neginr commited on
Commit
7326827
·
verified ·
1 Parent(s): 0a9e3b6

Training in progress, epoch 4

Browse files
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b6b3959cdecf6ef60c2b484206b5f3eab3add555134ac9cdec8ee93a95a778b0
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c94668da4336ca5110c9382d8cb491afaf17ff1715697af8ecd30efaab83d9a2
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6dbf87f404298501311732d1bbd04ac5114ac75dd2b23b06ff2ae6abc90fe7d3
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0e08a4065302e99f159f397a53f2821b1b31bc8db33adba71b87aff752cdf0d
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:81950c13053d29f0c3099f034d23d0da53df58ca5154e3915319cabf26661332
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e947ee6c7188c6d6278864fe773af25dd7e615c87643b7b59c7950858d6d416a
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7cb6a7886b5eb86cc0dbf900e68f539b297f739c9687953cfea61e522434dcc5
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:878dbbfb702c9ad11caa36352655cbc1787c4117de3a5b8e700e0ae02fabb924
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -340,3 +340,74 @@
340
  {"current_steps": 318, "total_steps": 390, "loss": 0.3434, "lr": 4.011144731929981e-06, "epoch": 4.073482428115016, "percentage": 81.54, "elapsed_time": "0:34:09", "remaining_time": "0:07:44"}
341
  {"current_steps": 319, "total_steps": 390, "loss": 0.32, "lr": 3.904248846874894e-06, "epoch": 4.086261980830671, "percentage": 81.79, "elapsed_time": "0:34:30", "remaining_time": "0:07:40"}
342
  {"current_steps": 320, "total_steps": 390, "loss": 0.3235, "lr": 3.7986423802166705e-06, "epoch": 4.099041533546326, "percentage": 82.05, "elapsed_time": "0:34:53", "remaining_time": "0:07:37"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
340
  {"current_steps": 318, "total_steps": 390, "loss": 0.3434, "lr": 4.011144731929981e-06, "epoch": 4.073482428115016, "percentage": 81.54, "elapsed_time": "0:34:09", "remaining_time": "0:07:44"}
341
  {"current_steps": 319, "total_steps": 390, "loss": 0.32, "lr": 3.904248846874894e-06, "epoch": 4.086261980830671, "percentage": 81.79, "elapsed_time": "0:34:30", "remaining_time": "0:07:40"}
342
  {"current_steps": 320, "total_steps": 390, "loss": 0.3235, "lr": 3.7986423802166705e-06, "epoch": 4.099041533546326, "percentage": 82.05, "elapsed_time": "0:34:53", "remaining_time": "0:07:37"}
343
+ {"current_steps": 321, "total_steps": 390, "loss": 0.3452, "lr": 3.694333792009115e-06, "epoch": 4.111821086261981, "percentage": 82.31, "elapsed_time": "0:35:13", "remaining_time": "0:07:34"}
344
+ {"current_steps": 322, "total_steps": 390, "loss": 0.3473, "lr": 3.5913314383339937e-06, "epoch": 4.124600638977636, "percentage": 82.56, "elapsed_time": "0:35:36", "remaining_time": "0:07:31"}
345
+ {"current_steps": 323, "total_steps": 390, "loss": 0.319, "lr": 3.4896435706316e-06, "epoch": 4.137380191693291, "percentage": 82.82, "elapsed_time": "0:35:59", "remaining_time": "0:07:27"}
346
+ {"current_steps": 324, "total_steps": 390, "loss": 0.3473, "lr": 3.3892783350397675e-06, "epoch": 4.1501597444089455, "percentage": 83.08, "elapsed_time": "0:36:21", "remaining_time": "0:07:24"}
347
+ {"current_steps": 325, "total_steps": 390, "loss": 0.3522, "lr": 3.290243771741275e-06, "epoch": 4.1629392971246, "percentage": 83.33, "elapsed_time": "0:36:45", "remaining_time": "0:07:21"}
