Training in progress, step 50, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 125048
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:203f6182ac8561c07cd1ace88db4e27016e57ce92f4f081ca67d1c038bdfabdd
|
| 3 |
size 125048
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 162868
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b4db1b35ee4408194e891cdb704b883592e01e7dec6dec012265977d17a75394
|
| 3 |
size 162868
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14244
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:edbcf2d15803e2421fecb3f78827c12e7e0cfd18cfa9f829993ebbbd3c374be1
|
| 3 |
size 14244
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1064
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 11.
|
| 3 |
-
"best_model_checkpoint": "miner_id_24/checkpoint-
|
| 4 |
-
"epoch": 0.
|
| 5 |
"eval_steps": 25,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -198,6 +198,189 @@
|
|
| 198 |
"eval_samples_per_second": 245.387,
|
| 199 |
"eval_steps_per_second": 122.693,
|
| 200 |
"step": 25
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 201 |
}
|
| 202 |
],
|
| 203 |
"logging_steps": 1,
|
|
@@ -221,12 +404,12 @@
|
|
| 221 |
"should_evaluate": false,
|
| 222 |
"should_log": false,
|
| 223 |
"should_save": true,
|
| 224 |
-
"should_training_stop":
|
| 225 |
},
|
| 226 |
"attributes": {}
|
| 227 |
}
|
| 228 |
},
|
| 229 |
-
"total_flos":
|
| 230 |
"train_batch_size": 2,
|
| 231 |
"trial_name": null,
|
| 232 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 11.072815895080566,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-50",
|
| 4 |
+
"epoch": 0.8,
|
| 5 |
"eval_steps": 25,
|
| 6 |
+
"global_step": 50,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 198 |
"eval_samples_per_second": 245.387,
|
| 199 |
"eval_steps_per_second": 122.693,
|
| 200 |
"step": 25
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 0.416,
|
| 204 |
+
"grad_norm": 4.728461742401123,
|
| 205 |
+
"learning_rate": 6.545084971874738e-05,
|
| 206 |
+
"loss": 177.3756,
|
| 207 |
+
"step": 26
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 0.432,
|
| 211 |
+
"grad_norm": 5.435032367706299,
|
| 212 |
+
"learning_rate": 6.167226819279528e-05,
|
| 213 |
+
"loss": 177.3018,
|
| 214 |
+
"step": 27
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 0.448,
|
| 218 |
+
"grad_norm": 5.371153831481934,
|
| 219 |
+
"learning_rate": 5.782172325201155e-05,
|
| 220 |
+
"loss": 177.4762,
|
| 221 |
+
"step": 28
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 0.464,
|
| 225 |
+
"grad_norm": 4.894636631011963,
|
| 226 |
+
"learning_rate": 5.392295478639225e-05,
|
| 227 |
+
"loss": 177.4025,
|
| 228 |
+
"step": 29
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 0.48,
|
| 232 |
+
"grad_norm": 5.693634510040283,
|
| 233 |
+
"learning_rate": 5e-05,
|
| 234 |
+
"loss": 177.4451,
|
| 235 |
+
"step": 30
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"epoch": 0.496,
|
| 239 |
+
"grad_norm": 4.987210273742676,
|
| 240 |
+
"learning_rate": 4.607704521360776e-05,
|
| 241 |
+
"loss": 177.2171,
|
| 242 |
+
"step": 31
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 0.512,
|
| 246 |
+
"grad_norm": 6.440840244293213,
|
| 247 |
+
"learning_rate": 4.2178276747988446e-05,
|
| 248 |
+
"loss": 177.2202,
|
| 249 |
+
"step": 32
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.528,
|
| 253 |
+
"grad_norm": 5.610371112823486,
|
| 254 |
+
"learning_rate": 3.832773180720475e-05,
|
| 255 |
+
"loss": 177.2815,
|
| 256 |
+
"step": 33
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 0.544,
|
| 260 |
+
"grad_norm": 5.382572650909424,
|
| 261 |
+
"learning_rate": 3.4549150281252636e-05,
|
| 262 |
+
"loss": 177.4306,
|
| 263 |
+
"step": 34
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 0.56,
|
| 267 |
+
"grad_norm": 5.3845086097717285,
|
| 268 |
+
"learning_rate": 3.086582838174551e-05,
