Training in progress, step 150, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 100689176
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9c0dcc370af7068987019d5ad7c55775cd4aa685f984103fd5fb8da8d0263a78
|
| 3 |
size 100689176
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 201488698
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5c6a4f4139c8708380a359a5afcbe53de60e8b0bdaaaef9b89ffbc87e489ebb1
|
| 3 |
size 201488698
|
last-checkpoint/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:adee8db53dd522679041ac1e22258a9dccde0894ff7e7335c959c7a488f59fa9
|
| 3 |
+
size 14244
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1256
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e5f37e21fbe85e09b136734aed2deb2ce642b5bd3d64c65196a2c110d8c5ff3a
|
| 3 |
size 1256
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,351 +1,125 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 1.
|
| 3 |
-
"best_model_checkpoint": "./output/checkpoint-
|
| 4 |
-
"epoch": 0.
|
| 5 |
"eval_steps": 150,
|
| 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 |
-
"grad_norm": 1.
|
| 14 |
-
"learning_rate":
|
| 15 |
-
"loss": 1.
|
| 16 |
"step": 10
|
| 17 |
},
|
| 18 |
{
|
| 19 |
-
"epoch": 0.
|
| 20 |
-
"grad_norm": 1.
|
| 21 |
-
"learning_rate":
|
| 22 |
-
"loss": 1.
|
| 23 |
"step": 20
|
| 24 |
},
|
| 25 |
{
|
| 26 |
-
"epoch": 0.
|
| 27 |
-
"grad_norm":
|
| 28 |
-
"learning_rate":
|
| 29 |
-
"loss": 1.
|
| 30 |
"step": 30
|
| 31 |
},
|
| 32 |
{
|
| 33 |
-
"epoch": 0.
|
| 34 |
-
"grad_norm":
|
| 35 |
-
"learning_rate":
|
| 36 |
-
"loss":
|
| 37 |
"step": 40
|
| 38 |
},
|
| 39 |
{
|
| 40 |
-
"epoch": 0.
|
| 41 |
-
"grad_norm": 1.
|
| 42 |
-
"learning_rate":
|
| 43 |
-
"loss": 1.
|
| 44 |
"step": 50
|
| 45 |
},
|
| 46 |
{
|
| 47 |
-
"epoch": 0.
|
| 48 |
-
"grad_norm": 1.
|
| 49 |
-
"learning_rate":
|
| 50 |
-
"loss": 1.
|
| 51 |
"step": 60
|
| 52 |
},
|
| 53 |
{
|
| 54 |
-
"epoch": 0.
|
| 55 |
-
"grad_norm": 1.
|
| 56 |
-
"learning_rate":
|
| 57 |
-
"loss": 1.
|
| 58 |
"step": 70
|
| 59 |
},
|
| 60 |
{
|
| 61 |
-
"epoch": 0.
|
| 62 |
-
"grad_norm":
|
| 63 |
-
"learning_rate":
|
| 64 |
-
"loss": 1.
|
| 65 |
"step": 80
|
| 66 |
},
|
| 67 |
{
|
| 68 |
-
"epoch": 0.
|
| 69 |
-
"grad_norm":
|
| 70 |
-
"learning_rate":
|
| 71 |
-
"loss": 1.
|
| 72 |
"step": 90
|
| 73 |
},
|
| 74 |
{
|
| 75 |
-
"epoch": 0.
|
| 76 |
-
"grad_norm": 1.
|
| 77 |
-
"learning_rate":
|
| 78 |
-
"loss": 1.
|
| 79 |
"step": 100
|
| 80 |
},
|
| 81 |
{
|
| 82 |
-
"epoch": 0.
|
| 83 |
-
"grad_norm": 1.
|
| 84 |
-
"learning_rate":
|
| 85 |
-
"loss": 1.
|
| 86 |
"step": 110
|
| 87 |
},
|
| 88 |
{
|
| 89 |
-
"epoch": 0.
|
| 90 |
-
"grad_norm": 1.
