Training in progress, step 1000, checkpoint
Browse files- last-checkpoint/model.safetensors +1 -1
- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/rng_state_0.pth +1 -1
- last-checkpoint/rng_state_1.pth +1 -1
- last-checkpoint/rng_state_2.pth +1 -1
- last-checkpoint/rng_state_3.pth +1 -1
- last-checkpoint/rng_state_4.pth +1 -1
- last-checkpoint/rng_state_5.pth +1 -1
- last-checkpoint/rng_state_6.pth +1 -1
- last-checkpoint/rng_state_7.pth +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +341 -1121
- last-checkpoint/training_args.bin +1 -1
last-checkpoint/model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 570000656
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5231f6d9e7ef5468f165a9ddf9eb10aca5d30ad2e63b6ff5faf513d9cb1cdb85
|
| 3 |
size 570000656
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1622091
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4020e46ea6c605bfcefd3b8616c44e4c244991bae8eb63b4be0c8c2da4f8ed63
|
| 3 |
size 1622091
|
last-checkpoint/rng_state_0.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14469
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9005df1db3604719ef2b1f952bcbe6e5795d91eb0bc40df5034fd8db2705365e
|
| 3 |
size 14469
|
last-checkpoint/rng_state_1.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14469
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d608683ffb8e84cf2d336157b612a438455b21c1600a21c17c850a2632c0fedc
|
| 3 |
size 14469
|
last-checkpoint/rng_state_2.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14469
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8042083e4cce93a1000bc15c672459f6a53221e9e39b96887f2517bac83f10ef
|
| 3 |
size 14469
|
last-checkpoint/rng_state_3.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14469
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e58d6d1599b3abb1a8cdce2f14fd9c1c4addaa2af7376feba879df9dae37078b
|
| 3 |
size 14469
|
last-checkpoint/rng_state_4.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14469
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:407b22baf13dac6bcd1015b1df28b2dd3a3c97fbede2f76998def32b5e905567
|
| 3 |
size 14469
|
last-checkpoint/rng_state_5.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14469
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:071373895eb00df0c26cc9e3d11eb09f6b8857b9b793650d36134b166517b58a
|
| 3 |
size 14469
|
last-checkpoint/rng_state_6.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14469
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:35d119cff383a6da3658fd22867e623b9344c15dbe5f28858bcd429d9f0c2ca3
|
| 3 |
size 14469
|
last-checkpoint/rng_state_7.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14469
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ba1de290ddd3fc1c66aa674896665299ba7c226ec725195539df4670b870604d
|
| 3 |
size 14469
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1465
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:899ab97511d0e21be97a2d87a9698c3d8bea9c4b76df29fbfa02ea0530b878e3
|
| 3 |
size 1465
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -2,1572 +2,792 @@
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
-
"epoch": 0.
|
| 6 |
"eval_steps": 100,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": false,
|
| 10 |
"is_world_process_zero": true,
|
| 11 |
"log_history": [
|
| 12 |
{
|
| 13 |
"epoch": 0.0009090909090909091,
|
| 14 |
-
"grad_norm":
|
| 15 |
-
"learning_rate": 9.999983482695944e-
|
| 16 |
-
"loss": 31.
|
| 17 |
"step": 10
|
| 18 |
},
|
| 19 |
{
|
| 20 |
"epoch": 0.0018181818181818182,
|
| 21 |
-
"grad_norm":
|
| 22 |
-
"learning_rate": 9.
|
| 23 |
-
"loss":
|
| 24 |
"step": 20
|
| 25 |
},
|
| 26 |
{
|
| 27 |
"epoch": 0.0027272727272727275,
|
| 28 |
-
"grad_norm":
|
| 29 |
-
"learning_rate": 9.
|
| 30 |
-
"loss": 31.
|
| 31 |
"step": 30
|
| 32 |
},
|
| 33 |
{
|
| 34 |
"epoch": 0.0036363636363636364,
|
| 35 |
-
"grad_norm":
|
| 36 |
-
"learning_rate": 9.
|
| 37 |
-
"loss": 31.
|
| 38 |
"step": 40
|
| 39 |
},
|
| 40 |
{
|
| 41 |
"epoch": 0.004545454545454545,
|
| 42 |
-
"grad_norm":
|
| 43 |
-
"learning_rate": 9.999510402201835e-
|
| 44 |
-
"loss": 31.
|
| 45 |
"step": 50
|
| 46 |
},
|
| 47 |
{
|
| 48 |
"epoch": 0.005454545454545455,
|
| 49 |
-
"grad_norm":
|
| 50 |
-
"learning_rate": 9.99929018016486e-
|
| 51 |
-
"loss": 31.
|
| 52 |
"step": 60
|
| 53 |
},
|
| 54 |
{
|
| 55 |
"epoch": 0.006363636363636364,
|
| 56 |
-
"grad_norm":
|
| 57 |
-
"learning_rate": 9.
|
| 58 |
-
"loss": 31.
|
| 59 |
"step": 70
|
| 60 |
},
|
| 61 |
{
|
| 62 |
"epoch": 0.007272727272727273,
|
| 63 |
-
"grad_norm":
|
| 64 |
-
"learning_rate": 9.
|
| 65 |
-
"loss": 31.
|
| 66 |
"step": 80
|
| 67 |
},
|
| 68 |
{
|
| 69 |
"epoch": 0.008181818181818182,
|
| 70 |
-
"grad_norm":
|
| 71 |
-
"learning_rate": 9.
|
| 72 |
-
"loss": 31.
|
| 73 |
"step": 90
|
| 74 |
},
|
| 75 |
{
|
| 76 |
"epoch": 0.00909090909090909,
|
| 77 |
-
"grad_norm":
|
| 78 |
-
"learning_rate": 9.
|
| 79 |
-
"loss": 31.
|
| 80 |
"step": 100
|
| 81 |
},
|
| 82 |
{
|
| 83 |
"epoch": 0.00909090909090909,
|
| 84 |
-
"eval_loss":
|
| 85 |
-
"eval_runtime": 22.
|
| 86 |
"eval_samples_per_second": 0.179,
|
| 87 |
"eval_steps_per_second": 0.045,
|
| 88 |
"step": 100
|
| 89 |
},
|
| 90 |
{
|
| 91 |
"epoch": 0.01,
|
| 92 |
-
"grad_norm":
|
| 93 |
-
"learning_rate": 9.
|
| 94 |
-
"loss": 31.
|
| 95 |
"step": 110
|
| 96 |
},
|
| 97 |
{
|
| 98 |
"epoch": 0.01090909090909091,
|
| 99 |
-
"grad_norm":
|
| 100 |
-
"learning_rate": 9.
|
| 101 |
-
"loss": 31.
|
| 102 |
"step": 120
|
| 103 |
},
|
| 104 |
{
|
| 105 |
"epoch": 0.011818181818181818,
|
| 106 |
-
"grad_norm":
|
| 107 |
-
"learning_rate": 9.
|
| 108 |
-
"loss":
|
| 109 |
"step": 130
|
| 110 |
},
|
| 111 |
{
|
| 112 |
"epoch": 0.012727272727272728,
|
| 113 |
-
"grad_norm":
|
| 114 |
-
"learning_rate": 9.
|
| 115 |
-
"loss": 31.
|
| 116 |
"step": 140
|
| 117 |
},
|
| 118 |
{
|
| 119 |
"epoch": 0.013636363636363636,
|
| 120 |
-
"grad_norm":
|
| 121 |
-
"learning_rate": 9.
|
| 122 |
-
"loss": 31.
|
| 123 |
"step": 150
|
| 124 |
},
|
| 125 |
{
|
| 126 |
"epoch": 0.014545454545454545,
|
| 127 |
-
"grad_norm":
|
| 128 |
-
"learning_rate": 9.
|
| 129 |
-
"loss":
|
| 130 |
"step": 160
|
| 131 |
},
|
| 132 |
{
|
| 133 |
"epoch": 0.015454545454545455,
|
| 134 |
-
"grad_norm":
|
| 135 |
-
"learning_rate": 9.
|
| 136 |
-
"loss":
|
| 137 |
"step": 170
|
| 138 |
},
|
| 139 |
{
|
| 140 |
"epoch": 0.016363636363636365,
|
| 141 |
-
"grad_norm":
|
| 142 |
-
"learning_rate": 9.
|
| 143 |
-
"loss": 31.
|
| 144 |
"step": 180
|
| 145 |
},
|
| 146 |
{
|
| 147 |
"epoch": 0.017272727272727273,
|
| 148 |
-
"grad_norm":
|
| 149 |
-
"learning_rate": 9.992717633349635e-
|
| 150 |
-
"loss": 31.
|
| 151 |
"step": 190
|
| 152 |
},
|
| 153 |
{
|
| 154 |
"epoch": 0.01818181818181818,
|
| 155 |
-
"grad_norm":
|
| 156 |
-
"learning_rate": 9.
|
| 157 |
-
"loss":
|
| 158 |
"step": 200
|
| 159 |
},
|
| 160 |
{
|
| 161 |
"epoch": 0.01818181818181818,
|
| 162 |
-
"eval_loss":
|
| 163 |
-
"eval_runtime": 2.
|
| 164 |
-
"eval_samples_per_second": 1.
|
| 165 |
-
"eval_steps_per_second": 0.
|
| 166 |
"step": 200
|
| 167 |
},
|
| 168 |
{
|
| 169 |
"epoch": 0.019090909090909092,
|
| 170 |
-
"grad_norm":
|
| 171 |
-
"learning_rate": 9.
|
| 172 |
-
"loss": 31.
|
| 173 |
"step": 210
|
| 174 |
},
|
| 175 |
{
|
| 176 |
"epoch": 0.02,
|
| 177 |
-
"grad_norm":
|
| 178 |
-
"learning_rate": 9.
|
| 179 |
-
"loss": 31.
|
| 180 |
"step": 220
|
| 181 |
},
|
| 182 |
{
|
| 183 |
"epoch": 0.02090909090909091,
|
| 184 |
-
"grad_norm":
|
| 185 |
-
"learning_rate": 9.
|
| 186 |
-
"loss": 31.
|
| 187 |
"step": 230
|
| 188 |
},
|
| 189 |
{
|
| 190 |
"epoch": 0.02181818181818182,
|
| 191 |
-
"grad_norm":
|
| 192 |
-
"learning_rate": 9.
|
| 193 |
-
"loss":
|
| 194 |
"step": 240
|
| 195 |
},
|
| 196 |
{
|
| 197 |
"epoch": 0.022727272727272728,
|
| 198 |
-
"grad_norm":
|
| 199 |
-
"learning_rate": 9.
|
| 200 |
-
"loss":
|
| 201 |
"step": 250
|
| 202 |
},
|
| 203 |
{
|
| 204 |
"epoch": 0.023636363636363636,
|
| 205 |
-
"grad_norm":
|
| 206 |
-
"learning_rate": 9.
|
| 207 |
-
"loss": 30.
|
| 208 |
"step": 260
|
| 209 |
},
|
| 210 |
{
|
| 211 |
"epoch": 0.024545454545454544,
|
| 212 |
-
"grad_norm":
|
| 213 |
-
"learning_rate": 9.
|
| 214 |
-
"loss":
|
| 215 |
"step": 270
|
| 216 |
},
|
| 217 |
{
|
| 218 |
"epoch": 0.025454545454545455,
|
| 219 |
-
"grad_norm":
|
| 220 |
-
"learning_rate": 9.
|
| 221 |
-
"loss": 31.
|
| 222 |
"step": 280
|
| 223 |
},
|
| 224 |
{
|
| 225 |
"epoch": 0.026363636363636363,
|
| 226 |
-
"grad_norm":
|
| 227 |
-
"learning_rate": 9.
|
| 228 |
-
"loss":
|
| 229 |
"step": 290
|
| 230 |
},
|
| 231 |
{
|
| 232 |
"epoch": 0.02727272727272727,
|
| 233 |
-
"grad_norm":
|
| 234 |
-
"learning_rate": 9.
|
| 235 |
-
"loss": 31.
|
| 236 |
"step": 300
|
| 237 |
},
|
| 238 |
{
|
| 239 |
"epoch": 0.02727272727272727,
|
| 240 |
-
"eval_loss":
|
| 241 |
-
"eval_runtime": 2.
|
| 242 |
-
"eval_samples_per_second": 1.
|
| 243 |
-
"eval_steps_per_second": 0.
|
| 244 |
"step": 300
|
| 245 |
},
|
| 246 |
{
|
| 247 |
"epoch": 0.028181818181818183,
|
| 248 |
-
"grad_norm":
|
| 249 |
-
"learning_rate": 9.
|
| 250 |
-
"loss": 31.
|
| 251 |
"step": 310
|
| 252 |
},
|
| 253 |
{
|
| 254 |
"epoch": 0.02909090909090909,
|
| 255 |
-
"grad_norm":
|
| 256 |
-
"learning_rate": 9.
|
| 257 |
-
"loss":
|
| 258 |
"step": 320
|
| 259 |
},
|
| 260 |
{
|
| 261 |
"epoch": 0.03,
|
| 262 |
-
"grad_norm":
|
| 263 |
-
"learning_rate": 9.
|
| 264 |
-
"loss":
|
| 265 |
"step": 330
|
| 266 |
},
|
| 267 |
{
|
| 268 |
"epoch": 0.03090909090909091,
|
| 269 |
-
"grad_norm":
|
| 270 |
-
"learning_rate": 9.
|
| 271 |
-
"loss": 30.
|
| 272 |
"step": 340
|
| 273 |
},
|
| 274 |
{
|
| 275 |
"epoch": 0.031818181818181815,
|
| 276 |
-
"grad_norm":
|
| 277 |
-
"learning_rate": 9.
|
| 278 |
-
"loss":
|
| 279 |
"step": 350
|
| 280 |
},
|
| 281 |
{
|
| 282 |
"epoch": 0.03272727272727273,
|
| 283 |
-
"grad_norm":
|
| 284 |
-
"learning_rate": 9.
|
| 285 |
-
"loss":
|
| 286 |
"step": 360
|
| 287 |
},
|
| 288 |
{
|
| 289 |
"epoch": 0.03363636363636364,
|
| 290 |
-
"grad_norm":
|
| 291 |
-
"learning_rate": 9.
|
| 292 |
-
"loss":
|
| 293 |
"step": 370
|
| 294 |
},
|
| 295 |
{
|
| 296 |
"epoch": 0.034545454545454546,
|
| 297 |
-
"grad_norm":
|
| 298 |
-
"learning_rate": 9.
