DeepDream2045 commited on
Commit
86c2b53
·
verified ·
1 Parent(s): 6ab1f17

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 sha256:2956cf60941a812577a7bb382abec355b7473e4668bde75c51810d767f67c6ab
3
  size 1521616
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82c91c45dfd169ef7a04fde099791f201aacb2f9cd22fb5d66ed67f8897264a9
3
  size 1521616
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3827d407e78f42494a5ba20785c082ab043720861d5f86dbeffd771e5a2d2d80
3
  size 3108666
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55b14132be7924cc2b708a00fcbeb248d9299c18f525af806b455b330775e6b8
3
  size 3108666
last-checkpoint/rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3082cba210b61ff926f0a994e0a8141e1ed34ce63f93b187aedd4ff264d6dddd
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92758b8bc20b76b574f835cd2cf08afcfac78eaa2d132bc55570eb980196651e
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:f21bd79c357e4a03ca6be0286f672f537cb6dc6c2316ce2c57a219f65fc1de65
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd81b2756aaa88007f5ee3c1e6a7ed0e8a1374ee54374238a39dbf745b6bf5a9
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:d144fe7c880a88dd42094dce6c0f6bec1a490055ab05c8671e3eaa8e23020bd7
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:614b3c6630b2bec39c8d5233b7f52785686706b6d40b3352e6d998172e64917a
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 sha256:946427562c01f98a3586a658f22e525d550f32895451f4855d7d5021d5b783d4
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27db58b70b437300421dcbcd991eb6cee5c1a35e7b812293c3a19312578eecab
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": 9.319945335388184,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-25",
4
- "epoch": 0.12380068090374496,
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": 221.934,
199
  "eval_steps_per_second": 27.884,
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": 116296916140032.0,
230
  "train_batch_size": 2,
231
  "trial_name": null,
232
  "trial_params": null
 
1
  {
2
+ "best_metric": 9.110738754272461,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
+ "epoch": 0.24760136180748993,
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": 221.934,
199
  "eval_steps_per_second": 27.884,
200
  "step": 25
201
+ },
202
+ {
203
+ "epoch": 0.12875270813989476,
204
+ "grad_norm": 3.141822338104248,
205
+ "learning_rate": 5e-05,
206
+ "loss": 9.3686,
207
+ "step": 26
208
+ },
209
+ {
210
+ "epoch": 0.13370473537604458,
211
+ "grad_norm": 2.925520181655884,
212
+ "learning_rate": 4.6729843538492847e-05,
213
+ "loss": 9.332,
214
+ "step": 27
215
+ },
216
+ {
217
+ "epoch": 0.13865676261219437,
218
+ "grad_norm": 2.8429415225982666,
219
+ "learning_rate": 4.347369038899744e-05,
220
+ "loss": 9.3123,
221
+ "step": 28
222
+ },
223
+ {
224
+ "epoch": 0.14360878984834416,
225
+ "grad_norm": 2.663667678833008,
226
+ "learning_rate": 4.0245483899193595e-05,
227
+ "loss": 9.2803,
228
+ "step": 29
229
+ },
230
+ {
231
+ "epoch": 0.14856081708449395,
232
+ "grad_norm": 2.525662899017334,
233
+ "learning_rate": 3.705904774487396e-05,
234
+ "loss": 9.2936,
235
+ "step": 30
236
+ },
237
+ {
238
+ "epoch": 0.15351284432064377,
239
+ "grad_norm": 2.4328393936157227,
240
+ "learning_rate": 3.392802673484193e-05,
241
+ "loss": 9.2449,
242
+ "step": 31
243
+ },
244
+ {
245
+ "epoch": 0.15846487155679356,
246
+ "grad_norm": 2.222417116165161,
247
+ "learning_rate": 3.086582838174551e-05,
248
+ "loss": 9.183,
249
+ "step": 32
250
+ },
251
+ {
