dada22231 commited on
Commit
401f10a
1 Parent(s): 6b60088

Training in progress, step 50, checkpoint

Browse files
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e48e4a42d5b83281f75491c7b54216484f34e0a9099b433e9ea3709fa6f6bfee
3
  size 141053442
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c79c881928c01183186d36cf8fc2b8a93d944f13824643ebc632285c19511fce
3
  size 141053442
last-checkpoint/rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e44e5fe31937b4799c6231e0a3e3b3781ada07119ebe630a3e9db01020969c51
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f42bcc3d5a7780bbfdf2f3a2dd310533942cc1a7daba4bba71cc9190a8ff7a4f
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 sha256:4bd00ae53d2c311916d6881e828d7563797ceff6e8f0dba5d80b7181cd99478e
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:906a4f9aaa923edcd0bbad58070787fdbfc7346cd0f27289b8ddbf4ad0b5b97b
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:ae0473852757a3424c0d03588c09be5f2f757192275683a837c9304ffa271ecf
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b69a62ecbd94a05cce59e49c042d4f56fc143eb947140e6223d762628381d7b
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:c156b299f14def071dead23d3d7b85d49a1160c047c4f14ba262b44c50a54a51
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f77bb8910f4bad63417a2e9bc34997892faac8c1432df601758e94d40b0aa1cd
3
  size 15024
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0f5c305e4a92be904895c02f0f0a1da666e6e7555f6043a8f089990c87f4ce88
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df19ed1a9610a5422497073697cbf4575f80de47fbb46ef0cdd2779386b031fa
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": NaN,
3
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
4
- "epoch": 0.24301336573511542,
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": 68.136,
199
  "eval_steps_per_second": 17.715,
200
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
201
  }
202
  ],
203
  "logging_steps": 1,
@@ -212,7 +395,7 @@
212
  "early_stopping_threshold": 0.0
213
  },
214
  "attributes": {
215
- "early_stopping_patience_counter": 0
216
  }
217
  },
218
  "TrainerControl": {
@@ -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": 1.47650456322048e+16,
230
  "train_batch_size": 1,
231
  "trial_name": null,
232
  "trial_params": null
 
