dsakerkwq commited on
Commit
c8f7f9a
1 Parent(s): 81cba96

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 sha256:39e8dbce7aad02405fe8fabe1559911b8f26f929c3fdabc9dbdd17039fd4a3b6
3
  size 432223744
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b26bf245c06c4725608a67574a8366856f7769caf8048ae734c32129a9c71ab2
3
  size 432223744
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0f86f20ec1ec1918883a755fa401dbda9dcdb408b5238494f96ca06b4ec8c0e4
3
  size 864785974
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b19e52dd143e6af8cfd11f19a7d01712860ce1b4f83d905176f49115562770e
3
  size 864785974
last-checkpoint/rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:859a89733a0f19db48e79aae86660d0420c9d31b3b6976e03d7e9111b6126889
3
  size 14960
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a778c3d3993a96084c802d9d59bfe215c97dab181335161ad04bdbc6b414588
3
  size 14960
last-checkpoint/rng_state_1.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9b9900db17e6e4fc13aa494320972e17c34bdbc2b175d7b26ac407b71a71a506
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:215045760bb10458c36ff879e589cf673f5363d67ac86c453f1435924909145c
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 sha256:291111ce5b4e341d3a6141411c95058559bea8287b3b45b3594d68ada42bcd9b
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8302e9ac496c13897f2c4a9fd190e4882b1eb0f431e2047ab3a12bc980261ca0
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 sha256:7c1c00f49142280d24edaaf013d27865244a29ddd6f2cebc8a6f72bbf1a9aabf
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:489f29702e3b9c3a96a1a37289986d1bdd60c6a2ba12c194c6ab89942e733951
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": 0.0008296275627799332,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-25",
4
- "epoch": 0.5979073243647235,
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": 11.088,
199
  "eval_steps_per_second": 2.883,
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": 3.390293917554442e+17,
230
  "train_batch_size": 2,
231
  "trial_name": null,
232
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.0002391961170360446,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
+ "epoch": 1.2062780269058295,
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": 11.088,
199
  "eval_steps_per_second": 2.883,
200
  "step": 25
201
+ },
202
+ {
203
+ "epoch": 0.6218236173393124,
204
+ "grad_norm": 0.012360863387584686,
205
+ "learning_rate": 5.500000000000001e-05,
206
+ "loss": 0.0005,
207
+ "step": 26
208
+ },
209
+ {
210
+ "epoch": 0.6457399103139013,
211
+ "grad_norm": 0.030168309807777405,
212
+ "learning_rate": 5.205685918464356e-05,
213
+ "loss": 0.001,
214
+ "step": 27
215
+ },
216
+ {
217
+ "epoch": 0.6696562032884903,
218
+ "grad_norm": 0.01952563412487507,
219
+ "learning_rate": 4.912632135009769e-05,
220
+ "loss": 0.0006,
221
+ "step": 28
222
+ },
223
+ {
224
+ "epoch": 0.6935724962630793,
225
+ "grad_norm": 0.025816479697823524,
226
+ "learning_rate": 4.6220935509274235e-05,
227
+ "loss": 0.0001,
228
+ "step": 29
229
+ },
230
+ {
231
+ "epoch": 0.7174887892376681,
232
+ "grad_norm": 0.023305699229240417,
233
+ "learning_rate": 4.3353142970386564e-05,
234
+ "loss": 0.0003,
235
+ "step": 30
236
+ },
237
+ {
238
+ "epoch": 0.7414050822122571,
239
+ "grad_norm": 0.042270027101039886,
240
+ "learning_rate": 4.053522406135775e-05,
241
+ "loss": 0.004,
242
+ "step": 31
243
+ },
244
+ {
245
+ "epoch": 0.7653213751868461,
246
+ "grad_norm": 0.013639895245432854,
247
+ "learning_rate": 3.777924554357096e-05,
248
+ "loss": 0.0011,
