Training in progress, step 2829, checkpoint
Browse files
checkpoint-2829/adapter_config.json
CHANGED
|
@@ -23,13 +23,13 @@
|
|
| 23 |
"rank_pattern": {},
|
| 24 |
"revision": null,
|
| 25 |
"target_modules": [
|
| 26 |
-
"up_proj",
|
| 27 |
-
"gate_proj",
|
| 28 |
-
"v_proj",
|
| 29 |
-
"down_proj",
|
| 30 |
"o_proj",
|
|
|
|
|
|
|
|
|
|
|
|
|
| 31 |
"q_proj",
|
| 32 |
-
"
|
| 33 |
],
|
| 34 |
"task_type": "CAUSAL_LM",
|
| 35 |
"use_dora": false,
|
|
|
|
| 23 |
"rank_pattern": {},
|
| 24 |
"revision": null,
|
| 25 |
"target_modules": [
|
|
|
|
|
|
|
|
|
|
|
|
|
| 26 |
"o_proj",
|
| 27 |
+
"down_proj",
|
| 28 |
+
"v_proj",
|
| 29 |
+
"up_proj",
|
| 30 |
+
"k_proj",
|
| 31 |
"q_proj",
|
| 32 |
+
"gate_proj"
|
| 33 |
],
|
| 34 |
"task_type": "CAUSAL_LM",
|
| 35 |
"use_dora": false,
|
checkpoint-2829/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 161533192
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dfb2255e4c3fb20e8e4bccbaad552f223e6ccbe6e3f398b950768e7faa2dda15
|
| 3 |
size 161533192
|
checkpoint-2829/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 323290986
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2c889fe2f9148ff98f8a1248f5589c57d3fb18cdbb34a05474927c2b2f88d393
|
| 3 |
size 323290986
|
checkpoint-2829/trainer_state.json
CHANGED
|
@@ -10,2424 +10,2424 @@
|
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 0.010604453870625663,
|
| 13 |
-
"grad_norm": 2.
|
| 14 |
"learning_rate": 4.982325910215624e-05,
|
| 15 |
-
"loss": 1.
|
| 16 |
"step": 10
|
| 17 |
},
|
| 18 |
{
|
| 19 |
"epoch": 0.021208907741251327,
|
| 20 |
-
"grad_norm": 0.
|
| 21 |
"learning_rate": 4.964651820431248e-05,
|
| 22 |
-
"loss":
|
| 23 |
"step": 20
|
| 24 |
},
|
| 25 |
{
|
| 26 |
"epoch": 0.031813361611876985,
|
| 27 |
-
"grad_norm": 0.
|
| 28 |
"learning_rate": 4.946977730646872e-05,
|
| 29 |
-
"loss": 0.
|
| 30 |
"step": 30
|
| 31 |
},
|
| 32 |
{
|
| 33 |
"epoch": 0.042417815482502653,
|
| 34 |
-
"grad_norm": 0.
|
| 35 |
"learning_rate": 4.929303640862496e-05,
|
| 36 |
-
"loss": 0.
|
| 37 |
"step": 40
|
| 38 |
},
|
| 39 |
{
|
| 40 |
"epoch": 0.053022269353128315,
|
| 41 |
-
"grad_norm": 0.
|
| 42 |
"learning_rate": 4.91162955107812e-05,
|
| 43 |
-
"loss": 0.
|
| 44 |
"step": 50
|
| 45 |
},
|
| 46 |
{
|
| 47 |
"epoch": 0.053022269353128315,
|
| 48 |
-
"eval_loss": 0.
|
| 49 |
-
"eval_runtime": 11.
|
| 50 |
-
"eval_samples_per_second": 40.
|
| 51 |
-
"eval_steps_per_second": 2.
|
| 52 |
"step": 50
|
| 53 |
},
|
| 54 |
{
|
| 55 |
"epoch": 0.06362672322375397,
|
| 56 |
-
"grad_norm": 0.
|
| 57 |
"learning_rate": 4.893955461293744e-05,
|
| 58 |
-
"loss": 0.
|
| 59 |
"step": 60
|
| 60 |
},
|
| 61 |
{
|
| 62 |
"epoch": 0.07423117709437964,
|
| 63 |
-
"grad_norm": 0.
|
| 64 |
"learning_rate": 4.876281371509368e-05,
|
| 65 |
-
"loss": 0.
|
| 66 |
"step": 70
|
| 67 |
},
|
| 68 |
{
|
| 69 |
"epoch": 0.08483563096500531,
|
| 70 |
-
"grad_norm": 0.
|
| 71 |
"learning_rate": 4.858607281724991e-05,
|
| 72 |
-
"loss": 0.
|
| 73 |
"step": 80
|
| 74 |
},
|
| 75 |
{
|
| 76 |
"epoch": 0.09544008483563096,
|
| 77 |
-
"grad_norm": 0.
|
| 78 |
"learning_rate": 4.8409331919406155e-05,
|
| 79 |
-
"loss": 0.
|
| 80 |
"step": 90
|
| 81 |
},
|
| 82 |
{
|
| 83 |
"epoch": 0.10604453870625663,
|
| 84 |
-
"grad_norm": 0.
|
| 85 |
"learning_rate": 4.823259102156239e-05,
|
| 86 |
-
"loss": 0.
|
| 87 |
"step": 100
|
| 88 |
},
|
| 89 |
{
|
| 90 |
"epoch": 0.10604453870625663,
|
| 91 |
-
"eval_loss": 0.
|
| 92 |
-
"eval_runtime": 11.
|
| 93 |
-
"eval_samples_per_second": 40.
|
| 94 |
-
"eval_steps_per_second": 2.
|
| 95 |
"step": 100
|
| 96 |
},
|
| 97 |
{
|
| 98 |
"epoch": 0.11664899257688228,
|
| 99 |
-
"grad_norm": 0.
|
| 100 |
"learning_rate": 4.8055850123718633e-05,
|
| 101 |
-
"loss": 0.
|
| 102 |
"step": 110
|
| 103 |
},
|
| 104 |
{
|
| 105 |
"epoch": 0.12725344644750794,
|
| 106 |
-
"grad_norm": 0.
|
| 107 |
"learning_rate": 4.7879109225874866e-05,
|
| 108 |
-
"loss": 0.
|
| 109 |
"step": 120
|
| 110 |
},
|
| 111 |
{
|
| 112 |
"epoch": 0.1378579003181336,
|
| 113 |
-
"grad_norm": 0.
|
| 114 |
"learning_rate": 4.770236832803111e-05,
|
| 115 |
-
"loss": 0.
|
| 116 |
"step": 130
|
| 117 |
},
|
| 118 |
{
|
| 119 |
"epoch": 0.14846235418875928,
|
| 120 |
-
"grad_norm": 0.
|
| 121 |
"learning_rate": 4.7525627430187344e-05,
|
| 122 |
-
"loss": 0.
|
| 123 |
"step": 140
|
| 124 |
},
|
| 125 |
{
|
| 126 |
"epoch": 0.15906680805938495,
|
| 127 |
-
"grad_norm": 0.
|
| 128 |
"learning_rate": 4.734888653234359e-05,
|
| 129 |
-
"loss": 0.
|
| 130 |
"step": 150
|
| 131 |
},
|
| 132 |
{
|
| 133 |
"epoch": 0.15906680805938495,
|
| 134 |
-
"eval_loss": 0.
|
| 135 |
-
"eval_runtime": 11.
|
| 136 |
-
"eval_samples_per_second": 40.
|
| 137 |
-
"eval_steps_per_second": 2.
|
| 138 |
"step": 150
|
| 139 |
},
|
| 140 |
{
|
| 141 |
"epoch": 0.16967126193001061,
|
| 142 |
-
"grad_norm": 0.
|
| 143 |
"learning_rate": 4.717214563449982e-05,
|
| 144 |
-
"loss": 0.
|
| 145 |
"step": 160
|
| 146 |
},
|
| 147 |
{
|
| 148 |
"epoch": 0.18027571580063625,
|
| 149 |
-
"grad_norm": 0.
|
| 150 |
"learning_rate": 4.699540473665606e-05,
|
| 151 |
-
"loss": 0.
|
| 152 |
"step": 170
|
| 153 |
},
|
| 154 |
{
|
| 155 |
"epoch": 0.19088016967126192,
|
| 156 |
-
"grad_norm": 0.
|
| 157 |
"learning_rate": 4.681866383881231e-05,
|
| 158 |
-
"loss": 0.
|
| 159 |
"step": 180
|
| 160 |
},
|
| 161 |
{
|
| 162 |
"epoch": 0.2014846235418876,
|
| 163 |
-
"grad_norm": 0.
|
| 164 |
"learning_rate": 4.664192294096854e-05,
|
| 165 |
-
"loss": 0.
|
| 166 |
"step": 190
|
| 167 |
},
|
| 168 |
{
|
| 169 |
"epoch": 0.21208907741251326,
|
| 170 |
-
"grad_norm": 0.
|
| 171 |
"learning_rate": 4.6465182043124786e-05,
|
| 172 |
-
"loss": 0.
|
| 173 |
"step": 200
|
| 174 |
},
|
| 175 |
{
|
| 176 |
"epoch": 0.21208907741251326,
|
| 177 |
-
"eval_loss": 0.
|
| 178 |
-
"eval_runtime": 11.
|
| 179 |
-
"eval_samples_per_second": 40.
|
| 180 |
-
"eval_steps_per_second": 2.
|
| 181 |
"step": 200
|
| 182 |
},
|
| 183 |
{
|
| 184 |
"epoch": 0.22269353128313893,
|
| 185 |
-
"grad_norm": 0.
|
| 186 |
"learning_rate": 4.628844114528102e-05,
|
| 187 |
-
"loss": 0.
|
| 188 |
"step": 210
|
| 189 |
},
|
| 190 |
{
|
| 191 |
"epoch": 0.23329798515376457,
|
| 192 |
-
"grad_norm": 0.
|
| 193 |
"learning_rate": 4.6111700247437265e-05,
|
| 194 |
-
"loss": 0.
|
| 195 |
"step": 220
|
| 196 |
},
|
| 197 |
{
|
| 198 |
"epoch": 0.24390243902439024,
|
| 199 |
-
"grad_norm": 0.
|
| 200 |
"learning_rate": 4.59349593495935e-05,
|
| 201 |
-
"loss": 0.
|
| 202 |
"step": 230
|
| 203 |
},
|
| 204 |
{
|
| 205 |
"epoch": 0.2545068928950159,
|
| 206 |
-
"grad_norm": 0.
|
| 207 |
"learning_rate": 4.5758218451749736e-05,
|
| 208 |
-
"loss": 0.
|
| 209 |
"step": 240
|
| 210 |
},
|
| 211 |
{
|
| 212 |
"epoch": 0.2651113467656416,
|
| 213 |
-
"grad_norm": 0.
|
| 214 |
"learning_rate": 4.5581477553905975e-05,
|
| 215 |
-
"loss": 0.
|
| 216 |
"step": 250
|
| 217 |
},
|
| 218 |
{
|
| 219 |
"epoch": 0.2651113467656416,
|
| 220 |
-
"eval_loss": 0.
|
| 221 |
-
"eval_runtime": 11.
|
| 222 |
-
"eval_samples_per_second": 40.
|
| 223 |
-
"eval_steps_per_second": 2.
|
| 224 |
"step": 250
|
| 225 |
},
|
| 226 |
{
|
| 227 |
"epoch": 0.2757158006362672,
|
| 228 |
-
"grad_norm": 0.
|
| 229 |
"learning_rate": 4.5404736656062215e-05,
|
| 230 |
"loss": 0.477,
|
| 231 |
"step": 260
|
| 232 |
},
|
| 233 |
{
|
| 234 |
"epoch": 0.2863202545068929,
|
| 235 |
-
"grad_norm": 0.
|
| 236 |
"learning_rate": 4.5227995758218454e-05,
|
| 237 |
-
"loss": 0.
|
| 238 |
"step": 270
|
| 239 |
},
|
| 240 |
{
|
| 241 |
"epoch": 0.29692470837751855,
|
| 242 |
-
"grad_norm": 0.
|
| 243 |
"learning_rate": 4.505125486037469e-05,
|
| 244 |
-
"loss": 0.
|
| 245 |
"step": 280
|
| 246 |
},
|
| 247 |
{
|
| 248 |
"epoch": 0.3075291622481442,
|
| 249 |
-
"grad_norm": 0.
|
| 250 |
"learning_rate": 4.487451396253093e-05,
|
| 251 |
-
"loss": 0.
|
| 252 |
"step": 290
|
| 253 |
},
|
| 254 |
{
|
| 255 |
"epoch": 0.3181336161187699,
|
| 256 |
-
"grad_norm": 0.
|
| 257 |
"learning_rate": 4.469777306468717e-05,
|
| 258 |
-
"loss": 0.
|
| 259 |
"step": 300
|
| 260 |
},
|
| 261 |
{
|
| 262 |
"epoch": 0.3181336161187699,
|
| 263 |
-
"eval_loss": 0.
|
| 264 |
-
"eval_runtime": 11.
|
| 265 |
-
"eval_samples_per_second": 40.
|
| 266 |
-
"eval_steps_per_second": 2.
|
| 267 |
"step": 300
|
| 268 |
},
|
| 269 |
{
|
| 270 |
"epoch": 0.32873806998939553,
|
| 271 |
-
"grad_norm": 0.
|
| 272 |
"learning_rate": 4.452103216684341e-05,
|
| 273 |
-
"loss": 0.
|
| 274 |
"step": 310
|
| 275 |
},
|
| 276 |
{
|
| 277 |
"epoch": 0.33934252386002123,
|
| 278 |
-
"grad_norm": 0.
|
| 279 |
"learning_rate": 4.434429126899965e-05,
|
| 280 |
-
"loss": 0.
|
| 281 |
"step": 320
|
| 282 |
},
|
| 283 |
{
|
| 284 |
"epoch": 0.34994697773064687,
|
| 285 |
-
"grad_norm": 0.
|
| 286 |
"learning_rate": 4.416755037115589e-05,
|
| 287 |
-
"loss": 0.
|
| 288 |
"step": 330
|
| 289 |
},
|
| 290 |
{
|
| 291 |
"epoch": 0.3605514316012725,
|
| 292 |
-
"grad_norm": 0.
|
| 293 |
"learning_rate": 4.399080947331213e-05,
|
| 294 |
-
"loss": 0.
|
| 295 |
"step": 340
|
| 296 |
},
|
| 297 |
{
|
| 298 |
"epoch": 0.3711558854718982,
|
| 299 |
-
"grad_norm": 0.
|
| 300 |
"learning_rate": 4.381406857546837e-05,
|
| 301 |
-
"loss": 0.
|
| 302 |
"step": 350
|
| 303 |
},
|
| 304 |
{
|
| 305 |
"epoch": 0.3711558854718982,
|
| 306 |
-
"eval_loss": 0.
|
| 307 |
-
"eval_runtime": 11.
|
| 308 |
-
"eval_samples_per_second": 40.
|
| 309 |
-
"eval_steps_per_second": 2.
|
| 310 |
"step": 350
|
| 311 |
},
|
| 312 |
{
|
| 313 |
"epoch": 0.38176033934252385,
|
| 314 |
-
"grad_norm": 0.
|
| 315 |
"learning_rate": 4.3637327677624606e-05,
|
| 316 |
-
"loss": 0.
|
| 317 |
"step": 360
|
| 318 |
},
|
| 319 |
{
|
| 320 |
"epoch": 0.39236479321314954,
|
| 321 |
-
"grad_norm": 0.
|
| 322 |
"learning_rate": 4.3460586779780846e-05,
|
| 323 |
"loss": 0.4528,
|
| 324 |
"step": 370
|
| 325 |
},
|
| 326 |
{
|
| 327 |
"epoch": 0.4029692470837752,
|
| 328 |
-
"grad_norm": 0.
|
| 329 |
"learning_rate": 4.328384588193708e-05,
|
| 330 |
-
"loss": 0.
|
| 331 |
"step": 380
|
| 332 |
},
|
| 333 |
{
|
| 334 |
"epoch": 0.4135737009544008,
|
| 335 |
-
"grad_norm": 0.
|
| 336 |
"learning_rate": 4.3107104984093324e-05,
|
| 337 |
-
"loss": 0.
|
| 338 |
"step": 390
|
| 339 |
},
|
| 340 |
{
|
| 341 |
"epoch": 0.4241781548250265,
|
| 342 |
-
"grad_norm": 0.
|
| 343 |
"learning_rate": 4.2930364086249556e-05,
|
| 344 |
-
"loss": 0.
|
| 345 |
"step": 400
|
| 346 |
},
|
| 347 |
{
|
| 348 |
"epoch": 0.4241781548250265,
|
| 349 |
-
"eval_loss": 0.
|
| 350 |
-
"eval_runtime": 11.
|
| 351 |
-
"eval_samples_per_second": 40.
|
| 352 |
-
"eval_steps_per_second": 2.
|
| 353 |
"step": 400
|
| 354 |
},
|
| 355 |
{
|
| 356 |
"epoch": 0.43478260869565216,
|
| 357 |
-
"grad_norm": 0.
|
| 358 |
"learning_rate": 4.27536231884058e-05,
|
| 359 |
-
"loss": 0.
|
| 360 |
"step": 410
|
| 361 |
},
|
| 362 |
{
|
| 363 |
"epoch": 0.44538706256627786,
|
| 364 |
-
"grad_norm": 0.
|
| 365 |
"learning_rate": 4.2576882290562035e-05,
|
| 366 |
-
"loss": 0.
|
| 367 |
"step": 420
|
| 368 |
},
|
| 369 |
{
|
| 370 |
"epoch": 0.4559915164369035,
|
| 371 |
-
"grad_norm": 0.
|
| 372 |
"learning_rate": 4.240014139271828e-05,
|
| 373 |
-
"loss": 0.
|
| 374 |
"step": 430
|
| 375 |
},
|
| 376 |
{
|
| 377 |
"epoch": 0.46659597030752914,
|
| 378 |
-
"grad_norm": 0.
|
| 379 |
"learning_rate": 4.222340049487451e-05,
|
| 380 |
-
"loss": 0.
|
| 381 |
"step": 440
|
| 382 |
},
|
| 383 |
{
|
| 384 |
"epoch": 0.47720042417815484,
|
| 385 |
-
"grad_norm": 0.
|
| 386 |
"learning_rate": 4.204665959703076e-05,
|
| 387 |
-
"loss": 0.
|
| 388 |
"step": 450
|
| 389 |
},
|
| 390 |
{
|
| 391 |
"epoch": 0.47720042417815484,
|
| 392 |
-
"eval_loss": 0.
|
| 393 |
-
"eval_runtime": 11.
|
| 394 |
-
"eval_samples_per_second": 40.
|
| 395 |
-
"eval_steps_per_second": 2.
|
| 396 |
"step": 450
|
| 397 |
},
|
| 398 |
{
|
| 399 |
"epoch": 0.4878048780487805,
|
| 400 |
-
"grad_norm": 0.
|
| 401 |
"learning_rate": 4.186991869918699e-05,
|
| 402 |
"loss": 0.4294,
|
| 403 |
"step": 460
|
| 404 |
},
|
| 405 |
{
|
| 406 |
"epoch": 0.4984093319194062,
|
| 407 |
-
"grad_norm": 0.
|
| 408 |
"learning_rate": 4.169317780134323e-05,
|
| 409 |
-
"loss": 0.
|
| 410 |
"step": 470
|
| 411 |
},
|
| 412 |
{
|
| 413 |
"epoch": 0.5090137857900318,
|
| 414 |
-
"grad_norm": 0.
|
| 415 |
"learning_rate": 4.151643690349947e-05,
|
| 416 |
"loss": 0.4639,
|
| 417 |
"step": 480
|
| 418 |
},
|
| 419 |
{
|
| 420 |
"epoch": 0.5196182396606575,
|
| 421 |
-
"grad_norm": 0.
|
| 422 |
"learning_rate": 4.133969600565571e-05,
|
| 423 |
"loss": 0.4173,
|
| 424 |
"step": 490
|
| 425 |
},
|
| 426 |
{
|
| 427 |
"epoch": 0.5302226935312832,
|
| 428 |
-
"grad_norm": 0.
|
| 429 |
"learning_rate": 4.116295510781195e-05,
|
| 430 |
-
"loss": 0.
|
| 431 |
"step": 500
|
| 432 |
},
|
| 433 |
{
|
| 434 |
"epoch": 0.5302226935312832,
|
| 435 |
-
"eval_loss": 0.
|
| 436 |
-
"eval_runtime": 11.
|
| 437 |
-
"eval_samples_per_second": 40.
|
| 438 |
-
"eval_steps_per_second": 2.
|
| 439 |
"step": 500
|
| 440 |
},
|
| 441 |
{
|
| 442 |
"epoch": 0.5408271474019088,
|
| 443 |
-
"grad_norm": 0.
|
| 444 |
"learning_rate": 4.098621420996819e-05,
|
| 445 |
-
"loss": 0.
|
| 446 |
"step": 510
|
| 447 |
},
|
| 448 |
{
|
| 449 |
"epoch": 0.5514316012725344,
|
| 450 |
-
"grad_norm": 0.
|
| 451 |
"learning_rate": 4.080947331212443e-05,
|
| 452 |
-
"loss": 0.
|
| 453 |
"step": 520
|
| 454 |
},
|
| 455 |
{
|
| 456 |
"epoch": 0.5620360551431601,
|
| 457 |
-
"grad_norm":
|
| 458 |
"learning_rate": 4.0632732414280666e-05,
|
| 459 |
-
"loss": 0.
|
| 460 |
"step": 530
|
| 461 |
},
|
| 462 |
{
|
| 463 |
"epoch": 0.5726405090137858,
|
| 464 |
-
"grad_norm": 1.
|
| 465 |
"learning_rate": 4.0455991516436905e-05,
|
| 466 |
-
"loss": 0.
|
| 467 |
"step": 540
|
| 468 |
},
|
| 469 |
{
|
| 470 |
"epoch": 0.5832449628844114,
|
| 471 |
-
"grad_norm": 0.
|
| 472 |
"learning_rate": 4.0279250618593144e-05,
|
| 473 |
-
"loss": 0.
|
| 474 |
"step": 550
|
| 475 |
},
|
| 476 |
{
|
| 477 |
"epoch": 0.5832449628844114,
|
| 478 |
-
"eval_loss": 0.
|
| 479 |
-
"eval_runtime": 11.
|
| 480 |
-
"eval_samples_per_second": 40.
|
| 481 |
-
"eval_steps_per_second": 2.
|
| 482 |
"step": 550
|
| 483 |
},
|
| 484 |
{
|
| 485 |
"epoch": 0.5938494167550371,
|
| 486 |
-
"grad_norm": 1.
|
| 487 |
"learning_rate": 4.0102509720749383e-05,
|
| 488 |
-
"loss": 0.
|
| 489 |
"step": 560
|
| 490 |
},
|
| 491 |
{
|
| 492 |
"epoch": 0.6044538706256628,
|
| 493 |
-
"grad_norm": 1.
|
| 494 |
"learning_rate": 3.992576882290562e-05,
|
| 495 |
-
"loss": 0.
|
| 496 |
"step": 570
|
| 497 |
},
|
| 498 |
{
|
| 499 |
"epoch": 0.6150583244962884,
|
| 500 |
-
"grad_norm": 0.
|
| 501 |
"learning_rate": 3.974902792506186e-05,
|
| 502 |
-
"loss": 0.
|
| 503 |
"step": 580
|
| 504 |
},
|
| 505 |
{
|
| 506 |
"epoch": 0.6256627783669141,
|
| 507 |
-
"grad_norm": 0.
|
| 508 |
"learning_rate": 3.95722870272181e-05,
|
| 509 |
-
"loss": 0.
|
| 510 |
"step": 590
|
| 511 |
},
|
| 512 |
{
|
| 513 |
"epoch": 0.6362672322375398,
|
| 514 |
-
"grad_norm": 0.
|
| 515 |
"learning_rate": 3.939554612937434e-05,
|
| 516 |
-
"loss": 0.
|
| 517 |
"step": 600
|
| 518 |
},
|
| 519 |
{
|
| 520 |
"epoch": 0.6362672322375398,
|
| 521 |
-
"eval_loss": 0.
|
| 522 |
-
"eval_runtime": 11.
|
| 523 |
-
"eval_samples_per_second": 40.
|
| 524 |
-
"eval_steps_per_second": 2.
|
| 525 |
"step": 600
|
| 526 |
},
|
| 527 |
{
|
| 528 |
"epoch": 0.6468716861081655,
|
| 529 |
-
"grad_norm": 0.
|
| 530 |
"learning_rate": 3.921880523153057e-05,
|
| 531 |
-
"loss": 0.
|
| 532 |
"step": 610
|
| 533 |
},
|
| 534 |
{
|
| 535 |
"epoch": 0.6574761399787911,
|
| 536 |
-
"grad_norm": 0.
|
| 537 |
"learning_rate": 3.904206433368682e-05,
|
| 538 |
-
"loss": 0.
|
| 539 |
"step": 620
|
| 540 |
},
|
| 541 |
{
|
| 542 |
"epoch": 0.6680805938494168,
|
| 543 |
-
"grad_norm": 0.
|
| 544 |
"learning_rate": 3.886532343584305e-05,
|
| 545 |
-
"loss": 0.
|
| 546 |
"step": 630
|
| 547 |
},
|
| 548 |
{
|
| 549 |
"epoch": 0.6786850477200425,
|
| 550 |
-
"grad_norm": 0.
|
| 551 |
"learning_rate": 3.86885825379993e-05,
|
| 552 |
-
"loss": 0.
|
| 553 |
"step": 640
|
| 554 |
},
|
| 555 |
{
|
| 556 |
"epoch": 0.689289501590668,
|
| 557 |
-
"grad_norm": 0.
|
| 558 |
"learning_rate": 3.851184164015553e-05,
|
| 559 |
-
"loss": 0.
|
| 560 |
"step": 650
|
| 561 |
},
|
| 562 |
{
|
| 563 |
"epoch": 0.689289501590668,
|
| 564 |
-
"eval_loss": 0.
|
| 565 |
-
"eval_runtime": 11.
|
| 566 |
-
"eval_samples_per_second": 40.
|
| 567 |
-
"eval_steps_per_second": 2.
|
| 568 |
"step": 650
|
| 569 |
},
|
| 570 |
{
|
| 571 |
"epoch": 0.6998939554612937,
|
| 572 |
-
"grad_norm": 0.
|
| 573 |
"learning_rate": 3.8335100742311775e-05,
|
| 574 |
"loss": 0.4264,
|
| 575 |
"step": 660
|
| 576 |
},
|
| 577 |
{
|
| 578 |
"epoch": 0.7104984093319194,
|
| 579 |
-
"grad_norm": 1.
|
| 580 |
"learning_rate": 3.8158359844468015e-05,
|
| 581 |
-
"loss": 0.
|
| 582 |
"step": 670
|
| 583 |
},
|
| 584 |
{
|
| 585 |
"epoch": 0.721102863202545,
|
| 586 |
-
"grad_norm": 0.
|
| 587 |
"learning_rate": 3.7981618946624254e-05,
|
| 588 |
-
"loss": 0.
|
| 589 |
"step": 680
|
| 590 |
},
|
| 591 |
{
|
| 592 |
"epoch": 0.7317073170731707,
|
| 593 |
-
"grad_norm": 1.
|
| 594 |
"learning_rate": 3.780487804878049e-05,
|
| 595 |
-
"loss": 0.
|
| 596 |
"step": 690
|
| 597 |
},
|
| 598 |
{
|
| 599 |
"epoch": 0.7423117709437964,
|
| 600 |
-
"grad_norm": 1.
|
| 601 |
"learning_rate": 3.7628137150936725e-05,
|
| 602 |
-
"loss": 0.
|
| 603 |
"step": 700
|
| 604 |
},
|
| 605 |
{
|
| 606 |
"epoch": 0.7423117709437964,
|
| 607 |
-
"eval_loss": 0.
|
| 608 |
-
"eval_runtime": 11.
|
| 609 |
-
"eval_samples_per_second": 40.
|
| 610 |
-
"eval_steps_per_second": 2.
|
| 611 |
"step": 700
|
| 612 |
},
|
| 613 |
{
|
| 614 |
"epoch": 0.7529162248144221,
|
| 615 |
-
"grad_norm": 1.
|
| 616 |
"learning_rate": 3.745139625309297e-05,
|
| 617 |
-
"loss": 0.
|
| 618 |
"step": 710
|
| 619 |
},
|
| 620 |
{
|
| 621 |
"epoch": 0.7635206786850477,
|
| 622 |
-
"grad_norm": 1.
|
| 623 |
"learning_rate": 3.7274655355249204e-05,
|
| 624 |
-
"loss": 0.
|
| 625 |
"step": 720
|
| 626 |
},
|
| 627 |
{
|
| 628 |
"epoch": 0.7741251325556734,
|
| 629 |
-
"grad_norm": 0.
