dada22231 commited on
Commit
89ccf7a
·
verified ·
1 Parent(s): 5340dd2

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 sha256:5519d5ab7b8b90107a44fe64f3dd0a3968f94883e86a5e4285d00ed6790e872c
3
  size 203456160
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc281c005895cbcd7babef5f8d6e2b5ba7e8c32ff03b91e13ed702d42c124ce1
3
  size 203456160
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e9daa85e618af6fd8c2ccefd9219937ed81c73389f4759e552a0ba37b962f768
3
  size 407121750
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57eae5b7a9203592b39d6c8e64a2236ad564a69eafa702e0698bd72b994d8e73
3
  size 407121750
last-checkpoint/rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a74bb1b107aeda8296e2f3e8df27ebeb75245312f5e26e41475b4d264eb6c74d
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c5eece366a06ab00b0ad7cc4861a8ff8e015794402f77a8230e3d04c57dc436
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 sha256:61cd012f6369b226c5e43e8cede78129aea1ff03e7ea88d33d0183ba5f259624
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0aded9315b66cedadce3c319b51ea654805c99c057f4bbc74177cf8e96656ea6
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 sha256:35af4c17be4b63d8150e066a684cc566a11f187d0e54c0d50ea38d7cfa4339a1
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3961af8cc04be0bd24e401e74ef15fe021233c531c7d0ac062363a6a06a440a6
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 sha256:00883995982b716cc58d0c57e293a44f3d1b0cd5cbb12c86880a89866097227f
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:392155fab8607289ce13e7e5ddc2dc13bdb8660456c8f289385c7b495348c89d
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": 0.015339481908998524,
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": 11.251,
199
  "eval_steps_per_second": 2.925,
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": 1.327074698592256e+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": 0.03067896381799705,
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": 11.251,
199
  "eval_steps_per_second": 2.925,
200
  "step": 25
201
+ },
202
+ {
203
+ "epoch": 0.015953061185358466,
204
+ "grad_norm": 0.26287588477134705,
205
+ "learning_rate": 5.500000000000001e-05,
206
+ "loss": 0.0904,
207
+ "step": 26
208
+ },
209
+ {
210
+ "epoch": 0.016566640461718407,
211
+ "grad_norm": 0.2254049926996231,
212
+ "learning_rate": 5.205685918464356e-05,
213
+ "loss": 0.0666,
214
+ "step": 27
215
+ },
216
+ {
217
+ "epoch": 0.017180219738078345,
218
+ "grad_norm": 0.18865813314914703,
219
+ "learning_rate": 4.912632135009769e-05,
220
+ "loss": 0.0741,
221
+ "step": 28
222
+ },
223
+ {
224
+ "epoch": 0.017793799014438286,
225
+ "grad_norm": 0.20661719143390656,
226
+ "learning_rate": 4.6220935509274235e-05,
227
+ "loss": 0.0737,
228
+ "step": 29
229
+ },
230
+ {
231
+ "epoch": 0.018407378290798228,
232
+ "grad_norm": 0.20987176895141602,
233
+ "learning_rate": 4.3353142970386564e-05,
234
+ "loss": 0.0836,
235
+ "step": 30
236
+ },
237
+ {
238
+ "epoch": 0.01902095756715817,
239
+ "grad_norm": 0.1971331536769867,
240
+ "learning_rate": 4.053522406135775e-05,
241
+ "loss": 0.066,
242
+ "step": 31
243
+ },
244
+ {
245
+ "epoch": 0.01963453684351811,
246
+ "grad_norm": 0.19305665791034698,
247
+ "learning_rate": 3.777924554357096e-05,
248
+ "loss": 0.0698,
249
+ "step": 32
250
+ },
251
+ {
252
+ "epoch": 0.020248116119878052,
253
+ "grad_norm": 0.2463589310646057,
254
+ "learning_rate": 3.509700894014496e-05,
