Commit
·
1066c4c
1
Parent(s):
556c6f4
Donw lstr 512
Browse files- optimizer.pt +2 -2
- pytorch_model.bin +1 -1
- rng_state.pth +2 -2
- scaler.pt +1 -1
- scheduler.pt +1 -1
- trainer_state.json +59 -329
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:c5772f0d132c52d6c7666a76eefa6acb743e5062963c285f6e91ff07779b68b1
|
| 3 |
+
size 2498513929
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1266126445
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2a3ba17d5b17bb6071632212add5e7a861df1991153686e2b139bda01650420d
|
| 3 |
size 1266126445
|
rng_state.pth
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:c7c914e03b6244226666d251f841b0bbc1d1bfb51226ea62c98deeaaf6176005
|
| 3 |
+
size 14567
|
scaler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 559
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4e26ec2eeed5d2393eae8db5740c3d49711ae46ff10dcff4c5d8a4a07cdc5062
|
| 3 |
size 559
|
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 sha256:5fff2c89694c75e0ec2f7fd167cc6e42ee90aad80a67c0b576b690e62f6ab285
|
| 3 |
size 623
|
trainer_state.json
CHANGED
|
@@ -1,376 +1,106 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 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 |
-
"eval_accuracy": 0.
|
| 19 |
-
"eval_loss":
|
| 20 |
-
"eval_runtime":
|
| 21 |
-
"eval_samples_per_second": 4.
|
| 22 |
-
"eval_steps_per_second": 1.
|
| 23 |
"step": 10
|
| 24 |
},
|
| 25 |
{
|
| 26 |
-
"epoch": 0.
|
| 27 |
-
"learning_rate":
|
| 28 |
-
"loss":
|
| 29 |
"step": 20
|
| 30 |
},
|
| 31 |
{
|
| 32 |
-
"epoch": 0.
|
| 33 |
-
"eval_accuracy": 0.
|
| 34 |
-
"eval_loss":
|
| 35 |
-
"eval_runtime":
|
| 36 |
-
"eval_samples_per_second": 4.
|
| 37 |
-
"eval_steps_per_second": 1.
|
| 38 |
"step": 20
|
| 39 |
},
|
| 40 |
{
|
| 41 |
-
"epoch":
|
| 42 |
-
"learning_rate":
|
| 43 |
-
"loss":
|
| 44 |
"step": 30
|
| 45 |
},
|
| 46 |
{
|
| 47 |
-
"epoch":
|
| 48 |
-
"eval_accuracy": 0.
|
| 49 |
-
"eval_loss":
|
| 50 |
-
"eval_runtime":
|
| 51 |
-
"eval_samples_per_second": 4.
|
| 52 |
-
"eval_steps_per_second": 1.
|
| 53 |
"step": 30
|
| 54 |
},
|
| 55 |
{
|
| 56 |
-
"epoch":
|
| 57 |
-
"learning_rate":
|
| 58 |
-
"loss":
|
| 59 |
"step": 40
|
| 60 |
},
|
| 61 |
{
|
| 62 |
-
"epoch":
|
| 63 |
-
"eval_accuracy": 0.
|
| 64 |
-
"eval_loss": 1.
|
| 65 |
-
"eval_runtime":
|
| 66 |
-
"eval_samples_per_second": 4.
|
| 67 |
-
"eval_steps_per_second": 1.
|
| 68 |
"step": 40
|
| 69 |
},
|
| 70 |
{
|
| 71 |
-
"epoch":
|
| 72 |
-
"learning_rate":
|
| 73 |
-
"loss":
|
| 74 |
"step": 50
|
| 75 |
},
|
| 76 |
{
|
| 77 |
-
"epoch":
|
| 78 |
-
"eval_accuracy": 0.
