dada22231 commited on
Commit
d05e30c
·
verified ·
1 Parent(s): 2c6e34e

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 sha256:4d6e26b6da35a43dddf766ce292cbd75a8f3d4985f34aa67d345ff8ab604340c
3
  size 335604696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5417bef7e910b70ae7551b5ae8ce68b80aad629f6b22aa19a41c63a13f57ade7
3
  size 335604696
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:65ba76bab221c67a176cde570f6ba0533f36c16e4ed9e6487da8fcd1ca86c63f
3
  size 671466706
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1f89100c5b36fb6b2c1bf37ac3f36fe722775f150d643bba023c3904237f0ca
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 sha256:6d2cc206da7493a320230fb6e8ac6d0e55d4db8851531ce660a506cb603b5d1a
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5d4454ee4d041183013e50ad731a6545f1b11dc18a1b2d5ea7dbde423788655
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 sha256:8a4cfe23d5dcf55ae3b1defe2519d56289bae21c05479c1d091f84d0511e4601
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a190d37c33c30c6b71ea1046d513f1efb863a9be99a868fcef41deeae6ebb7e
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 sha256:867f93df9d2461bb0826da51aa8b7d400f15ee311c6a7f09e765a05cd9bf3981
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1beea2c7a7e883cb7862f4f83e58e75d5b90f76b384f1e9ff74d57a8c0f616d
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:d37f7635a79c35e677d457a431b495bcd93a7cbdacfd63b8fbee80751197e775
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a30430798ff28a9d1850ec59ed9d1b239d8d77c08d188ccd304cad5a28d042c7
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": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 0.010689756540794784,
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": 10.441,
199
  "eval_steps_per_second": 2.715,
200
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
201
  }
202
  ],
203
  "logging_steps": 1,
@@ -212,12 +395,12 @@
212
  "should_evaluate": false,
213
  "should_log": false,
214
  "should_save": true,
215
- "should_training_stop": false
216
  },
217
  "attributes": {}
218
  }
219
  },
220
- "total_flos": 2.874098022487163e+17,
221
  "train_batch_size": 1,
222
  "trial_name": null,
223
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.021379513081589568,
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": 10.441,
199
  "eval_steps_per_second": 2.715,
200
  "step": 25
201
+ },
202
+ {
203
+ "epoch": 0.011117346802426575,
204
+ "grad_norm": 12.312941551208496,
205
+ "learning_rate": 5.500000000000001e-05,
206
+ "loss": 11.3935,
207
+ "step": 26
208
+ },
209
+ {
210
+ "epoch": 0.011544937064058366,
211
+ "grad_norm": 14.37541675567627,
212
+ "learning_rate": 5.205685918464356e-05,
213
+ "loss": 15.2392,
214
+ "step": 27
215
+ },
216
+ {
217
+ "epoch": 0.011972527325690157,
218
+ "grad_norm": 12.340313911437988,
219
+ "learning_rate": 4.912632135009769e-05,
220
+ "loss": 15.1875,
221
+ "step": 28
222
+ },
223
+ {
224
+ "epoch": 0.012400117587321948,
225
+ "grad_norm": 11.889932632446289,
226
+ "learning_rate": 4.6220935509274235e-05,
227
+ "loss": 15.776,
228
+ "step": 29
229
+ },
230
+ {
231
+ "epoch": 0.01282770784895374,
232
+ "grad_norm": 13.100401878356934,
233
+ "learning_rate": 4.3353142970386564e-05,
234
+ "loss": 16.6528,
235
+ "step": 30
236
+ },
237
+ {
238
+ "epoch": 0.01325529811058553,
239
+ "grad_norm": 13.858903884887695,
240
+ "learning_rate": 4.053522406135775e-05,
241
+ "loss": 18.0721,
242
+ "step": 31
243
+ },
244
+ {
245
+ "epoch": 0.013682888372217322,
246
+ "grad_norm": 13.05334758758545,
247
+ "learning_rate": 3.777924554357096e-05,
248
+ "loss": 17.9538,
249
+ "step": 32
250
+ },
251
+ {
252
+ "epoch": 0.014110478633849115,
253
