Hugging Face's logo

dimasik87
/
88452488-9294-4057-b1b7-deed345fdbb1

PEFT
Safetensors
gemma
axolotl
Generated from Trainer
Model card Files
xet
 Community
dimasik87 commited on
Commit
fdfe2c9
·
verified ·
1 Parent(s): 8505c19

Training in progress, step 50, checkpoint

Browse files
Files changed (5) hide show
  1. last-checkpoint/adapter_model.safetensors +1 -1
  2. last-checkpoint/optimizer.pt +1 -1
  3. last-checkpoint/rng_state.pth +1 -1
  4. last-checkpoint/scheduler.pt +1 -1
  5. last-checkpoint/trainer_state.json +219 -4
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b6d9f04d5f99620a2a710868f48c7e938f260e6a8532f139ab14b2db31c2f246
3
  size 156926880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a3d8ac513bc555413baed62acee0e26ca3d0ed2b38bfb8389099cbc0a84bf09
3
  size 156926880
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2a870622036580c2544c0e7758ccb7d18f101b6c0d5fe13920d6198d75e360d1
3
  size 313998650
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f1db761ffce4a12e4aff1bf1601039f0b57c32fec239f761ef03908a9f25083
3
  size 313998650
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:961591796b059cb18d55a94a60e2cdf3c596a23fb10a29ed57fbfd8607208e38
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5fb2b7e5095e447137ccc7c7be9efd457870b25353eea6da0d58b673eacd92ad
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6676fe28230ae15b45fb334c871c6fdf1a7984a935952b9f8650896c37a8c106
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
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": 0.01063264221158958,
5
  "eval_steps": 5,
6
- "global_step": 25,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -230,6 +230,221 @@
230
  "eval_samples_per_second": 19.214,
231
  "eval_steps_per_second": 9.607,
232
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
233
  }
234
  ],
235
  "logging_steps": 1,
@@ -244,12 +459,12 @@
244
  "should_evaluate": false,
245
  "should_log": false,
246
  "should_save": true,
247
- "should_training_stop": false
248
  },
249
  "attributes": {}
250
  }
251
  },
252
- "total_flos": 4967074313011200.0,
253
  "train_batch_size": 2,
254
  "trial_name": null,
255
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.02126528442317916,
5
  "eval_steps": 5,
6
+ "global_step": 50,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
230
  "eval_samples_per_second": 19.214,
231
  "eval_steps_per_second": 9.607,
232
  "step": 25
233
+ },
234
+ {
235
+ "epoch": 0.011057947900053162,
236
+ "grad_norm": 1.9343523979187012,
237
+ "learning_rate": 6.545084971874738e-05,
238
+ "loss": 1.9707,
239
+ "step": 26
240
+ },
241
+ {
242
+ "epoch": 0.011483253588516746,
243
+ "grad_norm": 2.8466968536376953,
244
+ "learning_rate": 6.167226819279528e-05,
245
+ "loss": 2.2591,
246
+ "step": 27
247
+ },
248
+ {
249
+ "epoch": 0.01190855927698033,
250
+ "grad_norm": 2.180558443069458,
251
+ "learning_rate": 5.782172325201155e-05,
252
+ "loss": 2.004,
253
+ "step": 28
254
+ },
255
+ {
256
+ "epoch": 0.012333864965443912,
257
+ "grad_norm": 1.9480847120285034,
258
+ "learning_rate": 5.392295478639225e-05,
259
+ "loss": 1.8264,
260
+ "step": 29
261
+ },
262
+ {
263
+ "epoch": 0.012759170653907496,
264
+ "grad_norm": 2.1136586666107178,
265
+ "learning_rate": 5e-05,
266
+ "loss": 1.9864,
267
+ "step": 30
268
+ },
269
+ {
270
+ "epoch": 0.012759170653907496,
271
+ "eval_loss": 2.0316946506500244,
272
+ "eval_runtime": 51.4619,
273
+ "eval_samples_per_second": 19.238,
274
+ "eval_steps_per_second": 9.619,
275
+ "step": 30
276
+ },
277
+ {
278
+ "epoch": 0.01318447634237108,
279
+ "grad_norm": 2.396578788757324,
280
+ "learning_rate": 4.607704521360776e-05,
281
+ "loss": 1.7799,
282
+ "step": 31
283
+ },
284
+ {
285
+ "epoch": 0.013609782030834662,
286
+ "grad_norm": 2.040435552597046,
287
+ "learning_rate": 4.2178276747988446e-05,
288
+ "loss": 1.8772,
289
+ "step": 32
290
+ },
291
+ {
292
+ "epoch": 0.014035087719298246,
293
+ "grad_norm": 2.135164976119995,
294
+ "learning_rate": 3.832773180720475e-05,
295
+ "loss": 2.0432,
296
+ "step": 33
297
+ },
298
+ {
299
+ "epoch": 0.014460393407761828,
300
+ "grad_norm": 2.5923969745635986,
