ryanmarten commited on
Commit
512669a
·
verified ·
1 Parent(s): 0a905f9

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:a6ac934005724989a6ca066e098e26b228afb293b48efdcf59b275659c808afd
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d3d897906695d53d7933b644631b952fdcffc84c48ea935ff1097657e4c770e
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:20781c692477029cce27678ec3a12d3b26a46e1ab2df82bf12172b2fdafe13bf
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f333937e167c6a40a3f89b250d42d532f1c8a355af2c79b44ab882d0de421e2
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8b882754c49c6bc959ba29d3efb7f8254be8551fe434ba9afeeb6aa0c5a62b6f
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6b736dfca716bf6d137b1b831e07da2d13bfc8be8055a989cc67ae16e10c537
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:d19560b05a54f6ecf5d4ebf9c659aada81f736ebe2b1799dd66bd6d5f81ca2d8
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f015b342d6a94774776f2bb3703c6373940f128177c4ea7bb1599782e0c1abc
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -311,3 +311,81 @@
311
  {"current_steps": 311, "total_steps": 390, "loss": 0.4377, "lr": 4.794787480690597e-06, "epoch": 3.9808, "percentage": 79.74, "elapsed_time": "14:09:38", "remaining_time": "3:35:49"}
312
  {"current_steps": 312, "total_steps": 390, "loss": 0.4274, "lr": 4.679111137620442e-06, "epoch": 3.9936, "percentage": 80.0, "elapsed_time": "14:12:29", "remaining_time": "3:33:07"}
313
  {"current_steps": 313, "total_steps": 390, "loss": 0.4139, "lr": 4.5646621393177e-06, "epoch": 4.0064, "percentage": 80.26, "elapsed_time": "14:15:59", "remaining_time": "3:30:34"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
311
  {"current_steps": 311, "total_steps": 390, "loss": 0.4377, "lr": 4.794787480690597e-06, "epoch": 3.9808, "percentage": 79.74, "elapsed_time": "14:09:38", "remaining_time": "3:35:49"}
312
  {"current_steps": 312, "total_steps": 390, "loss": 0.4274, "lr": 4.679111137620442e-06, "epoch": 3.9936, "percentage": 80.0, "elapsed_time": "14:12:29", "remaining_time": "3:33:07"}
313
  {"current_steps": 313, "total_steps": 390, "loss": 0.4139, "lr": 4.5646621393177e-06, "epoch": 4.0064, "percentage": 80.26, "elapsed_time": "14:15:59", "remaining_time": "3:30:34"}
314
+ {"current_steps": 314, "total_steps": 390, "loss": 0.3825, "lr": 4.451449654204685e-06, "epoch": 4.0192, "percentage": 80.51, "elapsed_time": "14:18:42", "remaining_time": "3:27:50"}
315
+ {"current_steps": 315, "total_steps": 390, "loss": 0.4006, "lr": 4.339482751647557e-06, "epoch": 4.032, "percentage": 80.77, "elapsed_time": "14:21:17", "remaining_time": "3:25:04"}
316
+ {"current_steps": 316, "total_steps": 390, "loss": 0.3895, "lr": 4.228770401229824e-06, "epoch": 4.0448, "percentage": 81.03, "elapsed_time": "14:24:11", "remaining_time": "3:22:22"}
317
+ {"current_steps": 317, "total_steps": 390, "loss": 0.388, "lr": 4.119321472033779e-06, "epoch": 4.0576, "percentage": 81.28, "elapsed_time": "14:26:51", "remaining_time": "3:19:37"}
318
+ {"current_steps": 318, "total_steps": 390, "loss": 0.3922, "lr": 4.011144731929981e-06, "epoch": 4.0704, "percentage": 81.54, "elapsed_time": "14:29:31", "remaining_time": "3:16:52"}
319
+ {"current_steps": 319, "total_steps": 390, "loss": 0.3914, "lr": 3.904248846874894e-06, "epoch": 4.0832, "percentage": 81.79, "elapsed_time": "14:32:11", "remaining_time": "3:14:07"}