|
| 79 |
-
"eval_loss":
|
| 80 |
-
"eval_runtime":
|
| 81 |
-
"eval_samples_per_second":
|
| 82 |
-
"eval_steps_per_second":
|
| 83 |
"step": 50
|
| 84 |
},
|
| 85 |
{
|
| 86 |
-
"epoch":
|
| 87 |
-
"learning_rate":
|
| 88 |
-
"loss":
|
| 89 |
"step": 60
|
| 90 |
},
|
| 91 |
{
|
| 92 |
-
"epoch":
|
| 93 |
-
"eval_accuracy": 0.
|
| 94 |
-
"eval_loss":
|
| 95 |
-
"eval_runtime":
|
| 96 |
-
"eval_samples_per_second": 4.
|
| 97 |
-
"eval_steps_per_second": 1.
|
| 98 |
"step": 60
|
| 99 |
-
},
|
| 100 |
-
{
|
| 101 |
-
"epoch": 2.92,
|
| 102 |
-
"learning_rate": 5e-05,
|
| 103 |
-
"loss": 0.4054,
|
| 104 |
-
"step": 70
|
| 105 |
-
},
|
| 106 |
-
{
|
| 107 |
-
"epoch": 2.92,
|
| 108 |
-
"eval_accuracy": 0.75,
|
| 109 |
-
"eval_loss": 0.7560882568359375,
|
| 110 |
-
"eval_runtime": 10.3666,
|
| 111 |
-
"eval_samples_per_second": 4.63,
|
| 112 |
-
"eval_steps_per_second": 1.158,
|
| 113 |
-
"step": 70
|
| 114 |
-
},
|
| 115 |
-
{
|
| 116 |
-
"epoch": 3.33,
|
| 117 |
-
"learning_rate": 4.5833333333333334e-05,
|
| 118 |
-
"loss": 0.3773,
|
| 119 |
-
"step": 80
|
| 120 |
-
},
|
| 121 |
-
{
|
| 122 |
-
"epoch": 3.33,
|
| 123 |
-
"eval_accuracy": 0.8125,
|
| 124 |
-
"eval_loss": 0.6256787180900574,
|
| 125 |
-
"eval_runtime": 11.7432,
|
| 126 |
-
"eval_samples_per_second": 4.087,
|
| 127 |
-
"eval_steps_per_second": 1.022,
|
| 128 |
-
"step": 80
|
| 129 |
-
},
|
| 130 |
-
{
|
| 131 |
-
"epoch": 3.75,
|
| 132 |
-
"learning_rate": 4.166666666666667e-05,
|
| 133 |
-
"loss": 0.1139,
|
| 134 |
-
"step": 90
|
| 135 |
-
},
|
| 136 |
-
{
|
| 137 |
-
"epoch": 3.75,
|
| 138 |
-
"eval_accuracy": 0.875,
|
| 139 |
-
"eval_loss": 0.44811201095581055,
|
| 140 |
-
"eval_runtime": 10.2271,
|
| 141 |
-
"eval_samples_per_second": 4.693,
|
| 142 |
-
"eval_steps_per_second": 1.173,
|
| 143 |
-
"step": 90
|
| 144 |
-
},
|
| 145 |
-
{
|
| 146 |
-
"epoch": 4.17,
|
| 147 |
-
"learning_rate": 3.7500000000000003e-05,
|
| 148 |
-
"loss": 0.1395,
|
| 149 |
-
"step": 100
|
| 150 |
-
},
|
| 151 |
-
{
|
| 152 |
-
"epoch": 4.17,
|
| 153 |
-
"eval_accuracy": 0.7708333134651184,
|
| 154 |
-
"eval_loss": 0.7507086396217346,
|
| 155 |
-
"eval_runtime": 11.1455,
|
| 156 |
-
"eval_samples_per_second": 4.307,
|
| 157 |
-
"eval_steps_per_second": 1.077,
|
| 158 |
-
"step": 100
|
| 159 |
-
},
|
| 160 |
-
{
|
| 161 |
-
"epoch": 4.58,
|
| 162 |
-