252
+ "epoch": 0.16341689879294335,
253
+ "grad_norm": 2.1309008598327637,
254
+ "learning_rate": 2.7885565489049946e-05,
255
+ "loss": 9.1944,
256
+ "step": 33
257
+ },
258
+ {
259
+ "epoch": 0.16836892602909315,
260
+ "grad_norm": 2.2700769901275635,
261
+ "learning_rate": 2.500000000000001e-05,
262
+ "loss": 9.1398,
263
+ "step": 34
264
+ },
265
+ {
266
+ "epoch": 0.17332095326524297,
267
+ "grad_norm": 2.3253843784332275,
268
+ "learning_rate": 2.2221488349019903e-05,
269
+ "loss": 9.1568,
270
+ "step": 35
271
+ },
272
+ {
273
+ "epoch": 0.17827298050139276,
274
+ "grad_norm": 2.405583381652832,
275
+ "learning_rate": 1.9561928549563968e-05,
276
+ "loss": 9.1506,
277
+ "step": 36
278
+ },
279
+ {
280
+ "epoch": 0.18322500773754255,
281
+ "grad_norm": 2.8271777629852295,
282
+ "learning_rate": 1.703270924499656e-05,
283
+ "loss": 9.025,
284
+ "step": 37
285
+ },
286
+ {
287
+ "epoch": 0.18817703497369234,
288
+ "grad_norm": 2.783236026763916,
289
+ "learning_rate": 1.4644660940672627e-05,
290
+ "loss": 9.181,
291
+ "step": 38
292
+ },
293
+ {
294
+ "epoch": 0.19312906220984216,
295
+ "grad_norm": 2.6467456817626953,
296
+ "learning_rate": 1.2408009626051137e-05,
297
+ "loss": 9.1671,
298
+ "step": 39
299
+ },
300
+ {
301
+ "epoch": 0.19808108944599195,
302
+ "grad_norm": 2.3731637001037598,
303
+ "learning_rate": 1.0332332985438248e-05,
304
+ "loss": 9.1439,
305
+ "step": 40
306
+ },
307
+ {
308
+ "epoch": 0.20303311668214175,
309
+ "grad_norm": 2.2230052947998047,
310
+ "learning_rate": 8.426519384872733e-06,
311
+ "loss": 9.1583,
312
+ "step": 41
313
+ },
314
+ {
315
+ "epoch": 0.20798514391829154,
316
+ "grad_norm": 2.25925350189209,
317
+ "learning_rate": 6.698729810778065e-06,
318
+ "loss": 9.1528,
319
+ "step": 42
320
+ },
321
+ {
322
+ "epoch": 0.21293717115444136,
323
+ "grad_norm": 2.134979724884033,
324
+ "learning_rate": 5.156362923365588e-06,
325
+ "loss": 9.1479,
326
+ "step": 43
327
+ },
328
+ {
329
+ "epoch": 0.21788919839059115,
330
+ "grad_norm": 2.0616414546966553,
331
+ "learning_rate": 3.8060233744356633e-06,
332
+ "loss": 9.1364,
333
+ "step": 44
334
+ },
335
+ {
336
+ "epoch": 0.22284122562674094,
337
+ "grad_norm": 1.9881036281585693,
338
+ "learning_rate": 2.653493525244721e-06,
339
+ "loss": 9.0938,
340
+ "step": 45
341
+ },
342
+ {
343
+ "epoch": 0.22779325286289073,
344
+ "grad_norm": 1.959113359451294,
345
+ "learning_rate": 1.70370868554659e-06,
346
+ "loss": 9.1185,
347
+ "step": 46
348
+ },
349
+ {
350
+ "epoch": 0.23274528009904055,
351
+ "grad_norm": 2.01914381980896,
352
+ "learning_rate": 9.607359798384785e-07,
353
+ "loss": 9.1127,
354
+ "step": 47
355
+ },
356
+ {
357
+ "epoch": 0.23769730733519034,
358
+ "grad_norm": 2.156982421875,
359
+ "learning_rate": 4.277569313094809e-07,
360
+ "loss": 9.0668,
361
+ "step": 48
362
+ },
363
+ {
364
+ "epoch": 0.24264933457134014,
365
+ "grad_norm": 2.748440742492676,
366
+ "learning_rate": 1.0705383806982606e-07,
367
+ "loss": 9.0733,
368
+ "step": 49
369
+ },
370
+ {
371
+ "epoch": 0.24760136180748993,
372
+ "grad_norm": 3.4162144660949707,
373
+ "learning_rate": 0.0,
374
+ "loss": 9.0366,
375
+ "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.24760136180748993,
379
+ "eval_loss": 9.110738754272461,
380
+ "eval_runtime": 6.161,
381
+ "eval_samples_per_second": 220.907,
382
+ "eval_steps_per_second": 27.755,
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": 232593832280064.0,
413
  "train_batch_size": 2,
414
  "trial_name": null,
415
  "trial_params": null