ryanmarten commited on
Commit
abbdc6e
·
verified ·
1 Parent(s): 89dc811

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 sha256:56360302a6a784f7a617cf5daaaa53bb22cb5b2e2c5d15a048da38cedf42d8f7
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63f9da62a6afcc568bbc83934b5b93175a9e3696c571d0b54fcc1167f86e66c0
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:742895f89c0ad155ce7f9c5b80fd849be9b16bd3770de7df85bc35f94bb5a586
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df2def42ad29782f8d71c543382e17b098b056ea251a16f5a6f20e0d56d420ba
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:947b25005ce9913d0bc043ffa1b4be202519e9f698ae16347454c7e00d342ecc
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bcea8176a5ff76b82a9b43d4c83bdcd52071aafc4c77a686ba5fcf1cbbe5668a
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:824d63f1b8d2e9bbbf5cbe466be386c94b45adf34c0593d269a3a0f79e3fea52
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3fdea1a2a5d23595d8b97de40a7c5c3b7d92fc06ca0dcd22cd6c3a6fb7cc7ea0
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -312,3 +312,80 @@
312
  {"current_steps": 312, "total_steps": 390, "loss": 0.4236, "lr": 4.679111137620442e-06, "epoch": 3.9936, "percentage": 80.0, "elapsed_time": "14:08:37", "remaining_time": "3:32:09"}
313
  {"current_steps": 313, "total_steps": 390, "loss": 0.4076, "lr": 4.5646621393177e-06, "epoch": 4.0064, "percentage": 80.26, "elapsed_time": "14:12:21", "remaining_time": "3:29:41"}
314
  {"current_steps": 314, "total_steps": 390, "loss": 0.3949, "lr": 4.451449654204685e-06, "epoch": 4.0192, "percentage": 80.51, "elapsed_time": "14:15:03", "remaining_time": "3:26:57"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
312
  {"current_steps": 312, "total_steps": 390, "loss": 0.4236, "lr": 4.679111137620442e-06, "epoch": 3.9936, "percentage": 80.0, "elapsed_time": "14:08:37", "remaining_time": "3:32:09"}
313
  {"current_steps": 313, "total_steps": 390, "loss": 0.4076, "lr": 4.5646621393177e-06, "epoch": 4.0064, "percentage": 80.26, "elapsed_time": "14:12:21", "remaining_time": "3:29:41"}
314
  {"current_steps": 314, "total_steps": 390, "loss": 0.3949, "lr": 4.451449654204685e-06, "epoch": 4.0192, "percentage": 80.51, "elapsed_time": "14:15:03", "remaining_time": "3:26:57"}
315
+ {"current_steps": 315, "total_steps": 390, "loss": 0.3825, "lr": 4.339482751647557e-06, "epoch": 4.032, "percentage": 80.77, "elapsed_time": "14:17:53", "remaining_time": "3:24:15"}
316
+ {"current_steps": 316, "total_steps": 390, "loss": 0.3689, "lr": 4.228770401229824e-06, "epoch": 4.0448, "percentage": 81.03, "elapsed_time": "14:20:31", "remaining_time": "3:21:31"}
317
+ {"current_steps": 317, "total_steps": 390, "loss": 0.3833, "lr": 4.119321472033779e-06, "epoch": 4.0576, "percentage": 81.28, "elapsed_time": "14:23:24", "remaining_time": "3:18:49"}
318
+ {"current_steps": 318, "total_steps": 390, "loss": 0.3825, "lr": 4.011144731929981e-06, "epoch": 4.0704, "percentage": 81.54, "elapsed_time": "14:26:18", "remaining_time": "3:16:08"}
319
+ {"current_steps": 319, "total_steps": 390, "loss": 0.3877, "lr": 3.904248846874894e-06, "epoch": 4.0832, "percentage": 81.79, "elapsed_time": "14:29:11", "remaining_time": "3:13:27"}
320
+ {"current_steps": 320, "total_steps": 390, "loss": 0.3868, "lr": 3.7986423802166705e-06, "epoch": 4.096, "percentage": 82.05, "elapsed_time": "14:31:44", "remaining_time": "3:10:41"}