|
| 299 |
-
"loss":
|
| 300 |
"step": 380
|
| 301 |
},
|
| 302 |
{
|
| 303 |
"epoch": 0.035454545454545454,
|
| 304 |
-
"grad_norm":
|
| 305 |
-
"learning_rate": 9.969174733517693e-
|
| 306 |
-
"loss":
|
| 307 |
"step": 390
|
| 308 |
},
|
| 309 |
{
|
| 310 |
"epoch": 0.03636363636363636,
|
| 311 |
-
"grad_norm":
|
| 312 |
-
"learning_rate": 9.
|
| 313 |
-
"loss":
|
| 314 |
"step": 400
|
| 315 |
},
|
| 316 |
{
|
| 317 |
"epoch": 0.03636363636363636,
|
| 318 |
-
"eval_loss":
|
| 319 |
-
"eval_runtime": 2.
|
| 320 |
-
"eval_samples_per_second": 1.
|
| 321 |
-
"eval_steps_per_second": 0.
|
| 322 |
"step": 400
|
| 323 |
},
|
| 324 |
{
|
| 325 |
"epoch": 0.03727272727272727,
|
| 326 |
-
"grad_norm":
|
| 327 |
-
"learning_rate": 9.
|
| 328 |
-
"loss":
|
| 329 |
"step": 410
|
| 330 |
},
|
| 331 |
{
|
| 332 |
"epoch": 0.038181818181818185,
|
| 333 |
-
"grad_norm":
|
| 334 |
-
"learning_rate": 9.
|
| 335 |
-
"loss": 31.
|
| 336 |
"step": 420
|
| 337 |
},
|
| 338 |
{
|
| 339 |
"epoch": 0.03909090909090909,
|
| 340 |
-
"grad_norm":
|
| 341 |
-
"learning_rate": 9.96251775373412e-
|
| 342 |
-
"loss": 31.
|
| 343 |
"step": 430
|
| 344 |
},
|
| 345 |
{
|
| 346 |
"epoch": 0.04,
|
| 347 |
-
"grad_norm":
|
| 348 |
-
"learning_rate": 9.
|
| 349 |
-
"loss": 31.
|
| 350 |
"step": 440
|
| 351 |
},
|
| 352 |
{
|
| 353 |
"epoch": 0.04090909090909091,
|
| 354 |
-
"grad_norm":
|
| 355 |
-
"learning_rate": 9.
|
| 356 |
-
"loss": 31.
|
| 357 |
"step": 450
|
| 358 |
},
|
| 359 |
{
|
| 360 |
"epoch": 0.04181818181818182,
|
| 361 |
-
"grad_norm":
|
| 362 |
-
"learning_rate": 9.957099956370761e-
|
| 363 |
-
"loss":
|
| 364 |
"step": 460
|
| 365 |
},
|
| 366 |
{
|
| 367 |
"epoch": 0.042727272727272725,
|
| 368 |
-
"grad_norm":
|
| 369 |
-
"learning_rate": 9.
|
| 370 |
-
"loss": 31.
|
| 371 |
"step": 470
|
| 372 |
},
|
| 373 |
{
|
| 374 |
"epoch": 0.04363636363636364,
|
| 375 |
-
"grad_norm":
|
| 376 |
-
"learning_rate": 9.
|
| 377 |
-
"loss":
|
| 378 |
"step": 480
|
| 379 |
},
|
| 380 |
{
|
| 381 |
"epoch": 0.04454545454545455,
|
| 382 |
-
"grad_norm":
|
| 383 |
-
"learning_rate": 9.
|
| 384 |
-
"loss": 31.
|
| 385 |
"step": 490
|
| 386 |
},
|
| 387 |
{
|
| 388 |
"epoch": 0.045454545454545456,
|
| 389 |
-
"grad_norm":
|
| 390 |
-
"learning_rate": 9.
|
| 391 |
-
"loss": 31.
|
| 392 |
"step": 500
|
| 393 |
},
|
| 394 |
{
|
| 395 |
"epoch": 0.045454545454545456,
|
| 396 |
-
"eval_loss":
|
| 397 |
-
"eval_runtime": 2.
|
| 398 |
-
"eval_samples_per_second": 1.
|
| 399 |
-
"eval_steps_per_second": 0.
|
| 400 |
"step": 500
|
| 401 |
},
|
| 402 |
{
|
| 403 |
"epoch": 0.046363636363636364,
|
| 404 |
-
"grad_norm":
|
| 405 |
-
"learning_rate": 9.
|
| 406 |
-
"loss":
|
| 407 |
"step": 510
|
| 408 |
},
|
| 409 |
{
|
| 410 |
"epoch": 0.04727272727272727,
|
| 411 |
-
"grad_norm":
|
| 412 |
-
"learning_rate": 9.
|
| 413 |
-
"loss": 31.
|
| 414 |
"step": 520
|
| 415 |
},
|
| 416 |
{
|
| 417 |
"epoch": 0.04818181818181818,
|
| 418 |
-
"grad_norm":
|
| 419 |
-
"learning_rate": 9.94304400044953e-
|
| 420 |
-
"loss":
|
| 421 |
"step": 530
|
| 422 |
},
|
| 423 |
{
|
| 424 |
"epoch": 0.04909090909090909,
|
| 425 |
-
"grad_norm":
|
| 426 |
-
"learning_rate": 9.
|
| 427 |
-
"loss": 31.
|
| 428 |
"step": 540
|
| 429 |
},
|
| 430 |
{
|
| 431 |
"epoch": 0.05,
|
| 432 |
-
"grad_norm":
|
| 433 |
-
"learning_rate": 9.
|
| 434 |
-
"loss":
|
| 435 |
"step": 550
|
| 436 |
},
|
| 437 |
{
|
| 438 |
"epoch": 0.05090909090909091,
|
| 439 |
-
"grad_norm":
|
| 440 |
-
"learning_rate": 9.
|
| 441 |
-
"loss": 31.
|
| 442 |
"step": 560
|
| 443 |
},
|
| 444 |
{
|
| 445 |
"epoch": 0.05181818181818182,
|
| 446 |
-
"grad_norm":
|
| 447 |
-
"learning_rate": 9.
|
| 448 |
-
"loss": 31.
|
| 449 |
"step": 570
|
| 450 |
},
|
| 451 |
{
|
| 452 |
"epoch": 0.05272727272727273,
|
| 453 |
-
"grad_norm":
|
| 454 |
-
"learning_rate": 9.
|
| 455 |
-
"loss":
|
| 456 |
"step": 580
|
| 457 |
},
|
| 458 |
{
|
| 459 |
"epoch": 0.053636363636363635,
|
| 460 |
-
"grad_norm":
|
| 461 |
-
"learning_rate": 9.
|
| 462 |
-
"loss":
|
| 463 |
"step": 590
|
| 464 |
},
|
| 465 |
{
|
| 466 |
"epoch": 0.05454545454545454,
|
| 467 |
-
"grad_norm":
|
| 468 |
-
"learning_rate": 9.
|
| 469 |
-
"loss": 31.
|
| 470 |
"step": 600
|
| 471 |
},
|
| 472 |
{
|
| 473 |
"epoch": 0.05454545454545454,
|
| 474 |
-
"eval_loss":
|
| 475 |
-
"eval_runtime": 2.
|
| 476 |
-
"eval_samples_per_second": 1.
|
| 477 |
-
"eval_steps_per_second": 0.
|
| 478 |
"step": 600
|
| 479 |
},
|
| 480 |
{
|
| 481 |
"epoch": 0.05545454545454546,
|
| 482 |
-
"grad_norm":
|
| 483 |
-
"learning_rate": 9.924561360167858e-
|
| 484 |
-
"loss": 30.
|
| 485 |
"step": 610
|
| 486 |
},
|
| 487 |
{
|
| 488 |
"epoch": 0.056363636363636366,
|
| 489 |
-
"grad_norm":
|
| 490 |
-
"learning_rate": 9.
|
| 491 |
-
"loss":
|
| 492 |
"step": 620
|
| 493 |
},
|
| 494 |
{
|
| 495 |
"epoch": 0.057272727272727274,
|
| 496 |
-
"grad_norm":
|
| 497 |
-
"learning_rate": 9.91953862957702e-
|
| 498 |
-
"loss":
|
| 499 |
"step": 630
|
| 500 |
},
|
| 501 |
{
|
| 502 |
"epoch": 0.05818181818181818,
|
| 503 |
-
"grad_norm":
|
| 504 |
-
"learning_rate": 9.
|
| 505 |
-
"loss": 31.
|
| 506 |
"step": 640
|
| 507 |
},
|
| 508 |
{
|
| 509 |
"epoch": 0.05909090909090909,
|
| 510 |
-
"grad_norm":
|
| 511 |
-
"learning_rate": 9.
|
| 512 |
-
"loss": 31.
|
| 513 |
"step": 650
|
| 514 |
},
|
| 515 |
{
|
| 516 |
"epoch": 0.06,
|
| 517 |
-
"grad_norm":
|
| 518 |
-
"learning_rate": 9.91170363322581e-
|
| 519 |
-
"loss": 30.
|
| 520 |
"step": 660
|
| 521 |
},
|
| 522 |
{
|
| 523 |
"epoch": 0.060909090909090906,
|
| 524 |
-
"grad_norm":
|
| 525 |
-
"learning_rate": 9.90901181253448e-
|
| 526 |
-
"loss":
|
| 527 |
"step": 670
|
| 528 |
},
|
| 529 |
{
|
| 530 |
"epoch": 0.06181818181818182,
|
| 531 |
-
"grad_norm":
|
| 532 |
-
"learning_rate": 9.
|
| 533 |
-
"loss": 30.
|
| 534 |
"step": 680
|
| 535 |
},
|
| 536 |
{
|
| 537 |
"epoch": 0.06272727272727273,
|
| 538 |
-
"grad_norm":
|
| 539 |
-
"learning_rate": 9.
|
| 540 |
-
"loss":
|
| 541 |
"step": 690
|
| 542 |
},
|
| 543 |
{
|
| 544 |
"epoch": 0.06363636363636363,
|
| 545 |
-
"grad_norm":
|
| 546 |
-
"learning_rate": 9.
|
| 547 |
-
"loss":
|
| 548 |
"step": 700
|
| 549 |
},
|
| 550 |
{
|
| 551 |
"epoch": 0.06363636363636363,
|
| 552 |
-
"eval_loss":
|
| 553 |
-
"eval_runtime": 2.
|
| 554 |
-
"eval_samples_per_second": 1.
|
| 555 |
-
"eval_steps_per_second": 0.
|
| 556 |
"step": 700
|
| 557 |
},
|
| 558 |
{
|
| 559 |
"epoch": 0.06454545454545454,
|
| 560 |
-
"grad_norm":
|
| 561 |
-
"learning_rate": 9.
|
| 562 |
-
"loss": 30.
|
| 563 |
"step": 710
|
| 564 |
},
|
| 565 |
{
|
| 566 |
"epoch": 0.06545454545454546,
|
| 567 |
-
"grad_norm":
|
| 568 |
-
"learning_rate": 9.
|
| 569 |
-
"loss":
|
| 570 |
"step": 720
|
| 571 |
},
|
| 572 |
{
|
| 573 |
"epoch": 0.06636363636363636,
|
| 574 |
-
"grad_norm":
|
| 575 |
-
"learning_rate": 9.
|
| 576 |
-
"loss":
|
| 577 |
"step": 730
|
| 578 |
},
|
| 579 |
{
|
| 580 |
"epoch": 0.06727272727272728,
|
| 581 |
-
"grad_norm":
|
| 582 |
-
"learning_rate": 9.
|
| 583 |
-
"loss":
|
| 584 |
"step": 740
|
| 585 |
},
|
| 586 |
{
|
| 587 |
"epoch": 0.06818181818181818,
|
| 588 |
-
"grad_norm":
|
| 589 |
-
"learning_rate": 9.
|
| 590 |
-
"loss":
|
| 591 |
"step": 750
|
| 592 |
},
|
| 593 |
{
|
| 594 |
"epoch": 0.06909090909090909,
|
| 595 |
-
"grad_norm":
|
| 596 |
-
"learning_rate": 9.
|
| 597 |
-
"loss": 30.
|
| 598 |
"step": 760
|
| 599 |
},
|
| 600 |
{
|
| 601 |
"epoch": 0.07,
|
| 602 |
-
"grad_norm":
|
| 603 |
-
"learning_rate": 9.
|
| 604 |
-
"loss":
|
| 605 |
"step": 770
|
| 606 |
},
|
| 607 |
{
|
| 608 |
"epoch": 0.07090909090909091,
|
| 609 |
-
"grad_norm":
|
| 610 |
-
"learning_rate": 9.
|
| 611 |
-
"loss":
|
| 612 |
"step": 780
|
| 613 |
},
|
| 614 |
{
|
| 615 |
"epoch": 0.07181818181818182,
|
| 616 |
-
"grad_norm":
|
| 617 |
-
"learning_rate": 9.
|
| 618 |
-
"loss":
|
| 619 |
"step": 790
|
| 620 |
},
|
| 621 |
{
|
| 622 |
"epoch": 0.07272727272727272,
|
| 623 |
-
"grad_norm":
|
| 624 |
-
"learning_rate": 9.
|
| 625 |
-
"loss":
|
| 626 |
"step": 800
|
| 627 |
},
|
| 628 |
{
|
| 629 |
"epoch": 0.07272727272727272,
|
| 630 |
-
"eval_loss":
|
| 631 |
-
"eval_runtime": 2.
|
| 632 |
-
"eval_samples_per_second": 1.
|
| 633 |
-
"eval_steps_per_second": 0.
|
| 634 |
"step": 800
|
| 635 |
},
|
| 636 |
{
|
| 637 |
"epoch": 0.07363636363636364,
|
| 638 |
-
"grad_norm":
|
| 639 |
-
"learning_rate": 9.
|
| 640 |
-
"loss":
|
| 641 |
"step": 810
|
| 642 |
},
|
| 643 |
{
|
| 644 |
"epoch": 0.07454545454545454,
|
| 645 |
-
"grad_norm":
|
| 646 |
-
"learning_rate": 9.863842618016658e-
|
| 647 |
-
"loss":
|
| 648 |
"step": 820
|
| 649 |
},
|
| 650 |
{
|
| 651 |
"epoch": 0.07545454545454545,
|
| 652 |
-
"grad_norm":
|
| 653 |
-
"learning_rate": 9.
