ryanmarten commited on
Commit
6ffcc45
·
verified ·
1 Parent(s): df436c5

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 sha256:0313b120a4e40ca2120b24dac64233fca391d8075df7ea04a0296485ed46ff0b
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a562707fc6ff67d461c458ae828914f3707bb0c849728310e6231c27fdea337
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7fd14e36c1f913c056bd765fddc04809ba1ec0de175dccb3247a537c1eb59129
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b979c212971738be25d8c2ccadc4d8d37f6d4678fbb552b6a280f2f4332d2883
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:63920e10945c12dc18011c796f26e51e1ade988be362b473fa1d5574bfaa6eb7
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84b8c9c3ac49b3a74f64ae3341b57fdab5fb0556efb01e43ccf11b1dd06c51c6
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:479eb3b84a5f04443277671330ce14ee8134cbb7b43f9c51a1b58c1afeef91eb
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de0f9b12a167fe0e311f4e7d4d9b54e83b30c5cbaf7db7c2222e52718df52736
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -312,3 +312,80 @@
312
  {"current_steps": 312, "total_steps": 390, "loss": 0.4352, "lr": 4.679111137620442e-06, "epoch": 3.9936, "percentage": 80.0, "elapsed_time": "14:09:38", "remaining_time": "3:32:24"}
313
  {"current_steps": 313, "total_steps": 390, "loss": 0.401, "lr": 4.5646621393177e-06, "epoch": 4.0064, "percentage": 80.26, "elapsed_time": "14:13:14", "remaining_time": "3:29:54"}
314
  {"current_steps": 314, "total_steps": 390, "loss": 0.3838, "lr": 4.451449654204685e-06, "epoch": 4.0192, "percentage": 80.51, "elapsed_time": "14:15:42", "remaining_time": "3:27:06"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
312
  {"current_steps": 312, "total_steps": 390, "loss": 0.4352, "lr": 4.679111137620442e-06, "epoch": 3.9936, "percentage": 80.0, "elapsed_time": "14:09:38", "remaining_time": "3:32:24"}
313
  {"current_steps": 313, "total_steps": 390, "loss": 0.401, "lr": 4.5646621393177e-06, "epoch": 4.0064, "percentage": 80.26, "elapsed_time": "14:13:14", "remaining_time": "3:29:54"}
314
  {"current_steps": 314, "total_steps": 390, "loss": 0.3838, "lr": 4.451449654204685e-06, "epoch": 4.0192, "percentage": 80.51, "elapsed_time": "14:15:42", "remaining_time": "3:27:06"}
315
+ {"current_steps": 315, "total_steps": 390, "loss": 0.3786, "lr": 4.339482751647557e-06, "epoch": 4.032, "percentage": 80.77, "elapsed_time": "14:18:12", "remaining_time": "3:24:20"}
316
+ {"current_steps": 316, "total_steps": 390, "loss": 0.3871, "lr": 4.228770401229824e-06, "epoch": 4.0448, "percentage": 81.03, "elapsed_time": "14:20:52", "remaining_time": "3:21:35"}
317
+ {"current_steps": 317, "total_steps": 390, "loss": 0.3781, "lr": 4.119321472033779e-06, "epoch": 4.0576, "percentage": 81.28, "elapsed_time": "14:23:35", "remaining_time": "3:18:52"}
318
+ {"current_steps": 318, "total_steps": 390, "loss": 0.3754, "lr": 4.011144731929981e-06, "epoch": 4.0704, "percentage": 81.54, "elapsed_time": "14:26:15", "remaining_time": "3:16:08"}
319
+ {"current_steps": 319, "total_steps": 390, "loss": 0.3787, "lr": 3.904248846874894e-06, "epoch": 4.0832, "percentage": 81.79, "elapsed_time": "14:29:04", "remaining_time": "3:13:25"}
320
+ {"current_steps": 320, "total_steps": 390, "loss": 0.386, "lr": 3.7986423802166705e-06, "epoch": 4.096, "percentage": 82.05, "elapsed_time": "14:31:47", "remaining_time": "3:10:42"}
