Training in progress, step 50, checkpoint
Browse files
last-checkpoint/model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2066752
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:766cd54d702e68387e8a47e9d3324fdfdbfc71c54ddeef13d62611ad5f472b94
|
| 3 |
size 2066752
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2162798
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1b5bb660eb4533fdec1208a7777e32810eec328387b3ef7df3ee27820b9acfd8
|
| 3 |
size 2162798
|
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 14512
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:62f5415ab0d082726880d0dd73d69a20743d20a0a7c951a4836c628ef156f744
|
| 3 |
size 14512
|
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 14512
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1d64f701370aa11c801b0e964ae533eec7ae3c3c8e7535246f28875affe1de61
|
| 3 |
size 14512
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1064
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1b5bd1b09d58ee3e65553e6f9772dc7c5ca98238b1cade33cccd500df2328864
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch":
|
| 5 |
-
"eval_steps":
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -11,9 +11,9 @@
|
|
| 11 |
{
|
| 12 |
"epoch": 0.07692307692307693,
|
| 13 |
"eval_loss": 10.376392364501953,
|
| 14 |
-
"eval_runtime": 5.
|
| 15 |
-
"eval_samples_per_second":
|
| 16 |
-
"eval_steps_per_second": 4.
|
| 17 |
"step": 1
|
| 18 |
},
|
| 19 |
{
|
|
@@ -44,14 +44,6 @@
|
|
| 44 |
"loss": 10.3522,
|
| 45 |
"step": 40
|
| 46 |
},
|
| 47 |
-
{
|
| 48 |
-
"epoch": 3.076923076923077,
|
| 49 |
-
"eval_loss": 10.336621284484863,
|
| 50 |
-
"eval_runtime": 5.2692,
|
| 51 |
-
"eval_samples_per_second": 284.862,
|
| 52 |
-
"eval_steps_per_second": 4.555,
|
| 53 |
-
"step": 40
|
| 54 |
-
},
|
| 55 |
{
|
| 56 |
"epoch": 3.8461538461538463,
|
| 57 |
"grad_norm": 0.3203125,
|
|
@@ -60,508 +52,19 @@
|
|
| 60 |
"step": 50
|
| 61 |
},
|
| 62 |
{
|
| 63 |
-
"epoch":
|
| 64 |
-
"
|
| 65 |
-
"learning_rate": 0.00019863613034027224,
|
| 66 |
-
"loss": 10.2518,
|
| 67 |
-
"step": 60
|
| 68 |
-
},
|
| 69 |
-
{
|
| 70 |
-
"epoch": 5.384615384615385,
|
| 71 |
-
"grad_norm": 0.326171875,
|
| 72 |
-
"learning_rate": 0.00019757963826274357,
|
| 73 |
-
"loss": 10.1828,
|
| 74 |
-
"step": 70
|
| 75 |
-
},
|
| 76 |
-
{
|
| 77 |
-
"epoch": 6.153846153846154,
|
| 78 |
-
"grad_norm": 0.330078125,
|
| 79 |
-
"learning_rate": 0.00019622680003092503,
|
| 80 |
-
"loss": 10.1177,
|
| 81 |
-
"step": 80
|
| 82 |
-
},
|
| 83 |
-
{
|
| 84 |
-
"epoch": 6.153846153846154,
|
| 85 |
-
"eval_loss": 10.088459014892578,
|
| 86 |
-
"eval_runtime": 5.2612,
|
| 87 |
-
"eval_samples_per_second": 285.294,
|
| 88 |
-
"eval_steps_per_second": 4.562,
|
| 89 |
-
"step": 80
|
| 90 |
-
},
|
| 91 |
-
{
|
| 92 |
-
"epoch": 6.923076923076923,
|
| 93 |
-
"grad_norm": 0.33203125,
|
| 94 |
-
"learning_rate": 0.00019458172417006347,
|
| 95 |
-
"loss": 10.0565,
|
| 96 |
-
"step": 90
|
| 97 |
-
},
|
| 98 |
-
{
|
| 99 |
-
"epoch": 7.6923076923076925,
|
| 100 |
-
"grad_norm": 0.341796875,
|
| 101 |
-
"learning_rate": 0.00019264940672148018,
