vdos commited on
Commit
17aaa10
·
verified ·
1 Parent(s): 4ba2fb9

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 sha256:9cbb2db5c241a4553aa1fecfe60ceca22d6083bd9140b66a530b6781b682517e
3
  size 445688440
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8af414ea4566ce9e557b07e5c418d7c9ff37d01c29d557bde538ed5c255c733c
3
  size 445688440
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:582adbaeb4e63b43da432aa9342338950ae288202a1f5bc8eb34b806ba72c792
3
  size 891559354
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:027352818ad370e4f115af586e5d2b57b283031d240b62934785e50c6c4e27f9
3
  size 891559354
last-checkpoint/rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:98bed804501c83a443212e698c81e2f59ae0593a94cbdae7c3c0926caa0ddda1
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d210f1b4508e0b14718aee8b474a75ef33e570d2742ab3213d64f0c8d649c4d0
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 sha256:65f894f3bd0e6a7480a458b8103fd23e2f686650d9c5c430b236007af640eab3
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3eefb425294e5b1fb3776d7739e56463038021f05e6bdb62010a56abbef2a7d5
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:d49ee717dd8279a6e72085f7bf4733c9edf8d69e2fa0e890fbad97bee16a7720
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:486130ae337c3a862a90c41b0ef19134915cd67ce9f9cc4459bdbfb9d2b1a8e2
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 sha256:0ea27066bf16d8be6a42b4d79014f645d6346e018cc0dfd87577f4cd12227571
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e04d7b5c25e34a533abb24d633d6127ac51ab955d6bdabfdb43138f75172de6
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": 1.7844452857971191,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-25",
4
- "epoch": 0.039012971813127864,
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": 15.185,
199
  "eval_steps_per_second": 1.899,
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": 5.468644419043328e+17,
230
  "train_batch_size": 2,
231
  "trial_name": null,
232
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.713279128074646,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
+ "epoch": 0.07802594362625573,
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": 15.185,
199
  "eval_steps_per_second": 1.899,
200
  "step": 25
201
+ },
202
+ {
203
+ "epoch": 0.04057349068565298,
204
+ "grad_norm": 11.710362434387207,
205
+ "learning_rate": 5e-05,
206
+ "loss": 2.1715,
207
+ "step": 26
208
+ },
209
+ {
210
+ "epoch": 0.042134009558178094,
211
+ "grad_norm": 14.576261520385742,
212
+ "learning_rate": 4.6729843538492847e-05,
213
+ "loss": 2.0575,
214
+ "step": 27
215
+ },
216
+ {
217
+ "epoch": 0.043694528430703206,
218
+ "grad_norm": 13.412975311279297,
219
+ "learning_rate": 4.347369038899744e-05,
220
+ "loss": 1.9133,
221
+ "step": 28
222
+ },
223
+ {
224
+ "epoch": 0.045255047303228324,
225
+ "grad_norm": 11.340127944946289,
226
+ "learning_rate": 4.0245483899193595e-05,
227
+ "loss": 1.819,
228
+ "step": 29
229
+ },
230
+ {
231
+ "epoch": 0.046815566175753436,
232
+ "grad_norm": 11.435134887695312,
233
+ "learning_rate": 3.705904774487396e-05,
234
+ "loss": 1.8139,
235
+ "step": 30
236
+ },
237
+ {
238
+ "epoch": 0.048376085048278554,
239
+ "grad_norm": 10.115267753601074,
240
+ "learning_rate": 3.392802673484193e-05,
241
+ "loss": 1.7239,
242
+ "step": 31
243
+ },
244
+ {
245
+ "epoch": 0.049936603920803666,
246
+ "grad_norm": 7.939040660858154,
247
+ "learning_rate": 3.086582838174551e-05,
248
+ "loss": 1.5591,
249
+ "step": 32
250