|
| 654 |
-
"loss":
|
| 655 |
"step": 830
|
| 656 |
},
|
| 657 |
{
|
| 658 |
"epoch": 0.07636363636363637,
|
| 659 |
-
"grad_norm":
|
| 660 |
-
"learning_rate": 9.857143722169442e-
|
| 661 |
-
"loss":
|
| 662 |
"step": 840
|
| 663 |
},
|
| 664 |
{
|
| 665 |
"epoch": 0.07727272727272727,
|
| 666 |
-
"grad_norm":
|
| 667 |
-
"learning_rate": 9.
|
| 668 |
-
"loss":
|
| 669 |
"step": 850
|
| 670 |
},
|
| 671 |
{
|
| 672 |
"epoch": 0.07818181818181819,
|
| 673 |
-
"grad_norm":
|
| 674 |
-
"learning_rate": 9.
|
| 675 |
-
"loss":
|
| 676 |
"step": 860
|
| 677 |
},
|
| 678 |
{
|
| 679 |
"epoch": 0.07909090909090909,
|
| 680 |
-
"grad_norm":
|
| 681 |
-
"learning_rate": 9.
|
| 682 |
-
"loss":
|
| 683 |
"step": 870
|
| 684 |
},
|
| 685 |
{
|
| 686 |
"epoch": 0.08,
|
| 687 |
-
"grad_norm":
|
| 688 |
-
"learning_rate": 9.
|
| 689 |
-
"loss":
|
| 690 |
"step": 880
|
| 691 |
},
|
| 692 |
{
|
| 693 |
"epoch": 0.0809090909090909,
|
| 694 |
-
"grad_norm":
|
| 695 |
-
"learning_rate": 9.
|
| 696 |
-
"loss":
|
| 697 |
"step": 890
|
| 698 |
},
|
| 699 |
{
|
| 700 |
"epoch": 0.08181818181818182,
|
| 701 |
-
"grad_norm":
|
| 702 |
-
"learning_rate": 9.
|
| 703 |
-
"loss": 30.
|
| 704 |
"step": 900
|
| 705 |
},
|
| 706 |
{
|
| 707 |
"epoch": 0.08181818181818182,
|
| 708 |
-
"eval_loss":
|
| 709 |
-
"eval_runtime": 2.
|
| 710 |
-
"eval_samples_per_second": 1.
|
| 711 |
-
"eval_steps_per_second": 0.
|
| 712 |
"step": 900
|
| 713 |
},
|
| 714 |
{
|
| 715 |
"epoch": 0.08272727272727273,
|
| 716 |
-
"grad_norm":
|
| 717 |
-
"learning_rate": 9.832451096057912e-
|
| 718 |
-
"loss":
|
| 719 |
"step": 910
|
| 720 |
},
|
| 721 |
{
|
| 722 |
"epoch": 0.08363636363636363,
|
| 723 |
-
"grad_norm":
|
| 724 |
-
"learning_rate": 9.
|
| 725 |
-
"loss":
|
| 726 |
"step": 920
|
| 727 |
},
|
| 728 |
{
|
| 729 |
"epoch": 0.08454545454545455,
|
| 730 |
-
"grad_norm":
|
| 731 |
-
"learning_rate": 9.
|
| 732 |
-
"loss":
|
| 733 |
"step": 930
|
| 734 |
},
|
| 735 |
{
|
| 736 |
"epoch": 0.08545454545454545,
|
| 737 |
-
"grad_norm":
|
| 738 |
-
"learning_rate": 9.
|
| 739 |
-
"loss":
|
| 740 |
"step": 940
|
| 741 |
},
|
| 742 |
{
|
| 743 |
"epoch": 0.08636363636363636,
|
| 744 |
-
"grad_norm":
|
| 745 |
-
"learning_rate": 9.
|
| 746 |
-
"loss":
|
| 747 |
"step": 950
|
| 748 |
},
|
| 749 |
{
|
| 750 |
"epoch": 0.08727272727272728,
|
| 751 |
-
"grad_norm":
|
| 752 |
-
"learning_rate": 9.
|
| 753 |
-
"loss":
|
| 754 |
"step": 960
|
| 755 |
},
|
| 756 |
{
|
| 757 |
"epoch": 0.08818181818181818,
|
| 758 |
-
"grad_norm":
|
| 759 |
-
"learning_rate": 9.
|
| 760 |
-
"loss":
|
| 761 |
"step": 970
|
| 762 |
},
|
| 763 |
{
|
| 764 |
"epoch": 0.0890909090909091,
|
| 765 |
-
"grad_norm":
|
| 766 |
-
"learning_rate": 9.
|
| 767 |
-
"loss":
|
| 768 |
"step": 980
|
| 769 |
},
|
| 770 |
{
|
| 771 |
"epoch": 0.09,
|
| 772 |
-
"grad_norm":
|
| 773 |
-
"learning_rate": 9.
|
| 774 |
-
"loss":
|
| 775 |
"step": 990
|
| 776 |
},
|
| 777 |
{
|
| 778 |
"epoch": 0.09090909090909091,
|
| 779 |
-
"grad_norm":
|
| 780 |
-
"learning_rate": 9.
|
| 781 |
-
"loss":
|
| 782 |
"step": 1000
|
| 783 |
},
|
| 784 |
{
|
| 785 |
"epoch": 0.09090909090909091,
|
| 786 |
-
"eval_loss":
|
| 787 |
-
"eval_runtime": 2.
|
| 788 |
-
"eval_samples_per_second": 1.
|
| 789 |
-
"eval_steps_per_second": 0.446,
|
| 790 |
-
"step": 1000
|
| 791 |
-
},
|
| 792 |
-
{
|
| 793 |
-
"epoch": 0.09181818181818181,
|
| 794 |
-
"grad_norm": 4381165223936.0,
|
| 795 |
-
"learning_rate": 9.793828205468903e-06,
|
| 796 |
-
"loss": 30.489773559570313,
|
| 797 |
-
"step": 1010
|
| 798 |
-
},
|
| 799 |
-
{
|
| 800 |
-
"epoch": 0.09272727272727273,
|
| 801 |
-
"grad_norm": 7098638270464.0,
|
| 802 |
-
"learning_rate": 9.789750323596107e-06,
|
| 803 |
-
"loss": 30.310159301757814,
|
| 804 |
-
"step": 1020
|
| 805 |
-
},
|
| 806 |
-
{
|
| 807 |
-
"epoch": 0.09363636363636364,
|
| 808 |
-
"grad_norm": 7115639357440.0,
|
| 809 |
-
"learning_rate": 9.785633373203691e-06,
|
| 810 |
-
"loss": 30.755490112304688,
|
| 811 |
-
"step": 1030
|
| 812 |
-
},
|
| 813 |
-
{
|
| 814 |
-
"epoch": 0.09454545454545454,
|
| 815 |
-
"grad_norm": 5234526519296.0,
|
| 816 |
-
"learning_rate": 9.781477387872353e-06,
|
| 817 |
-
"loss": 30.480865478515625,
|
| 818 |
-
"step": 1040
|
| 819 |
-
},
|
| 820 |
-
{
|
| 821 |
-
"epoch": 0.09545454545454546,
|
| 822 |
-
"grad_norm": 21593254264832.0,
|
| 823 |
-
"learning_rate": 9.777282401501182e-06,
|
| 824 |
-
"loss": 30.507177734375,
|
| 825 |
-
"step": 1050
|
| 826 |
-
},
|
| 827 |
-
{
|
| 828 |
-
"epoch": 0.09636363636363636,
|
| 829 |
-
"grad_norm": 13908608811008.0,
|
| 830 |
-
"learning_rate": 9.773048448307397e-06,
|
| 831 |
-
"loss": 30.405853271484375,
|
| 832 |
-
"step": 1060
|
| 833 |
-
},
|
| 834 |
-
{
|
| 835 |
-
"epoch": 0.09727272727272727,
|
| 836 |
-
"grad_norm": 6315089854464.0,
|
| 837 |
-
"learning_rate": 9.768775562826048e-06,
|
| 838 |
-
"loss": 30.191403198242188,
|
| 839 |
-
"step": 1070
|
| 840 |
-
},
|
| 841 |
-
{
|
| 842 |
-
"epoch": 0.09818181818181818,
|
| 843 |
-
"grad_norm": 5838569734144.0,
|
| 844 |
-
"learning_rate": 9.764463779909748e-06,
|
| 845 |
-
"loss": 29.98668518066406,
|
| 846 |
-
"step": 1080
|
| 847 |
-
},
|
| 848 |
-
{
|
| 849 |
-
"epoch": 0.09909090909090909,
|
| 850 |
-
"grad_norm": 5027172188160.0,
|
| 851 |
-
"learning_rate": 9.760113134728383e-06,
|
| 852 |
-
"loss": 30.168685913085938,
|
| 853 |
-
"step": 1090
|
| 854 |
-
},
|
| 855 |
-
{
|
| 856 |
-
"epoch": 0.1,
|
| 857 |
-
"grad_norm": 6847641681920.0,
|
| 858 |
-
"learning_rate": 9.755723662768829e-06,
|
| 859 |
-
"loss": 30.630303955078126,
|
| 860 |
-
"step": 1100
|
| 861 |
-
},
|
| 862 |
-
{
|
| 863 |
-
"epoch": 0.1,
|
| 864 |
-
"eval_loss": 30.31258773803711,
|
| 865 |
-
"eval_runtime": 2.2676,
|
| 866 |
-
"eval_samples_per_second": 1.764,
|
| 867 |
"eval_steps_per_second": 0.441,
|
| 868 |
-
"step":
|
| 869 |
-
},
|
| 870 |
-
{
|
| 871 |
-
"epoch": 0.1009090909090909,
|
| 872 |
-
"grad_norm": 10138593263616.0,
|
| 873 |
-
"learning_rate": 9.751295399834654e-06,
|
| 874 |
-
"loss": 30.400457763671874,
|
| 875 |
-
"step": 1110
|
| 876 |
-
},
|
| 877 |
-
{
|
| 878 |
-
"epoch": 0.10181818181818182,
|
| 879 |
-
"grad_norm": 1873908596736.0,
|
| 880 |
-
"learning_rate": 9.746828382045843e-06,
|
| 881 |
-
"loss": 30.39214172363281,
|
| 882 |
-
"step": 1120
|
| 883 |
-
},
|
| 884 |
-
{
|
| 885 |
-
"epoch": 0.10272727272727272,
|
| 886 |
-
"grad_norm": 2132046249984.0,
|
| 887 |
-
"learning_rate": 9.742322645838479e-06,
|
| 888 |
-
"loss": 30.495956420898438,
|
| 889 |
-
"step": 1130
|
| 890 |
-
},
|
| 891 |
-
{
|
| 892 |
-
"epoch": 0.10363636363636364,
|
| 893 |
-
"grad_norm": 9749846294528.0,
|
| 894 |
-
"learning_rate": 9.737778227964469e-06,
|
| 895 |
-
"loss": 30.675448608398437,
|
| 896 |
-
"step": 1140
|
| 897 |
-
},
|
| 898 |
-
{
|
| 899 |
-
"epoch": 0.10454545454545454,
|
| 900 |
-
"grad_norm": 2964184629248.0,
|
| 901 |
-
"learning_rate": 9.733195165491229e-06,
|
| 902 |
-
"loss": 30.388763427734375,
|
| 903 |
-
"step": 1150
|
| 904 |
-
},
|
| 905 |
-
{
|
| 906 |
-
"epoch": 0.10545454545454545,
|
| 907 |
-
"grad_norm": 11201202356224.0,
|
| 908 |
-
"learning_rate": 9.728573495801393e-06,
|
| 909 |
-
"loss": 30.802352905273438,
|
| 910 |
-
"step": 1160
|
| 911 |
-
},
|
| 912 |
-
{
|
| 913 |
-
"epoch": 0.10636363636363637,
|
| 914 |
-
"grad_norm": 7261218930688.0,
|
| 915 |
-
"learning_rate": 9.723913256592496e-06,
|
| 916 |
-
"loss": 30.62236328125,
|
| 917 |
-
"step": 1170
|
| 918 |
-
},
|
| 919 |
-
{
|
| 920 |
-
"epoch": 0.10727272727272727,
|
| 921 |
-
"grad_norm": 7669089304576.0,
|
| 922 |
-
"learning_rate": 9.719214485876677e-06,
|
| 923 |
-
"loss": 31.039337158203125,
|
| 924 |
-
"step": 1180
|
| 925 |
-
},
|
| 926 |
-
{
|
| 927 |
-
"epoch": 0.10818181818181818,
|
| 928 |
-
"grad_norm": 3061822259200.0,
|
| 929 |
-
"learning_rate": 9.714477221980361e-06,
|
| 930 |
-
"loss": 30.47221984863281,
|
| 931 |
-
"step": 1190
|
| 932 |
-
},
|
| 933 |
-
{
|
| 934 |
-
"epoch": 0.10909090909090909,
|
| 935 |
-
"grad_norm": 12230697418752.0,
|
| 936 |
-
"learning_rate": 9.709701503543954e-06,
|
| 937 |
-
"loss": 30.745584106445314,
|
| 938 |
-
"step": 1200
|
| 939 |
-
},
|
| 940 |
-
{
|
| 941 |
-
"epoch": 0.10909090909090909,
|
| 942 |
-
"eval_loss": 30.373546600341797,
|
| 943 |
-
"eval_runtime": 2.2361,
|
| 944 |
-
"eval_samples_per_second": 1.789,
|
| 945 |
-
"eval_steps_per_second": 0.447,
|
| 946 |
-
"step": 1200
|
| 947 |
-
},
|
| 948 |
-
{
|
| 949 |
-
"epoch": 0.11,
|
| 950 |
-
"grad_norm": 4175631220736.0,
|
| 951 |
-
"learning_rate": 9.70488736952152e-06,
|
| 952 |
-
"loss": 31.123672485351562,
|
| 953 |
-
"step": 1210
|
| 954 |
-
},
|
| 955 |
-
{
|
| 956 |
-
"epoch": 0.11090909090909092,
|
| 957 |
-
"grad_norm": 3132377268224.0,
|
| 958 |
-
"learning_rate": 9.70003485918047e-06,
|
| 959 |
-
"loss": 30.429144287109374,
|
| 960 |
-
"step": 1220
|
| 961 |
-
},
|
| 962 |
-
{
|
| 963 |
-
"epoch": 0.11181818181818182,
|
| 964 |
-
"grad_norm": 10804191559680.0,
|
| 965 |
-
"learning_rate": 9.695144012101238e-06,
|
| 966 |
-
"loss": 30.479348754882814,
|
| 967 |
-
"step": 1230
|
| 968 |
-
},
|
| 969 |
-
{
|
| 970 |
-
"epoch": 0.11272727272727273,
|
| 971 |
-
