ryanmarten commited on
Commit
0d3f3fa
·
verified ·
1 Parent(s): 457ec6b

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 sha256:03efdb9e35b26c997ae14277b4c9cfc0e3da3a6f8c0fe6d4428fa06a5a14ccee
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aec94b68f734dd18b89d9b83e710b3e7d0c78815fb38db69699bc73f3df503ff
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4cda17c4738298d5616c56febb72ea5f69e9bc7eddb88d327b475a8c72fa7bd7
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c30254d1f57a8dd98abb2976d40c3ed888869f1237bcfe458e3c3e0b5c83208f
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:c8b6f3edcb887a3bb4b6a7eed4265b0cfc234e0e3b3d9ede8399a055db94f0ba
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3a948ad30653116c8ad5814485a18033ea71f2fdece3f6d1be11ffd05d75ff8
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:97ccc3a57be6e89e2a8157fd75898be9ad70d6ef186fd259f02838b95204b545
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3fdd739f023df0bcd47f591455484fbd62958ea41b110f26d2a573b5840a6185
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -311,3 +311,81 @@
311
  {"current_steps": 311, "total_steps": 390, "loss": 0.4299, "lr": 4.794787480690597e-06, "epoch": 3.9808, "percentage": 79.74, "elapsed_time": "14:01:37", "remaining_time": "3:33:47"}
312
  {"current_steps": 312, "total_steps": 390, "loss": 0.4267, "lr": 4.679111137620442e-06, "epoch": 3.9936, "percentage": 80.0, "elapsed_time": "14:04:24", "remaining_time": "3:31:06"}
313
  {"current_steps": 313, "total_steps": 390, "loss": 0.4036, "lr": 4.5646621393177e-06, "epoch": 4.0064, "percentage": 80.26, "elapsed_time": "14:08:14", "remaining_time": "3:28:40"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
311
  {"current_steps": 311, "total_steps": 390, "loss": 0.4299, "lr": 4.794787480690597e-06, "epoch": 3.9808, "percentage": 79.74, "elapsed_time": "14:01:37", "remaining_time": "3:33:47"}
312
  {"current_steps": 312, "total_steps": 390, "loss": 0.4267, "lr": 4.679111137620442e-06, "epoch": 3.9936, "percentage": 80.0, "elapsed_time": "14:04:24", "remaining_time": "3:31:06"}
313
  {"current_steps": 313, "total_steps": 390, "loss": 0.4036, "lr": 4.5646621393177e-06, "epoch": 4.0064, "percentage": 80.26, "elapsed_time": "14:08:14", "remaining_time": "3:28:40"}
314
+ {"current_steps": 314, "total_steps": 390, "loss": 0.3924, "lr": 4.451449654204685e-06, "epoch": 4.0192, "percentage": 80.51, "elapsed_time": "14:11:06", "remaining_time": "3:26:00"}
315
+ {"current_steps": 315, "total_steps": 390, "loss": 0.3638, "lr": 4.339482751647557e-06, "epoch": 4.032, "percentage": 80.77, "elapsed_time": "14:13:51", "remaining_time": "3:23:18"}
316
+ {"current_steps": 316, "total_steps": 390, "loss": 0.3823, "lr": 4.228770401229824e-06, "epoch": 4.0448, "percentage": 81.03, "elapsed_time": "14:16:39", "remaining_time": "3:20:36"}
317
+ {"current_steps": 317, "total_steps": 390, "loss": 0.3775, "lr": 4.119321472033779e-06, "epoch": 4.0576, "percentage": 81.28, "elapsed_time": "14:19:20", "remaining_time": "3:17:53"}
318
+ {"current_steps": 318, "total_steps": 390, "loss": 0.3813, "lr": 4.011144731929981e-06, "epoch": 4.0704, "percentage": 81.54, "elapsed_time": "14:22:04", "remaining_time": "3:15:11"}
319
+ {"current_steps": 319, "total_steps": 390, "loss": 0.3979, "lr": 3.904248846874894e-06, "epoch": 4.0832, "percentage": 81.79, "elapsed_time": "14:24:50", "remaining_time": "3:12:29"}