|
| 630 |
"learning_rate": 3.709791445740545e-05,
|
| 631 |
-
"loss": 0.
|
| 632 |
"step": 730
|
| 633 |
},
|
| 634 |
{
|
| 635 |
"epoch": 0.7847295864262991,
|
| 636 |
-
"grad_norm": 1.
|
| 637 |
"learning_rate": 3.692117355956168e-05,
|
| 638 |
-
"loss": 0.
|
| 639 |
"step": 740
|
| 640 |
},
|
| 641 |
{
|
| 642 |
"epoch": 0.7953340402969247,
|
| 643 |
-
"grad_norm": 1.
|
| 644 |
"learning_rate": 3.674443266171793e-05,
|
| 645 |
-
"loss": 0.
|
| 646 |
"step": 750
|
| 647 |
},
|
| 648 |
{
|
| 649 |
"epoch": 0.7953340402969247,
|
| 650 |
-
"eval_loss": 0.
|
| 651 |
-
"eval_runtime": 11.
|
| 652 |
-
"eval_samples_per_second": 40.
|
| 653 |
-
"eval_steps_per_second": 2.
|
| 654 |
"step": 750
|
| 655 |
},
|
| 656 |
{
|
| 657 |
"epoch": 0.8059384941675504,
|
| 658 |
-
"grad_norm": 0.
|
| 659 |
"learning_rate": 3.656769176387416e-05,
|
| 660 |
-
"loss": 0.
|
| 661 |
"step": 760
|
| 662 |
},
|
| 663 |
{
|
| 664 |
"epoch": 0.8165429480381761,
|
| 665 |
-
"grad_norm": 0.
|
| 666 |
"learning_rate": 3.63909508660304e-05,
|
| 667 |
-
"loss": 0.
|
| 668 |
"step": 770
|
| 669 |
},
|
| 670 |
{
|
| 671 |
"epoch": 0.8271474019088016,
|
| 672 |
-
"grad_norm": 0.
|
| 673 |
"learning_rate": 3.621420996818664e-05,
|
| 674 |
-
"loss": 0.
|
| 675 |
"step": 780
|
| 676 |
},
|
| 677 |
{
|
| 678 |
"epoch": 0.8377518557794273,
|
| 679 |
-
"grad_norm": 1.
|
| 680 |
"learning_rate": 3.603746907034288e-05,
|
| 681 |
-
"loss": 0.
|
| 682 |
"step": 790
|
| 683 |
},
|
| 684 |
{
|
| 685 |
"epoch": 0.848356309650053,
|
| 686 |
-
"grad_norm": 1.
|
| 687 |
"learning_rate": 3.586072817249912e-05,
|
| 688 |
"loss": 0.4224,
|
| 689 |
"step": 800
|
| 690 |
},
|
| 691 |
{
|
| 692 |
"epoch": 0.848356309650053,
|
| 693 |
-
"eval_loss": 0.
|
| 694 |
-
"eval_runtime": 11.
|
| 695 |
-
"eval_samples_per_second": 40.
|
| 696 |
-
"eval_steps_per_second": 2.
|
| 697 |
"step": 800
|
| 698 |
},
|
| 699 |
{
|
| 700 |
"epoch": 0.8589607635206787,
|
| 701 |
-
"grad_norm": 1.
|
| 702 |
"learning_rate": 3.5683987274655356e-05,
|
| 703 |
-
"loss": 0.
|
| 704 |
"step": 810
|
| 705 |
},
|
| 706 |
{
|
| 707 |
"epoch": 0.8695652173913043,
|
| 708 |
-
"grad_norm": 1.
|
| 709 |
"learning_rate": 3.5507246376811596e-05,
|
| 710 |
-
"loss": 0.
|
| 711 |
"step": 820
|
| 712 |
},
|
| 713 |
{
|
| 714 |
"epoch": 0.88016967126193,
|
| 715 |
-
"grad_norm":
|
| 716 |
"learning_rate": 3.5330505478967835e-05,
|
| 717 |
-
"loss": 0.
|
| 718 |
"step": 830
|
| 719 |
},
|
| 720 |
{
|
| 721 |
"epoch": 0.8907741251325557,
|
| 722 |
-
"grad_norm": 1.
|
| 723 |
"learning_rate": 3.5153764581124074e-05,
|
| 724 |
-
"loss": 0.
|
| 725 |
"step": 840
|
| 726 |
},
|
| 727 |
{
|
| 728 |
"epoch": 0.9013785790031813,
|
| 729 |
-
"grad_norm": 1.
|
| 730 |
"learning_rate": 3.497702368328031e-05,
|
| 731 |
-
"loss": 0.
|
| 732 |
"step": 850
|
| 733 |
},
|
| 734 |
{
|
| 735 |
"epoch": 0.9013785790031813,
|
| 736 |
-
"eval_loss": 0.
|
| 737 |
-
"eval_runtime": 11.
|
| 738 |
-
"eval_samples_per_second": 40.
|
| 739 |
-
"eval_steps_per_second": 2.
|
| 740 |
"step": 850
|
| 741 |
},
|
| 742 |
{
|
| 743 |
"epoch": 0.911983032873807,
|
| 744 |
-
"grad_norm": 1.
|
| 745 |
"learning_rate": 3.480028278543655e-05,
|
| 746 |
-
"loss": 0.
|
| 747 |
"step": 860
|
| 748 |
},
|
| 749 |
{
|
| 750 |
"epoch": 0.9225874867444327,
|
| 751 |
-
"grad_norm": 1.
|
| 752 |
"learning_rate": 3.462354188759279e-05,
|
| 753 |
-
"loss": 0.
|
| 754 |
"step": 870
|
| 755 |
},
|
| 756 |
{
|
| 757 |
"epoch": 0.9331919406150583,
|
| 758 |
-
"grad_norm": 1.
|
| 759 |
"learning_rate": 3.444680098974903e-05,
|
| 760 |
-
"loss": 0.
|
| 761 |
"step": 880
|
| 762 |
},
|
| 763 |
{
|
| 764 |
"epoch": 0.943796394485684,
|
| 765 |
-
"grad_norm": 1.
|
| 766 |
"learning_rate": 3.427006009190527e-05,
|
| 767 |
-
"loss": 0.
|
| 768 |
"step": 890
|
| 769 |
},
|
| 770 |
{
|
| 771 |
"epoch": 0.9544008483563097,
|
| 772 |
-
"grad_norm": 0.
|
| 773 |
"learning_rate": 3.409331919406151e-05,
|
| 774 |
-
"loss": 0.
|
| 775 |
"step": 900
|
| 776 |
},
|
| 777 |
{
|
| 778 |
"epoch": 0.9544008483563097,
|
| 779 |
-
"eval_loss": 0.
|
| 780 |
-
"eval_runtime": 11.
|
| 781 |
-
"eval_samples_per_second": 40.
|
| 782 |
-
"eval_steps_per_second": 2.
|
| 783 |
"step": 900
|
| 784 |
},
|
| 785 |
{
|
| 786 |
"epoch": 0.9650053022269353,
|
| 787 |
-
"grad_norm": 1.
|
| 788 |
"learning_rate": 3.391657829621775e-05,
|
| 789 |
-
"loss": 0.
|
| 790 |
"step": 910
|
| 791 |
},
|
| 792 |
{
|
| 793 |
"epoch": 0.975609756097561,
|
| 794 |
-
"grad_norm": 1.
|
| 795 |
"learning_rate": 3.373983739837399e-05,
|
| 796 |
-
"loss": 0.
|
| 797 |
"step": 920
|
| 798 |
},
|
| 799 |
{
|
| 800 |
"epoch": 0.9862142099681867,
|
| 801 |
-
"grad_norm": 1.
|
| 802 |
"learning_rate": 3.356309650053022e-05,
|
| 803 |
-
"loss": 0.
|
| 804 |
"step": 930
|
| 805 |
},
|
| 806 |
{
|
| 807 |
"epoch": 0.9968186638388123,
|
| 808 |
-
"grad_norm": 1.
|
| 809 |
"learning_rate": 3.3386355602686466e-05,
|
| 810 |
-
"loss": 0.
|
| 811 |
"step": 940
|
| 812 |
},
|
| 813 |
{
|
| 814 |
"epoch": 1.007423117709438,
|
| 815 |
-
"grad_norm": 1.
|
| 816 |
"learning_rate": 3.32096147048427e-05,
|
| 817 |
-
"loss": 0.
|
| 818 |
"step": 950
|
| 819 |
},
|
| 820 |
{
|
| 821 |
"epoch": 1.007423117709438,
|
| 822 |
-
"eval_loss": 0.
|
| 823 |
-
"eval_runtime": 11.
|
| 824 |
-
"eval_samples_per_second": 40.
|
| 825 |
-
"eval_steps_per_second": 2.
|
| 826 |
"step": 950
|
| 827 |
},
|
| 828 |
{
|
| 829 |
"epoch": 1.0180275715800637,
|
| 830 |
-
"grad_norm": 1.
|
| 831 |
"learning_rate": 3.3032873806998944e-05,
|
| 832 |
-
"loss": 0.
|
| 833 |
"step": 960
|
| 834 |
},
|
| 835 |
{
|
| 836 |
"epoch": 1.0286320254506893,
|
| 837 |
-
"grad_norm": 1.
|
| 838 |
"learning_rate": 3.285613290915518e-05,
|
| 839 |
-
"loss": 0.
|
| 840 |
"step": 970
|
| 841 |
},
|
| 842 |
{
|
| 843 |
"epoch": 1.039236479321315,
|
| 844 |
-
"grad_norm": 1.
|
| 845 |
"learning_rate": 3.267939201131142e-05,
|
| 846 |
-
"loss": 0.
|
| 847 |
"step": 980
|
| 848 |
},
|
| 849 |
{
|
| 850 |
"epoch": 1.0498409331919407,
|
| 851 |
-
"grad_norm": 1.
|
| 852 |
"learning_rate": 3.2502651113467655e-05,
|
| 853 |
-
"loss": 0.
|
| 854 |
"step": 990
|
| 855 |
},
|
| 856 |
{
|
| 857 |
"epoch": 1.0604453870625663,
|
| 858 |
-
"grad_norm": 1.
|
| 859 |
"learning_rate": 3.2325910215623894e-05,
|
| 860 |
-
"loss": 0.
|
| 861 |
"step": 1000
|
| 862 |
},
|
| 863 |
{
|
| 864 |
"epoch": 1.0604453870625663,
|
| 865 |
-
"eval_loss": 0.
|
| 866 |
-
"eval_runtime": 11.
|
| 867 |
-
"eval_samples_per_second": 40.
|
| 868 |
-
"eval_steps_per_second": 2.
|
| 869 |
"step": 1000
|
| 870 |
},
|
| 871 |
{
|
| 872 |
"epoch": 1.0710498409331919,
|
| 873 |
-
"grad_norm": 1.
|
| 874 |
"learning_rate": 3.2149169317780133e-05,
|
| 875 |
"loss": 0.3274,
|
| 876 |
"step": 1010
|
| 877 |
},
|
| 878 |
{
|
| 879 |
"epoch": 1.0816542948038177,
|
| 880 |
-
"grad_norm": 1.
|
| 881 |
"learning_rate": 3.197242841993637e-05,
|
| 882 |
-
"loss": 0.
|
| 883 |
"step": 1020
|
| 884 |
},
|
| 885 |
{
|
| 886 |
"epoch": 1.0922587486744433,
|
| 887 |
-
"grad_norm": 1.
|
| 888 |
"learning_rate": 3.179568752209262e-05,
|
| 889 |
-
"loss": 0.
|
| 890 |
"step": 1030
|
| 891 |
},
|
| 892 |
{
|
| 893 |
"epoch": 1.1028632025450689,
|
| 894 |
-
"grad_norm": 1.
|
| 895 |
"learning_rate": 3.161894662424885e-05,
|
| 896 |
-
"loss": 0.
|
| 897 |
"step": 1040
|
| 898 |
},
|
| 899 |
{
|
| 900 |
"epoch": 1.1134676564156947,
|
| 901 |
-
"grad_norm": 1.
|
| 902 |
"learning_rate": 3.14422057264051e-05,
|
| 903 |
-
"loss": 0.
|
| 904 |
"step": 1050
|
| 905 |
},
|
| 906 |
{
|
| 907 |
"epoch": 1.1134676564156947,
|
| 908 |
-
"eval_loss": 0.
|
| 909 |
-
"eval_runtime": 11.
|
| 910 |
-
"eval_samples_per_second": 40.
|
| 911 |
-
"eval_steps_per_second": 2.
|
| 912 |
"step": 1050
|
| 913 |
},
|
| 914 |
{
|
| 915 |
"epoch": 1.1240721102863203,
|
| 916 |
-
"grad_norm": 1.
|
| 917 |
"learning_rate": 3.126546482856133e-05,
|
| 918 |
-
"loss": 0.
|
| 919 |
"step": 1060
|
| 920 |
},
|
| 921 |
{
|
| 922 |
"epoch": 1.1346765641569458,
|
| 923 |
-
"grad_norm": 1.
|
| 924 |
"learning_rate": 3.108872393071757e-05,
|
| 925 |
-
"loss": 0.
|
| 926 |
"step": 1070
|
| 927 |
},
|
| 928 |
{
|
| 929 |
"epoch": 1.1452810180275717,
|
| 930 |
-
"grad_norm": 1.
|
| 931 |
"learning_rate": 3.091198303287381e-05,
|
| 932 |
-
"loss": 0.
|
| 933 |
"step": 1080
|
| 934 |
},
|
| 935 |
{
|
| 936 |
"epoch": 1.1558854718981972,
|
| 937 |
-
"grad_norm": 1.
|
| 938 |
"learning_rate": 3.073524213503005e-05,
|
| 939 |
-
"loss": 0.
|
| 940 |
"step": 1090
|
| 941 |
},
|
| 942 |
{
|
| 943 |
"epoch": 1.1664899257688228,
|
| 944 |
-
"grad_norm": 1.
|
| 945 |
"learning_rate": 3.0558501237186286e-05,
|
| 946 |
-
"loss": 0.
|
| 947 |
"step": 1100
|
| 948 |
},
|
| 949 |
{
|
| 950 |
"epoch": 1.1664899257688228,
|
| 951 |
-
"eval_loss": 0.
|
| 952 |
-
"eval_runtime": 11.
|
| 953 |
-
"eval_samples_per_second": 40.
|
| 954 |
-
"eval_steps_per_second": 2.
|
| 955 |
"step": 1100
|
| 956 |
},
|
| 957 |
{
|
| 958 |
"epoch": 1.1770943796394486,
|
| 959 |
-
"grad_norm": 1.
|
| 960 |
"learning_rate": 3.0381760339342525e-05,
|
| 961 |
-
"loss": 0.
|
| 962 |
"step": 1110
|
| 963 |
},
|
| 964 |
{
|
| 965 |
"epoch": 1.1876988335100742,
|
| 966 |
-
"grad_norm": 1.
|
| 967 |
"learning_rate": 3.0205019441498768e-05,
|
| 968 |
"loss": 0.3238,
|
| 969 |
"step": 1120
|
| 970 |
},
|
| 971 |
{
|
| 972 |
"epoch": 1.1983032873806998,
|
| 973 |
-
"grad_norm": 1.
|
| 974 |
"learning_rate": 3.0028278543655004e-05,
|
| 975 |
-
"loss": 0.
|
| 976 |
"step": 1130
|
| 977 |
},
|
| 978 |
{
|
| 979 |
"epoch": 1.2089077412513256,
|
| 980 |
-
"grad_norm": 1.
|
| 981 |
"learning_rate": 2.985153764581124e-05,
|
| 982 |
-
"loss": 0.
|
| 983 |
"step": 1140
|
| 984 |
},
|
| 985 |
{
|
| 986 |
"epoch": 1.2195121951219512,
|
| 987 |
-
"grad_norm": 1.
|
| 988 |
"learning_rate": 2.9674796747967482e-05,
|
| 989 |
"loss": 0.3431,
|
| 990 |
"step": 1150
|
| 991 |
},
|
| 992 |
{
|
| 993 |
"epoch": 1.2195121951219512,
|
| 994 |
-
"eval_loss": 0.
|
| 995 |
-
"eval_runtime": 11.
|
| 996 |
-
"eval_samples_per_second": 40.
|
| 997 |
-
"eval_steps_per_second": 2.
|
| 998 |
"step": 1150
|
| 999 |
},
|
| 1000 |
{
|
| 1001 |
"epoch": 1.2301166489925768,
|
| 1002 |
-
"grad_norm": 1.
|
| 1003 |
"learning_rate": 2.9498055850123718e-05,
|
| 1004 |
-
"loss": 0.
|
| 1005 |
"step": 1160
|
| 1006 |
},
|
| 1007 |
{
|
| 1008 |
"epoch": 1.2407211028632026,
|
| 1009 |
-
"grad_norm": 1.
|
| 1010 |
"learning_rate": 2.932131495227996e-05,
|
| 1011 |
-
"loss": 0.
|
| 1012 |
"step": 1170
|
| 1013 |
},
|
| 1014 |
{
|
| 1015 |
"epoch": 1.2513255567338282,
|
| 1016 |
-
"grad_norm": 1.
|
| 1017 |
"learning_rate": 2.9144574054436196e-05,
|
| 1018 |
-
"loss": 0.
|
| 1019 |
"step": 1180
|
| 1020 |
},
|
| 1021 |
{
|
| 1022 |
"epoch": 1.2619300106044538,
|
| 1023 |
-
"grad_norm": 1.
|
| 1024 |
"learning_rate": 2.896783315659244e-05,
|
| 1025 |
-
"loss": 0.
|
| 1026 |
"step": 1190
|
| 1027 |
},
|
| 1028 |
{
|
| 1029 |
"epoch": 1.2725344644750796,
|
| 1030 |
-
"grad_norm": 1.
|
| 1031 |
"learning_rate": 2.8791092258748675e-05,
|
| 1032 |
-
"loss": 0.
|
| 1033 |
"step": 1200
|
| 1034 |
},
|
| 1035 |
{
|
| 1036 |
"epoch": 1.2725344644750796,
|
| 1037 |
-
"eval_loss": 0.
|
| 1038 |
-
"eval_runtime": 11.
|
| 1039 |
-
"eval_samples_per_second": 40.
|
| 1040 |
-
"eval_steps_per_second": 2.
|
| 1041 |
"step": 1200
|
| 1042 |
},
|
| 1043 |
{
|
| 1044 |
"epoch": 1.2831389183457051,
|
| 1045 |
-
"grad_norm": 1.
|
| 1046 |
"learning_rate": 2.8614351360904917e-05,
|
| 1047 |
-
"loss": 0.
|
| 1048 |
"step": 1210
|
| 1049 |
},
|
| 1050 |
{
|
| 1051 |
"epoch": 1.2937433722163307,
|
| 1052 |
-
"grad_norm": 1.
|
| 1053 |
"learning_rate": 2.8437610463061153e-05,
|
| 1054 |
"loss": 0.3253,
|
| 1055 |
"step": 1220
|
| 1056 |
},
|
| 1057 |
{
|
| 1058 |
"epoch": 1.3043478260869565,
|
| 1059 |
-
"grad_norm": 1.
|
| 1060 |
"learning_rate": 2.826086956521739e-05,
|
| 1061 |
-
"loss": 0.
|
| 1062 |
"step": 1230
|
| 1063 |
},
|
| 1064 |
{
|
| 1065 |
"epoch": 1.3149522799575821,
|
| 1066 |
-
"grad_norm": 1.
|
| 1067 |
"learning_rate": 2.808412866737363e-05,
|
| 1068 |
-
"loss": 0.
|
| 1069 |
"step": 1240
|
| 1070 |
},
|
| 1071 |
{
|
| 1072 |
"epoch": 1.3255567338282077,
|
| 1073 |
-
"grad_norm": 1.
|
| 1074 |
"learning_rate": 2.790738776952987e-05,
|
| 1075 |
-
"loss": 0.
|
| 1076 |
"step": 1250
|
| 1077 |
},
|
| 1078 |
{
|
| 1079 |
"epoch": 1.3255567338282077,
|
| 1080 |
-
"eval_loss": 0.
|
| 1081 |
-
"eval_runtime": 11.
|
| 1082 |
-
"eval_samples_per_second": 40.
|
| 1083 |
-
"eval_steps_per_second": 2.
|
| 1084 |
"step": 1250
|
| 1085 |
},
|
| 1086 |
{
|
| 1087 |
"epoch": 1.3361611876988335,
|
| 1088 |
-
"grad_norm": 1.
|
| 1089 |
"learning_rate": 2.773064687168611e-05,
|
| 1090 |
-
"loss": 0.
|
| 1091 |
"step": 1260
|
| 1092 |
},
|
| 1093 |
{
|
| 1094 |
"epoch": 1.346765641569459,
|
| 1095 |
-
"grad_norm": 1.
|
| 1096 |
"learning_rate": 2.755390597384235e-05,
|
| 1097 |
-
"loss": 0.
|
| 1098 |
"step": 1270
|
| 1099 |
},
|
| 1100 |
{
|
| 1101 |
"epoch": 1.357370095440085,
|
| 1102 |
-
"grad_norm": 1.
|
| 1103 |
"learning_rate": 2.7377165075998588e-05,
|
| 1104 |
-
"loss": 0.
|
| 1105 |
"step": 1280
|
| 1106 |
},
|
| 1107 |
{
|
| 1108 |
"epoch": 1.3679745493107105,
|
| 1109 |
-
"grad_norm": 1.
|
| 1110 |
"learning_rate": 2.7200424178154827e-05,
|
| 1111 |
-
"loss": 0.
|
| 1112 |
"step": 1290
|
| 1113 |
},
|
| 1114 |
{
|
| 1115 |
"epoch": 1.378579003181336,
|
| 1116 |
-
"grad_norm": 1.
|
| 1117 |
"learning_rate": 2.7023683280311063e-05,
|
| 1118 |
-
"loss": 0.
|
| 1119 |
"step": 1300
|
| 1120 |
},
|
| 1121 |
{
|
| 1122 |
"epoch": 1.378579003181336,
|
| 1123 |
-
"eval_loss": 0.
|
| 1124 |
-
"eval_runtime": 11.
|
| 1125 |
-
"eval_samples_per_second": 40.
|
| 1126 |
-
"eval_steps_per_second": 2.
|
| 1127 |
"step": 1300
|
| 1128 |
},
|
| 1129 |
{
|
| 1130 |
"epoch": 1.389183457051962,
|
| 1131 |
-
"grad_norm": 1.
|
| 1132 |
"learning_rate": 2.6846942382467306e-05,
|
| 1133 |
-
"loss": 0.
|
| 1134 |
"step": 1310
|
| 1135 |
},
|
| 1136 |
{
|
| 1137 |
"epoch": 1.3997879109225875,
|
| 1138 |
-
"grad_norm": 1.
|
| 1139 |
"learning_rate": 2.667020148462354e-05,
|
| 1140 |
-
"loss": 0.
|
| 1141 |
"step": 1320
|
| 1142 |
},
|
| 1143 |
{
|
| 1144 |
"epoch": 1.4103923647932133,
|
| 1145 |
-
"grad_norm": 1.
|
| 1146 |
"learning_rate": 2.6493460586779784e-05,
|
| 1147 |
-
"loss": 0.
|
| 1148 |
"step": 1330
|
| 1149 |
},
|
| 1150 |
{
|
| 1151 |
"epoch": 1.4209968186638389,
|
| 1152 |
-
"grad_norm": 1.
|
| 1153 |
"learning_rate": 2.631671968893602e-05,
|
| 1154 |
-
"loss": 0.
|
| 1155 |
"step": 1340
|
| 1156 |
},
|
| 1157 |
{
|
| 1158 |
"epoch": 1.4316012725344645,
|
| 1159 |
-
"grad_norm": 1.
|
| 1160 |
"learning_rate": 2.6139978791092262e-05,
|
| 1161 |
-
"loss": 0.
|
| 1162 |
"step": 1350
|
| 1163 |
},
|
| 1164 |
{
|
| 1165 |
"epoch": 1.4316012725344645,
|
| 1166 |
-
"eval_loss": 0.
|
| 1167 |
-
"eval_runtime": 11.
|
| 1168 |
-
"eval_samples_per_second": 40.
|
| 1169 |
-
"eval_steps_per_second": 2.
|
| 1170 |
"step": 1350
|
| 1171 |
},
|
| 1172 |
{
|
| 1173 |
"epoch": 1.4422057264050903,
|
| 1174 |
-
"grad_norm": 1.
|
| 1175 |
"learning_rate": 2.5963237893248498e-05,
|
| 1176 |
-
"loss": 0.
|
| 1177 |
"step": 1360
|
| 1178 |
},
|
| 1179 |
{
|
| 1180 |
"epoch": 1.4528101802757158,
|
| 1181 |
-
"grad_norm": 1.
|
| 1182 |
"learning_rate": 2.5786496995404734e-05,
|
| 1183 |
-
"loss": 0.
|
| 1184 |
"step": 1370
|
| 1185 |
},
|
| 1186 |
{
|
| 1187 |
"epoch": 1.4634146341463414,
|
| 1188 |
-
"grad_norm": 1.
|
| 1189 |
"learning_rate": 2.5609756097560977e-05,
|
| 1190 |
"loss": 0.3271,
|
| 1191 |
"step": 1380
|
| 1192 |
},
|
| 1193 |
{
|
| 1194 |
"epoch": 1.4740190880169672,
|
| 1195 |
-
"grad_norm": 1.
|
| 1196 |
"learning_rate": 2.5433015199717212e-05,
|
| 1197 |
-
"loss": 0.
|
| 1198 |
"step": 1390
|
| 1199 |
},
|
| 1200 |
{
|
| 1201 |
"epoch": 1.4846235418875928,
|
| 1202 |
-
"grad_norm": 1.
|
| 1203 |
"learning_rate": 2.5256274301873455e-05,
|
| 1204 |
-
"loss": 0.
|
| 1205 |
"step": 1400
|
| 1206 |
},
|
| 1207 |
{
|
| 1208 |
"epoch": 1.4846235418875928,
|
| 1209 |
-
"eval_loss": 0.
|
| 1210 |
-
"eval_runtime": 11.
|
| 1211 |
-
"eval_samples_per_second": 40.
|
| 1212 |
-
"eval_steps_per_second": 2.
|
| 1213 |
"step": 1400
|
| 1214 |
},
|
| 1215 |
{
|
| 1216 |
"epoch": 1.4952279957582184,
|
| 1217 |
-
"grad_norm": 1.
|
| 1218 |
"learning_rate": 2.507953340402969e-05,
|
| 1219 |
-
"loss": 0.
|
| 1220 |
"step": 1410
|
| 1221 |
},
|
| 1222 |
{
|
| 1223 |
"epoch": 1.5058324496288442,
|
| 1224 |
-
"grad_norm": 1.
|
| 1225 |
"learning_rate": 2.4902792506185933e-05,
|
| 1226 |
-
"loss": 0.
|
| 1227 |
"step": 1420
|
| 1228 |
},
|
| 1229 |
{
|
| 1230 |
"epoch": 1.5164369034994698,
|
| 1231 |
-
"grad_norm": 1.
|
| 1232 |
"learning_rate": 2.4726051608342173e-05,
|
| 1233 |
-
"loss": 0.
|
| 1234 |
"step": 1430
|
| 1235 |
},
|
| 1236 |
{
|
| 1237 |
"epoch": 1.5270413573700954,
|
| 1238 |
-
"grad_norm": 1.
|
| 1239 |
"learning_rate": 2.4549310710498412e-05,
|
| 1240 |
-
"loss": 0.
|
| 1241 |
"step": 1440
|
| 1242 |
},
|
| 1243 |
{
|
| 1244 |
"epoch": 1.5376458112407212,
|
| 1245 |
-
"grad_norm": 1.
|
| 1246 |
"learning_rate": 2.437256981265465e-05,
|
| 1247 |
-
"loss": 0.
|
| 1248 |
"step": 1450
|
| 1249 |
},
|
| 1250 |
{
|
| 1251 |
"epoch": 1.5376458112407212,
|
| 1252 |
-
"eval_loss": 0.
|
| 1253 |
-
"eval_runtime": 11.
|
| 1254 |
-
"eval_samples_per_second": 40.
|
| 1255 |
-
"eval_steps_per_second": 2.
|
| 1256 |
"step": 1450
|
| 1257 |
},
|
| 1258 |
{
|
| 1259 |
"epoch": 1.5482502651113468,
|
| 1260 |
-
"grad_norm": 1.
|
| 1261 |
"learning_rate": 2.419582891481089e-05,
|
| 1262 |
"loss": 0.3233,
|
| 1263 |
"step": 1460
|
| 1264 |
},
|
| 1265 |
{
|
| 1266 |
"epoch": 1.5588547189819724,
|
| 1267 |
-
"grad_norm": 1.