"grad_norm": 1749328592896.0,
|
| 972 |
-
"learning_rate": 9.690214868176959e-06,
|
| 973 |
-
"loss": 30.477676391601562,
|
| 974 |
-
"step": 1240
|
| 975 |
-
},
|
| 976 |
-
{
|
| 977 |
-
"epoch": 0.11363636363636363,
|
| 978 |
-
"grad_norm": 11384572084224.0,
|
| 979 |
-
"learning_rate": 9.685247467613141e-06,
|
| 980 |
-
"loss": 31.031317138671874,
|
| 981 |
-
"step": 1250
|
| 982 |
-
},
|
| 983 |
-
{
|
| 984 |
-
"epoch": 0.11454545454545455,
|
| 985 |
-
"grad_norm": 10482409799680.0,
|
| 986 |
-
"learning_rate": 9.680241850927344e-06,
|
| 987 |
-
"loss": 30.4051025390625,
|
| 988 |
-
"step": 1260
|
| 989 |
-
},
|
| 990 |
-
{
|
| 991 |
-
"epoch": 0.11545454545454545,
|
| 992 |
-
"grad_norm": 4815250784256.0,
|
| 993 |
-
"learning_rate": 9.675198058948844e-06,
|
| 994 |
-
"loss": 30.68555603027344,
|
| 995 |
-
"step": 1270
|
| 996 |
-
},
|
| 997 |
-
{
|
| 998 |
-
"epoch": 0.11636363636363636,
|
| 999 |
-
"grad_norm": 15365955387392.0,
|
| 1000 |
-
"learning_rate": 9.670116132818298e-06,
|
| 1001 |
-
"loss": 30.3914306640625,
|
| 1002 |
-
"step": 1280
|
| 1003 |
-
},
|
| 1004 |
-
{
|
| 1005 |
-
"epoch": 0.11727272727272728,
|
| 1006 |
-
"grad_norm": 6781031940096.0,
|
| 1007 |
-
"learning_rate": 9.664996113987415e-06,
|
| 1008 |
-
"loss": 30.56275634765625,
|
| 1009 |
-
"step": 1290
|
| 1010 |
-
},
|
| 1011 |
-
{
|
| 1012 |
-
"epoch": 0.11818181818181818,
|
| 1013 |
-
"grad_norm": 3305072754688.0,
|
| 1014 |
-
"learning_rate": 9.659838044218612e-06,
|
| 1015 |
-
"loss": 30.5663818359375,
|
| 1016 |
-
"step": 1300
|
| 1017 |
-
},
|
| 1018 |
-
{
|
| 1019 |
-
"epoch": 0.11818181818181818,
|
| 1020 |
-
"eval_loss": 30.511932373046875,
|
| 1021 |
-
"eval_runtime": 2.2289,
|
| 1022 |
-
"eval_samples_per_second": 1.795,
|
| 1023 |
-
"eval_steps_per_second": 0.449,
|
| 1024 |
-
"step": 1300
|
| 1025 |
-
},
|
| 1026 |
-
{
|
| 1027 |
-
"epoch": 0.1190909090909091,
|
| 1028 |
-
"grad_norm": 2636002361344.0,
|
| 1029 |
-
"learning_rate": 9.65464196558468e-06,
|
| 1030 |
-
"loss": 31.185601806640626,
|
| 1031 |
-
"step": 1310
|
| 1032 |
-
},
|
| 1033 |
-
{
|
| 1034 |
-
"epoch": 0.12,
|
| 1035 |
-
"grad_norm": 5977038913536.0,
|
| 1036 |
-
"learning_rate": 9.64940792046843e-06,
|
| 1037 |
-
"loss": 30.778460693359374,
|
| 1038 |
-
"step": 1320
|
| 1039 |
-
},
|
| 1040 |
-
{
|
| 1041 |
-
"epoch": 0.12090909090909091,
|
| 1042 |
-
"grad_norm": 8069467078656.0,
|
| 1043 |
-
"learning_rate": 9.64413595156236e-06,
|
| 1044 |
-
"loss": 31.10213623046875,
|
| 1045 |
-
"step": 1330
|
| 1046 |
-
},
|
| 1047 |
-
{
|
| 1048 |
-
"epoch": 0.12181818181818181,
|
| 1049 |
-
"grad_norm": 8260079321088.0,
|
| 1050 |
-
"learning_rate": 9.638826101868297e-06,
|
| 1051 |
-
"loss": 30.64208984375,
|
| 1052 |
-
"step": 1340
|
| 1053 |
-
},
|
| 1054 |
-
{
|
| 1055 |
-
"epoch": 0.12272727272727273,
|
| 1056 |
-
"grad_norm": 1883967979520.0,
|
| 1057 |
-
"learning_rate": 9.633478414697051e-06,
|
| 1058 |
-
"loss": 30.968768310546874,
|
| 1059 |
-
"step": 1350
|
| 1060 |
-
},
|
| 1061 |
-
{
|
| 1062 |
-
"epoch": 0.12363636363636364,
|
| 1063 |
-
"grad_norm": 5390394720256.0,
|
| 1064 |
-
"learning_rate": 9.628092933668062e-06,
|
| 1065 |
-
"loss": 30.793280029296874,
|
| 1066 |
-
"step": 1360
|
| 1067 |
-
},
|
| 1068 |
-
{
|
| 1069 |
-
"epoch": 0.12454545454545454,
|
| 1070 |
-
"grad_norm": 3483799126016.0,
|
| 1071 |
-
"learning_rate": 9.62266970270904e-06,
|
| 1072 |
-
"loss": 31.143099975585937,
|
| 1073 |
-
"step": 1370
|
| 1074 |
-
},
|
| 1075 |
-
{
|
| 1076 |
-
"epoch": 0.12545454545454546,
|
| 1077 |
-
"grad_norm": 5412520198144.0,
|
| 1078 |
-
"learning_rate": 9.617208766055613e-06,
|
| 1079 |
-
"loss": 31.14643249511719,
|
| 1080 |
-
"step": 1380
|
| 1081 |
-
},
|
| 1082 |
-
{
|
| 1083 |
-
"epoch": 0.12636363636363637,
|
| 1084 |
-
"grad_norm": 5890521432064.0,
|
| 1085 |
-
"learning_rate": 9.611710168250961e-06,
|
| 1086 |
-
"loss": 30.540472412109374,
|
| 1087 |
-
"step": 1390
|
| 1088 |
-
},
|
| 1089 |
-
{
|
| 1090 |
-
"epoch": 0.12727272727272726,
|
| 1091 |
-
"grad_norm": 2935032119296.0,
|
| 1092 |
-
"learning_rate": 9.606173954145453e-06,
|
| 1093 |
-
"loss": 30.9363037109375,
|
| 1094 |
-
"step": 1400
|
| 1095 |
-
},
|
| 1096 |
-
{
|
| 1097 |
-
"epoch": 0.12727272727272726,
|
| 1098 |
-
"eval_loss": 30.66790008544922,
|
| 1099 |
-
"eval_runtime": 2.2296,
|
| 1100 |
-
"eval_samples_per_second": 1.794,
|
| 1101 |
-
"eval_steps_per_second": 0.449,
|
| 1102 |
-
"step": 1400
|
| 1103 |
-
},
|
| 1104 |
-
{
|
| 1105 |
-
"epoch": 0.12818181818181817,
|
| 1106 |
-
"grad_norm": 14951601143808.0,
|
| 1107 |
-
"learning_rate": 9.600600168896285e-06,
|
| 1108 |
-
"loss": 31.166165161132813,
|
| 1109 |
-
"step": 1410
|
| 1110 |
-
},
|
| 1111 |
-
{
|
| 1112 |
-
"epoch": 0.1290909090909091,
|
| 1113 |
-
"grad_norm": 18465345765376.0,
|
| 1114 |
-
"learning_rate": 9.594988857967107e-06,
|
| 1115 |
-
"loss": 30.707781982421874,
|
| 1116 |
-
"step": 1420
|
| 1117 |
-
},
|
| 1118 |
-
{
|
| 1119 |
-
"epoch": 0.13,
|
| 1120 |
-
"grad_norm": 11442516393984.0,
|
| 1121 |
-
"learning_rate": 9.589340067127657e-06,
|
| 1122 |
-
"loss": 31.122097778320313,
|
| 1123 |
-
"step": 1430
|
| 1124 |
-
},
|
| 1125 |
-
{
|
| 1126 |
-
"epoch": 0.13090909090909092,
|
| 1127 |
-
"grad_norm": 5658760445952.0,
|
| 1128 |
-
"learning_rate": 9.583653842453385e-06,
|
| 1129 |
-
"loss": 30.8050048828125,
|
| 1130 |
-
"step": 1440
|
| 1131 |
-
},
|
| 1132 |
-
{
|
| 1133 |
-
"epoch": 0.1318181818181818,
|
| 1134 |
-
"grad_norm": 9346052259840.0,
|
| 1135 |
-
"learning_rate": 9.577930230325073e-06,
|
| 1136 |
-
"loss": 31.267306518554687,
|
| 1137 |
-
"step": 1450
|
| 1138 |
-
},
|
| 1139 |
-
{
|
| 1140 |
-
"epoch": 0.13272727272727272,
|
| 1141 |
-
"grad_norm": 17905546690560.0,
|
| 1142 |
-
"learning_rate": 9.572169277428466e-06,
|
| 1143 |
-
"loss": 31.230621337890625,
|
| 1144 |
-
"step": 1460
|
| 1145 |
-
},
|
| 1146 |
-
{
|
| 1147 |
-
"epoch": 0.13363636363636364,
|
| 1148 |
-
"grad_norm": 9790963056640.0,
|
| 1149 |
-
"learning_rate": 9.566371030753882e-06,
|
| 1150 |
-
"loss": 30.92609558105469,
|
| 1151 |
-
"step": 1470
|
| 1152 |
-
},
|
| 1153 |
-
{
|
| 1154 |
-
"epoch": 0.13454545454545455,
|
| 1155 |
-
"grad_norm": 9170735595520.0,
|
| 1156 |
-
"learning_rate": 9.56053553759584e-06,
|
| 1157 |
-
"loss": 31.646261596679686,
|
| 1158 |
-
"step": 1480
|
| 1159 |
-
},
|
| 1160 |
-
{
|
| 1161 |
-
"epoch": 0.13545454545454547,
|
| 1162 |
-
"grad_norm": 22038278307840.0,
|
| 1163 |
-
"learning_rate": 9.554662845552657e-06,
|
| 1164 |
-
"loss": 30.207147216796876,
|
| 1165 |
-
"step": 1490
|
| 1166 |
-
},
|
| 1167 |
-
{
|
| 1168 |
-
"epoch": 0.13636363636363635,
|
| 1169 |
-
"grad_norm": 11540973486080.0,
|
| 1170 |
-
"learning_rate": 9.548753002526076e-06,
|
| 1171 |
-
"loss": 31.0428955078125,
|
| 1172 |
-
"step": 1500
|
| 1173 |
-
},
|
| 1174 |
-
{
|
| 1175 |
-
"epoch": 0.13636363636363635,
|
| 1176 |
-
"eval_loss": 30.903549194335938,
|
| 1177 |
-
"eval_runtime": 2.219,
|
| 1178 |
-
"eval_samples_per_second": 1.803,
|
| 1179 |
-
"eval_steps_per_second": 0.451,
|
| 1180 |
-
"step": 1500
|
| 1181 |
-
},
|
| 1182 |
-
{
|
| 1183 |
-
"epoch": 0.13727272727272727,
|
| 1184 |
-
"grad_norm": 12314027753472.0,
|
| 1185 |
-
"learning_rate": 9.542806056720871e-06,
|
| 1186 |
-
"loss": 31.15526123046875,
|
| 1187 |
-
"step": 1510
|
| 1188 |
-
},
|
| 1189 |
-
{
|
| 1190 |
-
"epoch": 0.13818181818181818,
|
| 1191 |
-
"grad_norm": 15213582614528.0,
|
| 1192 |
-
"learning_rate": 9.536822056644446e-06,
|
| 1193 |
-
"loss": 31.196783447265624,
|
| 1194 |
-
"step": 1520
|
| 1195 |
-
},
|
| 1196 |
-
{
|
| 1197 |
-
"epoch": 0.1390909090909091,
|
| 1198 |
-
"grad_norm": 5029657837568.0,
|
| 1199 |
-
"learning_rate": 9.530801051106449e-06,
|
| 1200 |
-
"loss": 30.717410278320312,
|
| 1201 |
-
"step": 1530
|
| 1202 |
-
},
|
| 1203 |
-
{
|
| 1204 |
-
"epoch": 0.14,
|
| 1205 |
-
"grad_norm": 3814568230912.0,
|
| 1206 |
-
"learning_rate": 9.524743089218371e-06,
|
| 1207 |
-
"loss": 31.505865478515624,
|
| 1208 |
-
"step": 1540
|
| 1209 |
-
},
|
| 1210 |
-
{
|
| 1211 |
-
"epoch": 0.1409090909090909,
|
| 1212 |
-
"grad_norm": 11058694586368.0,
|
| 1213 |
-
"learning_rate": 9.518648220393143e-06,
|
| 1214 |
-
"loss": 31.2138427734375,
|
| 1215 |
-
"step": 1550
|
| 1216 |
-
},
|
| 1217 |
-
{
|
| 1218 |
-
"epoch": 0.14181818181818182,
|
| 1219 |
-
"grad_norm": 16550942736384.0,
|
| 1220 |
-
"learning_rate": 9.512516494344733e-06,
|
| 1221 |
-
"loss": 30.97614440917969,
|
| 1222 |
-
"step": 1560
|
| 1223 |
-
},
|
| 1224 |
-
{
|
| 1225 |
-
"epoch": 0.14272727272727273,
|
| 1226 |
-
"grad_norm": 14170502201344.0,
|
| 1227 |
-
"learning_rate": 9.506347961087746e-06,
|
| 1228 |
-
"loss": 31.417559814453124,
|
| 1229 |
-
"step": 1570
|
| 1230 |
-
},
|
| 1231 |
-
{
|
| 1232 |
-
"epoch": 0.14363636363636365,
|
| 1233 |
-
"grad_norm": 14292605730816.0,
|
| 1234 |
-
"learning_rate": 9.500142670937007e-06,
|
| 1235 |
-
"loss": 31.37445983886719,
|
| 1236 |
-
"step": 1580
|
| 1237 |
-
},
|
| 1238 |
-
{
|
| 1239 |
-
"epoch": 0.14454545454545453,
|
| 1240 |
-
"grad_norm": 19206800146432.0,
|
| 1241 |
-
"learning_rate": 9.49390067450716e-06,
|
| 1242 |
-
"loss": 31.374490356445314,
|
| 1243 |