348
+ {"current_steps": 326, "total_steps": 390, "loss": 0.3364, "lr": 3.1925478143197418e-06, "epoch": 4.175718849840256, "percentage": 83.59, "elapsed_time": "0:37:08", "remaining_time": "0:07:17"}
349
+ {"current_steps": 327, "total_steps": 390, "loss": 0.3383, "lr": 3.0961982891241083e-06, "epoch": 4.18849840255591, "percentage": 83.85, "elapsed_time": "0:37:31", "remaining_time": "0:07:13"}
350
+ {"current_steps": 328, "total_steps": 390, "loss": 0.3387, "lr": 3.001202914641628e-06, "epoch": 4.201277955271565, "percentage": 84.1, "elapsed_time": "0:37:55", "remaining_time": "0:07:10"}
351
+ {"current_steps": 329, "total_steps": 390, "loss": 0.3359, "lr": 2.907569300879596e-06, "epoch": 4.214057507987221, "percentage": 84.36, "elapsed_time": "0:38:18", "remaining_time": "0:07:06"}
352
+ {"current_steps": 330, "total_steps": 390, "loss": 0.3116, "lr": 2.815304948755664e-06, "epoch": 4.226837060702875, "percentage": 84.62, "elapsed_time": "0:38:39", "remaining_time": "0:07:01"}
353
+ {"current_steps": 331, "total_steps": 390, "loss": 0.3369, "lr": 2.7244172494969978e-06, "epoch": 4.23961661341853, "percentage": 84.87, "elapsed_time": "0:39:03", "remaining_time": "0:06:57"}
354
+ {"current_steps": 332, "total_steps": 390, "loss": 0.3716, "lr": 2.6349134840481294e-06, "epoch": 4.252396166134186, "percentage": 85.13, "elapsed_time": "0:39:26", "remaining_time": "0:06:53"}
355
+ {"current_steps": 333, "total_steps": 390, "loss": 0.3573, "lr": 2.546800822487714e-06, "epoch": 4.26517571884984, "percentage": 85.38, "elapsed_time": "0:39:50", "remaining_time": "0:06:49"}
356
+ {"current_steps": 334, "total_steps": 390, "loss": 0.3409, "lr": 2.4600863234541338e-06, "epoch": 4.277955271565495, "percentage": 85.64, "elapsed_time": "0:40:13", "remaining_time": "0:06:44"}
357
+ {"current_steps": 335, "total_steps": 390, "loss": 0.3146, "lr": 2.374776933580025e-06, "epoch": 4.2907348242811505, "percentage": 85.9, "elapsed_time": "0:40:35", "remaining_time": "0:06:39"}
358
+ {"current_steps": 336, "total_steps": 390, "loss": 0.3442, "lr": 2.2908794869358044e-06, "epoch": 4.303514376996805, "percentage": 86.15, "elapsed_time": "0:40:59", "remaining_time": "0:06:35"}
359
+ {"current_steps": 337, "total_steps": 390, "loss": 0.3352, "lr": 2.2084007044821764e-06, "epoch": 4.31629392971246, "percentage": 86.41, "elapsed_time": "0:41:20", "remaining_time": "0:06:30"}
360
+ {"current_steps": 338, "total_steps": 390, "loss": 0.3388, "lr": 2.127347193531757e-06, "epoch": 4.329073482428115, "percentage": 86.67, "elapsed_time": "0:41:42", "remaining_time": "0:06:24"}
361
+ {"current_steps": 339, "total_steps": 390, "loss": 0.3379, "lr": 2.0477254472197237e-06, "epoch": 4.34185303514377, "percentage": 86.92, "elapsed_time": "0:42:05", "remaining_time": "0:06:19"}
362
+ {"current_steps": 340, "total_steps": 390, "loss": 0.3239, "lr": 1.96954184398368e-06, "epoch": 4.354632587859425, "percentage": 87.18, "elapsed_time": "0:42:27", "remaining_time": "0:06:14"}
363
+ {"current_steps": 341, "total_steps": 390, "loss": 0.3671, "lr": 1.8928026470526917e-06, "epoch": 4.36741214057508, "percentage": 87.44, "elapsed_time": "0:42:50", "remaining_time": "0:06:09"}
364