"learning_rate": 3.3333333333333335e-05,
|
| 163 |
-
"loss": 0.0564,
|
| 164 |
-
"step": 110
|
| 165 |
-
},
|
| 166 |
-
{
|
| 167 |
-
"epoch": 4.58,
|
| 168 |
-
"eval_accuracy": 0.7916666865348816,
|
| 169 |
-
"eval_loss": 0.7551252841949463,
|
| 170 |
-
"eval_runtime": 10.0567,
|
| 171 |
-
"eval_samples_per_second": 4.773,
|
| 172 |
-
"eval_steps_per_second": 1.193,
|
| 173 |
-
"step": 110
|
| 174 |
-
},
|
| 175 |
-
{
|
| 176 |
-
"epoch": 5.0,
|
| 177 |
-
"learning_rate": 2.916666666666667e-05,
|
| 178 |
-
"loss": 0.0767,
|
| 179 |
-
"step": 120
|
| 180 |
-
},
|
| 181 |
-
{
|
| 182 |
-
"epoch": 5.0,
|
| 183 |
-
"eval_accuracy": 0.7916666865348816,
|
| 184 |
-
"eval_loss": 0.7378367781639099,
|
| 185 |
-
"eval_runtime": 11.5811,
|
| 186 |
-
"eval_samples_per_second": 4.145,
|
| 187 |
-
"eval_steps_per_second": 1.036,
|
| 188 |
-
"step": 120
|
| 189 |
-
},
|
| 190 |
-
{
|
| 191 |
-
"epoch": 5.42,
|
| 192 |
-
"learning_rate": 2.5e-05,
|
| 193 |
-
"loss": 0.0464,
|
| 194 |
-
"step": 130
|
| 195 |
-
},
|
| 196 |
-
{
|
| 197 |
-
"epoch": 5.42,
|
| 198 |
-
"eval_accuracy": 0.7291666865348816,
|
| 199 |
-
"eval_loss": 1.1143478155136108,
|
| 200 |
-
"eval_runtime": 10.0199,
|
| 201 |
-
"eval_samples_per_second": 4.79,
|
| 202 |
-
"eval_steps_per_second": 1.198,
|
| 203 |
-
"step": 130
|
| 204 |
-
},
|
| 205 |
-
{
|
| 206 |
-
"epoch": 5.83,
|
| 207 |
-
"learning_rate": 2.0833333333333336e-05,
|
| 208 |
-
"loss": 0.0996,
|
| 209 |
-
"step": 140
|
| 210 |
-
},
|
| 211 |
-
{
|
| 212 |
-
"epoch": 5.83,
|
| 213 |
-
"eval_accuracy": 0.8333333134651184,
|
| 214 |
-
"eval_loss": 0.6909031867980957,
|
| 215 |
-
"eval_runtime": 11.7023,
|
| 216 |
-
"eval_samples_per_second": 4.102,
|
| 217 |
-
"eval_steps_per_second": 1.025,
|
| 218 |
-
"step": 140
|
| 219 |
-
},
|
| 220 |
-
{
|
| 221 |
-
"epoch": 6.25,
|
| 222 |
-
"learning_rate": 1.6666666666666667e-05,
|
| 223 |
-
"loss": 0.0166,
|
| 224 |
-
"step": 150
|
| 225 |
-
},
|
| 226 |
-
{
|
| 227 |
-
"epoch": 6.25,
|
| 228 |
-
"eval_accuracy": 0.8333333134651184,
|
| 229 |
-
"eval_loss": 0.6695077419281006,
|
| 230 |
-
"eval_runtime": 9.8609,
|
| 231 |
-
"eval_samples_per_second": 4.868,
|
| 232 |
-
"eval_steps_per_second": 1.217,
|
| 233 |
-
"step": 150
|
| 234 |
-
},
|
| 235 |
-
{
|
| 236 |
-
"epoch": 6.67,
|
| 237 |
-
"learning_rate": 1.25e-05,
|
| 238 |
-
"loss": 0.0547,
|
| 239 |
-
"step": 160
|