320
+ {"current_steps": 320, "total_steps": 390, "loss": 0.3793, "lr": 3.7986423802166705e-06, "epoch": 4.096, "percentage": 82.05, "elapsed_time": "14:35:07", "remaining_time": "3:11:26"}
321
+ {"current_steps": 321, "total_steps": 390, "loss": 0.3892, "lr": 3.694333792009115e-06, "epoch": 4.1088, "percentage": 82.31, "elapsed_time": "14:37:46", "remaining_time": "3:08:40"}
322
+ {"current_steps": 322, "total_steps": 390, "loss": 0.3906, "lr": 3.5913314383339937e-06, "epoch": 4.1216, "percentage": 82.56, "elapsed_time": "14:40:36", "remaining_time": "3:05:58"}
323
+ {"current_steps": 323, "total_steps": 390, "loss": 0.3976, "lr": 3.4896435706316e-06, "epoch": 4.1344, "percentage": 82.82, "elapsed_time": "14:43:25", "remaining_time": "3:03:14"}
324
+ {"current_steps": 324, "total_steps": 390, "loss": 0.4012, "lr": 3.3892783350397675e-06, "epoch": 4.1472, "percentage": 83.08, "elapsed_time": "14:46:10", "remaining_time": "3:00:31"}
325
+ {"current_steps": 325, "total_steps": 390, "loss": 0.393, "lr": 3.290243771741275e-06, "epoch": 4.16, "percentage": 83.33, "elapsed_time": "14:48:55", "remaining_time": "2:57:47"}
326
+ {"current_steps": 326, "total_steps": 390, "loss": 0.3902, "lr": 3.1925478143197418e-06, "epoch": 4.1728, "percentage": 83.59, "elapsed_time": "14:51:43", "remaining_time": "2:55:03"}
327
+ {"current_steps": 327, "total_steps": 390, "loss": 0.385, "lr": 3.0961982891241083e-06, "epoch": 4.1856, "percentage": 83.85, "elapsed_time": "14:54:27", "remaining_time": "2:52:19"}
328
+ {"current_steps": 328, "total_steps": 390, "loss": 0.3842, "lr": 3.001202914641628e-06, "epoch": 4.1984, "percentage": 84.1, "elapsed_time": "14:56:53", "remaining_time": "2:49:32"}
329
+ {"current_steps": 329, "total_steps": 390, "loss": 0.3894, "lr": 2.907569300879596e-06, "epoch": 4.2112, "percentage": 84.36, "elapsed_time": "14:59:43", "remaining_time": "2:46:49"}
330
+ {"current_steps": 330, "total_steps": 390, "loss": 0.3955, "lr": 2.815304948755664e-06, "epoch": 4.224, "percentage": 84.62, "elapsed_time": "15:02:31", "remaining_time": "2:44:05"}
331
+ {"current_steps": 331, "total_steps": 390, "loss": 0.4006, "lr": 2.7244172494969978e-06, "epoch": 4.2368, "percentage": 84.87, "elapsed_time": "15:05:16", "remaining_time": "2:41:21"}
332
+ {"current_steps": 332, "total_steps": 390, "loss": 0.3758, "lr": 2.6349134840481294e-06, "epoch": 4.2496, "percentage": 85.13, "elapsed_time": "15:08:01", "remaining_time": "2:38:37"}
333
+ {"current_steps": 333, "total_steps": 390, "loss": 0.3971, "lr": 2.546800822487714e-06, "epoch": 4.2624, "percentage": 85.38, "elapsed_time": "15:10:38", "remaining_time": "2:35:52"}
334
+ {"current_steps": 334, "total_steps": 390, "loss": 0.3678, "lr": 2.4600863234541338e-06, "epoch": 4.2752, "percentage": 85.64, "elapsed_time": "15:13:22", "remaining_time": "2:33:08"}
335
+ {"current_steps": 335, "total_steps": 390, "loss": 0.3855, "lr": 2.374776933580025e-06, "epoch": 4.288, "percentage": 85.9, "elapsed_time": "15:15:58", "remaining_time": "2:30:23"}
336
+ {"current_steps": 336, "total_steps": 390, "loss": 0.3864, "lr": 2.2908794869358044e-06, "epoch": 4.3008, "percentage": 86.15, "elapsed_time": "15:18:55", "remaining_time": "2:27:41"}
337
+ {"current_steps": 337, "total_steps": 390, "loss": 0.3892, "lr": 2.2084007044821764e-06, "epoch": 4.3136, "percentage": 86.41, "elapsed_time": "15:21:44", "remaining_time": "2:24:57"}
