vdos commited on
Commit
589264d
·
verified ·
1 Parent(s): f9a5e8a

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 sha256:4180229e1353a0fe3c18262fb7aa490c96befe6cc775f94b47f57c2e8791c0fa
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f24acffade741425aee0ad726b0c0a98723272a7ef33b0422c7e4c6578262d3
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:60ce3aff6cc54e862f7fe0e3589929bae222aa3cc4674a851879f4d23b4a5e3f
3
  size 141053442
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c79c45414c0cc0de8001442cf0e8768c2d65447d1f2d3af1b90d69b48e199523
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 sha256:1d520ba555e04dc7522cf77ddbf4a7e929c14dcf12d3d25af0127a7ca7b9b7be
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76524de3e48d292e541333568f6c4d054eae3f3e278a90f3b16d7252d860395d
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:c1568e69205d414862fae81fd0ef27887deb68e91d3e4a5c3b06a6e22b85555a
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0cb3c290a5c31772847f5fb2fa4140d3e64a0681a103a008f39bd7bdbe904b64
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 sha256:53c89a4487096d903594bded7dc1457cf778dc5feafd8545c9391c6ca1b51a7c
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f41b9b4cedf2727a0862f5037b3ba9e8a1212968404dcf81a0c67c23bc16559f
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 sha256:7528f2c2e376713fdf6f575b29a798fdac884c1421ccd5844746b7b08acf85c9
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38b2f2b4f34f4de4bd7add6f388fedf704f33c2609233c8254447be248f1ff05
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": 1.014263391494751,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-25",
4
- "epoch": 0.00447047252894631,
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": 67.383,
199
  "eval_steps_per_second": 8.424,
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": 0.9053548574447632,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
+ "epoch": 0.00894094505789262,
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": 67.383,
199
  "eval_steps_per_second": 8.424,
200
  "step": 25
201
+ },
202
+ {
203
+ "epoch": 0.004649291430104162,
204
+ "grad_norm": 2.7061338424682617,
205
+ "learning_rate": 5e-05,
206
+ "loss": 0.8658,
207
+ "step": 26
208
+ },
209
+ {
210
+ "epoch": 0.004828110331262014,
211
+ "grad_norm": 1.9943201541900635,
212
+ "learning_rate": 4.6729843538492847e-05,
213
+ "loss": 0.9373,
214
+ "step": 27
215
+ },
216
+ {
217
+ "epoch": 0.005006929232419867,
218
+ "grad_norm": 1.6644830703735352,
219
+ "learning_rate": 4.347369038899744e-05,
220
+ "loss": 0.9823,
221
+ "step": 28
222
+ },
223
+ {
224
+ "epoch": 0.005185748133577719,
225
+ "grad_norm": 2.06219744682312,
226
+ "learning_rate": 4.0245483899193595e-05,
227
+ "loss": 0.9581,
228
+ "step": 29
229
+ },
230
+ {
231
+ "epoch": 0.005364567034735572,
232
+ "grad_norm": 1.7488588094711304,
233
+ "learning_rate": 3.705904774487396e-05,
234
+ "loss": 1.1204,
235
+ "step": 30
236
+ },
237
+ {
238
+ "epoch": 0.005543385935893424,
239
+ "grad_norm": 2.7978739738464355,
240
+ "learning_rate": 3.392802673484193e-05,
241
+ "loss": 1.1661,
242
+ "step": 31
243
+ },
244
+ {
245
+ "epoch": 0.005722204837051276,
246
+ "grad_norm": 1.6409696340560913,
247
+ "learning_rate": 3.086582838174551e-05,
248
+ "loss": 0.9434,
249
+ "step": 32
250
+ },
251
+ {
252
+ "epoch": 0.005901023738209128,
253
