dsakerkwq commited on
Commit
87aeb0e
·
verified ·
1 Parent(s): 2a3ca04

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 sha256:5aab4adc6b0dbec7e1743bf6cde67ef44aa80e2d00aaa449c7ca50d808465fef
3
  size 335604696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f84bc46ab082201af00b13fc3e49507a5eac90b1c7e80f11d0a3342ab5471437
3
  size 335604696
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:14436c094f46d49eb3d302d2f6b8344d3857e41ffd7e1698b2fd06f898939c46
3
  size 671466706
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df43e68ae69ca6fe623c5339703762fc5186b0d3ef75f1f046b9cbcf6ef89e2b
3
  size 671466706
last-checkpoint/rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:eee36ac8044f097fa73431eecd9a36c27ad34d0e94366822052e74bd11e11442
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7fe2cb3d01825c410e330747e7e279fb91669b5110d15006c23934d653066aa4
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 sha256:33ed813f95f0df74a7cfc9b90bb14af775b5366807e7c5f50203c51abb56cf04
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea3188ef2e7e51d77ff10f9d2e6b0fbf3942c61a09c7ede44dfe7b9265c40322
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 sha256:335c56a04daad3c962106aff3fa6d25de4c7ef1f4a1fc9cdbd691744eee4a15f
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:963e746fcf9e20fefe1f4e76f83f50ed28fb8d3e1d88aca2cdebcf851fc23a30
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 sha256:79f145fef545aef607f885888f929f2f6a9d171448d0104ec3a1424448a130c0
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:827516dcc892666c88721a0e6e85b3d1b3a1774a9700764ffd127f76b9040e8b
3
  size 15024
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d271cdb95f63cd655315f063ca2e25c78dc5ae4275523c5d4f80f367586b3351
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5607f6de446164d9d9adb8b91c44cec55b14aa391e24ba5637c08b834eedda2a
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 0.0015900260768830776,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-25",
4
- "epoch": 0.03211174888612371,
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": 16.226,
199
  "eval_steps_per_second": 4.219,
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": 2.984974321220321e+17,
230
  "train_batch_size": 1,
231
  "trial_name": null,
232
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.00047391914995387197,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
+ "epoch": 0.06422349777224742,
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": 16.226,
199
  "eval_steps_per_second": 4.219,
200
  "step": 25
201
+ },
202
+ {
203
+ "epoch": 0.03339621884156866,
204
+ "grad_norm": 0.03176894038915634,
205
+ "learning_rate": 5.500000000000001e-05,
206
+ "loss": 0.0021,
207
+ "step": 26
208
+ },
209
+ {
210
+ "epoch": 0.03468068879701361,
211
+ "grad_norm": 0.05508633702993393,
212
+ "learning_rate": 5.205685918464356e-05,
213
+ "loss": 0.0008,
214
+ "step": 27
215
+ },
216
+ {
217
+ "epoch": 0.03596515875245856,
218
+ "grad_norm": 0.05035363510251045,
219
+ "learning_rate": 4.912632135009769e-05,
220
+ "loss": 0.0006,
221
+ "step": 28
222
+ },
223
+ {
224
+ "epoch": 0.03724962870790351,
225
+ "grad_norm": 0.009650109335780144,
226
+ "learning_rate": 4.6220935509274235e-05,
227
+ "loss": 0.0002,
228
+ "step": 29
229
+ },
230
+ {
231
+ "epoch": 0.038534098663348455,
232
+ "grad_norm": 0.018937963992357254,
233
+ "learning_rate": 4.3353142970386564e-05,
234
+ "loss": 0.0002,
235
+ "step": 30
236
+ },
237
+ {
238
+ "epoch": 0.039818568618793404,
239
+ "grad_norm": 0.033147167414426804,
240
+ "learning_rate": 4.053522406135775e-05,
241
+ "loss": 0.0002,
242
+ "step": 31
243
+ },
244
+ {
245
+ "epoch": 0.04110303857423835,
246
