Training in progress, step 100, checkpoint
Browse files
last-checkpoint/model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 136000488
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0a6e94e6f9602b019dfddf88bbd7631188723c74100c86f84c8aa54a9c83d963
|
| 3 |
size 136000488
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 268176506
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3f2395a5137dda5eb97e54395eb65f6e40d010266167d521b6e12b7cb1436435
|
| 3 |
size 268176506
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15006
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5c208ccb16ca4d1a71397af65ad74bbc2d33a691a42a2d223ddec56de42a775e
|
| 3 |
size 15006
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1064
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ea9b67c97ec0b0a1b79a6330badd5da865b550616c82ba334622fd4f95186829
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,1422 +1,27 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 1.
|
| 3 |
-
"best_model_checkpoint": "mgh6/TCS_MLM_50/checkpoint-
|
| 4 |
-
"epoch":
|
| 5 |
"eval_steps": 100,
|
| 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": 0.02902757619738752,
|
| 13 |
-
"grad_norm": 1.
|
| 14 |
"learning_rate": 9.970972423802612e-05,
|
| 15 |
-
"loss": 2.
|
| 16 |
"step": 100
|
| 17 |
},
|
| 18 |
{
|
| 19 |
"epoch": 0.02902757619738752,
|
| 20 |
-
"eval_loss": 1.
|
| 21 |
-
"eval_runtime": 213.
|
| 22 |
-
"eval_samples_per_second":
|
| 23 |
-
"eval_steps_per_second": 3.329,
|
| 24 |
-
"step": 100
|
| 25 |
-
},
|
| 26 |
-
{
|
| 27 |
-
"epoch": 0.05805515239477504,
|
| 28 |
-
"grad_norm": 1.0239707231521606,
|
| 29 |
-
"learning_rate": 9.941944847605225e-05,
|
| 30 |
-
"loss": 2.7081,
|
| 31 |
-
"step": 200
|
| 32 |
-
},
|
| 33 |
-
{
|
| 34 |
-
"epoch": 0.05805515239477504,
|
| 35 |
-
"eval_loss": 1.2453378438949585,
|
| 36 |
-
"eval_runtime": 212.9056,
|
| 37 |
-
"eval_samples_per_second": 213.705,
|
| 38 |
-
"eval_steps_per_second": 3.34,
|
| 39 |
-
"step": 200
|
| 40 |
-
},
|
| 41 |
-
{
|
| 42 |
-
"epoch": 0.08708272859216255,
|
| 43 |
-
"grad_norm": 1.1205116510391235,
|
| 44 |
-
"learning_rate": 9.912917271407838e-05,
|
| 45 |
-
"loss": 2.642,
|
| 46 |
-
"step": 300
|
| 47 |
-
},
|
| 48 |
-
{
|
| 49 |
-
"epoch": 0.08708272859216255,
|
| 50 |
-
"eval_loss": 1.2237757444381714,
|
| 51 |
-
"eval_runtime": 214.4447,
|
| 52 |
-
"eval_samples_per_second": 212.171,
|
| 53 |
-
"eval_steps_per_second": 3.316,
|
| 54 |
-
"step": 300
|
| 55 |
-
},
|
| 56 |
-
{
|
| 57 |
-
"epoch": 0.11611030478955008,
|
| 58 |
-
"grad_norm": 1.0193355083465576,
|
| 59 |
-
"learning_rate": 9.883889695210451e-05,
|
| 60 |
-
"loss": 2.6037,
|
| 61 |
-
"step": 400
|
| 62 |
-
},
|
| 63 |
-
{
|
| 64 |
-
"epoch": 0.11611030478955008,
|
| 65 |
-
"eval_loss": 1.2148627042770386,
|
| 66 |
-
"eval_runtime": 213.5123,
|
| 67 |
-
"eval_samples_per_second": 213.098,
|
| 68 |
-
"eval_steps_per_second": 3.33,
|
| 69 |
-
"step": 400
|
| 70 |
-
},
|
| 71 |
-
{
|
| 72 |
-
"epoch": 0.14513788098693758,
|
| 73 |
-
"grad_norm": 1.05299711227417,
|
| 74 |
-
"learning_rate": 9.854862119013063e-05,
|
| 75 |
-
"loss": 2.5791,
|
| 76 |
-
"step": 500
|
| 77 |
-
},
|
| 78 |
-
{
|
| 79 |
-
"epoch": 0.14513788098693758,
|
| 80 |
-
"eval_loss": 1.2020208835601807,
|
| 81 |
-
"eval_runtime": 213.769,
|
| 82 |
-
"eval_samples_per_second": 212.842,
|
| 83 |
-
"eval_steps_per_second": 3.326,
|
| 84 |
-
"step": 500
|
| 85 |
-
},
|
| 86 |
-
{
|
| 87 |
-
"epoch": 0.1741654571843251,
|
| 88 |
-
"grad_norm": 1.0508314371109009,
|
| 89 |
-
"learning_rate": 9.825834542815675e-05,
|
| 90 |
-
"loss": 2.5464,
|
| 91 |
-
"step": 600
|
| 92 |
-
},
|
| 93 |
-
{
|
| 94 |
-
"epoch": 0.1741654571843251,
|
| 95 |
-
"eval_loss": 1.1960116624832153,
|
| 96 |
-
"eval_runtime": 214.1083,
|
| 97 |
-
"eval_samples_per_second": 212.505,
|
| 98 |
-
"eval_steps_per_second": 3.321,
|
| 99 |
-
"step": 600
|
| 100 |
-
},
|
| 101 |
-
{
|
| 102 |
-
"epoch": 0.20319303338171263,
|
| 103 |
-
"grad_norm": 1.158460021018982,
|
| 104 |
-
"learning_rate": 9.796806966618288e-05,
|
| 105 |
-
"loss": 2.5391,
|
| 106 |
-
"step": 700
|
| 107 |
-
},
|
| 108 |
-
{
|
| 109 |
-
"epoch": 0.20319303338171263,
|
| 110 |
-
"eval_loss": 1.186664342880249,
|
| 111 |
-
"eval_runtime": 213.4364,
|
| 112 |
-
"eval_samples_per_second": 213.174,
|
| 113 |
-
"eval_steps_per_second": 3.331,
|
| 114 |
-
"step": 700
|
| 115 |
-
},
|
| 116 |
-
{
|
| 117 |
-
"epoch": 0.23222060957910015,
|
| 118 |
-
"grad_norm": 1.0704821348190308,
|
| 119 |
-
"learning_rate": 9.767779390420901e-05,
|
| 120 |
-
"loss": 2.4944,
|
| 121 |
-
"step": 800
|
| 122 |
-
},
|
| 123 |
-
{
|
| 124 |
-
"epoch": 0.23222060957910015,
|
| 125 |
-
"eval_loss": 1.1850290298461914,
|
| 126 |
-
"eval_runtime": 213.63,
|
| 127 |
-
"eval_samples_per_second": 212.98,
|
| 128 |
-
"eval_steps_per_second": 3.328,
|
| 129 |
-
"step": 800
|
| 130 |
-
},
|
| 131 |
-
{
|
| 132 |
-
"epoch": 0.2612481857764877,
|
| 133 |
-
"grad_norm": 1.0562227964401245,
|
| 134 |
-
"learning_rate": 9.738751814223513e-05,
|
| 135 |
-
"loss": 2.4879,
|
| 136 |
-
"step": 900
|
| 137 |
-
},
|
| 138 |
-
{
|
| 139 |
-
"epoch": 0.2612481857764877,
|
| 140 |
-
"eval_loss": 1.1725127696990967,
|
| 141 |
-
"eval_runtime": 213.7307,
|
| 142 |
-
"eval_samples_per_second": 212.88,
|
| 143 |
-
"eval_steps_per_second": 3.327,
|
| 144 |
-
"step": 900
|
| 145 |
-
},
|
| 146 |
-
{
|
| 147 |
-
"epoch": 0.29027576197387517,
|
| 148 |
-
"grad_norm": 1.136777639389038,
|
| 149 |
-
"learning_rate": 9.709724238026126e-05,
|
| 150 |
-
"loss": 2.4647,
|
| 151 |
-
"step": 1000
|
| 152 |
-
},
|
| 153 |
-
{
|
| 154 |
-
"epoch": 0.29027576197387517,
|
| 155 |
-
"eval_loss": 1.1709253787994385,
|
| 156 |
-
"eval_runtime": 213.2147,
|
| 157 |
-
"eval_samples_per_second": 213.395,
|
| 158 |
-
"eval_steps_per_second": 3.335,
|
| 159 |
-
"step": 1000
|
| 160 |
-
},
|
| 161 |
-
{
|
| 162 |
-
"epoch": 0.3193033381712627,
|
| 163 |
-
"grad_norm": 1.0949931144714355,
|
| 164 |
-
"learning_rate": 9.680696661828737e-05,
|
| 165 |
-
"loss": 2.4441,
|
| 166 |
-
"step": 1100
|
| 167 |
-
},
|
| 168 |
-
{
|
| 169 |
-
"epoch": 0.3193033381712627,
|
| 170 |
-
"eval_loss": 1.1647560596466064,
|
| 171 |
-