249
+ "step": 32
250
+ },
251
+ {
252
+ "epoch": 0.7892376681614349,
253
+ "grad_norm": 0.015320922248065472,
254
+ "learning_rate": 3.509700894014496e-05,
255
+ "loss": 0.0009,
256
+ "step": 33
257
+ },
258
+ {
259
+ "epoch": 0.8131539611360239,
260
+ "grad_norm": 0.017550518736243248,
261
+ "learning_rate": 3.250000000000001e-05,
262
+ "loss": 0.0004,
263
+ "step": 34
264
+ },
265
+ {
266
+ "epoch": 0.8370702541106129,
267
+ "grad_norm": 0.018104810267686844,
268
+ "learning_rate": 2.9999339514117912e-05,
269
+ "loss": 0.0007,
270
+ "step": 35
271
+ },
272
+ {
273
+ "epoch": 0.8609865470852018,
274
+ "grad_norm": 0.024184156209230423,
275
+ "learning_rate": 2.760573569460757e-05,
276
+ "loss": 0.0011,
277
+ "step": 36
278
+ },
279
+ {
280
+ "epoch": 0.8849028400597907,
281
+ "grad_norm": 0.026356741786003113,
282
+ "learning_rate": 2.53294383204969e-05,
283
+ "loss": 0.001,
284
+ "step": 37
285
+ },
286
+ {
287
+ "epoch": 0.9088191330343797,
288
+ "grad_norm": 0.014368100091814995,
289
+ "learning_rate": 2.3180194846605367e-05,
290
+ "loss": 0.0003,
291
+ "step": 38
292
+ },
293
+ {
294
+ "epoch": 0.9327354260089686,
295
+ "grad_norm": 0.01398097537457943,
296
+ "learning_rate": 2.1167208663446025e-05,
297
+ "loss": 0.0003,
298
+ "step": 39
299
+ },
300
+ {
301
+ "epoch": 0.9566517189835575,
302
+ "grad_norm": 0.01466523390263319,
303
+ "learning_rate": 1.9299099686894423e-05,
304
+ "loss": 0.0001,
305
+ "step": 40
306
+ },
307
+ {
308
+ "epoch": 0.9805680119581465,
309
+ "grad_norm": 0.014875360764563084,
310
+ "learning_rate": 1.758386744638546e-05,
311
+ "loss": 0.0002,
312
+ "step": 41
313
+ },
314
+ {
315
+ "epoch": 1.014947683109118,
316
+ "grad_norm": 0.02478068880736828,
317
+ "learning_rate": 1.602885682970026e-05,
318
+ "loss": 0.0065,
319
+ "step": 42
320
+ },
321
+ {
322
+ "epoch": 1.038863976083707,
323
+ "grad_norm": 0.009487264789640903,
324
+ "learning_rate": 1.464072663102903e-05,
325
+ "loss": 0.0005,
326
+ "step": 43
327
+ },
328
+ {
329
+ "epoch": 1.062780269058296,
330
+ "grad_norm": 0.010159480385482311,
331
+ "learning_rate": 1.3425421036992098e-05,
332
+ "loss": 0.0004,
333
+ "step": 44
334
+ },
335
+ {
336
+ "epoch": 1.086696562032885,
337
+ "grad_norm": 0.009533469565212727,
338
+ "learning_rate": 1.2388144172720251e-05,
339
+ "loss": 0.0003,
340
+ "step": 45
341
+ },
342
+ {
343
+ "epoch": 1.1106128550074739,
344
+ "grad_norm": 0.008421096950769424,
345
+ "learning_rate": 1.1533337816991932e-05,
346
+ "loss": 0.0002,
347
+ "step": 46
348
+ },
349
+ {
350
+ "epoch": 1.1345291479820627,
351
+ "grad_norm": 0.00984017550945282,
352
+ "learning_rate": 1.0864662381854632e-05,
353
+ "loss": 0.0003,
354
+ "step": 47
355
+ },
356
+ {
357
+ "epoch": 1.1584454409566518,
358
+ "grad_norm": 0.014092501252889633,
359
+ "learning_rate": 1.0384981238178534e-05,
360
+ "loss": 0.0002,
361
+ "step": 48
362
+ },
363
+ {
364
+ "epoch": 1.1823617339312407,
365
+ "grad_norm": 0.003745349822565913,
366
+ "learning_rate": 1.0096348454262845e-05,
367
+ "loss": 0.0001,
368
+ "step": 49
369
+ },
370
+ {
371
+ "epoch": 1.2062780269058295,
372
+ "grad_norm": 0.0038105223793536425,
373
+ "learning_rate": 1e-05,
374
+ "loss": 0.0001,
375
+ "step": 50
376
+ },
377
+ {
378
+ "epoch": 1.2062780269058295,
379
+ "eval_loss": 0.0002391961170360446,
380
+ "eval_runtime": 4.1649,
381
+ "eval_samples_per_second": 12.005,
382
+ "eval_steps_per_second": 3.121,
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": 6.757792457246638e+17,
413
  "train_batch_size": 2,
414
  "trial_name": null,
415
  "trial_params": null