+ "grad_norm": 2.0203638076782227,
254
+ "learning_rate": 2.7885565489049946e-05,
255
+ "loss": 1.0251,
256
+ "step": 33
257
+ },
258
+ {
259
+ "epoch": 0.0060798426393669815,
260
+ "grad_norm": 3.090269088745117,
261
+ "learning_rate": 2.500000000000001e-05,
262
+ "loss": 1.0402,
263
+ "step": 34
264
+ },
265
+ {
266
+ "epoch": 0.006258661540524834,
267
+ "grad_norm": 2.0892794132232666,
268
+ "learning_rate": 2.2221488349019903e-05,
269
+ "loss": 1.0091,
270
+ "step": 35
271
+ },
272
+ {
273
+ "epoch": 0.006437480441682686,
274
+ "grad_norm": 1.66879403591156,
275
+ "learning_rate": 1.9561928549563968e-05,
276
+ "loss": 0.92,
277
+ "step": 36
278
+ },
279
+ {
280
+ "epoch": 0.006616299342840538,
281
+ "grad_norm": 2.061055898666382,
282
+ "learning_rate": 1.703270924499656e-05,
283
+ "loss": 0.9722,
284
+ "step": 37
285
+ },
286
+ {
287
+ "epoch": 0.00679511824399839,
288
+ "grad_norm": 2.040457010269165,
289
+ "learning_rate": 1.4644660940672627e-05,
290
+ "loss": 0.9406,
291
+ "step": 38
292
+ },
293
+ {
294
+ "epoch": 0.006973937145156243,
295
+ "grad_norm": 1.8687992095947266,
296
+ "learning_rate": 1.2408009626051137e-05,
297
+ "loss": 0.7691,
298
+ "step": 39
299
+ },
300
+ {
301
+ "epoch": 0.0071527560463140955,
302
+ "grad_norm": 1.7558640241622925,
303
+ "learning_rate": 1.0332332985438248e-05,
304
+ "loss": 0.8971,
305
+ "step": 40
306
+ },
307
+ {
308
+ "epoch": 0.007331574947471948,
309
+ "grad_norm": 1.9526532888412476,
310
+ "learning_rate": 8.426519384872733e-06,
311
+ "loss": 0.8504,
312
+ "step": 41
313
+ },
314
+ {
315
+ "epoch": 0.0075103938486298,
316
+ "grad_norm": 1.6909708976745605,
317
+ "learning_rate": 6.698729810778065e-06,
318
+ "loss": 0.9497,
319
+ "step": 42
320
+ },
321
+ {
322
+ "epoch": 0.007689212749787653,
323
+ "grad_norm": 1.443602204322815,
324
+ "learning_rate": 5.156362923365588e-06,
325
+ "loss": 0.8797,
326
+ "step": 43
327
+ },
328
+ {
329
+ "epoch": 0.007868031650945505,
330
+ "grad_norm": 1.661456823348999,
331
+ "learning_rate": 3.8060233744356633e-06,
332
+ "loss": 0.9609,
333
+ "step": 44
334
+ },
335
+ {
336
+ "epoch": 0.008046850552103357,
337
+ "grad_norm": 1.4534142017364502,
338
+ "learning_rate": 2.653493525244721e-06,
339
+ "loss": 0.8973,
340
+ "step": 45
341
+ },
342
+ {
343
+ "epoch": 0.00822566945326121,
344
+ "grad_norm": 2.08626127243042,
345
+ "learning_rate": 1.70370868554659e-06,
346
+ "loss": 0.9699,
347
+ "step": 46
348
+ },
349
+ {
350
+ "epoch": 0.008404488354419062,
351
+ "grad_norm": 1.9656062126159668,
352
+ "learning_rate": 9.607359798384785e-07,
353
+ "loss": 1.035,
354
+ "step": 47
355
+ },
356
+ {
357
+ "epoch": 0.008583307255576914,
358
+ "grad_norm": 1.7307604551315308,
359
+ "learning_rate": 4.277569313094809e-07,
360
+ "loss": 0.8978,
361
+ "step": 48
362
+ },
363
+ {
364
+ "epoch": 0.008762126156734766,
365
+ "grad_norm": 1.9000718593597412,
366
+ "learning_rate": 1.0705383806982606e-07,
367
+ "loss": 0.9207,
368
+ "step": 49
369
+ },
370
+ {
371
+ "epoch": 0.00894094505789262,
372
+ "grad_norm": 2.231043577194214,
373
+ "learning_rate": 0.0,
374
+ "loss": 1.0866,
375
+ "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.00894094505789262,
379
+ "eval_loss": 0.9053548574447632,
380
+ "eval_runtime": 559.2119,
381
+ "eval_samples_per_second": 67.37,
382
+ "eval_steps_per_second": 8.423,
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