|
| 1268 |
"learning_rate": 2.401908801696713e-05,
|
| 1269 |
-
"loss": 0.
|
| 1270 |
"step": 1470
|
| 1271 |
},
|
| 1272 |
{
|
| 1273 |
"epoch": 1.5694591728525982,
|
| 1274 |
-
"grad_norm": 1.
|
| 1275 |
"learning_rate": 2.3842347119123365e-05,
|
| 1276 |
-
"loss": 0.
|
| 1277 |
"step": 1480
|
| 1278 |
},
|
| 1279 |
{
|
| 1280 |
"epoch": 1.5800636267232238,
|
| 1281 |
-
"grad_norm": 1.
|
| 1282 |
"learning_rate": 2.3665606221279604e-05,
|
| 1283 |
-
"loss": 0.
|
| 1284 |
"step": 1490
|
| 1285 |
},
|
| 1286 |
{
|
| 1287 |
"epoch": 1.5906680805938493,
|
| 1288 |
-
"grad_norm": 1.
|
| 1289 |
"learning_rate": 2.3488865323435844e-05,
|
| 1290 |
-
"loss": 0.
|
| 1291 |
"step": 1500
|
| 1292 |
},
|
| 1293 |
{
|
| 1294 |
"epoch": 1.5906680805938493,
|
| 1295 |
-
"eval_loss": 0.
|
| 1296 |
-
"eval_runtime": 11.
|
| 1297 |
-
"eval_samples_per_second": 40.
|
| 1298 |
-
"eval_steps_per_second": 2.
|
| 1299 |
"step": 1500
|
| 1300 |
},
|
| 1301 |
{
|
| 1302 |
"epoch": 1.6012725344644752,
|
| 1303 |
-
"grad_norm": 1.
|
| 1304 |
"learning_rate": 2.3312124425592083e-05,
|
| 1305 |
-
"loss": 0.
|
| 1306 |
"step": 1510
|
| 1307 |
},
|
| 1308 |
{
|
| 1309 |
"epoch": 1.6118769883351007,
|
| 1310 |
-
"grad_norm": 1.
|
| 1311 |
"learning_rate": 2.3135383527748322e-05,
|
| 1312 |
-
"loss": 0.
|
| 1313 |
"step": 1520
|
| 1314 |
},
|
| 1315 |
{
|
| 1316 |
"epoch": 1.6224814422057263,
|
| 1317 |
-
"grad_norm": 1.
|
| 1318 |
"learning_rate": 2.295864262990456e-05,
|
| 1319 |
-
"loss": 0.
|
| 1320 |
"step": 1530
|
| 1321 |
},
|
| 1322 |
{
|
| 1323 |
"epoch": 1.6330858960763521,
|
| 1324 |
-
"grad_norm": 1.
|
| 1325 |
"learning_rate": 2.27819017320608e-05,
|
| 1326 |
-
"loss": 0.
|
| 1327 |
"step": 1540
|
| 1328 |
},
|
| 1329 |
{
|
| 1330 |
"epoch": 1.6436903499469777,
|
| 1331 |
-
"grad_norm": 1.
|
| 1332 |
"learning_rate": 2.260516083421704e-05,
|
| 1333 |
-
"loss": 0.
|
| 1334 |
"step": 1550
|
| 1335 |
},
|
| 1336 |
{
|
| 1337 |
"epoch": 1.6436903499469777,
|
| 1338 |
-
"eval_loss": 0.
|
| 1339 |
-
"eval_runtime": 11.
|
| 1340 |
-
"eval_samples_per_second": 40.
|
| 1341 |
-
"eval_steps_per_second": 2.
|
| 1342 |
"step": 1550
|
| 1343 |
},
|
| 1344 |
{
|
| 1345 |
"epoch": 1.6542948038176033,
|
| 1346 |
-
"grad_norm": 1.
|
| 1347 |
"learning_rate": 2.2428419936373275e-05,
|
| 1348 |
-
"loss": 0.
|
| 1349 |
"step": 1560
|
| 1350 |
},
|
| 1351 |
{
|
| 1352 |
"epoch": 1.664899257688229,
|
| 1353 |
-
"grad_norm": 1.
|
| 1354 |
"learning_rate": 2.2251679038529514e-05,
|
| 1355 |
-
"loss": 0.
|
| 1356 |
"step": 1570
|
| 1357 |
},
|
| 1358 |
{
|
| 1359 |
"epoch": 1.6755037115588547,
|
| 1360 |
-
"grad_norm": 1.
|
| 1361 |
"learning_rate": 2.2074938140685754e-05,
|
| 1362 |
-
"loss": 0.
|
| 1363 |
"step": 1580
|
| 1364 |
},
|
| 1365 |
{
|
| 1366 |
"epoch": 1.6861081654294803,
|
| 1367 |
-
"grad_norm": 1.
|
| 1368 |
"learning_rate": 2.1898197242841996e-05,
|
| 1369 |
"loss": 0.3194,
|
| 1370 |
"step": 1590
|
| 1371 |
},
|
| 1372 |
{
|
| 1373 |
"epoch": 1.696712619300106,
|
| 1374 |
-
"grad_norm": 1.
|
| 1375 |
"learning_rate": 2.1721456344998235e-05,
|
| 1376 |
-
"loss": 0.
|
| 1377 |
"step": 1600
|
| 1378 |
},
|
| 1379 |
{
|
| 1380 |
"epoch": 1.696712619300106,
|
| 1381 |
-
"eval_loss": 0.
|
| 1382 |
-
"eval_runtime": 11.
|
| 1383 |
-
"eval_samples_per_second": 40.
|
| 1384 |
-
"eval_steps_per_second": 2.
|
| 1385 |
"step": 1600
|
| 1386 |
},
|
| 1387 |
{
|
| 1388 |
"epoch": 1.7073170731707317,
|
| 1389 |
-
"grad_norm": 1.
|
| 1390 |
"learning_rate": 2.1544715447154475e-05,
|
| 1391 |
-
"loss": 0.
|
| 1392 |
"step": 1610
|
| 1393 |
},
|
| 1394 |
{
|
| 1395 |
"epoch": 1.7179215270413573,
|
| 1396 |
-
"grad_norm": 1.
|
| 1397 |
"learning_rate": 2.1367974549310714e-05,
|
| 1398 |
-
"loss": 0.
|
| 1399 |
"step": 1620
|
| 1400 |
},
|
| 1401 |
{
|
| 1402 |
"epoch": 1.728525980911983,
|
| 1403 |
-
"grad_norm": 1.
|
| 1404 |
"learning_rate": 2.1191233651466953e-05,
|
| 1405 |
-
"loss": 0.
|
| 1406 |
"step": 1630
|
| 1407 |
},
|
| 1408 |
{
|
| 1409 |
"epoch": 1.7391304347826086,
|
| 1410 |
-
"grad_norm": 1.
|
| 1411 |
"learning_rate": 2.101449275362319e-05,
|
| 1412 |
-
"loss": 0.
|
| 1413 |
"step": 1640
|
| 1414 |
},
|
| 1415 |
{
|
| 1416 |
"epoch": 1.7497348886532342,
|
| 1417 |
-
"grad_norm": 1.
|
| 1418 |
"learning_rate": 2.0837751855779428e-05,
|
| 1419 |
-
"loss": 0.
|
| 1420 |
"step": 1650
|
| 1421 |
},
|
| 1422 |
{
|
| 1423 |
"epoch": 1.7497348886532342,
|
| 1424 |
-
"eval_loss": 0.
|
| 1425 |
-
"eval_runtime": 11.
|
| 1426 |
-
"eval_samples_per_second": 40.
|
| 1427 |
-
"eval_steps_per_second": 2.
|
| 1428 |
"step": 1650
|
| 1429 |
},
|
| 1430 |
{
|
| 1431 |
"epoch": 1.76033934252386,
|
| 1432 |
-
"grad_norm": 1.
|
| 1433 |
"learning_rate": 2.0661010957935667e-05,
|
| 1434 |
-
"loss": 0.
|
| 1435 |
"step": 1660
|
| 1436 |
},
|
| 1437 |
{
|
| 1438 |
"epoch": 1.7709437963944858,
|
| 1439 |
-
"grad_norm": 1.
|
| 1440 |
"learning_rate": 2.0484270060091906e-05,
|
| 1441 |
-
"loss": 0.
|
| 1442 |
"step": 1670
|
| 1443 |
},
|
| 1444 |
{
|
| 1445 |
"epoch": 1.7815482502651112,
|
| 1446 |
-
"grad_norm": 1.
|
| 1447 |
"learning_rate": 2.0307529162248146e-05,
|
| 1448 |
-
"loss": 0.
|
| 1449 |
"step": 1680
|
| 1450 |
},
|
| 1451 |
{
|
| 1452 |
"epoch": 1.792152704135737,
|
| 1453 |
-
"grad_norm": 1.
|
| 1454 |
"learning_rate": 2.0130788264404385e-05,
|
| 1455 |
-
"loss": 0.
|
| 1456 |
"step": 1690
|
| 1457 |
},
|
| 1458 |
{
|
| 1459 |
"epoch": 1.8027571580063628,
|
| 1460 |
-
"grad_norm": 1.
|
| 1461 |
"learning_rate": 1.9954047366560624e-05,
|
| 1462 |
-
"loss": 0.
|
| 1463 |
"step": 1700
|
| 1464 |
},
|
| 1465 |
{
|
| 1466 |
"epoch": 1.8027571580063628,
|
| 1467 |
-
"eval_loss": 0.
|
| 1468 |
-
"eval_runtime": 11.
|
| 1469 |
-
"eval_samples_per_second": 40.
|
| 1470 |
-
"eval_steps_per_second": 2.
|
| 1471 |
"step": 1700
|
| 1472 |
},
|
| 1473 |
{
|
| 1474 |
"epoch": 1.8133616118769882,
|
| 1475 |
-
"grad_norm": 1.
|
| 1476 |
"learning_rate": 1.977730646871686e-05,
|
| 1477 |
-
"loss": 0.
|
| 1478 |
"step": 1710
|
| 1479 |
},
|
| 1480 |
{
|
| 1481 |
"epoch": 1.823966065747614,
|
| 1482 |
-
"grad_norm": 1.
|
| 1483 |
"learning_rate": 1.96005655708731e-05,
|
| 1484 |
-
"loss": 0.
|
| 1485 |
"step": 1720
|
| 1486 |
},
|
| 1487 |
{
|
| 1488 |
"epoch": 1.8345705196182398,
|
| 1489 |
-
"grad_norm": 1.
|
| 1490 |
"learning_rate": 1.9423824673029338e-05,
|
| 1491 |
-
"loss": 0.
|
| 1492 |
"step": 1730
|
| 1493 |
},
|
| 1494 |
{
|
| 1495 |
"epoch": 1.8451749734888652,
|
| 1496 |
-
"grad_norm": 1.
|
| 1497 |
"learning_rate": 1.9247083775185577e-05,
|
| 1498 |
-
"loss": 0.
|
| 1499 |
"step": 1740
|
| 1500 |
},
|
| 1501 |
{
|
| 1502 |
"epoch": 1.855779427359491,
|
| 1503 |
-
"grad_norm": 1.
|
| 1504 |
"learning_rate": 1.9070342877341817e-05,
|
| 1505 |
-
"loss": 0.
|
| 1506 |
"step": 1750
|
| 1507 |
},
|
| 1508 |
{
|
| 1509 |
"epoch": 1.855779427359491,
|
| 1510 |
-
"eval_loss": 0.
|
| 1511 |
-
"eval_runtime": 11.
|
| 1512 |
-
"eval_samples_per_second": 40.
|
| 1513 |
-
"eval_steps_per_second": 2.
|
| 1514 |
"step": 1750
|
| 1515 |
},
|
| 1516 |
{
|
| 1517 |
"epoch": 1.8663838812301168,
|
| 1518 |
-
"grad_norm": 1.
|
| 1519 |
"learning_rate": 1.8893601979498056e-05,
|
| 1520 |
-
"loss": 0.
|
| 1521 |
"step": 1760
|
| 1522 |
},
|
| 1523 |
{
|
| 1524 |
"epoch": 1.8769883351007424,
|
| 1525 |
-
"grad_norm": 1.
|
| 1526 |
"learning_rate": 1.8716861081654298e-05,
|
| 1527 |
-
"loss": 0.
|
| 1528 |
"step": 1770
|
| 1529 |
},
|
| 1530 |
{
|
| 1531 |
"epoch": 1.887592788971368,
|
| 1532 |
-
"grad_norm": 1.
|
| 1533 |
"learning_rate": 1.8540120183810537e-05,
|
| 1534 |
-
"loss": 0.
|
| 1535 |
"step": 1780
|
| 1536 |
},
|
| 1537 |
{
|
| 1538 |
"epoch": 1.8981972428419938,
|
| 1539 |
-
"grad_norm": 1.
|
| 1540 |
"learning_rate": 1.8363379285966773e-05,
|
| 1541 |
"loss": 0.2913,
|
| 1542 |
"step": 1790
|
| 1543 |
},
|
| 1544 |
{
|
| 1545 |
"epoch": 1.9088016967126193,
|
| 1546 |
-
"grad_norm": 1.
|
| 1547 |
"learning_rate": 1.8186638388123012e-05,
|
| 1548 |
"loss": 0.3066,
|
| 1549 |
"step": 1800
|
| 1550 |
},
|
| 1551 |
{
|
| 1552 |
"epoch": 1.9088016967126193,
|
| 1553 |
-
"eval_loss": 0.
|
| 1554 |
-
"eval_runtime": 11.
|
| 1555 |
-
"eval_samples_per_second": 40.
|
| 1556 |
"eval_steps_per_second": 2.537,
|
| 1557 |
"step": 1800
|
| 1558 |
},
|
| 1559 |
{
|
| 1560 |
"epoch": 1.919406150583245,
|
| 1561 |
-
"grad_norm": 1.
|
| 1562 |
"learning_rate": 1.800989749027925e-05,
|
| 1563 |
-
"loss": 0.
|
| 1564 |
"step": 1810
|
| 1565 |
},
|
| 1566 |
{
|
| 1567 |
"epoch": 1.9300106044538707,
|
| 1568 |
-
"grad_norm": 1.
|
| 1569 |
"learning_rate": 1.783315659243549e-05,
|
| 1570 |
-
"loss": 0.
|
| 1571 |
"step": 1820
|
| 1572 |
},
|
| 1573 |
{
|
| 1574 |
"epoch": 1.9406150583244963,
|
| 1575 |
-
"grad_norm": 1.
|
| 1576 |
"learning_rate": 1.765641569459173e-05,
|
| 1577 |
-
"loss": 0.
|
| 1578 |
"step": 1830
|
| 1579 |
},
|
| 1580 |
{
|
| 1581 |
"epoch": 1.951219512195122,
|
| 1582 |
-
"grad_norm": 1.
|
| 1583 |
"learning_rate": 1.747967479674797e-05,
|
| 1584 |
-
"loss": 0.
|
| 1585 |
"step": 1840
|
| 1586 |
},
|
| 1587 |
{
|
| 1588 |
"epoch": 1.9618239660657477,
|
| 1589 |
-
"grad_norm": 1.
|
| 1590 |
"learning_rate": 1.730293389890421e-05,
|
| 1591 |
-
"loss": 0.
|
| 1592 |
"step": 1850
|
| 1593 |
},
|
| 1594 |
{
|
| 1595 |
"epoch": 1.9618239660657477,
|
| 1596 |
-
"eval_loss": 0.
|
| 1597 |
-
"eval_runtime": 11.
|
| 1598 |
-
"eval_samples_per_second": 40.
|
| 1599 |
-
"eval_steps_per_second": 2.
|
| 1600 |
"step": 1850
|
| 1601 |
},
|
| 1602 |
{
|
| 1603 |
"epoch": 1.9724284199363733,
|
| 1604 |
-
"grad_norm": 1.
|
| 1605 |
"learning_rate": 1.7126193001060444e-05,
|
| 1606 |
"loss": 0.2911,
|
| 1607 |
"step": 1860
|
| 1608 |
},
|
| 1609 |
{
|
| 1610 |
"epoch": 1.9830328738069989,
|
| 1611 |
-
"grad_norm": 1.
|
| 1612 |
"learning_rate": 1.6949452103216683e-05,
|
| 1613 |
-
"loss": 0.
|
| 1614 |
"step": 1870
|
| 1615 |
},
|
| 1616 |
{
|
| 1617 |
"epoch": 1.9936373276776247,
|
| 1618 |
-
"grad_norm": 1.
|
| 1619 |
"learning_rate": 1.6772711205372923e-05,
|
| 1620 |
-
"loss": 0.
|
| 1621 |
"step": 1880
|
| 1622 |
},
|
| 1623 |
{
|
| 1624 |
"epoch": 2.00424178154825,
|
| 1625 |
-
"grad_norm": 1.
|
| 1626 |
"learning_rate": 1.6595970307529162e-05,
|
| 1627 |
-
"loss": 0.
|
| 1628 |
"step": 1890
|
| 1629 |
},
|
| 1630 |
{
|
| 1631 |
"epoch": 2.014846235418876,
|
| 1632 |
-
"grad_norm": 1.
|
| 1633 |
"learning_rate": 1.64192294096854e-05,
|
| 1634 |
-
"loss": 0.
|
| 1635 |
"step": 1900
|
| 1636 |
},
|
| 1637 |
{
|
| 1638 |
"epoch": 2.014846235418876,
|
| 1639 |
-
"eval_loss": 0.
|
| 1640 |
-
"eval_runtime": 11.
|
| 1641 |
-
"eval_samples_per_second": 40.
|
| 1642 |
-
"eval_steps_per_second": 2.
|
| 1643 |
"step": 1900
|
| 1644 |
},
|
| 1645 |
{
|
| 1646 |
"epoch": 2.0254506892895017,
|
| 1647 |
-
"grad_norm": 1.
|
| 1648 |
"learning_rate": 1.624248851184164e-05,
|
| 1649 |
"loss": 0.2482,
|
| 1650 |
"step": 1910
|
| 1651 |
},
|
| 1652 |
{
|
| 1653 |
"epoch": 2.0360551431601275,
|
| 1654 |
-
"grad_norm": 1.
|
| 1655 |
"learning_rate": 1.606574761399788e-05,
|
| 1656 |
-
"loss": 0.
|
| 1657 |
"step": 1920
|
| 1658 |
},
|
| 1659 |
{
|
| 1660 |
"epoch": 2.046659597030753,
|
| 1661 |
-
"grad_norm": 1.
|
| 1662 |
"learning_rate": 1.588900671615412e-05,
|
| 1663 |
-
"loss": 0.
|
| 1664 |
"step": 1930
|
| 1665 |
},
|
| 1666 |
{
|
| 1667 |
"epoch": 2.0572640509013786,
|
| 1668 |
-
"grad_norm": 1.
|
| 1669 |
"learning_rate": 1.5712265818310358e-05,
|
| 1670 |
-
"loss": 0.
|
| 1671 |
"step": 1940
|
| 1672 |
},
|
| 1673 |
{
|
| 1674 |
"epoch": 2.0678685047720045,
|
| 1675 |
-
"grad_norm": 1.
|
| 1676 |
"learning_rate": 1.5535524920466597e-05,
|
| 1677 |
-
"loss": 0.
|
| 1678 |
"step": 1950
|
| 1679 |
},
|
| 1680 |
{
|
| 1681 |
"epoch": 2.0678685047720045,
|
| 1682 |
-
"eval_loss": 0.
|
| 1683 |
-
"eval_runtime": 11.
|
| 1684 |
-
"eval_samples_per_second": 40.
|
| 1685 |
-
"eval_steps_per_second": 2.
|
| 1686 |
"step": 1950
|
| 1687 |
},
|
| 1688 |
{
|
| 1689 |
"epoch": 2.07847295864263,
|
| 1690 |
-
"grad_norm": 1.
|
| 1691 |
"learning_rate": 1.5358784022622836e-05,
|
| 1692 |
-
"loss": 0.
|
| 1693 |
"step": 1960
|
| 1694 |
},
|
| 1695 |
{
|
| 1696 |
"epoch": 2.0890774125132556,
|
| 1697 |
-
"grad_norm": 1.
|
| 1698 |
"learning_rate": 1.5182043124779075e-05,
|
| 1699 |
-
"loss": 0.
|
| 1700 |
"step": 1970
|
| 1701 |
},
|
| 1702 |
{
|
| 1703 |
"epoch": 2.0996818663838814,
|
| 1704 |
-
"grad_norm": 1.
|
| 1705 |
"learning_rate": 1.5005302226935314e-05,
|
| 1706 |
-
"loss": 0.
|
| 1707 |
"step": 1980
|
| 1708 |
},
|
| 1709 |
{
|
| 1710 |
"epoch": 2.110286320254507,
|
| 1711 |
-
"grad_norm": 1.
|
| 1712 |
"learning_rate": 1.4828561329091554e-05,
|
| 1713 |
-
"loss": 0.
|
| 1714 |
"step": 1990
|
| 1715 |
},
|
| 1716 |
{
|
| 1717 |
"epoch": 2.1208907741251326,
|
| 1718 |
-
"grad_norm": 1.
|
| 1719 |
"learning_rate": 1.4651820431247793e-05,
|
| 1720 |
-
"loss": 0.
|
| 1721 |
"step": 2000
|
| 1722 |
},
|
| 1723 |
{
|
| 1724 |
"epoch": 2.1208907741251326,
|
| 1725 |
-
"eval_loss": 0.
|
| 1726 |
-
"eval_runtime": 11.
|
| 1727 |
-
"eval_samples_per_second": 40.
|
| 1728 |
-
"eval_steps_per_second": 2.
|
| 1729 |
"step": 2000
|
| 1730 |
},
|
| 1731 |
{
|
| 1732 |
"epoch": 2.1314952279957584,
|
| 1733 |
-
"grad_norm": 1.
|
| 1734 |
"learning_rate": 1.4475079533404029e-05,
|
| 1735 |
-
"loss": 0.
|
| 1736 |
"step": 2010
|
| 1737 |
},
|
| 1738 |
{
|
| 1739 |
"epoch": 2.1420996818663838,
|
| 1740 |
-
"grad_norm": 1.
|
| 1741 |
"learning_rate": 1.4298338635560268e-05,
|
| 1742 |
-
"loss": 0.
|
| 1743 |
"step": 2020
|
| 1744 |
},
|
| 1745 |
{
|
| 1746 |
"epoch": 2.1527041357370096,
|
| 1747 |
-
"grad_norm": 1.
|
| 1748 |
"learning_rate": 1.4121597737716507e-05,
|
| 1749 |
-
"loss": 0.
|
| 1750 |
"step": 2030
|
| 1751 |
},
|
| 1752 |
{
|
| 1753 |
"epoch": 2.1633085896076354,
|
| 1754 |
-
"grad_norm": 1.
|
| 1755 |
"learning_rate": 1.3944856839872746e-05,
|
| 1756 |
-
"loss": 0.
|
| 1757 |
"step": 2040
|
| 1758 |
},
|
| 1759 |
{
|
| 1760 |
"epoch": 2.1739130434782608,
|
| 1761 |
-
"grad_norm": 1.
|
| 1762 |
"learning_rate": 1.3768115942028985e-05,
|
| 1763 |
-
"loss": 0.
|
| 1764 |
"step": 2050
|
| 1765 |
},
|
| 1766 |
{
|
| 1767 |
"epoch": 2.1739130434782608,
|
| 1768 |
-
"eval_loss": 0.
|
| 1769 |
-
"eval_runtime": 11.
|
| 1770 |
-
"eval_samples_per_second": 40.
|
| 1771 |
-
"eval_steps_per_second": 2.
|
| 1772 |
"step": 2050
|
| 1773 |
},
|
| 1774 |
{
|
| 1775 |
"epoch": 2.1845174973488866,
|
| 1776 |
-
"grad_norm": 1.
|
| 1777 |
"learning_rate": 1.3591375044185226e-05,
|
| 1778 |
-
"loss": 0.
|
| 1779 |
"step": 2060
|
| 1780 |
},
|
| 1781 |
{
|
| 1782 |
"epoch": 2.1951219512195124,
|
| 1783 |
-
"grad_norm": 1.
|
| 1784 |
"learning_rate": 1.3414634146341466e-05,
|
| 1785 |
-
"loss": 0.
|
| 1786 |
"step": 2070
|
| 1787 |
},
|
| 1788 |
{
|
| 1789 |
"epoch": 2.2057264050901377,
|
| 1790 |
-
"grad_norm": 1.
|
| 1791 |
"learning_rate": 1.3237893248497705e-05,
|
| 1792 |
-
"loss": 0.
|
| 1793 |
"step": 2080
|
| 1794 |
},
|
| 1795 |
{
|
| 1796 |
"epoch": 2.2163308589607635,
|
| 1797 |
-
"grad_norm": 1.
|
| 1798 |
"learning_rate": 1.306115235065394e-05,
|
| 1799 |
-
"loss": 0.
|
| 1800 |
"step": 2090
|
| 1801 |
},
|
| 1802 |
{
|
| 1803 |
"epoch": 2.2269353128313893,
|
| 1804 |
-
"grad_norm": 1.
|
| 1805 |
"learning_rate": 1.288441145281018e-05,
|
| 1806 |
-
"loss": 0.
|
| 1807 |
"step": 2100
|
| 1808 |
},
|
| 1809 |
{
|
| 1810 |
"epoch": 2.2269353128313893,
|
| 1811 |
-
"eval_loss": 0.
|
| 1812 |
-
"eval_runtime": 11.
|
| 1813 |
-
"eval_samples_per_second": 40.
|
| 1814 |
-
"eval_steps_per_second": 2.
|
| 1815 |
"step": 2100
|
| 1816 |
},
|
| 1817 |
{
|
| 1818 |
"epoch": 2.2375397667020147,
|
| 1819 |
-
"grad_norm": 1.
|
| 1820 |
"learning_rate": 1.2707670554966419e-05,
|
| 1821 |
-
"loss": 0.
|
| 1822 |
"step": 2110
|
| 1823 |
},
|
| 1824 |
{
|
| 1825 |
"epoch": 2.2481442205726405,
|
| 1826 |
-
"grad_norm": 1.
|
| 1827 |
"learning_rate": 1.2530929657122658e-05,
|
| 1828 |
-
"loss": 0.
|
| 1829 |
"step": 2120
|
| 1830 |
},
|
| 1831 |
{
|
| 1832 |
"epoch": 2.2587486744432663,
|
| 1833 |
-
"grad_norm": 1.
|
| 1834 |
"learning_rate": 1.2354188759278897e-05,
|
| 1835 |
-
"loss": 0.
|
| 1836 |
"step": 2130
|
| 1837 |
},
|
| 1838 |
{
|
| 1839 |
"epoch": 2.2693531283138917,
|
| 1840 |
-
"grad_norm": 1.
|
| 1841 |
"learning_rate": 1.2177447861435136e-05,
|
| 1842 |
-
"loss": 0.
|
| 1843 |
"step": 2140
|
| 1844 |
},
|
| 1845 |
{
|
| 1846 |
"epoch": 2.2799575821845175,
|
| 1847 |
-
"grad_norm": 1.
|
| 1848 |
"learning_rate": 1.2000706963591376e-05,
|
| 1849 |
-
"loss": 0.
|
| 1850 |
"step": 2150
|
| 1851 |
},
|
| 1852 |
{
|
| 1853 |
"epoch": 2.2799575821845175,
|
| 1854 |
-
"eval_loss": 0.
|
| 1855 |
-
"eval_runtime": 11.
|
| 1856 |
-
"eval_samples_per_second": 40.
|
| 1857 |
-
"eval_steps_per_second": 2.
|
| 1858 |
"step": 2150
|
| 1859 |
},
|
| 1860 |
{
|
| 1861 |
"epoch": 2.2905620360551433,
|
| 1862 |
-
"grad_norm": 1.
|
| 1863 |
"learning_rate": 1.1823966065747615e-05,
|
| 1864 |
-
"loss": 0.
|
| 1865 |
"step": 2160
|
| 1866 |
},
|
| 1867 |
{
|
| 1868 |
"epoch": 2.3011664899257687,
|
| 1869 |
-
"grad_norm": 1.
|
| 1870 |
"learning_rate": 1.1647225167903854e-05,
|
| 1871 |
-
"loss": 0.
|
| 1872 |
"step": 2170
|
| 1873 |
},
|
| 1874 |
{
|
| 1875 |
"epoch": 2.3117709437963945,
|
| 1876 |
-
"grad_norm": 1.
|
| 1877 |
"learning_rate": 1.1470484270060093e-05,
|
| 1878 |
-
"loss": 0.
|
| 1879 |
"step": 2180
|
| 1880 |
},
|
| 1881 |
{
|
| 1882 |
"epoch": 2.3223753976670203,
|
| 1883 |
-
"grad_norm": 1.
|
| 1884 |
"learning_rate": 1.129374337221633e-05,
|
| 1885 |
-
"loss": 0.