| 240 |
-
},
|
| 241 |
-
{
|
| 242 |
-
"epoch": 6.67,
|
| 243 |
-
"eval_accuracy": 0.75,
|
| 244 |
-
"eval_loss": 0.9423481822013855,
|
| 245 |
-
"eval_runtime": 11.5884,
|
| 246 |
-
"eval_samples_per_second": 4.142,
|
| 247 |
-
"eval_steps_per_second": 1.036,
|
| 248 |
-
"step": 160
|
| 249 |
-
},
|
| 250 |
-
{
|
| 251 |
-
"epoch": 7.08,
|
| 252 |
-
"learning_rate": 8.333333333333334e-06,
|
| 253 |
-
"loss": 0.1214,
|
| 254 |
-
"step": 170
|
| 255 |
-
},
|
| 256 |
-
{
|
| 257 |
-
"epoch": 7.08,
|
| 258 |
-
"eval_accuracy": 0.7916666865348816,
|
| 259 |
-
"eval_loss": 0.7280401587486267,
|
| 260 |
-
"eval_runtime": 10.0684,
|
| 261 |
-
"eval_samples_per_second": 4.767,
|
| 262 |
-
"eval_steps_per_second": 1.192,
|
| 263 |
-
"step": 170
|
| 264 |
-
},
|
| 265 |
-
{
|
| 266 |
-
"epoch": 7.5,
|
| 267 |
-
"learning_rate": 4.166666666666667e-06,
|
| 268 |
-
"loss": 0.0096,
|
| 269 |
-
"step": 180
|
| 270 |
-
},
|
| 271 |
-
{
|
| 272 |
-
"epoch": 7.5,
|
| 273 |
-
"eval_accuracy": 0.7916666865348816,
|
| 274 |
-
"eval_loss": 0.6912185549736023,
|
| 275 |
-
"eval_runtime": 11.3942,
|
| 276 |
-
"eval_samples_per_second": 4.213,
|
| 277 |
-
"eval_steps_per_second": 1.053,
|
| 278 |
-
"step": 180
|
| 279 |
-
},
|
| 280 |
-
{
|
| 281 |
-
"epoch": 7.92,
|
| 282 |
-
"learning_rate": 0.0,
|
| 283 |
-
"loss": 0.0611,
|
| 284 |
-
"step": 190
|
| 285 |
-
},
|
| 286 |
-
{
|
| 287 |
-
"epoch": 7.92,
|
| 288 |
-
"eval_accuracy": 0.7916666865348816,
|
| 289 |
-
"eval_loss": 0.6880165934562683,
|
| 290 |
-
"eval_runtime": 10.0683,
|
| 291 |
-
"eval_samples_per_second": 4.767,
|
| 292 |
-
"eval_steps_per_second": 1.192,
|
| 293 |
-
"step": 190
|
| 294 |
-
},
|
| 295 |
-
{
|
| 296 |
-
"epoch": 8.33,
|
| 297 |
-
"learning_rate": 0.0,
|
| 298 |
-
"loss": 0.0254,
|
| 299 |
-
"step": 200
|
| 300 |
-
},
|
| 301 |
-
{
|
| 302 |
-
"epoch": 8.33,
|
| 303 |
-
"eval_accuracy": 0.7916666865348816,
|
| 304 |
-
"eval_loss": 0.6880165934562683,
|
| 305 |
-
"eval_runtime": 12.1412,
|
| 306 |
-
"eval_samples_per_second": 3.953,
|
| 307 |
-
"eval_steps_per_second": 0.988,
|
| 308 |
-
"step": 200
|
| 309 |
-
},
|
| 310 |
-
{
|
| 311 |
-
"epoch": 8.75,
|
| 312 |
-
"learning_rate": 0.0,
|
| 313 |
-
"loss": 0.0073,
|
| 314 |
-
"step": 210
|
| 315 |
-
},
|
| 316 |
-
{
|
| 317 |
-
"epoch": 8.75,
|
| 318 |
-
"eval_accuracy": 0.7916666865348816,
|
| 319 |
-