+ "grad_norm": 13.130781173706055,
254
+ "learning_rate": 3.509700894014496e-05,
255
+ "loss": 17.6755,
256
+ "step": 33
257
+ },
258
+ {
259
+ "epoch": 0.014538068895480906,
260
+ "grad_norm": 12.964271545410156,
261
+ "learning_rate": 3.250000000000001e-05,
262
+ "loss": 18.443,
263
+ "step": 34
264
+ },
265
+ {
266
+ "epoch": 0.014965659157112697,
267
+ "grad_norm": 13.65394401550293,
268
+ "learning_rate": 2.9999339514117912e-05,
269
+ "loss": 18.8783,
270
+ "step": 35
271
+ },
272
+ {
273
+ "epoch": 0.015393249418744488,
274
+ "grad_norm": 14.562626838684082,
275
+ "learning_rate": 2.760573569460757e-05,
276
+ "loss": 19.9088,
277
+ "step": 36
278
+ },
279
+ {
280
+ "epoch": 0.01582083968037628,
281
+ "grad_norm": 15.111961364746094,
282
+ "learning_rate": 2.53294383204969e-05,
283
+ "loss": 20.2572,
284
+ "step": 37
285
+ },
286
+ {
287
+ "epoch": 0.01624842994200807,
288
+ "grad_norm": 12.405916213989258,
289
+ "learning_rate": 2.3180194846605367e-05,
290
+ "loss": 14.7318,
291
+ "step": 38
292
+ },
293
+ {
294
+ "epoch": 0.01667602020363986,
295
+ "grad_norm": 11.5278959274292,
296
+ "learning_rate": 2.1167208663446025e-05,
297
+ "loss": 13.9384,
298
+ "step": 39
299
+ },
300
+ {
301
+ "epoch": 0.017103610465271653,
302
+ "grad_norm": 12.947035789489746,
303
+ "learning_rate": 1.9299099686894423e-05,
304
+ "loss": 15.3045,
305
+ "step": 40
306
+ },
307
+ {
308
+ "epoch": 0.017531200726903444,
309
+ "grad_norm": 13.242534637451172,
310
+ "learning_rate": 1.758386744638546e-05,
311
+ "loss": 16.33,
312
+ "step": 41
313
+ },
314
+ {
315
+ "epoch": 0.017958790988535235,
316
+ "grad_norm": 12.534408569335938,
317
+ "learning_rate": 1.602885682970026e-05,
318
+ "loss": 16.4756,
319
+ "step": 42
320
+ },
321
+ {
322
+ "epoch": 0.018386381250167026,
323
+ "grad_norm": 12.54093074798584,
324
+ "learning_rate": 1.464072663102903e-05,
325
+ "loss": 17.4493,
326
+ "step": 43
327
+ },
328
+ {
329
+ "epoch": 0.018813971511798817,
330
+ "grad_norm": 12.03007698059082,
331
+ "learning_rate": 1.3425421036992098e-05,
332
+ "loss": 16.682,
333
+ "step": 44
334
+ },
335
+ {
336
+ "epoch": 0.01924156177343061,
337
+ "grad_norm": 13.081326484680176,
338
+ "learning_rate": 1.2388144172720251e-05,
339
+ "loss": 17.7897,
340
+ "step": 45
341
+ },
342
+ {
343
+ "epoch": 0.019669152035062403,
344
+ "grad_norm": 13.734363555908203,
345
+ "learning_rate": 1.1533337816991932e-05,
346
+ "loss": 18.6434,
347
+ "step": 46
348
+ },
349
+ {
350
+ "epoch": 0.020096742296694194,
351
+ "grad_norm": 13.227235794067383,
352
+ "learning_rate": 1.0864662381854632e-05,
353
+ "loss": 18.1203,
354
+ "step": 47
355
+ },
356
+ {
357
+ "epoch": 0.020524332558325985,
358
+ "grad_norm": 14.222868919372559,
359
+ "learning_rate": 1.0384981238178534e-05,
360
+ "loss": 18.8453,
361
+ "step": 48
362
+ },
363
+ {
364
+ "epoch": 0.020951922819957777,
365
+ "grad_norm": 17.175867080688477,
366
+ "learning_rate": 1.0096348454262845e-05,
367
+ "loss": 20.3476,
368
+ "step": 49
369
+ },
370
+ {
371
+ "epoch": 0.021379513081589568,
372
+ "grad_norm": 19.736366271972656,
373
+ "learning_rate": 1e-05,
374
+ "loss": 20.5668,
375
+ "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.021379513081589568,
379
+ "eval_loss": 0.5390623807907104,
380
+ "eval_runtime": 4.8096,
381
+ "eval_samples_per_second": 10.396,
382
+ "eval_steps_per_second": 2.703,
383
+ "step": 50
384
  }
385
  ],
386
  "logging_steps": 1,
 
395
  "should_evaluate": false,
396
  "should_log": false,
397
  "should_save": true,
398
+ "should_training_stop": true
399
  },
400
  "attributes": {}
401
  }
402
  },
403
+ "total_flos": 5.755268578358067e+17,
404
  "train_batch_size": 1,
405
  "trial_name": null,
406
  "trial_params": null