dada22231 commited on
Commit
46c9d30
·
verified ·
1 Parent(s): c19acc3

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:b47bd1cb502625382b7081c7142ec4befe8fd7e9dc6eef80c7ab64d8a16410d8
3
  size 319876032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9980203fecea2945dec7038d57bdb0d4b64e45457dbbe03d078ee5fec5b47cd6
3
  size 319876032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9ae133cc30b18eb0ce9f2660c18bb3a26e05019a45660f2501d5c72a602a22bf
3
  size 640009682
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a950501e59cc60556b6e60bfae58a8e2ab2978861c2b00aa8bedf3d3212648c2
3
  size 640009682
last-checkpoint/rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0df0e009d997c8dcade38dcf66565d13b41b25ac5a0ad35eb29c2f550ad248ba
3
  size 14960
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca4c6d5cc9a3ae8d0f927ed244d11d19b09603eb60a1b538ba52cec69a6f328e
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 sha256:872f608404dcb445df442829c1378677d23455a96e5bda1b70e12ce4ccd70951
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1664f76e4f4a0eb0086113d4f38f040f4f17780acd2ffa2a8e61d2fa9947dede
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:e9786223e5c6333bbd673a87ec449175d93624cf2ed38966e8dab7782e48bc9d
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82c5005b061155693e44ef1703233f9ad82f2db8a33d842cbc3269ac2f7b1fc1
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:fb08ef9da12f851416d6f45dc900bf8d229bcd39bb866ef944b302cb374fd696
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e90433fee02cc00f1834d9a6d7419bbbe6ced9e1ddd9aa53ca1fdc96c4b7f604
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": 0.1036110669374466,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-25",
4
- "epoch": 0.04113322021697774,
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": 5.981,
199
  "eval_steps_per_second": 1.555,
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": 3.2845074557147546e+17,
230
  "train_batch_size": 1,
231
  "trial_name": null,
232
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.08817896246910095,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
+ "epoch": 0.08226644043395548,
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": 5.981,
199
  "eval_steps_per_second": 1.555,
200
  "step": 25
201
+ },
202
+ {
203
+ "epoch": 0.042778549025656844,
204
+ "grad_norm": 0.7192914485931396,
205
+ "learning_rate": 5.500000000000001e-05,
206
+ "loss": 0.5559,
207
+ "step": 26
208
+ },
209
+ {
210
+ "epoch": 0.044423877834335955,
211
+ "grad_norm": 0.7658919095993042,
212
+ "learning_rate": 5.205685918464356e-05,
213
+ "loss": 0.6265,
214
+ "step": 27
215
+ },
216
+ {
217
+ "epoch": 0.046069206643015066,
218
+ "grad_norm": 0.6952080726623535,
219
+ "learning_rate": 4.912632135009769e-05,
220
+ "loss": 0.6117,
221
+ "step": 28
222
+ },
223
+ {
224
+ "epoch": 0.04771453545169418,
225
+ "grad_norm": 0.5986710786819458,
226
+ "learning_rate": 4.6220935509274235e-05,
227
+ "loss": 0.6545,
228
+ "step": 29
229
+ },
230
+ {
231
+ "epoch": 0.04935986426037328,
232
+ "grad_norm": 0.6377705335617065,
233
+ "learning_rate": 4.3353142970386564e-05,
234
+ "loss": 0.8012,
235
+ "step": 30
236
+ },
237
+ {
238
+ "epoch": 0.05100519306905239,
239
+ "grad_norm": 0.7861823439598083,
240
+ "learning_rate": 4.053522406135775e-05,
241
+ "loss": 0.9109,
242
+ "step": 31
243
+ },
244
+ {
245
+ "epoch": 0.052650521877731504,
246
+ "grad_norm": 0.9364539980888367,
247
+ "learning_rate": 3.777924554357096e-05,
248
+ "loss": 1.1027,
249
+ "step": 32
250