321
+ {"current_steps": 321, "total_steps": 390, "loss": 0.3809, "lr": 3.694333792009115e-06, "epoch": 4.1088, "percentage": 82.31, "elapsed_time": "14:34:27", "remaining_time": "3:07:57"}
322
+ {"current_steps": 322, "total_steps": 390, "loss": 0.3746, "lr": 3.5913314383339937e-06, "epoch": 4.1216, "percentage": 82.56, "elapsed_time": "14:37:12", "remaining_time": "3:05:14"}
323
+ {"current_steps": 323, "total_steps": 390, "loss": 0.362, "lr": 3.4896435706316e-06, "epoch": 4.1344, "percentage": 82.82, "elapsed_time": "14:39:48", "remaining_time": "3:02:29"}
324
+ {"current_steps": 324, "total_steps": 390, "loss": 0.3768, "lr": 3.3892783350397675e-06, "epoch": 4.1472, "percentage": 83.08, "elapsed_time": "14:42:29", "remaining_time": "2:59:46"}
325
+ {"current_steps": 325, "total_steps": 390, "loss": 0.3666, "lr": 3.290243771741275e-06, "epoch": 4.16, "percentage": 83.33, "elapsed_time": "14:45:11", "remaining_time": "2:57:02"}
326
+ {"current_steps": 326, "total_steps": 390, "loss": 0.3709, "lr": 3.1925478143197418e-06, "epoch": 4.1728, "percentage": 83.59, "elapsed_time": "14:47:58", "remaining_time": "2:54:19"}
327
+ {"current_steps": 327, "total_steps": 390, "loss": 0.3818, "lr": 3.0961982891241083e-06, "epoch": 4.1856, "percentage": 83.85, "elapsed_time": "14:50:57", "remaining_time": "2:51:39"}
328
+ {"current_steps": 328, "total_steps": 390, "loss": 0.3642, "lr": 3.001202914641628e-06, "epoch": 4.1984, "percentage": 84.1, "elapsed_time": "14:53:39", "remaining_time": "2:48:55"}
329
+ {"current_steps": 329, "total_steps": 390, "loss": 0.3781, "lr": 2.907569300879596e-06, "epoch": 4.2112, "percentage": 84.36, "elapsed_time": "14:56:31", "remaining_time": "2:46:13"}
330
+ {"current_steps": 330, "total_steps": 390, "loss": 0.3767, "lr": 2.815304948755664e-06, "epoch": 4.224, "percentage": 84.62, "elapsed_time": "14:59:03", "remaining_time": "2:43:27"}
331
+ {"current_steps": 331, "total_steps": 390, "loss": 0.3879, "lr": 2.7244172494969978e-06, "epoch": 4.2368, "percentage": 84.87, "elapsed_time": "15:01:55", "remaining_time": "2:40:46"}
332
+ {"current_steps": 332, "total_steps": 390, "loss": 0.3851, "lr": 2.6349134840481294e-06, "epoch": 4.2496, "percentage": 85.13, "elapsed_time": "15:04:39", "remaining_time": "2:38:02"}
333
+ {"current_steps": 333, "total_steps": 390, "loss": 0.3787, "lr": 2.546800822487714e-06, "epoch": 4.2624, "percentage": 85.38, "elapsed_time": "15:07:10", "remaining_time": "2:35:16"}
334
+ {"current_steps": 334, "total_steps": 390, "loss": 0.3863, "lr": 2.4600863234541338e-06, "epoch": 4.2752, "percentage": 85.64, "elapsed_time": "15:09:49", "remaining_time": "2:32:32"}
335
+ {"current_steps": 335, "total_steps": 390, "loss": 0.3803, "lr": 2.374776933580025e-06, "epoch": 4.288, "percentage": 85.9, "elapsed_time": "15:12:32", "remaining_time": "2:29:49"}
336
+ {"current_steps": 336, "total_steps": 390, "loss": 0.3633, "lr": 2.2908794869358044e-06, "epoch": 4.3008, "percentage": 86.15, "elapsed_time": "15:15:22", "remaining_time": "2:27:06"}
337
+ {"current_steps": 337, "total_steps": 390, "loss": 0.3984, "lr": 2.2084007044821764e-06, "epoch": 4.3136, "percentage": 86.41, "elapsed_time": "15:18:11", "remaining_time": "2:24:24"}
338
+ {"current_steps": 338, "total_steps": 390, "loss": 0.3871, "lr": 2.127347193531757e-06, "epoch": 4.3264, "percentage": 86.67, "elapsed_time": "15:20:43", "remaining_time": "2:21:39"}