|
| 102 |
-
"loss": 9.998,
|
| 103 |
-
"step": 100
|
| 104 |
-
},
|
| 105 |
-
{
|
| 106 |
-
"epoch": 8.461538461538462,
|
| 107 |
-
"grad_norm": 0.345703125,
|
| 108 |
-
"learning_rate": 0.00019043571606975777,
|
| 109 |
-
"loss": 9.942,
|
| 110 |
-
"step": 110
|
| 111 |
-
},
|
| 112 |
-
{
|
| 113 |
-
"epoch": 9.23076923076923,
|
| 114 |
-
"grad_norm": 0.34765625,
|
| 115 |
-
"learning_rate": 0.0001879473751206489,
|
| 116 |
-
"loss": 9.8887,
|
| 117 |
-
"step": 120
|
| 118 |
-
},
|
| 119 |
-
{
|
| 120 |
-
"epoch": 9.23076923076923,
|
| 121 |
-
"eval_loss": 9.867681503295898,
|
| 122 |
-
"eval_runtime": 5.2873,
|
| 123 |
-
"eval_samples_per_second": 283.888,
|
| 124 |
-
"eval_steps_per_second": 4.539,
|
| 125 |
-
"step": 120
|
| 126 |
-
},
|
| 127 |
-
{
|
| 128 |
-
"epoch": 10.0,
|
| 129 |
-
"grad_norm": 0.349609375,
|
| 130 |
-
"learning_rate": 0.00018519194088383273,
|
| 131 |
-
"loss": 9.836,
|
| 132 |
-
"step": 130
|
| 133 |
-
},
|
| 134 |
-
{
|
| 135 |
-
"epoch": 10.76923076923077,
|
| 136 |
-
"grad_norm": 0.357421875,
|
| 137 |
-
"learning_rate": 0.0001821777815225245,
|
| 138 |
-
"loss": 9.7845,
|
| 139 |
-
"step": 140
|
| 140 |
-
},
|
| 141 |
-
{
|
| 142 |
-
"epoch": 11.538461538461538,
|
| 143 |
-
"grad_norm": 0.361328125,
|
| 144 |
-
"learning_rate": 0.00017891405093963938,
|
| 145 |
-
"loss": 9.7359,
|
| 146 |
-
"step": 150
|
| 147 |
-
},
|
| 148 |
-
{
|
| 149 |
-
"epoch": 12.307692307692308,
|
| 150 |
-
"grad_norm": 0.369140625,
|
| 151 |
-
"learning_rate": 0.00017541066097768963,
|
| 152 |
-
"loss": 9.688,
|
| 153 |
-
"step": 160
|
| 154 |
-
},
|
| 155 |
-
{
|
| 156 |
-
"epoch": 12.307692307692308,
|
| 157 |
-
"eval_loss": 9.67237663269043,
|
| 158 |
-
"eval_runtime": 5.3075,
|
| 159 |
-
"eval_samples_per_second": 282.81,
|
| 160 |
-
"eval_steps_per_second": 4.522,
|
| 161 |
-
"step": 160
|
| 162 |
-
},
|
| 163 |
-
{
|
| 164 |
-
"epoch": 13.076923076923077,
|
| 165 |
-
"grad_norm": 0.3671875,
|
| 166 |
-
"learning_rate": 0.00017167825131684513,
|
| 167 |
-
"loss": 9.6416,
|
| 168 |
-
"step": 170
|
| 169 |
-
},
|
| 170 |
-
{
|
| 171 |
-
"epoch": 13.846153846153847,
|
| 172 |
-
"grad_norm": 0.375,
|
| 173 |
-
"learning_rate": 0.00016772815716257412,
|
| 174 |
-
"loss": 9.597,
|
| 175 |
-
"step": 180
|
| 176 |
-
},
|
| 177 |
-
{
|
| 178 |
-
"epoch": 14.615384615384615,
|
| 179 |
-
"grad_norm": 0.380859375,
|
| 180 |
-
"learning_rate": 0.00016357237482099684,
|
| 181 |
-
"loss": 9.5534,
|
| 182 |
-
"step": 190
|
| 183 |
-
},
|
| 184 |
-
{
|
| 185 |
-
"epoch": 15.384615384615385,
|
| 186 |
-
"grad_norm": 0.37890625,
|
| 187 |
-
"learning_rate": 0.00015922352526649803,
|
| 188 |
-
"loss": 9.5151,
|
| 189 |
-
"step": 200
|
| 190 |
-
},
|
| 191 |
-
{
|
| 192 |
-
"epoch": 15.384615384615385,
|
| 193 |
-
"eval_loss": 9.505026817321777,
|
| 194 |
-
"eval_runtime": 5.2791,
|
| 195 |
-
"eval_samples_per_second": 284.328,
|
| 196 |
-
"eval_steps_per_second": 4.546,
|
| 197 |
-
"step": 200
|
| 198 |
-
},
|
| 199 |
-
{
|
| 200 |
-
"epoch": 16.153846153846153,
|
| 201 |
-
"grad_norm": 0.3828125,
|
| 202 |
-
"learning_rate": 0.00015469481581224272,