|
| 1886 |
"step": 2190
|
| 1887 |
},
|
| 1888 |
{
|
| 1889 |
"epoch": 2.3329798515376456,
|
| 1890 |
-
"grad_norm": 1.
|
| 1891 |
"learning_rate": 1.111700247437257e-05,
|
| 1892 |
-
"loss": 0.
|
| 1893 |
"step": 2200
|
| 1894 |
},
|
| 1895 |
{
|
| 1896 |
"epoch": 2.3329798515376456,
|
| 1897 |
-
"eval_loss": 0.
|
| 1898 |
-
"eval_runtime": 11.
|
| 1899 |
-
"eval_samples_per_second": 40.
|
| 1900 |
-
"eval_steps_per_second": 2.
|
| 1901 |
"step": 2200
|
| 1902 |
},
|
| 1903 |
{
|
| 1904 |
"epoch": 2.3435843054082715,
|
| 1905 |
-
"grad_norm": 1.
|
| 1906 |
"learning_rate": 1.0940261576528809e-05,
|
| 1907 |
-
"loss": 0.
|
| 1908 |
"step": 2210
|
| 1909 |
},
|
| 1910 |
{
|
| 1911 |
"epoch": 2.3541887592788973,
|
| 1912 |
-
"grad_norm": 1.
|
| 1913 |
"learning_rate": 1.0763520678685048e-05,
|
| 1914 |
-
"loss": 0.
|
| 1915 |
"step": 2220
|
| 1916 |
},
|
| 1917 |
{
|
| 1918 |
"epoch": 2.3647932131495226,
|
| 1919 |
-
"grad_norm": 1.
|
| 1920 |
"learning_rate": 1.0586779780841287e-05,
|
| 1921 |
-
"loss": 0.
|
| 1922 |
"step": 2230
|
| 1923 |
},
|
| 1924 |
{
|
| 1925 |
"epoch": 2.3753976670201484,
|
| 1926 |
-
"grad_norm": 1.
|
| 1927 |
"learning_rate": 1.0410038882997527e-05,
|
| 1928 |
-
"loss": 0.
|
| 1929 |
"step": 2240
|
| 1930 |
},
|
| 1931 |
{
|
| 1932 |
"epoch": 2.3860021208907742,
|
| 1933 |
-
"grad_norm": 1.
|
| 1934 |
"learning_rate": 1.0233297985153766e-05,
|
| 1935 |
-
"loss": 0.
|
| 1936 |
"step": 2250
|
| 1937 |
},
|
| 1938 |
{
|
| 1939 |
"epoch": 2.3860021208907742,
|
| 1940 |
-
"eval_loss": 0.
|
| 1941 |
-
"eval_runtime": 11.
|
| 1942 |
-
"eval_samples_per_second": 40.
|
| 1943 |
-
"eval_steps_per_second": 2.
|
| 1944 |
"step": 2250
|
| 1945 |
},
|
| 1946 |
{
|
| 1947 |
"epoch": 2.3966065747613996,
|
| 1948 |
-
"grad_norm": 1.
|
| 1949 |
"learning_rate": 1.0056557087310003e-05,
|
| 1950 |
"loss": 0.2502,
|
| 1951 |
"step": 2260
|
| 1952 |
},
|
| 1953 |
{
|
| 1954 |
"epoch": 2.4072110286320254,
|
| 1955 |
-
"grad_norm": 1.
|
| 1956 |
"learning_rate": 9.879816189466243e-06,
|
| 1957 |
-
"loss": 0.
|
| 1958 |
"step": 2270
|
| 1959 |
},
|
| 1960 |
{
|
| 1961 |
"epoch": 2.417815482502651,
|
| 1962 |
-
"grad_norm": 1.
|
| 1963 |
"learning_rate": 9.703075291622482e-06,
|
| 1964 |
-
"loss": 0.
|
| 1965 |
"step": 2280
|
| 1966 |
},
|
| 1967 |
{
|
| 1968 |
"epoch": 2.4284199363732766,
|
| 1969 |
-
"grad_norm": 1.
|
| 1970 |
"learning_rate": 9.526334393778721e-06,
|
| 1971 |
-
"loss": 0.
|
| 1972 |
"step": 2290
|
| 1973 |
},
|
| 1974 |
{
|
| 1975 |
"epoch": 2.4390243902439024,
|
| 1976 |
-
"grad_norm": 1.
|
| 1977 |
"learning_rate": 9.34959349593496e-06,
|
| 1978 |
-
"loss": 0.
|
| 1979 |
"step": 2300
|
| 1980 |
},
|
| 1981 |
{
|
| 1982 |
"epoch": 2.4390243902439024,
|
| 1983 |
-
"eval_loss": 0.
|
| 1984 |
-
"eval_runtime": 11.
|
| 1985 |
-
"eval_samples_per_second": 40.
|
| 1986 |
-
"eval_steps_per_second": 2.
|
| 1987 |
"step": 2300
|
| 1988 |
},
|
| 1989 |
{
|
| 1990 |
"epoch": 2.449628844114528,
|
| 1991 |
-
"grad_norm": 1.
|
| 1992 |
"learning_rate": 9.1728525980912e-06,
|
| 1993 |
-
"loss": 0.
|
| 1994 |
"step": 2310
|
| 1995 |
},
|
| 1996 |
{
|
| 1997 |
"epoch": 2.4602332979851536,
|
| 1998 |
-
"grad_norm": 1.
|
| 1999 |
"learning_rate": 8.996111700247438e-06,
|
| 2000 |
-
"loss": 0.
|
| 2001 |
"step": 2320
|
| 2002 |
},
|
| 2003 |
{
|
| 2004 |
"epoch": 2.4708377518557794,
|
| 2005 |
-
"grad_norm": 1.
|
| 2006 |
"learning_rate": 8.819370802403678e-06,
|
| 2007 |
-
"loss": 0.
|
| 2008 |
"step": 2330
|
| 2009 |
},
|
| 2010 |
{
|
| 2011 |
"epoch": 2.481442205726405,
|
| 2012 |
-
"grad_norm": 1.
|
| 2013 |
"learning_rate": 8.642629904559915e-06,
|
| 2014 |
-
"loss": 0.
|
| 2015 |
"step": 2340
|
| 2016 |
},
|
| 2017 |
{
|
| 2018 |
"epoch": 2.4920466595970305,
|
| 2019 |
-
"grad_norm": 1.
|
| 2020 |
"learning_rate": 8.465889006716154e-06,
|
| 2021 |
-
"loss": 0.
|
| 2022 |
"step": 2350
|
| 2023 |
},
|
| 2024 |
{
|
| 2025 |
"epoch": 2.4920466595970305,
|
| 2026 |
-
"eval_loss": 0.
|
| 2027 |
-
"eval_runtime": 11.
|
| 2028 |
-
"eval_samples_per_second": 40.
|
| 2029 |
-
"eval_steps_per_second": 2.
|
| 2030 |
"step": 2350
|
| 2031 |
},
|
| 2032 |
{
|
| 2033 |
"epoch": 2.5026511134676563,
|
| 2034 |
-
"grad_norm": 1.
|
| 2035 |
"learning_rate": 8.289148108872394e-06,
|
| 2036 |
-
"loss": 0.
|
| 2037 |
"step": 2360
|
| 2038 |
},
|
| 2039 |
{
|
| 2040 |
"epoch": 2.513255567338282,
|
| 2041 |
-
"grad_norm": 1.
|
| 2042 |
"learning_rate": 8.112407211028633e-06,
|
| 2043 |
-
"loss": 0.
|
| 2044 |
"step": 2370
|
| 2045 |
},
|
| 2046 |
{
|
| 2047 |
"epoch": 2.5238600212089075,
|
| 2048 |
-
"grad_norm": 1.
|
| 2049 |
"learning_rate": 7.93566631318487e-06,
|
| 2050 |
-
"loss": 0.
|
| 2051 |
"step": 2380
|
| 2052 |
},
|
| 2053 |
{
|
| 2054 |
"epoch": 2.5344644750795333,
|
| 2055 |
-
"grad_norm": 1.
|
| 2056 |
"learning_rate": 7.758925415341111e-06,
|
| 2057 |
-
"loss": 0.
|
| 2058 |
"step": 2390
|
| 2059 |
},
|
| 2060 |
{
|
| 2061 |
"epoch": 2.545068928950159,
|
| 2062 |
-
"grad_norm": 1.
|
| 2063 |
"learning_rate": 7.5821845174973494e-06,
|
| 2064 |
-
"loss": 0.
|
| 2065 |
"step": 2400
|
| 2066 |
},
|
| 2067 |
{
|
| 2068 |
"epoch": 2.545068928950159,
|
| 2069 |
-
"eval_loss": 0.
|
| 2070 |
-
"eval_runtime": 11.
|
| 2071 |
-
"eval_samples_per_second": 40.
|
| 2072 |
-
"eval_steps_per_second": 2.
|
| 2073 |
"step": 2400
|
| 2074 |
},
|
| 2075 |
{
|
| 2076 |
"epoch": 2.5556733828207845,
|
| 2077 |
-
"grad_norm": 1.
|
| 2078 |
"learning_rate": 7.405443619653588e-06,
|
| 2079 |
-
"loss": 0.
|
| 2080 |
"step": 2410
|
| 2081 |
},
|
| 2082 |
{
|
| 2083 |
"epoch": 2.5662778366914103,
|
| 2084 |
-
"grad_norm": 1.
|
| 2085 |
"learning_rate": 7.228702721809827e-06,
|
| 2086 |
-
"loss": 0.
|
| 2087 |
"step": 2420
|
| 2088 |
},
|
| 2089 |
{
|
| 2090 |
"epoch": 2.576882290562036,
|
| 2091 |
-
"grad_norm": 1.
|
| 2092 |
"learning_rate": 7.051961823966066e-06,
|
| 2093 |
-
"loss": 0.
|
| 2094 |
"step": 2430
|
| 2095 |
},
|
| 2096 |
{
|
| 2097 |
"epoch": 2.5874867444326615,
|
| 2098 |
-
"grad_norm": 1.
|
| 2099 |
"learning_rate": 6.875220926122305e-06,
|
| 2100 |
-
"loss": 0.
|
| 2101 |
"step": 2440
|
| 2102 |
},
|
| 2103 |
{
|
| 2104 |
"epoch": 2.5980911983032873,
|
| 2105 |
-
"grad_norm": 1.
|
| 2106 |
"learning_rate": 6.698480028278544e-06,
|
| 2107 |
-
"loss": 0.
|
| 2108 |
"step": 2450
|
| 2109 |
},
|
| 2110 |
{
|
| 2111 |
"epoch": 2.5980911983032873,
|
| 2112 |
-
"eval_loss": 0.
|
| 2113 |
-
"eval_runtime": 11.
|
| 2114 |
-
"eval_samples_per_second": 40.
|
| 2115 |
-
"eval_steps_per_second": 2.
|
| 2116 |
"step": 2450
|
| 2117 |
},
|
| 2118 |
{
|
| 2119 |
"epoch": 2.608695652173913,
|
| 2120 |
-
"grad_norm": 1.
|
| 2121 |
"learning_rate": 6.521739130434783e-06,
|
| 2122 |
-
"loss": 0.
|
| 2123 |
"step": 2460
|
| 2124 |
},
|
| 2125 |
{
|
| 2126 |
"epoch": 2.6193001060445384,
|
| 2127 |
-
"grad_norm": 1.
|
| 2128 |
"learning_rate": 6.344998232591022e-06,
|
| 2129 |
-
"loss": 0.
|
| 2130 |
"step": 2470
|
| 2131 |
},
|
| 2132 |
{
|
| 2133 |
"epoch": 2.6299045599151643,
|
| 2134 |
-
"grad_norm": 1.
|
| 2135 |
"learning_rate": 6.16825733474726e-06,
|
| 2136 |
-
"loss": 0.
|
| 2137 |
"step": 2480
|
| 2138 |
},
|
| 2139 |
{
|
| 2140 |
"epoch": 2.64050901378579,
|
| 2141 |
-
"grad_norm": 1.
|
| 2142 |
"learning_rate": 5.9915164369035e-06,
|
| 2143 |
-
"loss": 0.
|
| 2144 |
"step": 2490
|
| 2145 |
},
|
| 2146 |
{
|
| 2147 |
"epoch": 2.6511134676564154,
|
| 2148 |
-
"grad_norm": 1.
|
| 2149 |
"learning_rate": 5.814775539059739e-06,
|
| 2150 |
-
"loss": 0.
|
| 2151 |
"step": 2500
|
| 2152 |
},
|
| 2153 |
{
|
| 2154 |
"epoch": 2.6511134676564154,
|
| 2155 |
-
"eval_loss": 0.
|
| 2156 |
-
"eval_runtime": 11.
|
| 2157 |
-
"eval_samples_per_second": 40.
|
| 2158 |
-
"eval_steps_per_second": 2.
|
| 2159 |
"step": 2500
|
| 2160 |
},
|
| 2161 |
{
|
| 2162 |
"epoch": 2.6617179215270412,
|
| 2163 |
-
"grad_norm": 1.
|
| 2164 |
"learning_rate": 5.638034641215978e-06,
|
| 2165 |
-
"loss": 0.
|
| 2166 |
"step": 2510
|
| 2167 |
},
|
| 2168 |
{
|
| 2169 |
"epoch": 2.672322375397667,
|
| 2170 |
-
"grad_norm": 1.
|
| 2171 |
"learning_rate": 5.461293743372216e-06,
|
| 2172 |
-
"loss": 0.
|
| 2173 |
"step": 2520
|
| 2174 |
},
|
| 2175 |
{
|
| 2176 |
"epoch": 2.682926829268293,
|
| 2177 |
-
"grad_norm": 1.
|
| 2178 |
"learning_rate": 5.2845528455284555e-06,
|
| 2179 |
-
"loss": 0.
|
| 2180 |
"step": 2530
|
| 2181 |
},
|
| 2182 |
{
|
| 2183 |
"epoch": 2.693531283138918,
|
| 2184 |
-
"grad_norm":
|
| 2185 |
"learning_rate": 5.107811947684695e-06,
|
| 2186 |
-
"loss": 0.
|
| 2187 |
"step": 2540
|
| 2188 |
},
|
| 2189 |
{
|
| 2190 |
"epoch": 2.704135737009544,
|
| 2191 |
-
"grad_norm": 1.
|
| 2192 |
"learning_rate": 4.931071049840934e-06,
|
| 2193 |
-
"loss": 0.
|
| 2194 |
"step": 2550
|
| 2195 |
},
|
| 2196 |
{
|
| 2197 |
"epoch": 2.704135737009544,
|
| 2198 |
-
"eval_loss": 0.
|
| 2199 |
-
"eval_runtime": 11.
|
| 2200 |
-
"eval_samples_per_second": 40.
|
| 2201 |
-
"eval_steps_per_second": 2.
|
| 2202 |
"step": 2550
|
| 2203 |
},
|
| 2204 |
{
|
| 2205 |
"epoch": 2.71474019088017,
|
| 2206 |
-
"grad_norm": 1.
|
| 2207 |
"learning_rate": 4.754330151997172e-06,
|
| 2208 |
-
"loss": 0.
|
| 2209 |
"step": 2560
|
| 2210 |
},
|
| 2211 |
{
|
| 2212 |
"epoch": 2.725344644750795,
|
| 2213 |
-
"grad_norm": 1.
|
| 2214 |
"learning_rate": 4.577589254153411e-06,
|
| 2215 |
-
"loss": 0.
|
| 2216 |
"step": 2570
|
| 2217 |
},
|
| 2218 |
{
|
| 2219 |
"epoch": 2.735949098621421,
|
| 2220 |
-
"grad_norm": 1.
|
| 2221 |
"learning_rate": 4.400848356309651e-06,
|
| 2222 |
-
"loss": 0.
|
| 2223 |
"step": 2580
|
| 2224 |
},
|
| 2225 |
{
|
| 2226 |
"epoch": 2.746553552492047,
|
| 2227 |
-
"grad_norm": 1.
|
| 2228 |
"learning_rate": 4.224107458465889e-06,
|
| 2229 |
-
"loss": 0.
|
| 2230 |
"step": 2590
|
| 2231 |
},
|
| 2232 |
{
|
| 2233 |
"epoch": 2.757158006362672,
|
| 2234 |
-
"grad_norm": 1.
|
| 2235 |
"learning_rate": 4.047366560622128e-06,
|
| 2236 |
-
"loss": 0.
|
| 2237 |
"step": 2600
|
| 2238 |
},
|
| 2239 |
{
|
| 2240 |
"epoch": 2.757158006362672,
|
| 2241 |
-
"eval_loss": 0.
|
| 2242 |
-
"eval_runtime": 11.
|
| 2243 |
-
"eval_samples_per_second": 40.
|
| 2244 |
-
"eval_steps_per_second": 2.
|
| 2245 |
"step": 2600
|
| 2246 |
},
|
| 2247 |
{
|
| 2248 |
"epoch": 2.767762460233298,
|
| 2249 |
-
"grad_norm": 1.
|
| 2250 |
"learning_rate": 3.8706256627783665e-06,
|
| 2251 |
-
"loss": 0.
|
| 2252 |
"step": 2610
|
| 2253 |
},
|
| 2254 |
{
|
| 2255 |
"epoch": 2.778366914103924,
|
| 2256 |
-
"grad_norm": 1.
|
| 2257 |
"learning_rate": 3.693884764934606e-06,
|
| 2258 |
-
"loss": 0.
|
| 2259 |
"step": 2620
|
| 2260 |
},
|
| 2261 |
{
|
| 2262 |
"epoch": 2.7889713679745496,
|
| 2263 |
-
"grad_norm": 1.
|
| 2264 |
"learning_rate": 3.517143867090845e-06,
|
| 2265 |
-
"loss": 0.
|
| 2266 |
"step": 2630
|
| 2267 |
},
|
| 2268 |
{
|
| 2269 |
"epoch": 2.799575821845175,
|
| 2270 |
-
"grad_norm": 1.
|
| 2271 |
"learning_rate": 3.340402969247084e-06,
|
| 2272 |
-
"loss": 0.
|
| 2273 |
"step": 2640
|
| 2274 |
},
|
| 2275 |
{
|
| 2276 |
"epoch": 2.8101802757158008,
|
| 2277 |
-
"grad_norm": 1.
|
| 2278 |
"learning_rate": 3.163662071403323e-06,
|
| 2279 |
-
"loss": 0.
|
| 2280 |
"step": 2650
|
| 2281 |
},
|
| 2282 |
{
|
| 2283 |
"epoch": 2.8101802757158008,
|
| 2284 |
-
"eval_loss": 0.
|
| 2285 |
-
"eval_runtime": 11.
|
| 2286 |
-
"eval_samples_per_second": 40.
|
| 2287 |
-
"eval_steps_per_second": 2.
|
| 2288 |
"step": 2650
|
| 2289 |
},
|
| 2290 |
{
|
| 2291 |
"epoch": 2.8207847295864266,
|
| 2292 |
-
"grad_norm": 1.
|
| 2293 |
"learning_rate": 2.9869211735595616e-06,
|
| 2294 |
-
"loss": 0.
|
| 2295 |
"step": 2660
|
| 2296 |
},
|
| 2297 |
{
|
| 2298 |
"epoch": 2.831389183457052,
|
| 2299 |
-
"grad_norm": 1.
|
| 2300 |
"learning_rate": 2.8101802757158008e-06,
|
| 2301 |
-
"loss": 0.
|
| 2302 |
"step": 2670
|
| 2303 |
},
|
| 2304 |
{
|
| 2305 |
"epoch": 2.8419936373276777,
|
| 2306 |
-
"grad_norm": 1.
|
| 2307 |
"learning_rate": 2.6334393778720395e-06,
|
| 2308 |
-
"loss": 0.
|
| 2309 |
"step": 2680
|
| 2310 |
},
|
| 2311 |
{
|
| 2312 |
"epoch": 2.8525980911983035,
|
| 2313 |
-
"grad_norm": 1.
|
| 2314 |
"learning_rate": 2.4566984800282787e-06,
|
| 2315 |
-
"loss": 0.
|
| 2316 |
"step": 2690
|
| 2317 |
},
|
| 2318 |
{
|
| 2319 |
"epoch": 2.863202545068929,
|
| 2320 |
-
"grad_norm": 1.
|
| 2321 |
"learning_rate": 2.2799575821845175e-06,
|
| 2322 |
-
"loss": 0.
|
| 2323 |
"step": 2700
|
| 2324 |
},
|
| 2325 |
{
|
| 2326 |
"epoch": 2.863202545068929,
|
| 2327 |
-
"eval_loss": 0.
|
| 2328 |
-
"eval_runtime": 11.
|
| 2329 |
-
"eval_samples_per_second": 40.
|
| 2330 |
-
"eval_steps_per_second": 2.
|
| 2331 |
"step": 2700
|
| 2332 |
},
|
| 2333 |
{
|
| 2334 |
"epoch": 2.8738069989395547,
|
| 2335 |
-
"grad_norm": 1.
|
| 2336 |
"learning_rate": 2.1032166843407567e-06,
|
| 2337 |
-
"loss": 0.
|
| 2338 |
"step": 2710
|
| 2339 |
},
|
| 2340 |
{
|
| 2341 |
"epoch": 2.8844114528101805,
|
| 2342 |
-
"grad_norm": 1.
|
| 2343 |
"learning_rate": 1.9264757864969955e-06,
|
| 2344 |
-
"loss": 0.
|
| 2345 |
"step": 2720
|
| 2346 |
},
|
| 2347 |
{
|
| 2348 |
"epoch": 2.895015906680806,
|
| 2349 |
-
"grad_norm": 1.
|
| 2350 |
"learning_rate": 1.7497348886532344e-06,
|
| 2351 |
-
"loss": 0.
|
| 2352 |
"step": 2730
|
| 2353 |
},
|
| 2354 |
{
|
| 2355 |
"epoch": 2.9056203605514317,
|
| 2356 |
-
"grad_norm": 1.
|
| 2357 |
"learning_rate": 1.5729939908094734e-06,
|
| 2358 |
-
"loss": 0.
|
| 2359 |
"step": 2740
|
| 2360 |
},
|
| 2361 |
{
|
| 2362 |
"epoch": 2.9162248144220575,
|
| 2363 |
-
"grad_norm": 1.
|
| 2364 |
"learning_rate": 1.3962530929657124e-06,
|
| 2365 |
-
"loss": 0.
|
| 2366 |
"step": 2750
|
| 2367 |
},
|
| 2368 |
{
|
| 2369 |
"epoch": 2.9162248144220575,
|
| 2370 |
-
"eval_loss": 0.
|
| 2371 |
-
"eval_runtime": 11.
|
| 2372 |
-
"eval_samples_per_second": 40.
|
| 2373 |
-
"eval_steps_per_second": 2.
|
| 2374 |
"step": 2750
|
| 2375 |
},
|
| 2376 |
{
|
| 2377 |
"epoch": 2.926829268292683,
|
| 2378 |
-
"grad_norm": 1.
|
| 2379 |
"learning_rate": 1.2195121951219514e-06,
|
| 2380 |
-
"loss": 0.
|
| 2381 |
"step": 2760
|
| 2382 |
},
|
| 2383 |
{
|
| 2384 |
"epoch": 2.9374337221633087,
|
| 2385 |
-
"grad_norm": 1.
|
| 2386 |
"learning_rate": 1.0427712972781903e-06,
|
| 2387 |
-
"loss": 0.
|
| 2388 |
"step": 2770
|
| 2389 |
},
|
| 2390 |
{
|
| 2391 |
"epoch": 2.9480381760339345,
|
| 2392 |
-
"grad_norm": 1.
|
| 2393 |
"learning_rate": 8.660303994344292e-07,
|
| 2394 |
-
"loss": 0.
|
| 2395 |
"step": 2780
|
| 2396 |
},
|
| 2397 |
{
|
| 2398 |
"epoch": 2.95864262990456,
|
| 2399 |
-
"grad_norm": 1.
|
| 2400 |
"learning_rate": 6.892895015906681e-07,
|
| 2401 |
-
"loss": 0.
|
| 2402 |
"step": 2790
|
| 2403 |
},
|
| 2404 |
{
|
| 2405 |
"epoch": 2.9692470837751856,
|
| 2406 |
-
"grad_norm": 1.
|
| 2407 |
"learning_rate": 5.125486037469071e-07,
|
| 2408 |
-
"loss": 0.
|
| 2409 |
"step": 2800
|
| 2410 |
},
|
| 2411 |
{
|
| 2412 |
"epoch": 2.9692470837751856,
|
| 2413 |
-
"eval_loss": 0.
|
| 2414 |
-
"eval_runtime": 11.
|
| 2415 |
-
"eval_samples_per_second": 40.
|
| 2416 |
-
"eval_steps_per_second": 2.
|
| 2417 |
"step": 2800
|
| 2418 |
},
|
| 2419 |
{
|
| 2420 |
"epoch": 2.9798515376458115,
|
| 2421 |
-
"grad_norm": 1.
|
| 2422 |
"learning_rate": 3.35807705903146e-07,
|
| 2423 |
-
"loss": 0.
|
| 2424 |
"step": 2810
|
| 2425 |
},
|
| 2426 |
{
|
| 2427 |
"epoch": 2.990455991516437,
|
| 2428 |
-
"grad_norm": 1.
|
| 2429 |
"learning_rate": 1.5906680805938495e-07,
|
| 2430 |
-
"loss": 0.