321
+ {"current_steps": 321, "total_steps": 390, "loss": 0.3761, "lr": 3.694333792009115e-06, "epoch": 4.1088, "percentage": 82.31, "elapsed_time": "14:34:40", "remaining_time": "3:08:00"}
322
+ {"current_steps": 322, "total_steps": 390, "loss": 0.3821, "lr": 3.5913314383339937e-06, "epoch": 4.1216, "percentage": 82.56, "elapsed_time": "14:37:32", "remaining_time": "3:05:19"}
323
+ {"current_steps": 323, "total_steps": 390, "loss": 0.3621, "lr": 3.4896435706316e-06, "epoch": 4.1344, "percentage": 82.82, "elapsed_time": "14:40:25", "remaining_time": "3:02:37"}
324
+ {"current_steps": 324, "total_steps": 390, "loss": 0.3838, "lr": 3.3892783350397675e-06, "epoch": 4.1472, "percentage": 83.08, "elapsed_time": "14:43:10", "remaining_time": "2:59:54"}
325
+ {"current_steps": 325, "total_steps": 390, "loss": 0.3896, "lr": 3.290243771741275e-06, "epoch": 4.16, "percentage": 83.33, "elapsed_time": "14:46:08", "remaining_time": "2:57:13"}
326
+ {"current_steps": 326, "total_steps": 390, "loss": 0.3766, "lr": 3.1925478143197418e-06, "epoch": 4.1728, "percentage": 83.59, "elapsed_time": "14:48:51", "remaining_time": "2:54:29"}
327
+ {"current_steps": 327, "total_steps": 390, "loss": 0.3752, "lr": 3.0961982891241083e-06, "epoch": 4.1856, "percentage": 83.85, "elapsed_time": "14:51:48", "remaining_time": "2:51:48"}
328
+ {"current_steps": 328, "total_steps": 390, "loss": 0.3891, "lr": 3.001202914641628e-06, "epoch": 4.1984, "percentage": 84.1, "elapsed_time": "14:54:22", "remaining_time": "2:49:03"}
329
+ {"current_steps": 329, "total_steps": 390, "loss": 0.3657, "lr": 2.907569300879596e-06, "epoch": 4.2112, "percentage": 84.36, "elapsed_time": "14:56:57", "remaining_time": "2:46:18"}
330
+ {"current_steps": 330, "total_steps": 390, "loss": 0.3812, "lr": 2.815304948755664e-06, "epoch": 4.224, "percentage": 84.62, "elapsed_time": "14:59:49", "remaining_time": "2:43:36"}
331
+ {"current_steps": 331, "total_steps": 390, "loss": 0.3761, "lr": 2.7244172494969978e-06, "epoch": 4.2368, "percentage": 84.87, "elapsed_time": "15:02:40", "remaining_time": "2:40:53"}
332
+ {"current_steps": 332, "total_steps": 390, "loss": 0.3857, "lr": 2.6349134840481294e-06, "epoch": 4.2496, "percentage": 85.13, "elapsed_time": "15:05:24", "remaining_time": "2:38:10"}
333
+ {"current_steps": 333, "total_steps": 390, "loss": 0.3816, "lr": 2.546800822487714e-06, "epoch": 4.2624, "percentage": 85.38, "elapsed_time": "15:08:07", "remaining_time": "2:35:26"}
334
+ {"current_steps": 334, "total_steps": 390, "loss": 0.368, "lr": 2.4600863234541338e-06, "epoch": 4.2752, "percentage": 85.64, "elapsed_time": "15:10:53", "remaining_time": "2:32:43"}
335
+ {"current_steps": 335, "total_steps": 390, "loss": 0.3918, "lr": 2.374776933580025e-06, "epoch": 4.288, "percentage": 85.9, "elapsed_time": "15:13:37", "remaining_time": "2:29:59"}
336
+ {"current_steps": 336, "total_steps": 390, "loss": 0.369, "lr": 2.2908794869358044e-06, "epoch": 4.3008, "percentage": 86.15, "elapsed_time": "15:16:12", "remaining_time": "2:27:14"}
337
+ {"current_steps": 337, "total_steps": 390, "loss": 0.3684, "lr": 2.2084007044821764e-06, "epoch": 4.3136, "percentage": 86.41, "elapsed_time": "15:19:02", "remaining_time": "2:24:32"}
338
+ {"current_steps": 338, "total_steps": 390, "loss": 0.3681, "lr": 2.127347193531757e-06, "epoch": 4.3264, "percentage": 86.67, "elapsed_time": "15:21:41", "remaining_time": "2:21:47"}