|
| 269 |
+
"loss": 177.2016,
|
| 270 |
+
"step": 35
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 0.576,
|
| 274 |
+
"grad_norm": 5.593583106994629,
|
| 275 |
+
"learning_rate": 2.7300475013022663e-05,
|
| 276 |
+
"loss": 177.2794,
|
| 277 |
+
"step": 36
|
| 278 |
+
},
|
| 279 |
+
{
|
| 280 |
+
"epoch": 0.592,
|
| 281 |
+
"grad_norm": 5.033830642700195,
|
| 282 |
+
"learning_rate": 2.3875071764202563e-05,
|
| 283 |
+
"loss": 177.1855,
|
| 284 |
+
"step": 37
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 0.608,
|
| 288 |
+
"grad_norm": 5.018127918243408,
|
| 289 |
+
"learning_rate": 2.061073738537635e-05,
|
| 290 |
+
"loss": 177.1274,
|
| 291 |
+
"step": 38
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 0.624,
|
| 295 |
+
"grad_norm": 5.058304309844971,
|
| 296 |
+
"learning_rate": 1.7527597583490822e-05,
|
| 297 |
+
"loss": 177.3111,
|
| 298 |
+
"step": 39
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 0.64,
|
| 302 |
+
"grad_norm": 5.06426477432251,
|
| 303 |
+
"learning_rate": 1.4644660940672627e-05,
|
| 304 |
+
"loss": 177.2481,
|
| 305 |
+
"step": 40
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 0.656,
|
| 309 |
+
"grad_norm": 5.429646015167236,
|
| 310 |
+
"learning_rate": 1.1979701719998453e-05,
|
| 311 |
+
"loss": 177.2853,
|
| 312 |
+
"step": 41
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 0.672,
|
| 316 |
+
"grad_norm": 5.491520404815674,
|
| 317 |
+
"learning_rate": 9.549150281252633e-06,
|
| 318 |
+
"loss": 177.268,
|
| 319 |
+
"step": 42
|
| 320 |
+
},
|
| 321 |
+
{
|
| 322 |
+
"epoch": 0.688,
|
| 323 |
+
"grad_norm": 5.68138313293457,
|
| 324 |
+
"learning_rate": 7.367991782295391e-06,
|
| 325 |
+
"loss": 177.2044,
|
| 326 |
+
"step": 43
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 0.704,
|
| 330 |
+
"grad_norm": 5.430667877197266,
|
| 331 |
+
"learning_rate": 5.449673790581611e-06,
|
| 332 |
+
"loss": 177.1413,
|
| 333 |
+
"step": 44
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 0.72,
|
| 337 |
+
"grad_norm": 5.618349075317383,
|
| 338 |
+
"learning_rate": 3.8060233744356633e-06,
|
| 339 |
+
"loss": 177.3678,
|
| 340 |
+
"step": 45
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 0.736,
|
| 344 |
+
"grad_norm": 5.020064353942871,
|
| 345 |
+
"learning_rate": 2.4471741852423237e-06,
|
| 346 |
+
"loss": 177.4148,
|
| 347 |
+
"step": 46
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"epoch": 0.752,
|
| 351 |
+
"grad_norm": 4.966926097869873,
|
| 352 |
+
"learning_rate": 1.3815039801161721e-06,
|
| 353 |
+
"loss": 177.1741,
|
| 354 |
+
"step": 47
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 0.768,
|
| 358 |
+
"grad_norm": 5.503310203552246,
|
| 359 |
+
"learning_rate": 6.15582970243117e-07,
|
| 360 |
+
"loss": 177.2908,
|
| 361 |
+
"step": 48
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 0.784,
|
| 365 |
+
"grad_norm": 5.39885139465332,
|
| 366 |
+
"learning_rate": 1.5413331334360182e-07,
|
| 367 |
+
"loss": 177.5115,
|
| 368 |
+
"step": 49
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 0.8,
|
| 372 |
+
"grad_norm": 4.973806858062744,
|
| 373 |
+
"learning_rate": 0.0,
|
| 374 |
+
"loss": 177.3928,
|
| 375 |
+
"step": 50
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.8,
|
| 379 |
+
"eval_loss": 11.072815895080566,
|
| 380 |
+
"eval_runtime": 0.4307,
|
| 381 |
+
"eval_samples_per_second": 246.086,
|
| 382 |
+
"eval_steps_per_second": 123.043,
|
| 383 |
+
"step": 50
|
| 384 |
}
|
| 385 |
],
|
| 386 |
"logging_steps": 1,
|
|
|
|
| 404 |
"should_evaluate": false,
|
| 405 |
"should_log": false,
|
| 406 |
"should_save": true,
|
| 407 |
+
"should_training_stop": true
|
| 408 |
},
|
| 409 |
"attributes": {}
|
| 410 |
}
|
| 411 |
},
|
| 412 |
+
"total_flos": 1050673152000.0,
|
| 413 |
"train_batch_size": 2,
|
| 414 |
"trial_name": null,
|
| 415 |
"trial_params": null
|