DeepDream2045 commited on
Commit
d8d5e3f
1 Parent(s): 5752318

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 sha256:2e2580e5769e7e1adb6028f6ba06f863851d39cbdf90e2eeb239763aa5d2af53
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a080d537f62f470eccc60ed16f4ea91e3b39d5350203424ff165c17abbcec5d2
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:df6d0582f2f5bacc8d198f7fdfe25a268592edcbb493ae94534972b183fdc356
3
  size 141053442
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a64b73123db2508651f09618b5c29aa980c4a53d31eb8efe735e9d09addeb601
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:b56ecbb0019b555079fa18e466c5c23e0cadd219670840340df46806c2945b58
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ebc4ddc1efeac96780ce5903968074ecadce7881f18f5481e03c7eecfecf054
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 sha256:8b26e5fc1f5641507a0cdce630f9fb1d2edd70af94c5db707561bf99f67b343f
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cba87e08fadc311b170ac6dd12aa3e0a4c545a1ceba7a0982a85208cca768417
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:d1af51f33f74c86fc2cdd68de732d726817a5fc2cefd5664d8ac110c7144b3eb
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84c81774f3814271bab0adf4b4cca6e79ca6c231fdb6253c44c114e6d388816c
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:a70ed74d16dac201d697e4c8dea15e6c327eebe18cab69f112ab8e6cd340bb51
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d1ce3c69cfec74dfed3edfe3a9751d24984ae40f17102c62d823903084fe3409
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": 1.025231957435608,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-25",
4
- "epoch": 0.13311148086522462,
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": 68.277,
199
  "eval_steps_per_second": 8.582,
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": 1.47650456322048e+16,
230
  "train_batch_size": 2,
231
  "trial_name": null,
232
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.6133490204811096,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
+ "epoch": 0.26622296173044924,
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": 68.277,
199
  "eval_steps_per_second": 8.582,
200
  "step": 25
201
+ },
202
+ {
203
+ "epoch": 0.13843594009983362,
204
+ "grad_norm": 6.450296878814697,
205
+ "learning_rate": 5e-05,
206
+ "loss": 1.0312,
207
+ "step": 26
208
+ },
209
+ {
210
+ "epoch": 0.1437603993344426,
211
+ "grad_norm": 5.499378681182861,
212
+ "learning_rate": 4.6729843538492847e-05,
213
+ "loss": 1.0271,
214
+ "step": 27
215
+ },
216
+ {
217
+ "epoch": 0.14908485856905157,
218
+ "grad_norm": 4.80499267578125,
219
+ "learning_rate": 4.347369038899744e-05,
220
+ "loss": 0.8741,
221
+ "step": 28
222
+ },
223
+ {
224
+ "epoch": 0.15440931780366057,
225
+ "grad_norm": 4.07858943939209,
226
+ "learning_rate": 4.0245483899193595e-05,
227
+ "loss": 0.8599,
228
+ "step": 29
229
+ },
230
+ {
231
+ "epoch": 0.15973377703826955,
232
+ "grad_norm": 3.2893877029418945,
233
+ "learning_rate": 3.705904774487396e-05,
234
+ "loss": 0.8015,
235
+ "step": 30
236
+ },
237
+ {
238
+ "epoch": 0.16505823627287852,
239
+ "grad_norm": 3.4834606647491455,
240
+ "learning_rate": 3.392802673484193e-05,
241
+ "loss": 0.7614,
242
+ "step": 31
243
+ },
244
+ {
245
+ "epoch": 0.17038269550748752,
246
+ "grad_norm": 3.2497472763061523,
247
+ "learning_rate": 3.086582838174551e-05,
248
+ "loss": 0.7866,
249
+ "step": 32
250
+ },
251
+ {
252
+ "epoch": 0.1757071547420965,