"eval_runtime": 213.5056,
|
| 172 |
-
"eval_samples_per_second": 213.104,
|
| 173 |
-
"eval_steps_per_second": 3.33,
|
| 174 |
-
"step": 1100
|
| 175 |
-
},
|
| 176 |
-
{
|
| 177 |
-
"epoch": 0.3483309143686502,
|
| 178 |
-
"grad_norm": 1.2719751596450806,
|
| 179 |
-
"learning_rate": 9.65166908563135e-05,
|
| 180 |
-
"loss": 2.432,
|
| 181 |
-
"step": 1200
|
| 182 |
-
},
|
| 183 |
-
{
|
| 184 |
-
"epoch": 0.3483309143686502,
|
| 185 |
-
"eval_loss": 1.1668621301651,
|
| 186 |
-
"eval_runtime": 213.8017,
|
| 187 |
-
"eval_samples_per_second": 212.809,
|
| 188 |
-
"eval_steps_per_second": 3.326,
|
| 189 |
-
"step": 1200
|
| 190 |
-
},
|
| 191 |
-
{
|
| 192 |
-
"epoch": 0.37735849056603776,
|
| 193 |
-
"grad_norm": 1.1357173919677734,
|
| 194 |
-
"learning_rate": 9.622641509433963e-05,
|
| 195 |
-
"loss": 2.4173,
|
| 196 |
-
"step": 1300
|
| 197 |
-
},
|
| 198 |
-
{
|
| 199 |
-
"epoch": 0.37735849056603776,
|
| 200 |
-
"eval_loss": 1.1585583686828613,
|
| 201 |
-
"eval_runtime": 212.8448,
|
| 202 |
-
"eval_samples_per_second": 213.766,
|
| 203 |
-
"eval_steps_per_second": 3.34,
|
| 204 |
-
"step": 1300
|
| 205 |
-
},
|
| 206 |
-
{
|
| 207 |
-
"epoch": 0.40638606676342526,
|
| 208 |
-
"grad_norm": 1.1240577697753906,
|
| 209 |
-
"learning_rate": 9.593613933236575e-05,
|
| 210 |
-
"loss": 2.4029,
|
| 211 |
-
"step": 1400
|
| 212 |
-
},
|
| 213 |
-
{
|
| 214 |
-
"epoch": 0.40638606676342526,
|
| 215 |
-
"eval_loss": 1.1513617038726807,
|
| 216 |
-
"eval_runtime": 214.5547,
|
| 217 |
-
"eval_samples_per_second": 212.063,
|
| 218 |
-
"eval_steps_per_second": 3.314,
|
| 219 |
-
"step": 1400
|
| 220 |
-
},
|
| 221 |
-
{
|
| 222 |
-
"epoch": 0.43541364296081275,
|
| 223 |
-
"grad_norm": 1.074048399925232,
|
| 224 |
-
"learning_rate": 9.564586357039188e-05,
|
| 225 |
-
"loss": 2.3964,
|
| 226 |
-
"step": 1500
|
| 227 |
-
},
|
| 228 |
-
{
|
| 229 |
-
"epoch": 0.43541364296081275,
|
| 230 |
-
"eval_loss": 1.1514214277267456,
|
| 231 |
-
"eval_runtime": 213.8115,
|
| 232 |
-
"eval_samples_per_second": 212.8,
|
| 233 |
-
"eval_steps_per_second": 3.325,
|
| 234 |
-
"step": 1500
|
| 235 |
-
},
|
| 236 |
-
{
|
| 237 |
-
"epoch": 0.4644412191582003,
|
| 238 |
-
"grad_norm": 1.2565686702728271,
|
| 239 |
-
"learning_rate": 9.5355587808418e-05,
|
| 240 |
-
"loss": 2.3548,
|
| 241 |
-
"step": 1600
|
| 242 |
-
},
|
| 243 |
-
{
|
| 244 |
-
"epoch": 0.4644412191582003,
|
| 245 |
-
"eval_loss": 1.1476994752883911,
|
| 246 |
-
"eval_runtime": 214.3759,
|
| 247 |
-
"eval_samples_per_second": 212.239,
|
| 248 |
-
"eval_steps_per_second": 3.317,
|
| 249 |
-
"step": 1600
|
| 250 |
-
},
|
| 251 |
-
{
|
| 252 |
-
"epoch": 0.4934687953555878,
|
| 253 |
-
"grad_norm": 1.1474090814590454,
|
| 254 |
-
"learning_rate": 9.506531204644412e-05,
|
| 255 |
-
"loss": 2.36,
|
| 256 |
-
"step": 1700
|
| 257 |
-
},
|
| 258 |
-
{
|
| 259 |
-
"epoch": 0.4934687953555878,
|
| 260 |
-
"eval_loss": 1.1446571350097656,
|
| 261 |
-
"eval_runtime": 213.458,
|
| 262 |
-
"eval_samples_per_second": 213.152,
|
| 263 |
-
"eval_steps_per_second": 3.331,
|
| 264 |
-
"step": 1700
|
| 265 |
-
},
|
| 266 |
-
{
|
| 267 |
-
"epoch": 0.5224963715529753,
|
| 268 |
-
"grad_norm": 1.2290916442871094,
|
| 269 |
-
"learning_rate": 9.477503628447025e-05,
|
| 270 |
-
"loss": 2.3438,
|
| 271 |
-
"step": 1800
|
| 272 |
-
},
|
| 273 |
-
{
|
| 274 |
-
"epoch": 0.5224963715529753,
|
| 275 |
-
"eval_loss": 1.1393438577651978,
|
| 276 |
-
"eval_runtime": 213.014,
|
| 277 |
-
"eval_samples_per_second": 213.596,
|
| 278 |
-
"eval_steps_per_second": 3.338,
|
| 279 |
-
"step": 1800
|
| 280 |
-
},
|
| 281 |
-
{
|
| 282 |
-
"epoch": 0.5515239477503628,
|
| 283 |
-
"grad_norm": 1.1700950860977173,
|
| 284 |
-
"learning_rate": 9.448476052249638e-05,
|
| 285 |
-
"loss": 2.3416,
|
| 286 |
-
"step": 1900
|
| 287 |
-
},
|
| 288 |
-
{
|
| 289 |
-
"epoch": 0.5515239477503628,
|
| 290 |
-
"eval_loss": 1.1348192691802979,
|
| 291 |
-
"eval_runtime": 213.2252,
|
| 292 |
-
"eval_samples_per_second": 213.385,
|
| 293 |
-
"eval_steps_per_second": 3.335,
|
| 294 |
-
"step": 1900
|
| 295 |
-
},
|
| 296 |
-
{
|
| 297 |
-
"epoch": 0.5805515239477503,
|
| 298 |
-
"grad_norm": 1.1090705394744873,
|
| 299 |
-
"learning_rate": 9.419448476052251e-05,
|
| 300 |
-
"loss": 2.3289,
|
| 301 |
-
"step": 2000
|
| 302 |
-
},
|
| 303 |
-
{
|
| 304 |
-
"epoch": 0.5805515239477503,
|
| 305 |
-
"eval_loss": 1.130873203277588,
|
| 306 |
-
"eval_runtime": 212.7564,
|
| 307 |
-
"eval_samples_per_second": 213.855,
|
| 308 |
-
"eval_steps_per_second": 3.342,
|
| 309 |
-
"step": 2000
|
| 310 |
-
},
|
| 311 |
-
{
|
| 312 |
-
"epoch": 0.6095791001451378,
|
| 313 |
-
"grad_norm": 1.17753267288208,
|
| 314 |
-
"learning_rate": 9.390420899854863e-05,
|
| 315 |
-
"loss": 2.3218,
|
| 316 |
-
"step": 2100
|
| 317 |
-
},
|
| 318 |
-
{
|
| 319 |
-
"epoch": 0.6095791001451378,
|
| 320 |
-
"eval_loss": 1.1335190534591675,
|
| 321 |
-
"eval_runtime": 212.7619,
|
| 322 |
-
"eval_samples_per_second": 213.849,
|
| 323 |
-
"eval_steps_per_second": 3.342,
|
| 324 |
-
"step": 2100
|
| 325 |
-
},
|
| 326 |
-
{
|
| 327 |
-
"epoch": 0.6386066763425254,
|
| 328 |
-
"grad_norm": 1.087358832359314,
|
| 329 |
-
"learning_rate": 9.361393323657474e-05,
|
| 330 |
-
"loss": 2.3072,
|
| 331 |
-
"step": 2200
|
| 332 |
-
},
|
| 333 |
-
{
|
| 334 |
-
"epoch": 0.6386066763425254,
|
| 335 |
-
"eval_loss": 1.1303313970565796,
|
| 336 |
-
"eval_runtime": 213.3449,
|
| 337 |
-
"eval_samples_per_second": 213.265,
|
| 338 |
-
"eval_steps_per_second": 3.333,
|
| 339 |
-
"step": 2200
|
| 340 |
-
},
|
| 341 |
-
{
|
| 342 |
-
"epoch": 0.6676342525399129,
|
| 343 |
-
"grad_norm": 1.1286981105804443,
|
| 344 |
-
"learning_rate": 9.332365747460087e-05,
|
| 345 |
-
"loss": 2.2881,
|
| 346 |
-
"step": 2300
|
| 347 |
-
},
|
| 348 |
-
{
|
| 349 |
-
"epoch": 0.6676342525399129,
|
| 350 |
-
"eval_loss": 1.1234804391860962,
|
| 351 |
-
"eval_runtime": 213.3465,
|
| 352 |
-
"eval_samples_per_second": 213.263,
|
| 353 |
-
"eval_steps_per_second": 3.333,
|
| 354 |
-
"step": 2300
|
| 355 |
-
},
|
| 356 |
-
{
|
| 357 |
-
"epoch": 0.6966618287373004,
|
| 358 |
-
"grad_norm": 1.1590163707733154,
|
| 359 |
-
"learning_rate": 9.3033381712627e-05,
|
| 360 |
-