339
+ {"current_steps": 339, "total_steps": 390, "loss": 0.3777, "lr": 2.0477254472197237e-06, "epoch": 4.3392, "percentage": 86.92, "elapsed_time": "15:23:16", "remaining_time": "2:18:54"}
340
+ {"current_steps": 340, "total_steps": 390, "loss": 0.3863, "lr": 1.96954184398368e-06, "epoch": 4.352, "percentage": 87.18, "elapsed_time": "15:25:50", "remaining_time": "2:16:09"}
341
+ {"current_steps": 341, "total_steps": 390, "loss": 0.3711, "lr": 1.8928026470526917e-06, "epoch": 4.3648, "percentage": 87.44, "elapsed_time": "15:28:21", "remaining_time": "2:13:24"}
342
+ {"current_steps": 342, "total_steps": 390, "loss": 0.3727, "lr": 1.817514003945524e-06, "epoch": 4.3776, "percentage": 87.69, "elapsed_time": "15:30:59", "remaining_time": "2:10:39"}
343
+ {"current_steps": 343, "total_steps": 390, "loss": 0.3745, "lr": 1.743681945978184e-06, "epoch": 4.3904, "percentage": 87.95, "elapsed_time": "15:33:41", "remaining_time": "2:07:56"}
344
+ {"current_steps": 344, "total_steps": 390, "loss": 0.3611, "lr": 1.6713123877807413e-06, "epoch": 4.4032, "percentage": 88.21, "elapsed_time": "15:36:19", "remaining_time": "2:05:12"}
345
+ {"current_steps": 345, "total_steps": 390, "loss": 0.3681, "lr": 1.6004111268235156e-06, "epoch": 4.416, "percentage": 88.46, "elapsed_time": "15:39:13", "remaining_time": "2:02:30"}
346
+ {"current_steps": 346, "total_steps": 390, "loss": 0.3804, "lr": 1.5309838429526714e-06, "epoch": 4.4288, "percentage": 88.72, "elapsed_time": "15:41:56", "remaining_time": "1:59:47"}
347
+ {"current_steps": 347, "total_steps": 390, "loss": 0.3731, "lr": 1.4630360979351644e-06, "epoch": 4.4416, "percentage": 88.97, "elapsed_time": "15:44:41", "remaining_time": "1:57:03"}
348
+ {"current_steps": 348, "total_steps": 390, "loss": 0.3888, "lr": 1.396573335013236e-06, "epoch": 4.4544, "percentage": 89.23, "elapsed_time": "15:47:27", "remaining_time": "1:54:20"}
349
+ {"current_steps": 349, "total_steps": 390, "loss": 0.3806, "lr": 1.3316008784683265e-06, "epoch": 4.4672, "percentage": 89.49, "elapsed_time": "15:50:01", "remaining_time": "1:51:36"}
350
+ {"current_steps": 350, "total_steps": 390, "loss": 0.358, "lr": 1.2681239331945695e-06, "epoch": 4.48, "percentage": 89.74, "elapsed_time": "15:52:57", "remaining_time": "1:48:54"}
351
+ {"current_steps": 351, "total_steps": 390, "loss": 0.3923, "lr": 1.2061475842818337e-06, "epoch": 4.4928, "percentage": 90.0, "elapsed_time": "15:55:51", "remaining_time": "1:46:12"}
352
+ {"current_steps": 352, "total_steps": 390, "loss": 0.3663, "lr": 1.1456767966083393e-06, "epoch": 4.5056, "percentage": 90.26, "elapsed_time": "15:58:29", "remaining_time": "1:43:28"}
353
+ {"current_steps": 353, "total_steps": 390, "loss": 0.3745, "lr": 1.086716414442952e-06, "epoch": 4.5184, "percentage": 90.51, "elapsed_time": "16:01:08", "remaining_time": "1:40:44"}
354
+ {"current_steps": 354, "total_steps": 390, "loss": 0.3734, "lr": 1.0292711610570904e-06, "epoch": 4.5312, "percentage": 90.77, "elapsed_time": "16:03:41", "remaining_time": "1:38:00"}
355
+ {"current_steps": 355, "total_steps": 390, "loss": 0.3761, "lr": 9.733456383463658e-07, "epoch": 4.5440000000000005, "percentage": 91.03, "elapsed_time": "16:06:35", "remaining_time": "1:35:17"}
356