|
| 2431 |
"step": 2820
|
| 2432 |
}
|
| 2433 |
],
|
|
|
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 0.010604453870625663,
|
| 13 |
+
"grad_norm": 2.276311159133911,
|
| 14 |
"learning_rate": 4.982325910215624e-05,
|
| 15 |
+
"loss": 1.9038,
|
| 16 |
"step": 10
|
| 17 |
},
|
| 18 |
{
|
| 19 |
"epoch": 0.021208907741251327,
|
| 20 |
+
"grad_norm": 0.7678110003471375,
|
| 21 |
"learning_rate": 4.964651820431248e-05,
|
| 22 |
+
"loss": 0.997,
|
| 23 |
"step": 20
|
| 24 |
},
|
| 25 |
{
|
| 26 |
"epoch": 0.031813361611876985,
|
| 27 |
+
"grad_norm": 0.6726565361022949,
|
| 28 |
"learning_rate": 4.946977730646872e-05,
|
| 29 |
+
"loss": 0.8021,
|
| 30 |
"step": 30
|
| 31 |
},
|
| 32 |
{
|
| 33 |
"epoch": 0.042417815482502653,
|
| 34 |
+
"grad_norm": 0.7318501472473145,
|
| 35 |
"learning_rate": 4.929303640862496e-05,
|
| 36 |
+
"loss": 0.7122,
|
| 37 |
"step": 40
|
| 38 |
},
|
| 39 |
{
|
| 40 |
"epoch": 0.053022269353128315,
|
| 41 |
+
"grad_norm": 0.6708294749259949,
|
| 42 |
"learning_rate": 4.91162955107812e-05,
|
| 43 |
+
"loss": 0.6783,
|
| 44 |
"step": 50
|
| 45 |
},
|
| 46 |
{
|
| 47 |
"epoch": 0.053022269353128315,
|
| 48 |
+
"eval_loss": 0.8075584173202515,
|
| 49 |
+
"eval_runtime": 11.7244,
|
| 50 |
+
"eval_samples_per_second": 40.94,
|
| 51 |
+
"eval_steps_per_second": 2.559,
|
| 52 |
"step": 50
|
| 53 |
},
|
| 54 |
{
|
| 55 |
"epoch": 0.06362672322375397,
|
| 56 |
+
"grad_norm": 0.7024317979812622,
|
| 57 |
"learning_rate": 4.893955461293744e-05,
|
| 58 |
+
"loss": 0.6244,
|
| 59 |
"step": 60
|
| 60 |
},
|
| 61 |
{
|
| 62 |
"epoch": 0.07423117709437964,
|
| 63 |
+
"grad_norm": 0.6959078907966614,
|
| 64 |
"learning_rate": 4.876281371509368e-05,
|
| 65 |
+
"loss": 0.6117,
|
| 66 |
"step": 70
|
| 67 |
},
|
| 68 |
{
|
| 69 |
"epoch": 0.08483563096500531,
|
| 70 |
+
"grad_norm": 0.7824214696884155,
|
| 71 |
"learning_rate": 4.858607281724991e-05,
|
| 72 |
+
"loss": 0.5989,
|
| 73 |
"step": 80
|
| 74 |
},
|
| 75 |
{
|
| 76 |
"epoch": 0.09544008483563096,
|
| 77 |
+
"grad_norm": 0.7792642116546631,
|
| 78 |
"learning_rate": 4.8409331919406155e-05,
|
| 79 |
+
"loss": 0.6033,
|
| 80 |
"step": 90
|
| 81 |
},
|
| 82 |
{
|
| 83 |
"epoch": 0.10604453870625663,
|
| 84 |
+
"grad_norm": 0.7486705780029297,
|
| 85 |
"learning_rate": 4.823259102156239e-05,
|
| 86 |
+
"loss": 0.5904,
|
| 87 |
"step": 100
|
| 88 |
},
|
| 89 |
{
|
| 90 |
"epoch": 0.10604453870625663,
|
| 91 |
+
"eval_loss": 0.7230511903762817,
|
| 92 |
+
"eval_runtime": 11.7589,
|
| 93 |
+
"eval_samples_per_second": 40.82,
|
| 94 |
+
"eval_steps_per_second": 2.551,
|
| 95 |
"step": 100
|
| 96 |
},
|
| 97 |
{
|
| 98 |
"epoch": 0.11664899257688228,
|
| 99 |
+
"grad_norm": 0.8214134573936462,
|
| 100 |
"learning_rate": 4.8055850123718633e-05,
|
| 101 |
+
"loss": 0.5778,
|
| 102 |
"step": 110
|
| 103 |
},
|
| 104 |
{
|
| 105 |
"epoch": 0.12725344644750794,
|
| 106 |
+
"grad_norm": 0.7937195897102356,
|
| 107 |
"learning_rate": 4.7879109225874866e-05,
|
| 108 |
+
"loss": 0.5748,
|
| 109 |
"step": 120
|
| 110 |
},
|
| 111 |
{
|
| 112 |
"epoch": 0.1378579003181336,
|
| 113 |
+
"grad_norm": 0.7781085968017578,
|
| 114 |
"learning_rate": 4.770236832803111e-05,
|
| 115 |
+
"loss": 0.5469,
|
| 116 |
"step": 130
|
| 117 |
},
|
| 118 |
{
|
| 119 |
"epoch": 0.14846235418875928,
|
| 120 |
+
"grad_norm": 0.695203423500061,
|
| 121 |
"learning_rate": 4.7525627430187344e-05,
|
| 122 |
+
"loss": 0.5511,
|
| 123 |
"step": 140
|
| 124 |
},
|
| 125 |
{
|
| 126 |
"epoch": 0.15906680805938495,
|
| 127 |
+
"grad_norm": 0.7824985384941101,
|
| 128 |
"learning_rate": 4.734888653234359e-05,
|
| 129 |
+
"loss": 0.5258,
|
| 130 |
"step": 150
|
| 131 |
},
|
| 132 |
{
|
| 133 |
"epoch": 0.15906680805938495,
|
| 134 |
+
"eval_loss": 0.6867014765739441,
|
| 135 |
+
"eval_runtime": 11.7852,
|
| 136 |
+
"eval_samples_per_second": 40.729,
|
| 137 |
+
"eval_steps_per_second": 2.546,
|
| 138 |
"step": 150
|
| 139 |
},
|
| 140 |
{
|
| 141 |
"epoch": 0.16967126193001061,
|
| 142 |
+
"grad_norm": 0.7392640113830566,
|
| 143 |
"learning_rate": 4.717214563449982e-05,
|
| 144 |
+
"loss": 0.5714,
|
| 145 |
"step": 160
|
| 146 |
},
|
| 147 |
{
|
| 148 |
"epoch": 0.18027571580063625,
|
| 149 |
+
"grad_norm": 0.8316007852554321,
|
| 150 |
"learning_rate": 4.699540473665606e-05,
|
| 151 |
+
"loss": 0.4982,
|
| 152 |
"step": 170
|
| 153 |
},
|
| 154 |
{
|
| 155 |
"epoch": 0.19088016967126192,
|
| 156 |
+
"grad_norm": 0.8199877738952637,
|
| 157 |
"learning_rate": 4.681866383881231e-05,
|
| 158 |
+
"loss": 0.5092,
|
| 159 |
"step": 180
|
| 160 |
},
|
| 161 |
{
|
| 162 |
"epoch": 0.2014846235418876,
|
| 163 |
+
"grad_norm": 0.7089737057685852,
|
| 164 |
"learning_rate": 4.664192294096854e-05,
|
| 165 |
+
"loss": 0.4953,
|
| 166 |
"step": 190
|
| 167 |
},
|
| 168 |
{
|
| 169 |
"epoch": 0.21208907741251326,
|
| 170 |
+
"grad_norm": 0.7906930446624756,
|
| 171 |
"learning_rate": 4.6465182043124786e-05,
|
| 172 |
+
"loss": 0.4974,
|
| 173 |
"step": 200
|
| 174 |
},
|
| 175 |
{
|
| 176 |
"epoch": 0.21208907741251326,
|
| 177 |
+
"eval_loss": 0.669015645980835,
|
| 178 |
+
"eval_runtime": 11.8934,
|
| 179 |
+
"eval_samples_per_second": 40.358,
|
| 180 |
+
"eval_steps_per_second": 2.522,
|
| 181 |
"step": 200
|
| 182 |
},
|
| 183 |
{
|
| 184 |
"epoch": 0.22269353128313893,
|
| 185 |
+
"grad_norm": 0.9085277318954468,
|
| 186 |
"learning_rate": 4.628844114528102e-05,
|
| 187 |
+
"loss": 0.4991,
|
| 188 |
"step": 210
|
| 189 |
},
|
| 190 |
{
|
| 191 |
"epoch": 0.23329798515376457,
|
| 192 |
+
"grad_norm": 0.7775648832321167,
|
| 193 |
"learning_rate": 4.6111700247437265e-05,
|
| 194 |
+
"loss": 0.5024,
|
| 195 |
"step": 220
|
| 196 |
},
|
| 197 |
{
|
| 198 |
"epoch": 0.24390243902439024,
|
| 199 |
+
"grad_norm": 0.8324123620986938,
|
| 200 |
"learning_rate": 4.59349593495935e-05,
|
| 201 |
+
"loss": 0.5187,
|
| 202 |
"step": 230
|
| 203 |
},
|
| 204 |
{
|
| 205 |
"epoch": 0.2545068928950159,
|
| 206 |
+
"grad_norm": 0.8002191781997681,
|
| 207 |
"learning_rate": 4.5758218451749736e-05,
|
| 208 |
+
"loss": 0.4785,
|
| 209 |
"step": 240
|
| 210 |
},
|
| 211 |
{
|
| 212 |
"epoch": 0.2651113467656416,
|
| 213 |
+
"grad_norm": 0.8004704117774963,
|
| 214 |
"learning_rate": 4.5581477553905975e-05,
|
| 215 |
+
"loss": 0.5073,
|
| 216 |
"step": 250
|
| 217 |
},
|
| 218 |
{
|
| 219 |
"epoch": 0.2651113467656416,
|
| 220 |
+
"eval_loss": 0.6479213833808899,
|
| 221 |
+
"eval_runtime": 11.882,
|
| 222 |
+
"eval_samples_per_second": 40.397,
|
| 223 |
+
"eval_steps_per_second": 2.525,
|
| 224 |
"step": 250
|
| 225 |
},
|
| 226 |
{
|
| 227 |
"epoch": 0.2757158006362672,
|
| 228 |
+
"grad_norm": 0.893301248550415,
|
| 229 |
"learning_rate": 4.5404736656062215e-05,
|
| 230 |
"loss": 0.477,
|
| 231 |
"step": 260
|
| 232 |
},
|
| 233 |
{
|
| 234 |
"epoch": 0.2863202545068929,
|
| 235 |
+
"grad_norm": 0.8550834059715271,
|
| 236 |
"learning_rate": 4.5227995758218454e-05,
|
| 237 |
+
"loss": 0.4923,
|
| 238 |
"step": 270
|
| 239 |
},
|
| 240 |
{
|
| 241 |
"epoch": 0.29692470837751855,
|
| 242 |
+
"grad_norm": 0.8929152488708496,
|
| 243 |
"learning_rate": 4.505125486037469e-05,
|
| 244 |
+
"loss": 0.4624,
|
| 245 |
"step": 280
|
| 246 |
},
|
| 247 |
{
|
| 248 |
"epoch": 0.3075291622481442,
|
| 249 |
+
"grad_norm": 0.9584974050521851,
|
| 250 |
"learning_rate": 4.487451396253093e-05,
|
| 251 |
+
"loss": 0.4801,
|
| 252 |
"step": 290
|
| 253 |
},
|
| 254 |
{
|
| 255 |
"epoch": 0.3181336161187699,
|
| 256 |
+
"grad_norm": 0.7924031615257263,
|
| 257 |
"learning_rate": 4.469777306468717e-05,
|
| 258 |
+
"loss": 0.4942,
|
| 259 |
"step": 300
|
| 260 |
},
|
| 261 |
{
|
| 262 |
"epoch": 0.3181336161187699,
|
| 263 |
+
"eval_loss": 0.6371316313743591,
|
| 264 |
+
"eval_runtime": 11.8575,
|
| 265 |
+
"eval_samples_per_second": 40.481,
|
| 266 |
+
"eval_steps_per_second": 2.53,
|
| 267 |
"step": 300
|
| 268 |
},
|
| 269 |
{
|
| 270 |
"epoch": 0.32873806998939553,
|
| 271 |
+
"grad_norm": 0.9247742295265198,
|
| 272 |
"learning_rate": 4.452103216684341e-05,
|
| 273 |
+
"loss": 0.5234,
|
| 274 |
"step": 310
|
| 275 |
},
|
| 276 |
{
|
| 277 |
"epoch": 0.33934252386002123,
|
| 278 |
+
"grad_norm": 0.8617805242538452,
|
| 279 |
"learning_rate": 4.434429126899965e-05,
|
| 280 |
+
"loss": 0.4808,
|
| 281 |
"step": 320
|
| 282 |
},
|
| 283 |
{
|
| 284 |
"epoch": 0.34994697773064687,
|
| 285 |
+
"grad_norm": 0.8334285616874695,
|
| 286 |
"learning_rate": 4.416755037115589e-05,
|
| 287 |
+
"loss": 0.4758,
|
| 288 |
"step": 330
|
| 289 |
},
|
| 290 |
{
|
| 291 |
"epoch": 0.3605514316012725,
|
| 292 |
+
"grad_norm": 0.9079923629760742,
|
| 293 |
"learning_rate": 4.399080947331213e-05,
|
| 294 |
+
"loss": 0.463,
|
| 295 |
"step": 340
|
| 296 |
},
|
| 297 |
{
|
| 298 |
"epoch": 0.3711558854718982,
|
| 299 |
+
"grad_norm": 0.7632007002830505,
|
| 300 |
"learning_rate": 4.381406857546837e-05,
|
| 301 |
+
"loss": 0.4828,
|
| 302 |
"step": 350
|
| 303 |
},
|
| 304 |
{
|
| 305 |
"epoch": 0.3711558854718982,
|
| 306 |
+
"eval_loss": 0.6212183237075806,
|
| 307 |
+
"eval_runtime": 11.8497,
|
| 308 |
+
"eval_samples_per_second": 40.507,
|
| 309 |
+
"eval_steps_per_second": 2.532,
|
| 310 |
"step": 350
|
| 311 |
},
|
| 312 |
{
|
| 313 |
"epoch": 0.38176033934252385,
|
| 314 |
+
"grad_norm": 0.8430343270301819,
|
| 315 |
"learning_rate": 4.3637327677624606e-05,
|
| 316 |
+
"loss": 0.4711,
|
| 317 |
"step": 360
|
| 318 |
},
|
| 319 |
{
|
| 320 |
"epoch": 0.39236479321314954,
|
| 321 |
+
"grad_norm": 0.9495126605033875,
|
| 322 |
"learning_rate": 4.3460586779780846e-05,
|
| 323 |
"loss": 0.4528,
|
| 324 |
"step": 370
|
| 325 |
},
|
| 326 |
{
|
| 327 |
"epoch": 0.4029692470837752,
|
| 328 |
+
"grad_norm": 0.8903242945671082,
|
| 329 |
"learning_rate": 4.328384588193708e-05,
|
| 330 |
+
"loss": 0.468,
|
| 331 |
"step": 380
|
| 332 |
},
|
| 333 |
{
|
| 334 |
"epoch": 0.4135737009544008,
|
| 335 |
+
"grad_norm": 0.9306944608688354,
|
| 336 |
"learning_rate": 4.3107104984093324e-05,
|
| 337 |
+
"loss": 0.4299,
|
| 338 |
"step": 390
|
| 339 |
},
|
| 340 |
{
|
| 341 |
"epoch": 0.4241781548250265,
|
| 342 |
+
"grad_norm": 0.7949309349060059,
|
| 343 |
"learning_rate": 4.2930364086249556e-05,
|
| 344 |
+
"loss": 0.4589,
|
| 345 |
"step": 400
|
| 346 |
},
|
| 347 |
{
|
| 348 |
"epoch": 0.4241781548250265,
|
| 349 |
+
"eval_loss": 0.6148895621299744,
|
| 350 |
+
"eval_runtime": 11.8536,
|
| 351 |
+
"eval_samples_per_second": 40.494,
|
| 352 |
+
"eval_steps_per_second": 2.531,
|
| 353 |
"step": 400
|
| 354 |
},
|
| 355 |
{
|
| 356 |
"epoch": 0.43478260869565216,
|
| 357 |
+
"grad_norm": 0.8351686000823975,
|
| 358 |
"learning_rate": 4.27536231884058e-05,
|
| 359 |
+
"loss": 0.4836,
|
| 360 |
"step": 410
|
| 361 |
},
|
| 362 |
{
|
| 363 |
"epoch": 0.44538706256627786,
|
| 364 |
+
"grad_norm": 0.9184524416923523,
|
| 365 |
"learning_rate": 4.2576882290562035e-05,
|
| 366 |
+
"loss": 0.4686,
|
| 367 |
"step": 420
|
| 368 |
},
|
| 369 |
{
|
| 370 |
"epoch": 0.4559915164369035,
|
| 371 |
+
"grad_norm": 0.9610297679901123,
|
| 372 |
"learning_rate": 4.240014139271828e-05,
|
| 373 |
+
"loss": 0.4804,
|
| 374 |
"step": 430
|
| 375 |
},
|
| 376 |
{
|
| 377 |
"epoch": 0.46659597030752914,
|
| 378 |
+
"grad_norm": 0.8793377876281738,
|
| 379 |
"learning_rate": 4.222340049487451e-05,
|
| 380 |
+
"loss": 0.4571,
|
| 381 |
"step": 440
|
| 382 |
},
|
| 383 |
{
|
| 384 |
"epoch": 0.47720042417815484,
|
| 385 |
+
"grad_norm": 0.913858950138092,
|
| 386 |
"learning_rate": 4.204665959703076e-05,
|
| 387 |
+
"loss": 0.4391,
|
| 388 |
"step": 450
|
| 389 |
},
|
| 390 |
{
|
| 391 |
"epoch": 0.47720042417815484,
|
| 392 |
+
"eval_loss": 0.6096637845039368,
|
| 393 |
+
"eval_runtime": 11.8533,
|
| 394 |
+
"eval_samples_per_second": 40.495,
|
| 395 |
+
"eval_steps_per_second": 2.531,
|
| 396 |
"step": 450
|
| 397 |
},
|
| 398 |
{
|
| 399 |
"epoch": 0.4878048780487805,
|
| 400 |
+
"grad_norm": 0.9159062504768372,
|
| 401 |
"learning_rate": 4.186991869918699e-05,
|
| 402 |
"loss": 0.4294,
|
| 403 |
"step": 460
|
| 404 |
},
|
| 405 |
{
|
| 406 |
"epoch": 0.4984093319194062,
|
| 407 |
+
"grad_norm": 0.9346657395362854,
|
| 408 |
"learning_rate": 4.169317780134323e-05,
|
| 409 |
+
"loss": 0.433,
|
| 410 |
"step": 470
|
| 411 |
},
|
| 412 |
{
|
| 413 |
"epoch": 0.5090137857900318,
|
| 414 |
+
"grad_norm": 0.8480401635169983,
|
| 415 |
"learning_rate": 4.151643690349947e-05,
|
| 416 |
"loss": 0.4639,
|
| 417 |
"step": 480
|
| 418 |
},
|
| 419 |
{
|
| 420 |
"epoch": 0.5196182396606575,
|
| 421 |
+
"grad_norm": 0.9547140002250671,
|
| 422 |
"learning_rate": 4.133969600565571e-05,
|
| 423 |
"loss": 0.4173,
|
| 424 |
"step": 490
|
| 425 |
},
|
| 426 |
{
|
| 427 |
"epoch": 0.5302226935312832,
|
| 428 |
+
"grad_norm": 0.8660142421722412,
|
| 429 |
"learning_rate": 4.116295510781195e-05,
|
| 430 |
+
"loss": 0.4644,
|
| 431 |
"step": 500
|
| 432 |
},
|
| 433 |
{
|
| 434 |
"epoch": 0.5302226935312832,
|
| 435 |
+
"eval_loss": 0.6053425073623657,
|
| 436 |
+
"eval_runtime": 11.8341,
|
| 437 |
+
"eval_samples_per_second": 40.561,
|
| 438 |
+
"eval_steps_per_second": 2.535,
|
| 439 |
"step": 500
|
| 440 |
},
|
| 441 |
{
|
| 442 |
"epoch": 0.5408271474019088,
|
| 443 |
+
"grad_norm": 0.9299489855766296,
|
| 444 |
"learning_rate": 4.098621420996819e-05,
|
| 445 |
+
"loss": 0.4488,
|
| 446 |
"step": 510
|
| 447 |
},
|
| 448 |
{
|
| 449 |
"epoch": 0.5514316012725344,
|
| 450 |
+
"grad_norm": 0.9637112021446228,
|
| 451 |
"learning_rate": 4.080947331212443e-05,
|
| 452 |
+
"loss": 0.4197,
|
| 453 |
"step": 520
|
| 454 |
},
|
| 455 |
{
|
| 456 |
"epoch": 0.5620360551431601,
|
| 457 |
+
"grad_norm": 0.9725180864334106,
|
| 458 |
"learning_rate": 4.0632732414280666e-05,
|
| 459 |
+
"loss": 0.4308,
|
| 460 |
"step": 530
|
| 461 |
},
|
| 462 |
{
|
| 463 |
"epoch": 0.5726405090137858,
|
| 464 |
+
"grad_norm": 1.095697045326233,
|
| 465 |
"learning_rate": 4.0455991516436905e-05,
|
| 466 |
+
"loss": 0.4473,
|
| 467 |
"step": 540
|
| 468 |
},
|
| 469 |
{
|
| 470 |
"epoch": 0.5832449628844114,
|
| 471 |
+
"grad_norm": 0.8940134048461914,
|
| 472 |
"learning_rate": 4.0279250618593144e-05,
|
| 473 |
+
"loss": 0.441,
|
| 474 |
"step": 550
|
| 475 |
},
|
| 476 |
{
|
| 477 |
"epoch": 0.5832449628844114,
|
| 478 |
+
"eval_loss": 0.6002687215805054,
|
| 479 |
+
"eval_runtime": 11.8218,
|
| 480 |
+
"eval_samples_per_second": 40.603,
|
| 481 |
+
"eval_steps_per_second": 2.538,
|
| 482 |
"step": 550
|
| 483 |
},
|
| 484 |
{
|
| 485 |
"epoch": 0.5938494167550371,
|
| 486 |
+
"grad_norm": 1.051446795463562,
|
| 487 |
"learning_rate": 4.0102509720749383e-05,
|
| 488 |
+
"loss": 0.4531,
|
| 489 |
"step": 560
|
| 490 |
},
|
| 491 |
{
|
| 492 |
"epoch": 0.6044538706256628,
|
| 493 |
+
"grad_norm": 1.055331826210022,
|
| 494 |
"learning_rate": 3.992576882290562e-05,
|
| 495 |
+
"loss": 0.4405,
|
| 496 |
"step": 570
|
| 497 |
},
|
| 498 |
{
|
| 499 |
"epoch": 0.6150583244962884,
|
| 500 |
+
"grad_norm": 0.9812480211257935,
|
| 501 |
"learning_rate": 3.974902792506186e-05,
|
| 502 |
+
"loss": 0.4128,
|
| 503 |
"step": 580
|
| 504 |
},
|
| 505 |
{
|
| 506 |
"epoch": 0.6256627783669141,
|
| 507 |
+
"grad_norm": 0.9506167769432068,
|
| 508 |
"learning_rate": 3.95722870272181e-05,
|
| 509 |
+
"loss": 0.4077,
|
| 510 |
"step": 590
|
| 511 |
},
|
| 512 |
{
|
| 513 |
"epoch": 0.6362672322375398,
|
| 514 |
+
"grad_norm": 0.9744945764541626,
|
| 515 |
"learning_rate": 3.939554612937434e-05,
|
| 516 |
+
"loss": 0.4531,
|
| 517 |
"step": 600
|
| 518 |
},
|
| 519 |
{
|
| 520 |
"epoch": 0.6362672322375398,
|
| 521 |
+
"eval_loss": 0.5941649079322815,
|
| 522 |
+
"eval_runtime": 11.8037,
|
| 523 |
+
"eval_samples_per_second": 40.665,
|
| 524 |
+
"eval_steps_per_second": 2.542,
|
| 525 |
"step": 600
|
| 526 |
},
|
| 527 |
{
|
| 528 |
"epoch": 0.6468716861081655,
|
| 529 |
+
"grad_norm": 0.9825407862663269,
|
| 530 |
"learning_rate": 3.921880523153057e-05,
|
| 531 |
+
"loss": 0.4281,
|
| 532 |
"step": 610
|
| 533 |
},
|
| 534 |
{
|
| 535 |
"epoch": 0.6574761399787911,
|
| 536 |
+
"grad_norm": 0.9444342851638794,
|
| 537 |
"learning_rate": 3.904206433368682e-05,
|
| 538 |
+
"loss": 0.4069,
|
| 539 |
"step": 620
|
| 540 |
},
|
| 541 |
{
|
| 542 |
"epoch": 0.6680805938494168,
|
| 543 |
+
"grad_norm": 0.8893631100654602,
|
| 544 |
"learning_rate": 3.886532343584305e-05,
|
| 545 |
+
"loss": 0.4067,
|
| 546 |
"step": 630
|
| 547 |
},
|
| 548 |
{
|
| 549 |
"epoch": 0.6786850477200425,
|
| 550 |
+
"grad_norm": 0.9782839417457581,
|
| 551 |
"learning_rate": 3.86885825379993e-05,
|
| 552 |
+
"loss": 0.4237,
|
| 553 |
"step": 640
|
| 554 |
},
|
| 555 |
{
|
| 556 |
"epoch": 0.689289501590668,
|
| 557 |
+
"grad_norm": 0.9258303642272949,
|
| 558 |
"learning_rate": 3.851184164015553e-05,
|
| 559 |
+
"loss": 0.4181,
|
| 560 |
"step": 650
|
| 561 |
},
|
| 562 |
{
|
| 563 |
"epoch": 0.689289501590668,
|
| 564 |
+
"eval_loss": 0.5927689671516418,
|
| 565 |
+
"eval_runtime": 11.8222,
|
| 566 |
+
"eval_samples_per_second": 40.601,
|
| 567 |
+
"eval_steps_per_second": 2.538,
|
| 568 |
"step": 650
|
| 569 |
},
|
| 570 |
{
|
| 571 |
"epoch": 0.6998939554612937,
|
| 572 |
+
"grad_norm": 0.9336357116699219,
|
| 573 |
"learning_rate": 3.8335100742311775e-05,
|
| 574 |
"loss": 0.4264,
|
| 575 |
"step": 660
|
| 576 |
},
|
| 577 |
{
|
| 578 |
"epoch": 0.7104984093319194,
|
| 579 |
+
"grad_norm": 1.0914337635040283,
|
| 580 |
"learning_rate": 3.8158359844468015e-05,
|
| 581 |
+
"loss": 0.4163,
|
| 582 |
"step": 670
|
| 583 |
},
|
| 584 |
{
|
| 585 |
"epoch": 0.721102863202545,
|
| 586 |
+
"grad_norm": 0.9416537284851074,
|
| 587 |
"learning_rate": 3.7981618946624254e-05,
|
| 588 |
+
"loss": 0.4292,
|
| 589 |
"step": 680
|
| 590 |
},
|
| 591 |
{
|
| 592 |
"epoch": 0.7317073170731707,
|
| 593 |
+
"grad_norm": 1.0038481950759888,
|
| 594 |
"learning_rate": 3.780487804878049e-05,
|
| 595 |
+
"loss": 0.4532,
|
| 596 |
"step": 690
|
| 597 |
},
|
| 598 |
{
|
| 599 |
"epoch": 0.7423117709437964,
|
| 600 |
+
"grad_norm": 1.0638171434402466,
|
| 601 |
"learning_rate": 3.7628137150936725e-05,
|
| 602 |
+
"loss": 0.437,
|
| 603 |
"step": 700
|
| 604 |
},
|
| 605 |
{
|
| 606 |
"epoch": 0.7423117709437964,
|
| 607 |
+
"eval_loss": 0.5840710997581482,
|
| 608 |
+
"eval_runtime": 11.8245,
|
| 609 |
+
"eval_samples_per_second": 40.594,
|
| 610 |
+
"eval_steps_per_second": 2.537,
|
| 611 |
"step": 700
|
| 612 |
},
|
| 613 |
{
|
| 614 |
"epoch": 0.7529162248144221,
|
| 615 |
+
"grad_norm": 1.091558814048767,
|
| 616 |
"learning_rate": 3.745139625309297e-05,
|
| 617 |
+
"loss": 0.4171,
|
| 618 |
"step": 710
|
| 619 |
},
|
| 620 |
{
|
| 621 |
"epoch": 0.7635206786850477,
|
| 622 |
+
"grad_norm": 1.052101731300354,
|
| 623 |
"learning_rate": 3.7274655355249204e-05,
|
| 624 |
+
"loss": 0.425,
|
| 625 |
"step": 720
|
| 626 |
},
|
| 627 |
{
|
| 628 |
"epoch": 0.7741251325556734,
|
| 629 |
+
"grad_norm": 0.9969995021820068,
|
| 630 |
"learning_rate": 3.709791445740545e-05,