"eval_loss": 0.6880165934562683,
|
| 320 |
-
"eval_runtime": 9.9345,
|
| 321 |
-
"eval_samples_per_second": 4.832,
|
| 322 |
-
"eval_steps_per_second": 1.208,
|
| 323 |
-
"step": 210
|
| 324 |
-
},
|
| 325 |
-
{
|
| 326 |
-
"epoch": 9.17,
|
| 327 |
-
"learning_rate": 0.0,
|
| 328 |
-
"loss": 0.0153,
|
| 329 |
-
"step": 220
|
| 330 |
-
},
|
| 331 |
-
{
|
| 332 |
-
"epoch": 9.17,
|
| 333 |
-
"eval_accuracy": 0.7916666865348816,
|
| 334 |
-
"eval_loss": 0.6880165934562683,
|
| 335 |
-
"eval_runtime": 10.0673,
|
| 336 |
-
"eval_samples_per_second": 4.768,
|
| 337 |
-
"eval_steps_per_second": 1.192,
|
| 338 |
-
"step": 220
|
| 339 |
-
},
|
| 340 |
-
{
|
| 341 |
-
"epoch": 9.58,
|
| 342 |
-
"learning_rate": 0.0,
|
| 343 |
-
"loss": 0.0093,
|
| 344 |
-
"step": 230
|
| 345 |
-
},
|
| 346 |
-
{
|
| 347 |
-
"epoch": 9.58,
|
| 348 |
-
"eval_accuracy": 0.7916666865348816,
|
| 349 |
-
"eval_loss": 0.6880165934562683,
|
| 350 |
-
"eval_runtime": 9.9352,
|
| 351 |
-
"eval_samples_per_second": 4.831,
|
| 352 |
-
"eval_steps_per_second": 1.208,
|
| 353 |
-
"step": 230
|
| 354 |
-
},
|
| 355 |
-
{
|
| 356 |
-
"epoch": 10.0,
|
| 357 |
-
"learning_rate": 0.0,
|
| 358 |
-
"loss": 0.0575,
|
| 359 |
-
"step": 240
|
| 360 |
-
},
|
| 361 |
-
{
|
| 362 |
-
"epoch": 10.0,
|
| 363 |
-
"eval_accuracy": 0.7916666865348816,
|
| 364 |
-
"eval_loss": 0.6880165934562683,
|
| 365 |
-
"eval_runtime": 10.1458,
|
| 366 |
-
"eval_samples_per_second": 4.731,
|
| 367 |
-
"eval_steps_per_second": 1.183,
|
| 368 |
-
"step": 240
|
| 369 |
}
|
| 370 |
],
|
| 371 |
-
"max_steps":
|
| 372 |
-
"num_train_epochs":
|
| 373 |
-
"total_flos":
|
| 374 |
"trial_name": null,
|
| 375 |
"trial_params": null
|
| 376 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.3908045977011494,
|
| 5 |
+
"global_step": 60,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
| 9 |
"log_history": [
|
| 10 |
{
|
| 11 |
+
"epoch": 0.23,
|
| 12 |
+
"learning_rate": 9.418604651162792e-05,
|
| 13 |
+
"loss": 1.9238,
|
| 14 |
"step": 10
|
| 15 |
},
|
| 16 |
{
|
| 17 |
+
"epoch": 0.23,
|
| 18 |
+
"eval_accuracy": 0.1818181872367859,
|
| 19 |
+
"eval_loss": 1.9564208984375,
|
| 20 |
+
"eval_runtime": 19.1351,
|
| 21 |
+
"eval_samples_per_second": 4.599,
|
| 22 |
+
"eval_steps_per_second": 1.15,
|
| 23 |
"step": 10
|
| 24 |
},
|
| 25 |
{
|
| 26 |
+
"epoch": 0.46,
|
| 27 |
+