338
+ {"current_steps": 338, "total_steps": 390, "loss": 0.3933, "lr": 2.127347193531757e-06, "epoch": 4.3264, "percentage": 86.67, "elapsed_time": "15:24:29", "remaining_time": "2:22:13"}
339
+ {"current_steps": 339, "total_steps": 390, "loss": 0.3761, "lr": 2.0477254472197237e-06, "epoch": 4.3392, "percentage": 86.92, "elapsed_time": "15:27:20", "remaining_time": "2:19:30"}
340
+ {"current_steps": 340, "total_steps": 390, "loss": 0.376, "lr": 1.96954184398368e-06, "epoch": 4.352, "percentage": 87.18, "elapsed_time": "15:29:54", "remaining_time": "2:16:45"}
341
+ {"current_steps": 341, "total_steps": 390, "loss": 0.3869, "lr": 1.8928026470526917e-06, "epoch": 4.3648, "percentage": 87.44, "elapsed_time": "15:32:45", "remaining_time": "2:14:02"}
342
+ {"current_steps": 342, "total_steps": 390, "loss": 0.401, "lr": 1.817514003945524e-06, "epoch": 4.3776, "percentage": 87.69, "elapsed_time": "15:35:20", "remaining_time": "2:11:16"}
343
+ {"current_steps": 343, "total_steps": 390, "loss": 0.3963, "lr": 1.743681945978184e-06, "epoch": 4.3904, "percentage": 87.95, "elapsed_time": "15:38:05", "remaining_time": "2:08:32"}
344
+ {"current_steps": 344, "total_steps": 390, "loss": 0.3866, "lr": 1.6713123877807413e-06, "epoch": 4.4032, "percentage": 88.21, "elapsed_time": "15:41:03", "remaining_time": "2:05:50"}
345
+ {"current_steps": 345, "total_steps": 390, "loss": 0.3896, "lr": 1.6004111268235156e-06, "epoch": 4.416, "percentage": 88.46, "elapsed_time": "15:43:50", "remaining_time": "2:03:06"}
346
+ {"current_steps": 346, "total_steps": 390, "loss": 0.3939, "lr": 1.5309838429526714e-06, "epoch": 4.4288, "percentage": 88.72, "elapsed_time": "15:46:35", "remaining_time": "2:00:22"}
347
+ {"current_steps": 347, "total_steps": 390, "loss": 0.4032, "lr": 1.4630360979351644e-06, "epoch": 4.4416, "percentage": 88.97, "elapsed_time": "15:49:04", "remaining_time": "1:57:36"}
348
+ {"current_steps": 348, "total_steps": 390, "loss": 0.4079, "lr": 1.396573335013236e-06, "epoch": 4.4544, "percentage": 89.23, "elapsed_time": "15:52:01", "remaining_time": "1:54:53"}
349
+ {"current_steps": 349, "total_steps": 390, "loss": 0.3783, "lr": 1.3316008784683265e-06, "epoch": 4.4672, "percentage": 89.49, "elapsed_time": "15:54:43", "remaining_time": "1:52:09"}
350
+ {"current_steps": 350, "total_steps": 390, "loss": 0.3747, "lr": 1.2681239331945695e-06, "epoch": 4.48, "percentage": 89.74, "elapsed_time": "15:57:26", "remaining_time": "1:49:25"}
351
+ {"current_steps": 351, "total_steps": 390, "loss": 0.4062, "lr": 1.2061475842818337e-06, "epoch": 4.4928, "percentage": 90.0, "elapsed_time": "16:00:18", "remaining_time": "1:46:42"}
352
+ {"current_steps": 352, "total_steps": 390, "loss": 0.3945, "lr": 1.1456767966083393e-06, "epoch": 4.5056, "percentage": 90.26, "elapsed_time": "16:02:51", "remaining_time": "1:43:56"}
353
+ {"current_steps": 353, "total_steps": 390, "loss": 0.3994, "lr": 1.086716414442952e-06, "epoch": 4.5184, "percentage": 90.51, "elapsed_time": "16:05:35", "remaining_time": "1:41:12"}
354
+ {"current_steps": 354, "total_steps": 390, "loss": 0.3848, "lr": 1.0292711610570904e-06, "epoch": 4.5312, "percentage": 90.77, "elapsed_time": "16:08:00", "remaining_time": "1:38:26"}
355
+ {"current_steps": 355, "total_steps": 390, "loss": 0.4013, "lr": 9.733456383463658e-07, "epoch": 4.5440000000000005, "percentage": 91.03, "elapsed_time": "16:11:03", "remaining_time": "1:35:44"}
