lesso02 commited on
Commit
5d905f0
·
verified ·
1 Parent(s): 8239c06

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 sha256:48787c5fef2c02f86ae6792eb44737f6a524195d73b40f7c34158eb7bcf512d0
3
  size 161533192
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d69da96e99b550c8bc4ec96d53e300287d27c1e2f3d22cedad6d6afaa46cfdc
3
  size 161533192
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1076e16d3cca430cd7b928c92636c3173e191dbbc3cf490937726a49562b706c
3
  size 323290986
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49f2c04f51b8a81da1c77752bdb8d8a84e0190d484cbe6e483beaec85c248765
3
  size 323290986
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:65c54d36cddb436ce3a318bd94d1d6c930494124860d0a76fda5de6844070d4d
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e57eeebfb8e0c877305053bf725aec6321ea0e9911c28c239bcba2f5196f7235
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": 0.2336448598130841,
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": 7.626,
231
  "eval_steps_per_second": 1.017,
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": 1.992260275981517e+16,
253
  "train_batch_size": 8,
254
  "trial_name": null,
255
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.4672897196261682,
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": 7.626,
231
  "eval_steps_per_second": 1.017,
232
  "step": 25
233
+ },
234
+ {
235
+ "epoch": 0.24299065420560748,
236
+ "grad_norm": 0.5318223237991333,
237
+ "learning_rate": 6.545084971874738e-05,
238
+ "loss": 3.2,
239
+ "step": 26
240
+ },
241
+ {
242
+ "epoch": 0.2523364485981308,
243
+ "grad_norm": 0.5088294744491577,
244
+ "learning_rate": 6.167226819279528e-05,
245
+ "loss": 2.9652,
246
+ "step": 27
247
+ },
248
+ {
249
+ "epoch": 0.2616822429906542,
250
+ "grad_norm": 0.709073007106781,
251
+ "learning_rate": 5.782172325201155e-05,
252
+ "loss": 3.07,
253
+ "step": 28
254
+ },
255
+ {
256
+ "epoch": 0.27102803738317754,
257
+ "grad_norm": 0.6809924244880676,
258
+ "learning_rate": 5.392295478639225e-05,
259
+ "loss": 3.1059,
260
+ "step": 29
261
+ },
262
+ {
263
+ "epoch": 0.2803738317757009,
264
+ "grad_norm": 0.7320699691772461,
265
+ "learning_rate": 5e-05,
266
+ "loss": 3.4134,
267
+ "step": 30
268
+ },
269
+ {
270
+ "epoch": 0.2803738317757009,
271
+ "eval_loss": 3.0135130882263184,
272
+ "eval_runtime": 11.8129,
273
+ "eval_samples_per_second": 7.619,
274
+ "eval_steps_per_second": 1.016,
275
+ "step": 30
276
+ },
277
+ {
278
+ "epoch": 0.2897196261682243,
279
+ "grad_norm": 0.5812227129936218,
280
+ "learning_rate": 4.607704521360776e-05,
281
+ "loss": 3.084,
282
+ "step": 31
283
+ },
284
+ {
285
+ "epoch": 0.29906542056074764,
286
+ "grad_norm": 0.6772279143333435,
287
+ "learning_rate": 4.2178276747988446e-05,
288
+ "loss": 3.2903,
289
+ "step": 32
290
+ },
291
+ {
292
+ "epoch": 0.308411214953271,
293
+ "grad_norm": 0.5976366400718689,
294
+ "learning_rate": 3.832773180720475e-05,
295
+ "loss": 3.4381,
296
+ "step": 33
297
+ },
298
+ {
299
+ "epoch": 0.3177570093457944,
300
+ "grad_norm": 0.6841944456100464,
301
+ "learning_rate": 3.4549150281252636e-05,
302
+ "loss": 3.1514,
303
+ "step": 34
304
+ },
305
+ {
306
+ "epoch": 0.32710280373831774,
307
+ "grad_norm": 0.5981345176696777,
308
+ "learning_rate": 3.086582838174551e-05,
309
+ "loss": 3.1474,
310
+ "step": 35
311
+ },
312
+ {
313
+ "epoch": 0.32710280373831774,
314
+ "eval_loss": 2.9548096656799316,
315
+ "eval_runtime": 11.8546,
316
+ "eval_samples_per_second": 7.592,
