DeepDream2045 commited on
Commit
0dfb680
·
verified ·
1 Parent(s): f442567

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 sha256:4f34ad64f1901f2d1116a8aba4a12d35473cd6e11802af86c5fd9cd784dd210b
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ebc03b6adb6290f7af6d0817c1e97dbaf6fbb8f4ef6c0f94bbcfb7bb997a6017
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a47964c6b430e40936d88c4a101fa50affdabc3a558cd3b5e6c2458aba6311bd
3
  size 141053442
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a535c96c50b058b2c545d13db3c6802eed22ba4d3deef6101596db3faf99fe1e
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 sha256:9680a944bef460f5c0fcdb855256a41499f61e9eb15b49a7e8297ed7b7315e03
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9b2f93bb34f9ab258e8b7d815c0fc107961a573b0edefba6ad48030fa58b946
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 sha256:9263ebb6f5ec69efe14cfb78386f242489847aefdda5baa400343a347a74b52e
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa0e54acfb8909567b0ceab199fa010e93ce755181b2b5a1191352037c6b653d
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:d59962e8a4b6d548cbb5afd262fc0b65fdc633fae1f38f88f417403d0d4faadd
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac60eaeb99d2b3512987257778b41ccaaa24a06f18f717d5d1393c9f2d2b5c4a
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 sha256:208c5b21c4697b6a0e40cfab706d1d698d8de80096caf41fa1e613dff8943ac0
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe44bb8b29e81dbd880a5009d521d9baeebcb1723d0b374eeedacbcdf3efbb60
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": 0.18581102788448334,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-25",
4
- "epoch": 0.010188227503120144,
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": 150.803,
199
  "eval_steps_per_second": 18.856,
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": 0.13740140199661255,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
+ "epoch": 0.020376455006240288,
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": 150.803,
199
  "eval_steps_per_second": 18.856,
200
  "step": 25
201
+ },
202
+ {
203
+ "epoch": 0.01059575660324495,
204
+ "grad_norm": 10.906742095947266,
205
+ "learning_rate": 5e-05,
206
+ "loss": 1.3397,
207
+ "step": 26
208
+ },
209
+ {
210
+ "epoch": 0.011003285703369756,
211
+ "grad_norm": 0.29901590943336487,
212
+ "learning_rate": 4.6729843538492847e-05,
213
+ "loss": 0.0026,
214
+ "step": 27
215
+ },
216
+ {
217
+ "epoch": 0.011410814803494563,
218
+ "grad_norm": 0.4468698501586914,
219
+ "learning_rate": 4.347369038899744e-05,
220
+ "loss": 0.0045,
221
+ "step": 28
222
+ },
223
+ {
224
+ "epoch": 0.011818343903619367,
225
+ "grad_norm": 0.343263179063797,
226
+ "learning_rate": 4.0245483899193595e-05,
227
+ "loss": 0.0034,
228
+ "step": 29
229
+ },
230
+ {
231
+ "epoch": 0.012225873003744173,
232
+ "grad_norm": 0.13799554109573364,
233
+ "learning_rate": 3.705904774487396e-05,
234
+ "loss": 0.0018,
235
+ "step": 30
236
+ },
237
+ {
238
+ "epoch": 0.01263340210386898,
239
+ "grad_norm": 0.08895780146121979,
240
+ "learning_rate": 3.392802673484193e-05,
241
+ "loss": 0.0011,
242
+ "step": 31
243
+ },
244
+ {
245
+ "epoch": 0.013040931203993786,
246
+ "grad_norm": 0.06465604156255722,
247
+ "learning_rate": 3.086582838174551e-05,
248
+ "loss": 0.0008,
249
+ "step": 32
250
+ },
251
+ {
252
+ "epoch": 0.01344846030411859,
253