+ },
251
+ {
252
+ "epoch": 0.051497122793328784,
253
+ "grad_norm": 8.323566436767578,
254
+ "learning_rate": 2.7885565489049946e-05,
255
+ "loss": 1.5233,
256
+ "step": 33
257
+ },
258
+ {
259
+ "epoch": 0.053057641665853895,
260
+ "grad_norm": 8.962291717529297,
261
+ "learning_rate": 2.500000000000001e-05,
262
+ "loss": 1.6057,
263
+ "step": 34
264
+ },
265
+ {
266
+ "epoch": 0.054618160538379014,
267
+ "grad_norm": 11.388747215270996,
268
+ "learning_rate": 2.2221488349019903e-05,
269
+ "loss": 1.3288,
270
+ "step": 35
271
+ },
272
+ {
273
+ "epoch": 0.056178679410904125,
274
+ "grad_norm": 9.159733772277832,
275
+ "learning_rate": 1.9561928549563968e-05,
276
+ "loss": 1.467,
277
+ "step": 36
278
+ },
279
+ {
280
+ "epoch": 0.05773919828342924,
281
+ "grad_norm": 18.99442481994629,
282
+ "learning_rate": 1.703270924499656e-05,
283
+ "loss": 1.8765,
284
+ "step": 37
285
+ },
286
+ {
287
+ "epoch": 0.059299717155954355,
288
+ "grad_norm": 25.547096252441406,
289
+ "learning_rate": 1.4644660940672627e-05,
290
+ "loss": 2.1997,
291
+ "step": 38
292
+ },
293
+ {
294
+ "epoch": 0.06086023602847947,
295
+ "grad_norm": 7.026412487030029,
296
+ "learning_rate": 1.2408009626051137e-05,
297
+ "loss": 2.0025,
298
+ "step": 39
299
+ },
300
+ {
301
+ "epoch": 0.062420754901004585,
302
+ "grad_norm": 7.772118091583252,
303
+ "learning_rate": 1.0332332985438248e-05,
304
+ "loss": 2.0808,
305
+ "step": 40
306
+ },
307
+ {
308
+ "epoch": 0.0639812737735297,
309
+ "grad_norm": 6.68425989151001,
310
+ "learning_rate": 8.426519384872733e-06,
311
+ "loss": 1.8221,
312
+ "step": 41
313
+ },
314
+ {
315
+ "epoch": 0.06554179264605481,
316
+ "grad_norm": 6.783787250518799,
317
+ "learning_rate": 6.698729810778065e-06,
318
+ "loss": 1.8117,
319
+ "step": 42
320
+ },
321
+ {
322
+ "epoch": 0.06710231151857993,
323
+ "grad_norm": 8.404589653015137,
324
+ "learning_rate": 5.156362923365588e-06,
325
+ "loss": 1.8148,
326
+ "step": 43
327
+ },
328
+ {
329
+ "epoch": 0.06866283039110505,
330
+ "grad_norm": 6.892530918121338,
331
+ "learning_rate": 3.8060233744356633e-06,
332
+ "loss": 1.6587,
333
+ "step": 44
334
+ },
335
+ {
336
+ "epoch": 0.07022334926363016,
337
+ "grad_norm": 6.792155742645264,
338
+ "learning_rate": 2.653493525244721e-06,
339
+ "loss": 1.6503,
340
+ "step": 45
341
+ },
342
+ {
343
+ "epoch": 0.07178386813615527,
344
+ "grad_norm": 8.016270637512207,
345
+ "learning_rate": 1.70370868554659e-06,
346
+ "loss": 1.515,
347
+ "step": 46
348
+ },
349
+ {
350
+ "epoch": 0.07334438700868039,
351
+ "grad_norm": 10.944890975952148,
352
+ "learning_rate": 9.607359798384785e-07,
353
+ "loss": 1.457,
354
+ "step": 47
355
+ },
356
+ {
357
+ "epoch": 0.0749049058812055,
358
+ "grad_norm": 9.899993896484375,
359
+ "learning_rate": 4.277569313094809e-07,
360
+ "loss": 1.4708,
361
+ "step": 48
362
+ },
363
+ {
364
+ "epoch": 0.07646542475373061,
365
+ "grad_norm": 12.46395492553711,
366
+ "learning_rate": 1.0705383806982606e-07,
367
+ "loss": 1.5409,
368
+ "step": 49
369
+ },
370
+ {
371
+ "epoch": 0.07802594362625573,
372
+ "grad_norm": 30.2358341217041,
373
+ "learning_rate": 0.0,
374
+ "loss": 2.1207,
375
+ "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.07802594362625573,
379
+ "eval_loss": 1.713279128074646,
380
+ "eval_runtime": 284.2744,
381
+ "eval_samples_per_second": 15.186,
382
+ "eval_steps_per_second": 1.9,
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": 1.0937288838086656e+18,
413
  "train_batch_size": 2,
414
  "trial_name": null,
415
  "trial_params": null