320
+ {"current_steps": 320, "total_steps": 390, "loss": 0.3839, "lr": 3.7986423802166705e-06, "epoch": 4.096, "percentage": 82.05, "elapsed_time": "14:27:34", "remaining_time": "3:09:46"}
321
+ {"current_steps": 321, "total_steps": 390, "loss": 0.3807, "lr": 3.694333792009115e-06, "epoch": 4.1088, "percentage": 82.31, "elapsed_time": "14:30:06", "remaining_time": "3:07:01"}
322
+ {"current_steps": 322, "total_steps": 390, "loss": 0.3578, "lr": 3.5913314383339937e-06, "epoch": 4.1216, "percentage": 82.56, "elapsed_time": "14:32:47", "remaining_time": "3:04:19"}
323
+ {"current_steps": 323, "total_steps": 390, "loss": 0.3817, "lr": 3.4896435706316e-06, "epoch": 4.1344, "percentage": 82.82, "elapsed_time": "14:35:26", "remaining_time": "3:01:35"}
324
+ {"current_steps": 324, "total_steps": 390, "loss": 0.3889, "lr": 3.3892783350397675e-06, "epoch": 4.1472, "percentage": 83.08, "elapsed_time": "14:38:10", "remaining_time": "2:58:53"}
325
+ {"current_steps": 325, "total_steps": 390, "loss": 0.3846, "lr": 3.290243771741275e-06, "epoch": 4.16, "percentage": 83.33, "elapsed_time": "14:41:05", "remaining_time": "2:56:13"}
326
+ {"current_steps": 326, "total_steps": 390, "loss": 0.3701, "lr": 3.1925478143197418e-06, "epoch": 4.1728, "percentage": 83.59, "elapsed_time": "14:43:40", "remaining_time": "2:53:28"}
327
+ {"current_steps": 327, "total_steps": 390, "loss": 0.3775, "lr": 3.0961982891241083e-06, "epoch": 4.1856, "percentage": 83.85, "elapsed_time": "14:46:25", "remaining_time": "2:50:46"}
328
+ {"current_steps": 328, "total_steps": 390, "loss": 0.3694, "lr": 3.001202914641628e-06, "epoch": 4.1984, "percentage": 84.1, "elapsed_time": "14:49:08", "remaining_time": "2:48:04"}
329
+ {"current_steps": 329, "total_steps": 390, "loss": 0.3931, "lr": 2.907569300879596e-06, "epoch": 4.2112, "percentage": 84.36, "elapsed_time": "14:51:45", "remaining_time": "2:45:20"}
330
+ {"current_steps": 330, "total_steps": 390, "loss": 0.3722, "lr": 2.815304948755664e-06, "epoch": 4.224, "percentage": 84.62, "elapsed_time": "14:54:34", "remaining_time": "2:42:38"}
331
+ {"current_steps": 331, "total_steps": 390, "loss": 0.3979, "lr": 2.7244172494969978e-06, "epoch": 4.2368, "percentage": 84.87, "elapsed_time": "14:57:19", "remaining_time": "2:39:56"}
332
+ {"current_steps": 332, "total_steps": 390, "loss": 0.3781, "lr": 2.6349134840481294e-06, "epoch": 4.2496, "percentage": 85.13, "elapsed_time": "14:59:55", "remaining_time": "2:37:13"}
333
+ {"current_steps": 333, "total_steps": 390, "loss": 0.3693, "lr": 2.546800822487714e-06, "epoch": 4.2624, "percentage": 85.38, "elapsed_time": "15:02:46", "remaining_time": "2:34:31"}
334
+ {"current_steps": 334, "total_steps": 390, "loss": 0.4017, "lr": 2.4600863234541338e-06, "epoch": 4.2752, "percentage": 85.64, "elapsed_time": "15:05:32", "remaining_time": "2:31:49"}
335
+ {"current_steps": 335, "total_steps": 390, "loss": 0.3788, "lr": 2.374776933580025e-06, "epoch": 4.288, "percentage": 85.9, "elapsed_time": "15:07:54", "remaining_time": "2:29:03"}
336
+ {"current_steps": 336, "total_steps": 390, "loss": 0.3809, "lr": 2.2908794869358044e-06, "epoch": 4.3008, "percentage": 86.15, "elapsed_time": "15:10:36", "remaining_time": "2:26:20"}
337
+ {"current_steps": 337, "total_steps": 390, "loss": 0.3826, "lr": 2.2084007044821764e-06, "epoch": 4.3136, "percentage": 86.41, "elapsed_time": "15:13:25", "remaining_time": "2:23:39"}