|
| 203 |
-
"loss": 9.4734,
|
| 204 |
-
"step": 210
|
| 205 |
-
},
|
| 206 |
-
{
|
| 207 |
-
"epoch": 16.923076923076923,
|
| 208 |
-
"grad_norm": 0.388671875,
|
| 209 |
-
"learning_rate": 0.00015000000000000001,
|
| 210 |
-
"loss": 9.4381,
|
| 211 |
-
"step": 220
|
| 212 |
-
},
|
| 213 |
-
{
|
| 214 |
-
"epoch": 17.692307692307693,
|
| 215 |
-
"grad_norm": 0.39453125,
|
| 216 |
-
"learning_rate": 0.00014515333583108896,
|
| 217 |
-
"loss": 9.4021,
|
| 218 |
-
"step": 230
|
| 219 |
-
},
|
| 220 |
-
{
|
| 221 |
-
"epoch": 18.46153846153846,
|
| 222 |
-
"grad_norm": 0.396484375,
|
| 223 |
-
"learning_rate": 0.00014016954246529696,
|
| 224 |
-
"loss": 9.3725,
|
| 225 |
-
"step": 240
|
| 226 |
-
},
|
| 227 |
-
{
|
| 228 |
-
"epoch": 18.46153846153846,
|
| 229 |
-
"eval_loss": 9.3687162399292,
|
| 230 |
-
"eval_runtime": 5.2722,
|
| 231 |
-
"eval_samples_per_second": 284.702,
|
| 232 |
-
"eval_steps_per_second": 4.552,
|
| 233 |
-
"step": 240
|
| 234 |
-
},
|
| 235 |
-
{
|
| 236 |
-
"epoch": 19.23076923076923,
|
| 237 |
-
"grad_norm": 0.396484375,
|
| 238 |
-
"learning_rate": 0.00013506375551927547,
|
| 239 |
-
"loss": 9.3407,
|
| 240 |
-
"step": 250
|
| 241 |
-
},
|
| 242 |
-
{
|
| 243 |
-
"epoch": 20.0,
|
| 244 |
-
"grad_norm": 0.400390625,
|
| 245 |
-
"learning_rate": 0.00012985148110016947,
|
| 246 |
-
"loss": 9.3153,
|
| 247 |
-
"step": 260
|
| 248 |
-
},
|
| 249 |
-
{
|
| 250 |
-
"epoch": 20.76923076923077,
|
| 251 |
-
"grad_norm": 0.40234375,
|
| 252 |
-
"learning_rate": 0.00012454854871407994,
|
| 253 |
-
"loss": 9.2905,
|
| 254 |
-
"step": 270
|
| 255 |
-
},
|
| 256 |
-
{
|
| 257 |
-
"epoch": 21.53846153846154,
|
| 258 |
-
"grad_norm": 0.408203125,
|
| 259 |
-
"learning_rate": 0.00011917106319237386,
|
| 260 |
-
"loss": 9.2678,
|
| 261 |
-
"step": 280
|
| 262 |
-
},
|
| 263 |
-
{
|
| 264 |
-
"epoch": 21.53846153846154,
|
| 265 |
-
"eval_loss": 9.273423194885254,
|
| 266 |
-
"eval_runtime": 5.3547,
|
| 267 |
-
"eval_samples_per_second": 280.313,
|
| 268 |
-
"eval_steps_per_second": 4.482,
|
| 269 |
-
"step": 280
|
| 270 |
-
},
|
| 271 |
-
{
|
| 272 |
-
"epoch": 22.307692307692307,
|
| 273 |
-
"grad_norm": 0.404296875,
|
| 274 |
-
"learning_rate": 0.00011373535578184082,
|
| 275 |
-
"loss": 9.2496,
|
| 276 |
-
"step": 290
|
| 277 |
-
},
|
| 278 |
-
{
|
| 279 |
-
"epoch": 23.076923076923077,
|
| 280 |
-
"grad_norm": 0.40625,
|
| 281 |
-
"learning_rate": 0.00010825793454723325,
|
| 282 |
-
"loss": 9.2338,
|
| 283 |
-
"step": 300
|
| 284 |
-
},
|
| 285 |
-
{
|
| 286 |
-
"epoch": 23.846153846153847,
|
| 287 |
-
"grad_norm": 0.412109375,
|
| 288 |
-
"learning_rate": 0.00010275543423681621,
|
| 289 |
-
"loss": 9.2184,
|
| 290 |
-
"step": 310
|
| 291 |
-
},
|
| 292 |
-
{
|
| 293 |
-
"epoch": 24.615384615384617,
|
| 294 |
-
"grad_norm": 0.4140625,
|
| 295 |
-
"learning_rate": 9.724456576318381e-05,
|
| 296 |
-
"loss": 9.2101,
|
| 297 |
-
"step": 320
|
| 298 |
-
},
|
| 299 |
-
{
|
| 300 |
-
"epoch": 24.615384615384617,
|
| 301 |
-
"eval_loss": 9.220477104187012,
|
| 302 |
"eval_runtime": 5.2726,
|
| 303 |
-
"eval_samples_per_second": 284.