|
| 631 |
+
"loss": 0.4329,
|
| 632 |
"step": 730
|
| 633 |
},
|
| 634 |
{
|
| 635 |
"epoch": 0.7847295864262991,
|
| 636 |
+
"grad_norm": 1.0250300168991089,
|
| 637 |
"learning_rate": 3.692117355956168e-05,
|
| 638 |
+
"loss": 0.4221,
|
| 639 |
"step": 740
|
| 640 |
},
|
| 641 |
{
|
| 642 |
"epoch": 0.7953340402969247,
|
| 643 |
+
"grad_norm": 1.0140836238861084,
|
| 644 |
"learning_rate": 3.674443266171793e-05,
|
| 645 |
+
"loss": 0.4059,
|
| 646 |
"step": 750
|
| 647 |
},
|
| 648 |
{
|
| 649 |
"epoch": 0.7953340402969247,
|
| 650 |
+
"eval_loss": 0.5901935696601868,
|
| 651 |
+
"eval_runtime": 11.8492,
|
| 652 |
+
"eval_samples_per_second": 40.509,
|
| 653 |
+
"eval_steps_per_second": 2.532,
|
| 654 |
"step": 750
|
| 655 |
},
|
| 656 |
{
|
| 657 |
"epoch": 0.8059384941675504,
|
| 658 |
+
"grad_norm": 0.9665971994400024,
|
| 659 |
"learning_rate": 3.656769176387416e-05,
|
| 660 |
+
"loss": 0.3824,
|
| 661 |
"step": 760
|
| 662 |
},
|
| 663 |
{
|
| 664 |
"epoch": 0.8165429480381761,
|
| 665 |
+
"grad_norm": 0.9899901747703552,
|
| 666 |
"learning_rate": 3.63909508660304e-05,
|
| 667 |
+
"loss": 0.402,
|
| 668 |
"step": 770
|
| 669 |
},
|
| 670 |
{
|
| 671 |
"epoch": 0.8271474019088016,
|
| 672 |
+
"grad_norm": 0.9623307585716248,
|
| 673 |
"learning_rate": 3.621420996818664e-05,
|
| 674 |
+
"loss": 0.4078,
|
| 675 |
"step": 780
|
| 676 |
},
|
| 677 |
{
|
| 678 |
"epoch": 0.8377518557794273,
|
| 679 |
+
"grad_norm": 1.0048012733459473,
|
| 680 |
"learning_rate": 3.603746907034288e-05,
|
| 681 |
+
"loss": 0.4211,
|
| 682 |
"step": 790
|
| 683 |
},
|
| 684 |
{
|
| 685 |
"epoch": 0.848356309650053,
|
| 686 |
+
"grad_norm": 1.04786217212677,
|
| 687 |
"learning_rate": 3.586072817249912e-05,
|
| 688 |
"loss": 0.4224,
|
| 689 |
"step": 800
|
| 690 |
},
|
| 691 |
{
|
| 692 |
"epoch": 0.848356309650053,
|
| 693 |
+
"eval_loss": 0.5850113034248352,
|
| 694 |
+
"eval_runtime": 11.8518,
|
| 695 |
+
"eval_samples_per_second": 40.5,
|
| 696 |
+
"eval_steps_per_second": 2.531,
|
| 697 |
"step": 800
|
| 698 |
},
|
| 699 |
{
|
| 700 |
"epoch": 0.8589607635206787,
|
| 701 |
+
"grad_norm": 1.1098370552062988,
|
| 702 |
"learning_rate": 3.5683987274655356e-05,
|
| 703 |
+
"loss": 0.4033,
|
| 704 |
"step": 810
|
| 705 |
},
|
| 706 |
{
|
| 707 |
"epoch": 0.8695652173913043,
|
| 708 |
+
"grad_norm": 1.0828533172607422,
|
| 709 |
"learning_rate": 3.5507246376811596e-05,
|
| 710 |
+
"loss": 0.3976,
|
| 711 |
"step": 820
|
| 712 |
},
|
| 713 |
{
|
| 714 |
"epoch": 0.88016967126193,
|
| 715 |
+
"grad_norm": 1.0007745027542114,
|
| 716 |
"learning_rate": 3.5330505478967835e-05,
|
| 717 |
+
"loss": 0.4101,
|
| 718 |
"step": 830
|
| 719 |
},
|
| 720 |
{
|
| 721 |
"epoch": 0.8907741251325557,
|
| 722 |
+
"grad_norm": 1.0621625185012817,
|
| 723 |
"learning_rate": 3.5153764581124074e-05,
|
| 724 |
+
"loss": 0.4113,
|
| 725 |
"step": 840
|
| 726 |
},
|
| 727 |
{
|
| 728 |
"epoch": 0.9013785790031813,
|
| 729 |
+
"grad_norm": 1.0198171138763428,
|
| 730 |
"learning_rate": 3.497702368328031e-05,
|
| 731 |
+
"loss": 0.3957,
|
| 732 |
"step": 850
|
| 733 |
},
|
| 734 |
{
|
| 735 |
"epoch": 0.9013785790031813,
|
| 736 |
+
"eval_loss": 0.5811945199966431,
|
| 737 |
+
"eval_runtime": 11.8706,
|
| 738 |
+
"eval_samples_per_second": 40.436,
|
| 739 |
+
"eval_steps_per_second": 2.527,
|
| 740 |
"step": 850
|
| 741 |
},
|
| 742 |
{
|
| 743 |
"epoch": 0.911983032873807,
|
| 744 |
+
"grad_norm": 1.035551905632019,
|
| 745 |
"learning_rate": 3.480028278543655e-05,
|
| 746 |
+
"loss": 0.4047,
|
| 747 |
"step": 860
|
| 748 |
},
|
| 749 |
{
|
| 750 |
"epoch": 0.9225874867444327,
|
| 751 |
+
"grad_norm": 1.0746926069259644,
|
| 752 |
"learning_rate": 3.462354188759279e-05,
|
| 753 |
+
"loss": 0.4035,
|
| 754 |
"step": 870
|
| 755 |
},
|
| 756 |
{
|
| 757 |
"epoch": 0.9331919406150583,
|
| 758 |
+
"grad_norm": 1.0593372583389282,
|
| 759 |
"learning_rate": 3.444680098974903e-05,
|
| 760 |
+
"loss": 0.403,
|
| 761 |
"step": 880
|
| 762 |
},
|
| 763 |
{
|
| 764 |
"epoch": 0.943796394485684,
|
| 765 |
+
"grad_norm": 1.0974407196044922,
|
| 766 |
"learning_rate": 3.427006009190527e-05,
|
| 767 |
+
"loss": 0.3994,
|
| 768 |
"step": 890
|
| 769 |
},
|
| 770 |
{
|
| 771 |
"epoch": 0.9544008483563097,
|
| 772 |
+
"grad_norm": 0.924757182598114,
|
| 773 |
"learning_rate": 3.409331919406151e-05,
|
| 774 |
+
"loss": 0.3854,
|
| 775 |
"step": 900
|
| 776 |
},
|
| 777 |
{
|
| 778 |
"epoch": 0.9544008483563097,
|
| 779 |
+
"eval_loss": 0.5818654894828796,
|
| 780 |
+
"eval_runtime": 11.8558,
|
| 781 |
+
"eval_samples_per_second": 40.486,
|
| 782 |
+
"eval_steps_per_second": 2.53,
|
| 783 |
"step": 900
|
| 784 |
},
|
| 785 |
{
|
| 786 |
"epoch": 0.9650053022269353,
|
| 787 |
+
"grad_norm": 1.0254701375961304,
|
| 788 |
"learning_rate": 3.391657829621775e-05,
|
| 789 |
+
"loss": 0.4214,
|
| 790 |
"step": 910
|
| 791 |
},
|
| 792 |
{
|
| 793 |
"epoch": 0.975609756097561,
|
| 794 |
+
"grad_norm": 1.0513700246810913,
|
| 795 |
"learning_rate": 3.373983739837399e-05,
|
| 796 |
+
"loss": 0.3934,
|
| 797 |
"step": 920
|
| 798 |
},
|
| 799 |
{
|
| 800 |
"epoch": 0.9862142099681867,
|
| 801 |
+
"grad_norm": 1.0283734798431396,
|
| 802 |
"learning_rate": 3.356309650053022e-05,
|
| 803 |
+
"loss": 0.3792,
|
| 804 |
"step": 930
|
| 805 |
},
|
| 806 |
{
|
| 807 |
"epoch": 0.9968186638388123,
|
| 808 |
+
"grad_norm": 1.0671693086624146,
|
| 809 |
"learning_rate": 3.3386355602686466e-05,
|
| 810 |
+
"loss": 0.3777,
|
| 811 |
"step": 940
|
| 812 |
},
|
| 813 |
{
|
| 814 |
"epoch": 1.007423117709438,
|
| 815 |
+
"grad_norm": 1.0414798259735107,
|
| 816 |
"learning_rate": 3.32096147048427e-05,
|
| 817 |
+
"loss": 0.3681,
|
| 818 |
"step": 950
|
| 819 |
},
|
| 820 |
{
|
| 821 |
"epoch": 1.007423117709438,
|
| 822 |
+
"eval_loss": 0.5841290950775146,
|
| 823 |
+
"eval_runtime": 11.8527,
|
| 824 |
+
"eval_samples_per_second": 40.497,
|
| 825 |
+
"eval_steps_per_second": 2.531,
|
| 826 |
"step": 950
|
| 827 |
},
|
| 828 |
{
|
| 829 |
"epoch": 1.0180275715800637,
|
| 830 |
+
"grad_norm": 1.1088826656341553,
|
| 831 |
"learning_rate": 3.3032873806998944e-05,
|
| 832 |
+
"loss": 0.3536,
|
| 833 |
"step": 960
|
| 834 |
},
|
| 835 |
{
|
| 836 |
"epoch": 1.0286320254506893,
|
| 837 |
+
"grad_norm": 1.2678877115249634,
|
| 838 |
"learning_rate": 3.285613290915518e-05,
|
| 839 |
+
"loss": 0.38,
|
| 840 |
"step": 970
|
| 841 |
},
|
| 842 |
{
|
| 843 |
"epoch": 1.039236479321315,
|
| 844 |
+
"grad_norm": 1.0846420526504517,
|
| 845 |
"learning_rate": 3.267939201131142e-05,
|
| 846 |
+
"loss": 0.3522,
|
| 847 |
"step": 980
|
| 848 |
},
|
| 849 |
{
|
| 850 |
"epoch": 1.0498409331919407,
|
| 851 |
+
"grad_norm": 1.0741760730743408,
|
| 852 |
"learning_rate": 3.2502651113467655e-05,
|
| 853 |
+
"loss": 0.3392,
|
| 854 |
"step": 990
|
| 855 |
},
|
| 856 |
{
|
| 857 |
"epoch": 1.0604453870625663,
|
| 858 |
+
"grad_norm": 1.2564727067947388,
|
| 859 |
"learning_rate": 3.2325910215623894e-05,
|
| 860 |
+
"loss": 0.3538,
|
| 861 |
"step": 1000
|
| 862 |
},
|
| 863 |
{
|
| 864 |
"epoch": 1.0604453870625663,
|
| 865 |
+
"eval_loss": 0.5931693911552429,
|
| 866 |
+
"eval_runtime": 11.8583,
|
| 867 |
+
"eval_samples_per_second": 40.478,
|
| 868 |
+
"eval_steps_per_second": 2.53,
|
| 869 |
"step": 1000
|
| 870 |
},
|
| 871 |
{
|
| 872 |
"epoch": 1.0710498409331919,
|
| 873 |
+
"grad_norm": 1.1698198318481445,
|
| 874 |
"learning_rate": 3.2149169317780133e-05,
|
| 875 |
"loss": 0.3274,
|
| 876 |
"step": 1010
|
| 877 |
},
|
| 878 |
{
|
| 879 |
"epoch": 1.0816542948038177,
|
| 880 |
+
"grad_norm": 1.1250603199005127,
|
| 881 |
"learning_rate": 3.197242841993637e-05,
|
| 882 |
+
"loss": 0.3519,
|
| 883 |
"step": 1020
|
| 884 |
},
|
| 885 |
{
|
| 886 |
"epoch": 1.0922587486744433,
|
| 887 |
+
"grad_norm": 1.1354424953460693,
|
| 888 |
"learning_rate": 3.179568752209262e-05,
|
| 889 |
+
"loss": 0.3474,
|
| 890 |
"step": 1030
|
| 891 |
},
|
| 892 |
{
|
| 893 |
"epoch": 1.1028632025450689,
|
| 894 |
+
"grad_norm": 1.2070807218551636,
|
| 895 |
"learning_rate": 3.161894662424885e-05,
|
| 896 |
+
"loss": 0.3426,
|
| 897 |
"step": 1040
|
| 898 |
},
|
| 899 |
{
|
| 900 |
"epoch": 1.1134676564156947,
|
| 901 |
+
"grad_norm": 1.147916555404663,
|
| 902 |
"learning_rate": 3.14422057264051e-05,
|
| 903 |
+
"loss": 0.3449,
|
| 904 |
"step": 1050
|
| 905 |
},
|
| 906 |
{
|
| 907 |
"epoch": 1.1134676564156947,
|
| 908 |
+
"eval_loss": 0.5951507687568665,
|
| 909 |
+
"eval_runtime": 11.8382,
|
| 910 |
+
"eval_samples_per_second": 40.547,
|
| 911 |
+
"eval_steps_per_second": 2.534,
|
| 912 |
"step": 1050
|
| 913 |
},
|
| 914 |
{
|
| 915 |
"epoch": 1.1240721102863203,
|
| 916 |
+
"grad_norm": 1.1941380500793457,
|
| 917 |
"learning_rate": 3.126546482856133e-05,
|
| 918 |
+
"loss": 0.3348,
|
| 919 |
"step": 1060
|
| 920 |
},
|
| 921 |
{
|
| 922 |
"epoch": 1.1346765641569458,
|
| 923 |
+
"grad_norm": 1.0945191383361816,
|
| 924 |
"learning_rate": 3.108872393071757e-05,
|
| 925 |
+
"loss": 0.3724,
|
| 926 |
"step": 1070
|
| 927 |
},
|
| 928 |
{
|
| 929 |
"epoch": 1.1452810180275717,
|
| 930 |
+
"grad_norm": 1.322505235671997,
|
| 931 |
"learning_rate": 3.091198303287381e-05,
|
| 932 |
+
"loss": 0.3312,
|
| 933 |
"step": 1080
|
| 934 |
},
|
| 935 |
{
|
| 936 |
"epoch": 1.1558854718981972,
|
| 937 |
+
"grad_norm": 1.0995663404464722,
|
| 938 |
"learning_rate": 3.073524213503005e-05,
|
| 939 |
+
"loss": 0.351,
|
| 940 |
"step": 1090
|
| 941 |
},
|
| 942 |
{
|
| 943 |
"epoch": 1.1664899257688228,
|
| 944 |
+
"grad_norm": 1.1347137689590454,
|
| 945 |
"learning_rate": 3.0558501237186286e-05,
|
| 946 |
+
"loss": 0.343,
|
| 947 |
"step": 1100
|
| 948 |
},
|
| 949 |
{
|
| 950 |
"epoch": 1.1664899257688228,
|
| 951 |
+
"eval_loss": 0.59864342212677,
|
| 952 |
+
"eval_runtime": 11.8201,
|
| 953 |
+
"eval_samples_per_second": 40.609,
|
| 954 |
+
"eval_steps_per_second": 2.538,
|
| 955 |
"step": 1100
|
| 956 |
},
|
| 957 |
{
|
| 958 |
"epoch": 1.1770943796394486,
|
| 959 |
+
"grad_norm": 1.2727549076080322,
|
| 960 |
"learning_rate": 3.0381760339342525e-05,
|
| 961 |
+
"loss": 0.342,
|
| 962 |
"step": 1110
|
| 963 |
},
|
| 964 |
{
|
| 965 |
"epoch": 1.1876988335100742,
|
| 966 |
+
"grad_norm": 1.1988881826400757,
|
| 967 |
"learning_rate": 3.0205019441498768e-05,
|
| 968 |
"loss": 0.3238,
|
| 969 |
"step": 1120
|
| 970 |
},
|
| 971 |
{
|
| 972 |
"epoch": 1.1983032873806998,
|
| 973 |
+
"grad_norm": 1.1220091581344604,
|
| 974 |
"learning_rate": 3.0028278543655004e-05,
|
| 975 |
+
"loss": 0.3281,
|
| 976 |
"step": 1130
|
| 977 |
},
|
| 978 |
{
|
| 979 |
"epoch": 1.2089077412513256,
|
| 980 |
+
"grad_norm": 1.1029518842697144,
|
| 981 |
"learning_rate": 2.985153764581124e-05,
|
| 982 |
+
"loss": 0.3566,
|
| 983 |
"step": 1140
|
| 984 |
},
|
| 985 |
{
|
| 986 |
"epoch": 1.2195121951219512,
|
| 987 |
+
"grad_norm": 1.0658305883407593,
|
| 988 |
"learning_rate": 2.9674796747967482e-05,
|
| 989 |
"loss": 0.3431,
|
| 990 |
"step": 1150
|
| 991 |
},
|
| 992 |
{
|
| 993 |
"epoch": 1.2195121951219512,
|
| 994 |
+
"eval_loss": 0.5974192023277283,
|
| 995 |
+
"eval_runtime": 11.8028,
|
| 996 |
+
"eval_samples_per_second": 40.668,
|
| 997 |
+
"eval_steps_per_second": 2.542,
|
| 998 |
"step": 1150
|
| 999 |
},
|
| 1000 |
{
|
| 1001 |
"epoch": 1.2301166489925768,
|
| 1002 |
+
"grad_norm": 1.306966781616211,
|
| 1003 |
"learning_rate": 2.9498055850123718e-05,
|
| 1004 |
+
"loss": 0.3355,
|
| 1005 |
"step": 1160
|
| 1006 |
},
|
| 1007 |
{
|
| 1008 |
"epoch": 1.2407211028632026,
|
| 1009 |
+
"grad_norm": 1.370133638381958,
|
| 1010 |
"learning_rate": 2.932131495227996e-05,
|
| 1011 |
+
"loss": 0.3475,
|
| 1012 |
"step": 1170
|
| 1013 |
},
|
| 1014 |
{
|
| 1015 |
"epoch": 1.2513255567338282,
|
| 1016 |
+
"grad_norm": 1.2001569271087646,
|
| 1017 |
"learning_rate": 2.9144574054436196e-05,
|
| 1018 |
+
"loss": 0.331,
|
| 1019 |
"step": 1180
|
| 1020 |
},
|
| 1021 |
{
|
| 1022 |
"epoch": 1.2619300106044538,
|
| 1023 |
+
"grad_norm": 1.27125883102417,
|
| 1024 |
"learning_rate": 2.896783315659244e-05,
|
| 1025 |
+
"loss": 0.3461,
|
| 1026 |
"step": 1190
|
| 1027 |
},
|
| 1028 |
{
|
| 1029 |
"epoch": 1.2725344644750796,
|
| 1030 |
+
"grad_norm": 1.417680025100708,
|
| 1031 |
"learning_rate": 2.8791092258748675e-05,
|
| 1032 |
+
"loss": 0.3298,
|
| 1033 |
"step": 1200
|
| 1034 |
},
|
| 1035 |
{
|
| 1036 |
"epoch": 1.2725344644750796,
|
| 1037 |
+
"eval_loss": 0.6026219129562378,
|
| 1038 |
+
"eval_runtime": 11.8206,
|
| 1039 |
+
"eval_samples_per_second": 40.607,
|
| 1040 |
+
"eval_steps_per_second": 2.538,
|
| 1041 |
"step": 1200
|
| 1042 |
},
|
| 1043 |
{
|
| 1044 |
"epoch": 1.2831389183457051,
|
| 1045 |
+
"grad_norm": 1.3502525091171265,
|
| 1046 |
"learning_rate": 2.8614351360904917e-05,
|
| 1047 |
+
"loss": 0.3348,
|
| 1048 |
"step": 1210
|
| 1049 |
},
|
| 1050 |
{
|
| 1051 |
"epoch": 1.2937433722163307,
|
| 1052 |
+
"grad_norm": 1.0501817464828491,
|
| 1053 |
"learning_rate": 2.8437610463061153e-05,
|
| 1054 |
"loss": 0.3253,
|
| 1055 |
"step": 1220
|
| 1056 |
},
|
| 1057 |
{
|
| 1058 |
"epoch": 1.3043478260869565,
|
| 1059 |
+
"grad_norm": 1.197717308998108,
|
| 1060 |
"learning_rate": 2.826086956521739e-05,
|
| 1061 |
+
"loss": 0.3251,
|
| 1062 |
"step": 1230
|
| 1063 |
},
|
| 1064 |
{
|
| 1065 |
"epoch": 1.3149522799575821,
|
| 1066 |
+
"grad_norm": 1.1236610412597656,
|
| 1067 |
"learning_rate": 2.808412866737363e-05,
|
| 1068 |
+
"loss": 0.3229,
|
| 1069 |
"step": 1240
|
| 1070 |
},
|
| 1071 |
{
|
| 1072 |
"epoch": 1.3255567338282077,
|
| 1073 |
+
"grad_norm": 1.172448754310608,
|
| 1074 |
"learning_rate": 2.790738776952987e-05,
|
| 1075 |
+
"loss": 0.3408,
|
| 1076 |
"step": 1250
|
| 1077 |
},
|
| 1078 |
{
|
| 1079 |
"epoch": 1.3255567338282077,
|
| 1080 |
+
"eval_loss": 0.6030397415161133,
|
| 1081 |
+
"eval_runtime": 11.8274,
|
| 1082 |
+
"eval_samples_per_second": 40.584,
|
| 1083 |
+
"eval_steps_per_second": 2.536,
|
| 1084 |
"step": 1250
|
| 1085 |
},
|
| 1086 |
{
|
| 1087 |
"epoch": 1.3361611876988335,
|
| 1088 |
+
"grad_norm": 1.33034086227417,
|
| 1089 |
"learning_rate": 2.773064687168611e-05,
|
| 1090 |
+
"loss": 0.3351,
|
| 1091 |
"step": 1260
|
| 1092 |
},
|
| 1093 |
{
|
| 1094 |
"epoch": 1.346765641569459,
|
| 1095 |
+
"grad_norm": 1.3041718006134033,
|
| 1096 |
"learning_rate": 2.755390597384235e-05,
|
| 1097 |
+
"loss": 0.339,
|
| 1098 |
"step": 1270
|
| 1099 |
},
|
| 1100 |
{
|
| 1101 |
"epoch": 1.357370095440085,
|
| 1102 |
+
"grad_norm": 1.3249897956848145,
|
| 1103 |
"learning_rate": 2.7377165075998588e-05,
|
| 1104 |
+
"loss": 0.3357,
|
| 1105 |
"step": 1280
|
| 1106 |
},
|
| 1107 |
{
|
| 1108 |
"epoch": 1.3679745493107105,
|
| 1109 |
+
"grad_norm": 1.2230838537216187,
|
| 1110 |
"learning_rate": 2.7200424178154827e-05,
|
| 1111 |
+
"loss": 0.3445,
|
| 1112 |
"step": 1290
|
| 1113 |
},
|
| 1114 |
{
|
| 1115 |
"epoch": 1.378579003181336,
|
| 1116 |
+
"grad_norm": 1.249778389930725,
|
| 1117 |
"learning_rate": 2.7023683280311063e-05,
|
| 1118 |
+
"loss": 0.3321,
|
| 1119 |
"step": 1300
|
| 1120 |
},
|
| 1121 |
{
|
| 1122 |
"epoch": 1.378579003181336,
|
| 1123 |
+
"eval_loss": 0.6035539507865906,
|
| 1124 |
+
"eval_runtime": 11.8513,
|
| 1125 |
+
"eval_samples_per_second": 40.502,
|
| 1126 |
+
"eval_steps_per_second": 2.531,
|
| 1127 |
"step": 1300
|
| 1128 |
},
|
| 1129 |
{
|
| 1130 |
"epoch": 1.389183457051962,
|
| 1131 |
+
"grad_norm": 1.2172768115997314,
|
| 1132 |
"learning_rate": 2.6846942382467306e-05,
|
| 1133 |
+
"loss": 0.3265,
|
| 1134 |
"step": 1310
|
| 1135 |
},
|
| 1136 |
{
|
| 1137 |
"epoch": 1.3997879109225875,
|
| 1138 |
+
"grad_norm": 1.420792579650879,
|
| 1139 |
"learning_rate": 2.667020148462354e-05,
|
| 1140 |
+
"loss": 0.3291,
|
| 1141 |
"step": 1320
|
| 1142 |
},
|
| 1143 |
{
|
| 1144 |
"epoch": 1.4103923647932133,
|
| 1145 |
+
"grad_norm": 1.5471575260162354,
|
| 1146 |
"learning_rate": 2.6493460586779784e-05,
|
| 1147 |
+
"loss": 0.3282,
|
| 1148 |
"step": 1330
|
| 1149 |
},
|
| 1150 |
{
|
| 1151 |
"epoch": 1.4209968186638389,
|
| 1152 |
+
"grad_norm": 1.1769243478775024,
|
| 1153 |
"learning_rate": 2.631671968893602e-05,
|
| 1154 |
+
"loss": 0.314,
|
| 1155 |
"step": 1340
|
| 1156 |
},
|
| 1157 |
{
|
| 1158 |
"epoch": 1.4316012725344645,
|
| 1159 |
+
"grad_norm": 1.299428105354309,
|
| 1160 |
"learning_rate": 2.6139978791092262e-05,
|
| 1161 |
+
"loss": 0.3055,
|
| 1162 |
"step": 1350
|
| 1163 |
},
|
| 1164 |
{
|
| 1165 |
"epoch": 1.4316012725344645,
|
| 1166 |
+
"eval_loss": 0.6074148416519165,
|
| 1167 |
+
"eval_runtime": 11.8791,
|
| 1168 |
+
"eval_samples_per_second": 40.407,
|
| 1169 |
+
"eval_steps_per_second": 2.525,
|
| 1170 |
"step": 1350
|
| 1171 |
},
|
| 1172 |
{
|
| 1173 |
"epoch": 1.4422057264050903,
|
| 1174 |
+
"grad_norm": 1.2306607961654663,
|
| 1175 |
"learning_rate": 2.5963237893248498e-05,
|
| 1176 |
+
"loss": 0.3355,
|
| 1177 |
"step": 1360
|
| 1178 |
},
|
| 1179 |
{
|
| 1180 |
"epoch": 1.4528101802757158,
|
| 1181 |
+
"grad_norm": 1.236029863357544,
|
| 1182 |
"learning_rate": 2.5786496995404734e-05,
|
| 1183 |
+
"loss": 0.3299,
|
| 1184 |
"step": 1370
|
| 1185 |
},
|
| 1186 |
{
|
| 1187 |
"epoch": 1.4634146341463414,
|
| 1188 |
+
"grad_norm": 1.1422163248062134,
|
| 1189 |
"learning_rate": 2.5609756097560977e-05,
|
| 1190 |
"loss": 0.3271,
|
| 1191 |
"step": 1380
|
| 1192 |
},
|
| 1193 |
{
|
| 1194 |
"epoch": 1.4740190880169672,
|
| 1195 |
+
"grad_norm": 1.4650191068649292,
|
| 1196 |
"learning_rate": 2.5433015199717212e-05,
|
| 1197 |
+
"loss": 0.3298,
|
| 1198 |
"step": 1390
|
| 1199 |
},
|
| 1200 |
{
|
| 1201 |
"epoch": 1.4846235418875928,
|
| 1202 |
+
"grad_norm": 1.3182368278503418,
|
| 1203 |
"learning_rate": 2.5256274301873455e-05,
|
| 1204 |
+
"loss": 0.3273,
|
| 1205 |
"step": 1400
|
| 1206 |
},
|
| 1207 |
{
|
| 1208 |
"epoch": 1.4846235418875928,
|
| 1209 |
+
"eval_loss": 0.6101020574569702,
|
| 1210 |
+
"eval_runtime": 11.8749,
|
| 1211 |
+
"eval_samples_per_second": 40.421,
|
| 1212 |
+
"eval_steps_per_second": 2.526,
|
| 1213 |
"step": 1400
|
| 1214 |
},
|
| 1215 |
{
|
| 1216 |
"epoch": 1.4952279957582184,
|
| 1217 |
+
"grad_norm": 1.2115826606750488,
|
| 1218 |
"learning_rate": 2.507953340402969e-05,
|
| 1219 |
+
"loss": 0.3087,
|
| 1220 |
"step": 1410
|
| 1221 |
},
|
| 1222 |
{
|
| 1223 |
"epoch": 1.5058324496288442,
|
| 1224 |
+
"grad_norm": 1.4292011260986328,
|
| 1225 |
"learning_rate": 2.4902792506185933e-05,
|
| 1226 |
+
"loss": 0.3048,
|
| 1227 |
"step": 1420
|
| 1228 |
},
|
| 1229 |
{
|
| 1230 |
"epoch": 1.5164369034994698,
|
| 1231 |
+
"grad_norm": 1.291587471961975,
|
| 1232 |
"learning_rate": 2.4726051608342173e-05,
|
| 1233 |
+
"loss": 0.3277,
|
| 1234 |
"step": 1430
|
| 1235 |
},
|
| 1236 |
{
|
| 1237 |
"epoch": 1.5270413573700954,
|
| 1238 |
+
"grad_norm": 1.21229088306427,
|
| 1239 |
"learning_rate": 2.4549310710498412e-05,
|
| 1240 |
+
"loss": 0.3119,
|
| 1241 |
"step": 1440
|
| 1242 |
},
|