338
+ {"current_steps": 338, "total_steps": 390, "loss": 0.3767, "lr": 2.127347193531757e-06, "epoch": 4.3264, "percentage": 86.67, "elapsed_time": "15:16:06", "remaining_time": "2:20:56"}
339
+ {"current_steps": 339, "total_steps": 390, "loss": 0.3805, "lr": 2.0477254472197237e-06, "epoch": 4.3392, "percentage": 86.92, "elapsed_time": "15:18:57", "remaining_time": "2:18:14"}
340
+ {"current_steps": 340, "total_steps": 390, "loss": 0.3723, "lr": 1.96954184398368e-06, "epoch": 4.352, "percentage": 87.18, "elapsed_time": "15:21:39", "remaining_time": "2:15:32"}
341
+ {"current_steps": 341, "total_steps": 390, "loss": 0.3721, "lr": 1.8928026470526917e-06, "epoch": 4.3648, "percentage": 87.44, "elapsed_time": "15:24:15", "remaining_time": "2:12:48"}
342
+ {"current_steps": 342, "total_steps": 390, "loss": 0.3674, "lr": 1.817514003945524e-06, "epoch": 4.3776, "percentage": 87.69, "elapsed_time": "15:27:00", "remaining_time": "2:10:06"}
343
+ {"current_steps": 343, "total_steps": 390, "loss": 0.3668, "lr": 1.743681945978184e-06, "epoch": 4.3904, "percentage": 87.95, "elapsed_time": "15:29:37", "remaining_time": "2:07:22"}
344
+ {"current_steps": 344, "total_steps": 390, "loss": 0.3667, "lr": 1.6713123877807413e-06, "epoch": 4.4032, "percentage": 88.21, "elapsed_time": "15:32:08", "remaining_time": "2:04:38"}
345
+ {"current_steps": 345, "total_steps": 390, "loss": 0.3856, "lr": 1.6004111268235156e-06, "epoch": 4.416, "percentage": 88.46, "elapsed_time": "15:34:47", "remaining_time": "2:01:55"}
346
+ {"current_steps": 346, "total_steps": 390, "loss": 0.4001, "lr": 1.5309838429526714e-06, "epoch": 4.4288, "percentage": 88.72, "elapsed_time": "15:37:22", "remaining_time": "1:59:12"}
347
+ {"current_steps": 347, "total_steps": 390, "loss": 0.3966, "lr": 1.4630360979351644e-06, "epoch": 4.4416, "percentage": 88.97, "elapsed_time": "15:39:59", "remaining_time": "1:56:28"}
348
+ {"current_steps": 348, "total_steps": 390, "loss": 0.3894, "lr": 1.396573335013236e-06, "epoch": 4.4544, "percentage": 89.23, "elapsed_time": "15:42:46", "remaining_time": "1:53:47"}
349
+ {"current_steps": 349, "total_steps": 390, "loss": 0.3691, "lr": 1.3316008784683265e-06, "epoch": 4.4672, "percentage": 89.49, "elapsed_time": "15:45:27", "remaining_time": "1:51:04"}
350
+ {"current_steps": 350, "total_steps": 390, "loss": 0.3887, "lr": 1.2681239331945695e-06, "epoch": 4.48, "percentage": 89.74, "elapsed_time": "15:48:02", "remaining_time": "1:48:20"}
351
+ {"current_steps": 351, "total_steps": 390, "loss": 0.3905, "lr": 1.2061475842818337e-06, "epoch": 4.4928, "percentage": 90.0, "elapsed_time": "15:50:39", "remaining_time": "1:45:37"}
352
+ {"current_steps": 352, "total_steps": 390, "loss": 0.384, "lr": 1.1456767966083393e-06, "epoch": 4.5056, "percentage": 90.26, "elapsed_time": "15:53:41", "remaining_time": "1:42:57"}
353
+ {"current_steps": 353, "total_steps": 390, "loss": 0.3797, "lr": 1.086716414442952e-06, "epoch": 4.5184, "percentage": 90.51, "elapsed_time": "15:56:27", "remaining_time": "1:40:15"}
354
+ {"current_steps": 354, "total_steps": 390, "loss": 0.3737, "lr": 1.0292711610570904e-06, "epoch": 4.5312, "percentage": 90.77, "elapsed_time": "15:59:10", "remaining_time": "1:37:32"}
355
+ {"current_steps": 355, "total_steps": 390, "loss": 0.3815, "lr": 9.733456383463658e-07, "epoch": 4.5440000000000005, "percentage": 91.03, "elapsed_time": "16:01:49", "remaining_time": "1:34:49"}
