vdos commited on
Commit
22808cc
·
verified ·
1 Parent(s): 257d88b

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 sha256:89f2cfb57dd80e308b72e55392fceb84c8701a5500997baa2fa6eae9feaa2318
3
  size 100966336
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b511287b37fa9f2c162dbfc01c7f56b6189864e6d658283b1a9cc5ca0ab55894
3
  size 100966336
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8462f627e607ea4a0262e47afca26abca9c0c043218c3d97eb7323f0165ff428
3
  size 202110330
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6bb86d3f97ddfefd3fbeb414f62210226725c552858521d1e1acaa24ecc46ade
3
  size 202110330
last-checkpoint/rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4e0b082cddeba6b0c26bcc9d691030d91b2a80f324040eaec0daca641a8efbb0
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e91438d76d33329ff16fb47fcb7f62add4f09bb7904624b07279406a9316fd3
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 sha256:4d371d78ccac6b572ac59d7d3dac380366dad3d407acd99fed12c58a0237f5e9
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37eda4f053a814c2ea8964cf89a5e226a10933077b953704ac93a212f2cfb977
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 sha256:009469e7bc96707ce9f137c73b8c9ffbd5a5605185575b37e9d964d179818fd6
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8a4c5cb0bf96f1aa81d2748ace74d86724d1b5c50b42cd153039951909d953a
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 sha256:1d127bf156080c324770ec55aa9ff32a6fdd42c05abc11fc080f70f8a0ecb251
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c00bad6c1a9a7f8976b939a594cd4c027163ac2235f75e9321730065a73a5a4
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": 4.343160152435303,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-25",
4
- "epoch": 0.06817794443497528,
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": 109.502,
199
  "eval_steps_per_second": 13.699,
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": 4.16708196040704e+16,
230
  "train_batch_size": 2,
231
  "trial_name": null,
232
  "trial_params": null
 
1
  {
2
+ "best_metric": 4.112647533416748,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
+ "epoch": 0.13635588886995056,
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": 109.502,
199
  "eval_steps_per_second": 13.699,
200
  "step": 25
201
+ },
202
+ {
203
+ "epoch": 0.0709050622123743,
204
+ "grad_norm": 4.764070510864258,
205
+ "learning_rate": 5e-05,
206
+ "loss": 4.1109,
207
+ "step": 26
208
+ },
209
+ {
210
+ "epoch": 0.07363217998977331,
211
+ "grad_norm": 4.184199333190918,
212
+ "learning_rate": 4.6729843538492847e-05,
213
+ "loss": 4.1216,
214
+ "step": 27
215
+ },
216
+ {
217
+ "epoch": 0.07635929776717232,
218
+ "grad_norm": 4.299893379211426,
219
+ "learning_rate": 4.347369038899744e-05,
220
+ "loss": 4.1499,
221
+ "step": 28
222
+ },
223
+ {
224
+ "epoch": 0.07908641554457133,
225
+ "grad_norm": 3.13893723487854,
226
+ "learning_rate": 4.0245483899193595e-05,
227
+ "loss": 4.0184,
228
+ "step": 29
229
+ },
230
+ {
231
+ "epoch": 0.08181353332197035,
232
+ "grad_norm": 2.336858034133911,
233
+ "learning_rate": 3.705904774487396e-05,
234
+ "loss": 4.0306,
235
+ "step": 30
236
+ },
237
+ {
238
+ "epoch": 0.08454065109936935,
239
+ "grad_norm": 2.0125699043273926,
240
+ "learning_rate": 3.392802673484193e-05,
241
+ "loss": 4.0846,
242
+ "step": 31
243
+ },
244
+ {
245
+ "epoch": 0.08726776887676836,
246
+ "grad_norm": 1.9820997714996338,
247
+ "learning_rate": 3.086582838174551e-05,
248
+ "loss": 4.1918,
249
+ "step": 32
250
+ },
251