356
+ {"current_steps": 356, "total_steps": 390, "loss": 0.4044, "lr": 9.189443264619102e-07, "epoch": 4.5568, "percentage": 91.28, "elapsed_time": "16:13:38", "remaining_time": "1:32:59"}
357
+ {"current_steps": 357, "total_steps": 390, "loss": 0.3846, "lr": 8.660715834514977e-07, "epoch": 4.5696, "percentage": 91.54, "elapsed_time": "16:16:26", "remaining_time": "1:30:15"}
358
+ {"current_steps": 358, "total_steps": 390, "loss": 0.3983, "lr": 8.147316449103959e-07, "epoch": 4.5824, "percentage": 91.79, "elapsed_time": "16:19:09", "remaining_time": "1:27:31"}
359
+ {"current_steps": 359, "total_steps": 390, "loss": 0.3941, "lr": 7.649286236420806e-07, "epoch": 4.5952, "percentage": 92.05, "elapsed_time": "16:22:00", "remaining_time": "1:24:47"}
360
+ {"current_steps": 360, "total_steps": 390, "loss": 0.3881, "lr": 7.166665093287539e-07, "epoch": 4.608, "percentage": 92.31, "elapsed_time": "16:24:43", "remaining_time": "1:22:03"}
361
+ {"current_steps": 361, "total_steps": 390, "loss": 0.3912, "lr": 6.69949168211721e-07, "epoch": 4.6208, "percentage": 92.56, "elapsed_time": "16:27:34", "remaining_time": "1:19:20"}
362
+ {"current_steps": 362, "total_steps": 390, "loss": 0.4021, "lr": 6.247803427816945e-07, "epoch": 4.6336, "percentage": 92.82, "elapsed_time": "16:30:21", "remaining_time": "1:16:36"}
363
+ {"current_steps": 363, "total_steps": 390, "loss": 0.3934, "lr": 5.811636514789598e-07, "epoch": 4.6464, "percentage": 93.08, "elapsed_time": "16:33:08", "remaining_time": "1:13:52"}
364
+ {"current_steps": 364, "total_steps": 390, "loss": 0.3939, "lr": 5.391025884035239e-07, "epoch": 4.6592, "percentage": 93.33, "elapsed_time": "16:35:57", "remaining_time": "1:11:08"}
365
+ {"current_steps": 365, "total_steps": 390, "loss": 0.4031, "lr": 4.986005230351954e-07, "epoch": 4.672, "percentage": 93.59, "elapsed_time": "16:38:44", "remaining_time": "1:08:24"}
366
+ {"current_steps": 366, "total_steps": 390, "loss": 0.3818, "lr": 4.5966069996365993e-07, "epoch": 4.6848, "percentage": 93.85, "elapsed_time": "16:41:19", "remaining_time": "1:05:39"}
367
+ {"current_steps": 367, "total_steps": 390, "loss": 0.3748, "lr": 4.22286238628562e-07, "epoch": 4.6975999999999996, "percentage": 94.1, "elapsed_time": "16:43:58", "remaining_time": "1:02:55"}
368
+ {"current_steps": 368, "total_steps": 390, "loss": 0.383, "lr": 3.8648013306960664e-07, "epoch": 4.7104, "percentage": 94.36, "elapsed_time": "16:46:34", "remaining_time": "1:00:10"}
369
+ {"current_steps": 369, "total_steps": 390, "loss": 0.3935, "lr": 3.522452516867048e-07, "epoch": 4.7232, "percentage": 94.62, "elapsed_time": "16:49:15", "remaining_time": "0:57:26"}
370
+ {"current_steps": 370, "total_steps": 390, "loss": 0.4018, "lr": 3.1958433701019697e-07, "epoch": 4.736, "percentage": 94.87, "elapsed_time": "16:52:02", "remaining_time": "0:54:42"}
371
+ {"current_steps": 371, "total_steps": 390, "loss": 0.3927, "lr": 2.8850000548115155e-07, "epoch": 4.7488, "percentage": 95.13, "elapsed_time": "16:54:37", "remaining_time": "0:51:57"}
372
+ {"current_steps": 372, "total_steps": 390, "loss": 0.4095, "lr": 2.5899474724174313e-07, "epoch": 4.7616, "percentage": 95.38, "elapsed_time": "16:57:19", "remaining_time": "0:49:13"}
373
+ {"current_steps": 373, "total_steps": 390, "loss": 0.376, "lr": 2.3107092593579905e-07, "epoch": 4.7744, "percentage": 95.64, "elapsed_time": "16:59:57", "remaining_time": "0:46:29"}