|
| 304 |
"eval_steps_per_second": 4.552,
|
| 305 |
-
"step":
|
| 306 |
-
},
|
| 307 |
-
{
|
| 308 |
-
"epoch": 25.384615384615383,
|
| 309 |
-
"grad_norm": 0.412109375,
|
| 310 |
-
"learning_rate": 9.174206545276677e-05,
|
| 311 |
-
"loss": 9.2001,
|
| 312 |
-
"step": 330
|
| 313 |
-
},
|
| 314 |
-
{
|
| 315 |
-
"epoch": 26.153846153846153,
|
| 316 |
-
"grad_norm": 0.416015625,
|
| 317 |
-
"learning_rate": 8.626464421815919e-05,
|
| 318 |
-
"loss": 9.193,
|
| 319 |
-
"step": 340
|
| 320 |
-
},
|
| 321 |
-
{
|
| 322 |
-
"epoch": 26.923076923076923,
|
| 323 |
-
"grad_norm": 0.41015625,
|
| 324 |
-
"learning_rate": 8.082893680762619e-05,
|
| 325 |
-
"loss": 9.1896,
|
| 326 |
-
"step": 350
|
| 327 |
-
},
|
| 328 |
-
{
|
| 329 |
-
"epoch": 27.692307692307693,
|
| 330 |
-
"grad_norm": 0.416015625,
|
| 331 |
-
"learning_rate": 7.54514512859201e-05,
|
| 332 |
-
"loss": 9.186,
|
| 333 |
-
"step": 360
|
| 334 |
-
},
|
| 335 |
-
{
|
| 336 |
-
"epoch": 27.692307692307693,
|
| 337 |
-
"eval_loss": 9.2018404006958,
|
| 338 |
-
"eval_runtime": 5.2765,
|
| 339 |
-
"eval_samples_per_second": 284.47,
|
| 340 |
-
"eval_steps_per_second": 4.548,
|
| 341 |
-
"step": 360
|
| 342 |
-
},
|
| 343 |
-
{
|
| 344 |
-
"epoch": 28.46153846153846,
|
| 345 |
-
"grad_norm": 0.412109375,
|
| 346 |
-
"learning_rate": 7.014851889983057e-05,
|
| 347 |
-
"loss": 9.182,
|
| 348 |
-
"step": 370
|
| 349 |
-
},
|
| 350 |
-
{
|
| 351 |
-
"epoch": 29.23076923076923,
|
| 352 |
-
"grad_norm": 0.416015625,
|
| 353 |
-
"learning_rate": 6.493624448072457e-05,
|
| 354 |
-
"loss": 9.1822,
|
| 355 |
-
"step": 380
|
| 356 |
-
},
|
| 357 |
-
{
|
| 358 |
-
"epoch": 30.0,
|
| 359 |
-
"grad_norm": 0.4140625,
|
| 360 |
-
"learning_rate": 5.983045753470308e-05,
|
| 361 |
-
"loss": 9.1806,
|
| 362 |
-
"step": 390
|
| 363 |
-
},
|
| 364 |
-
{
|
| 365 |
-
"epoch": 30.76923076923077,
|
| 366 |
-
"grad_norm": 0.419921875,
|
| 367 |
-
"learning_rate": 5.484666416891109e-05,
|
| 368 |
-
"loss": 9.18,
|
| 369 |
-
"step": 400
|
| 370 |
-
},
|
| 371 |
-
{
|
| 372 |
-
"epoch": 30.76923076923077,
|
| 373 |
-
"eval_loss": 9.19638442993164,
|
| 374 |
-
"eval_runtime": 5.3201,
|
| 375 |
-
"eval_samples_per_second": 282.139,
|
| 376 |
-
"eval_steps_per_second": 4.511,
|
| 377 |
-
"step": 400
|
| 378 |
-
},
|
| 379 |
-
{
|
| 380 |
-
"epoch": 31.53846153846154,
|
| 381 |
-
"grad_norm": 0.4140625,
|
| 382 |
-
"learning_rate": 5.000000000000002e-05,
|
| 383 |
-
"loss": 9.1787,
|
| 384 |
-
"step": 410
|
| 385 |
-
},
|
| 386 |
-
{
|
| 387 |
-
"epoch": 32.30769230769231,