+ "grad_norm": 0.044299881905317307,
254
+ "learning_rate": 2.7885565489049946e-05,
255
+ "loss": 0.0006,
256
+ "step": 33
257
+ },
258
+ {
259
+ "epoch": 0.013855989404243397,
260
+ "grad_norm": 0.032806701958179474,
261
+ "learning_rate": 2.500000000000001e-05,
262
+ "loss": 0.0004,
263
+ "step": 34
264
+ },
265
+ {
266
+ "epoch": 0.014263518504368203,
267
+ "grad_norm": 0.024947363883256912,
268
+ "learning_rate": 2.2221488349019903e-05,
269
+ "loss": 0.0003,
270
+ "step": 35
271
+ },
272
+ {
273
+ "epoch": 0.014671047604493009,
274
+ "grad_norm": 8.804998397827148,
275
+ "learning_rate": 1.9561928549563968e-05,
276
+ "loss": 0.2376,
277
+ "step": 36
278
+ },
279
+ {
280
+ "epoch": 0.015078576704617814,
281
+ "grad_norm": 18.46295928955078,
282
+ "learning_rate": 1.703270924499656e-05,
283
+ "loss": 0.8035,
284
+ "step": 37
285
+ },
286
+ {
287
+ "epoch": 0.01548610580474262,
288
+ "grad_norm": 10.507019996643066,
289
+ "learning_rate": 1.4644660940672627e-05,
290
+ "loss": 1.2105,
291
+ "step": 38
292
+ },
293
+ {
294
+ "epoch": 0.015893634904867424,
295
+ "grad_norm": 0.02539847604930401,
296
+ "learning_rate": 1.2408009626051137e-05,
297
+ "loss": 0.0003,
298
+ "step": 39
299
+ },
300
+ {
301
+ "epoch": 0.016301164004992232,
302
+ "grad_norm": 0.030192432925105095,
303
+ "learning_rate": 1.0332332985438248e-05,
304
+ "loss": 0.0004,
305
+ "step": 40
306
+ },
307
+ {
308
+ "epoch": 0.016708693105117037,
309
+ "grad_norm": 0.03641684353351593,
310
+ "learning_rate": 8.426519384872733e-06,
311
+ "loss": 0.0005,
312
+ "step": 41
313
+ },
314
+ {
315
+ "epoch": 0.017116222205241845,
316
+ "grad_norm": 0.041325893253088,
317
+ "learning_rate": 6.698729810778065e-06,
318
+ "loss": 0.0005,
319
+ "step": 42
320
+ },
321
+ {
322
+ "epoch": 0.01752375130536665,
323
+ "grad_norm": 0.04761205241084099,
324
+ "learning_rate": 5.156362923365588e-06,
325
+ "loss": 0.0006,
326
+ "step": 43
327
+ },
328
+ {
329
+ "epoch": 0.017931280405491454,
330
+ "grad_norm": 0.050131577998399734,
331
+ "learning_rate": 3.8060233744356633e-06,
332
+ "loss": 0.0006,
333
+ "step": 44
334
+ },
335
+ {
336
+ "epoch": 0.01833880950561626,
337
+ "grad_norm": 0.05262096971273422,
338
+ "learning_rate": 2.653493525244721e-06,
339
+ "loss": 0.0007,
340
+ "step": 45
341
+ },
342
+ {
343
+ "epoch": 0.018746338605741066,
344
+ "grad_norm": 0.05300018563866615,
345
+ "learning_rate": 1.70370868554659e-06,
346
+ "loss": 0.0007,
347
+ "step": 46
348
+ },
349
+ {
350
+ "epoch": 0.01915386770586587,
351
+ "grad_norm": 0.05538802593946457,
352
+ "learning_rate": 9.607359798384785e-07,
353
+ "loss": 0.0007,
354
+ "step": 47
355
+ },
356
+ {
357
+ "epoch": 0.01956139680599068,
358
+ "grad_norm": 0.05361310392618179,
359
+ "learning_rate": 4.277569313094809e-07,
360
+ "loss": 0.0007,
361
+ "step": 48
362
+ },
363
+ {
364
+ "epoch": 0.019968925906115483,
365
+ "grad_norm": 10.175657272338867,
366
+ "learning_rate": 1.0705383806982606e-07,
367
+ "loss": 0.4815,
368
+ "step": 49
369
+ },
370
+ {
371
+ "epoch": 0.020376455006240288,
372
+ "grad_norm": 10.826835632324219,
373
+ "learning_rate": 0.0,
374
+ "loss": 0.5115,
375
+ "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.020376455006240288,
379
+ "eval_loss": 0.13740140199661255,
380
+ "eval_runtime": 109.8174,
381
+ "eval_samples_per_second": 150.532,
382
+ "eval_steps_per_second": 18.822,
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