+ {"current_steps": 356, "total_steps": 390, "loss": 0.3643, "lr": 9.189443264619102e-07, "epoch": 4.5568, "percentage": 91.28, "elapsed_time": "16:09:23", "remaining_time": "1:32:34"}
357
+ {"current_steps": 357, "total_steps": 390, "loss": 0.3668, "lr": 8.660715834514977e-07, "epoch": 4.5696, "percentage": 91.54, "elapsed_time": "16:12:03", "remaining_time": "1:29:51"}
358
+ {"current_steps": 358, "total_steps": 390, "loss": 0.4034, "lr": 8.147316449103959e-07, "epoch": 4.5824, "percentage": 91.79, "elapsed_time": "16:14:48", "remaining_time": "1:27:08"}
359
+ {"current_steps": 359, "total_steps": 390, "loss": 0.3841, "lr": 7.649286236420806e-07, "epoch": 4.5952, "percentage": 92.05, "elapsed_time": "16:17:29", "remaining_time": "1:24:24"}
360
+ {"current_steps": 360, "total_steps": 390, "loss": 0.3855, "lr": 7.166665093287539e-07, "epoch": 4.608, "percentage": 92.31, "elapsed_time": "16:20:11", "remaining_time": "1:21:40"}
361
+ {"current_steps": 361, "total_steps": 390, "loss": 0.353, "lr": 6.69949168211721e-07, "epoch": 4.6208, "percentage": 92.56, "elapsed_time": "16:22:31", "remaining_time": "1:18:55"}
362
+ {"current_steps": 362, "total_steps": 390, "loss": 0.3889, "lr": 6.247803427816945e-07, "epoch": 4.6336, "percentage": 92.82, "elapsed_time": "16:25:19", "remaining_time": "1:16:12"}
363
+ {"current_steps": 363, "total_steps": 390, "loss": 0.3778, "lr": 5.811636514789598e-07, "epoch": 4.6464, "percentage": 93.08, "elapsed_time": "16:28:07", "remaining_time": "1:13:29"}
364
+ {"current_steps": 364, "total_steps": 390, "loss": 0.3782, "lr": 5.391025884035239e-07, "epoch": 4.6592, "percentage": 93.33, "elapsed_time": "16:30:41", "remaining_time": "1:10:45"}
365
+ {"current_steps": 365, "total_steps": 390, "loss": 0.3708, "lr": 4.986005230351954e-07, "epoch": 4.672, "percentage": 93.59, "elapsed_time": "16:33:08", "remaining_time": "1:08:01"}
366
+ {"current_steps": 366, "total_steps": 390, "loss": 0.3808, "lr": 4.5966069996365993e-07, "epoch": 4.6848, "percentage": 93.85, "elapsed_time": "16:35:54", "remaining_time": "1:05:18"}
367
+ {"current_steps": 367, "total_steps": 390, "loss": 0.3769, "lr": 4.22286238628562e-07, "epoch": 4.6975999999999996, "percentage": 94.1, "elapsed_time": "16:38:41", "remaining_time": "1:02:35"}
368
+ {"current_steps": 368, "total_steps": 390, "loss": 0.3759, "lr": 3.8648013306960664e-07, "epoch": 4.7104, "percentage": 94.36, "elapsed_time": "16:41:27", "remaining_time": "0:59:52"}
369
+ {"current_steps": 369, "total_steps": 390, "loss": 0.3868, "lr": 3.522452516867048e-07, "epoch": 4.7232, "percentage": 94.62, "elapsed_time": "16:44:10", "remaining_time": "0:57:08"}
370
+ {"current_steps": 370, "total_steps": 390, "loss": 0.3757, "lr": 3.1958433701019697e-07, "epoch": 4.736, "percentage": 94.87, "elapsed_time": "16:46:56", "remaining_time": "0:54:25"}
371
+ {"current_steps": 371, "total_steps": 390, "loss": 0.3805, "lr": 2.8850000548115155e-07, "epoch": 4.7488, "percentage": 95.13, "elapsed_time": "16:49:39", "remaining_time": "0:51:42"}
372
+ {"current_steps": 372, "total_steps": 390, "loss": 0.3817, "lr": 2.5899474724174313e-07, "epoch": 4.7616, "percentage": 95.38, "elapsed_time": "16:52:24", "remaining_time": "0:48:59"}
373
+ {"current_steps": 373, "total_steps": 390, "loss": 0.3825, "lr": 2.3107092593579905e-07, "epoch": 4.7744, "percentage": 95.64, "elapsed_time": "16:55:10", "remaining_time": "0:46:16"}