|
| 91 |
-
"learning_rate":
|
| 92 |
-
"loss": 1.
|
| 93 |
"step": 120
|
| 94 |
},
|
| 95 |
{
|
| 96 |
-
"epoch": 0.
|
| 97 |
-
"grad_norm":
|
| 98 |
-
"learning_rate":
|
| 99 |
-
"loss": 1.
|
| 100 |
"step": 130
|
| 101 |
},
|
| 102 |
{
|
| 103 |
-
"epoch": 0.
|
| 104 |
-
"grad_norm":
|
| 105 |
-
"learning_rate":
|
| 106 |
-
"loss": 1.
|
| 107 |
"step": 140
|
| 108 |
},
|
| 109 |
{
|
| 110 |
-
"epoch": 0.
|
| 111 |
-
"grad_norm":
|
| 112 |
-
"learning_rate":
|
| 113 |
-
"loss": 1.
|
| 114 |
"step": 150
|
| 115 |
},
|
| 116 |
{
|
| 117 |
-
"epoch": 0.
|
| 118 |
-
"eval_loss": 1.
|
| 119 |
-
"eval_runtime": 68.
|
| 120 |
-
"eval_samples_per_second": 7.
|
| 121 |
-
"eval_steps_per_second": 7.
|
| 122 |
"step": 150
|
| 123 |
-
},
|
| 124 |
-
{
|
| 125 |
-
"epoch": 0.011579099724996381,
|
| 126 |
-
"grad_norm": 1.0022648572921753,
|
| 127 |
-
"learning_rate": 0.00012495376120044173,
|
| 128 |
-
"loss": 1.0762,
|
| 129 |
-
"step": 160
|
| 130 |
-
},
|
| 131 |
-
{
|
| 132 |
-
"epoch": 0.012302793457808655,
|
| 133 |
-
"grad_norm": 1.0098097324371338,
|
| 134 |
-
"learning_rate": 0.00012493706665883217,
|
| 135 |
-
"loss": 1.0473,
|
| 136 |
-
"step": 170
|
| 137 |
-
},
|
| 138 |
-
{
|
| 139 |
-
"epoch": 0.013026487190620929,
|
| 140 |
-
"grad_norm": 0.9342713952064514,
|
| 141 |
-
"learning_rate": 0.00012491780557396154,
|
| 142 |
-
"loss": 1.2133,
|
| 143 |
-
"step": 180
|
| 144 |
-
},
|
| 145 |
-
{
|
| 146 |
-
"epoch": 0.013750180923433204,
|
| 147 |
-
"grad_norm": 1.2415492534637451,
|
| 148 |
-
"learning_rate": 0.00012489597873757756,
|
| 149 |
-
"loss": 1.1635,
|
| 150 |
-
"step": 190
|
| 151 |
-
},
|
| 152 |
-
{
|
| 153 |
-
"epoch": 0.014473874656245478,
|
| 154 |
-
"grad_norm": 0.727070152759552,
|
| 155 |
-
"learning_rate": 0.00012487158704689602,
|
| 156 |
-
"loss": 1.1106,
|
| 157 |
-
"step": 200
|
| 158 |
-
},
|
| 159 |
-
{
|
| 160 |
-
"epoch": 0.015197568389057751,
|
| 161 |
-
"grad_norm": 1.039361596107483,
|
| 162 |
-
"learning_rate": 0.0001248446315045638,
|
| 163 |
-
"loss": 1.1199,
|
| 164 |
-
"step": 210
|
| 165 |
-
},
|
| 166 |
-
{
|
| 167 |
-
"epoch": 0.015921262121870023,
|
| 168 |
-
"grad_norm": 1.1260257959365845,
|
| 169 |
-
"learning_rate": 0.00012481511321861763,
|
| 170 |
-
"loss": 1.1924,
|
| 171 |
-
"step": 220
|
| 172 |
-
},
|
| 173 |
-
{
|
| 174 |
-
"epoch": 0.0166449558546823,
|
| 175 |
-
"grad_norm": 0.9752004742622375,
|
| 176 |
-
"learning_rate": 0.00012478303340243864,
|
| 177 |
-