339
+ {"current_steps": 339, "total_steps": 390, "loss": 0.379, "lr": 2.0477254472197237e-06, "epoch": 4.3392, "percentage": 86.92, "elapsed_time": "15:24:21", "remaining_time": "2:19:03"}
340
+ {"current_steps": 340, "total_steps": 390, "loss": 0.3676, "lr": 1.96954184398368e-06, "epoch": 4.352, "percentage": 87.18, "elapsed_time": "15:26:59", "remaining_time": "2:16:19"}
341
+ {"current_steps": 341, "total_steps": 390, "loss": 0.3894, "lr": 1.8928026470526917e-06, "epoch": 4.3648, "percentage": 87.44, "elapsed_time": "15:29:36", "remaining_time": "2:13:34"}
342
+ {"current_steps": 342, "total_steps": 390, "loss": 0.3614, "lr": 1.817514003945524e-06, "epoch": 4.3776, "percentage": 87.69, "elapsed_time": "15:32:18", "remaining_time": "2:10:51"}
343
+ {"current_steps": 343, "total_steps": 390, "loss": 0.3917, "lr": 1.743681945978184e-06, "epoch": 4.3904, "percentage": 87.95, "elapsed_time": "15:35:10", "remaining_time": "2:08:08"}
344
+ {"current_steps": 344, "total_steps": 390, "loss": 0.3712, "lr": 1.6713123877807413e-06, "epoch": 4.4032, "percentage": 88.21, "elapsed_time": "15:37:39", "remaining_time": "2:05:23"}
345
+ {"current_steps": 345, "total_steps": 390, "loss": 0.3683, "lr": 1.6004111268235156e-06, "epoch": 4.416, "percentage": 88.46, "elapsed_time": "15:40:24", "remaining_time": "2:02:39"}
346
+ {"current_steps": 346, "total_steps": 390, "loss": 0.3618, "lr": 1.5309838429526714e-06, "epoch": 4.4288, "percentage": 88.72, "elapsed_time": "15:42:57", "remaining_time": "1:59:54"}
347
+ {"current_steps": 347, "total_steps": 390, "loss": 0.3729, "lr": 1.4630360979351644e-06, "epoch": 4.4416, "percentage": 88.97, "elapsed_time": "15:45:37", "remaining_time": "1:57:10"}
348
+ {"current_steps": 348, "total_steps": 390, "loss": 0.3835, "lr": 1.396573335013236e-06, "epoch": 4.4544, "percentage": 89.23, "elapsed_time": "15:48:09", "remaining_time": "1:54:26"}
349
+ {"current_steps": 349, "total_steps": 390, "loss": 0.3853, "lr": 1.3316008784683265e-06, "epoch": 4.4672, "percentage": 89.49, "elapsed_time": "15:50:55", "remaining_time": "1:51:42"}
350
+ {"current_steps": 350, "total_steps": 390, "loss": 0.3675, "lr": 1.2681239331945695e-06, "epoch": 4.48, "percentage": 89.74, "elapsed_time": "15:53:33", "remaining_time": "1:48:58"}
351
+ {"current_steps": 351, "total_steps": 390, "loss": 0.3786, "lr": 1.2061475842818337e-06, "epoch": 4.4928, "percentage": 90.0, "elapsed_time": "15:56:08", "remaining_time": "1:46:14"}
352
+ {"current_steps": 352, "total_steps": 390, "loss": 0.3796, "lr": 1.1456767966083393e-06, "epoch": 4.5056, "percentage": 90.26, "elapsed_time": "15:58:55", "remaining_time": "1:43:31"}
353
+ {"current_steps": 353, "total_steps": 390, "loss": 0.3947, "lr": 1.086716414442952e-06, "epoch": 4.5184, "percentage": 90.51, "elapsed_time": "16:01:40", "remaining_time": "1:40:47"}
354
+ {"current_steps": 354, "total_steps": 390, "loss": 0.3686, "lr": 1.0292711610570904e-06, "epoch": 4.5312, "percentage": 90.77, "elapsed_time": "16:04:25", "remaining_time": "1:38:04"}
355
+ {"current_steps": 355, "total_steps": 390, "loss": 0.3921, "lr": 9.733456383463658e-07, "epoch": 4.5440000000000005, "percentage": 91.03, "elapsed_time": "16:07:02", "remaining_time": "1:35:20"}
356
