dada22231 commited on
Commit
ee4fb34
·
verified ·
1 Parent(s): d99e115

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 sha256:2a20e42f228d66e5e1ef7c3e904241d4700bc42d3030daabf20110d4831164cc
3
  size 671466706
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f3e52a3921808d5243bd4d25361e27378db547355114798e0235ae3400ef7c6
3
  size 671466706
last-checkpoint/rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dc134a59bbf19e7df3f2bbfe8565cef559781a5a7561fb118ced92bc7660f29e
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4965ed29d112c45c0109516ef8b033cd15dc4b3e58584ab053ae65ba09215db
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 sha256:6641fc369f27788189e6d6a67a25f8f79806f851240817157b0b30b88c1bee64
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:10ca4ba0a5dd21288a7c64633435da8e548948eec8f5393a10b2e8c016fe054e
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 sha256:9e166b36a4eade3728dacb5bef3a0305e13e9a05a3b725216490013079af68f3
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:457d22e172c67d5867b199accb5c90eba1b218453f4e78c3778b2bc6b406b570
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 sha256:5fdc45d78ffb2c1f4f83bb6a88801d6d4850f34f06673c3c55753e6b37e07d63
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:64d9137a02e7ba2acf48c77f5bc3662136968acc70934e3ae597f54a5f15f0ab
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": 0.7393715341959335,
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": 15.839,
199
  "eval_steps_per_second": 4.118,
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": 2.829013890367488e+17,
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": 1.4972273567467653,
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": 15.839,
199
  "eval_steps_per_second": 4.118,
200
  "step": 25
201
+ },
202
+ {
203
+ "epoch": 0.7689463955637708,
204
+ "grad_norm": NaN,
205
+ "learning_rate": 8.681980515339464e-05,
206
+ "loss": 0.0,
207
+ "step": 26
208
+ },
209
+ {
210
+ "epoch": 0.7985212569316081,
211
+ "grad_norm": NaN,
212
+ "learning_rate": 8.571489144483944e-05,
213
+ "loss": 0.0,
214
+ "step": 27
215
+ },
216
+ {
217
+ "epoch": 0.8280961182994455,
218
+ "grad_norm": NaN,
219
+ "learning_rate": 8.457416554680877e-05,
220
+ "loss": 0.0,
221
+ "step": 28
222
+ },
223
+ {
224
+ "epoch": 0.8576709796672828,
225
+ "grad_norm": NaN,
226
+ "learning_rate": 8.339895749467238e-05,
227
+ "loss": 0.0,
228
+ "step": 29
229
+ },
230
+ {
231
+ "epoch": 0.8872458410351202,
232
+ "grad_norm": NaN,
233
+ "learning_rate": 8.219063752844926e-05,
234
+ "loss": 0.0,
235
+ "step": 30
236
+ },
237
+ {
238
+ "epoch": 0.9168207024029574,
239
+ "grad_norm": NaN,
240
+ "learning_rate": 8.095061449516903e-05,
241
+ "loss": 0.0,
242
+ "step": 31
243
+ },
244
+ {
245
+ "epoch": 0.9463955637707948,
246
+ "grad_norm": NaN,
247
+ "learning_rate": 7.968033420621935e-05,
248
+ "loss": 0.0,
249
+ "step": 32
250
+ },
251
+ {
252
+ "epoch": 0.9759704251386322,
253
+ "grad_norm": NaN,
254
+ "learning_rate": 7.838127775159452e-05,
255
+ "loss": 0.0,