| 1243 |
{
|
| 1244 |
"epoch": 1.5376458112407212,
|
| 1245 |
+
"grad_norm": 1.3125064373016357,
|
| 1246 |
"learning_rate": 2.437256981265465e-05,
|
| 1247 |
+
"loss": 0.3179,
|
| 1248 |
"step": 1450
|
| 1249 |
},
|
| 1250 |
{
|
| 1251 |
"epoch": 1.5376458112407212,
|
| 1252 |
+
"eval_loss": 0.6085401773452759,
|
| 1253 |
+
"eval_runtime": 11.8623,
|
| 1254 |
+
"eval_samples_per_second": 40.464,
|
| 1255 |
+
"eval_steps_per_second": 2.529,
|
| 1256 |
"step": 1450
|
| 1257 |
},
|
| 1258 |
{
|
| 1259 |
"epoch": 1.5482502651113468,
|
| 1260 |
+
"grad_norm": 1.279478907585144,
|
| 1261 |
"learning_rate": 2.419582891481089e-05,
|
| 1262 |
"loss": 0.3233,
|
| 1263 |
"step": 1460
|
| 1264 |
},
|
| 1265 |
{
|
| 1266 |
"epoch": 1.5588547189819724,
|
| 1267 |
+
"grad_norm": 1.2751704454421997,
|
| 1268 |
"learning_rate": 2.401908801696713e-05,
|
| 1269 |
+
"loss": 0.3192,
|
| 1270 |
"step": 1470
|
| 1271 |
},
|
| 1272 |
{
|
| 1273 |
"epoch": 1.5694591728525982,
|
| 1274 |
+
"grad_norm": 1.305484652519226,
|
| 1275 |
"learning_rate": 2.3842347119123365e-05,
|
| 1276 |
+
"loss": 0.3175,
|
| 1277 |
"step": 1480
|
| 1278 |
},
|
| 1279 |
{
|
| 1280 |
"epoch": 1.5800636267232238,
|
| 1281 |
+
"grad_norm": 1.276348352432251,
|
| 1282 |
"learning_rate": 2.3665606221279604e-05,
|
| 1283 |
+
"loss": 0.3043,
|
| 1284 |
"step": 1490
|
| 1285 |
},
|
| 1286 |
{
|
| 1287 |
"epoch": 1.5906680805938493,
|
| 1288 |
+
"grad_norm": 1.3701218366622925,
|
| 1289 |
"learning_rate": 2.3488865323435844e-05,
|
| 1290 |
+
"loss": 0.3185,
|
| 1291 |
"step": 1500
|
| 1292 |
},
|
| 1293 |
{
|
| 1294 |
"epoch": 1.5906680805938493,
|
| 1295 |
+
"eval_loss": 0.6127668619155884,
|
| 1296 |
+
"eval_runtime": 11.8543,
|
| 1297 |
+
"eval_samples_per_second": 40.492,
|
| 1298 |
+
"eval_steps_per_second": 2.531,
|
| 1299 |
"step": 1500
|
| 1300 |
},
|
| 1301 |
{
|
| 1302 |
"epoch": 1.6012725344644752,
|
| 1303 |
+
"grad_norm": 1.39030122756958,
|
| 1304 |
"learning_rate": 2.3312124425592083e-05,
|
| 1305 |
+
"loss": 0.316,
|
| 1306 |
"step": 1510
|
| 1307 |
},
|
| 1308 |
{
|
| 1309 |
"epoch": 1.6118769883351007,
|
| 1310 |
+
"grad_norm": 1.2342959642410278,
|
| 1311 |
"learning_rate": 2.3135383527748322e-05,
|
| 1312 |
+
"loss": 0.2928,
|
| 1313 |
"step": 1520
|
| 1314 |
},
|
| 1315 |
{
|
| 1316 |
"epoch": 1.6224814422057263,
|
| 1317 |
+
"grad_norm": 1.546506404876709,
|
| 1318 |
"learning_rate": 2.295864262990456e-05,
|
| 1319 |
+
"loss": 0.3195,
|
| 1320 |
"step": 1530
|
| 1321 |
},
|
| 1322 |
{
|
| 1323 |
"epoch": 1.6330858960763521,
|
| 1324 |
+
"grad_norm": 1.483469009399414,
|
| 1325 |
"learning_rate": 2.27819017320608e-05,
|
| 1326 |
+
"loss": 0.3208,
|
| 1327 |
"step": 1540
|
| 1328 |
},
|
| 1329 |
{
|
| 1330 |
"epoch": 1.6436903499469777,
|
| 1331 |
+
"grad_norm": 1.4679921865463257,
|
| 1332 |
"learning_rate": 2.260516083421704e-05,
|
| 1333 |
+
"loss": 0.3217,
|
| 1334 |
"step": 1550
|
| 1335 |
},
|
| 1336 |
{
|
| 1337 |
"epoch": 1.6436903499469777,
|
| 1338 |
+
"eval_loss": 0.6129384636878967,
|
| 1339 |
+
"eval_runtime": 11.8494,
|
| 1340 |
+
"eval_samples_per_second": 40.508,
|
| 1341 |
+
"eval_steps_per_second": 2.532,
|
| 1342 |
"step": 1550
|
| 1343 |
},
|
| 1344 |
{
|
| 1345 |
"epoch": 1.6542948038176033,
|
| 1346 |
+
"grad_norm": 1.4147011041641235,
|
| 1347 |
"learning_rate": 2.2428419936373275e-05,
|
| 1348 |
+
"loss": 0.3424,
|
| 1349 |
"step": 1560
|
| 1350 |
},
|
| 1351 |
{
|
| 1352 |
"epoch": 1.664899257688229,
|
| 1353 |
+
"grad_norm": 1.2510008811950684,
|
| 1354 |
"learning_rate": 2.2251679038529514e-05,
|
| 1355 |
+
"loss": 0.3153,
|
| 1356 |
"step": 1570
|
| 1357 |
},
|
| 1358 |
{
|
| 1359 |
"epoch": 1.6755037115588547,
|
| 1360 |
+
"grad_norm": 1.3089756965637207,
|
| 1361 |
"learning_rate": 2.2074938140685754e-05,
|
| 1362 |
+
"loss": 0.3235,
|
| 1363 |
"step": 1580
|
| 1364 |
},
|
| 1365 |
{
|
| 1366 |
"epoch": 1.6861081654294803,
|
| 1367 |
+
"grad_norm": 1.4045295715332031,
|
| 1368 |
"learning_rate": 2.1898197242841996e-05,
|
| 1369 |
"loss": 0.3194,
|
| 1370 |
"step": 1590
|
| 1371 |
},
|
| 1372 |
{
|
| 1373 |
"epoch": 1.696712619300106,
|
| 1374 |
+
"grad_norm": 1.552812099456787,
|
| 1375 |
"learning_rate": 2.1721456344998235e-05,
|
| 1376 |
+
"loss": 0.3172,
|
| 1377 |
"step": 1600
|
| 1378 |
},
|
| 1379 |
{
|
| 1380 |
"epoch": 1.696712619300106,
|
| 1381 |
+
"eval_loss": 0.6166751980781555,
|
| 1382 |
+
"eval_runtime": 11.8313,
|
| 1383 |
+
"eval_samples_per_second": 40.57,
|
| 1384 |
+
"eval_steps_per_second": 2.536,
|
| 1385 |
"step": 1600
|
| 1386 |
},
|
| 1387 |
{
|
| 1388 |
"epoch": 1.7073170731707317,
|
| 1389 |
+
"grad_norm": 1.5868216753005981,
|
| 1390 |
"learning_rate": 2.1544715447154475e-05,
|
| 1391 |
+
"loss": 0.3125,
|
| 1392 |
"step": 1610
|
| 1393 |
},
|
| 1394 |
{
|
| 1395 |
"epoch": 1.7179215270413573,
|
| 1396 |
+
"grad_norm": 1.2543333768844604,
|
| 1397 |
"learning_rate": 2.1367974549310714e-05,
|
| 1398 |
+
"loss": 0.303,
|
| 1399 |
"step": 1620
|
| 1400 |
},
|
| 1401 |
{
|
| 1402 |
"epoch": 1.728525980911983,
|
| 1403 |
+
"grad_norm": 1.451438546180725,
|
| 1404 |
"learning_rate": 2.1191233651466953e-05,
|
| 1405 |
+
"loss": 0.3154,
|
| 1406 |
"step": 1630
|
| 1407 |
},
|
| 1408 |
{
|
| 1409 |
"epoch": 1.7391304347826086,
|
| 1410 |
+
"grad_norm": 1.565056562423706,
|
| 1411 |
"learning_rate": 2.101449275362319e-05,
|
| 1412 |
+
"loss": 0.3258,
|
| 1413 |
"step": 1640
|
| 1414 |
},
|
| 1415 |
{
|
| 1416 |
"epoch": 1.7497348886532342,
|
| 1417 |
+
"grad_norm": 1.1945902109146118,
|
| 1418 |
"learning_rate": 2.0837751855779428e-05,
|
| 1419 |
+
"loss": 0.2997,
|
| 1420 |
"step": 1650
|
| 1421 |
},
|
| 1422 |
{
|
| 1423 |
"epoch": 1.7497348886532342,
|
| 1424 |
+
"eval_loss": 0.610952615737915,
|
| 1425 |
+
"eval_runtime": 11.8045,
|
| 1426 |
+
"eval_samples_per_second": 40.663,
|
| 1427 |
+
"eval_steps_per_second": 2.541,
|
| 1428 |
"step": 1650
|
| 1429 |
},
|
| 1430 |
{
|
| 1431 |
"epoch": 1.76033934252386,
|
| 1432 |
+
"grad_norm": 1.303575873374939,
|
| 1433 |
"learning_rate": 2.0661010957935667e-05,
|
| 1434 |
+
"loss": 0.3052,
|
| 1435 |
"step": 1660
|
| 1436 |
},
|
| 1437 |
{
|
| 1438 |
"epoch": 1.7709437963944858,
|
| 1439 |
+
"grad_norm": 1.2875950336456299,
|
| 1440 |
"learning_rate": 2.0484270060091906e-05,
|
| 1441 |
+
"loss": 0.3165,
|
| 1442 |
"step": 1670
|
| 1443 |
},
|
| 1444 |
{
|
| 1445 |
"epoch": 1.7815482502651112,
|
| 1446 |
+
"grad_norm": 1.3722983598709106,
|
| 1447 |
"learning_rate": 2.0307529162248146e-05,
|
| 1448 |
+
"loss": 0.315,
|
| 1449 |
"step": 1680
|
| 1450 |
},
|
| 1451 |
{
|
| 1452 |
"epoch": 1.792152704135737,
|
| 1453 |
+
"grad_norm": 1.575512409210205,
|
| 1454 |
"learning_rate": 2.0130788264404385e-05,
|
| 1455 |
+
"loss": 0.3111,
|
| 1456 |
"step": 1690
|
| 1457 |
},
|
| 1458 |
{
|
| 1459 |
"epoch": 1.8027571580063628,
|
| 1460 |
+
"grad_norm": 1.5420628786087036,
|
| 1461 |
"learning_rate": 1.9954047366560624e-05,
|
| 1462 |
+
"loss": 0.3016,
|
| 1463 |
"step": 1700
|
| 1464 |
},
|
| 1465 |
{
|
| 1466 |
"epoch": 1.8027571580063628,
|
| 1467 |
+
"eval_loss": 0.6173704862594604,
|
| 1468 |
+
"eval_runtime": 11.8101,
|
| 1469 |
+
"eval_samples_per_second": 40.643,
|
| 1470 |
+
"eval_steps_per_second": 2.54,
|
| 1471 |
"step": 1700
|
| 1472 |
},
|
| 1473 |
{
|
| 1474 |
"epoch": 1.8133616118769882,
|
| 1475 |
+
"grad_norm": 1.4816402196884155,
|
| 1476 |
"learning_rate": 1.977730646871686e-05,
|
| 1477 |
+
"loss": 0.3094,
|
| 1478 |
"step": 1710
|
| 1479 |
},
|
| 1480 |
{
|
| 1481 |
"epoch": 1.823966065747614,
|
| 1482 |
+
"grad_norm": 1.4740856885910034,
|
| 1483 |
"learning_rate": 1.96005655708731e-05,
|
| 1484 |
+
"loss": 0.302,
|
| 1485 |
"step": 1720
|
| 1486 |
},
|
| 1487 |
{
|
| 1488 |
"epoch": 1.8345705196182398,
|
| 1489 |
+
"grad_norm": 1.4715994596481323,
|
| 1490 |
"learning_rate": 1.9423824673029338e-05,
|
| 1491 |
+
"loss": 0.3056,
|
| 1492 |
"step": 1730
|
| 1493 |
},
|
| 1494 |
{
|
| 1495 |
"epoch": 1.8451749734888652,
|
| 1496 |
+
"grad_norm": 1.5108782052993774,
|
| 1497 |
"learning_rate": 1.9247083775185577e-05,
|
| 1498 |
+
"loss": 0.3066,
|
| 1499 |
"step": 1740
|
| 1500 |
},
|
| 1501 |
{
|
| 1502 |
"epoch": 1.855779427359491,
|
| 1503 |
+
"grad_norm": 1.2223414182662964,
|
| 1504 |
"learning_rate": 1.9070342877341817e-05,
|
| 1505 |
+
"loss": 0.2908,
|
| 1506 |
"step": 1750
|
| 1507 |
},
|
| 1508 |
{
|
| 1509 |
"epoch": 1.855779427359491,
|
| 1510 |
+
"eval_loss": 0.6226276159286499,
|
| 1511 |
+
"eval_runtime": 11.8207,
|
| 1512 |
+
"eval_samples_per_second": 40.607,
|
| 1513 |
+
"eval_steps_per_second": 2.538,
|
| 1514 |
"step": 1750
|
| 1515 |
},
|
| 1516 |
{
|
| 1517 |
"epoch": 1.8663838812301168,
|
| 1518 |
+
"grad_norm": 1.3992316722869873,
|
| 1519 |
"learning_rate": 1.8893601979498056e-05,
|
| 1520 |
+
"loss": 0.2927,
|
| 1521 |
"step": 1760
|
| 1522 |
},
|
| 1523 |
{
|
| 1524 |
"epoch": 1.8769883351007424,
|
| 1525 |
+
"grad_norm": 1.416420578956604,
|
| 1526 |
"learning_rate": 1.8716861081654298e-05,
|
| 1527 |
+
"loss": 0.2992,
|
| 1528 |
"step": 1770
|
| 1529 |
},
|
| 1530 |
{
|
| 1531 |
"epoch": 1.887592788971368,
|
| 1532 |
+
"grad_norm": 1.3242861032485962,
|
| 1533 |
"learning_rate": 1.8540120183810537e-05,
|
| 1534 |
+
"loss": 0.3239,
|
| 1535 |
"step": 1780
|
| 1536 |
},
|
| 1537 |
{
|
| 1538 |
"epoch": 1.8981972428419938,
|
| 1539 |
+
"grad_norm": 1.4421693086624146,
|
| 1540 |
"learning_rate": 1.8363379285966773e-05,
|
| 1541 |
"loss": 0.2913,
|
| 1542 |
"step": 1790
|
| 1543 |
},
|
| 1544 |
{
|
| 1545 |
"epoch": 1.9088016967126193,
|
| 1546 |
+
"grad_norm": 1.4093183279037476,
|
| 1547 |
"learning_rate": 1.8186638388123012e-05,
|
| 1548 |
"loss": 0.3066,
|
| 1549 |
"step": 1800
|
| 1550 |
},
|
| 1551 |
{
|
| 1552 |
"epoch": 1.9088016967126193,
|
| 1553 |
+
"eval_loss": 0.6219280362129211,
|
| 1554 |
+
"eval_runtime": 11.8265,
|
| 1555 |
+
"eval_samples_per_second": 40.587,
|
| 1556 |
"eval_steps_per_second": 2.537,
|
| 1557 |
"step": 1800
|
| 1558 |
},
|
| 1559 |
{
|
| 1560 |
"epoch": 1.919406150583245,
|
| 1561 |
+
"grad_norm": 1.415610909461975,
|
| 1562 |
"learning_rate": 1.800989749027925e-05,
|
| 1563 |
+
"loss": 0.2964,
|
| 1564 |
"step": 1810
|
| 1565 |
},
|
| 1566 |
{
|
| 1567 |
"epoch": 1.9300106044538707,
|
| 1568 |
+
"grad_norm": 1.5223126411437988,
|
| 1569 |
"learning_rate": 1.783315659243549e-05,
|
| 1570 |
+
"loss": 0.3052,
|
| 1571 |
"step": 1820
|
| 1572 |
},
|
| 1573 |
{
|
| 1574 |
"epoch": 1.9406150583244963,
|
| 1575 |
+
"grad_norm": 1.4438203573226929,
|
| 1576 |
"learning_rate": 1.765641569459173e-05,
|
| 1577 |
+
"loss": 0.2857,
|
| 1578 |
"step": 1830
|
| 1579 |
},
|
| 1580 |
{
|
| 1581 |
"epoch": 1.951219512195122,
|
| 1582 |
+
"grad_norm": 1.367473840713501,
|
| 1583 |
"learning_rate": 1.747967479674797e-05,
|
| 1584 |
+
"loss": 0.3032,
|
| 1585 |
"step": 1840
|
| 1586 |
},
|
| 1587 |
{
|
| 1588 |
"epoch": 1.9618239660657477,
|
| 1589 |
+
"grad_norm": 1.6663137674331665,
|
| 1590 |
"learning_rate": 1.730293389890421e-05,
|
| 1591 |
+
"loss": 0.2932,
|
| 1592 |
"step": 1850
|
| 1593 |
},
|
| 1594 |
{
|
| 1595 |
"epoch": 1.9618239660657477,
|
| 1596 |
+
"eval_loss": 0.6298917531967163,
|
| 1597 |
+
"eval_runtime": 11.8449,
|
| 1598 |
+
"eval_samples_per_second": 40.524,
|
| 1599 |
+
"eval_steps_per_second": 2.533,
|
| 1600 |
"step": 1850
|
| 1601 |
},
|
| 1602 |
{
|
| 1603 |
"epoch": 1.9724284199363733,
|
| 1604 |
+
"grad_norm": 1.795198917388916,
|
| 1605 |
"learning_rate": 1.7126193001060444e-05,
|
| 1606 |
"loss": 0.2911,
|
| 1607 |
"step": 1860
|
| 1608 |
},
|
| 1609 |
{
|
| 1610 |
"epoch": 1.9830328738069989,
|
| 1611 |
+
"grad_norm": 1.300916314125061,
|
| 1612 |
"learning_rate": 1.6949452103216683e-05,
|
| 1613 |
+
"loss": 0.2991,
|
| 1614 |
"step": 1870
|
| 1615 |
},
|
| 1616 |
{
|
| 1617 |
"epoch": 1.9936373276776247,
|
| 1618 |
+
"grad_norm": 1.5338672399520874,
|
| 1619 |
"learning_rate": 1.6772711205372923e-05,
|
| 1620 |
+
"loss": 0.3015,
|
| 1621 |
"step": 1880
|
| 1622 |
},
|
| 1623 |
{
|
| 1624 |
"epoch": 2.00424178154825,
|
| 1625 |
+
"grad_norm": 1.107972264289856,
|
| 1626 |
"learning_rate": 1.6595970307529162e-05,
|
| 1627 |
+
"loss": 0.2838,
|
| 1628 |
"step": 1890
|
| 1629 |
},
|
| 1630 |
{
|
| 1631 |
"epoch": 2.014846235418876,
|
| 1632 |
+
"grad_norm": 1.3510525226593018,
|
| 1633 |
"learning_rate": 1.64192294096854e-05,
|
| 1634 |
+
"loss": 0.2528,
|
| 1635 |
"step": 1900
|
| 1636 |
},
|
| 1637 |
{
|
| 1638 |
"epoch": 2.014846235418876,
|
| 1639 |
+
"eval_loss": 0.6525193452835083,
|
| 1640 |
+
"eval_runtime": 11.8539,
|
| 1641 |
+
"eval_samples_per_second": 40.493,
|
| 1642 |
+
"eval_steps_per_second": 2.531,
|
| 1643 |
"step": 1900
|
| 1644 |
},
|
| 1645 |
{
|
| 1646 |
"epoch": 2.0254506892895017,
|
| 1647 |
+
"grad_norm": 1.611437201499939,
|
| 1648 |
"learning_rate": 1.624248851184164e-05,
|
| 1649 |
"loss": 0.2482,
|
| 1650 |
"step": 1910
|
| 1651 |
},
|
| 1652 |
{
|
| 1653 |
"epoch": 2.0360551431601275,
|
| 1654 |
+
"grad_norm": 1.381274938583374,
|
| 1655 |
"learning_rate": 1.606574761399788e-05,
|
| 1656 |
+
"loss": 0.2531,
|
| 1657 |
"step": 1920
|
| 1658 |
},
|
| 1659 |
{
|
| 1660 |
"epoch": 2.046659597030753,
|
| 1661 |
+
"grad_norm": 1.4334505796432495,
|
| 1662 |
"learning_rate": 1.588900671615412e-05,
|
| 1663 |
+
"loss": 0.2589,
|
| 1664 |
"step": 1930
|
| 1665 |
},
|
| 1666 |
{
|
| 1667 |
"epoch": 2.0572640509013786,
|
| 1668 |
+
"grad_norm": 1.5322158336639404,
|
| 1669 |
"learning_rate": 1.5712265818310358e-05,
|
| 1670 |
+
"loss": 0.2526,
|
| 1671 |
"step": 1940
|
| 1672 |
},
|
| 1673 |
{
|
| 1674 |
"epoch": 2.0678685047720045,
|
| 1675 |
+
"grad_norm": 1.4440096616744995,
|
| 1676 |
"learning_rate": 1.5535524920466597e-05,
|
| 1677 |
+
"loss": 0.2612,
|
| 1678 |
"step": 1950
|
| 1679 |
},
|
| 1680 |
{
|
| 1681 |
"epoch": 2.0678685047720045,
|
| 1682 |
+
"eval_loss": 0.6737074255943298,
|
| 1683 |
+
"eval_runtime": 11.8536,
|
| 1684 |
+
"eval_samples_per_second": 40.494,
|
| 1685 |
+
"eval_steps_per_second": 2.531,
|
| 1686 |
"step": 1950
|
| 1687 |
},
|
| 1688 |
{
|
| 1689 |
"epoch": 2.07847295864263,
|
| 1690 |
+
"grad_norm": 1.5944284200668335,
|
| 1691 |
"learning_rate": 1.5358784022622836e-05,
|
| 1692 |
+
"loss": 0.2477,
|
| 1693 |
"step": 1960
|
| 1694 |
},
|
| 1695 |
{
|
| 1696 |
"epoch": 2.0890774125132556,
|
| 1697 |
+
"grad_norm": 1.423839807510376,
|
| 1698 |
"learning_rate": 1.5182043124779075e-05,
|
| 1699 |
+
"loss": 0.2479,
|
| 1700 |
"step": 1970
|
| 1701 |
},
|
| 1702 |
{
|
| 1703 |
"epoch": 2.0996818663838814,
|
| 1704 |
+
"grad_norm": 1.5031301975250244,
|
| 1705 |
"learning_rate": 1.5005302226935314e-05,
|
| 1706 |
+
"loss": 0.2471,
|
| 1707 |
"step": 1980
|
| 1708 |
},
|
| 1709 |
{
|
| 1710 |
"epoch": 2.110286320254507,
|
| 1711 |
+
"grad_norm": 1.3962875604629517,
|
| 1712 |
"learning_rate": 1.4828561329091554e-05,
|
| 1713 |
+
"loss": 0.2455,
|
| 1714 |
"step": 1990
|
| 1715 |
},
|
| 1716 |
{
|
| 1717 |
"epoch": 2.1208907741251326,
|
| 1718 |
+
"grad_norm": 1.3927381038665771,
|
| 1719 |
"learning_rate": 1.4651820431247793e-05,
|
| 1720 |
+
"loss": 0.2535,
|
| 1721 |
"step": 2000
|
| 1722 |
},
|
| 1723 |
{
|
| 1724 |
"epoch": 2.1208907741251326,
|
| 1725 |
+
"eval_loss": 0.6821760535240173,
|
| 1726 |
+
"eval_runtime": 11.8524,
|
| 1727 |
+
"eval_samples_per_second": 40.498,
|
| 1728 |
+
"eval_steps_per_second": 2.531,
|
| 1729 |
"step": 2000
|
| 1730 |
},
|
| 1731 |
{
|
| 1732 |
"epoch": 2.1314952279957584,
|
| 1733 |
+
"grad_norm": 1.3482441902160645,
|
| 1734 |
"learning_rate": 1.4475079533404029e-05,
|
| 1735 |
+
"loss": 0.249,
|
| 1736 |
"step": 2010
|
| 1737 |
},
|
| 1738 |
{
|
| 1739 |
"epoch": 2.1420996818663838,
|
| 1740 |
+
"grad_norm": 1.8277605772018433,
|
| 1741 |
"learning_rate": 1.4298338635560268e-05,
|
| 1742 |
+
"loss": 0.2488,
|
| 1743 |
"step": 2020
|
| 1744 |
},
|
| 1745 |
{
|
| 1746 |
"epoch": 2.1527041357370096,
|
| 1747 |
+
"grad_norm": 1.4258739948272705,
|
| 1748 |
"learning_rate": 1.4121597737716507e-05,
|
| 1749 |
+
"loss": 0.2561,
|
| 1750 |
"step": 2030
|
| 1751 |
},
|
| 1752 |
{
|
| 1753 |
"epoch": 2.1633085896076354,
|
| 1754 |
+
"grad_norm": 1.3997256755828857,
|
| 1755 |
"learning_rate": 1.3944856839872746e-05,
|
| 1756 |
+
"loss": 0.2548,
|
| 1757 |
"step": 2040
|
| 1758 |
},
|
| 1759 |
{
|
| 1760 |
"epoch": 2.1739130434782608,
|
| 1761 |
+
"grad_norm": 1.5165802240371704,
|
| 1762 |
"learning_rate": 1.3768115942028985e-05,
|
| 1763 |
+
"loss": 0.2537,
|
| 1764 |
"step": 2050
|
| 1765 |
},
|
| 1766 |
{
|
| 1767 |
"epoch": 2.1739130434782608,
|
| 1768 |
+
"eval_loss": 0.6767822504043579,
|
| 1769 |
+
"eval_runtime": 11.8499,
|
| 1770 |
+
"eval_samples_per_second": 40.507,
|
| 1771 |
+
"eval_steps_per_second": 2.532,
|
| 1772 |
"step": 2050
|
| 1773 |
},
|
| 1774 |
{
|
| 1775 |
"epoch": 2.1845174973488866,
|
| 1776 |
+
"grad_norm": 1.3862613439559937,
|
| 1777 |
"learning_rate": 1.3591375044185226e-05,
|
| 1778 |
+
"loss": 0.2493,
|
| 1779 |
"step": 2060
|
| 1780 |
},
|
| 1781 |
{
|
| 1782 |
"epoch": 2.1951219512195124,
|
| 1783 |
+
"grad_norm": 1.4445819854736328,
|
| 1784 |
"learning_rate": 1.3414634146341466e-05,
|
| 1785 |
+
"loss": 0.2534,
|
| 1786 |
"step": 2070
|
| 1787 |
},
|
| 1788 |
{
|
| 1789 |
"epoch": 2.2057264050901377,
|
| 1790 |
+
"grad_norm": 1.5333936214447021,
|
| 1791 |
"learning_rate": 1.3237893248497705e-05,
|
| 1792 |
+
"loss": 0.2493,
|
| 1793 |
"step": 2080
|
| 1794 |
},
|
| 1795 |
{
|
| 1796 |
"epoch": 2.2163308589607635,
|
| 1797 |
+
"grad_norm": 1.4717518091201782,
|
| 1798 |
"learning_rate": 1.306115235065394e-05,
|
| 1799 |
+
"loss": 0.241,
|
| 1800 |
"step": 2090
|
| 1801 |
},
|
| 1802 |
{
|
| 1803 |
"epoch": 2.2269353128313893,
|
| 1804 |
+
"grad_norm": 1.283262014389038,
|
| 1805 |
"learning_rate": 1.288441145281018e-05,
|
| 1806 |
+
"loss": 0.2453,
|
| 1807 |
"step": 2100
|
| 1808 |
},
|
| 1809 |
{
|
| 1810 |
"epoch": 2.2269353128313893,
|
| 1811 |
+
"eval_loss": 0.6884390711784363,
|
| 1812 |
+
"eval_runtime": 11.8363,
|
| 1813 |
+
"eval_samples_per_second": 40.553,
|
| 1814 |
+
"eval_steps_per_second": 2.535,
|
| 1815 |
"step": 2100
|
| 1816 |
},
|
| 1817 |
{
|
| 1818 |
"epoch": 2.2375397667020147,
|
| 1819 |
+
"grad_norm": 1.6603565216064453,
|
| 1820 |
"learning_rate": 1.2707670554966419e-05,
|
| 1821 |
+
"loss": 0.2507,
|
| 1822 |
"step": 2110
|
| 1823 |
},
|
| 1824 |
{
|
| 1825 |
"epoch": 2.2481442205726405,
|
| 1826 |
+
"grad_norm": 1.7477449178695679,
|
| 1827 |
"learning_rate": 1.2530929657122658e-05,
|
| 1828 |
+
"loss": 0.2532,
|
| 1829 |
"step": 2120
|
| 1830 |
},
|
| 1831 |
{
|
| 1832 |
"epoch": 2.2587486744432663,
|
| 1833 |
+
"grad_norm": 1.550327181816101,
|
| 1834 |
"learning_rate": 1.2354188759278897e-05,
|
| 1835 |
+
"loss": 0.245,
|
| 1836 |
"step": 2130
|
| 1837 |
},
|
| 1838 |
{
|
| 1839 |
"epoch": 2.2693531283138917,
|
| 1840 |
+
"grad_norm": 1.5506653785705566,
|
| 1841 |