+ {"current_steps": 356, "total_steps": 390, "loss": 0.3593, "lr": 9.189443264619102e-07, "epoch": 4.5568, "percentage": 91.28, "elapsed_time": "16:09:48", "remaining_time": "1:32:37"}
357
+ {"current_steps": 357, "total_steps": 390, "loss": 0.3725, "lr": 8.660715834514977e-07, "epoch": 4.5696, "percentage": 91.54, "elapsed_time": "16:12:37", "remaining_time": "1:29:54"}
358
+ {"current_steps": 358, "total_steps": 390, "loss": 0.3839, "lr": 8.147316449103959e-07, "epoch": 4.5824, "percentage": 91.79, "elapsed_time": "16:15:20", "remaining_time": "1:27:10"}
359
+ {"current_steps": 359, "total_steps": 390, "loss": 0.3895, "lr": 7.649286236420806e-07, "epoch": 4.5952, "percentage": 92.05, "elapsed_time": "16:18:10", "remaining_time": "1:24:28"}
360
+ {"current_steps": 360, "total_steps": 390, "loss": 0.3761, "lr": 7.166665093287539e-07, "epoch": 4.608, "percentage": 92.31, "elapsed_time": "16:20:48", "remaining_time": "1:21:44"}
361
+ {"current_steps": 361, "total_steps": 390, "loss": 0.3809, "lr": 6.69949168211721e-07, "epoch": 4.6208, "percentage": 92.56, "elapsed_time": "16:23:30", "remaining_time": "1:19:00"}
362
+ {"current_steps": 362, "total_steps": 390, "loss": 0.3765, "lr": 6.247803427816945e-07, "epoch": 4.6336, "percentage": 92.82, "elapsed_time": "16:26:16", "remaining_time": "1:16:17"}
363
+ {"current_steps": 363, "total_steps": 390, "loss": 0.387, "lr": 5.811636514789598e-07, "epoch": 4.6464, "percentage": 93.08, "elapsed_time": "16:28:57", "remaining_time": "1:13:33"}
364
+ {"current_steps": 364, "total_steps": 390, "loss": 0.3805, "lr": 5.391025884035239e-07, "epoch": 4.6592, "percentage": 93.33, "elapsed_time": "16:31:33", "remaining_time": "1:10:49"}
365
+ {"current_steps": 365, "total_steps": 390, "loss": 0.3658, "lr": 4.986005230351954e-07, "epoch": 4.672, "percentage": 93.59, "elapsed_time": "16:34:17", "remaining_time": "1:08:06"}
366
+ {"current_steps": 366, "total_steps": 390, "loss": 0.3825, "lr": 4.5966069996365993e-07, "epoch": 4.6848, "percentage": 93.85, "elapsed_time": "16:36:41", "remaining_time": "1:05:21"}
367
+ {"current_steps": 367, "total_steps": 390, "loss": 0.3739, "lr": 4.22286238628562e-07, "epoch": 4.6975999999999996, "percentage": 94.1, "elapsed_time": "16:39:24", "remaining_time": "1:02:37"}
368
+ {"current_steps": 368, "total_steps": 390, "loss": 0.3764, "lr": 3.8648013306960664e-07, "epoch": 4.7104, "percentage": 94.36, "elapsed_time": "16:42:11", "remaining_time": "0:59:54"}
369
+ {"current_steps": 369, "total_steps": 390, "loss": 0.3815, "lr": 3.522452516867048e-07, "epoch": 4.7232, "percentage": 94.62, "elapsed_time": "16:45:01", "remaining_time": "0:57:11"}
370
+ {"current_steps": 370, "total_steps": 390, "loss": 0.3697, "lr": 3.1958433701019697e-07, "epoch": 4.736, "percentage": 94.87, "elapsed_time": "16:47:50", "remaining_time": "0:54:28"}
371
+ {"current_steps": 371, "total_steps": 390, "loss": 0.3702, "lr": 2.8850000548115155e-07, "epoch": 4.7488, "percentage": 95.13, "elapsed_time": "16:50:34", "remaining_time": "0:51:45"}
372
+ {"current_steps": 372, "total_steps": 390, "loss": 0.3765, "lr": 2.5899474724174313e-07, "epoch": 4.7616, "percentage": 95.38, "elapsed_time": "16:53:09", "remaining_time": "0:49:01"}
373
+ {"current_steps": 373, "total_steps": 390, "loss": 0.3791, "lr": 2.3107092593579905e-07, "epoch": 4.7744, "percentage": 95.64, "elapsed_time": "16:56:02", "remaining_time": "0:46:18"}
