Rodo-Sami commited on
Commit
41bb319
·
verified ·
1 Parent(s): ce5b5f0

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 sha256:1dcd5fb4856e11bbf274d3bba7c89ceb65fea52385cbe2940edd03888dd4cb8e
3
  size 319876032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:264d2b60416d5e465c5eb93918a04d762377fa8ff324bf6117e8ee19dacf14b9
3
  size 319876032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f613b844ace0327a06e80c3bbe801358341260010f4120c7b35f81a711359e99
3
  size 640009682
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83c2aac1632d13c6352fe9e5534a9da62abc0d1e2dcacdd1f1eaa8844a629c33
3
  size 640009682
last-checkpoint/rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ca26cd479827a1640e3f7c6a7454f072d913f4f395d1bfea4982ad5bcf08fc04
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3cbfe626dd4bd5a1aa6cd5d5d57099509c169c0727d36250d6c75bf9f0245033
3
  size 15024
last-checkpoint/rng_state_1.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ab2735f25c72fc9665b772cae9c46d654e884d526370c0cef883c8407391be0d
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd4f50b03f2922a175655f61b408c895901975b432a8e9d549c037a05f5a1f8f
3
  size 15024
last-checkpoint/rng_state_2.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4115f9aa68f80c1b4ccea841b66d1c1325e7385f47c83b057f4fc32f5b624225
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:138a9a54f798c70911413670494691461e27871396cb976a89e5e55976282b86
3
  size 15024
last-checkpoint/rng_state_3.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9223a78f8b40965ac96b35f3958857cc977ab3cf50cfc78e94bc99cd7d5466b1
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39f1d760ee37963744a86924be1fe5790c4f1c17c8621701f9fb691ec45f92eb
3
  size 15024
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f37b2aa490ccb1598b01e14cda36e9081f7ce646deab4d3c2d03de0d2169a755
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": 0.003064053598791361,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-25",
4
- "epoch": 0.08462026655383964,
5
  "eval_steps": 25,
6
- "global_step": 25,
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": 34.689,
199
  "eval_steps_per_second": 4.34,
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": false
225
  },
226
  "attributes": {}
227
  }
228
  },
229
- "total_flos": 2.652642132099072e+17,
230
  "train_batch_size": 2,
231
  "trial_name": null,
232
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.0014108235482126474,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
+ "epoch": 0.16924053310767928,
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": 34.689,
199
  "eval_steps_per_second": 4.34,
200
  "step": 25
201
+ },
202
+ {
203
+ "epoch": 0.08800507721599322,
204
+ "grad_norm": 1.4910016059875488,
205
+ "learning_rate": 5e-05,
206
+ "loss": 0.0228,
207
+ "step": 26
208
+ },
209
+ {
210
+ "epoch": 0.09138988787814682,
211
+ "grad_norm": 0.24254511296749115,
212
+ "learning_rate": 4.6729843538492847e-05,
213
+ "loss": 0.0037,
214
+ "step": 27
215
+ },
216
+ {
217
+ "epoch": 0.0947746985403004,
218
+ "grad_norm": 0.2668854892253876,
219
+ "learning_rate": 4.347369038899744e-05,
220
+ "loss": 0.0015,
221
+ "step": 28
222
+ },
223
+ {
224
+ "epoch": 0.09815950920245399,
225
+ "grad_norm": 0.5330218076705933,
226
+ "learning_rate": 4.0245483899193595e-05,
227
+ "loss": 0.0019,
228
+ "step": 29
229
+ },
230
+ {
231
+ "epoch": 0.10154431986460757,
232
+ "grad_norm": 0.03539638966321945,
233
+ "learning_rate": 3.705904774487396e-05,
234
+ "loss": 0.0012,
235
+ "step": 30
236
+ },
237
+ {
238
+ "epoch": 0.10492913052676116,
239
+ "grad_norm": 0.034347571432590485,
240
+ "learning_rate": 3.392802673484193e-05,
241
+ "loss": 0.0012,
242
+ "step": 31
243
+ },
244
