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 3152280
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0f42bdd53eae1f6066a19e8bc842cf167180aa4250c10903b8d81c7a8d94f43c
|
| 3 |
size 3152280
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1655994
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bf15b084871635b7d58f560d1a52a2fc91003918a3245a73d323de7db833cbcf
|
| 3 |
size 1655994
|
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 sha256:0ab5ccdad43927d63bd8d76fd77baa5de4bf6004eef00d57d059343b275b46f9
|
| 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": 4.
|
| 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": 431.91,
|
| 199 |
"eval_steps_per_second": 53.989,
|
| 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": 8,
|
| 231 |
"trial_name": null,
|
| 232 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 4.609181880950928,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-50",
|
| 4 |
+
"epoch": 0.4056795131845842,
|
| 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": 431.91,
|
| 199 |
"eval_steps_per_second": 53.989,
|
| 200 |
"step": 25
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 0.21095334685598377,
|
| 204 |
+
"grad_norm": 19504.337890625,
|
| 205 |
+
"learning_rate": 5.522642316338268e-05,
|
| 206 |
+
"loss": 17.9022,
|
| 207 |
+
"step": 26
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 0.21906693711967545,
|
| 211 |
+
"grad_norm": 22843.296875,
|
| 212 |
+
"learning_rate": 5.174497483512506e-05,
|
| 213 |
+
"loss": 16.5643,
|
| 214 |
+
"step": 27
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 0.22718052738336714,
|
| 218 |
+
"grad_norm": 26412.322265625,
|
| 219 |
+
"learning_rate": 4.825502516487497e-05,
|
| 220 |
+
"loss": 18.8916,
|
| 221 |
+
"step": 28
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 0.23529411764705882,
|
| 225 |
+
"grad_norm": 26284.06640625,
|
| 226 |
+
"learning_rate": 4.477357683661734e-05,
|
| 227 |
+
"loss": 16.6758,
|
| 228 |
+
"step": 29
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 0.2434077079107505,
|
| 232 |
+
"grad_norm": 21581.443359375,
|
| 233 |
+
"learning_rate": 4.131759111665349e-05,
|
| 234 |
+
"loss": 16.0591,
|
| 235 |
+
"step": 30
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"epoch": 0.2515212981744422,
|
| 239 |
+
"grad_norm": 5018.412109375,
|
| 240 |
+
"learning_rate": 3.790390522001662e-05,
|
| 241 |
+
"loss": 24.0238,
|
| 242 |
+
"step": 31
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 0.25963488843813387,
|
| 246 |
+
"grad_norm": 6716.75048828125,
|
| 247 |
+
"learning_rate": 3.4549150281252636e-05,
|
| 248 |
+
"loss": 19.779,
|
| 249 |
+
"step": 32
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.26774847870182555,
|
| 253 |
+
"grad_norm": 10650.5966796875,
|
| 254 |
+
"learning_rate": 3.12696703292044e-05,
|
| 255 |
+
"loss": 19.1537,
|
| 256 |
+
"step": 33
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 0.27586206896551724,
|
| 260 |
+
"grad_norm": 11114.6806640625,
|
| 261 |
+
"learning_rate": 2.8081442660546125e-05,
|
| 262 |
+
"loss": 18.7671,
|
| 263 |
+
"step": 34
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 0.2839756592292089,
|
| 267 |
+
"grad_norm": 16058.6171875,
|
| 268 |
+
"learning_rate": 2.500000000000001e-05,
|
| 269 |
+
"loss": 18.4901,
|
| 270 |
+
"step": 35
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 0.2920892494929006,
|
| 274 |
+
"grad_norm": 13689.95703125,
|
| 275 |
+
"learning_rate": 2.2040354826462668e-05,
|
| 276 |
+
"loss": 19.7398,