"loss": 2.2751,
|
| 361 |
-
"step": 2400
|
| 362 |
-
},
|
| 363 |
-
{
|
| 364 |
-
"epoch": 0.6966618287373004,
|
| 365 |
-
"eval_loss": 1.120328664779663,
|
| 366 |
-
"eval_runtime": 213.9246,
|
| 367 |
-
"eval_samples_per_second": 212.687,
|
| 368 |
-
"eval_steps_per_second": 3.324,
|
| 369 |
-
"step": 2400
|
| 370 |
-
},
|
| 371 |
-
{
|
| 372 |
-
"epoch": 0.7256894049346879,
|
| 373 |
-
"grad_norm": 1.3988169431686401,
|
| 374 |
-
"learning_rate": 9.274310595065312e-05,
|
| 375 |
-
"loss": 2.2666,
|
| 376 |
-
"step": 2500
|
| 377 |
-
},
|
| 378 |
-
{
|
| 379 |
-
"epoch": 0.7256894049346879,
|
| 380 |
-
"eval_loss": 1.1266223192214966,
|
| 381 |
-
"eval_runtime": 214.3634,
|
| 382 |
-
"eval_samples_per_second": 212.252,
|
| 383 |
-
"eval_steps_per_second": 3.317,
|
| 384 |
-
"step": 2500
|
| 385 |
-
},
|
| 386 |
-
{
|
| 387 |
-
"epoch": 0.7547169811320755,
|
| 388 |
-
"grad_norm": 1.239560842514038,
|
| 389 |
-
"learning_rate": 9.245283018867925e-05,
|
| 390 |
-
"loss": 2.2702,
|
| 391 |
-
"step": 2600
|
| 392 |
-
},
|
| 393 |
-
{
|
| 394 |
-
"epoch": 0.7547169811320755,
|
| 395 |
-
"eval_loss": 1.1224210262298584,
|
| 396 |
-
"eval_runtime": 213.2424,
|
| 397 |
-
"eval_samples_per_second": 213.367,
|
| 398 |
-
"eval_steps_per_second": 3.334,
|
| 399 |
-
"step": 2600
|
| 400 |
-
},
|
| 401 |
-
{
|
| 402 |
-
"epoch": 0.783744557329463,
|
| 403 |
-
"grad_norm": 1.1289948225021362,
|
| 404 |
-
"learning_rate": 9.216255442670537e-05,
|
| 405 |
-
"loss": 2.256,
|
| 406 |
-
"step": 2700
|
| 407 |
-
},
|
| 408 |
-
{
|
| 409 |
-
"epoch": 0.783744557329463,
|
| 410 |
-
"eval_loss": 1.1150513887405396,
|
| 411 |
-
"eval_runtime": 213.4486,
|
| 412 |
-
"eval_samples_per_second": 213.161,
|
| 413 |
-
"eval_steps_per_second": 3.331,
|
| 414 |
-
"step": 2700
|
| 415 |
-
},
|
| 416 |
-
{
|
| 417 |
-
"epoch": 0.8127721335268505,
|
| 418 |
-
"grad_norm": 1.1463016271591187,
|
| 419 |
-
"learning_rate": 9.18722786647315e-05,
|
| 420 |
-
"loss": 2.2483,
|
| 421 |
-
"step": 2800
|
| 422 |
-
},
|
| 423 |
-
{
|
| 424 |
-
"epoch": 0.8127721335268505,
|
| 425 |
-
"eval_loss": 1.1185483932495117,
|
| 426 |
-
"eval_runtime": 212.704,
|
| 427 |
-
"eval_samples_per_second": 213.908,
|
| 428 |
-
"eval_steps_per_second": 3.343,
|
| 429 |
-
"step": 2800
|
| 430 |
-
},
|
| 431 |
-
{
|
| 432 |
-
"epoch": 0.841799709724238,
|
| 433 |
-
"grad_norm": 1.1233168840408325,
|
| 434 |
-
"learning_rate": 9.158200290275763e-05,
|
| 435 |
-
"loss": 2.2328,
|
| 436 |
-
"step": 2900
|
| 437 |
-
},
|
| 438 |
-
{
|
| 439 |
-
"epoch": 0.841799709724238,
|
| 440 |
-
"eval_loss": 1.1085420846939087,
|
| 441 |
-
"eval_runtime": 213.7255,
|
| 442 |
-
"eval_samples_per_second": 212.885,
|
| 443 |
-
"eval_steps_per_second": 3.327,
|
| 444 |
-
"step": 2900
|
| 445 |
-
},
|
| 446 |
-
{
|
| 447 |
-
"epoch": 0.8708272859216255,
|
| 448 |
-
"grad_norm": 1.1887527704238892,
|
| 449 |
-
"learning_rate": 9.129172714078375e-05,
|
| 450 |
-
"loss": 2.235,
|
| 451 |
-
"step": 3000
|
| 452 |
-
},
|
| 453 |
-
{
|
| 454 |
-
"epoch": 0.8708272859216255,
|
| 455 |
-
"eval_loss": 1.1104073524475098,
|
| 456 |
-
"eval_runtime": 213.9252,
|
| 457 |
-
"eval_samples_per_second": 212.687,
|
| 458 |
-
"eval_steps_per_second": 3.324,
|
| 459 |
-
"step": 3000
|
| 460 |
-
},
|
| 461 |
-
{
|
| 462 |
-
"epoch": 0.8998548621190131,
|
| 463 |
-
"grad_norm": 1.2834577560424805,
|
| 464 |
-
"learning_rate": 9.100145137880988e-05,
|
| 465 |
-
"loss": 2.2209,
|
| 466 |
-
"step": 3100
|
| 467 |
-
},
|
| 468 |
-
{
|
| 469 |
-
"epoch": 0.8998548621190131,
|
| 470 |
-
"eval_loss": 1.1137757301330566,
|
| 471 |
-
"eval_runtime": 213.6201,
|
| 472 |
-
"eval_samples_per_second": 212.99,
|
| 473 |
-
"eval_steps_per_second": 3.328,
|
| 474 |
-
"step": 3100
|
| 475 |
-
},
|
| 476 |
-
{
|
| 477 |
-
"epoch": 0.9288824383164006,
|
| 478 |
-
"grad_norm": 1.3034873008728027,
|
| 479 |
-
"learning_rate": 9.0711175616836e-05,
|
| 480 |
-
"loss": 2.2185,
|
| 481 |
-
"step": 3200
|
| 482 |
-
},
|
| 483 |
-
{
|
| 484 |
-
"epoch": 0.9288824383164006,
|
| 485 |
-
"eval_loss": 1.107863187789917,
|
| 486 |
-
"eval_runtime": 213.1098,
|
| 487 |
-
"eval_samples_per_second": 213.5,
|
| 488 |
-
"eval_steps_per_second": 3.336,
|
| 489 |
-
"step": 3200
|
| 490 |
-
},
|
| 491 |
-
{
|
| 492 |
-
"epoch": 0.9579100145137881,
|
| 493 |
-
"grad_norm": 1.1802492141723633,
|
| 494 |
-
"learning_rate": 9.042089985486212e-05,
|
| 495 |
-
"loss": 2.2147,
|
| 496 |
-
"step": 3300
|
| 497 |
-
},
|
| 498 |
-
{
|
| 499 |
-
"epoch": 0.9579100145137881,
|
| 500 |
-
"eval_loss": 1.1041762828826904,
|
| 501 |
-
"eval_runtime": 213.2962,
|
| 502 |
-
"eval_samples_per_second": 213.314,
|
| 503 |
-
"eval_steps_per_second": 3.333,
|
| 504 |
-
"step": 3300
|
| 505 |
-
},
|
| 506 |
-
{
|
| 507 |
-
"epoch": 0.9869375907111756,
|
| 508 |
-
"grad_norm": 1.2992894649505615,
|
| 509 |
-
"learning_rate": 9.013062409288826e-05,
|
| 510 |
-
"loss": 2.216,
|
| 511 |
-
"step": 3400
|
| 512 |
-
},
|
| 513 |
-
{
|
| 514 |
-
"epoch": 0.9869375907111756,
|
| 515 |
-
"eval_loss": 1.1009138822555542,
|
| 516 |
-
"eval_runtime": 213.7998,
|
| 517 |
-
"eval_samples_per_second": 212.811,
|
| 518 |
-
"eval_steps_per_second": 3.326,
|
| 519 |
-
"step": 3400
|
| 520 |
-
},
|
| 521 |
-
{
|
| 522 |
-
"epoch": 1.0159651669085632,
|
| 523 |
-
"grad_norm": 1.1432065963745117,
|
| 524 |
-
"learning_rate": 8.984034833091437e-05,
|
| 525 |
-
"loss": 2.1952,
|
| 526 |
-
"step": 3500
|
| 527 |
-
},
|
| 528 |
-
{
|
| 529 |
-
"epoch": 1.0159651669085632,
|
| 530 |
-
"eval_loss": 1.106726884841919,
|
| 531 |
-
"eval_runtime": 213.7054,
|
| 532 |
-
"eval_samples_per_second": 212.905,
|
| 533 |
-
"eval_steps_per_second": 3.327,
|
| 534 |
-
"step": 3500
|
| 535 |
-
},
|
| 536 |
-
{
|
| 537 |
-
"epoch": 1.0449927431059507,
|
| 538 |
-
"grad_norm": 1.1603158712387085,
|
| 539 |
-
"learning_rate": 8.95500725689405e-05,
|
| 540 |
-
"loss": 2.2019,
|
| 541 |
-
"step": 3600
|
| 542 |
-
},
|
| 543 |
-
{
|
| 544 |
-
"epoch": 1.0449927431059507,
|
| 545 |
-
"eval_loss": 1.1014330387115479,
|
| 546 |
-
"eval_runtime": 213.1977,
|
| 547 |
-
"eval_samples_per_second": 213.412,
|
| 548 |
-
"eval_steps_per_second": 3.335,
|
| 549 |
-
"step": 3600
|
| 550 |
-
},
|
| 551 |