374
+ {"current_steps": 374, "total_steps": 390, "loss": 0.3679, "lr": 2.0473077851942858e-07, "epoch": 4.7872, "percentage": 95.9, "elapsed_time": "16:57:48", "remaining_time": "0:43:32"}
375
+ {"current_steps": 375, "total_steps": 390, "loss": 0.3834, "lr": 1.799764150818306e-07, "epoch": 4.8, "percentage": 96.15, "elapsed_time": "17:00:36", "remaining_time": "0:40:49"}
376
+ {"current_steps": 376, "total_steps": 390, "loss": 0.3756, "lr": 1.5680981867625566e-07, "epoch": 4.8128, "percentage": 96.41, "elapsed_time": "17:03:20", "remaining_time": "0:38:06"}
377
+ {"current_steps": 377, "total_steps": 390, "loss": 0.372, "lr": 1.3523284516113955e-07, "epoch": 4.8256, "percentage": 96.67, "elapsed_time": "17:06:06", "remaining_time": "0:35:22"}
378
+ {"current_steps": 378, "total_steps": 390, "loss": 0.3718, "lr": 1.1524722305144231e-07, "epoch": 4.8384, "percentage": 96.92, "elapsed_time": "17:08:41", "remaining_time": "0:32:39"}
379
+ {"current_steps": 379, "total_steps": 390, "loss": 0.3798, "lr": 9.685455338016347e-08, "epoch": 4.8512, "percentage": 97.18, "elapsed_time": "17:11:37", "remaining_time": "0:29:56"}
380
+ {"current_steps": 380, "total_steps": 390, "loss": 0.3727, "lr": 8.005630957010014e-08, "epoch": 4.864, "percentage": 97.44, "elapsed_time": "17:14:06", "remaining_time": "0:27:12"}
381
+ {"current_steps": 381, "total_steps": 390, "loss": 0.3758, "lr": 6.485383731580142e-08, "epoch": 4.8768, "percentage": 97.69, "elapsed_time": "17:16:51", "remaining_time": "0:24:29"}
382
+ {"current_steps": 382, "total_steps": 390, "loss": 0.3719, "lr": 5.1248354475768034e-08, "epoch": 4.8896, "percentage": 97.95, "elapsed_time": "17:19:32", "remaining_time": "0:21:46"}
383
+ {"current_steps": 383, "total_steps": 390, "loss": 0.3662, "lr": 3.924095097489922e-08, "epoch": 4.9024, "percentage": 98.21, "elapsed_time": "17:22:02", "remaining_time": "0:19:02"}
384
+ {"current_steps": 384, "total_steps": 390, "loss": 0.3774, "lr": 2.8832588717164766e-08, "epoch": 4.9152000000000005, "percentage": 98.46, "elapsed_time": "17:24:41", "remaining_time": "0:16:19"}
385
+ {"current_steps": 385, "total_steps": 390, "loss": 0.3731, "lr": 2.0024101508555604e-08, "epoch": 4.928, "percentage": 98.72, "elapsed_time": "17:27:14", "remaining_time": "0:13:36"}
386
+ {"current_steps": 386, "total_steps": 390, "loss": 0.3801, "lr": 1.281619499029274e-08, "epoch": 4.9408, "percentage": 98.97, "elapsed_time": "17:30:00", "remaining_time": "0:10:52"}
387
+ {"current_steps": 387, "total_steps": 390, "loss": 0.3551, "lr": 7.209446582292501e-09, "epoch": 4.9536, "percentage": 99.23, "elapsed_time": "17:32:40", "remaining_time": "0:08:09"}
388
+ {"current_steps": 388, "total_steps": 390, "loss": 0.3714, "lr": 3.2043054369057523e-09, "epoch": 4.9664, "percentage": 99.49, "elapsed_time": "17:35:26", "remaining_time": "0:05:26"}
389
+ {"current_steps": 389, "total_steps": 390, "loss": 0.3798, "lr": 8.010924029533406e-10, "epoch": 4.9792, "percentage": 99.74, "elapsed_time": "17:38:21", "remaining_time": "0:02:43"}
390
+ {"current_steps": 390, "total_steps": 390, "loss": 0.3857, "lr": 0.0, "epoch": 4.992, "percentage": 100.0, "elapsed_time": "17:41:15", "remaining_time": "0:00:00"}
391
+ {"current_steps": 390, "total_steps": 390, "epoch": 4.992, "percentage": 100.0, "elapsed_time": "17:42:52", "remaining_time": "0:00:00"}