"loss": 1.0699,
|
| 178 |
-
"step": 230
|
| 179 |
-
},
|
| 180 |
-
{
|
| 181 |
-
"epoch": 0.017368649587494574,
|
| 182 |
-
"grad_norm": 1.4011763334274292,
|
| 183 |
-
"learning_rate": 0.00012474839337470246,
|
| 184 |
-
"loss": 1.106,
|
| 185 |
-
"step": 240
|
| 186 |
-
},
|
| 187 |
-
{
|
| 188 |
-
"epoch": 0.018092343320306847,
|
| 189 |
-
"grad_norm": 0.9429338574409485,
|
| 190 |
-
"learning_rate": 0.0001247111945593249,
|
| 191 |
-
"loss": 1.161,
|
| 192 |
-
"step": 250
|
| 193 |
-
},
|
| 194 |
-
{
|
| 195 |
-
"epoch": 0.01881603705311912,
|
| 196 |
-
"grad_norm": 1.0999586582183838,
|
| 197 |
-
"learning_rate": 0.00012467143848540359,
|
| 198 |
-
"loss": 1.1911,
|
| 199 |
-
"step": 260
|
| 200 |
-
},
|
| 201 |
-
{
|
| 202 |
-
"epoch": 0.019539730785931395,
|
| 203 |
-
"grad_norm": 1.1027190685272217,
|
| 204 |
-
"learning_rate": 0.000124629126787155,
|
| 205 |
-
"loss": 1.2331,
|
| 206 |
-
"step": 270
|
| 207 |
-
},
|
| 208 |
-
{
|
| 209 |
-
"epoch": 0.020263424518743668,
|
| 210 |
-
"grad_norm": 0.9375354647636414,
|
| 211 |
-
"learning_rate": 0.00012458426120384738,
|
| 212 |
-
"loss": 1.0836,
|
| 213 |
-
"step": 280
|
| 214 |
-
},
|
| 215 |
-
{
|
| 216 |
-
"epoch": 0.020987118251555942,
|
| 217 |
-
"grad_norm": 2.151923894882202,
|
| 218 |
-
"learning_rate": 0.00012453684357972906,
|
| 219 |
-
"loss": 1.0584,
|
| 220 |
-
"step": 290
|
| 221 |
-
},
|
| 222 |
-
{
|
| 223 |
-
"epoch": 0.021710811984368215,
|
| 224 |
-
"grad_norm": 0.833605945110321,
|
| 225 |
-
"learning_rate": 0.00012448687586395289,
|
| 226 |
-
"loss": 1.1453,
|
| 227 |
-
"step": 300
|
| 228 |
-
},
|
| 229 |
-
{
|
| 230 |
-
"epoch": 0.021710811984368215,
|
| 231 |
-
"eval_loss": 1.061118483543396,
|
| 232 |
-
"eval_runtime": 67.9747,
|
| 233 |
-
"eval_samples_per_second": 7.356,
|
| 234 |
-
"eval_steps_per_second": 7.356,
|
| 235 |
-
"step": 300
|
| 236 |
-
},
|
| 237 |
-
{
|
| 238 |
-
"epoch": 0.02243450571718049,
|
| 239 |
-
"grad_norm": 1.0999945402145386,
|
| 240 |
-
"learning_rate": 0.00012443436011049593,
|
| 241 |
-
"loss": 1.2021,
|
| 242 |
-
"step": 310
|
| 243 |
-
},
|
| 244 |
-
{
|
| 245 |
-
"epoch": 0.023158199449992763,
|
| 246 |
-
"grad_norm": 1.1812015771865845,
|
| 247 |
-
"learning_rate": 0.0001243792984780751,
|
| 248 |
-
"loss": 1.0777,
|
| 249 |
-
"step": 320
|
| 250 |
-
},
|
| 251 |
-
{
|
| 252 |
-
"epoch": 0.023881893182805036,
|
| 253 |
-
"grad_norm": 1.6861599683761597,
|
| 254 |
-
"learning_rate": 0.00012432169323005853,