374
+ {"current_steps": 374, "total_steps": 390, "loss": 0.3687, "lr": 2.0473077851942858e-07, "epoch": 4.7872, "percentage": 95.9, "elapsed_time": "16:58:50", "remaining_time": "0:43:35"}
375
+ {"current_steps": 375, "total_steps": 390, "loss": 0.3762, "lr": 1.799764150818306e-07, "epoch": 4.8, "percentage": 96.15, "elapsed_time": "17:01:45", "remaining_time": "0:40:52"}
376
+ {"current_steps": 376, "total_steps": 390, "loss": 0.3887, "lr": 1.5680981867625566e-07, "epoch": 4.8128, "percentage": 96.41, "elapsed_time": "17:04:37", "remaining_time": "0:38:09"}
377
+ {"current_steps": 377, "total_steps": 390, "loss": 0.3766, "lr": 1.3523284516113955e-07, "epoch": 4.8256, "percentage": 96.67, "elapsed_time": "17:07:08", "remaining_time": "0:35:25"}
378
+ {"current_steps": 378, "total_steps": 390, "loss": 0.3698, "lr": 1.1524722305144231e-07, "epoch": 4.8384, "percentage": 96.92, "elapsed_time": "17:09:56", "remaining_time": "0:32:41"}
379
+ {"current_steps": 379, "total_steps": 390, "loss": 0.3787, "lr": 9.685455338016347e-08, "epoch": 4.8512, "percentage": 97.18, "elapsed_time": "17:12:22", "remaining_time": "0:29:57"}
380
+ {"current_steps": 380, "total_steps": 390, "loss": 0.3697, "lr": 8.005630957010014e-08, "epoch": 4.864, "percentage": 97.44, "elapsed_time": "17:14:58", "remaining_time": "0:27:14"}
381
+ {"current_steps": 381, "total_steps": 390, "loss": 0.3618, "lr": 6.485383731580142e-08, "epoch": 4.8768, "percentage": 97.69, "elapsed_time": "17:17:42", "remaining_time": "0:24:30"}
382
+ {"current_steps": 382, "total_steps": 390, "loss": 0.3823, "lr": 5.1248354475768034e-08, "epoch": 4.8896, "percentage": 97.95, "elapsed_time": "17:20:32", "remaining_time": "0:21:47"}
383
+ {"current_steps": 383, "total_steps": 390, "loss": 0.3861, "lr": 3.924095097489922e-08, "epoch": 4.9024, "percentage": 98.21, "elapsed_time": "17:23:05", "remaining_time": "0:19:03"}
384
+ {"current_steps": 384, "total_steps": 390, "loss": 0.385, "lr": 2.8832588717164766e-08, "epoch": 4.9152000000000005, "percentage": 98.46, "elapsed_time": "17:25:40", "remaining_time": "0:16:20"}
385
+ {"current_steps": 385, "total_steps": 390, "loss": 0.388, "lr": 2.0024101508555604e-08, "epoch": 4.928, "percentage": 98.72, "elapsed_time": "17:28:30", "remaining_time": "0:13:37"}
386
+ {"current_steps": 386, "total_steps": 390, "loss": 0.3664, "lr": 1.281619499029274e-08, "epoch": 4.9408, "percentage": 98.97, "elapsed_time": "17:31:11", "remaining_time": "0:10:53"}
387
+ {"current_steps": 387, "total_steps": 390, "loss": 0.3869, "lr": 7.209446582292501e-09, "epoch": 4.9536, "percentage": 99.23, "elapsed_time": "17:34:00", "remaining_time": "0:08:10"}
388
+ {"current_steps": 388, "total_steps": 390, "loss": 0.3887, "lr": 3.2043054369057523e-09, "epoch": 4.9664, "percentage": 99.49, "elapsed_time": "17:36:40", "remaining_time": "0:05:26"}
389
+ {"current_steps": 389, "total_steps": 390, "loss": 0.3771, "lr": 8.010924029533406e-10, "epoch": 4.9792, "percentage": 99.74, "elapsed_time": "17:39:15", "remaining_time": "0:02:43"}
390
+ {"current_steps": 390, "total_steps": 390, "loss": 0.3715, "lr": 0.0, "epoch": 4.992, "percentage": 100.0, "elapsed_time": "17:42:00", "remaining_time": "0:00:00"}
391
+ {"current_steps": 390, "total_steps": 390, "epoch": 4.992, "percentage": 100.0, "elapsed_time": "17:43:45", "remaining_time": "0:00:00"}