-
"step": 1590
|
| 1244 |
-
},
|
| 1245 |
-
{
|
| 1246 |
-
"epoch": 0.14545454545454545,
|
| 1247 |
-
"grad_norm": 27451564490752.0,
|
| 1248 |
-
"learning_rate": 9.487622022712249e-06,
|
| 1249 |
-
"loss": 31.736862182617188,
|
| 1250 |
-
"step": 1600
|
| 1251 |
-
},
|
| 1252 |
-
{
|
| 1253 |
-
"epoch": 0.14545454545454545,
|
| 1254 |
-
"eval_loss": 31.390056610107422,
|
| 1255 |
-
"eval_runtime": 2.2392,
|
| 1256 |
-
"eval_samples_per_second": 1.786,
|
| 1257 |
-
"eval_steps_per_second": 0.447,
|
| 1258 |
-
"step": 1600
|
| 1259 |
-
},
|
| 1260 |
-
{
|
| 1261 |
-
"epoch": 0.14636363636363636,
|
| 1262 |
-
"grad_norm": 10258579718144.0,
|
| 1263 |
-
"learning_rate": 9.481306766765305e-06,
|
| 1264 |
-
"loss": 31.774203491210937,
|
| 1265 |
-
"step": 1610
|
| 1266 |
-
},
|
| 1267 |
-
{
|
| 1268 |
-
"epoch": 0.14727272727272728,
|
| 1269 |
-
"grad_norm": 10325241888768.0,
|
| 1270 |
-
"learning_rate": 9.474954958177926e-06,
|
| 1271 |
-
"loss": 31.747982788085938,
|
| 1272 |
-
"step": 1620
|
| 1273 |
-
},
|
| 1274 |
-
{
|
| 1275 |
-
"epoch": 0.1481818181818182,
|
| 1276 |
-
"grad_norm": 13619729268736.0,
|
| 1277 |
-
"learning_rate": 9.468566648759864e-06,
|
| 1278 |
-
"loss": 31.699578857421876,
|
| 1279 |
-
"step": 1630
|
| 1280 |
-
},
|
| 1281 |
-
{
|
| 1282 |
-
"epoch": 0.14909090909090908,
|
| 1283 |
-
"grad_norm": 11932865134592.0,
|
| 1284 |
-
"learning_rate": 9.46214189061859e-06,
|
| 1285 |
-
"loss": 32.11009826660156,
|
| 1286 |
-
"step": 1640
|
| 1287 |
-
},
|
| 1288 |
-
{
|
| 1289 |
-
"epoch": 0.15,
|
| 1290 |
-
"grad_norm": 19572193230848.0,
|
| 1291 |
-
"learning_rate": 9.455680736158881e-06,
|
| 1292 |
-
"loss": 31.782620239257813,
|
| 1293 |
-
"step": 1650
|
| 1294 |
-
},
|
| 1295 |
-
{
|
| 1296 |
-
"epoch": 0.1509090909090909,
|
| 1297 |
-
"grad_norm": 3280040361984.0,
|
| 1298 |
-
"learning_rate": 9.449183238082384e-06,
|
| 1299 |
-
"loss": 31.564590454101562,
|
| 1300 |
-
"step": 1660
|
| 1301 |
-
},
|
| 1302 |
-
{
|
| 1303 |
-
"epoch": 0.15181818181818182,
|
| 1304 |
-
"grad_norm": 7981176979456.0,
|
| 1305 |
-
"learning_rate": 9.442649449387195e-06,
|
| 1306 |
-
"loss": 32.106405639648436,
|
| 1307 |
-
"step": 1670
|
| 1308 |
-
},
|
| 1309 |
-
{
|
| 1310 |
-
"epoch": 0.15272727272727274,
|
| 1311 |
-
"grad_norm": 11420098887680.0,
|
| 1312 |
-
"learning_rate": 9.436079423367413e-06,
|
| 1313 |
-
"loss": 31.888082885742186,
|
| 1314 |
-
"step": 1680
|
| 1315 |
-
},
|
| 1316 |
-
{
|
| 1317 |
-
"epoch": 0.15363636363636363,
|
| 1318 |
-
"grad_norm": 5575196278784.0,
|
| 1319 |
-
"learning_rate": 9.429473213612724e-06,
|
| 1320 |
-
"loss": 32.15013122558594,
|
| 1321 |
-
"step": 1690
|
| 1322 |
-
},
|
| 1323 |
-
{
|
| 1324 |
-
"epoch": 0.15454545454545454,
|
| 1325 |
-
"grad_norm": 14530922938368.0,
|
| 1326 |
-
"learning_rate": 9.422830874007944e-06,
|
| 1327 |
-
"loss": 32.137445068359376,
|
| 1328 |
-
"step": 1700
|
| 1329 |
-
},
|
| 1330 |
-
{
|
| 1331 |
-
"epoch": 0.15454545454545454,
|
| 1332 |
-
"eval_loss": 32.02363586425781,
|
| 1333 |
-
"eval_runtime": 2.2508,
|
| 1334 |
-
"eval_samples_per_second": 1.777,
|
| 1335 |
-
"eval_steps_per_second": 0.444,
|
| 1336 |
-
"step": 1700
|
| 1337 |
-
},
|
| 1338 |
-
{
|
| 1339 |
-
"epoch": 0.15545454545454546,
|
| 1340 |
-
"grad_norm": 3318463332352.0,
|
| 1341 |
-
"learning_rate": 9.416152458732595e-06,
|
| 1342 |
-
"loss": 32.3702392578125,
|
| 1343 |
-
"step": 1710
|
| 1344 |
-
},
|
| 1345 |
-
{
|
| 1346 |
-
"epoch": 0.15636363636363637,
|
| 1347 |
-
"grad_norm": 30810249887744.0,
|
| 1348 |
-
"learning_rate": 9.409438022260457e-06,
|
| 1349 |
-
"loss": 32.926510620117185,
|
| 1350 |
-
"step": 1720
|
| 1351 |
-
},
|
| 1352 |
-
{
|
| 1353 |
-
"epoch": 0.1572727272727273,
|
| 1354 |
-
"grad_norm": 21961272983552.0,
|
| 1355 |
-
"learning_rate": 9.40268761935912e-06,
|
| 1356 |
-
"loss": 32.80148620605469,
|
| 1357 |
-
"step": 1730
|
| 1358 |
-
},
|
| 1359 |
-
{
|
| 1360 |
-
"epoch": 0.15818181818181817,
|
| 1361 |
-
"grad_norm": 7398799966208.0,
|
| 1362 |
-
"learning_rate": 9.395901305089545e-06,
|
| 1363 |
-
"loss": 32.54508666992187,
|
| 1364 |
-
"step": 1740
|
| 1365 |
-
},
|
| 1366 |
-
{
|
| 1367 |
-
"epoch": 0.1590909090909091,
|
| 1368 |
-
"grad_norm": 19706209632256.0,
|
| 1369 |
-
"learning_rate": 9.38907913480561e-06,
|
| 1370 |
-
"loss": 32.26361999511719,
|
| 1371 |
-
"step": 1750
|
| 1372 |
-
},
|
| 1373 |
-
{
|
| 1374 |
-
"epoch": 0.16,
|
| 1375 |
-
"grad_norm": 4903741685760.0,
|
| 1376 |
-
"learning_rate": 9.382221164153656e-06,
|
| 1377 |
-
"loss": 31.852926635742186,
|
| 1378 |
-
"step": 1760
|
| 1379 |
-
},
|
| 1380 |
-
{
|
| 1381 |
-
"epoch": 0.16090909090909092,
|
| 1382 |
-
"grad_norm": 5960596193280.0,
|
| 1383 |
-
"learning_rate": 9.37532744907204e-06,
|
| 1384 |
-
"loss": 32.537167358398435,
|
| 1385 |
-
"step": 1770
|
| 1386 |
-
},
|
| 1387 |
-
{
|
| 1388 |
-
"epoch": 0.1618181818181818,
|
| 1389 |
-
"grad_norm": 20588651347968.0,
|
| 1390 |
-
"learning_rate": 9.368398045790679e-06,
|
| 1391 |
-
"loss": 32.38728332519531,
|
| 1392 |
-
"step": 1780
|
| 1393 |
-
},
|
| 1394 |
-
{
|
| 1395 |
-
"epoch": 0.16272727272727272,
|
| 1396 |
-
"grad_norm": 12039432962048.0,
|
| 1397 |
-
"learning_rate": 9.361433010830578e-06,
|
| 1398 |
-
"loss": 32.65169982910156,
|
| 1399 |
-
"step": 1790
|
| 1400 |
-
},
|
| 1401 |
-
{
|
| 1402 |
-
"epoch": 0.16363636363636364,
|
| 1403 |
-
"grad_norm": 5257930735616.0,
|
| 1404 |
-
"learning_rate": 9.354432401003387e-06,
|
| 1405 |
-
"loss": 33.31449584960937,
|
| 1406 |
-
"step": 1800
|
| 1407 |
-
},
|
| 1408 |
-
{
|
| 1409 |
-
"epoch": 0.16363636363636364,
|
| 1410 |
-
"eval_loss": 32.65924072265625,
|
| 1411 |
-
"eval_runtime": 2.2228,
|
| 1412 |
-
"eval_samples_per_second": 1.8,
|
| 1413 |
-
"eval_steps_per_second": 0.45,
|
| 1414 |
-
"step": 1800
|
| 1415 |
-
},
|
| 1416 |
-
{
|
| 1417 |
-
"epoch": 0.16454545454545455,
|
| 1418 |
-
"grad_norm": 19231353602048.0,
|
| 1419 |
-
"learning_rate": 9.347396273410926e-06,
|
| 1420 |
-
"loss": 32.776092529296875,
|
| 1421 |
-
"step": 1810
|
| 1422 |
-
},
|
| 1423 |
-
{
|
| 1424 |
-
"epoch": 0.16545454545454547,
|
| 1425 |
-
"grad_norm": 16898675703808.0,
|
| 1426 |
-
"learning_rate": 9.340324685444721e-06,
|
| 1427 |
-
"loss": 33.000860595703124,
|
| 1428 |
-
"step": 1820
|
| 1429 |
-
},
|
| 1430 |
-
{
|
| 1431 |
-
"epoch": 0.16636363636363635,
|
| 1432 |
-
"grad_norm": 68008458321920.0,
|
| 1433 |
-
"learning_rate": 9.333217694785543e-06,
|
| 1434 |
-
"loss": 32.81432189941406,
|
| 1435 |
-
"step": 1830
|
| 1436 |
-
},
|
| 1437 |
-
{
|
| 1438 |
-
"epoch": 0.16727272727272727,
|
| 1439 |
-
"grad_norm": 15164053127168.0,
|
| 1440 |
-
"learning_rate": 9.326075359402926e-06,
|
| 1441 |
-
"loss": 33.27540893554688,
|
| 1442 |
-
"step": 1840
|
| 1443 |
-
},
|
| 1444 |
-
{
|
| 1445 |
-
"epoch": 0.16818181818181818,
|
| 1446 |
-
"grad_norm": 22001701879808.0,
|
| 1447 |
-
"learning_rate": 9.3188977375547e-06,
|
| 1448 |
-
"loss": 33.165444946289064,
|
| 1449 |
-
"step": 1850
|
| 1450 |
-
},
|
| 1451 |
-
{
|
| 1452 |
-
"epoch": 0.1690909090909091,
|
| 1453 |
-
"grad_norm": 22931172229120.0,
|
| 1454 |
-
"learning_rate": 9.31168488778652e-06,
|
| 1455 |
-
"loss": 33.036984252929685,
|
| 1456 |
-
"step": 1860
|
| 1457 |
-
},
|
| 1458 |
-
{
|
| 1459 |
-
"epoch": 0.17,
|
| 1460 |
-
"grad_norm": 34937067536384.0,
|
| 1461 |
-
"learning_rate": 9.304436868931384e-06,
|
| 1462 |
-
"loss": 33.12846069335937,
|
| 1463 |
-
"step": 1870
|
| 1464 |
-
},
|
| 1465 |
-
{
|
| 1466 |
-
"epoch": 0.1709090909090909,
|
| 1467 |
-
"grad_norm": 17089225031680.0,
|
| 1468 |
-
"learning_rate": 9.297153740109149e-06,
|
| 1469 |
-
"loss": 33.338644409179686,
|
| 1470 |
-
"step": 1880
|
| 1471 |
-
},
|
| 1472 |
-
{
|
| 1473 |
-
"epoch": 0.17181818181818181,
|
| 1474 |
-
"grad_norm": 16702327750656.0,
|
| 1475 |
-
"learning_rate": 9.289835560726054e-06,
|
| 1476 |
-
"loss": 32.967626953125,
|
| 1477 |
-
"step": 1890
|
| 1478 |
-
},
|
| 1479 |
-
{
|
| 1480 |
-
"epoch": 0.17272727272727273,
|
| 1481 |
-
"grad_norm": 47055904964608.0,
|
| 1482 |
-
"learning_rate": 9.28248239047424e-06,
|
| 1483 |
-
"loss": 33.560003662109374,
|
| 1484 |
-
"step": 1900
|
| 1485 |
-
},
|
| 1486 |
-
{
|
| 1487 |
-
"epoch": 0.17272727272727273,
|
| 1488 |
-
"eval_loss": 33.12340545654297,
|
| 1489 |
-
"eval_runtime": 2.2364,
|
| 1490 |
-
"eval_samples_per_second": 1.789,
|
| 1491 |
-
"eval_steps_per_second": 0.447,
|
| 1492 |
-
"step": 1900
|
| 1493 |
-
},
|
| 1494 |
-
{
|
| 1495 |
-
"epoch": 0.17363636363636364,
|
| 1496 |
-
"grad_norm": 39783350927360.0,
|
| 1497 |
-
"learning_rate": 9.275094289331255e-06,
|
| 1498 |
-
"loss": 33.179928588867185,
|
| 1499 |
-
"step": 1910
|
| 1500 |
-
},
|
| 1501 |
-
{
|
| 1502 |
-
"epoch": 0.17454545454545456,
|
| 1503 |
-
"grad_norm": 24787021725696.0,
|
| 1504 |
-
"learning_rate": 9.267671317559564e-06,
|
| 1505 |
-
"loss": 33.633059692382815,
|
| 1506 |
-
"step": 1920
|
| 1507 |
-
},
|
| 1508 |
-
{
|
| 1509 |
-
"epoch": 0.17545454545454545,
|
| 1510 |
-
"grad_norm": 59121021747200.0,
|
| 1511 |
-
"learning_rate": 9.260213535706064e-06,
|
| 1512 |
-
"loss": 33.45337829589844,
|
| 1513 |
-
"step": 1930
|
| 1514 |
-
},
|
| 1515 |
-