255
+ "loss": 0.0877,
256
+ "step": 33
257
+ },
258
+ {
259
+ "epoch": 0.020861695396237993,
260
+ "grad_norm": 0.22322812676429749,
261
+ "learning_rate": 3.250000000000001e-05,
262
+ "loss": 0.0831,
263
+ "step": 34
264
+ },
265
+ {
266
+ "epoch": 0.021475274672597935,
267
+ "grad_norm": 0.2534312605857849,
268
+ "learning_rate": 2.9999339514117912e-05,
269
+ "loss": 0.0936,
270
+ "step": 35
271
+ },
272
+ {
273
+ "epoch": 0.022088853948957873,
274
+ "grad_norm": 0.26816612482070923,
275
+ "learning_rate": 2.760573569460757e-05,
276
+ "loss": 0.0723,
277
+ "step": 36
278
+ },
279
+ {
280
+ "epoch": 0.022702433225317814,
281
+ "grad_norm": 0.31204140186309814,
282
+ "learning_rate": 2.53294383204969e-05,
283
+ "loss": 0.094,
284
+ "step": 37
285
+ },
286
+ {
287
+ "epoch": 0.023316012501677755,
288
+ "grad_norm": 0.207439124584198,
289
+ "learning_rate": 2.3180194846605367e-05,
290
+ "loss": 0.0737,
291
+ "step": 38
292
+ },
293
+ {
294
+ "epoch": 0.023929591778037697,
295
+ "grad_norm": 0.14335572719573975,
296
+ "learning_rate": 2.1167208663446025e-05,
297
+ "loss": 0.0493,
298
+ "step": 39
299
+ },
300
+ {
301
+ "epoch": 0.024543171054397638,
302
+ "grad_norm": 0.17882516980171204,
303
+ "learning_rate": 1.9299099686894423e-05,
304
+ "loss": 0.0657,
305
+ "step": 40
306
+ },
307
+ {
308
+ "epoch": 0.02515675033075758,
309
+ "grad_norm": 0.17820951342582703,
310
+ "learning_rate": 1.758386744638546e-05,
311
+ "loss": 0.062,
312
+ "step": 41
313
+ },
314
+ {
315
+ "epoch": 0.02577032960711752,
316
+ "grad_norm": 0.1789134442806244,
317
+ "learning_rate": 1.602885682970026e-05,
318
+ "loss": 0.0618,
319
+ "step": 42
320
+ },
321
+ {
322
+ "epoch": 0.02638390888347746,
323
+ "grad_norm": 0.16019491851329803,
324
+ "learning_rate": 1.464072663102903e-05,
325
+ "loss": 0.0569,
326
+ "step": 43
327
+ },
328
+ {
329
+ "epoch": 0.0269974881598374,
330
+ "grad_norm": 0.17127665877342224,
331
+ "learning_rate": 1.3425421036992098e-05,
332
+ "loss": 0.0615,
333
+ "step": 44
334
+ },
335
+ {
336
+ "epoch": 0.02761106743619734,
337
+ "grad_norm": 0.17631715536117554,
338
+ "learning_rate": 1.2388144172720251e-05,
339
+ "loss": 0.0661,
340
+ "step": 45
341
+ },
342
+ {
343
+ "epoch": 0.028224646712557283,
344
+ "grad_norm": 0.21898619830608368,
345
+ "learning_rate": 1.1533337816991932e-05,
346
+ "loss": 0.0683,
347
+ "step": 46
348
+ },
349
+ {
350
+ "epoch": 0.028838225988917224,
351
+ "grad_norm": 0.2262589931488037,
352
+ "learning_rate": 1.0864662381854632e-05,
353
+ "loss": 0.0705,
354
+ "step": 47
355
+ },
356
+ {
357
+ "epoch": 0.029451805265277166,
358
+ "grad_norm": 0.22292573750019073,
359
+ "learning_rate": 1.0384981238178534e-05,
360
+ "loss": 0.0725,
361
+ "step": 48
362
+ },
363
+ {
364
+ "epoch": 0.030065384541637107,
365
+ "grad_norm": 0.29249176383018494,
366
+ "learning_rate": 1.0096348454262845e-05,
367
+ "loss": 0.0901,
368
+ "step": 49
369
+ },
370
+ {
371
+ "epoch": 0.03067896381799705,
372
+ "grad_norm": 0.3059021830558777,
373
+ "learning_rate": 1e-05,
374
+ "loss": 0.0922,
375
+ "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.03067896381799705,
379
+ "eval_loss": 0.06421475112438202,
380
+ "eval_runtime": 4.4458,
381
+ "eval_samples_per_second": 11.247,
382
+ "eval_steps_per_second": 2.924,
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": 2.654149397184512e+17,
404
  "train_batch_size": 1,
405
  "trial_name": null,
406
  "trial_params": null