256
+ "step": 33
257
+ },
258
+ {
259
+ "epoch": 1.024029574861368,
260
+ "grad_norm": NaN,
261
+ "learning_rate": 7.705495977301078e-05,
262
+ "loss": 0.0,
263
+ "step": 34
264
+ },
265
+ {
266
+ "epoch": 1.0536044362292052,
267
+ "grad_norm": NaN,
268
+ "learning_rate": 7.570292669790186e-05,
269
+ "loss": 0.0,
270
+ "step": 35
271
+ },
272
+ {
273
+ "epoch": 1.0831792975970425,
274
+ "grad_norm": NaN,
275
+ "learning_rate": 7.43267549363537e-05,
276
+ "loss": 0.0,
277
+ "step": 36
278
+ },
279
+ {
280
+ "epoch": 1.11275415896488,
281
+ "grad_norm": NaN,
282
+ "learning_rate": 7.292804904308087e-05,
283
+ "loss": 0.0,
284
+ "step": 37
285
+ },
286
+ {
287
+ "epoch": 1.1423290203327172,
288
+ "grad_norm": NaN,
289
+ "learning_rate": 7.150843984658754e-05,
290
+ "loss": 0.0,
291
+ "step": 38
292
+ },
293
+ {
294
+ "epoch": 1.1719038817005545,
295
+ "grad_norm": NaN,
296
+ "learning_rate": 7.006958254769438e-05,
297
+ "loss": 0.0,
298
+ "step": 39
299
+ },
300
+ {
301
+ "epoch": 1.201478743068392,
302
+ "grad_norm": NaN,
303
+ "learning_rate": 6.861315478964841e-05,
304
+ "loss": 0.0,
305
+ "step": 40
306
+ },
307
+ {
308
+ "epoch": 1.2310536044362292,
309
+ "grad_norm": NaN,
310
+ "learning_rate": 6.714085470206609e-05,
311
+ "loss": 0.0,
312
+ "step": 41
313
+ },
314
+ {
315
+ "epoch": 1.2606284658040665,
316
+ "grad_norm": NaN,
317
+ "learning_rate": 6.56543989209901e-05,
318
+ "loss": 0.0,
319
+ "step": 42
320
+ },
321
+ {
322
+ "epoch": 1.2902033271719038,
323
+ "grad_norm": NaN,
324
+ "learning_rate": 6.415552058736854e-05,
325
+ "loss": 0.0,
326
+ "step": 43
327
+ },
328
+ {
329
+ "epoch": 1.3197781885397413,
330
+ "grad_norm": NaN,
331
+ "learning_rate": 6.264596732629e-05,
332
+ "loss": 0.0,
333
+ "step": 44
334
+ },
335
+ {
336
+ "epoch": 1.3493530499075785,
337
+ "grad_norm": NaN,
338
+ "learning_rate": 6.112749920933111e-05,
339
+ "loss": 0.0,
340
+ "step": 45
341
+ },
342
+ {
343
+ "epoch": 1.378927911275416,
344
+ "grad_norm": NaN,
345
+ "learning_rate": 5.960188670239154e-05,
346
+ "loss": 0.0,
347
+ "step": 46
348
+ },
349
+ {
350
+ "epoch": 1.4085027726432533,
351
+ "grad_norm": NaN,
352
+ "learning_rate": 5.80709086014102e-05,
353
+ "loss": 0.0,
354
+ "step": 47
355
+ },
356
+ {
357
+ "epoch": 1.4380776340110906,
358
+ "grad_norm": NaN,
359
+ "learning_rate": 5.653634995836856e-05,
360
+ "loss": 0.0,
361
+ "step": 48
362
+ },
363
+ {
364
+ "epoch": 1.4676524953789278,
365
+ "grad_norm": NaN,
366
+ "learning_rate": 5.500000000000001e-05,
367
+ "loss": 0.0,
368
+ "step": 49
369
+ },
370
+ {
371
+ "epoch": 1.4972273567467653,
372
+ "grad_norm": NaN,
373
+ "learning_rate": 5.346365004163145e-05,
374
+ "loss": 0.0,
375
+ "step": 50
376
+ },
377
+ {
378
+ "epoch": 1.4972273567467653,
379
+ "eval_loss": NaN,
380
+ "eval_runtime": 3.145,
381
+ "eval_samples_per_second": 15.898,
382
+ "eval_steps_per_second": 4.134,
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": 5.658027780734976e+17,
413
  "train_batch_size": 1,
414
  "trial_name": null,
415
  "trial_params": null