-
{
|
| 552 |
-
"epoch": 1.0740203193033382,
|
| 553 |
-
"grad_norm": 1.2428488731384277,
|
| 554 |
-
"learning_rate": 8.925979680696662e-05,
|
| 555 |
-
"loss": 2.1959,
|
| 556 |
-
"step": 3700
|
| 557 |
-
},
|
| 558 |
-
{
|
| 559 |
-
"epoch": 1.0740203193033382,
|
| 560 |
-
"eval_loss": 1.1004406213760376,
|
| 561 |
-
"eval_runtime": 213.3658,
|
| 562 |
-
"eval_samples_per_second": 213.244,
|
| 563 |
-
"eval_steps_per_second": 3.332,
|
| 564 |
-
"step": 3700
|
| 565 |
-
},
|
| 566 |
-
{
|
| 567 |
-
"epoch": 1.1030478955007257,
|
| 568 |
-
"grad_norm": 1.1615545749664307,
|
| 569 |
-
"learning_rate": 8.896952104499274e-05,
|
| 570 |
-
"loss": 2.1776,
|
| 571 |
-
"step": 3800
|
| 572 |
-
},
|
| 573 |
-
{
|
| 574 |
-
"epoch": 1.1030478955007257,
|
| 575 |
-
"eval_loss": 1.0938160419464111,
|
| 576 |
-
"eval_runtime": 213.3987,
|
| 577 |
-
"eval_samples_per_second": 213.211,
|
| 578 |
-
"eval_steps_per_second": 3.332,
|
| 579 |
-
"step": 3800
|
| 580 |
-
},
|
| 581 |
-
{
|
| 582 |
-
"epoch": 1.1320754716981132,
|
| 583 |
-
"grad_norm": 1.1921610832214355,
|
| 584 |
-
"learning_rate": 8.867924528301888e-05,
|
| 585 |
-
"loss": 2.1762,
|
| 586 |
-
"step": 3900
|
| 587 |
-
},
|
| 588 |
-
{
|
| 589 |
-
"epoch": 1.1320754716981132,
|
| 590 |
-
"eval_loss": 1.0960694551467896,
|
| 591 |
-
"eval_runtime": 213.1832,
|
| 592 |
-
"eval_samples_per_second": 213.427,
|
| 593 |
-
"eval_steps_per_second": 3.335,
|
| 594 |
-
"step": 3900
|
| 595 |
-
},
|
| 596 |
-
{
|
| 597 |
-
"epoch": 1.1611030478955007,
|
| 598 |
-
"grad_norm": 1.1980363130569458,
|
| 599 |
-
"learning_rate": 8.8388969521045e-05,
|
| 600 |
-
"loss": 2.1717,
|
| 601 |
-
"step": 4000
|
| 602 |
-
},
|
| 603 |
-
{
|
| 604 |
-
"epoch": 1.1611030478955007,
|
| 605 |
-
"eval_loss": 1.0951919555664062,
|
| 606 |
-
"eval_runtime": 213.4024,
|
| 607 |
-
"eval_samples_per_second": 213.207,
|
| 608 |
-
"eval_steps_per_second": 3.332,
|
| 609 |
-
"step": 4000
|
| 610 |
-
},
|
| 611 |
-
{
|
| 612 |
-
"epoch": 1.1901306240928882,
|
| 613 |
-
"grad_norm": 1.217236042022705,
|
| 614 |
-
"learning_rate": 8.809869375907113e-05,
|
| 615 |
-
"loss": 2.1534,
|
| 616 |
-
"step": 4100
|
| 617 |
-
},
|
| 618 |
-
{
|
| 619 |
-
"epoch": 1.1901306240928882,
|
| 620 |
-
"eval_loss": 1.0937577486038208,
|
| 621 |
-
"eval_runtime": 213.8113,
|
| 622 |
-
"eval_samples_per_second": 212.8,
|
| 623 |
-
"eval_steps_per_second": 3.325,
|
| 624 |
-
"step": 4100
|
| 625 |
-
},
|
| 626 |
-
{
|
| 627 |
-
"epoch": 1.2191582002902757,
|
| 628 |
-
"grad_norm": 1.2121118307113647,
|
| 629 |
-
"learning_rate": 8.780841799709725e-05,
|
| 630 |
-
"loss": 2.1639,
|
| 631 |
-
"step": 4200
|
| 632 |
-
},
|
| 633 |
-
{
|
| 634 |
-
"epoch": 1.2191582002902757,
|
| 635 |
-
"eval_loss": 1.0909945964813232,
|
| 636 |
-
"eval_runtime": 212.8308,
|
| 637 |
-
"eval_samples_per_second": 213.78,
|
| 638 |
-
"eval_steps_per_second": 3.341,
|
| 639 |
-
"step": 4200
|
| 640 |
-
},
|
| 641 |
-
{
|
| 642 |
-
"epoch": 1.2481857764876634,
|
| 643 |
-
"grad_norm": 1.17587411403656,
|
| 644 |
-
"learning_rate": 8.751814223512336e-05,
|
| 645 |
-
"loss": 2.146,
|
| 646 |
-
"step": 4300
|
| 647 |
-
},
|
| 648 |
-
{
|
| 649 |
-
"epoch": 1.2481857764876634,
|
| 650 |
-
"eval_loss": 1.0888868570327759,
|
| 651 |
-
"eval_runtime": 213.8752,
|
| 652 |
-
"eval_samples_per_second": 212.736,
|
| 653 |
-
"eval_steps_per_second": 3.324,
|
| 654 |
-
"step": 4300
|
| 655 |
-
},
|
| 656 |
-
{
|
| 657 |
-
"epoch": 1.2772133526850509,
|
| 658 |
-
"grad_norm": 1.2848412990570068,
|
| 659 |
-
"learning_rate": 8.722786647314949e-05,
|
| 660 |
-
"loss": 2.1357,
|
| 661 |
-
"step": 4400
|
| 662 |
-
},
|
| 663 |
-
{
|
| 664 |
-
"epoch": 1.2772133526850509,
|
| 665 |
-
"eval_loss": 1.091068983078003,
|
| 666 |
-
"eval_runtime": 213.4081,
|
| 667 |
-
"eval_samples_per_second": 213.202,
|
| 668 |
-
"eval_steps_per_second": 3.332,
|
| 669 |
-
"step": 4400
|
| 670 |
-
},
|
| 671 |
-
{
|
| 672 |
-
"epoch": 1.3062409288824384,
|
| 673 |
-
"grad_norm": 1.2059731483459473,
|
| 674 |
-
"learning_rate": 8.693759071117562e-05,
|
| 675 |
-
"loss": 2.1456,
|
| 676 |
-
"step": 4500
|
| 677 |
-
},
|
| 678 |
-
{
|
| 679 |
-
"epoch": 1.3062409288824384,
|
| 680 |
-
"eval_loss": 1.0857021808624268,
|
| 681 |
-
"eval_runtime": 213.7314,
|
| 682 |
-
"eval_samples_per_second": 212.879,
|
| 683 |
-
"eval_steps_per_second": 3.327,
|
| 684 |
-
"step": 4500
|
| 685 |
-
},
|
| 686 |
-
{
|
| 687 |
-
"epoch": 1.3352685050798259,
|
| 688 |
-
"grad_norm": 1.226241946220398,
|
| 689 |
-
"learning_rate": 8.664731494920174e-05,
|
| 690 |
-
"loss": 2.1453,
|
| 691 |
-
"step": 4600
|
| 692 |
-
},
|
| 693 |
-
{
|
| 694 |
-
"epoch": 1.3352685050798259,
|
| 695 |
-
"eval_loss": 1.0845140218734741,
|
| 696 |
-
"eval_runtime": 213.4698,
|
| 697 |
-
"eval_samples_per_second": 213.14,
|
| 698 |
-
"eval_steps_per_second": 3.331,
|
| 699 |
-
"step": 4600
|
| 700 |
-
},
|
| 701 |
-
{
|
| 702 |
-
"epoch": 1.3642960812772134,
|
| 703 |
-
"grad_norm": 1.1810499429702759,
|
| 704 |
-
"learning_rate": 8.635703918722787e-05,
|
| 705 |
-
"loss": 2.1425,
|
| 706 |
-
"step": 4700
|
| 707 |
-
},
|
| 708 |
-
{
|
| 709 |
-
"epoch": 1.3642960812772134,
|
| 710 |
-
"eval_loss": 1.0831544399261475,
|
| 711 |
-
"eval_runtime": 214.2077,
|
| 712 |
-
"eval_samples_per_second": 212.406,
|
| 713 |
-
"eval_steps_per_second": 3.319,
|
| 714 |
-
"step": 4700
|
| 715 |
-
},
|
| 716 |
-
{
|
| 717 |
-
"epoch": 1.3933236574746009,
|
| 718 |
-
"grad_norm": 1.155281662940979,
|
| 719 |
-
"learning_rate": 8.606676342525399e-05,
|
| 720 |
-
"loss": 2.1173,
|
| 721 |
-
"step": 4800
|
| 722 |
-
},
|
| 723 |
-
{
|
| 724 |
-
"epoch": 1.3933236574746009,
|
| 725 |
-
"eval_loss": 1.0785441398620605,
|
| 726 |
-
"eval_runtime": 213.6973,
|
| 727 |
-
"eval_samples_per_second": 212.913,
|
| 728 |
-
"eval_steps_per_second": 3.327,
|
| 729 |
-
"step": 4800
|
| 730 |
-
},
|
| 731 |
-
{
|
| 732 |
-
"epoch": 1.4223512336719883,
|
| 733 |
-
"grad_norm": 1.2070744037628174,
|
| 734 |
-
"learning_rate": 8.577648766328012e-05,
|
| 735 |
-
"loss": 2.1183,
|
| 736 |
-
"step": 4900
|
| 737 |
-
},
|
| 738 |
-
{
|
| 739 |
-
"epoch": 1.4223512336719883,
|
| 740 |
-
"eval_loss": 1.0808286666870117,
|
| 741 |