356
+ {"current_steps": 356, "total_steps": 390, "loss": 0.3779, "lr": 9.189443264619102e-07, "epoch": 4.5568, "percentage": 91.28, "elapsed_time": "16:04:26", "remaining_time": "1:32:06"}
357
+ {"current_steps": 357, "total_steps": 390, "loss": 0.3756, "lr": 8.660715834514977e-07, "epoch": 4.5696, "percentage": 91.54, "elapsed_time": "16:07:05", "remaining_time": "1:29:23"}
358
+ {"current_steps": 358, "total_steps": 390, "loss": 0.385, "lr": 8.147316449103959e-07, "epoch": 4.5824, "percentage": 91.79, "elapsed_time": "16:09:47", "remaining_time": "1:26:41"}
359
+ {"current_steps": 359, "total_steps": 390, "loss": 0.3787, "lr": 7.649286236420806e-07, "epoch": 4.5952, "percentage": 92.05, "elapsed_time": "16:12:30", "remaining_time": "1:23:58"}
360
+ {"current_steps": 360, "total_steps": 390, "loss": 0.4023, "lr": 7.166665093287539e-07, "epoch": 4.608, "percentage": 92.31, "elapsed_time": "16:15:18", "remaining_time": "1:21:16"}
361
+ {"current_steps": 361, "total_steps": 390, "loss": 0.3768, "lr": 6.69949168211721e-07, "epoch": 4.6208, "percentage": 92.56, "elapsed_time": "16:17:53", "remaining_time": "1:18:33"}
362
+ {"current_steps": 362, "total_steps": 390, "loss": 0.3682, "lr": 6.247803427816945e-07, "epoch": 4.6336, "percentage": 92.82, "elapsed_time": "16:20:31", "remaining_time": "1:15:50"}
363
+ {"current_steps": 363, "total_steps": 390, "loss": 0.3651, "lr": 5.811636514789598e-07, "epoch": 4.6464, "percentage": 93.08, "elapsed_time": "16:23:10", "remaining_time": "1:13:07"}
364
+ {"current_steps": 364, "total_steps": 390, "loss": 0.3761, "lr": 5.391025884035239e-07, "epoch": 4.6592, "percentage": 93.33, "elapsed_time": "16:25:47", "remaining_time": "1:10:24"}
365
+ {"current_steps": 365, "total_steps": 390, "loss": 0.3818, "lr": 4.986005230351954e-07, "epoch": 4.672, "percentage": 93.59, "elapsed_time": "16:28:23", "remaining_time": "1:07:41"}
366
+ {"current_steps": 366, "total_steps": 390, "loss": 0.3799, "lr": 4.5966069996365993e-07, "epoch": 4.6848, "percentage": 93.85, "elapsed_time": "16:31:02", "remaining_time": "1:04:59"}
367
+ {"current_steps": 367, "total_steps": 390, "loss": 0.3902, "lr": 4.22286238628562e-07, "epoch": 4.6975999999999996, "percentage": 94.1, "elapsed_time": "16:33:57", "remaining_time": "1:02:17"}
368
+ {"current_steps": 368, "total_steps": 390, "loss": 0.3741, "lr": 3.8648013306960664e-07, "epoch": 4.7104, "percentage": 94.36, "elapsed_time": "16:36:48", "remaining_time": "0:59:35"}
369
+ {"current_steps": 369, "total_steps": 390, "loss": 0.3865, "lr": 3.522452516867048e-07, "epoch": 4.7232, "percentage": 94.62, "elapsed_time": "16:39:40", "remaining_time": "0:56:53"}
370
+ {"current_steps": 370, "total_steps": 390, "loss": 0.3904, "lr": 3.1958433701019697e-07, "epoch": 4.736, "percentage": 94.87, "elapsed_time": "16:42:25", "remaining_time": "0:54:11"}
371
+ {"current_steps": 371, "total_steps": 390, "loss": 0.3801, "lr": 2.8850000548115155e-07, "epoch": 4.7488, "percentage": 95.13, "elapsed_time": "16:45:01", "remaining_time": "0:51:28"}
372
+ {"current_steps": 372, "total_steps": 390, "loss": 0.3825, "lr": 2.5899474724174313e-07, "epoch": 4.7616, "percentage": 95.38, "elapsed_time": "16:47:49", "remaining_time": "0:48:45"}
373
+ {"current_steps": 373, "total_steps": 390, "loss": 0.378, "lr": 2.3107092593579905e-07, "epoch": 4.7744, "percentage": 95.64, "elapsed_time": "16:50:36", "remaining_time": "0:46:03"}