{
|
| 1516 |
-
"epoch": 0.17636363636363636,
|
| 1517 |
-
"grad_norm": 38006677307392.0,
|
| 1518 |
-
"learning_rate": 9.252721004601587e-06,
|
| 1519 |
-
"loss": 33.815695190429686,
|
| 1520 |
-
"step": 1940
|
| 1521 |
-
},
|
| 1522 |
-
{
|
| 1523 |
-
"epoch": 0.17727272727272728,
|
| 1524 |
-
"grad_norm": 23238140755968.0,
|
| 1525 |
-
"learning_rate": 9.245193785360407e-06,
|
| 1526 |
-
"loss": 33.58963623046875,
|
| 1527 |
-
"step": 1950
|
| 1528 |
-
},
|
| 1529 |
-
{
|
| 1530 |
-
"epoch": 0.1781818181818182,
|
| 1531 |
-
"grad_norm": 16146431475712.0,
|
| 1532 |
-
"learning_rate": 9.237631939379731e-06,
|
| 1533 |
-
"loss": 33.774557495117186,
|
| 1534 |
-
"step": 1960
|
| 1535 |
-
},
|
| 1536 |
-
{
|
| 1537 |
-
"epoch": 0.17909090909090908,
|
| 1538 |
-
"grad_norm": 73825001668608.0,
|
| 1539 |
-
"learning_rate": 9.230035528339212e-06,
|
| 1540 |
-
"loss": 32.61050720214844,
|
| 1541 |
-
"step": 1970
|
| 1542 |
-
},
|
| 1543 |
-
{
|
| 1544 |
-
"epoch": 0.18,
|
| 1545 |
-
"grad_norm": 77602744172544.0,
|
| 1546 |
-
"learning_rate": 9.222404614200437e-06,
|
| 1547 |
-
"loss": 34.036373901367185,
|
| 1548 |
-
"step": 1980
|
| 1549 |
-
},
|
| 1550 |
-
{
|
| 1551 |
-
"epoch": 0.1809090909090909,
|
| 1552 |
-
"grad_norm": 52128609468416.0,
|
| 1553 |
-
"learning_rate": 9.214739259206424e-06,
|
| 1554 |
-
"loss": 33.779693603515625,
|
| 1555 |
-
"step": 1990
|
| 1556 |
-
},
|
| 1557 |
-
{
|
| 1558 |
-
"epoch": 0.18181818181818182,
|
| 1559 |
-
"grad_norm": 4887862050816.0,
|
| 1560 |
-
"learning_rate": 9.207039525881117e-06,
|
| 1561 |
-
"loss": 33.33510131835938,
|
| 1562 |
-
"step": 2000
|
| 1563 |
-
},
|
| 1564 |
-
{
|
| 1565 |
-
"epoch": 0.18181818181818182,
|
| 1566 |
-
"eval_loss": 33.294410705566406,
|
| 1567 |
-
"eval_runtime": 2.2304,
|
| 1568 |
-
"eval_samples_per_second": 1.793,
|
| 1569 |
-
"eval_steps_per_second": 0.448,
|
| 1570 |
-
"step": 2000
|
| 1571 |
}
|
| 1572 |
],
|
| 1573 |
"logging_steps": 10,
|
|
@@ -1587,7 +807,7 @@
|
|
| 1587 |
"attributes": {}
|
| 1588 |
}
|
| 1589 |
},
|
| 1590 |
-
"total_flos":
|
| 1591 |
"train_batch_size": 1,
|
| 1592 |
"trial_name": null,
|
| 1593 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.09090909090909091,
|
| 6 |
"eval_steps": 100,
|
| 7 |
+
"global_step": 1000,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": false,
|
| 10 |
"is_world_process_zero": true,
|
| 11 |
"log_history": [
|
| 12 |
{
|
| 13 |
"epoch": 0.0009090909090909091,
|
| 14 |
+
"grad_norm": 24835585474560.0,
|
| 15 |
+
"learning_rate": 9.999983482695944e-07,
|
| 16 |
+
"loss": 31.50365295410156,
|
| 17 |
"step": 10
|
| 18 |
},
|
| 19 |
{
|
| 20 |
"epoch": 0.0018181818181818182,
|
| 21 |
+
"grad_norm": 15793144201216.0,
|
| 22 |
+
"learning_rate": 9.999926385982519e-07,
|
| 23 |
+
"loss": 31.015130615234376,
|
| 24 |
"step": 20
|
| 25 |
},
|
| 26 |
{
|
| 27 |
"epoch": 0.0027272727272727275,
|
| 28 |
+
"grad_norm": 20612445634560.0,
|
| 29 |
+
"learning_rate": 9.999828506408003e-07,
|
| 30 |
+
"loss": 31.242529296875,
|
| 31 |
"step": 30
|
| 32 |
},
|
| 33 |
{
|
| 34 |
"epoch": 0.0036363636363636364,
|
| 35 |
+
"grad_norm": 34239179390976.0,
|
| 36 |
+
"learning_rate": 9.999689844770766e-07,
|
| 37 |
+
"loss": 31.6640625,
|
| 38 |
"step": 40
|
| 39 |
},
|
| 40 |
{
|
| 41 |
"epoch": 0.004545454545454545,
|
| 42 |
+
"grad_norm": 51216444817408.0,
|
| 43 |
+
"learning_rate": 9.999510402201835e-07,
|
| 44 |
+
"loss": 31.64912109375,
|
| 45 |
"step": 50
|
| 46 |
},
|
| 47 |
{
|
| 48 |
"epoch": 0.005454545454545455,
|
| 49 |
+
"grad_norm": 20637055713280.0,
|
| 50 |
+
"learning_rate": 9.99929018016486e-07,
|
| 51 |
+
"loss": 31.355593872070312,
|
| 52 |
"step": 60
|
| 53 |
},
|
| 54 |
{
|
| 55 |
"epoch": 0.006363636363636364,
|
| 56 |
+
"grad_norm": 32561835278336.0,
|
| 57 |
+
"learning_rate": 9.999029180456129e-07,
|
| 58 |
+
"loss": 31.931137084960938,
|
| 59 |
"step": 70
|
| 60 |
},
|
| 61 |
{
|
| 62 |
"epoch": 0.007272727272727273,
|
| 63 |
+
"grad_norm": 68632881135616.0,
|
| 64 |
+
"learning_rate": 9.998727405204534e-07,
|
| 65 |
+
"loss": 31.378302001953124,
|
| 66 |
"step": 80
|
| 67 |
},
|
| 68 |
{
|
| 69 |
"epoch": 0.008181818181818182,
|
| 70 |
+
"grad_norm": 42669824802816.0,
|
| 71 |
+
"learning_rate": 9.998384856871564e-07,
|
| 72 |
+
"loss": 31.455963134765625,
|
| 73 |
"step": 90
|
| 74 |
},
|
| 75 |
{
|
| 76 |
"epoch": 0.00909090909090909,
|
| 77 |
+
"grad_norm": 16400540237824.0,
|
| 78 |
+
"learning_rate": 9.998001538251282e-07,
|
| 79 |
+
"loss": 31.83574523925781,
|
| 80 |
"step": 100
|
| 81 |
},
|
| 82 |
{
|
| 83 |
"epoch": 0.00909090909090909,
|
| 84 |
+
"eval_loss": 31.256309509277344,
|
| 85 |
+
"eval_runtime": 22.3946,
|
| 86 |
"eval_samples_per_second": 0.179,
|
| 87 |
"eval_steps_per_second": 0.045,
|
| 88 |
"step": 100
|
| 89 |
},
|
| 90 |
{
|
| 91 |
"epoch": 0.01,
|
| 92 |
+
"grad_norm": 29021217751040.0,
|
| 93 |
+
"learning_rate": 9.997577452470298e-07,
|
| 94 |
+
"loss": 31.68128662109375,
|
| 95 |
"step": 110
|
| 96 |
},
|
| 97 |
{
|
| 98 |
"epoch": 0.01090909090909091,
|
| 99 |
+
"grad_norm": 43289218646016.0,
|
| 100 |
+
"learning_rate": 9.99711260298775e-07,
|
| 101 |
+
"loss": 31.50353088378906,
|
| 102 |
"step": 120
|
| 103 |
},
|
| 104 |
{
|
| 105 |
"epoch": 0.011818181818181818,
|
| 106 |
+
"grad_norm": 128646291390464.0,
|
| 107 |
+
"learning_rate": 9.99660699359527e-07,
|
| 108 |
+
"loss": 31.131292724609374,
|
| 109 |
"step": 130
|
| 110 |
},
|
| 111 |
{
|
| 112 |
"epoch": 0.012727272727272728,
|
| 113 |
+
"grad_norm": 37279833784320.0,
|
| 114 |
+
"learning_rate": 9.996060628416963e-07,
|
| 115 |
+
"loss": 31.5599853515625,
|
| 116 |
"step": 140
|
| 117 |
},
|
| 118 |
{
|
| 119 |
"epoch": 0.013636363636363636,
|
| 120 |
+
"grad_norm": 43879491436544.0,
|
| 121 |
+
"learning_rate": 9.995473511909357e-07,
|
| 122 |
+
"loss": 31.862338256835937,
|
| 123 |
"step": 150
|
| 124 |
},
|
| 125 |
{
|
| 126 |
"epoch": 0.014545454545454545,
|
| 127 |
+
"grad_norm": 25585361354752.0,
|
| 128 |
+
"learning_rate": 9.994845648861382e-07,
|
| 129 |
+
"loss": 31.210086059570312,
|
| 130 |
"step": 160
|
| 131 |
},
|
| 132 |
{
|
| 133 |
"epoch": 0.015454545454545455,
|
| 134 |
+
"grad_norm": 90612418215936.0,
|
| 135 |
+
"learning_rate": 9.994177044394322e-07,
|
| 136 |
+
"loss": 31.158685302734376,
|
| 137 |
"step": 170
|
| 138 |
},
|
| 139 |
{
|
| 140 |
"epoch": 0.016363636363636365,
|
| 141 |
+
"grad_norm": 92622169309184.0,
|
| 142 |
+
"learning_rate": 9.993467703961784e-07,
|
| 143 |
+
"loss": 31.556906127929686,
|
| 144 |
"step": 180
|
| 145 |
},
|
| 146 |
{
|
| 147 |
"epoch": 0.017272727272727273,
|
| 148 |
+
"grad_norm": 83515236417536.0,
|
| 149 |
+
"learning_rate": 9.992717633349635e-07,
|
| 150 |
+
"loss": 31.514627075195314,
|
| 151 |
"step": 190
|
| 152 |
},
|
| 153 |
{
|
| 154 |
"epoch": 0.01818181818181818,
|
| 155 |
+
"grad_norm": 42516023869440.0,
|
| 156 |
+
"learning_rate": 9.99192683867597e-07,
|
| 157 |
+
"loss": 31.424298095703126,
|
| 158 |
"step": 200
|
| 159 |
},
|
| 160 |
{
|
| 161 |
"epoch": 0.01818181818181818,
|
| 162 |
+
"eval_loss": 31.22693634033203,
|
| 163 |
+
"eval_runtime": 2.254,
|
| 164 |
+
"eval_samples_per_second": 1.775,
|
| 165 |
+
"eval_steps_per_second": 0.444,
|
| 166 |
"step": 200
|
| 167 |
},
|
| 168 |
{
|
| 169 |
"epoch": 0.019090909090909092,
|
| 170 |
+
"grad_norm": 74708263370752.0,
|
| 171 |
+
"learning_rate": 9.99109532639106e-07,
|
| 172 |
+
"loss": 31.736981201171876,
|
| 173 |
"step": 210
|
| 174 |
},
|
| 175 |
{
|
| 176 |
"epoch": 0.02,
|
| 177 |
+
"grad_norm": 137343843434496.0,
|
| 178 |
+
"learning_rate": 9.99022310327729e-07,
|
| 179 |
+
"loss": 31.506015014648437,
|
| 180 |
"step": 220
|
| 181 |
},
|
| 182 |
{
|
| 183 |
"epoch": 0.02090909090909091,
|
| 184 |
+
"grad_norm": 48417904525312.0,
|
| 185 |
+
"learning_rate": 9.98931017644912e-07,
|
| 186 |
+
"loss": 31.584011840820313,
|
| 187 |
"step": 230
|
| 188 |
},
|
| 189 |
{
|
| 190 |
"epoch": 0.02181818181818182,
|
| 191 |
+
"grad_norm": 58472024506368.0,
|
| 192 |
+
"learning_rate": 9.988356553353017e-07,
|
| 193 |
+
"loss": 31.47820129394531,
|
| 194 |
"step": 240
|
| 195 |
},
|
| 196 |
{
|
| 197 |
"epoch": 0.022727272727272728,
|
| 198 |
+
"grad_norm": 19866878738432.0,
|
| 199 |
+
"learning_rate": 9.987362241767383e-07,
|
| 200 |
+
"loss": 31.335162353515624,
|
| 201 |
"step": 250
|
| 202 |
},
|
| 203 |
{
|
| 204 |
"epoch": 0.023636363636363636,
|
| 205 |
+
"grad_norm": 31799931568128.0,
|
| 206 |
+
"learning_rate": 9.986327249802515e-07,
|
| 207 |
+
"loss": 30.963482666015626,
|
| 208 |
"step": 260
|
| 209 |
},
|
| 210 |
{
|
| 211 |
"epoch": 0.024545454545454544,
|
| 212 |
+
"grad_norm": 85499729412096.0,
|
| 213 |
+
"learning_rate": 9.985251585900525e-07,
|
| 214 |
+
"loss": 31.298876953125,
|
| 215 |
"step": 270
|
| 216 |
},
|
| 217 |
{
|
| 218 |
"epoch": 0.025454545454545455,
|
| 219 |
+
"grad_norm": 48352565657600.0,
|
| 220 |
+
"learning_rate": 9.984135258835272e-07,
|
| 221 |
+
"loss": 31.747039794921875,
|
| 222 |
"step": 280
|
| 223 |
},
|
| 224 |
{
|
| 225 |
"epoch": 0.026363636363636363,
|
| 226 |
+
"grad_norm": 31058988892160.0,
|
| 227 |
+
"learning_rate": 9.98297827771229e-07,
|
| 228 |
+