317
+ "eval_steps_per_second": 1.012,
318
+ "step": 35
319
+ },
320
+ {
321
+ "epoch": 0.3364485981308411,
322
+ "grad_norm": 0.582588791847229,
323
+ "learning_rate": 2.7300475013022663e-05,
324
+ "loss": 3.0558,
325
+ "step": 36
326
+ },
327
+ {
328
+ "epoch": 0.34579439252336447,
329
+ "grad_norm": 0.5256133079528809,
330
+ "learning_rate": 2.3875071764202563e-05,
331
+ "loss": 2.6748,
332
+ "step": 37
333
+ },
334
+ {
335
+ "epoch": 0.35514018691588783,
336
+ "grad_norm": 0.5302594900131226,
337
+ "learning_rate": 2.061073738537635e-05,
338
+ "loss": 2.8574,
339
+ "step": 38
340
+ },
341
+ {
342
+ "epoch": 0.3644859813084112,
343
+ "grad_norm": 0.4886729419231415,
344
+ "learning_rate": 1.7527597583490822e-05,
345
+ "loss": 3.3767,
346
+ "step": 39
347
+ },
348
+ {
349
+ "epoch": 0.37383177570093457,
350
+ "grad_norm": 0.5390812754631042,
351
+ "learning_rate": 1.4644660940672627e-05,
352
+ "loss": 2.9575,
353
+ "step": 40
354
+ },
355
+ {
356
+ "epoch": 0.37383177570093457,
357
+ "eval_loss": 2.925156593322754,
358
+ "eval_runtime": 11.8574,
359
+ "eval_samples_per_second": 7.59,
360
+ "eval_steps_per_second": 1.012,
361
+ "step": 40
362
+ },
363
+ {
364
+ "epoch": 0.38317757009345793,
365
+ "grad_norm": 0.6799167394638062,
366
+ "learning_rate": 1.1979701719998453e-05,
367
+ "loss": 3.0448,
368
+ "step": 41
369
+ },
370
+ {
371
+ "epoch": 0.3925233644859813,
372
+ "grad_norm": 0.5341367125511169,
373
+ "learning_rate": 9.549150281252633e-06,
374
+ "loss": 2.5492,
375
+ "step": 42
376
+ },
377
+ {
378
+ "epoch": 0.40186915887850466,
379
+ "grad_norm": 0.6501630544662476,
380
+ "learning_rate": 7.367991782295391e-06,
381
+ "loss": 3.0428,
382
+ "step": 43
383
+ },
384
+ {
385
+ "epoch": 0.411214953271028,
386
+ "grad_norm": 0.9022209644317627,
387
+ "learning_rate": 5.449673790581611e-06,
388
+ "loss": 2.5926,
389
+ "step": 44
390
+ },
391
+ {
392
+ "epoch": 0.4205607476635514,
393
+ "grad_norm": 0.6173515319824219,
394
+ "learning_rate": 3.8060233744356633e-06,
395
+ "loss": 3.3802,
396
+ "step": 45
397
+ },
398
+ {
399
+ "epoch": 0.4205607476635514,
400
+ "eval_loss": 2.912790536880493,
401
+ "eval_runtime": 11.8555,
402
+ "eval_samples_per_second": 7.591,
403
+ "eval_steps_per_second": 1.012,
404
+ "step": 45
405
+ },
406
+ {
407
+ "epoch": 0.42990654205607476,
408
+ "grad_norm": 0.6342452764511108,
409
+ "learning_rate": 2.4471741852423237e-06,
410
+ "loss": 3.3427,
411
+ "step": 46
412
+ },
413
+ {
414
+ "epoch": 0.4392523364485981,
415
+ "grad_norm": 0.5459204912185669,
416
+ "learning_rate": 1.3815039801161721e-06,
417
+ "loss": 2.9628,
418
+ "step": 47
419
+ },
420
+ {
421
+ "epoch": 0.4485981308411215,
422
+ "grad_norm": 0.627280056476593,
423
+ "learning_rate": 6.15582970243117e-07,
424
+ "loss": 2.8912,
425
+ "step": 48
426
+ },
427
+ {
428
+ "epoch": 0.45794392523364486,
429
+ "grad_norm": 0.7783709764480591,
430
+ "learning_rate": 1.5413331334360182e-07,
431
+ "loss": 3.4217,
432
+ "step": 49
433
+ },
434
+ {
435
+ "epoch": 0.4672897196261682,
436
+ "grad_norm": 0.9556735754013062,
437
+ "learning_rate": 0.0,
438
+ "loss": 3.1384,
439
+ "step": 50
440
+ },
441
+ {
442
+ "epoch": 0.4672897196261682,
443
+ "eval_loss": 2.9103848934173584,
444
+ "eval_runtime": 11.854,
445
+ "eval_samples_per_second": 7.592,
446
+ "eval_steps_per_second": 1.012,
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": 4.124328290628403e+16,
468
  "train_batch_size": 8,
469
  "trial_name": null,
470
  "trial_params": null