301
+ "learning_rate": 3.4549150281252636e-05,
302
+ "loss": 2.0384,
303
+ "step": 34
304
+ },
305
+ {
306
+ "epoch": 0.014885699096225412,
307
+ "grad_norm": 2.1935601234436035,
308
+ "learning_rate": 3.086582838174551e-05,
309
+ "loss": 1.7639,
310
+ "step": 35
311
+ },
312
+ {
313
+ "epoch": 0.014885699096225412,
314
+ "eval_loss": 1.9980850219726562,
315
+ "eval_runtime": 51.4531,
316
+ "eval_samples_per_second": 19.241,
317
+ "eval_steps_per_second": 9.62,
318
+ "step": 35
319
+ },
320
+ {
321
+ "epoch": 0.015311004784688996,
322
+ "grad_norm": 2.1146159172058105,
323
+ "learning_rate": 2.7300475013022663e-05,
324
+ "loss": 2.2388,
325
+ "step": 36
326
+ },
327
+ {
328
+ "epoch": 0.01573631047315258,
329
+ "grad_norm": 2.1292548179626465,
330
+ "learning_rate": 2.3875071764202563e-05,
331
+ "loss": 2.2011,
332
+ "step": 37
333
+ },
334
+ {
335
+ "epoch": 0.01616161616161616,
336
+ "grad_norm": 2.6756248474121094,
337
+ "learning_rate": 2.061073738537635e-05,
338
+ "loss": 2.3853,
339
+ "step": 38
340
+ },
341
+ {
342
+ "epoch": 0.016586921850079744,
343
+ "grad_norm": 2.1600706577301025,
344
+ "learning_rate": 1.7527597583490822e-05,
345
+ "loss": 2.0725,
346
+ "step": 39
347
+ },
348
+ {
349
+ "epoch": 0.01701222753854333,
350
+ "grad_norm": 1.9623900651931763,
351
+ "learning_rate": 1.4644660940672627e-05,
352
+ "loss": 1.8797,
353
+ "step": 40
354
+ },
355
+ {
356
+ "epoch": 0.01701222753854333,
357
+ "eval_loss": 1.9786725044250488,
358
+ "eval_runtime": 51.2153,
359
+ "eval_samples_per_second": 19.33,
360
+ "eval_steps_per_second": 9.665,
361
+ "step": 40
362
+ },
363
+ {
364
+ "epoch": 0.01743753322700691,
365
+ "grad_norm": 1.8925254344940186,
366
+ "learning_rate": 1.1979701719998453e-05,
367
+ "loss": 1.739,
368
+ "step": 41
369
+ },
370
+ {
371
+ "epoch": 0.017862838915470493,
372
+ "grad_norm": 2.1422901153564453,
373
+ "learning_rate": 9.549150281252633e-06,
374
+ "loss": 2.1882,
375
+ "step": 42
376
+ },
377
+ {
378
+ "epoch": 0.01828814460393408,
379
+ "grad_norm": 2.3237416744232178,
380
+ "learning_rate": 7.367991782295391e-06,
381
+ "loss": 2.077,
382
+ "step": 43
383
+ },
384
+ {
385
+ "epoch": 0.01871345029239766,
386
+ "grad_norm": 2.0759365558624268,
387
+ "learning_rate": 5.449673790581611e-06,
388
+ "loss": 1.6761,
389
+ "step": 44
390
+ },
391
+ {
392
+ "epoch": 0.019138755980861243,
393
+ "grad_norm": 2.3377480506896973,
394
+ "learning_rate": 3.8060233744356633e-06,
395
+ "loss": 2.0266,
396
+ "step": 45
397
+ },
398
+ {
399
+ "epoch": 0.019138755980861243,
400
+ "eval_loss": 1.9705880880355835,
401
+ "eval_runtime": 51.3602,
402
+ "eval_samples_per_second": 19.276,
403
+ "eval_steps_per_second": 9.638,
404
+ "step": 45
405
+ },
406
+ {
407
+ "epoch": 0.01956406166932483,
408
+ "grad_norm": 2.2036025524139404,
409
+ "learning_rate": 2.4471741852423237e-06,
410
+ "loss": 2.1409,
411
+ "step": 46
412
+ },
413
+ {
414
+ "epoch": 0.01998936735778841,
415
+ "grad_norm": 1.7146847248077393,
416
+ "learning_rate": 1.3815039801161721e-06,
417
+ "loss": 1.3589,
418
+ "step": 47
419
+ },
420
+ {
421
+ "epoch": 0.020414673046251993,
422
+ "grad_norm": 2.24995756149292,
423
+ "learning_rate": 6.15582970243117e-07,
424
+ "loss": 2.0739,
425
+ "step": 48
426
+ },
427
+ {
428
+ "epoch": 0.020839978734715575,
429
+ "grad_norm": 2.458615779876709,
430
+ "learning_rate": 1.5413331334360182e-07,
431
+ "loss": 2.086,
432
+ "step": 49
433
+ },
434
+ {
435
+ "epoch": 0.02126528442317916,
436
+ "grad_norm": 2.0223281383514404,
437
+ "learning_rate": 0.0,
438
+ "loss": 2.0527,
439
+ "step": 50
440
+ },
441
+ {
442
+ "epoch": 0.02126528442317916,
443
+ "eval_loss": 1.969186782836914,
444
+ "eval_runtime": 51.3823,
445
+ "eval_samples_per_second": 19.267,
446
+ "eval_steps_per_second": 9.634,
447
+ "step": 50
448
  }
449
  ],
450
  "logging_steps": 1,
 
459
  "should_evaluate": false,
460
  "should_log": false,
461
  "should_save": true,
462
+ "should_training_stop": true
463
  },
464
  "attributes": {}
465
  }
466
  },
467
+ "total_flos": 9934148626022400.0,
468
  "train_batch_size": 2,
469
  "trial_name": null,
470
  "trial_params": null