+ {"current_steps": 342, "total_steps": 390, "loss": 0.3573, "lr": 1.817514003945524e-06, "epoch": 4.380191693290735, "percentage": 87.69, "elapsed_time": "0:43:13", "remaining_time": "0:06:03"}
365
+ {"current_steps": 343, "total_steps": 390, "loss": 0.324, "lr": 1.743681945978184e-06, "epoch": 4.39297124600639, "percentage": 87.95, "elapsed_time": "0:43:37", "remaining_time": "0:05:58"}
366
+ {"current_steps": 344, "total_steps": 390, "loss": 0.3235, "lr": 1.6713123877807413e-06, "epoch": 4.405750798722044, "percentage": 88.21, "elapsed_time": "0:43:59", "remaining_time": "0:05:52"}
367
+ {"current_steps": 345, "total_steps": 390, "loss": 0.324, "lr": 1.6004111268235156e-06, "epoch": 4.4185303514377, "percentage": 88.46, "elapsed_time": "0:44:22", "remaining_time": "0:05:47"}
368
+ {"current_steps": 346, "total_steps": 390, "loss": 0.3324, "lr": 1.5309838429526714e-06, "epoch": 4.431309904153355, "percentage": 88.72, "elapsed_time": "0:44:45", "remaining_time": "0:05:41"}
369
+ {"current_steps": 347, "total_steps": 390, "loss": 0.3407, "lr": 1.4630360979351644e-06, "epoch": 4.444089456869009, "percentage": 88.97, "elapsed_time": "0:45:09", "remaining_time": "0:05:35"}
370
+ {"current_steps": 348, "total_steps": 390, "loss": 0.3324, "lr": 1.396573335013236e-06, "epoch": 4.456869009584665, "percentage": 89.23, "elapsed_time": "0:45:32", "remaining_time": "0:05:29"}
371
+ {"current_steps": 349, "total_steps": 390, "loss": 0.3538, "lr": 1.3316008784683265e-06, "epoch": 4.4696485623003195, "percentage": 89.49, "elapsed_time": "0:45:55", "remaining_time": "0:05:23"}
372
+ {"current_steps": 350, "total_steps": 390, "loss": 0.3309, "lr": 1.2681239331945695e-06, "epoch": 4.482428115015974, "percentage": 89.74, "elapsed_time": "0:46:18", "remaining_time": "0:05:17"}
373
+ {"current_steps": 351, "total_steps": 390, "loss": 0.3299, "lr": 1.2061475842818337e-06, "epoch": 4.49520766773163, "percentage": 90.0, "elapsed_time": "0:46:41", "remaining_time": "0:05:11"}
374
+ {"current_steps": 352, "total_steps": 390, "loss": 0.324, "lr": 1.1456767966083393e-06, "epoch": 4.507987220447284, "percentage": 90.26, "elapsed_time": "0:47:04", "remaining_time": "0:05:04"}
375
+ {"current_steps": 353, "total_steps": 390, "loss": 0.3676, "lr": 1.086716414442952e-06, "epoch": 4.520766773162939, "percentage": 90.51, "elapsed_time": "0:47:27", "remaining_time": "0:04:58"}
376
+ {"current_steps": 354, "total_steps": 390, "loss": 0.334, "lr": 1.0292711610570904e-06, "epoch": 4.533546325878595, "percentage": 90.77, "elapsed_time": "0:47:51", "remaining_time": "0:04:52"}
377
+ {"current_steps": 355, "total_steps": 390, "loss": 0.3481, "lr": 9.733456383463658e-07, "epoch": 4.546325878594249, "percentage": 91.03, "elapsed_time": "0:48:14", "remaining_time": "0:04:45"}
378
+ {"current_steps": 356, "total_steps": 390, "loss": 0.3256, "lr": 9.189443264619102e-07, "epoch": 4.559105431309904, "percentage": 91.28, "elapsed_time": "0:48:38", "remaining_time": "0:04:38"}
379
+ {"current_steps": 357, "total_steps": 390, "loss": 0.3173, "lr": 8.660715834514977e-07, "epoch": 4.571884984025559, "percentage": 91.54, "elapsed_time": "0:49:02", "remaining_time": "0:04:31"}
380
+ {"current_steps": 358, "total_steps": 390, "loss": 0.3446, "lr": 8.147316449103959e-07, "epoch": 4.584664536741214, "percentage": 91.79, "elapsed_time": "0:49:26", "remaining_time": "0:04:25"}