374
+ {"current_steps": 374, "total_steps": 390, "loss": 0.3847, "lr": 2.0473077851942858e-07, "epoch": 4.7872, "percentage": 95.9, "elapsed_time": "17:02:33", "remaining_time": "0:43:44"}
375
+ {"current_steps": 375, "total_steps": 390, "loss": 0.3729, "lr": 1.799764150818306e-07, "epoch": 4.8, "percentage": 96.15, "elapsed_time": "17:05:12", "remaining_time": "0:41:00"}
376
+ {"current_steps": 376, "total_steps": 390, "loss": 0.3982, "lr": 1.5680981867625566e-07, "epoch": 4.8128, "percentage": 96.41, "elapsed_time": "17:07:47", "remaining_time": "0:38:16"}
377
+ {"current_steps": 377, "total_steps": 390, "loss": 0.3784, "lr": 1.3523284516113955e-07, "epoch": 4.8256, "percentage": 96.67, "elapsed_time": "17:10:28", "remaining_time": "0:35:32"}
378
+ {"current_steps": 378, "total_steps": 390, "loss": 0.4079, "lr": 1.1524722305144231e-07, "epoch": 4.8384, "percentage": 96.92, "elapsed_time": "17:13:12", "remaining_time": "0:32:48"}
379
+ {"current_steps": 379, "total_steps": 390, "loss": 0.3764, "lr": 9.685455338016347e-08, "epoch": 4.8512, "percentage": 97.18, "elapsed_time": "17:15:58", "remaining_time": "0:30:04"}
380
+ {"current_steps": 380, "total_steps": 390, "loss": 0.3743, "lr": 8.005630957010014e-08, "epoch": 4.864, "percentage": 97.44, "elapsed_time": "17:18:42", "remaining_time": "0:27:20"}
381
+ {"current_steps": 381, "total_steps": 390, "loss": 0.4045, "lr": 6.485383731580142e-08, "epoch": 4.8768, "percentage": 97.69, "elapsed_time": "17:21:14", "remaining_time": "0:24:35"}
382
+ {"current_steps": 382, "total_steps": 390, "loss": 0.3862, "lr": 5.1248354475768034e-08, "epoch": 4.8896, "percentage": 97.95, "elapsed_time": "17:23:43", "remaining_time": "0:21:51"}
383
+ {"current_steps": 383, "total_steps": 390, "loss": 0.3849, "lr": 3.924095097489922e-08, "epoch": 4.9024, "percentage": 98.21, "elapsed_time": "17:26:17", "remaining_time": "0:19:07"}
384
+ {"current_steps": 384, "total_steps": 390, "loss": 0.3988, "lr": 2.8832588717164766e-08, "epoch": 4.9152000000000005, "percentage": 98.46, "elapsed_time": "17:29:03", "remaining_time": "0:16:23"}
385
+ {"current_steps": 385, "total_steps": 390, "loss": 0.3819, "lr": 2.0024101508555604e-08, "epoch": 4.928, "percentage": 98.72, "elapsed_time": "17:31:39", "remaining_time": "0:13:39"}
386
+ {"current_steps": 386, "total_steps": 390, "loss": 0.3758, "lr": 1.281619499029274e-08, "epoch": 4.9408, "percentage": 98.97, "elapsed_time": "17:34:22", "remaining_time": "0:10:55"}
387
+ {"current_steps": 387, "total_steps": 390, "loss": 0.3957, "lr": 7.209446582292501e-09, "epoch": 4.9536, "percentage": 99.23, "elapsed_time": "17:37:04", "remaining_time": "0:08:11"}
388
+ {"current_steps": 388, "total_steps": 390, "loss": 0.3957, "lr": 3.2043054369057523e-09, "epoch": 4.9664, "percentage": 99.49, "elapsed_time": "17:39:49", "remaining_time": "0:05:27"}
389
+ {"current_steps": 389, "total_steps": 390, "loss": 0.4052, "lr": 8.010924029533406e-10, "epoch": 4.9792, "percentage": 99.74, "elapsed_time": "17:42:33", "remaining_time": "0:02:43"}
390
+ {"current_steps": 390, "total_steps": 390, "loss": 0.3819, "lr": 0.0, "epoch": 4.992, "percentage": 100.0, "elapsed_time": "17:45:12", "remaining_time": "0:00:00"}
391
+ {"current_steps": 390, "total_steps": 390, "epoch": 4.992, "percentage": 100.0, "elapsed_time": "17:46:59", "remaining_time": "0:00:00"}