-
"eval_runtime": 213.4564,
|
| 742 |
-
"eval_samples_per_second": 213.154,
|
| 743 |
-
"eval_steps_per_second": 3.331,
|
| 744 |
-
"step": 4900
|
| 745 |
-
},
|
| 746 |
-
{
|
| 747 |
-
"epoch": 1.4513788098693758,
|
| 748 |
-
"grad_norm": 1.1901525259017944,
|
| 749 |
-
"learning_rate": 8.548621190130625e-05,
|
| 750 |
-
"loss": 2.1274,
|
| 751 |
-
"step": 5000
|
| 752 |
-
},
|
| 753 |
-
{
|
| 754 |
-
"epoch": 1.4513788098693758,
|
| 755 |
-
"eval_loss": 1.0827044248580933,
|
| 756 |
-
"eval_runtime": 212.5592,
|
| 757 |
-
"eval_samples_per_second": 214.053,
|
| 758 |
-
"eval_steps_per_second": 3.345,
|
| 759 |
-
"step": 5000
|
| 760 |
-
},
|
| 761 |
-
{
|
| 762 |
-
"epoch": 1.4804063860667633,
|
| 763 |
-
"grad_norm": 1.1999766826629639,
|
| 764 |
-
"learning_rate": 8.519593613933237e-05,
|
| 765 |
-
"loss": 2.1145,
|
| 766 |
-
"step": 5100
|
| 767 |
-
},
|
| 768 |
-
{
|
| 769 |
-
"epoch": 1.4804063860667633,
|
| 770 |
-
"eval_loss": 1.078644037246704,
|
| 771 |
-
"eval_runtime": 213.0532,
|
| 772 |
-
"eval_samples_per_second": 213.557,
|
| 773 |
-
"eval_steps_per_second": 3.337,
|
| 774 |
-
"step": 5100
|
| 775 |
-
},
|
| 776 |
-
{
|
| 777 |
-
"epoch": 1.509433962264151,
|
| 778 |
-
"grad_norm": 1.2294871807098389,
|
| 779 |
-
"learning_rate": 8.49056603773585e-05,
|
| 780 |
-
"loss": 2.1067,
|
| 781 |
-
"step": 5200
|
| 782 |
-
},
|
| 783 |
-
{
|
| 784 |
-
"epoch": 1.509433962264151,
|
| 785 |
-
"eval_loss": 1.0794402360916138,
|
| 786 |
-
"eval_runtime": 212.9617,
|
| 787 |
-
"eval_samples_per_second": 213.649,
|
| 788 |
-
"eval_steps_per_second": 3.339,
|
| 789 |
-
"step": 5200
|
| 790 |
-
},
|
| 791 |
-
{
|
| 792 |
-
"epoch": 1.5384615384615383,
|
| 793 |
-
"grad_norm": 1.2571580410003662,
|
| 794 |
-
"learning_rate": 8.461538461538461e-05,
|
| 795 |
-
"loss": 2.1032,
|
| 796 |
-
"step": 5300
|
| 797 |
-
},
|
| 798 |
-
{
|
| 799 |
-
"epoch": 1.5384615384615383,
|
| 800 |
-
"eval_loss": 1.0783346891403198,
|
| 801 |
-
"eval_runtime": 213.4656,
|
| 802 |
-
"eval_samples_per_second": 213.144,
|
| 803 |
-
"eval_steps_per_second": 3.331,
|
| 804 |
-
"step": 5300
|
| 805 |
-
},
|
| 806 |
-
{
|
| 807 |
-
"epoch": 1.567489114658926,
|
| 808 |
-
"grad_norm": 1.2078722715377808,
|
| 809 |
-
"learning_rate": 8.432510885341074e-05,
|
| 810 |
-
"loss": 2.0912,
|
| 811 |
-
"step": 5400
|
| 812 |
-
},
|
| 813 |
-
{
|
| 814 |
-
"epoch": 1.567489114658926,
|
| 815 |
-
"eval_loss": 1.0764219760894775,
|
| 816 |
-
"eval_runtime": 213.826,
|
| 817 |
-
"eval_samples_per_second": 212.785,
|
| 818 |
-
"eval_steps_per_second": 3.325,
|
| 819 |
-
"step": 5400
|
| 820 |
-
},
|
| 821 |
-
{
|
| 822 |
-
"epoch": 1.5965166908563135,
|
| 823 |
-
"grad_norm": 1.272294521331787,
|
| 824 |
-
"learning_rate": 8.403483309143688e-05,
|
| 825 |
-
"loss": 2.0784,
|
| 826 |
-
"step": 5500
|
| 827 |
-
},
|
| 828 |
-
{
|
| 829 |
-
"epoch": 1.5965166908563135,
|
| 830 |
-
"eval_loss": 1.0817687511444092,
|
| 831 |
-
"eval_runtime": 213.443,
|
| 832 |
-
"eval_samples_per_second": 213.167,
|
| 833 |
-
"eval_steps_per_second": 3.331,
|
| 834 |
-
"step": 5500
|
| 835 |
-
},
|
| 836 |
-
{
|
| 837 |
-
"epoch": 1.625544267053701,
|
| 838 |
-
"grad_norm": 1.2367442846298218,
|
| 839 |
-
"learning_rate": 8.374455732946299e-05,
|
| 840 |
-
"loss": 2.0997,
|
| 841 |
-
"step": 5600
|
| 842 |
-
},
|
| 843 |
-
{
|
| 844 |
-
"epoch": 1.625544267053701,
|
| 845 |
-
"eval_loss": 1.079858660697937,
|
| 846 |
-
"eval_runtime": 213.7339,
|
| 847 |
-
"eval_samples_per_second": 212.877,
|
| 848 |
-
"eval_steps_per_second": 3.327,
|
| 849 |
-
"step": 5600
|
| 850 |
-
},
|
| 851 |
-
{
|
| 852 |
-
"epoch": 1.6545718432510885,
|
| 853 |
-
"grad_norm": 1.2720229625701904,
|
| 854 |
-
"learning_rate": 8.345428156748912e-05,
|
| 855 |
-
"loss": 2.093,
|
| 856 |
-
"step": 5700
|
| 857 |
-
},
|
| 858 |
-
{
|
| 859 |
-
"epoch": 1.6545718432510885,
|
| 860 |
-
"eval_loss": 1.0779507160186768,
|
| 861 |
-
"eval_runtime": 213.2034,
|
| 862 |
-
"eval_samples_per_second": 213.407,
|
| 863 |
-
"eval_steps_per_second": 3.335,
|
| 864 |
-
"step": 5700
|
| 865 |
-
},
|
| 866 |
-
{
|
| 867 |
-
"epoch": 1.683599419448476,
|
| 868 |
-
"grad_norm": 1.1694726943969727,
|
| 869 |
-
"learning_rate": 8.316400580551524e-05,
|
| 870 |
-
"loss": 2.0822,
|
| 871 |
-
"step": 5800
|
| 872 |
-
},
|
| 873 |
-
{
|
| 874 |
-
"epoch": 1.683599419448476,
|
| 875 |
-
"eval_loss": 1.068250060081482,
|
| 876 |
-
"eval_runtime": 213.1022,
|
| 877 |
-
"eval_samples_per_second": 213.508,
|
| 878 |
-
"eval_steps_per_second": 3.336,
|
| 879 |
-
"step": 5800
|
| 880 |
-
},
|
| 881 |
-
{
|
| 882 |
-
"epoch": 1.7126269956458637,
|
| 883 |
-
"grad_norm": 1.2155323028564453,
|
| 884 |
-
"learning_rate": 8.287373004354137e-05,
|
| 885 |
-
"loss": 2.0792,
|
| 886 |
-
"step": 5900
|
| 887 |
-
},
|
| 888 |
-
{
|
| 889 |
-
"epoch": 1.7126269956458637,
|
| 890 |
-
"eval_loss": 1.0666776895523071,
|
| 891 |
-
"eval_runtime": 213.4935,
|
| 892 |
-
"eval_samples_per_second": 213.117,
|
| 893 |
-
"eval_steps_per_second": 3.33,
|
| 894 |
-
"step": 5900
|
| 895 |
-
},
|
| 896 |
-
{
|
| 897 |
-
"epoch": 1.741654571843251,
|
| 898 |
-
"grad_norm": 1.3163602352142334,
|
| 899 |
-
"learning_rate": 8.25834542815675e-05,
|
| 900 |
-
"loss": 2.0712,
|
| 901 |
-
"step": 6000
|
| 902 |
-
},
|
| 903 |
-
{
|
| 904 |
-
"epoch": 1.741654571843251,
|
| 905 |
-
"eval_loss": 1.0677340030670166,
|
| 906 |
-
"eval_runtime": 213.751,
|
| 907 |
-
"eval_samples_per_second": 212.86,
|
| 908 |
-
"eval_steps_per_second": 3.326,
|
| 909 |
-
"step": 6000
|
| 910 |
-
},
|
| 911 |
-
{
|
| 912 |
-
"epoch": 1.7706821480406387,
|
| 913 |
-
"grad_norm": 1.1972286701202393,
|
| 914 |
-
"learning_rate": 8.229317851959362e-05,
|
| 915 |
-
"loss": 2.0679,
|
| 916 |
-
"step": 6100
|
| 917 |
-
},
|
| 918 |
-
{
|
| 919 |
-
"epoch": 1.7706821480406387,
|
| 920 |
-
"eval_loss": 1.0662775039672852,
|
| 921 |
-
"eval_runtime": 213.7705,
|
| 922 |
-
"eval_samples_per_second": 212.84,
|
| 923 |
-
"eval_steps_per_second": 3.326,
|
| 924 |
-
"step": 6100
|
| 925 |
-
},
|
| 926 |
-
{
|
| 927 |
-
"epoch": 1.799709724238026,
|
| 928 |
-
"grad_norm": 1.189395546913147,
|
| 929 |
-
"learning_rate": 8.200290275761974e-05,
|
| 930 |
-
"loss": 2.0753,