"loss": 32.078277587890625,
|
| 229 |
"step": 290
|
| 230 |
},
|
| 231 |
{
|
| 232 |
"epoch": 0.02727272727272727,
|
| 233 |
+
"grad_norm": 77612550455296.0,
|
| 234 |
+
"learning_rate": 9.981780651968722e-07,
|
| 235 |
+
"loss": 31.41339111328125,
|
| 236 |
"step": 300
|
| 237 |
},
|
| 238 |
{
|
| 239 |
"epoch": 0.02727272727272727,
|
| 240 |
+
"eval_loss": 31.19794273376465,
|
| 241 |
+
"eval_runtime": 2.2652,
|
| 242 |
+
"eval_samples_per_second": 1.766,
|
| 243 |
+
"eval_steps_per_second": 0.441,
|
| 244 |
"step": 300
|
| 245 |
},
|
| 246 |
{
|
| 247 |
"epoch": 0.028181818181818183,
|
| 248 |
+
"grad_norm": 49784861753344.0,
|
| 249 |
+
"learning_rate": 9.980542391373232e-07,
|
| 250 |
+
"loss": 31.86634521484375,
|
| 251 |
"step": 310
|
| 252 |
},
|
| 253 |
{
|
| 254 |
"epoch": 0.02909090909090909,
|
| 255 |
+
"grad_norm": 97983580340224.0,
|
| 256 |
+
"learning_rate": 9.979263506025929e-07,
|
| 257 |
+
"loss": 31.366073608398438,
|
| 258 |
"step": 320
|
| 259 |
},
|
| 260 |
{
|
| 261 |
"epoch": 0.03,
|
| 262 |
+
"grad_norm": 40498060328960.0,
|
| 263 |
+
"learning_rate": 9.977944006358285e-07,
|
| 264 |
+
"loss": 31.210226440429686,
|
| 265 |
"step": 330
|
| 266 |
},
|
| 267 |
{
|
| 268 |
"epoch": 0.03090909090909091,
|
| 269 |
+
"grad_norm": 92092479045632.0,
|
| 270 |
+
"learning_rate": 9.976583903133059e-07,
|
| 271 |
+
"loss": 30.927703857421875,
|
| 272 |
"step": 340
|
| 273 |
},
|
| 274 |
{
|
| 275 |
"epoch": 0.031818181818181815,
|
| 276 |
+
"grad_norm": 72197787877376.0,
|
| 277 |
+
"learning_rate": 9.975183207444189e-07,
|
| 278 |
+
"loss": 30.43183288574219,
|
| 279 |
"step": 350
|
| 280 |
},
|
| 281 |
{
|
| 282 |
"epoch": 0.03272727272727273,
|
| 283 |
+
"grad_norm": 46449144365056.0,
|
| 284 |
+
"learning_rate": 9.97374193071672e-07,
|
| 285 |
+
"loss": 31.0708740234375,
|
| 286 |
"step": 360
|
| 287 |
},
|
| 288 |
{
|
| 289 |
"epoch": 0.03363636363636364,
|
| 290 |
+
"grad_norm": 16542873944064.0,
|
| 291 |
+
"learning_rate": 9.972260084706704e-07,
|
| 292 |
+
"loss": 31.289712524414064,
|
| 293 |
"step": 370
|
| 294 |
},
|
| 295 |
{
|
| 296 |
"epoch": 0.034545454545454546,
|
| 297 |
+
"grad_norm": 76645293621248.0,
|
| 298 |
+
"learning_rate": 9.970737681501104e-07,
|
| 299 |
+
"loss": 31.326876831054687,
|
| 300 |
"step": 380
|
| 301 |
},
|
| 302 |
{
|
| 303 |
"epoch": 0.035454545454545454,
|
| 304 |
+
"grad_norm": 24548648943616.0,
|
| 305 |
+
"learning_rate": 9.969174733517693e-07,
|
| 306 |
+
"loss": 31.130474853515626,
|
| 307 |
"step": 390
|
| 308 |
},
|
| 309 |
{
|
| 310 |
"epoch": 0.03636363636363636,
|
| 311 |
+
"grad_norm": 57560858099712.0,
|
| 312 |
+
"learning_rate": 9.967571253504956e-07,
|
| 313 |
+
"loss": 31.06658020019531,
|
| 314 |
"step": 400
|
| 315 |
},
|
| 316 |
{
|
| 317 |
"epoch": 0.03636363636363636,
|
| 318 |
+
"eval_loss": 31.173606872558594,
|
| 319 |
+
"eval_runtime": 2.2635,
|
| 320 |
+
"eval_samples_per_second": 1.767,
|
| 321 |
+
"eval_steps_per_second": 0.442,
|
| 322 |
"step": 400
|
| 323 |
},
|
| 324 |
{
|
| 325 |
"epoch": 0.03727272727272727,
|
| 326 |
+
"grad_norm": 40138956603392.0,
|
| 327 |
+
"learning_rate": 9.965927254541986e-07,
|
| 328 |
+
"loss": 31.133847045898438,
|
| 329 |
"step": 410
|
| 330 |
},
|
| 331 |
{
|
| 332 |
"epoch": 0.038181818181818185,
|
| 333 |
+
"grad_norm": 33342583996416.0,
|
| 334 |
+
"learning_rate": 9.964242750038379e-07,
|
| 335 |
+
"loss": 31.538308715820314,
|
| 336 |
"step": 420
|
| 337 |
},
|
| 338 |
{
|
| 339 |
"epoch": 0.03909090909090909,
|
| 340 |
+
"grad_norm": 38552683413504.0,
|
| 341 |
+
"learning_rate": 9.96251775373412e-07,
|
| 342 |
+
"loss": 31.598001098632814,
|
| 343 |
"step": 430
|
| 344 |
},
|
| 345 |
{
|
| 346 |
"epoch": 0.04,
|
| 347 |
+
"grad_norm": 43073170046976.0,
|
| 348 |
+
"learning_rate": 9.960752279699469e-07,
|
| 349 |
+
"loss": 31.713970947265626,
|
| 350 |
"step": 440
|
| 351 |
},
|
| 352 |
{
|
| 353 |
"epoch": 0.04090909090909091,
|
| 354 |
+
"grad_norm": 63941845712896.0,
|
| 355 |
+
"learning_rate": 9.958946342334858e-07,
|
| 356 |
+
"loss": 31.403384399414062,
|
| 357 |
"step": 450
|
| 358 |
},
|
| 359 |
{
|
| 360 |
"epoch": 0.04181818181818182,
|
| 361 |
+
"grad_norm": 81496106860544.0,
|
| 362 |
+
"learning_rate": 9.957099956370761e-07,
|
| 363 |
+
"loss": 31.192584228515624,
|
| 364 |
"step": 460
|
| 365 |
},
|
| 366 |
{
|
| 367 |
"epoch": 0.042727272727272725,
|
| 368 |
+
"grad_norm": 85547368316928.0,
|
| 369 |
+
"learning_rate": 9.95521313686758e-07,
|
| 370 |
+
"loss": 31.35161437988281,
|
| 371 |
"step": 470
|
| 372 |
},
|
| 373 |
{
|
| 374 |
"epoch": 0.04363636363636364,
|
| 375 |
+
"grad_norm": 33979606499328.0,
|
| 376 |
+
"learning_rate": 9.953285899215524e-07,
|
| 377 |
+
"loss": 31.211724853515626,
|
| 378 |
"step": 480
|
| 379 |
},
|
| 380 |
{
|
| 381 |
"epoch": 0.04454545454545455,
|
| 382 |
+
"grad_norm": 78801216208896.0,
|
| 383 |
+
"learning_rate": 9.951318259134473e-07,
|
| 384 |
+
"loss": 31.460574340820312,
|
| 385 |
"step": 490
|
| 386 |
},
|
| 387 |
{
|
| 388 |
"epoch": 0.045454545454545456,
|
| 389 |
+
"grad_norm": 17078298869760.0,
|
| 390 |
+
"learning_rate": 9.949310232673867e-07,
|
| 391 |
+
"loss": 31.416909790039064,
|
| 392 |
"step": 500
|
| 393 |
},
|
| 394 |
{
|
| 395 |
"epoch": 0.045454545454545456,
|
| 396 |
+
"eval_loss": 31.15839385986328,
|
| 397 |
+
"eval_runtime": 2.2493,
|
| 398 |
+
"eval_samples_per_second": 1.778,
|
| 399 |
+
"eval_steps_per_second": 0.445,
|
| 400 |
"step": 500
|
| 401 |
},
|
| 402 |
{
|
| 403 |
"epoch": 0.046363636363636364,
|
| 404 |
+
"grad_norm": 25643221778432.0,
|
| 405 |
+
"learning_rate": 9.947261836212555e-07,
|
| 406 |
+
"loss": 31.366104125976562,
|
| 407 |
"step": 510
|
| 408 |
},
|
| 409 |
{
|
| 410 |
"epoch": 0.04727272727272727,
|
| 411 |
+
"grad_norm": 68086552068096.0,
|
| 412 |
+
"learning_rate": 9.94517308645868e-07,
|
| 413 |
+
"loss": 31.929010009765626,
|
| 414 |
"step": 520
|
| 415 |
},
|
| 416 |
{
|
| 417 |
"epoch": 0.04818181818181818,
|
| 418 |
+
"grad_norm": 85420834553856.0,
|
| 419 |
+
"learning_rate": 9.94304400044953e-07,
|
| 420 |
+
"loss": 31.22962646484375,
|
| 421 |
"step": 530
|
| 422 |
},
|
| 423 |
{
|
| 424 |
"epoch": 0.04909090909090909,
|
| 425 |
+
"grad_norm": 34801671208960.0,
|
| 426 |
+
"learning_rate": 9.940874595551404e-07,
|
| 427 |
+
"loss": 31.47492370605469,
|
| 428 |
"step": 540
|
| 429 |
},
|
| 430 |
{
|
| 431 |
"epoch": 0.05,
|
| 432 |
+
"grad_norm": 50617645006848.0,
|
| 433 |
+
"learning_rate": 9.938664889459468e-07,
|
| 434 |
+
"loss": 31.026275634765625,
|
| 435 |
"step": 550
|
| 436 |
},
|
| 437 |
{
|
| 438 |
"epoch": 0.05090909090909091,
|
| 439 |
+
"grad_norm": 49960867332096.0,
|
| 440 |
+
"learning_rate": 9.936414900197618e-07,
|
| 441 |
+
"loss": 31.542160034179688,
|
| 442 |
"step": 560
|
| 443 |
},
|
| 444 |
{
|
| 445 |
"epoch": 0.05181818181818182,
|
| 446 |
+
"grad_norm": 32654523105280.0,
|
| 447 |
+
"learning_rate": 9.934124646118324e-07,
|
| 448 |
+
"loss": 31.71721496582031,
|
| 449 |
"step": 570
|
| 450 |
},
|
| 451 |
{
|
| 452 |
"epoch": 0.05272727272727273,
|
| 453 |
+
"grad_norm": 44004343283712.0,
|
| 454 |
+
"learning_rate": 9.931794145902485e-07,
|
| 455 |
+
"loss": 31.2598876953125,
|
| 456 |
"step": 580
|
| 457 |
},
|
| 458 |
{
|
| 459 |
"epoch": 0.053636363636363635,
|
| 460 |
+
"grad_norm": 66710199599104.0,
|
| 461 |
+
"learning_rate": 9.92942341855927e-07,
|
| 462 |
+
"loss": 31.227630615234375,
|
| 463 |
"step": 590
|
| 464 |
},
|
| 465 |
{
|
| 466 |
"epoch": 0.05454545454545454,
|
| 467 |
+
"grad_norm": 75621816336384.0,
|
| 468 |
+
"learning_rate": 9.927012483425976e-07,
|
| 469 |
+
"loss": 31.72113037109375,
|
| 470 |
"step": 600
|
| 471 |
},
|
| 472 |
{
|
| 473 |
"epoch": 0.05454545454545454,
|
| 474 |
+
"eval_loss": 31.14929962158203,
|
| 475 |
+
"eval_runtime": 2.2862,
|
| 476 |
+
"eval_samples_per_second": 1.75,
|
| 477 |
+
"eval_steps_per_second": 0.437,
|
| 478 |
"step": 600
|
| 479 |
},
|
| 480 |
{
|
| 481 |
"epoch": 0.05545454545454546,
|
| 482 |
+
"grad_norm": 60767218958336.0,
|
| 483 |
+
"learning_rate": 9.924561360167858e-07,
|
| 484 |
+
"loss": 30.905987548828126,
|
| 485 |
"step": 610
|
| 486 |
},
|
| 487 |
{
|
| 488 |
"epoch": 0.056363636363636366,
|
| 489 |
+
"grad_norm": 28232556478464.0,
|
| 490 |
+
"learning_rate": 9.922070068777972e-07,
|
| 491 |
+
"loss": 31.27515869140625,
|
| 492 |
"step": 620
|
| 493 |
},
|
| 494 |
{
|
| 495 |
"epoch": 0.057272727272727274,
|
| 496 |
+
"grad_norm": 57858754347008.0,
|
| 497 |
+
"learning_rate": 9.91953862957702e-07,
|
| 498 |
+
"loss": 31.28424072265625,
|
| 499 |
"step": 630
|
| 500 |
},
|
| 501 |
{
|
| 502 |
"epoch": 0.05818181818181818,
|
| 503 |
+
"grad_norm": 60663598678016.0,
|
| 504 |
+
"learning_rate": 9.91696706321317e-07,
|
| 505 |
+
"loss": 31.702291870117186,
|
| 506 |
"step": 640
|
| 507 |
},
|
| 508 |
{
|
| 509 |
"epoch": 0.05909090909090909,
|
| 510 |
+
"grad_norm": 64403231735808.0,
|
| 511 |
+
"learning_rate": 9.914355390661895e-07,
|
| 512 |
+
"loss": 31.74828186035156,
|
| 513 |
"step": 650
|
| 514 |
},
|
| 515 |
{
|
| 516 |
"epoch": 0.06,
|
| 517 |
+
"grad_norm": 49898036658176.0,
|
| 518 |
+
"learning_rate": 9.91170363322581e-07,