"learning_rate": 8.837209302325582e-05,
|
| 28 |
+
"loss": 1.9589,
|
| 29 |
"step": 20
|
| 30 |
},
|
| 31 |
{
|
| 32 |
+
"epoch": 0.46,
|
| 33 |
+
"eval_accuracy": 0.15909090638160706,
|
| 34 |
+
"eval_loss": 1.9498623609542847,
|
| 35 |
+
"eval_runtime": 21.5957,
|
| 36 |
+
"eval_samples_per_second": 4.075,
|
| 37 |
+
"eval_steps_per_second": 1.019,
|
| 38 |
"step": 20
|
| 39 |
},
|
| 40 |
{
|
| 41 |
+
"epoch": 0.69,
|
| 42 |
+
"learning_rate": 8.255813953488373e-05,
|
| 43 |
+
"loss": 1.9677,
|
| 44 |
"step": 30
|
| 45 |
},
|
| 46 |
{
|
| 47 |
+
"epoch": 0.69,
|
| 48 |
+
"eval_accuracy": 0.17045454680919647,
|
| 49 |
+
"eval_loss": 1.8762873411178589,
|
| 50 |
+
"eval_runtime": 19.1489,
|
| 51 |
+
"eval_samples_per_second": 4.596,
|
| 52 |
+
"eval_steps_per_second": 1.149,
|
| 53 |
"step": 30
|
| 54 |
},
|
| 55 |
{
|
| 56 |
+
"epoch": 0.92,
|
| 57 |
+
"learning_rate": 7.674418604651163e-05,
|
| 58 |
+
"loss": 1.9357,
|
| 59 |
"step": 40
|
| 60 |
},
|
| 61 |
{
|
| 62 |
+
"epoch": 0.92,
|
| 63 |
+
"eval_accuracy": 0.21590909361839294,
|
| 64 |
+
"eval_loss": 1.8796330690383911,
|
| 65 |
+
"eval_runtime": 21.6027,
|
| 66 |
+
"eval_samples_per_second": 4.074,
|
| 67 |
+
"eval_steps_per_second": 1.018,
|
| 68 |
"step": 40
|
| 69 |
},
|
| 70 |
{
|
| 71 |
+
"epoch": 1.16,
|
| 72 |
+
"learning_rate": 7.093023255813955e-05,
|
| 73 |
+
"loss": 1.9529,
|
| 74 |
"step": 50
|
| 75 |
},
|
| 76 |
{
|
| 77 |
+
"epoch": 1.16,
|
| 78 |
+
"eval_accuracy": 0.22727273404598236,
|
| 79 |
+
"eval_loss": 1.841020107269287,
|
| 80 |
+
"eval_runtime": 22.0824,
|
| 81 |
+
"eval_samples_per_second": 3.985,
|
| 82 |
+
"eval_steps_per_second": 0.996,
|
| 83 |
"step": 50
|
| 84 |
},
|
| 85 |
{
|
| 86 |
+
"epoch": 1.39,
|
| 87 |
+
"learning_rate": 6.511627906976745e-05,
|
| 88 |
+
"loss": 1.8197,
|
| 89 |
"step": 60
|
| 90 |
},
|
| 91 |
{
|
| 92 |
+
"epoch": 1.39,
|
| 93 |
+
"eval_accuracy": 0.35227271914482117,
|
| 94 |
+
"eval_loss": 1.6947021484375,
|
| 95 |
+
"eval_runtime": 21.8177,
|
| 96 |
+
"eval_samples_per_second": 4.033,
|
| 97 |
+
"eval_steps_per_second": 1.008,
|
| 98 |
"step": 60
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 99 |
}
|
| 100 |
],
|
| 101 |
+
"max_steps": 172,
|
| 102 |
+
"num_train_epochs": 4,
|
| 103 |
+
"total_flos": 1.7581701250290854e+17,
|
| 104 |
"trial_name": null,
|
| 105 |
"trial_params": null
|
| 106 |
}
|