381
+ {"current_steps": 359, "total_steps": 390, "loss": 0.3364, "lr": 7.649286236420806e-07, "epoch": 4.597444089456869, "percentage": 92.05, "elapsed_time": "0:49:49", "remaining_time": "0:04:18"}
382
+ {"current_steps": 360, "total_steps": 390, "loss": 0.3367, "lr": 7.166665093287539e-07, "epoch": 4.6102236421725244, "percentage": 92.31, "elapsed_time": "0:50:10", "remaining_time": "0:04:10"}
383
+ {"current_steps": 361, "total_steps": 390, "loss": 0.3602, "lr": 6.69949168211721e-07, "epoch": 4.623003194888179, "percentage": 92.56, "elapsed_time": "0:50:34", "remaining_time": "0:04:03"}
384
+ {"current_steps": 362, "total_steps": 390, "loss": 0.357, "lr": 6.247803427816945e-07, "epoch": 4.635782747603834, "percentage": 92.82, "elapsed_time": "0:50:58", "remaining_time": "0:03:56"}
385
+ {"current_steps": 363, "total_steps": 390, "loss": 0.3407, "lr": 5.811636514789598e-07, "epoch": 4.6485623003194885, "percentage": 93.08, "elapsed_time": "0:51:21", "remaining_time": "0:03:49"}
386
+ {"current_steps": 364, "total_steps": 390, "loss": 0.3283, "lr": 5.391025884035239e-07, "epoch": 4.661341853035144, "percentage": 93.33, "elapsed_time": "0:51:45", "remaining_time": "0:03:41"}
387
+ {"current_steps": 365, "total_steps": 390, "loss": 0.3358, "lr": 4.986005230351954e-07, "epoch": 4.674121405750799, "percentage": 93.59, "elapsed_time": "0:52:08", "remaining_time": "0:03:34"}
388
+ {"current_steps": 366, "total_steps": 390, "loss": 0.3331, "lr": 4.5966069996365993e-07, "epoch": 4.686900958466453, "percentage": 93.85, "elapsed_time": "0:52:30", "remaining_time": "0:03:26"}
389
+ {"current_steps": 367, "total_steps": 390, "loss": 0.3297, "lr": 4.22286238628562e-07, "epoch": 4.699680511182109, "percentage": 94.1, "elapsed_time": "0:52:53", "remaining_time": "0:03:18"}
390
+ {"current_steps": 368, "total_steps": 390, "loss": 0.3407, "lr": 3.8648013306960664e-07, "epoch": 4.712460063897764, "percentage": 94.36, "elapsed_time": "0:53:16", "remaining_time": "0:03:11"}
391
+ {"current_steps": 369, "total_steps": 390, "loss": 0.3278, "lr": 3.522452516867048e-07, "epoch": 4.725239616613418, "percentage": 94.62, "elapsed_time": "0:53:40", "remaining_time": "0:03:03"}
392
+ {"current_steps": 370, "total_steps": 390, "loss": 0.3136, "lr": 3.1958433701019697e-07, "epoch": 4.738019169329074, "percentage": 94.87, "elapsed_time": "0:54:03", "remaining_time": "0:02:55"}
393
+ {"current_steps": 371, "total_steps": 390, "loss": 0.342, "lr": 2.8850000548115155e-07, "epoch": 4.7507987220447285, "percentage": 95.13, "elapsed_time": "0:54:26", "remaining_time": "0:02:47"}
394
+ {"current_steps": 372, "total_steps": 390, "loss": 0.3507, "lr": 2.5899474724174313e-07, "epoch": 4.763578274760383, "percentage": 95.38, "elapsed_time": "0:54:50", "remaining_time": "0:02:39"}
395
+ {"current_steps": 373, "total_steps": 390, "loss": 0.3375, "lr": 2.3107092593579905e-07, "epoch": 4.776357827476039, "percentage": 95.64, "elapsed_time": "0:55:14", "remaining_time": "0:02:31"}
396
+ {"current_steps": 374, "total_steps": 390, "loss": 0.3524, "lr": 2.0473077851942858e-07, "epoch": 4.789137380191693, "percentage": 95.9, "elapsed_time": "0:55:37", "remaining_time": "0:02:22"}
397