374
+ {"current_steps": 374, "total_steps": 390, "loss": 0.3907, "lr": 2.0473077851942858e-07, "epoch": 4.7872, "percentage": 95.9, "elapsed_time": "16:53:25", "remaining_time": "0:43:21"}
375
+ {"current_steps": 375, "total_steps": 390, "loss": 0.3663, "lr": 1.799764150818306e-07, "epoch": 4.8, "percentage": 96.15, "elapsed_time": "16:56:14", "remaining_time": "0:40:38"}
376
+ {"current_steps": 376, "total_steps": 390, "loss": 0.3912, "lr": 1.5680981867625566e-07, "epoch": 4.8128, "percentage": 96.41, "elapsed_time": "16:58:51", "remaining_time": "0:37:56"}
377
+ {"current_steps": 377, "total_steps": 390, "loss": 0.3879, "lr": 1.3523284516113955e-07, "epoch": 4.8256, "percentage": 96.67, "elapsed_time": "17:01:39", "remaining_time": "0:35:13"}
378
+ {"current_steps": 378, "total_steps": 390, "loss": 0.3678, "lr": 1.1524722305144231e-07, "epoch": 4.8384, "percentage": 96.92, "elapsed_time": "17:04:20", "remaining_time": "0:32:31"}
379
+ {"current_steps": 379, "total_steps": 390, "loss": 0.3746, "lr": 9.685455338016347e-08, "epoch": 4.8512, "percentage": 97.18, "elapsed_time": "17:07:00", "remaining_time": "0:29:48"}
380
+ {"current_steps": 380, "total_steps": 390, "loss": 0.3888, "lr": 8.005630957010014e-08, "epoch": 4.864, "percentage": 97.44, "elapsed_time": "17:09:41", "remaining_time": "0:27:05"}
381
+ {"current_steps": 381, "total_steps": 390, "loss": 0.3595, "lr": 6.485383731580142e-08, "epoch": 4.8768, "percentage": 97.69, "elapsed_time": "17:12:13", "remaining_time": "0:24:23"}
382
+ {"current_steps": 382, "total_steps": 390, "loss": 0.3877, "lr": 5.1248354475768034e-08, "epoch": 4.8896, "percentage": 97.95, "elapsed_time": "17:14:56", "remaining_time": "0:21:40"}
383
+ {"current_steps": 383, "total_steps": 390, "loss": 0.3837, "lr": 3.924095097489922e-08, "epoch": 4.9024, "percentage": 98.21, "elapsed_time": "17:17:31", "remaining_time": "0:18:57"}
384
+ {"current_steps": 384, "total_steps": 390, "loss": 0.3817, "lr": 2.8832588717164766e-08, "epoch": 4.9152000000000005, "percentage": 98.46, "elapsed_time": "17:20:12", "remaining_time": "0:16:15"}
385
+ {"current_steps": 385, "total_steps": 390, "loss": 0.3791, "lr": 2.0024101508555604e-08, "epoch": 4.928, "percentage": 98.72, "elapsed_time": "17:22:56", "remaining_time": "0:13:32"}
386
+ {"current_steps": 386, "total_steps": 390, "loss": 0.3868, "lr": 1.281619499029274e-08, "epoch": 4.9408, "percentage": 98.97, "elapsed_time": "17:25:29", "remaining_time": "0:10:50"}
387
+ {"current_steps": 387, "total_steps": 390, "loss": 0.3642, "lr": 7.209446582292501e-09, "epoch": 4.9536, "percentage": 99.23, "elapsed_time": "17:27:56", "remaining_time": "0:08:07"}
388
+ {"current_steps": 388, "total_steps": 390, "loss": 0.372, "lr": 3.2043054369057523e-09, "epoch": 4.9664, "percentage": 99.49, "elapsed_time": "17:30:49", "remaining_time": "0:05:24"}
389
+ {"current_steps": 389, "total_steps": 390, "loss": 0.3661, "lr": 8.010924029533406e-10, "epoch": 4.9792, "percentage": 99.74, "elapsed_time": "17:33:39", "remaining_time": "0:02:42"}
390
+ {"current_steps": 390, "total_steps": 390, "loss": 0.3784, "lr": 0.0, "epoch": 4.992, "percentage": 100.0, "elapsed_time": "17:36:22", "remaining_time": "0:00:00"}
391
+ {"current_steps": 390, "total_steps": 390, "epoch": 4.992, "percentage": 100.0, "elapsed_time": "17:38:27", "remaining_time": "0:00:00"}