|
| 931 |
-
"step": 6200
|
| 932 |
-
},
|
| 933 |
-
{
|
| 934 |
-
"epoch": 1.799709724238026,
|
| 935 |
-
"eval_loss": 1.0646038055419922,
|
| 936 |
-
"eval_runtime": 213.3945,
|
| 937 |
-
"eval_samples_per_second": 213.215,
|
| 938 |
-
"eval_steps_per_second": 3.332,
|
| 939 |
-
"step": 6200
|
| 940 |
-
},
|
| 941 |
-
{
|
| 942 |
-
"epoch": 1.8287373004354137,
|
| 943 |
-
"grad_norm": 1.2696415185928345,
|
| 944 |
-
"learning_rate": 8.171262699564587e-05,
|
| 945 |
-
"loss": 2.063,
|
| 946 |
-
"step": 6300
|
| 947 |
-
},
|
| 948 |
-
{
|
| 949 |
-
"epoch": 1.8287373004354137,
|
| 950 |
-
"eval_loss": 1.0669814348220825,
|
| 951 |
-
"eval_runtime": 213.7587,
|
| 952 |
-
"eval_samples_per_second": 212.852,
|
| 953 |
-
"eval_steps_per_second": 3.326,
|
| 954 |
-
"step": 6300
|
| 955 |
-
},
|
| 956 |
-
{
|
| 957 |
-
"epoch": 1.8577648766328012,
|
| 958 |
-
"grad_norm": 1.241452693939209,
|
| 959 |
-
"learning_rate": 8.142235123367198e-05,
|
| 960 |
-
"loss": 2.0508,
|
| 961 |
-
"step": 6400
|
| 962 |
-
},
|
| 963 |
-
{
|
| 964 |
-
"epoch": 1.8577648766328012,
|
| 965 |
-
"eval_loss": 1.072275996208191,
|
| 966 |
-
"eval_runtime": 213.3197,
|
| 967 |
-
"eval_samples_per_second": 213.29,
|
| 968 |
-
"eval_steps_per_second": 3.333,
|
| 969 |
-
"step": 6400
|
| 970 |
-
},
|
| 971 |
-
{
|
| 972 |
-
"epoch": 1.8867924528301887,
|
| 973 |
-
"grad_norm": 1.22267484664917,
|
| 974 |
-
"learning_rate": 8.113207547169813e-05,
|
| 975 |
-
"loss": 2.07,
|
| 976 |
-
"step": 6500
|
| 977 |
-
},
|
| 978 |
-
{
|
| 979 |
-
"epoch": 1.8867924528301887,
|
| 980 |
-
"eval_loss": 1.0654535293579102,
|
| 981 |
-
"eval_runtime": 214.0386,
|
| 982 |
-
"eval_samples_per_second": 212.574,
|
| 983 |
-
"eval_steps_per_second": 3.322,
|
| 984 |
-
"step": 6500
|
| 985 |
-
},
|
| 986 |
-
{
|
| 987 |
-
"epoch": 1.9158200290275762,
|
| 988 |
-
"grad_norm": 1.2704839706420898,
|
| 989 |
-
"learning_rate": 8.084179970972424e-05,
|
| 990 |
-
"loss": 2.0646,
|
| 991 |
-
"step": 6600
|
| 992 |
-
},
|
| 993 |
-
{
|
| 994 |
-
"epoch": 1.9158200290275762,
|
| 995 |
-
"eval_loss": 1.0614382028579712,
|
| 996 |
-
"eval_runtime": 213.4971,
|
| 997 |
-
"eval_samples_per_second": 213.113,
|
| 998 |
-
"eval_steps_per_second": 3.33,
|
| 999 |
-
"step": 6600
|
| 1000 |
-
},
|
| 1001 |
-
{
|
| 1002 |
-
"epoch": 1.9448476052249637,
|
| 1003 |
-
"grad_norm": 1.3870867490768433,
|
| 1004 |
-
"learning_rate": 8.055152394775036e-05,
|
| 1005 |
-
"loss": 2.0598,
|
| 1006 |
-
"step": 6700
|
| 1007 |
-
},
|
| 1008 |
-
{
|
| 1009 |
-
"epoch": 1.9448476052249637,
|
| 1010 |
-
"eval_loss": 1.067047357559204,
|
| 1011 |
-
"eval_runtime": 214.0952,
|
| 1012 |
-
"eval_samples_per_second": 212.518,
|
| 1013 |
-
"eval_steps_per_second": 3.321,
|
| 1014 |
-
"step": 6700
|
| 1015 |
-
},
|
| 1016 |
-
{
|
| 1017 |
-
"epoch": 1.9738751814223512,
|
| 1018 |
-
"grad_norm": 1.3581643104553223,
|
| 1019 |
-
"learning_rate": 8.026124818577649e-05,
|
| 1020 |
-
"loss": 2.0501,
|
| 1021 |
-
"step": 6800
|
| 1022 |
-
},
|
| 1023 |
-
{
|
| 1024 |
-
"epoch": 1.9738751814223512,
|
| 1025 |
-
"eval_loss": 1.0663081407546997,
|
| 1026 |
-
"eval_runtime": 213.8995,
|
| 1027 |
-
"eval_samples_per_second": 212.712,
|
| 1028 |
-
"eval_steps_per_second": 3.324,
|
| 1029 |
-
"step": 6800
|
| 1030 |
-
},
|
| 1031 |
-
{
|
| 1032 |
-
"epoch": 2.0029027576197387,
|
| 1033 |
-
"grad_norm": 1.3438752889633179,
|
| 1034 |
-
"learning_rate": 7.997097242380261e-05,
|
| 1035 |
-
"loss": 2.0332,
|
| 1036 |
-
"step": 6900
|
| 1037 |
-
},
|
| 1038 |
-
{
|
| 1039 |
-
"epoch": 2.0029027576197387,
|
| 1040 |
-
"eval_loss": 1.059921383857727,
|
| 1041 |
-
"eval_runtime": 213.0183,
|
| 1042 |
-
"eval_samples_per_second": 213.592,
|
| 1043 |
-
"eval_steps_per_second": 3.338,
|
| 1044 |
-
"step": 6900
|
| 1045 |
-
},
|
| 1046 |
-
{
|
| 1047 |
-
"epoch": 2.0319303338171264,
|
| 1048 |
-
"grad_norm": 1.3646849393844604,
|
| 1049 |
-
"learning_rate": 7.968069666182875e-05,
|
| 1050 |
-
"loss": 2.0463,
|
| 1051 |
-
"step": 7000
|
| 1052 |
-
},
|
| 1053 |
-
{
|
| 1054 |
-
"epoch": 2.0319303338171264,
|
| 1055 |
-
"eval_loss": 1.0679893493652344,
|
| 1056 |
-
"eval_runtime": 213.3912,
|
| 1057 |
-
"eval_samples_per_second": 213.219,
|
| 1058 |
-
"eval_steps_per_second": 3.332,
|
| 1059 |
-
"step": 7000
|
| 1060 |
-
},
|
| 1061 |
-
{
|
| 1062 |
-
"epoch": 2.0609579100145137,
|
| 1063 |
-
"grad_norm": 1.2047359943389893,
|
| 1064 |
-
"learning_rate": 7.939042089985487e-05,
|
| 1065 |
-
"loss": 2.0376,
|
| 1066 |
-
"step": 7100
|
| 1067 |
-
},
|
| 1068 |
-
{
|
| 1069 |
-
"epoch": 2.0609579100145137,
|
| 1070 |
-
"eval_loss": 1.0566322803497314,
|
| 1071 |
-
"eval_runtime": 213.6266,
|
| 1072 |
-
"eval_samples_per_second": 212.984,
|
| 1073 |
-
"eval_steps_per_second": 3.328,
|
| 1074 |
-
"step": 7100
|
| 1075 |
-
},
|
| 1076 |
-
{
|
| 1077 |
-
"epoch": 2.0899854862119014,
|
| 1078 |
-
"grad_norm": 1.2285219430923462,
|
| 1079 |
-
"learning_rate": 7.910014513788099e-05,
|
| 1080 |
-
"loss": 2.0327,
|
| 1081 |
-
"step": 7200
|
| 1082 |
-
},
|
| 1083 |
-
{
|
| 1084 |
-
"epoch": 2.0899854862119014,
|
| 1085 |
-
"eval_loss": 1.058618426322937,
|
| 1086 |
-
"eval_runtime": 213.6922,
|
| 1087 |
-
"eval_samples_per_second": 212.918,
|
| 1088 |
-
"eval_steps_per_second": 3.327,
|
| 1089 |
-
"step": 7200
|
| 1090 |
-
},
|
| 1091 |
-
{
|
| 1092 |
-
"epoch": 2.1190130624092887,
|
| 1093 |
-
"grad_norm": 1.2674715518951416,
|
| 1094 |
-
"learning_rate": 7.880986937590712e-05,
|
| 1095 |
-
"loss": 2.0347,
|
| 1096 |
-
"step": 7300
|
| 1097 |
-
},
|
| 1098 |
-
{
|
| 1099 |
-
"epoch": 2.1190130624092887,
|
| 1100 |
-
"eval_loss": 1.0599507093429565,
|
| 1101 |
-
"eval_runtime": 213.5256,
|
| 1102 |
-
"eval_samples_per_second": 213.085,
|
| 1103 |
-
"eval_steps_per_second": 3.33,
|
| 1104 |
-
"step": 7300
|
| 1105 |
-
},
|
| 1106 |
-
{
|
| 1107 |
-
"epoch": 2.1480406386066764,
|
| 1108 |
-
"grad_norm": 1.3713229894638062,
|
| 1109 |
-
"learning_rate": 7.851959361393323e-05,
|
| 1110 |
-
"loss": 2.0321,
|
| 1111 |
-
"step": 7400
|
| 1112 |
-
},
|
| 1113 |
-
{
|
| 1114 |
-
"epoch": 2.1480406386066764,
|
| 1115 |
-
"eval_loss": 1.0617178678512573,
|
| 1116 |
-
"eval_runtime": 213.0273,
|
| 1117 |
-
