jssky commited on
Commit
249c4b5
1 Parent(s): a9395a0

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:faf3c4440d1c5208193e03ffaaf1c34ff0f90377bb2b0e28e5d1e2d659aad247
3
  size 646253418
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89906d3c2906009c34195b8862611a17aa777fc071fc359850f926918ea2daed
3
  size 646253418
last-checkpoint/rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:91ec3c19aca06805c29d78fc826a1161822f37f4ff6fc039da97c4ea42fb93b7
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62a4b3955c969198c13a495341aba7895e7090ec905f7fa1c4354e6132d590b8
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 sha256:5ab011cf819574e16b0d0219f3f477bdf92ec4aa8a01c067420b639d6ae8bd99
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24c7182dd594777c5beb8c987847051a9fc203028759c0067cd8a6f7d2557bc0
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:bb83f48d31587db10a70b22e0796587dba456e31aab712b1f94364ffa0c2b8e6
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02ba5bb612e8823e891e617d363671b4d6f883c2d7d1128de5a405bd9ad1678b
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 sha256:08e32082e343010082ddaaee1235464271c01dd39ea5f9e026c30e67bde6cff5
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d051701aa00fbcacab4dce348276ec710c6bc96d93905ab1579b3cbd331c2f97
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": NaN,
3
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
4
- "epoch": 0.008826904404625299,
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": 17.954,
199
  "eval_steps_per_second": 2.245,
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": 2.812028905324544e+17,
230
  "train_batch_size": 2,
231
  "trial_name": null,
232
  "trial_params": null
 
1
  {
2
  "best_metric": NaN,
3
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
4
+ "epoch": 0.017653808809250597,
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": 17.954,
199
  "eval_steps_per_second": 2.245,
200
  "step": 25
201
+ },
202
+ {
203
+ "epoch": 0.00917998058081031,
204
+ "grad_norm": NaN,
205
+ "learning_rate": 5e-05,
206
+ "loss": 0.0,
207
+ "step": 26
208
+ },
209
+ {
210
+ "epoch": 0.009533056756995322,
211
+ "grad_norm": NaN,
212
+ "learning_rate": 4.6729843538492847e-05,
213
+ "loss": 0.0,
214
+ "step": 27
215
+ },
216
+ {
217
+ "epoch": 0.009886132933180334,
218
+ "grad_norm": NaN,
219
+ "learning_rate": 4.347369038899744e-05,
220
+ "loss": 0.0,
221
+ "step": 28
222
+ },
223
+ {
224
+ "epoch": 0.010239209109365346,
225
+ "grad_norm": NaN,
226
+ "learning_rate": 4.0245483899193595e-05,
227
+ "loss": 0.0,
228
+ "step": 29
229
+ },
230
+ {
231
+ "epoch": 0.010592285285550358,
232
+ "grad_norm": NaN,
233
+ "learning_rate": 3.705904774487396e-05,
234
+ "loss": 0.0,
235
+ "step": 30
236
+ },
237
+ {
238
+ "epoch": 0.01094536146173537,
239
+ "grad_norm": NaN,
240
+ "learning_rate": 3.392802673484193e-05,
241
+ "loss": 0.0,
242
+ "step": 31
243
+ },
244
+ {
245
+ "epoch": 0.011298437637920381,
246
+ "grad_norm": NaN,
247
+ "learning_rate": 3.086582838174551e-05,
248
+ "loss": 0.0,
249
+ "step": 32
250
+ },
251
+ {
252
+ "epoch": 0.011651513814105393,
253
+ "grad_norm": NaN,