|
| 277 |
+
"step": 36
|
| 278 |
+
},
|
| 279 |
+
{
|
| 280 |
+
"epoch": 0.3002028397565923,
|
| 281 |
+
"grad_norm": 21634.2890625,
|
| 282 |
+
"learning_rate": 1.9216926233717085e-05,
|
| 283 |
+
"loss": 20.0653,
|
| 284 |
+
"step": 37
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 0.30831643002028397,
|
| 288 |
+
"grad_norm": 27462.826171875,
|
| 289 |
+
"learning_rate": 1.6543469682057106e-05,
|
| 290 |
+
"loss": 21.0282,
|
| 291 |
+
"step": 38
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 0.31643002028397565,
|
| 295 |
+
"grad_norm": 27072.787109375,
|
| 296 |
+
"learning_rate": 1.4033009983067452e-05,
|
| 297 |
+
"loss": 20.6084,
|
| 298 |
+
"step": 39
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 0.32454361054766734,
|
| 302 |
+
"grad_norm": 24505.671875,
|
| 303 |
+
"learning_rate": 1.1697777844051105e-05,
|
| 304 |
+
"loss": 20.9536,
|
| 305 |
+
"step": 40
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 0.332657200811359,
|
| 309 |
+
"grad_norm": 27974.205078125,
|
| 310 |
+
"learning_rate": 9.549150281252633e-06,
|
| 311 |
+
"loss": 23.1919,
|
| 312 |
+
"step": 41
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 0.3407707910750507,
|
| 316 |
+
"grad_norm": 24215.720703125,
|
| 317 |
+
"learning_rate": 7.597595192178702e-06,
|
| 318 |
+
"loss": 21.044,
|
| 319 |
+
"step": 42
|
| 320 |
+
},
|
| 321 |
+
{
|
| 322 |
+
"epoch": 0.3488843813387424,
|
| 323 |
+
"grad_norm": 28061.6875,
|
| 324 |
+
"learning_rate": 5.852620357053651e-06,
|
| 325 |
+
"loss": 21.3492,
|
| 326 |
+
"step": 43
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 0.35699797160243407,
|
| 330 |
+
"grad_norm": 21789.685546875,
|
| 331 |
+
"learning_rate": 4.322727117869951e-06,
|
| 332 |
+
"loss": 20.3473,
|
| 333 |
+
"step": 44
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 0.36511156186612576,
|
| 337 |
+
"grad_norm": 24379.7890625,
|
| 338 |
+
"learning_rate": 3.0153689607045845e-06,
|
| 339 |
+
"loss": 22.5963,
|
| 340 |
+
"step": 45
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 0.37322515212981744,
|
| 344 |
+
"grad_norm": 33108.9296875,
|
| 345 |
+
"learning_rate": 1.9369152030840556e-06,
|
| 346 |
+
"loss": 17.4469,
|
| 347 |
+
"step": 46
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"epoch": 0.3813387423935091,
|
| 351 |
+
"grad_norm": 34678.03125,
|
| 352 |
+
"learning_rate": 1.0926199633097157e-06,
|
| 353 |
+
"loss": 18.6767,
|
| 354 |
+
"step": 47
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 0.3894523326572008,
|
| 358 |
+
"grad_norm": 19315.302734375,
|
| 359 |
+
"learning_rate": 4.865965629214819e-07,
|
| 360 |
+
"loss": 17.476,
|
| 361 |
+
"step": 48
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 0.3975659229208925,
|
| 365 |
+
"grad_norm": 23598.388671875,
|
| 366 |
+
"learning_rate": 1.2179748700879012e-07,
|
| 367 |
+
"loss": 16.2114,
|
| 368 |
+
"step": 49
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 0.4056795131845842,
|
| 372 |
+
"grad_norm": 15638.3642578125,
|
| 373 |
+
"learning_rate": 0.0,
|
| 374 |
+
"loss": 16.4387,
|
| 375 |
+
"step": 50
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.4056795131845842,
|
| 379 |
+
"eval_loss": 4.609181880950928,
|
| 380 |
+
"eval_runtime": 0.4802,
|
| 381 |
+
"eval_samples_per_second": 433.185,
|
| 382 |
+
"eval_steps_per_second": 54.148,
|
| 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": 67420953772032.0,
|
| 413 |
"train_batch_size": 8,
|
| 414 |
"trial_name": null,
|
| 415 |
"trial_params": null
|