"eval_samples_per_second": 213.583,
|
| 1118 |
-
"eval_steps_per_second": 3.338,
|
| 1119 |
-
"step": 7400
|
| 1120 |
-
},
|
| 1121 |
-
{
|
| 1122 |
-
"epoch": 2.1770682148040637,
|
| 1123 |
-
"grad_norm": 1.292090654373169,
|
| 1124 |
-
"learning_rate": 7.822931785195937e-05,
|
| 1125 |
-
"loss": 2.01,
|
| 1126 |
-
"step": 7500
|
| 1127 |
-
},
|
| 1128 |
-
{
|
| 1129 |
-
"epoch": 2.1770682148040637,
|
| 1130 |
-
"eval_loss": 1.0593364238739014,
|
| 1131 |
-
"eval_runtime": 213.421,
|
| 1132 |
-
"eval_samples_per_second": 213.189,
|
| 1133 |
-
"eval_steps_per_second": 3.331,
|
| 1134 |
-
"step": 7500
|
| 1135 |
-
},
|
| 1136 |
-
{
|
| 1137 |
-
"epoch": 2.2060957910014514,
|
| 1138 |
-
"grad_norm": 1.1819452047348022,
|
| 1139 |
-
"learning_rate": 7.79390420899855e-05,
|
| 1140 |
-
"loss": 2.0209,
|
| 1141 |
-
"step": 7600
|
| 1142 |
-
},
|
| 1143 |
-
{
|
| 1144 |
-
"epoch": 2.2060957910014514,
|
| 1145 |
-
"eval_loss": 1.0524711608886719,
|
| 1146 |
-
"eval_runtime": 214.0149,
|
| 1147 |
-
"eval_samples_per_second": 212.597,
|
| 1148 |
-
"eval_steps_per_second": 3.322,
|
| 1149 |
-
"step": 7600
|
| 1150 |
-
},
|
| 1151 |
-
{
|
| 1152 |
-
"epoch": 2.235123367198839,
|
| 1153 |
-
"grad_norm": 1.2881128787994385,
|
| 1154 |
-
"learning_rate": 7.764876632801161e-05,
|
| 1155 |
-
"loss": 2.0085,
|
| 1156 |
-
"step": 7700
|
| 1157 |
-
},
|
| 1158 |
-
{
|
| 1159 |
-
"epoch": 2.235123367198839,
|
| 1160 |
-
"eval_loss": 1.0567752122879028,
|
| 1161 |
-
"eval_runtime": 213.6228,
|
| 1162 |
-
"eval_samples_per_second": 212.988,
|
| 1163 |
-
"eval_steps_per_second": 3.328,
|
| 1164 |
-
"step": 7700
|
| 1165 |
-
},
|
| 1166 |
-
{
|
| 1167 |
-
"epoch": 2.2641509433962264,
|
| 1168 |
-
"grad_norm": 1.2962584495544434,
|
| 1169 |
-
"learning_rate": 7.735849056603774e-05,
|
| 1170 |
-
"loss": 2.0204,
|
| 1171 |
-
"step": 7800
|
| 1172 |
-
},
|
| 1173 |
-
{
|
| 1174 |
-
"epoch": 2.2641509433962264,
|
| 1175 |
-
"eval_loss": 1.0586293935775757,
|
| 1176 |
-
"eval_runtime": 213.3516,
|
| 1177 |
-
"eval_samples_per_second": 213.258,
|
| 1178 |
-
"eval_steps_per_second": 3.333,
|
| 1179 |
-
"step": 7800
|
| 1180 |
-
},
|
| 1181 |
-
{
|
| 1182 |
-
"epoch": 2.293178519593614,
|
| 1183 |
-
"grad_norm": 1.2214884757995605,
|
| 1184 |
-
"learning_rate": 7.706821480406386e-05,
|
| 1185 |
-
"loss": 2.0184,
|
| 1186 |
-
"step": 7900
|
| 1187 |
-
},
|
| 1188 |
-
{
|
| 1189 |
-
"epoch": 2.293178519593614,
|
| 1190 |
-
"eval_loss": 1.0525050163269043,
|
| 1191 |
-
"eval_runtime": 212.5483,
|
| 1192 |
-
"eval_samples_per_second": 214.064,
|
| 1193 |
-
"eval_steps_per_second": 3.345,
|
| 1194 |
-
"step": 7900
|
| 1195 |
-
},
|
| 1196 |
-
{
|
| 1197 |
-
"epoch": 2.3222060957910013,
|
| 1198 |
-
"grad_norm": 1.2622853517532349,
|
| 1199 |
-
"learning_rate": 7.677793904208999e-05,
|
| 1200 |
-
"loss": 2.0162,
|
| 1201 |
-
"step": 8000
|
| 1202 |
-
},
|
| 1203 |
-
{
|
| 1204 |
-
"epoch": 2.3222060957910013,
|
| 1205 |
-
"eval_loss": 1.0512940883636475,
|
| 1206 |
-
"eval_runtime": 212.6462,
|
| 1207 |
-
"eval_samples_per_second": 213.966,
|
| 1208 |
-
"eval_steps_per_second": 3.344,
|
| 1209 |
-
"step": 8000
|
| 1210 |
-
},
|
| 1211 |
-
{
|
| 1212 |
-
"epoch": 2.351233671988389,
|
| 1213 |
-
"grad_norm": 1.2338088750839233,
|
| 1214 |
-
"learning_rate": 7.648766328011612e-05,
|
| 1215 |
-
"loss": 2.0029,
|
| 1216 |
-
"step": 8100
|
| 1217 |
-
},
|
| 1218 |
-
{
|
| 1219 |
-
"epoch": 2.351233671988389,
|
| 1220 |
-
"eval_loss": 1.0521414279937744,
|
| 1221 |
-
"eval_runtime": 213.5358,
|
| 1222 |
-
"eval_samples_per_second": 213.074,
|
| 1223 |
-
"eval_steps_per_second": 3.33,
|
| 1224 |
-
"step": 8100
|
| 1225 |
-
},
|
| 1226 |
-
{
|
| 1227 |
-
"epoch": 2.3802612481857763,
|
| 1228 |
-
"grad_norm": 1.2111109495162964,
|
| 1229 |
-
"learning_rate": 7.619738751814224e-05,
|
| 1230 |
-
"loss": 2.0101,
|
| 1231 |
-
"step": 8200
|
| 1232 |
-
},
|
| 1233 |
-
{
|
| 1234 |
-
"epoch": 2.3802612481857763,
|
| 1235 |
-
"eval_loss": 1.0501890182495117,
|
| 1236 |
-
"eval_runtime": 213.0351,
|
| 1237 |
-
"eval_samples_per_second": 213.575,
|
| 1238 |
-
"eval_steps_per_second": 3.337,
|
| 1239 |
-
"step": 8200
|
| 1240 |
-
},
|
| 1241 |
-
{
|
| 1242 |
-
"epoch": 2.409288824383164,
|
| 1243 |
-
"grad_norm": 1.2333025932312012,
|
| 1244 |
-
"learning_rate": 7.590711175616836e-05,
|
| 1245 |
-
"loss": 2.0,
|
| 1246 |
-
"step": 8300
|
| 1247 |
-
},
|
| 1248 |
-
{
|
| 1249 |
-
"epoch": 2.409288824383164,
|
| 1250 |
-
"eval_loss": 1.051579236984253,
|
| 1251 |
-
"eval_runtime": 213.5529,
|
| 1252 |
-
"eval_samples_per_second": 213.057,
|
| 1253 |
-
"eval_steps_per_second": 3.329,
|
| 1254 |
-
"step": 8300
|
| 1255 |
-
},
|
| 1256 |
-
{
|
| 1257 |
-
"epoch": 2.4383164005805513,
|
| 1258 |
-
"grad_norm": 1.3394699096679688,
|
| 1259 |
-
"learning_rate": 7.561683599419449e-05,
|
| 1260 |
-
"loss": 1.9986,
|
| 1261 |
-
"step": 8400
|
| 1262 |
-
},
|
| 1263 |
-
{
|
| 1264 |
-
"epoch": 2.4383164005805513,
|
| 1265 |
-
"eval_loss": 1.0520364046096802,
|
| 1266 |
-
"eval_runtime": 212.3818,
|
| 1267 |
-
"eval_samples_per_second": 214.232,
|
| 1268 |
-
"eval_steps_per_second": 3.348,
|
| 1269 |
-
"step": 8400
|
| 1270 |
-
},
|
| 1271 |
-
{
|
| 1272 |
-
"epoch": 2.467343976777939,
|
| 1273 |
-
"grad_norm": 1.334936261177063,
|
| 1274 |
-
"learning_rate": 7.532656023222062e-05,
|
| 1275 |
-
"loss": 1.993,
|
| 1276 |
-
"step": 8500
|
| 1277 |
-
},
|
| 1278 |
-
{
|
| 1279 |
-
"epoch": 2.467343976777939,
|
| 1280 |
-
"eval_loss": 1.0490361452102661,
|
| 1281 |
-
"eval_runtime": 213.9415,
|
| 1282 |
-
"eval_samples_per_second": 212.67,
|
| 1283 |
"eval_steps_per_second": 3.323,
|
| 1284 |
-
"step":
|
| 1285 |
-
},
|
| 1286 |
-
{
|
| 1287 |
-
"epoch": 2.4963715529753268,
|
| 1288 |
-
"grad_norm": 1.3085263967514038,
|
| 1289 |
-
"learning_rate": 7.503628447024675e-05,
|
| 1290 |
-
"loss": 1.9771,
|
| 1291 |
-
"step": 8600
|
| 1292 |
-
},
|
| 1293 |
-
{
|
| 1294 |
-
"epoch": 2.4963715529753268,
|
| 1295 |
-
"eval_loss": 1.0522186756134033,
|
| 1296 |
-
"eval_runtime": 212.3302,
|
| 1297 |
-
"eval_samples_per_second": 214.284,
|
| 1298 |
-
"eval_steps_per_second": 3.349,
|
| 1299 |
-
"step": 8600
|
| 1300 |
-
},
|
| 1301 |
-
{
|
| 1302 |
-