+ {
252
+ "epoch": 0.08999488665416738,
253
+ "grad_norm": 2.16211199760437,
254
+ "learning_rate": 2.7885565489049946e-05,
255
+ "loss": 4.2227,
256
+ "step": 33
257
+ },
258
+ {
259
+ "epoch": 0.09272200443156639,
260
+ "grad_norm": 2.516345500946045,
261
+ "learning_rate": 2.500000000000001e-05,
262
+ "loss": 4.2009,
263
+ "step": 34
264
+ },
265
+ {
266
+ "epoch": 0.0954491222089654,
267
+ "grad_norm": 3.102931261062622,
268
+ "learning_rate": 2.2221488349019903e-05,
269
+ "loss": 4.2232,
270
+ "step": 35
271
+ },
272
+ {
273
+ "epoch": 0.0981762399863644,
274
+ "grad_norm": 3.983875036239624,
275
+ "learning_rate": 1.9561928549563968e-05,
276
+ "loss": 4.3798,
277
+ "step": 36
278
+ },
279
+ {
280
+ "epoch": 0.10090335776376343,
281
+ "grad_norm": 5.531810283660889,
282
+ "learning_rate": 1.703270924499656e-05,
283
+ "loss": 4.5567,
284
+ "step": 37
285
+ },
286
+ {
287
+ "epoch": 0.10363047554116243,
288
+ "grad_norm": 2.6005947589874268,
289
+ "learning_rate": 1.4644660940672627e-05,
290
+ "loss": 3.9884,
291
+ "step": 38
292
+ },
293
+ {
294
+ "epoch": 0.10635759331856144,
295
+ "grad_norm": 1.9651516675949097,
296
+ "learning_rate": 1.2408009626051137e-05,
297
+ "loss": 3.7674,
298
+ "step": 39
299
+ },
300
+ {
301
+ "epoch": 0.10908471109596046,
302
+ "grad_norm": 1.7855304479599,
303
+ "learning_rate": 1.0332332985438248e-05,
304
+ "loss": 3.9421,
305
+ "step": 40
306
+ },
307
+ {
308
+ "epoch": 0.11181182887335947,
309
+ "grad_norm": 1.9799094200134277,
310
+ "learning_rate": 8.426519384872733e-06,
311
+ "loss": 3.8398,
312
+ "step": 41
313
+ },
314
+ {
315
+ "epoch": 0.11453894665075848,
316
+ "grad_norm": 2.2012786865234375,
317
+ "learning_rate": 6.698729810778065e-06,
318
+ "loss": 4.0074,
319
+ "step": 42
320
+ },
321
+ {
322
+ "epoch": 0.11726606442815748,
323
+ "grad_norm": 1.6592918634414673,
324
+ "learning_rate": 5.156362923365588e-06,
325
+ "loss": 3.9292,
326
+ "step": 43
327
+ },
328
+ {
329
+ "epoch": 0.1199931822055565,
330
+ "grad_norm": 2.1375982761383057,
331
+ "learning_rate": 3.8060233744356633e-06,
332
+ "loss": 4.1052,
333
+ "step": 44
334
+ },
335
+ {
336
+ "epoch": 0.12272029998295551,
337
+ "grad_norm": 1.5898287296295166,
338
+ "learning_rate": 2.653493525244721e-06,
339
+ "loss": 3.9829,
340
+ "step": 45
341
+ },
342
+ {
343
+ "epoch": 0.12544741776035453,
344
+ "grad_norm": 1.654889702796936,
345
+ "learning_rate": 1.70370868554659e-06,
346
+ "loss": 4.1315,
347
+ "step": 46
348
+ },
349
+ {
350
+ "epoch": 0.12817453553775354,
351
+ "grad_norm": 1.8290003538131714,
352
+ "learning_rate": 9.607359798384785e-07,
353
+ "loss": 4.1019,
354
+ "step": 47
355
+ },
356
+ {
357
+ "epoch": 0.13090165331515255,
358
+ "grad_norm": 2.4508116245269775,
359
+ "learning_rate": 4.277569313094809e-07,
360
+ "loss": 4.1894,
361
+ "step": 48
362
+ },
363
+ {
364
+ "epoch": 0.13362877109255156,
365
+ "grad_norm": 3.7340142726898193,
366
+ "learning_rate": 1.0705383806982606e-07,
367
+ "loss": 4.4175,
368
+ "step": 49
369
+ },
370
+ {
371
+ "epoch": 0.13635588886995056,
372
+ "grad_norm": 6.049724578857422,
373
+ "learning_rate": 0.0,
374
+ "loss": 4.6422,
375
+ "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.13635588886995056,
379
+ "eval_loss": 4.112647533416748,
380
+ "eval_runtime": 22.5493,
381
+ "eval_samples_per_second": 109.538,
382
+ "eval_steps_per_second": 13.703,
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": 8.33416392081408e+16,
413
  "train_batch_size": 2,
414
  "trial_name": null,
415
  "trial_params": null