+ "grad_norm": 0.006852135062217712,
247
+ "learning_rate": 3.777924554357096e-05,
248
+ "loss": 0.0001,
249
+ "step": 32
250
+ },
251
+ {
252
+ "epoch": 0.042387508529683295,
253
+ "grad_norm": 0.041326116770505905,
254
+ "learning_rate": 3.509700894014496e-05,
255
+ "loss": 0.0005,
256
+ "step": 33
257
+ },
258
+ {
259
+ "epoch": 0.04367197848512824,
260
+ "grad_norm": 0.005345545709133148,
261
+ "learning_rate": 3.250000000000001e-05,
262
+ "loss": 0.0001,
263
+ "step": 34
264
+ },
265
+ {
266
+ "epoch": 0.04495644844057319,
267
+ "grad_norm": 0.0073200250044465065,
268
+ "learning_rate": 2.9999339514117912e-05,
269
+ "loss": 0.0001,
270
+ "step": 35
271
+ },
272
+ {
273
+ "epoch": 0.04624091839601814,
274
+ "grad_norm": 0.0021784715354442596,
275
+ "learning_rate": 2.760573569460757e-05,
276
+ "loss": 0.0001,
277
+ "step": 36
278
+ },
279
+ {
280
+ "epoch": 0.04752538835146309,
281
+ "grad_norm": 0.04825184494256973,
282
+ "learning_rate": 2.53294383204969e-05,
283
+ "loss": 0.0003,
284
+ "step": 37
285
+ },
286
+ {
287
+ "epoch": 0.04880985830690804,
288
+ "grad_norm": 0.061808641999959946,
289
+ "learning_rate": 2.3180194846605367e-05,
290
+ "loss": 0.0012,
291
+ "step": 38
292
+ },
293
+ {
294
+ "epoch": 0.05009432826235299,
295
+ "grad_norm": 0.006139314267784357,
296
+ "learning_rate": 2.1167208663446025e-05,
297
+ "loss": 0.0002,
298
+ "step": 39
299
+ },
300
+ {
301
+ "epoch": 0.051378798217797936,
302
+ "grad_norm": 0.026299120858311653,
303
+ "learning_rate": 1.9299099686894423e-05,
304
+ "loss": 0.0006,
305
+ "step": 40
306
+ },
307
+ {
308
+ "epoch": 0.052663268173242885,
309
+ "grad_norm": 0.02521923929452896,
310
+ "learning_rate": 1.758386744638546e-05,
311
+ "loss": 0.0004,
312
+ "step": 41
313
+ },
314
+ {
315
+ "epoch": 0.05394773812868783,
316
+ "grad_norm": 0.022968459874391556,
317
+ "learning_rate": 1.602885682970026e-05,
318
+ "loss": 0.0001,
319
+ "step": 42
320
+ },
321
+ {
322
+ "epoch": 0.05523220808413278,
323
+ "grad_norm": 0.026028815656900406,
324
+ "learning_rate": 1.464072663102903e-05,
325
+ "loss": 0.0009,
326
+ "step": 43
327
+ },
328
+ {
329
+ "epoch": 0.05651667803957773,
330
+ "grad_norm": 0.007763250730931759,
331
+ "learning_rate": 1.3425421036992098e-05,
332
+ "loss": 0.0002,
333
+ "step": 44
334
+ },
335
+ {
336
+ "epoch": 0.05780114799502268,
337
+ "grad_norm": 0.03652654215693474,
338
+ "learning_rate": 1.2388144172720251e-05,
339
+ "loss": 0.0004,
340
+ "step": 45
341
+ },
342
+ {
343
+ "epoch": 0.05908561795046763,
344
+ "grad_norm": 0.06479442864656448,
345
+ "learning_rate": 1.1533337816991932e-05,
346
+ "loss": 0.0016,
347
+ "step": 46
348
+ },
349
+ {
350
+ "epoch": 0.06037008790591258,
351
+ "grad_norm": 0.005952225532382727,
352
+ "learning_rate": 1.0864662381854632e-05,
353
+ "loss": 0.0002,
354
+ "step": 47
355
+ },
356
+ {
357
+ "epoch": 0.061654557861357526,
358
+ "grad_norm": 0.001265592873096466,
359
+ "learning_rate": 1.0384981238178534e-05,
360
+ "loss": 0.0001,
361
+ "step": 48
362
+ },
363
+ {
364
+ "epoch": 0.06293902781680247,
365
+ "grad_norm": 0.003494854550808668,
366
+ "learning_rate": 1.0096348454262845e-05,
367
+ "loss": 0.0001,
368
+ "step": 49
369
+ },
370
+ {
371
+ "epoch": 0.06422349777224742,
372
+ "grad_norm": 0.030877213925123215,
373
+ "learning_rate": 1e-05,
374
+ "loss": 0.0008,
375
+ "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.06422349777224742,
379
+ "eval_loss": 0.00047391914995387197,
380
+ "eval_runtime": 3.0702,
381
+ "eval_samples_per_second": 16.286,
382
+ "eval_steps_per_second": 4.234,
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": 5.969016129878753e+17,
413
  "train_batch_size": 1,
414
  "trial_name": null,
415
  "trial_params": null