1
  {
2
  "best_metric": NaN,
3
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
4
+ "epoch": 0.48602673147023084,
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": 68.136,
199
  "eval_steps_per_second": 17.715,
200
  "step": 25
201
+ },
202
+ {
203
+ "epoch": 0.25273390036452004,
204
+ "grad_norm": NaN,
205
+ "learning_rate": 8.681980515339464e-05,
206
+ "loss": 0.0,
207
+ "step": 26
208
+ },
209
+ {
210
+ "epoch": 0.2624544349939247,
211
+ "grad_norm": NaN,
212
+ "learning_rate": 8.571489144483944e-05,
213
+ "loss": 0.0,
214
+ "step": 27
215
+ },
216
+ {
217
+ "epoch": 0.27217496962332927,
218
+ "grad_norm": NaN,
219
+ "learning_rate": 8.457416554680877e-05,
220
+ "loss": 0.0,
221
+ "step": 28
222
+ },
223
+ {
224
+ "epoch": 0.2818955042527339,
225
+ "grad_norm": NaN,
226
+ "learning_rate": 8.339895749467238e-05,
227
+ "loss": 0.0,
228
+ "step": 29
229
+ },
230
+ {
231
+ "epoch": 0.2916160388821385,
232
+ "grad_norm": NaN,
233
+ "learning_rate": 8.219063752844926e-05,
234
+ "loss": 0.0,
235
+ "step": 30
236
+ },
237
+ {
238
+ "epoch": 0.30133657351154314,
239
+ "grad_norm": NaN,
240
+ "learning_rate": 8.095061449516903e-05,
241
+ "loss": 0.0,
242
+ "step": 31
243
+ },
244
+ {
245
+ "epoch": 0.3110571081409477,
246
+ "grad_norm": NaN,
247
+ "learning_rate": 7.968033420621935e-05,
248
+ "loss": 0.0,
249
+ "step": 32
250
+ },
251
+ {
252
+ "epoch": 0.32077764277035237,
253
+ "grad_norm": NaN,
254
+ "learning_rate": 7.838127775159452e-05,
255
+ "loss": 0.0,
256
+ "step": 33
257
+ },
258
+ {
259
+ "epoch": 0.330498177399757,
260
+ "grad_norm": NaN,
261
+ "learning_rate": 7.705495977301078e-05,
262
+ "loss": 0.0,
263
+ "step": 34
264
+ },
265
+ {
266
+ "epoch": 0.3402187120291616,
267
+ "grad_norm": NaN,
268
+ "learning_rate": 7.570292669790186e-05,
269
+ "loss": 0.0,
270
+ "step": 35
271
+ },
272
+ {
273
+ "epoch": 0.34993924665856624,
274
+ "grad_norm": NaN,
275
+ "learning_rate": 7.43267549363537e-05,
276
+ "loss": 0.0,
277
+ "step": 36
278
+ },
279
+ {
280
+ "epoch": 0.3596597812879708,
281
+ "grad_norm": NaN,
282
+ "learning_rate": 7.292804904308087e-05,
283
+ "loss": 0.0,
284
+ "step": 37
285
+ },
286
+ {
287
+ "epoch": 0.36938031591737547,
288
+ "grad_norm": NaN,
289
+ "learning_rate": 7.150843984658754e-05,
290
+ "loss": 0.0,
291
+ "step": 38
292
+ },
293
+ {
294
+ "epoch": 0.37910085054678005,
295
+ "grad_norm": NaN,
296
+ "learning_rate": 7.006958254769438e-05,
297
+ "loss": 0.0,
298
+ "step": 39
299
+ },
300
+ {
301
+ "epoch": 0.3888213851761847,
302
+ "grad_norm": NaN,
303
+ "learning_rate": 6.861315478964841e-05,
304
+ "loss": 0.0,
305
+ "step": 40
306
+ },
307
+ {
308
+ "epoch": 0.3985419198055893,
309
+ "grad_norm": NaN,
310
+ "learning_rate": 6.714085470206609e-05,
311
+ "loss": 0.0,
312
+ "step": 41
313
+ },
314
+ {
315
+ "epoch": 0.4082624544349939,
316
+ "grad_norm": NaN,
317
+ "learning_rate": 6.56543989209901e-05,
318
+ "loss": 0.0,
319
+ "step": 42
320
+ },
321
+ {
322
+ "epoch": 0.41798298906439857,
323
+ "grad_norm": NaN,
324
+ "learning_rate": 6.415552058736854e-05,
325
+ "loss": 0.0,
326
+ "step": 43
327
+ },
328
+ {
329
+ "epoch": 0.42770352369380316,
330
+ "grad_norm": NaN,
331
+ "learning_rate": 6.264596732629e-05,
332
+ "loss": 0.0,
333
+ "step": 44
334
+ },
335
+ {
336
+ "epoch": 0.4374240583232078,
337
+ "grad_norm": NaN,
338
+ "learning_rate": 6.112749920933111e-05,
339
+ "loss": 0.0,
340
+ "step": 45
341
+ },
342
+ {
343
+ "epoch": 0.4471445929526124,
344
+ "grad_norm": NaN,
345
+ "learning_rate": 5.960188670239154e-05,
346
+ "loss": 0.0,
347
+ "step": 46
348
+ },
349
+ {
350
+ "epoch": 0.456865127582017,
351
+ "grad_norm": NaN,
352
+ "learning_rate": 5.80709086014102e-05,
353
+ "loss": 0.0,
354
+ "step": 47
355
+ },
356
+ {
357
+ "epoch": 0.4665856622114216,
358
+ "grad_norm": NaN,
359
+ "learning_rate": 5.653634995836856e-05,
360
+ "loss": 0.0,
361
+ "step": 48
362
+ },
363
+ {
364
+ "epoch": 0.47630619684082626,
365
+ "grad_norm": NaN,
366
+ "learning_rate": 5.500000000000001e-05,
367
+ "loss": 0.0,
368
+ "step": 49
369
+ },
370
+ {
371
+ "epoch": 0.48602673147023084,
372
+ "grad_norm": NaN,
373
+ "learning_rate": 5.346365004163145e-05,
374
+ "loss": 0.0,
375
+ "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.48602673147023084,
379
+ "eval_loss": NaN,
380
+ "eval_runtime": 0.7493,
381
+ "eval_samples_per_second": 66.726,
382
+ "eval_steps_per_second": 17.349,
383
+ "step": 50
384
  }
385
  ],
386
  "logging_steps": 1,
 
395
  "early_stopping_threshold": 0.0
396
  },
397
  "attributes": {
398
+ "early_stopping_patience_counter": 1
399
  }
400
  },
401
  "TrainerControl": {
 
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": 2.95300912644096e+16,
413
  "train_batch_size": 1,
414
  "trial_name": null,
415
  "trial_params": null