|
| 388 |
-
"grad_norm": 0.419921875,
|
| 389 |
-
"learning_rate": 4.530518418775733e-05,
|
| 390 |
-
"loss": 9.1782,
|
| 391 |
-
"step": 420
|
| 392 |
-
},
|
| 393 |
-
{
|
| 394 |
-
"epoch": 33.07692307692308,
|
| 395 |
-
"grad_norm": 0.41796875,
|
| 396 |
-
"learning_rate": 4.077647473350201e-05,
|
| 397 |
-
"loss": 9.1776,
|
| 398 |
-
"step": 430
|
| 399 |
-
},
|
| 400 |
-
{
|
| 401 |
-
"epoch": 33.84615384615385,
|
| 402 |
-
"grad_norm": 0.416015625,
|
| 403 |
-
"learning_rate": 3.642762517900322e-05,
|
| 404 |
-
"loss": 9.1787,
|
| 405 |
-
"step": 440
|
| 406 |
-
},
|
| 407 |
-
{
|
| 408 |
-
"epoch": 33.84615384615385,
|
| 409 |
-
"eval_loss": 9.194502830505371,
|
| 410 |
-
"eval_runtime": 5.2758,
|
| 411 |
-
"eval_samples_per_second": 284.509,
|
| 412 |
-
"eval_steps_per_second": 4.549,
|
| 413 |
-
"step": 440
|
| 414 |
-
},
|
| 415 |
-
{
|
| 416 |
-
"epoch": 34.61538461538461,
|
| 417 |
-
"grad_norm": 0.416015625,
|
| 418 |
-
"learning_rate": 3.227184283742591e-05,
|
| 419 |
-
"loss": 9.1777,
|
| 420 |
-
"step": 450
|
| 421 |
-
},
|
| 422 |
-
{
|
| 423 |
-
"epoch": 35.38461538461539,
|
| 424 |
-
"grad_norm": 0.4140625,
|
| 425 |
-
"learning_rate": 2.8321748683154893e-05,
|
| 426 |
-
"loss": 9.1782,
|
| 427 |
-
"step": 460
|
| 428 |
-
},
|
| 429 |
-
{
|
| 430 |
-
"epoch": 36.15384615384615,
|
| 431 |
-
"grad_norm": 0.419921875,
|
| 432 |
-
"learning_rate": 2.4589339022310386e-05,
|
| 433 |
-
"loss": 9.1783,
|
| 434 |
-
"step": 470
|
| 435 |
-
},
|
| 436 |
-
{
|
| 437 |
-
"epoch": 36.92307692307692,
|
| 438 |
-
"grad_norm": 0.416015625,
|
| 439 |
-
"learning_rate": 2.1085949060360654e-05,
|
| 440 |
-
"loss": 9.1768,
|
| 441 |
-
"step": 480
|
| 442 |
-
},
|
| 443 |
-
{
|
| 444 |
-
"epoch": 36.92307692307692,
|
| 445 |
-
"eval_loss": 9.194061279296875,
|
| 446 |
-
"eval_runtime": 5.2795,
|
| 447 |
-
"eval_samples_per_second": 284.308,
|
| 448 |
-
"eval_steps_per_second": 4.546,
|
| 449 |
-
"step": 480
|
| 450 |
-
},
|
| 451 |
-
{
|
| 452 |
-
"epoch": 37.69230769230769,
|
| 453 |
-
"grad_norm": 0.4140625,
|
| 454 |
-
"learning_rate": 1.7822218477475494e-05,
|
| 455 |
-
"loss": 9.1778,
|
| 456 |
-
"step": 490
|
| 457 |
-
},
|
| 458 |
-
{
|
| 459 |
-
"epoch": 38.46153846153846,
|
| 460 |
-
"grad_norm": 0.419921875,
|
| 461 |
-
"learning_rate": 1.4808059116167305e-05,
|
| 462 |
-
"loss": 9.1781,
|
| 463 |
-
"step": 500
|
| 464 |
-
},
|
| 465 |
-
{
|
| 466 |
-
"epoch": 39.23076923076923,
|
| 467 |
-
"grad_norm": 0.419921875,
|
| 468 |
-
"learning_rate": 1.2052624879351104e-05,
|