|
| 255 |
-
"loss": 1.1632,
|
| 256 |
-
"step": 330
|
| 257 |
-
},
|
| 258 |
-
{
|
| 259 |
-
"epoch": 0.02460558691561731,
|
| 260 |
-
"grad_norm": 1.1688460111618042,
|
| 261 |
-
"learning_rate": 0.00012426154673437223,
|
| 262 |
-
"loss": 1.07,
|
| 263 |
-
"step": 340
|
| 264 |
-
},
|
| 265 |
-
{
|
| 266 |
-
"epoch": 0.025329280648429583,
|
| 267 |
-
"grad_norm": 0.8406811952590942,
|
| 268 |
-
"learning_rate": 0.00012419886146340314,
|
| 269 |
-
"loss": 1.0175,
|
| 270 |
-
"step": 350
|
| 271 |
-
},
|
| 272 |
-
{
|
| 273 |
-
"epoch": 0.026052974381241857,
|
| 274 |
-
"grad_norm": 1.205870270729065,
|
| 275 |
-
"learning_rate": 0.0001241336399938972,
|
| 276 |
-
"loss": 1.2039,
|
| 277 |
-
"step": 360
|
| 278 |
-
},
|
| 279 |
-
{
|
| 280 |
-
"epoch": 0.02677666811405413,
|
| 281 |
-
"grad_norm": 0.7990264296531677,
|
| 282 |
-
"learning_rate": 0.00012406588500685355,
|
| 283 |
-
"loss": 1.0588,
|
| 284 |
-
"step": 370
|
| 285 |
-
},
|
| 286 |
-
{
|
| 287 |
-
"epoch": 0.027500361846866408,
|
| 288 |
-
"grad_norm": 1.1303527355194092,
|
| 289 |
-
"learning_rate": 0.00012399559928741435,
|
| 290 |
-
"loss": 1.1073,
|
| 291 |
-
"step": 380
|
| 292 |
-
},
|
| 293 |
-
{
|
| 294 |
-
"epoch": 0.02822405557967868,
|
| 295 |
-
"grad_norm": 0.7280349731445312,
|
| 296 |
-
"learning_rate": 0.00012392278572475023,
|
| 297 |
-
"loss": 1.0966,
|
| 298 |
-
"step": 390
|
| 299 |
-
},
|
| 300 |
-
{
|
| 301 |
-
"epoch": 0.028947749312490955,
|
| 302 |
-
"grad_norm": 1.076653242111206,
|
| 303 |
-
"learning_rate": 0.0001238474473119416,
|
| 304 |
-
"loss": 1.111,
|
| 305 |
-
"step": 400
|
| 306 |
-
},
|
| 307 |
-
{
|
| 308 |
-
"epoch": 0.02967144304530323,
|
| 309 |
-
"grad_norm": 0.9253267049789429,
|
| 310 |
-
"learning_rate": 0.00012376958714585545,
|
| 311 |
-
"loss": 1.1165,
|
| 312 |
-
"step": 410
|
| 313 |
-
},
|
| 314 |
-
{
|
| 315 |
-
"epoch": 0.030395136778115502,
|
| 316 |
-
"grad_norm": 0.9444619417190552,
|
| 317 |
-
"learning_rate": 0.0001236892084270183,
|
| 318 |
-
"loss": 1.1612,
|
| 319 |
-
"step": 420
|
| 320 |
-
},
|
| 321 |
-
{
|
| 322 |
-
"epoch": 0.031118830510927776,
|
| 323 |
-
"grad_norm": 1.2068166732788086,
|
| 324 |
-
"learning_rate": 0.00012360631445948448,
|
| 325 |
-
"loss": 1.1822,
|
| 326 |
-
"step": 430
|
| 327 |
-
},
|
| 328 |
-
{
|
| 329 |
-
"epoch": 0.031842524243740046,
|
| 330 |
-
"grad_norm": 0.8767175674438477,
|
| 331 |
-
"learning_rate": 0.00012352090865070026,
|
| 332 |
-