+ {
245
+ "epoch": 0.10831394118891474,
246
+ "grad_norm": 0.054929472506046295,
247
+ "learning_rate": 3.086582838174551e-05,
248
+ "loss": 0.001,
249
+ "step": 32
250
+ },
251
+ {
252
+ "epoch": 0.11169875185106833,
253
+ "grad_norm": 0.197361558675766,
254
+ "learning_rate": 2.7885565489049946e-05,
255
+ "loss": 0.0021,
256
+ "step": 33
257
+ },
258
+ {
259
+ "epoch": 0.11508356251322191,
260
+ "grad_norm": 0.18690542876720428,
261
+ "learning_rate": 2.500000000000001e-05,
262
+ "loss": 0.004,
263
+ "step": 34
264
+ },
265
+ {
266
+ "epoch": 0.11846837317537551,
267
+ "grad_norm": 0.010866144672036171,
268
+ "learning_rate": 2.2221488349019903e-05,
269
+ "loss": 0.0006,
270
+ "step": 35
271
+ },
272
+ {
273
+ "epoch": 0.12185318383752909,
274
+ "grad_norm": 0.037227921187877655,
275
+ "learning_rate": 1.9561928549563968e-05,
276
+ "loss": 0.0008,
277
+ "step": 36
278
+ },
279
+ {
280
+ "epoch": 0.12523799449968268,
281
+ "grad_norm": 0.026730114594101906,
282
+ "learning_rate": 1.703270924499656e-05,
283
+ "loss": 0.0015,
284
+ "step": 37
285
+ },
286
+ {
287
+ "epoch": 0.12862280516183627,
288
+ "grad_norm": 0.09857242554426193,
289
+ "learning_rate": 1.4644660940672627e-05,
290
+ "loss": 0.0032,
291
+ "step": 38
292
+ },
293
+ {
294
+ "epoch": 0.13200761582398984,
295
+ "grad_norm": 0.08650778979063034,
296
+ "learning_rate": 1.2408009626051137e-05,
297
+ "loss": 0.0017,
298
+ "step": 39
299
+ },
300
+ {
301
+ "epoch": 0.13539242648614344,
302
+ "grad_norm": 0.02394554391503334,
303
+ "learning_rate": 1.0332332985438248e-05,
304
+ "loss": 0.0013,
305
+ "step": 40
306
+ },
307
+ {
308
+ "epoch": 0.138777237148297,
309
+ "grad_norm": 0.3927086889743805,
310
+ "learning_rate": 8.426519384872733e-06,
311
+ "loss": 0.0048,
312
+ "step": 41
313
+ },
314
+ {
315
+ "epoch": 0.1421620478104506,
316
+ "grad_norm": 0.02811684086918831,
317
+ "learning_rate": 6.698729810778065e-06,
318
+ "loss": 0.0013,
319
+ "step": 42
320
+ },
321
+ {
322
+ "epoch": 0.14554685847260418,
323
+ "grad_norm": 0.04668286442756653,
324
+ "learning_rate": 5.156362923365588e-06,
325
+ "loss": 0.0011,
326
+ "step": 43
327
+ },
328
+ {
329
+ "epoch": 0.14893166913475778,
330
+ "grad_norm": 0.05839909240603447,
331
+ "learning_rate": 3.8060233744356633e-06,
332
+ "loss": 0.0014,
333
+ "step": 44
334
+ },
335
+ {
336
+ "epoch": 0.15231647979691135,
337
+ "grad_norm": 0.06195997819304466,
338
+ "learning_rate": 2.653493525244721e-06,
339
+ "loss": 0.0012,
340
+ "step": 45
341
+ },
342
+ {
343
+ "epoch": 0.15570129045906494,
344
+ "grad_norm": 0.02771010622382164,
345
+ "learning_rate": 1.70370868554659e-06,
346
+ "loss": 0.0011,
347
+ "step": 46
348
+ },
349
+ {
350
+ "epoch": 0.15908610112121854,
351
+ "grad_norm": 0.02765018679201603,
352
+ "learning_rate": 9.607359798384785e-07,
353
+ "loss": 0.0006,
354
+ "step": 47
355
+ },
356
+ {
357
+ "epoch": 0.1624709117833721,
358
+ "grad_norm": 0.028453974053263664,
359
+ "learning_rate": 4.277569313094809e-07,
360
+ "loss": 0.0009,
361
+ "step": 48
362
+ },
363
+ {
364
+ "epoch": 0.1658557224455257,
365
+ "grad_norm": 0.0173852127045393,
366
+ "learning_rate": 1.0705383806982606e-07,
367
+ "loss": 0.0012,
368
+ "step": 49
369
+ },
370
+ {
371
+ "epoch": 0.16924053310767928,
372
+ "grad_norm": 0.02612384408712387,
373
+ "learning_rate": 0.0,
374
+ "loss": 0.001,
375
+ "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.16924053310767928,
379
+ "eval_loss": 0.0014108235482126474,
380
+ "eval_runtime": 57.3651,
381
+ "eval_samples_per_second": 34.69,
382
+ "eval_steps_per_second": 4.341,
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": 5.305284264198144e+17,
413
  "train_batch_size": 2,
414
  "trial_name": null,
415
  "trial_params": null