+ },
251
+ {
252
+ "epoch": 0.054295850686410616,
253
+ "grad_norm": 1.606742024421692,
254
+ "learning_rate": 3.509700894014496e-05,
255
+ "loss": 1.5875,
256
+ "step": 33
257
+ },
258
+ {
259
+ "epoch": 0.05594117949508972,
260
+ "grad_norm": 2.1167681217193604,
261
+ "learning_rate": 3.250000000000001e-05,
262
+ "loss": 2.5575,
263
+ "step": 34
264
+ },
265
+ {
266
+ "epoch": 0.05758650830376883,
267
+ "grad_norm": 8.326395988464355,
268
+ "learning_rate": 2.9999339514117912e-05,
269
+ "loss": 5.9666,
270
+ "step": 35
271
+ },
272
+ {
273
+ "epoch": 0.05923183711244794,
274
+ "grad_norm": 10.054471015930176,
275
+ "learning_rate": 2.760573569460757e-05,
276
+ "loss": 10.1117,
277
+ "step": 36
278
+ },
279
+ {
280
+ "epoch": 0.060877165921127054,
281
+ "grad_norm": 11.48097038269043,
282
+ "learning_rate": 2.53294383204969e-05,
283
+ "loss": 11.9451,
284
+ "step": 37
285
+ },
286
+ {
287
+ "epoch": 0.06252249472980616,
288
+ "grad_norm": 14.909457206726074,
289
+ "learning_rate": 2.3180194846605367e-05,
290
+ "loss": 8.4022,
291
+ "step": 38
292
+ },
293
+ {
294
+ "epoch": 0.06416782353848527,
295
+ "grad_norm": 0.8173323273658752,
296
+ "learning_rate": 2.1167208663446025e-05,
297
+ "loss": 0.4723,
298
+ "step": 39
299
+ },
300
+ {
301
+ "epoch": 0.06581315234716438,
302
+ "grad_norm": 0.884682834148407,
303
+ "learning_rate": 1.9299099686894423e-05,
304
+ "loss": 0.5099,
305
+ "step": 40
306
+ },
307
+ {
308
+ "epoch": 0.06745848115584349,
309
+ "grad_norm": 0.9192363619804382,
310
+ "learning_rate": 1.758386744638546e-05,
311
+ "loss": 0.5514,
312
+ "step": 41
313
+ },
314
+ {
315
+ "epoch": 0.0691038099645226,
316
+ "grad_norm": 0.8022204041481018,
317
+ "learning_rate": 1.602885682970026e-05,
318
+ "loss": 0.7,
319
+ "step": 42
320
+ },
321
+ {
322
+ "epoch": 0.0707491387732017,
323
+ "grad_norm": 0.6816873550415039,
324
+ "learning_rate": 1.464072663102903e-05,
325
+ "loss": 0.7884,
326
+ "step": 43
327
+ },
328
+ {
329
+ "epoch": 0.07239446758188081,
330
+ "grad_norm": 1.0044586658477783,
331
+ "learning_rate": 1.3425421036992098e-05,
332
+ "loss": 0.9553,
333
+ "step": 44
334
+ },
335
+ {
336
+ "epoch": 0.07403979639055992,
337
+ "grad_norm": 1.6737107038497925,
338
+ "learning_rate": 1.2388144172720251e-05,
339
+ "loss": 1.3098,
340
+ "step": 45
341
+ },
342
+ {
343
+ "epoch": 0.07568512519923903,
344
+ "grad_norm": 1.7273823022842407,
345
+ "learning_rate": 1.1533337816991932e-05,
346
+ "loss": 1.6871,
347
+ "step": 46
348
+ },
349
+ {
350
+ "epoch": 0.07733045400791815,
351
+ "grad_norm": 2.9524919986724854,
352
+ "learning_rate": 1.0864662381854632e-05,
353
+ "loss": 3.5467,
354
+ "step": 47
355
+ },
356
+ {
357
+ "epoch": 0.07897578281659726,
358
+ "grad_norm": 6.543963432312012,
359
+ "learning_rate": 1.0384981238178534e-05,
360
+ "loss": 8.2054,
361
+ "step": 48
362
+ },
363
+ {
364
+ "epoch": 0.08062111162527637,
365
+ "grad_norm": 9.975615501403809,
366
+ "learning_rate": 1.0096348454262845e-05,
367
+ "loss": 11.5187,
368
+ "step": 49
369
+ },
370
+ {
371
+ "epoch": 0.08226644043395548,
372
+ "grad_norm": 18.941373825073242,
373
+ "learning_rate": 1e-05,
374
+ "loss": 13.8286,
375
+ "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.08226644043395548,
379
+ "eval_loss": 0.08817896246910095,
380
+ "eval_runtime": 8.3777,
381
+ "eval_samples_per_second": 5.968,
382
+ "eval_steps_per_second": 1.552,
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": 6.570658412877578e+17,
413
  "train_batch_size": 1,
414
  "trial_name": null,
415
  "trial_params": null