254
+ "learning_rate": 2.7885565489049946e-05,
255
+ "loss": 0.0,
256
+ "step": 33
257
+ },
258
+ {
259
+ "epoch": 0.012004589990290405,
260
+ "grad_norm": NaN,
261
+ "learning_rate": 2.500000000000001e-05,
262
+ "loss": 0.0,
263
+ "step": 34
264
+ },
265
+ {
266
+ "epoch": 0.012357666166475417,
267
+ "grad_norm": NaN,
268
+ "learning_rate": 2.2221488349019903e-05,
269
+ "loss": 0.0,
270
+ "step": 35
271
+ },
272
+ {
273
+ "epoch": 0.012710742342660428,
274
+ "grad_norm": NaN,
275
+ "learning_rate": 1.9561928549563968e-05,
276
+ "loss": 0.0,
277
+ "step": 36
278
+ },
279
+ {
280
+ "epoch": 0.01306381851884544,
281
+ "grad_norm": NaN,
282
+ "learning_rate": 1.703270924499656e-05,
283
+ "loss": 0.0,
284
+ "step": 37
285
+ },
286
+ {
287
+ "epoch": 0.013416894695030452,
288
+ "grad_norm": NaN,
289
+ "learning_rate": 1.4644660940672627e-05,
290
+ "loss": 0.0,
291
+ "step": 38
292
+ },
293
+ {
294
+ "epoch": 0.013769970871215466,
295
+ "grad_norm": NaN,
296
+ "learning_rate": 1.2408009626051137e-05,
297
+ "loss": 0.0,
298
+ "step": 39
299
+ },
300
+ {
301
+ "epoch": 0.014123047047400477,
302
+ "grad_norm": NaN,
303
+ "learning_rate": 1.0332332985438248e-05,
304
+ "loss": 0.0,
305
+ "step": 40
306
+ },
307
+ {
308
+ "epoch": 0.014476123223585489,
309
+ "grad_norm": NaN,
310
+ "learning_rate": 8.426519384872733e-06,
311
+ "loss": 0.0,
312
+ "step": 41
313
+ },
314
+ {
315
+ "epoch": 0.014829199399770501,
316
+ "grad_norm": NaN,
317
+ "learning_rate": 6.698729810778065e-06,
318
+ "loss": 0.0,
319
+ "step": 42
320
+ },
321
+ {
322
+ "epoch": 0.015182275575955513,
323
+ "grad_norm": NaN,
324
+ "learning_rate": 5.156362923365588e-06,
325
+ "loss": 0.0,
326
+ "step": 43
327
+ },
328
+ {
329
+ "epoch": 0.015535351752140525,
330
+ "grad_norm": NaN,
331
+ "learning_rate": 3.8060233744356633e-06,
332
+ "loss": 0.0,
333
+ "step": 44
334
+ },
335
+ {
336
+ "epoch": 0.015888427928325535,
337
+ "grad_norm": NaN,
338
+ "learning_rate": 2.653493525244721e-06,
339
+ "loss": 0.0,
340
+ "step": 45
341
+ },
342
+ {
343
+ "epoch": 0.01624150410451055,
344
+ "grad_norm": NaN,
345
+ "learning_rate": 1.70370868554659e-06,
346
+ "loss": 0.0,
347
+ "step": 46
348
+ },
349
+ {
350
+ "epoch": 0.01659458028069556,
351
+ "grad_norm": NaN,
352
+ "learning_rate": 9.607359798384785e-07,
353
+ "loss": 0.0,
354
+ "step": 47
355
+ },
356
+ {
357
+ "epoch": 0.016947656456880573,
358
+ "grad_norm": NaN,
359
+ "learning_rate": 4.277569313094809e-07,
360
+ "loss": 0.0,
361
+ "step": 48
362
+ },
363
+ {
364
+ "epoch": 0.017300732633065585,
365
+ "grad_norm": NaN,
366
+ "learning_rate": 1.0705383806982606e-07,
367
+ "loss": 0.0,
368
+ "step": 49
369
+ },
370
+ {
371
+ "epoch": 0.017653808809250597,
372
+ "grad_norm": NaN,
373
+ "learning_rate": 0.0,
374
+ "loss": 0.0,
375
+ "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.017653808809250597,
379
+ "eval_loss": NaN,
380
+ "eval_runtime": 856.9298,
381
+ "eval_samples_per_second": 22.267,
382
+ "eval_steps_per_second": 2.784,
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": 5.624057810649088e+17,
413
  "train_batch_size": 2,
414
  "trial_name": null,
415
  "trial_params": null