+ {"current_steps": 375, "total_steps": 390, "loss": 0.3511, "lr": 1.799764150818306e-07, "epoch": 4.801916932907348, "percentage": 96.15, "elapsed_time": "0:55:59", "remaining_time": "0:02:14"}
398
+ {"current_steps": 376, "total_steps": 390, "loss": 0.3334, "lr": 1.5680981867625566e-07, "epoch": 4.814696485623003, "percentage": 96.41, "elapsed_time": "0:56:23", "remaining_time": "0:02:05"}
399
+ {"current_steps": 377, "total_steps": 390, "loss": 0.3578, "lr": 1.3523284516113955e-07, "epoch": 4.827476038338658, "percentage": 96.67, "elapsed_time": "0:56:45", "remaining_time": "0:01:57"}
400
+ {"current_steps": 378, "total_steps": 390, "loss": 0.3482, "lr": 1.1524722305144231e-07, "epoch": 4.840255591054313, "percentage": 96.92, "elapsed_time": "0:57:08", "remaining_time": "0:01:48"}
401
+ {"current_steps": 379, "total_steps": 390, "loss": 0.344, "lr": 9.685455338016347e-08, "epoch": 4.853035143769968, "percentage": 97.18, "elapsed_time": "0:57:31", "remaining_time": "0:01:40"}
402
+ {"current_steps": 380, "total_steps": 390, "loss": 0.3507, "lr": 8.005630957010014e-08, "epoch": 4.865814696485623, "percentage": 97.44, "elapsed_time": "0:57:55", "remaining_time": "0:01:31"}
403
+ {"current_steps": 381, "total_steps": 390, "loss": 0.3338, "lr": 6.485383731580142e-08, "epoch": 4.878594249201278, "percentage": 97.69, "elapsed_time": "0:58:19", "remaining_time": "0:01:22"}
404
+ {"current_steps": 382, "total_steps": 390, "loss": 0.3269, "lr": 5.1248354475768034e-08, "epoch": 4.891373801916933, "percentage": 97.95, "elapsed_time": "0:58:41", "remaining_time": "0:01:13"}
405
+ {"current_steps": 383, "total_steps": 390, "loss": 0.3343, "lr": 3.924095097489922e-08, "epoch": 4.904153354632588, "percentage": 98.21, "elapsed_time": "0:59:03", "remaining_time": "0:01:04"}
406
+ {"current_steps": 384, "total_steps": 390, "loss": 0.3393, "lr": 2.8832588717164766e-08, "epoch": 4.916932907348243, "percentage": 98.46, "elapsed_time": "0:59:26", "remaining_time": "0:00:55"}
407
+ {"current_steps": 385, "total_steps": 390, "loss": 0.3312, "lr": 2.0024101508555604e-08, "epoch": 4.9297124600638975, "percentage": 98.72, "elapsed_time": "0:59:48", "remaining_time": "0:00:46"}
408
+ {"current_steps": 386, "total_steps": 390, "loss": 0.3482, "lr": 1.281619499029274e-08, "epoch": 4.942492012779553, "percentage": 98.97, "elapsed_time": "1:00:12", "remaining_time": "0:00:37"}
409
+ {"current_steps": 387, "total_steps": 390, "loss": 0.3349, "lr": 7.209446582292501e-09, "epoch": 4.955271565495208, "percentage": 99.23, "elapsed_time": "1:00:34", "remaining_time": "0:00:28"}
410
+ {"current_steps": 388, "total_steps": 390, "loss": 0.3281, "lr": 3.2043054369057523e-09, "epoch": 4.968051118210862, "percentage": 99.49, "elapsed_time": "1:00:57", "remaining_time": "0:00:18"}
411
+ {"current_steps": 389, "total_steps": 390, "loss": 0.3238, "lr": 8.010924029533406e-10, "epoch": 4.980830670926517, "percentage": 99.74, "elapsed_time": "1:01:19", "remaining_time": "0:00:09"}
412
+ {"current_steps": 390, "total_steps": 390, "loss": 0.3224, "lr": 0.0, "epoch": 4.993610223642173, "percentage": 100.0, "elapsed_time": "1:01:41", "remaining_time": "0:00:00"}
413
+ {"current_steps": 390, "total_steps": 390, "epoch": 4.993610223642173, "percentage": 100.0, "elapsed_time": "1:04:44", "remaining_time": "0:00:00"}