
| 161 |
+
"loss": 1.4757,
|
| 162 |
+
"step": 5888
|
| 163 |
},
|
| 164 |
{
|
| 165 |
+
"epoch": 2.73,
|
| 166 |
+
"learning_rate": 0.0008734040640172631,
|
| 167 |
+
"loss": 1.4712,
|
| 168 |
+
"step": 6144
|
| 169 |
},
|
| 170 |
{
|
| 171 |
+
"epoch": 2.84,
|
| 172 |
+
"learning_rate": 0.0008676497032907751,
|
| 173 |
+
"loss": 1.4494,
|
| 174 |
+
"step": 6400
|
| 175 |
},
|
| 176 |
{
|
| 177 |
+
"epoch": 2.96,
|
| 178 |
+
"learning_rate": 0.000861895342564287,
|
| 179 |
+
"loss": 1.4335,
|
| 180 |
+
"step": 6656
|
| 181 |
},
|
| 182 |
{
|
| 183 |
"epoch": 3.0,
|
| 184 |
+
"eval_loss": 1.6302473545074463,
|
| 185 |
+
"eval_runtime": 19.2598,
|
| 186 |
+
"eval_samples_per_second": 51.922,
|
| 187 |
+
"eval_steps_per_second": 6.49,
|
| 188 |
"step": 6750
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 189 |
}
|
| 190 |
],
|
| 191 |
"max_steps": 45000,
|
| 192 |
"num_train_epochs": 20,
|
| 193 |
+
"total_flos": 1.644186304512e+16,
|
| 194 |
"trial_name": null,
|
| 195 |
"trial_params": null
|
| 196 |
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3247
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f9f94538ce0aec66eea46f6157e258642c92c9896ec46a97d3fc35ee59ccc572
|
| 3 |
size 3247
|