"loss": 0.9645,
|
| 333 |
-
"step": 440
|
| 334 |
-
},
|
| 335 |
-
{
|
| 336 |
-
"epoch": 0.03256621797655232,
|
| 337 |
-
"grad_norm": 0.8043785691261292,
|
| 338 |
-
"learning_rate": 0.00012343299451136397,
|
| 339 |
-
"loss": 1.1397,
|
| 340 |
-
"step": 450
|
| 341 |
-
},
|
| 342 |
-
{
|
| 343 |
-
"epoch": 0.03256621797655232,
|
| 344 |
-
"eval_loss": 1.0556260347366333,
|
| 345 |
-
"eval_runtime": 67.7421,
|
| 346 |
-
"eval_samples_per_second": 7.381,
|
| 347 |
-
"eval_steps_per_second": 7.381,
|
| 348 |
-
"step": 450
|
| 349 |
}
|
| 350 |
],
|
| 351 |
"logging_steps": 10,
|
|
@@ -365,8 +139,8 @@
|
|
| 365 |
"attributes": {}
|
| 366 |
}
|
| 367 |
},
|
| 368 |
-
"total_flos":
|
| 369 |
-
"train_batch_size":
|
| 370 |
"trial_name": null,
|
| 371 |
"trial_params": null
|
| 372 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 1.0342717170715332,
|
| 3 |
+
"best_model_checkpoint": "./output/checkpoint-150",
|
| 4 |
+
"epoch": 0.005427702996092054,
|
| 5 |
"eval_steps": 150,
|
| 6 |
+
"global_step": 150,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
+
"epoch": 0.0003618468664061369,
|
| 13 |
+
"grad_norm": 1.2045749425888062,
|
| 14 |
+
"learning_rate": 5.500000000000001e-06,
|
| 15 |
+
"loss": 1.144,
|
| 16 |
"step": 10
|
| 17 |
},
|
| 18 |
{
|
| 19 |
+
"epoch": 0.0007236937328122738,
|
| 20 |
+
"grad_norm": 1.50728178024292,
|
| 21 |
+
"learning_rate": 1.1000000000000001e-05,
|
| 22 |
+
"loss": 1.1809,
|
| 23 |
"step": 20
|
| 24 |
},
|
| 25 |
{
|
| 26 |
+
"epoch": 0.0010855405992184109,
|
| 27 |
+
"grad_norm": 0.9494473934173584,
|
| 28 |
+
"learning_rate": 1.65e-05,
|
| 29 |
+
"loss": 1.0738,
|
| 30 |
"step": 30
|
| 31 |
},
|
| 32 |
{
|
| 33 |
+
"epoch": 0.0014473874656245477,
|
| 34 |
+
"grad_norm": 0.957133948802948,
|
| 35 |
+
"learning_rate": 2.2000000000000003e-05,
|
| 36 |
+
"loss": 0.9573,
|
| 37 |
"step": 40
|
| 38 |
},
|
| 39 |
{
|
| 40 |
+
"epoch": 0.0018092343320306847,
|
| 41 |
+
"grad_norm": 1.7268428802490234,
|
| 42 |
+
"learning_rate": 2.75e-05,
|
| 43 |
+
"loss": 1.0361,
|
| 44 |
"step": 50
|
| 45 |
},
|
| 46 |
{
|
| 47 |
+
"epoch": 0.0021710811984368217,
|
| 48 |
+
"grad_norm": 1.1843866109848022,
|
| 49 |
+
"learning_rate": 3.3e-05,
|
| 50 |
+
"loss": 1.0351,
|
| 51 |
"step": 60
|
| 52 |
},
|
| 53 |
{
|
| 54 |
+
"epoch": 0.0025329280648429585,
|
| 55 |
+
"grad_norm": 1.5817480087280273,
|
| 56 |
+
"learning_rate": 3.85e-05,
|
| 57 |
+
"loss": 1.1654,
|
| 58 |
"step": 70
|
| 59 |
},
|