"epoch": 2.525399129172714,
|
| 1303 |
-
"grad_norm": 1.4204107522964478,
|
| 1304 |
-
"learning_rate": 7.474600870827286e-05,
|
| 1305 |
-
"loss": 1.9848,
|
| 1306 |
-
"step": 8700
|
| 1307 |
-
},
|
| 1308 |
-
{
|
| 1309 |
-
"epoch": 2.525399129172714,
|
| 1310 |
-
"eval_loss": 1.0486035346984863,
|
| 1311 |
-
"eval_runtime": 213.5477,
|
| 1312 |
-
"eval_samples_per_second": 213.062,
|
| 1313 |
-
"eval_steps_per_second": 3.329,
|
| 1314 |
-
"step": 8700
|
| 1315 |
-
},
|
| 1316 |
-
{
|
| 1317 |
-
"epoch": 2.5544267053701017,
|
| 1318 |
-
"grad_norm": 1.2411503791809082,
|
| 1319 |
-
"learning_rate": 7.445573294629898e-05,
|
| 1320 |
-
"loss": 2.0016,
|
| 1321 |
-
"step": 8800
|
| 1322 |
-
},
|
| 1323 |
-
{
|
| 1324 |
-
"epoch": 2.5544267053701017,
|
| 1325 |
-
"eval_loss": 1.0516774654388428,
|
| 1326 |
-
"eval_runtime": 213.2425,
|
| 1327 |
-
"eval_samples_per_second": 213.367,
|
| 1328 |
-
"eval_steps_per_second": 3.334,
|
| 1329 |
-
"step": 8800
|
| 1330 |
-
},
|
| 1331 |
-
{
|
| 1332 |
-
"epoch": 2.583454281567489,
|
| 1333 |
-
"grad_norm": 1.2166720628738403,
|
| 1334 |
-
"learning_rate": 7.416545718432511e-05,
|
| 1335 |
-
"loss": 1.9761,
|
| 1336 |
-
"step": 8900
|
| 1337 |
-
},
|
| 1338 |
-
{
|
| 1339 |
-
"epoch": 2.583454281567489,
|
| 1340 |
-
"eval_loss": 1.0438764095306396,
|
| 1341 |
-
"eval_runtime": 213.2447,
|
| 1342 |
-
"eval_samples_per_second": 213.365,
|
| 1343 |
-
"eval_steps_per_second": 3.334,
|
| 1344 |
-
"step": 8900
|
| 1345 |
-
},
|
| 1346 |
-
{
|
| 1347 |
-
"epoch": 2.6124818577648767,
|
| 1348 |
-
"grad_norm": 1.307707667350769,
|
| 1349 |
-
"learning_rate": 7.387518142235124e-05,
|
| 1350 |
-
"loss": 1.9753,
|
| 1351 |
-
"step": 9000
|
| 1352 |
-
},
|
| 1353 |
-
{
|
| 1354 |
-
"epoch": 2.6124818577648767,
|
| 1355 |
-
"eval_loss": 1.0445740222930908,
|
| 1356 |
-
"eval_runtime": 212.5813,
|
| 1357 |
-
"eval_samples_per_second": 214.031,
|
| 1358 |
-
"eval_steps_per_second": 3.345,
|
| 1359 |
-
"step": 9000
|
| 1360 |
-
},
|
| 1361 |
-
{
|
| 1362 |
-
"epoch": 2.641509433962264,
|
| 1363 |
-
"grad_norm": 1.3446862697601318,
|
| 1364 |
-
"learning_rate": 7.358490566037736e-05,
|
| 1365 |
-
"loss": 1.9795,
|
| 1366 |
-
"step": 9100
|
| 1367 |
-
},
|
| 1368 |
-
{
|
| 1369 |
-
"epoch": 2.641509433962264,
|
| 1370 |
-
"eval_loss": 1.0461750030517578,
|
| 1371 |
-
"eval_runtime": 213.2022,
|
| 1372 |
-
"eval_samples_per_second": 213.408,
|
| 1373 |
-
"eval_steps_per_second": 3.335,
|
| 1374 |
-
"step": 9100
|
| 1375 |
-
},
|
| 1376 |
-
{
|
| 1377 |
-
"epoch": 2.6705370101596517,
|
| 1378 |
-
"grad_norm": 1.25364351272583,
|
| 1379 |
-
"learning_rate": 7.329462989840349e-05,
|
| 1380 |
-
"loss": 1.966,
|
| 1381 |
-
"step": 9200
|
| 1382 |
-
},
|
| 1383 |
-
{
|
| 1384 |
-
"epoch": 2.6705370101596517,
|
| 1385 |
-
"eval_loss": 1.0489540100097656,
|
| 1386 |
-
"eval_runtime": 213.3373,
|
| 1387 |
-
"eval_samples_per_second": 213.273,
|
| 1388 |
-
"eval_steps_per_second": 3.333,
|
| 1389 |
-
"step": 9200
|
| 1390 |
-
},
|
| 1391 |
-
{
|
| 1392 |
-
"epoch": 2.699564586357039,
|
| 1393 |
-
"grad_norm": 1.317325472831726,
|
| 1394 |
-
"learning_rate": 7.300435413642961e-05,
|
| 1395 |
-
"loss": 1.9853,
|
| 1396 |
-
"step": 9300
|
| 1397 |
-
},
|
| 1398 |
-
{
|
| 1399 |
-
"epoch": 2.699564586357039,
|
| 1400 |
-
"eval_loss": 1.04426109790802,
|
| 1401 |
-
"eval_runtime": 212.5953,
|
| 1402 |
-
"eval_samples_per_second": 214.017,
|
| 1403 |
-
"eval_steps_per_second": 3.344,
|
| 1404 |
-
"step": 9300
|
| 1405 |
-
},
|
| 1406 |
-
{
|
| 1407 |
-
"epoch": 2.7285921625544267,
|
| 1408 |
-
"grad_norm": 1.2580476999282837,
|
| 1409 |
-
"learning_rate": 7.271407837445574e-05,
|
| 1410 |
-
"loss": 1.9873,
|
| 1411 |
-
"step": 9400
|
| 1412 |
-
},
|
| 1413 |
-
{
|
| 1414 |
-
"epoch": 2.7285921625544267,
|
| 1415 |
-
"eval_loss": 1.0441796779632568,
|
| 1416 |
-
"eval_runtime": 213.1744,
|
| 1417 |
-
"eval_samples_per_second": 213.436,
|
| 1418 |
-
"eval_steps_per_second": 3.335,
|
| 1419 |
-
"step": 9400
|
| 1420 |
}
|
| 1421 |
],
|
| 1422 |
"logging_steps": 100,
|
|
@@ -1431,7 +36,7 @@
|
|
| 1431 |
"early_stopping_threshold": 0.0
|
| 1432 |
},
|
| 1433 |
"attributes": {
|
| 1434 |
-
"early_stopping_patience_counter":
|
| 1435 |
}
|
| 1436 |
},
|
| 1437 |
"TrainerControl": {
|
|
@@ -1440,12 +45,12 @@
|
|
| 1440 |
"should_evaluate": false,
|
| 1441 |
"should_log": false,
|
| 1442 |
"should_save": true,
|
| 1443 |
-
"should_training_stop":
|
| 1444 |
},
|
| 1445 |
"attributes": {}
|
| 1446 |
}
|
| 1447 |
},
|
| 1448 |
-
"total_flos":
|
| 1449 |
"train_batch_size": 64,
|
| 1450 |
"trial_name": null,
|
| 1451 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 1.2625532150268555,
|
| 3 |
+
"best_model_checkpoint": "mgh6/TCS_MLM_50/checkpoint-100",
|
| 4 |
+
"epoch": 0.02902757619738752,
|
| 5 |
"eval_steps": 100,
|
| 6 |
+
"global_step": 100,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 0.02902757619738752,
|
| 13 |
+
"grad_norm": 1.1695395708084106,
|
| 14 |
"learning_rate": 9.970972423802612e-05,
|
| 15 |
+
"loss": 2.8263,
|
| 16 |
"step": 100
|
| 17 |
},
|
| 18 |
{
|
| 19 |
"epoch": 0.02902757619738752,
|
| 20 |
+
"eval_loss": 1.2625532150268555,
|
| 21 |
+
"eval_runtime": 213.9369,
|
| 22 |
+
"eval_samples_per_second": 212.651,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 23 |
"eval_steps_per_second": 3.323,
|
| 24 |
+
"step": 100
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 25 |
}
|
| 26 |
],
|
| 27 |
"logging_steps": 100,
|
|
|
|
| 36 |
"early_stopping_threshold": 0.0
|
| 37 |
},
|
| 38 |
"attributes": {
|
| 39 |
+
"early_stopping_patience_counter": 0
|
| 40 |
}
|
| 41 |
},
|
| 42 |
"TrainerControl": {
|
|
|
|
| 45 |
"should_evaluate": false,
|
| 46 |
"should_log": false,
|
| 47 |
"should_save": true,
|
| 48 |
+
"should_training_stop": false
|
| 49 |
},
|
| 50 |
"attributes": {}
|
| 51 |
}
|
| 52 |
},
|
| 53 |
+
"total_flos": 1000387607789568.0,
|
| 54 |
"train_batch_size": 64,
|
| 55 |
"trial_name": null,
|
| 56 |
"trial_params": null
|
last-checkpoint/training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5368
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:98f4319603876b63ddfc21d2259b95fa764f31a2204f8d89c6fce365f7769879
|
| 3 |
size 5368
|