| 469 |
-
"loss": 9.1771,
|
| 470 |
-
"step": 510
|
| 471 |
-
},
|
| 472 |
-
{
|
| 473 |
-
"epoch": 40.0,
|
| 474 |
-
"grad_norm": 0.419921875,
|
| 475 |
-
"learning_rate": 9.564283930242257e-06,
|
| 476 |
-
"loss": 9.1775,
|
| 477 |
-
"step": 520
|
| 478 |
-
},
|
| 479 |
-
{
|
| 480 |
-
"epoch": 40.0,
|
| 481 |
-
"eval_loss": 9.193778991699219,
|
| 482 |
-
"eval_runtime": 5.2716,
|
| 483 |
-
"eval_samples_per_second": 284.736,
|
| 484 |
-
"eval_steps_per_second": 4.553,
|
| 485 |
-
"step": 520
|
| 486 |
-
},
|
| 487 |
-
{
|
| 488 |
-
"epoch": 40.76923076923077,
|
| 489 |
-
"grad_norm": 0.416015625,
|
| 490 |
-
"learning_rate": 7.350593278519824e-06,
|
| 491 |
-
"loss": 9.1773,
|
| 492 |
-
"step": 530
|
| 493 |
-
},
|
| 494 |
-
{
|
| 495 |
-
"epoch": 41.53846153846154,
|
| 496 |
-
"grad_norm": 0.41796875,
|
| 497 |
-
"learning_rate": 5.418275829936537e-06,
|
| 498 |
-
"loss": 9.1786,
|
| 499 |
-
"step": 540
|
| 500 |
-
},
|
| 501 |
-
{
|
| 502 |
-
"epoch": 42.30769230769231,
|
| 503 |
-
"grad_norm": 0.41796875,
|
| 504 |
-
"learning_rate": 3.7731999690749585e-06,
|
| 505 |
-
"loss": 9.1761,
|
| 506 |
-
"step": 550
|
| 507 |
-
},
|
| 508 |
-
{
|
| 509 |
-
"epoch": 43.07692307692308,
|
| 510 |
-
"grad_norm": 0.4140625,
|
| 511 |
-
"learning_rate": 2.420361737256438e-06,
|
| 512 |
-
"loss": 9.1784,
|
| 513 |
-
"step": 560
|
| 514 |
-
},
|
| 515 |
-
{
|
| 516 |
-
"epoch": 43.07692307692308,
|
| 517 |
-
"eval_loss": 9.194928169250488,
|
| 518 |
-
"eval_runtime": 5.2748,
|
| 519 |
-
"eval_samples_per_second": 284.561,
|
| 520 |
-
"eval_steps_per_second": 4.55,
|
| 521 |
-
"step": 560
|
| 522 |
-
},
|
| 523 |
-
{
|
| 524 |
-
"epoch": 43.84615384615385,
|
| 525 |
-
"grad_norm": 0.41796875,
|
| 526 |
-
"learning_rate": 1.3638696597277679e-06,
|
| 527 |
-
"loss": 9.1777,
|
| 528 |
-
"step": 570
|
| 529 |
-
},
|
| 530 |
-
{
|
| 531 |
-
"epoch": 44.61538461538461,
|
| 532 |
-
"grad_norm": 0.419921875,
|
| 533 |
-
"learning_rate": 6.069322682050516e-07,
|
| 534 |
-
"loss": 9.1766,
|
| 535 |
-
"step": 580
|
| 536 |
-
},
|
| 537 |
-
{
|
| 538 |
-
"epoch": 45.38461538461539,
|
| 539 |
-
"grad_norm": 0.412109375,
|
| 540 |
-
"learning_rate": 1.518483566683826e-07,
|
| 541 |
-
"loss": 9.1785,
|
| 542 |
-
"step": 590
|
| 543 |
-
},
|
| 544 |
-
{
|
| 545 |
-
"epoch": 46.15384615384615,
|
| 546 |
-
"grad_norm": 0.419921875,
|
| 547 |
-
"learning_rate": 0.0,
|
| 548 |
-
"loss": 9.1762,
|
| 549 |
-
"step": 600
|
| 550 |
-
},
|
| 551 |
-
{
|
| 552 |
-
"epoch": 46.15384615384615,
|
| 553 |
-
"eval_loss": 9.19438362121582,