| 60 |
{
|
| 61 |
+
"epoch": 0.0028947749312490953,
|
| 62 |
+
"grad_norm": 0.8221575617790222,
|
| 63 |
+
"learning_rate": 4.4000000000000006e-05,
|
| 64 |
+
"loss": 1.1031,
|
| 65 |
"step": 80
|
| 66 |
},
|
| 67 |
{
|
| 68 |
+
"epoch": 0.003256621797655232,
|
| 69 |
+
"grad_norm": 1.0210144519805908,
|
| 70 |
+
"learning_rate": 4.9500000000000004e-05,
|
| 71 |
+
"loss": 1.2083,
|
| 72 |
"step": 90
|
| 73 |
},
|
| 74 |
{
|
| 75 |
+
"epoch": 0.0036184686640613694,
|
| 76 |
+
"grad_norm": 1.6523082256317139,
|
| 77 |
+
"learning_rate": 5.5e-05,
|
| 78 |
+
"loss": 1.1551,
|
| 79 |
"step": 100
|
| 80 |
},
|
| 81 |
{
|
| 82 |
+
"epoch": 0.003980315530467506,
|
| 83 |
+
"grad_norm": 1.3959214687347412,
|
| 84 |
+
"learning_rate": 5.4999434791355066e-05,
|
| 85 |
+
"loss": 1.2088,
|
| 86 |
"step": 110
|
| 87 |
},
|
| 88 |
{
|
| 89 |
+
"epoch": 0.004342162396873643,
|
| 90 |
+
"grad_norm": 1.7850854396820068,
|
| 91 |
+
"learning_rate": 5.4997739188653784e-05,
|
| 92 |
+
"loss": 1.0394,
|
| 93 |
"step": 120
|
| 94 |
},
|
| 95 |
{
|
| 96 |
+
"epoch": 0.00470400926327978,
|
| 97 |
+
"grad_norm": 1.707861304283142,
|
| 98 |
+
"learning_rate": 5.4994913261595724e-05,
|
| 99 |
+
"loss": 1.0406,
|
| 100 |
"step": 130
|
| 101 |
},
|
| 102 |
{
|
| 103 |
+
"epoch": 0.005065856129685917,
|
| 104 |
+
"grad_norm": 1.622674584388733,
|
| 105 |
+
"learning_rate": 5.49909571263437e-05,
|
| 106 |
+
"loss": 1.0781,
|
| 107 |
"step": 140
|
| 108 |
},
|
| 109 |
{
|
| 110 |
+
"epoch": 0.005427702996092054,
|
| 111 |
+
"grad_norm": 1.135132908821106,
|
| 112 |
+
"learning_rate": 5.498587094551892e-05,
|
| 113 |
+
"loss": 1.2658,
|
| 114 |
"step": 150
|
| 115 |
},
|
| 116 |
{
|
| 117 |
+
"epoch": 0.005427702996092054,
|
| 118 |
+
"eval_loss": 1.0342717170715332,
|
| 119 |
+
"eval_runtime": 68.3584,
|
| 120 |
+
"eval_samples_per_second": 7.314,
|
| 121 |
+
"eval_steps_per_second": 7.314,
|
| 122 |
"step": 150
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 123 |
}
|
| 124 |
],
|
| 125 |
"logging_steps": 10,
|
|
|
|
| 139 |
"attributes": {}
|
| 140 |
}
|
| 141 |
},
|
| 142 |
+
"total_flos": 1.358716220940288e+16,
|
| 143 |
+
"train_batch_size": 4,
|
| 144 |
"trial_name": null,
|
| 145 |
"trial_params": null
|
| 146 |
}
|
last-checkpoint/training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5496
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:36ffe1bc7f9782a0960f25658b63a6896f6292d5fbd06dd9772d5fa0c7cd4b3b
|
| 3 |
size 5496
|