"learning_rate": 1.2177447861435136e-05,
|
| 1842 |
+
"loss": 0.2554,
|
| 1843 |
"step": 2140
|
| 1844 |
},
|
| 1845 |
{
|
| 1846 |
"epoch": 2.2799575821845175,
|
| 1847 |
+
"grad_norm": 1.5938143730163574,
|
| 1848 |
"learning_rate": 1.2000706963591376e-05,
|
| 1849 |
+
"loss": 0.2394,
|
| 1850 |
"step": 2150
|
| 1851 |
},
|
| 1852 |
{
|
| 1853 |
"epoch": 2.2799575821845175,
|
| 1854 |
+
"eval_loss": 0.6921836137771606,
|
| 1855 |
+
"eval_runtime": 11.8108,
|
| 1856 |
+
"eval_samples_per_second": 40.641,
|
| 1857 |
+
"eval_steps_per_second": 2.54,
|
| 1858 |
"step": 2150
|
| 1859 |
},
|
| 1860 |
{
|
| 1861 |
"epoch": 2.2905620360551433,
|
| 1862 |
+
"grad_norm": 1.5572457313537598,
|
| 1863 |
"learning_rate": 1.1823966065747615e-05,
|
| 1864 |
+
"loss": 0.2459,
|
| 1865 |
"step": 2160
|
| 1866 |
},
|
| 1867 |
{
|
| 1868 |
"epoch": 2.3011664899257687,
|
| 1869 |
+
"grad_norm": 1.599342703819275,
|
| 1870 |
"learning_rate": 1.1647225167903854e-05,
|
| 1871 |
+
"loss": 0.2417,
|
| 1872 |
"step": 2170
|
| 1873 |
},
|
| 1874 |
{
|
| 1875 |
"epoch": 2.3117709437963945,
|
| 1876 |
+
"grad_norm": 1.6454466581344604,
|
| 1877 |
"learning_rate": 1.1470484270060093e-05,
|
| 1878 |
+
"loss": 0.2534,
|
| 1879 |
"step": 2180
|
| 1880 |
},
|
| 1881 |
{
|
| 1882 |
"epoch": 2.3223753976670203,
|
| 1883 |
+
"grad_norm": 1.6182328462600708,
|
| 1884 |
"learning_rate": 1.129374337221633e-05,
|
| 1885 |
+
"loss": 0.2514,
|
| 1886 |
"step": 2190
|
| 1887 |
},
|
| 1888 |
{
|
| 1889 |
"epoch": 2.3329798515376456,
|
| 1890 |
+
"grad_norm": 1.4395092725753784,
|
| 1891 |
"learning_rate": 1.111700247437257e-05,
|
| 1892 |
+
"loss": 0.2436,
|
| 1893 |
"step": 2200
|
| 1894 |
},
|
| 1895 |
{
|
| 1896 |
"epoch": 2.3329798515376456,
|
| 1897 |
+
"eval_loss": 0.6941162347793579,
|
| 1898 |
+
"eval_runtime": 11.8078,
|
| 1899 |
+
"eval_samples_per_second": 40.651,
|
| 1900 |
+
"eval_steps_per_second": 2.541,
|
| 1901 |
"step": 2200
|
| 1902 |
},
|
| 1903 |
{
|
| 1904 |
"epoch": 2.3435843054082715,
|
| 1905 |
+
"grad_norm": 1.5516870021820068,
|
| 1906 |
"learning_rate": 1.0940261576528809e-05,
|
| 1907 |
+
"loss": 0.2408,
|
| 1908 |
"step": 2210
|
| 1909 |
},
|
| 1910 |
{
|
| 1911 |
"epoch": 2.3541887592788973,
|
| 1912 |
+
"grad_norm": 1.5500649213790894,
|
| 1913 |
"learning_rate": 1.0763520678685048e-05,
|
| 1914 |
+
"loss": 0.2491,
|
| 1915 |
"step": 2220
|
| 1916 |
},
|
| 1917 |
{
|
| 1918 |
"epoch": 2.3647932131495226,
|
| 1919 |
+
"grad_norm": 1.6337305307388306,
|
| 1920 |
"learning_rate": 1.0586779780841287e-05,
|
| 1921 |
+
"loss": 0.2434,
|
| 1922 |
"step": 2230
|
| 1923 |
},
|
| 1924 |
{
|
| 1925 |
"epoch": 2.3753976670201484,
|
| 1926 |
+
"grad_norm": 1.5644317865371704,
|
| 1927 |
"learning_rate": 1.0410038882997527e-05,
|
| 1928 |
+
"loss": 0.2399,
|
| 1929 |
"step": 2240
|
| 1930 |
},
|
| 1931 |
{
|
| 1932 |
"epoch": 2.3860021208907742,
|
| 1933 |
+
"grad_norm": 1.5931962728500366,
|
| 1934 |
"learning_rate": 1.0233297985153766e-05,
|
| 1935 |
+
"loss": 0.2473,
|
| 1936 |
"step": 2250
|
| 1937 |
},
|
| 1938 |
{
|
| 1939 |
"epoch": 2.3860021208907742,
|
| 1940 |
+
"eval_loss": 0.6962980628013611,
|
| 1941 |
+
"eval_runtime": 11.8143,
|
| 1942 |
+
"eval_samples_per_second": 40.629,
|
| 1943 |
+
"eval_steps_per_second": 2.539,
|
| 1944 |
"step": 2250
|
| 1945 |
},
|
| 1946 |
{
|
| 1947 |
"epoch": 2.3966065747613996,
|
| 1948 |
+
"grad_norm": 1.647518515586853,
|
| 1949 |
"learning_rate": 1.0056557087310003e-05,
|
| 1950 |
"loss": 0.2502,
|
| 1951 |
"step": 2260
|
| 1952 |
},
|
| 1953 |
{
|
| 1954 |
"epoch": 2.4072110286320254,
|
| 1955 |
+
"grad_norm": 1.7184380292892456,
|
| 1956 |
"learning_rate": 9.879816189466243e-06,
|
| 1957 |
+
"loss": 0.2461,
|
| 1958 |
"step": 2270
|
| 1959 |
},
|
| 1960 |
{
|
| 1961 |
"epoch": 2.417815482502651,
|
| 1962 |
+
"grad_norm": 1.454825520515442,
|
| 1963 |
"learning_rate": 9.703075291622482e-06,
|
| 1964 |
+
"loss": 0.2431,
|
| 1965 |
"step": 2280
|
| 1966 |
},
|
| 1967 |
{
|
| 1968 |
"epoch": 2.4284199363732766,
|
| 1969 |
+
"grad_norm": 1.6276512145996094,
|
| 1970 |
"learning_rate": 9.526334393778721e-06,
|
| 1971 |
+
"loss": 0.2467,
|
| 1972 |
"step": 2290
|
| 1973 |
},
|
| 1974 |
{
|
| 1975 |
"epoch": 2.4390243902439024,
|
| 1976 |
+
"grad_norm": 1.8010088205337524,
|
| 1977 |
"learning_rate": 9.34959349593496e-06,
|
| 1978 |
+
"loss": 0.252,
|
| 1979 |
"step": 2300
|
| 1980 |
},
|
| 1981 |
{
|
| 1982 |
"epoch": 2.4390243902439024,
|
| 1983 |
+
"eval_loss": 0.6980859637260437,
|
| 1984 |
+
"eval_runtime": 11.8237,
|
| 1985 |
+
"eval_samples_per_second": 40.596,
|
| 1986 |
+
"eval_steps_per_second": 2.537,
|
| 1987 |
"step": 2300
|
| 1988 |
},
|
| 1989 |
{
|
| 1990 |
"epoch": 2.449628844114528,
|
| 1991 |
+
"grad_norm": 1.5857385396957397,
|
| 1992 |
"learning_rate": 9.1728525980912e-06,
|
| 1993 |
+
"loss": 0.2317,
|
| 1994 |
"step": 2310
|
| 1995 |
},
|
| 1996 |
{
|
| 1997 |
"epoch": 2.4602332979851536,
|
| 1998 |
+
"grad_norm": 1.5389740467071533,
|
| 1999 |
"learning_rate": 8.996111700247438e-06,
|
| 2000 |
+
"loss": 0.2383,
|
| 2001 |
"step": 2320
|
| 2002 |
},
|
| 2003 |
{
|
| 2004 |
"epoch": 2.4708377518557794,
|
| 2005 |
+
"grad_norm": 1.6511685848236084,
|
| 2006 |
"learning_rate": 8.819370802403678e-06,
|
| 2007 |
+
"loss": 0.249,
|
| 2008 |
"step": 2330
|
| 2009 |
},
|
| 2010 |
{
|
| 2011 |
"epoch": 2.481442205726405,
|
| 2012 |
+
"grad_norm": 1.39755380153656,
|
| 2013 |
"learning_rate": 8.642629904559915e-06,
|
| 2014 |
+
"loss": 0.2444,
|
| 2015 |
"step": 2340
|
| 2016 |
},
|
| 2017 |
{
|
| 2018 |
"epoch": 2.4920466595970305,
|
| 2019 |
+
"grad_norm": 1.8113447427749634,
|
| 2020 |
"learning_rate": 8.465889006716154e-06,
|
| 2021 |
+
"loss": 0.2459,
|
| 2022 |
"step": 2350
|
| 2023 |
},
|
| 2024 |
{
|
| 2025 |
"epoch": 2.4920466595970305,
|
| 2026 |
+
"eval_loss": 0.7015708684921265,
|
| 2027 |
+
"eval_runtime": 11.8632,
|
| 2028 |
+
"eval_samples_per_second": 40.461,
|
| 2029 |
+
"eval_steps_per_second": 2.529,
|
| 2030 |
"step": 2350
|
| 2031 |
},
|
| 2032 |
{
|
| 2033 |
"epoch": 2.5026511134676563,
|
| 2034 |
+
"grad_norm": 1.5711174011230469,
|
| 2035 |
"learning_rate": 8.289148108872394e-06,
|
| 2036 |
+
"loss": 0.2471,
|
| 2037 |
"step": 2360
|
| 2038 |
},
|
| 2039 |
{
|
| 2040 |
"epoch": 2.513255567338282,
|
| 2041 |
+
"grad_norm": 1.645478367805481,
|
| 2042 |
"learning_rate": 8.112407211028633e-06,
|
| 2043 |
+
"loss": 0.2283,
|
| 2044 |
"step": 2370
|
| 2045 |
},
|
| 2046 |
{
|
| 2047 |
"epoch": 2.5238600212089075,
|
| 2048 |
+
"grad_norm": 1.8282196521759033,
|
| 2049 |
"learning_rate": 7.93566631318487e-06,
|
| 2050 |
+
"loss": 0.2374,
|
| 2051 |
"step": 2380
|
| 2052 |
},
|
| 2053 |
{
|
| 2054 |
"epoch": 2.5344644750795333,
|
| 2055 |
+
"grad_norm": 1.5373826026916504,
|
| 2056 |
"learning_rate": 7.758925415341111e-06,
|
| 2057 |
+
"loss": 0.2355,
|
| 2058 |
"step": 2390
|
| 2059 |
},
|
| 2060 |
{
|
| 2061 |
"epoch": 2.545068928950159,
|
| 2062 |
+
"grad_norm": 1.6934796571731567,
|
| 2063 |
"learning_rate": 7.5821845174973494e-06,
|
| 2064 |
+
"loss": 0.2431,
|
| 2065 |
"step": 2400
|
| 2066 |
},
|
| 2067 |
{
|
| 2068 |
"epoch": 2.545068928950159,
|
| 2069 |
+
"eval_loss": 0.7114112973213196,
|
| 2070 |
+
"eval_runtime": 11.8571,
|
| 2071 |
+
"eval_samples_per_second": 40.482,
|
| 2072 |
+
"eval_steps_per_second": 2.53,
|
| 2073 |
"step": 2400
|
| 2074 |
},
|
| 2075 |
{
|
| 2076 |
"epoch": 2.5556733828207845,
|
| 2077 |
+
"grad_norm": 1.4827890396118164,
|
| 2078 |
"learning_rate": 7.405443619653588e-06,
|
| 2079 |
+
"loss": 0.2352,
|
| 2080 |
"step": 2410
|
| 2081 |
},
|
| 2082 |
{
|
| 2083 |
"epoch": 2.5662778366914103,
|
| 2084 |
+
"grad_norm": 1.5535013675689697,
|
| 2085 |
"learning_rate": 7.228702721809827e-06,
|
| 2086 |
+
"loss": 0.2432,
|
| 2087 |
"step": 2420
|
| 2088 |
},
|
| 2089 |
{
|
| 2090 |
"epoch": 2.576882290562036,
|
| 2091 |
+
"grad_norm": 1.649556040763855,
|
| 2092 |
"learning_rate": 7.051961823966066e-06,
|
| 2093 |
+
"loss": 0.2422,
|
| 2094 |
"step": 2430
|
| 2095 |
},
|
| 2096 |
{
|
| 2097 |
"epoch": 2.5874867444326615,
|
| 2098 |
+
"grad_norm": 1.601514458656311,
|
| 2099 |
"learning_rate": 6.875220926122305e-06,
|
| 2100 |
+
"loss": 0.2301,
|
| 2101 |
"step": 2440
|
| 2102 |
},
|
| 2103 |
{
|
| 2104 |
"epoch": 2.5980911983032873,
|
| 2105 |
+
"grad_norm": 1.6807202100753784,
|
| 2106 |
"learning_rate": 6.698480028278544e-06,
|
| 2107 |
+
"loss": 0.2411,
|
| 2108 |
"step": 2450
|
| 2109 |
},
|
| 2110 |
{
|
| 2111 |
"epoch": 2.5980911983032873,
|
| 2112 |
+
"eval_loss": 0.7091912031173706,
|
| 2113 |
+
"eval_runtime": 11.8496,
|
| 2114 |
+
"eval_samples_per_second": 40.508,
|
| 2115 |
+
"eval_steps_per_second": 2.532,
|
| 2116 |
"step": 2450
|
| 2117 |
},
|
| 2118 |
{
|
| 2119 |
"epoch": 2.608695652173913,
|
| 2120 |
+
"grad_norm": 1.8097494840621948,
|
| 2121 |
"learning_rate": 6.521739130434783e-06,
|
| 2122 |
+
"loss": 0.2445,
|
| 2123 |
"step": 2460
|
| 2124 |
},
|
| 2125 |
{
|
| 2126 |
"epoch": 2.6193001060445384,
|
| 2127 |
+
"grad_norm": 1.789638638496399,
|
| 2128 |
"learning_rate": 6.344998232591022e-06,
|
| 2129 |
+
"loss": 0.2333,
|
| 2130 |
"step": 2470
|
| 2131 |
},
|
| 2132 |
{
|
| 2133 |
"epoch": 2.6299045599151643,
|
| 2134 |
+
"grad_norm": 1.7948154211044312,
|
| 2135 |
"learning_rate": 6.16825733474726e-06,
|
| 2136 |
+
"loss": 0.2373,
|
| 2137 |
"step": 2480
|
| 2138 |
},
|
| 2139 |
{
|
| 2140 |
"epoch": 2.64050901378579,
|
| 2141 |
+
"grad_norm": 1.4801874160766602,
|
| 2142 |
"learning_rate": 5.9915164369035e-06,
|
| 2143 |
+
"loss": 0.241,
|
| 2144 |
"step": 2490
|
| 2145 |
},
|
| 2146 |
{
|
| 2147 |
"epoch": 2.6511134676564154,
|
| 2148 |
+
"grad_norm": 1.6275895833969116,
|
| 2149 |
"learning_rate": 5.814775539059739e-06,
|
| 2150 |
+
"loss": 0.2321,
|
| 2151 |
"step": 2500
|
| 2152 |
},
|
| 2153 |
{
|
| 2154 |
"epoch": 2.6511134676564154,
|
| 2155 |
+
"eval_loss": 0.7164971828460693,
|
| 2156 |
+
"eval_runtime": 11.8672,
|
| 2157 |
+
"eval_samples_per_second": 40.448,
|
| 2158 |
+
"eval_steps_per_second": 2.528,
|
| 2159 |
"step": 2500
|
| 2160 |
},
|
| 2161 |
{
|
| 2162 |
"epoch": 2.6617179215270412,
|
| 2163 |
+
"grad_norm": 1.8132110834121704,
|
| 2164 |
"learning_rate": 5.638034641215978e-06,
|
| 2165 |
+
"loss": 0.2326,
|
| 2166 |
"step": 2510
|
| 2167 |
},
|
| 2168 |
{
|
| 2169 |
"epoch": 2.672322375397667,
|
| 2170 |
+
"grad_norm": 1.6873996257781982,
|
| 2171 |
"learning_rate": 5.461293743372216e-06,
|
| 2172 |
+
"loss": 0.2328,
|
| 2173 |
"step": 2520
|
| 2174 |
},
|
| 2175 |
{
|
| 2176 |
"epoch": 2.682926829268293,
|
| 2177 |
+
"grad_norm": 1.5824168920516968,
|
| 2178 |
"learning_rate": 5.2845528455284555e-06,
|
| 2179 |
+
"loss": 0.2285,
|
| 2180 |
"step": 2530
|
| 2181 |
},
|
| 2182 |
{
|
| 2183 |
"epoch": 2.693531283138918,
|
| 2184 |
+
"grad_norm": 1.958270788192749,
|
| 2185 |
"learning_rate": 5.107811947684695e-06,
|
| 2186 |
+
"loss": 0.2458,
|
| 2187 |
"step": 2540
|
| 2188 |
},
|
| 2189 |
{
|
| 2190 |
"epoch": 2.704135737009544,
|
| 2191 |
+
"grad_norm": 1.6053658723831177,
|
| 2192 |
"learning_rate": 4.931071049840934e-06,
|
| 2193 |
+
"loss": 0.2405,
|
| 2194 |
"step": 2550
|
| 2195 |
},
|
| 2196 |
{
|
| 2197 |
"epoch": 2.704135737009544,
|
| 2198 |
+
"eval_loss": 0.7160138487815857,
|
| 2199 |
+
"eval_runtime": 11.8452,
|
| 2200 |
+
"eval_samples_per_second": 40.523,
|
| 2201 |
+
"eval_steps_per_second": 2.533,
|
| 2202 |
"step": 2550
|
| 2203 |
},
|
| 2204 |
{
|
| 2205 |
"epoch": 2.71474019088017,
|
| 2206 |
+
"grad_norm": 1.6660462617874146,
|
| 2207 |
"learning_rate": 4.754330151997172e-06,
|
| 2208 |
+
"loss": 0.2302,
|
| 2209 |
"step": 2560
|
| 2210 |
},
|
| 2211 |
{
|
| 2212 |
"epoch": 2.725344644750795,
|
| 2213 |
+
"grad_norm": 1.5654237270355225,
|
| 2214 |
"learning_rate": 4.577589254153411e-06,
|
| 2215 |
+
"loss": 0.231,
|
| 2216 |
"step": 2570
|
| 2217 |
},
|
| 2218 |
{
|
| 2219 |
"epoch": 2.735949098621421,
|
| 2220 |
+
"grad_norm": 1.6218655109405518,
|
| 2221 |
"learning_rate": 4.400848356309651e-06,
|
| 2222 |
+
"loss": 0.235,
|
| 2223 |
"step": 2580
|
| 2224 |
},
|
| 2225 |
{
|
| 2226 |
"epoch": 2.746553552492047,
|
| 2227 |
+
"grad_norm": 1.7172789573669434,
|
| 2228 |
"learning_rate": 4.224107458465889e-06,
|
| 2229 |
+
"loss": 0.2331,
|
| 2230 |
"step": 2590
|
| 2231 |
},
|
| 2232 |
{
|
| 2233 |
"epoch": 2.757158006362672,
|
| 2234 |
+
"grad_norm": 1.790114402770996,
|
| 2235 |
"learning_rate": 4.047366560622128e-06,
|
| 2236 |
+
"loss": 0.2319,
|
| 2237 |
"step": 2600
|
| 2238 |
},
|
| 2239 |
{
|
| 2240 |
"epoch": 2.757158006362672,
|
| 2241 |
+
"eval_loss": 0.7233254909515381,
|
| 2242 |
+
"eval_runtime": 11.8311,
|
| 2243 |
+
"eval_samples_per_second": 40.571,
|
| 2244 |
+
"eval_steps_per_second": 2.536,
|
| 2245 |
"step": 2600
|
| 2246 |
},
|
| 2247 |
{
|
| 2248 |
"epoch": 2.767762460233298,
|
| 2249 |
+
"grad_norm": 1.8797370195388794,
|
| 2250 |
"learning_rate": 3.8706256627783665e-06,
|
| 2251 |
+
"loss": 0.2358,
|
| 2252 |
"step": 2610
|
| 2253 |
},
|
| 2254 |
{
|
| 2255 |
"epoch": 2.778366914103924,
|
| 2256 |
+
"grad_norm": 1.4993661642074585,
|
| 2257 |
"learning_rate": 3.693884764934606e-06,
|
| 2258 |
+
"loss": 0.2351,
|
| 2259 |
"step": 2620
|
| 2260 |
},
|
| 2261 |
{
|
| 2262 |
"epoch": 2.7889713679745496,
|
| 2263 |
+
"grad_norm": 1.7096601724624634,
|
| 2264 |
"learning_rate": 3.517143867090845e-06,
|
| 2265 |
+
"loss": 0.2338,
|
| 2266 |
"step": 2630
|
| 2267 |
},
|
| 2268 |
{
|
| 2269 |
"epoch": 2.799575821845175,
|
| 2270 |
+
"grad_norm": 1.462557077407837,
|
| 2271 |
"learning_rate": 3.340402969247084e-06,
|
| 2272 |
+
"loss": 0.2266,
|
| 2273 |
"step": 2640
|
| 2274 |
},
|
| 2275 |
{
|
| 2276 |
"epoch": 2.8101802757158008,
|
| 2277 |
+
"grad_norm": 1.9143799543380737,
|
| 2278 |
"learning_rate": 3.163662071403323e-06,
|
| 2279 |
+
"loss": 0.2342,
|
| 2280 |
"step": 2650
|
| 2281 |
},
|
| 2282 |
{
|
| 2283 |
"epoch": 2.8101802757158008,
|
| 2284 |
+
"eval_loss": 0.7250259518623352,
|
| 2285 |
+
"eval_runtime": 11.8251,
|
| 2286 |
+
"eval_samples_per_second": 40.592,
|
| 2287 |
+
"eval_steps_per_second": 2.537,
|
| 2288 |
"step": 2650
|
| 2289 |
},
|
| 2290 |
{
|
| 2291 |
"epoch": 2.8207847295864266,
|
| 2292 |
+
"grad_norm": 1.7199385166168213,
|
| 2293 |
"learning_rate": 2.9869211735595616e-06,
|
| 2294 |
+
"loss": 0.2397,
|
| 2295 |
"step": 2660
|
| 2296 |
},
|
| 2297 |
{
|
| 2298 |
"epoch": 2.831389183457052,
|
| 2299 |
+
"grad_norm": 1.9071093797683716,
|
| 2300 |
"learning_rate": 2.8101802757158008e-06,
|
| 2301 |
+
"loss": 0.2311,
|
| 2302 |
"step": 2670
|
| 2303 |
},
|
| 2304 |
{
|
| 2305 |
"epoch": 2.8419936373276777,
|
| 2306 |
+
"grad_norm": 1.6095807552337646,
|
| 2307 |
"learning_rate": 2.6334393778720395e-06,
|
| 2308 |
+
"loss": 0.2307,
|
| 2309 |
"step": 2680
|
| 2310 |
},
|
| 2311 |
{
|
| 2312 |
"epoch": 2.8525980911983035,
|
| 2313 |
+
"grad_norm": 1.850538730621338,
|
| 2314 |
"learning_rate": 2.4566984800282787e-06,
|
| 2315 |
+
"loss": 0.2308,
|
| 2316 |
"step": 2690
|
| 2317 |
},
|
| 2318 |
{
|
| 2319 |
"epoch": 2.863202545068929,
|
| 2320 |
+
"grad_norm": 1.5758758783340454,
|
| 2321 |
"learning_rate": 2.2799575821845175e-06,
|
| 2322 |
+
"loss": 0.2325,
|
| 2323 |
"step": 2700
|
| 2324 |
},
|
| 2325 |
{
|
| 2326 |
"epoch": 2.863202545068929,
|
| 2327 |
+
"eval_loss": 0.7233381867408752,
|
| 2328 |
+
"eval_runtime": 11.8214,
|
| 2329 |
+
"eval_samples_per_second": 40.604,
|
| 2330 |
+
"eval_steps_per_second": 2.538,
|
| 2331 |
"step": 2700
|
| 2332 |
},
|
| 2333 |
{
|
| 2334 |
"epoch": 2.8738069989395547,
|
| 2335 |
+
"grad_norm": 1.5955841541290283,
|
| 2336 |
"learning_rate": 2.1032166843407567e-06,
|
| 2337 |
+
"loss": 0.2289,
|
| 2338 |
"step": 2710
|
| 2339 |
},
|
| 2340 |
{
|
| 2341 |
"epoch": 2.8844114528101805,
|
| 2342 |
+
"grad_norm": 1.5036957263946533,
|
| 2343 |
"learning_rate": 1.9264757864969955e-06,
|
| 2344 |
+
"loss": 0.2376,
|
| 2345 |
"step": 2720
|
| 2346 |
},
|
| 2347 |
{
|
| 2348 |
"epoch": 2.895015906680806,
|
| 2349 |
+
"grad_norm": 1.6937369108200073,
|
| 2350 |
"learning_rate": 1.7497348886532344e-06,
|
| 2351 |
+
"loss": 0.232,
|
| 2352 |
"step": 2730
|
| 2353 |
},
|
| 2354 |
{
|
| 2355 |
"epoch": 2.9056203605514317,
|
| 2356 |
+
"grad_norm": 1.6967031955718994,
|
| 2357 |
"learning_rate": 1.5729939908094734e-06,
|
| 2358 |
+
"loss": 0.2291,
|
| 2359 |
"step": 2740
|
| 2360 |
},
|
| 2361 |
{
|
| 2362 |
"epoch": 2.9162248144220575,
|
| 2363 |
+
"grad_norm": 1.6392852067947388,
|
| 2364 |
"learning_rate": 1.3962530929657124e-06,
|
| 2365 |
+
"loss": 0.2303,
|
| 2366 |
"step": 2750
|
| 2367 |
},
|
| 2368 |
{
|
| 2369 |
"epoch": 2.9162248144220575,
|
| 2370 |
+
"eval_loss": 0.7259537577629089,
|
| 2371 |
+
"eval_runtime": 11.8299,
|
| 2372 |
+
"eval_samples_per_second": 40.575,
|
| 2373 |
+
"eval_steps_per_second": 2.536,
|
| 2374 |
"step": 2750
|
| 2375 |
},
|
| 2376 |
{
|
| 2377 |
"epoch": 2.926829268292683,
|
| 2378 |
+
"grad_norm": 1.5716761350631714,
|
| 2379 |
"learning_rate": 1.2195121951219514e-06,
|
| 2380 |
+
"loss": 0.2235,
|
| 2381 |
"step": 2760
|
| 2382 |
},
|
| 2383 |
{
|
| 2384 |
"epoch": 2.9374337221633087,
|
| 2385 |
+
"grad_norm": 1.7131025791168213,
|
| 2386 |
"learning_rate": 1.0427712972781903e-06,
|
| 2387 |
+
"loss": 0.2323,
|
| 2388 |
"step": 2770
|
| 2389 |
},
|
| 2390 |
{
|
| 2391 |
"epoch": 2.9480381760339345,
|
| 2392 |
+
"grad_norm": 1.562341570854187,
|
| 2393 |
"learning_rate": 8.660303994344292e-07,
|
| 2394 |
+
"loss": 0.2299,
|
| 2395 |
"step": 2780
|
| 2396 |
},
|
| 2397 |
{
|
| 2398 |
"epoch": 2.95864262990456,
|
| 2399 |
+
"grad_norm": 1.4186365604400635,
|
| 2400 |
"learning_rate": 6.892895015906681e-07,
|
| 2401 |
+
"loss": 0.2298,
|
| 2402 |
"step": 2790
|
| 2403 |
},
|
| 2404 |
{
|
| 2405 |
"epoch": 2.9692470837751856,
|
| 2406 |
+
"grad_norm": 1.7411495447158813,
|
| 2407 |
"learning_rate": 5.125486037469071e-07,
|
| 2408 |
+
"loss": 0.2263,
|
| 2409 |
"step": 2800
|
| 2410 |
},
|
| 2411 |
{
|
| 2412 |
"epoch": 2.9692470837751856,
|
| 2413 |
+
"eval_loss": 0.7280117869377136,
|
| 2414 |
+
"eval_runtime": 11.8491,
|
| 2415 |
+
"eval_samples_per_second": 40.509,
|
| 2416 |
+
"eval_steps_per_second": 2.532,
|
| 2417 |
"step": 2800
|
| 2418 |
},
|
| 2419 |
{
|
| 2420 |
"epoch": 2.9798515376458115,
|
| 2421 |
+
"grad_norm": 1.5102466344833374,
|
| 2422 |
"learning_rate": 3.35807705903146e-07,
|
| 2423 |
+
"loss": 0.232,
|
| 2424 |
"step": 2810
|
| 2425 |
},
|
| 2426 |
{
|
| 2427 |
"epoch": 2.990455991516437,
|
| 2428 |
+
"grad_norm": 1.566353440284729,
|
| 2429 |
"learning_rate": 1.5906680805938495e-07,
|
| 2430 |
+
"loss": 0.2316,
|
| 2431 |
"step": 2820
|
| 2432 |
}
|
| 2433 |
],
|
checkpoint-2829/training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5880
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:53a8c021c0523ab617f7d132f6e1d21f2075e97fdb7689e840960f38ef5cb15e
|
| 3 |
size 5880
|