|
| 554 |
-
"eval_runtime": 5.3128,
|
| 555 |
-
"eval_samples_per_second": 282.527,
|
| 556 |
-
"eval_steps_per_second": 4.517,
|
| 557 |
-
"step": 600
|
| 558 |
}
|
| 559 |
],
|
| 560 |
"logging_steps": 10,
|
| 561 |
"max_steps": 600,
|
| 562 |
"num_input_tokens_seen": 0,
|
| 563 |
"num_train_epochs": 47,
|
| 564 |
-
"save_steps":
|
| 565 |
"stateful_callbacks": {
|
| 566 |
"TrainerControl": {
|
| 567 |
"args": {
|
|
@@ -569,12 +72,12 @@
|
|
| 569 |
"should_evaluate": false,
|
| 570 |
"should_log": false,
|
| 571 |
"should_save": true,
|
| 572 |
-
"should_training_stop":
|
| 573 |
},
|
| 574 |
"attributes": {}
|
| 575 |
}
|
| 576 |
},
|
| 577 |
-
"total_flos":
|
| 578 |
"train_batch_size": 32,
|
| 579 |
"trial_name": null,
|
| 580 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 3.8461538461538463,
|
| 5 |
+
"eval_steps": 50,
|
| 6 |
+
"global_step": 50,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 11 |
{
|
| 12 |
"epoch": 0.07692307692307693,
|
| 13 |
"eval_loss": 10.376392364501953,
|
| 14 |
+
"eval_runtime": 5.3202,
|
| 15 |
+
"eval_samples_per_second": 282.131,
|
| 16 |
+
"eval_steps_per_second": 4.511,
|
| 17 |
"step": 1
|
| 18 |
},
|
| 19 |
{
|
|
|
|
| 44 |
"loss": 10.3522,
|
| 45 |
"step": 40
|
| 46 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 47 |
{
|
| 48 |
"epoch": 3.8461538461538463,
|
| 49 |
"grad_norm": 0.3203125,
|
|
|
|
| 52 |
"step": 50
|
| 53 |
},
|
| 54 |
{
|
| 55 |
+
"epoch": 3.8461538461538463,
|
| 56 |
+
"eval_loss": 10.285228729248047,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 57 |
"eval_runtime": 5.2726,
|
| 58 |
+
"eval_samples_per_second": 284.681,
|
| 59 |
"eval_steps_per_second": 4.552,
|
| 60 |
+
"step": 50
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 61 |
}
|
| 62 |
],
|
| 63 |
"logging_steps": 10,
|
| 64 |
"max_steps": 600,
|
| 65 |
"num_input_tokens_seen": 0,
|
| 66 |
"num_train_epochs": 47,
|
| 67 |
+
"save_steps": 50,
|
| 68 |
"stateful_callbacks": {
|
| 69 |
"TrainerControl": {
|
| 70 |
"args": {
|
|
|
|
| 72 |
"should_evaluate": false,
|
| 73 |
"should_log": false,
|
| 74 |
"should_save": true,
|
| 75 |
+
"should_training_stop": false
|
| 76 |
},
|
| 77 |
"attributes": {}
|
| 78 |
}
|
| 79 |
},
|
| 80 |
+
"total_flos": 20457927475200.0,
|
| 81 |
"train_batch_size": 32,
|
| 82 |
"trial_name": null,
|
| 83 |
"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 6904
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:120614a5953861571b441322c20a1add8c543820ada9a66731f41e9cf2b7b9de
|
| 3 |
size 6904
|