|
| 519 |
+
"loss": 30.9451904296875,
|
| 520 |
"step": 660
|
| 521 |
},
|
| 522 |
{
|
| 523 |
"epoch": 0.060909090909090906,
|
| 524 |
+
"grad_norm": 22820329357312.0,
|
| 525 |
+
"learning_rate": 9.90901181253448e-07,
|
| 526 |
+
"loss": 31.49604187011719,
|
| 527 |
"step": 670
|
| 528 |
},
|
| 529 |
{
|
| 530 |
"epoch": 0.06181818181818182,
|
| 531 |
+
"grad_norm": 170618632798208.0,
|
| 532 |
+
"learning_rate": 9.906279950544258e-07,
|
| 533 |
+
"loss": 30.988015747070314,
|
| 534 |
"step": 680
|
| 535 |
},
|
| 536 |
{
|
| 537 |
"epoch": 0.06272727272727273,
|
| 538 |
+
"grad_norm": 66990144225280.0,
|
| 539 |
+
"learning_rate": 9.903508069538107e-07,
|
| 540 |
+
"loss": 31.130947875976563,
|
| 541 |
"step": 690
|
| 542 |
},
|
| 543 |
{
|
| 544 |
"epoch": 0.06363636363636363,
|
| 545 |
+
"grad_norm": 39199952601088.0,
|
| 546 |
+
"learning_rate": 9.900696192125401e-07,
|
| 547 |
+
"loss": 31.55877685546875,
|
| 548 |
"step": 700
|
| 549 |
},
|
| 550 |
{
|
| 551 |
"epoch": 0.06363636363636363,
|
| 552 |
+
"eval_loss": 31.127349853515625,
|
| 553 |
+
"eval_runtime": 2.2839,
|
| 554 |
+
"eval_samples_per_second": 1.751,
|
| 555 |
+
"eval_steps_per_second": 0.438,
|
| 556 |
"step": 700
|
| 557 |
},
|
| 558 |
{
|
| 559 |
"epoch": 0.06454545454545454,
|
| 560 |
+
"grad_norm": 53508833280000.0,
|
| 561 |
+
"learning_rate": 9.897844341241764e-07,
|
| 562 |
+
"loss": 30.89222106933594,
|
| 563 |
"step": 710
|
| 564 |
},
|
| 565 |
{
|
| 566 |
"epoch": 0.06545454545454546,
|
| 567 |
+
"grad_norm": 76796364062720.0,
|
| 568 |
+
"learning_rate": 9.894952540148861e-07,
|
| 569 |
+
"loss": 31.557272338867186,
|
| 570 |
"step": 720
|
| 571 |
},
|
| 572 |
{
|
| 573 |
"epoch": 0.06636363636363636,
|
| 574 |
+
"grad_norm": 53238585884672.0,
|
| 575 |
+
"learning_rate": 9.892020812434227e-07,
|
| 576 |
+
"loss": 31.102691650390625,
|
| 577 |
"step": 730
|
| 578 |
},
|
| 579 |
{
|
| 580 |
"epoch": 0.06727272727272728,
|
| 581 |
+
"grad_norm": 72308743995392.0,
|
| 582 |
+
"learning_rate": 9.889049182011064e-07,
|
| 583 |
+
"loss": 31.06553955078125,
|
| 584 |
"step": 740
|
| 585 |
},
|
| 586 |
{
|
| 587 |
"epoch": 0.06818181818181818,
|
| 588 |
+
"grad_norm": 85104164601856.0,
|
| 589 |
+
"learning_rate": 9.886037673118046e-07,
|
| 590 |
+
"loss": 31.310086059570313,
|
| 591 |
"step": 750
|
| 592 |
},
|
| 593 |
{
|
| 594 |
"epoch": 0.06909090909090909,
|
| 595 |
+
"grad_norm": 75288956370944.0,
|
| 596 |
+
"learning_rate": 9.882986310319123e-07,
|
| 597 |
+
"loss": 30.976141357421874,
|
| 598 |
"step": 760
|
| 599 |
},
|
| 600 |
{
|
| 601 |
"epoch": 0.07,
|
| 602 |
+
"grad_norm": 39805987586048.0,
|
| 603 |
+
"learning_rate": 9.879895118503322e-07,
|
| 604 |
+
"loss": 31.357177734375,
|
| 605 |
"step": 770
|
| 606 |
},
|
| 607 |
{
|
| 608 |
"epoch": 0.07090909090909091,
|
| 609 |
+
"grad_norm": 13191673282560.0,
|
| 610 |
+
"learning_rate": 9.876764122884546e-07,
|
| 611 |
+
"loss": 31.26226806640625,
|
| 612 |
"step": 780
|
| 613 |
},
|
| 614 |
{
|
| 615 |
"epoch": 0.07181818181818182,
|
| 616 |
+
"grad_norm": 98536062451712.0,
|
| 617 |
+
"learning_rate": 9.873593349001363e-07,
|
| 618 |
+
"loss": 31.190093994140625,
|
| 619 |
"step": 790
|
| 620 |
},
|
| 621 |
{
|
| 622 |
"epoch": 0.07272727272727272,
|
| 623 |
+
"grad_norm": 86483419529216.0,
|
| 624 |
+
"learning_rate": 9.870382822716797e-07,
|
| 625 |
+
"loss": 31.130612182617188,
|
| 626 |
"step": 800
|
| 627 |
},
|
| 628 |
{
|
| 629 |
"epoch": 0.07272727272727272,
|
| 630 |
+
"eval_loss": 31.110492706298828,
|
| 631 |
+
"eval_runtime": 2.2472,
|
| 632 |
+
"eval_samples_per_second": 1.78,
|
| 633 |
+
"eval_steps_per_second": 0.445,
|
| 634 |
"step": 800
|
| 635 |
},
|
| 636 |
{
|
| 637 |
"epoch": 0.07363636363636364,
|
| 638 |
+
"grad_norm": 50370197848064.0,
|
| 639 |
+
"learning_rate": 9.867132570218127e-07,
|
| 640 |
+
"loss": 31.63127746582031,
|
| 641 |
"step": 810
|
| 642 |
},
|
| 643 |
{
|
| 644 |
"epoch": 0.07454545454545454,
|
| 645 |
+
"grad_norm": 66007850811392.0,
|
| 646 |
+
"learning_rate": 9.863842618016658e-07,
|
| 647 |
+
"loss": 31.623040771484376,
|
| 648 |
"step": 820
|
| 649 |
},
|
| 650 |
{
|
| 651 |
"epoch": 0.07545454545454545,
|
| 652 |
+
"grad_norm": 109455253438464.0,
|
| 653 |
+
"learning_rate": 9.86051299294752e-07,
|
| 654 |
+
"loss": 31.264794921875,
|
| 655 |
"step": 830
|
| 656 |
},
|
| 657 |
{
|
| 658 |
"epoch": 0.07636363636363637,
|
| 659 |
+
"grad_norm": 35646429200384.0,
|
| 660 |
+
"learning_rate": 9.857143722169442e-07,
|
| 661 |
+
"loss": 30.843011474609376,
|
| 662 |
"step": 840
|
| 663 |
},
|
| 664 |
{
|
| 665 |
"epoch": 0.07727272727272727,
|
| 666 |
+
"grad_norm": 35847839678464.0,
|
| 667 |
+
"learning_rate": 9.853734833164525e-07,
|
| 668 |
+
"loss": 31.70771484375,
|
| 669 |
"step": 850
|
| 670 |
},
|
| 671 |
{
|
| 672 |
"epoch": 0.07818181818181819,
|
| 673 |
+
"grad_norm": 169087560843264.0,
|
| 674 |
+
"learning_rate": 9.850286353738032e-07,
|
| 675 |
+
"loss": 31.51513671875,
|
| 676 |
"step": 860
|
| 677 |
},
|
| 678 |
{
|
| 679 |
"epoch": 0.07909090909090909,
|
| 680 |
+
"grad_norm": 35594008788992.0,
|
| 681 |
+
"learning_rate": 9.846798312018146e-07,
|
| 682 |
+
"loss": 31.227005004882812,
|
| 683 |
"step": 870
|
| 684 |
},
|
| 685 |
{
|
| 686 |
"epoch": 0.08,
|
| 687 |
+
"grad_norm": 34218442752000.0,
|
| 688 |
+
"learning_rate": 9.843270736455752e-07,
|
| 689 |
+
"loss": 31.844467163085938,
|
| 690 |
"step": 880
|
| 691 |
},
|
| 692 |
{
|
| 693 |
"epoch": 0.0809090909090909,
|
| 694 |
+
"grad_norm": 76758078455808.0,
|
| 695 |
+
"learning_rate": 9.839703655824194e-07,
|
| 696 |
+
"loss": 31.2140380859375,
|
| 697 |
"step": 890
|
| 698 |
},
|
| 699 |
{
|
| 700 |
"epoch": 0.08181818181818182,
|
| 701 |
+
"grad_norm": 25330528026624.0,
|
| 702 |
+
"learning_rate": 9.836097099219057e-07,
|
| 703 |
+
"loss": 30.997073364257812,
|
| 704 |
"step": 900
|
| 705 |
},
|
| 706 |
{
|
| 707 |
"epoch": 0.08181818181818182,
|
| 708 |
+
"eval_loss": 31.093814849853516,
|
| 709 |
+
"eval_runtime": 2.2539,
|
| 710 |
+
"eval_samples_per_second": 1.775,
|
| 711 |
+
"eval_steps_per_second": 0.444,
|
| 712 |
"step": 900
|
| 713 |
},
|
| 714 |
{
|
| 715 |
"epoch": 0.08272727272727273,
|
| 716 |
+
"grad_norm": 111150716944384.0,
|
| 717 |
+
"learning_rate": 9.832451096057912e-07,
|
| 718 |
+
"loss": 31.376983642578125,
|
| 719 |
"step": 910
|
| 720 |
},
|
| 721 |
{
|
| 722 |
"epoch": 0.08363636363636363,
|
| 723 |
+
"grad_norm": 90311955054592.0,
|
| 724 |
+
"learning_rate": 9.82876567608008e-07,
|
| 725 |
+
"loss": 31.437393188476562,
|
| 726 |
"step": 920
|
| 727 |
},
|
| 728 |
{
|
| 729 |
"epoch": 0.08454545454545455,
|
| 730 |
+
"grad_norm": 51954126422016.0,
|
| 731 |
+
"learning_rate": 9.825040869346404e-07,
|
| 732 |
+
"loss": 31.078985595703124,
|
| 733 |
"step": 930
|
| 734 |
},
|
| 735 |
{
|
| 736 |
"epoch": 0.08545454545454545,
|
| 737 |
+
"grad_norm": 53884227682304.0,
|
| 738 |
+
"learning_rate": 9.821276706238985e-07,
|
| 739 |
+
"loss": 31.514266967773438,
|
| 740 |
"step": 940
|
| 741 |
},
|
| 742 |
{
|
| 743 |
"epoch": 0.08636363636363636,
|
| 744 |
+
"grad_norm": 25048345739264.0,
|
| 745 |
+
"learning_rate": 9.81747321746094e-07,
|
| 746 |
+
"loss": 31.2593505859375,
|
| 747 |
"step": 950
|
| 748 |
},
|
| 749 |
{
|
| 750 |
"epoch": 0.08727272727272728,
|
| 751 |
+
"grad_norm": 77616040116224.0,
|
| 752 |
+
"learning_rate": 9.81363043403616e-07,
|
| 753 |
+
"loss": 31.06065673828125,
|
| 754 |
"step": 960
|
| 755 |
},
|
| 756 |
{
|
| 757 |
"epoch": 0.08818181818181818,
|
| 758 |
+
"grad_norm": 62835941965824.0,
|
| 759 |
+
"learning_rate": 9.809748387309047e-07,
|
| 760 |
+
"loss": 31.265579223632812,
|
| 761 |
"step": 970
|
| 762 |
},
|
| 763 |
{
|
| 764 |
"epoch": 0.0890909090909091,
|
| 765 |
+
"grad_norm": 36371255263232.0,
|
| 766 |
+
"learning_rate": 9.805827108944259e-07,
|
| 767 |
+
"loss": 31.292767333984376,
|
| 768 |
"step": 980
|
| 769 |
},
|
| 770 |
{
|
| 771 |
"epoch": 0.09,
|
| 772 |
+
"grad_norm": 43744346767360.0,
|
| 773 |
+
"learning_rate": 9.801866630926459e-07,
|
| 774 |
+
"loss": 31.146585083007814,
|
| 775 |
"step": 990
|
| 776 |
},
|
| 777 |
{
|
| 778 |
"epoch": 0.09090909090909091,
|
| 779 |
+
"grad_norm": 104874788257792.0,
|
| 780 |
+
"learning_rate": 9.797866985560049e-07,
|
| 781 |
+
"loss": 31.14124755859375,
|
| 782 |
"step": 1000
|
| 783 |
},
|
| 784 |
{
|
| 785 |
"epoch": 0.09090909090909091,
|
| 786 |
+
"eval_loss": 31.08183479309082,
|
| 787 |
+
"eval_runtime": 2.2692,
|
| 788 |
+
"eval_samples_per_second": 1.763,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 789 |
"eval_steps_per_second": 0.441,
|
| 790 |
+
"step": 1000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 791 |
}
|
| 792 |
],
|
| 793 |
"logging_steps": 10,
|
|
|
|
| 807 |
"attributes": {}
|
| 808 |
}
|
| 809 |
},
|
| 810 |
+
"total_flos": 4529923817472000.0,
|
| 811 |
"train_batch_size": 1,
|
| 812 |
"trial_name": null,
|
| 813 |
"trial_params": null
|
last-checkpoint/training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5265
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7cf61a5ac27b474cb6ad1ed3d1fff7cf6e73364e8351b1e88dc185439ef0439d
|
| 3 |
size 5265
|