253
+ "grad_norm": 4.107487201690674,
254
+ "learning_rate": 2.7885565489049946e-05,
255
+ "loss": 0.7755,
256
+ "step": 33
257
+ },
258
+ {
259
+ "epoch": 0.1810316139767055,
260
+ "grad_norm": 3.7900607585906982,
261
+ "learning_rate": 2.500000000000001e-05,
262
+ "loss": 0.6497,
263
+ "step": 34
264
+ },
265
+ {
266
+ "epoch": 0.18635607321131448,
267
+ "grad_norm": 4.495862007141113,
268
+ "learning_rate": 2.2221488349019903e-05,
269
+ "loss": 0.776,
270
+ "step": 35
271
+ },
272
+ {
273
+ "epoch": 0.19168053244592345,
274
+ "grad_norm": 4.210362434387207,
275
+ "learning_rate": 1.9561928549563968e-05,
276
+ "loss": 0.8306,
277
+ "step": 36
278
+ },
279
+ {
280
+ "epoch": 0.19700499168053245,
281
+ "grad_norm": 5.1397175788879395,
282
+ "learning_rate": 1.703270924499656e-05,
283
+ "loss": 0.859,
284
+ "step": 37
285
+ },
286
+ {
287
+ "epoch": 0.20232945091514143,
288
+ "grad_norm": 5.5402936935424805,
289
+ "learning_rate": 1.4644660940672627e-05,
290
+ "loss": 0.8157,
291
+ "step": 38
292
+ },
293
+ {
294
+ "epoch": 0.2076539101497504,
295
+ "grad_norm": 3.070615530014038,
296
+ "learning_rate": 1.2408009626051137e-05,
297
+ "loss": 0.5884,
298
+ "step": 39
299
+ },
300
+ {
301
+ "epoch": 0.2129783693843594,
302
+ "grad_norm": 3.0448577404022217,
303
+ "learning_rate": 1.0332332985438248e-05,
304
+ "loss": 0.6112,
305
+ "step": 40
306
+ },
307
+ {
308
+ "epoch": 0.21830282861896838,
309
+ "grad_norm": 3.166132926940918,
310
+ "learning_rate": 8.426519384872733e-06,
311
+ "loss": 0.6329,
312
+ "step": 41
313
+ },
314
+ {
315
+ "epoch": 0.22362728785357738,
316
+ "grad_norm": 2.86126971244812,
317
+ "learning_rate": 6.698729810778065e-06,
318
+ "loss": 0.4517,
319
+ "step": 42
320
+ },
321
+ {
322
+ "epoch": 0.22895174708818636,
323
+ "grad_norm": 3.097123384475708,
324
+ "learning_rate": 5.156362923365588e-06,
325
+ "loss": 0.5897,
326
+ "step": 43
327
+ },
328
+ {
329
+ "epoch": 0.23427620632279533,
330
+ "grad_norm": 2.668059825897217,
331
+ "learning_rate": 3.8060233744356633e-06,
332
+ "loss": 0.4817,
333
+ "step": 44
334
+ },
335
+ {
336
+ "epoch": 0.23960066555740434,
337
+ "grad_norm": 2.4491469860076904,
338
+ "learning_rate": 2.653493525244721e-06,
339
+ "loss": 0.4798,
340
+ "step": 45
341
+ },
342
+ {
343
+ "epoch": 0.2449251247920133,
344
+ "grad_norm": 4.0405778884887695,
345
+ "learning_rate": 1.70370868554659e-06,
346
+ "loss": 0.5788,
347
+ "step": 46
348
+ },
349
+ {
350
+ "epoch": 0.2502495840266223,
351
+ "grad_norm": 2.962510108947754,
352
+ "learning_rate": 9.607359798384785e-07,
353
+ "loss": 0.4239,
354
+ "step": 47
355
+ },
356
+ {
357
+ "epoch": 0.2555740432612313,
358
+ "grad_norm": 3.4761126041412354,
359
+ "learning_rate": 4.277569313094809e-07,
360
+ "loss": 0.5796,
361
+ "step": 48
362
+ },
363
+ {
364
+ "epoch": 0.2608985024958403,
365
+ "grad_norm": 3.6893534660339355,
366
+ "learning_rate": 1.0705383806982606e-07,
367
+ "loss": 0.6451,
368
+ "step": 49
369
+ },
370
+ {
371
+ "epoch": 0.26622296173044924,
372
+ "grad_norm": 6.921513080596924,
373
+ "learning_rate": 0.0,
374
+ "loss": 1.1654,
375
+ "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.26622296173044924,
379
+ "eval_loss": 0.6133490204811096,
380
+ "eval_runtime": 18.5142,
381
+ "eval_samples_per_second": 68.326,
382
+ "eval_steps_per_second": 8.588,
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": 2.95300912644096e+16,
413
  "train_batch_size": 2,
414
  "trial_name": null,
415
  "trial_params": null