ryanmarten commited on
Commit
20cc752
·
verified ·
1 Parent(s): 37d2416

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 sha256:71e70def1cfe4c110061d81470435dc7239d8fd6f62a0ad7da9ecdc4ed1f852e
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f71a60e040cfc63dc0769ba14d8737f64c3912b2712112a7a27738dc68aa455
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9195964663a281bf07681f5d1ac2dfc1c79c17262a2c8c005894d6b05fa969b2
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a29f2174093ce8f51e0260a802d4c4c6f017a760fe2d3b544463c82e9010ce19
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:f60a961c9398f76abec5ef4ddbfac2d4fa833bff6c1d72135ce5c481819e8cea
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:194bb531eb4c4f4b520ff95ba873ad686a266466024b5fa2a626d3bea3ae2556
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2060f7132320a353c7ac7b0f857867dd4560ee4c5c59f6d73c0d9f4a92bcd6ad
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:15dbda156697707d8959244c396e678311fe9df6eb11068ec4b86b5d441f97a9
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -312,3 +312,80 @@
312
  {"current_steps": 312, "total_steps": 390, "loss": 0.2458, "lr": 4.679111137620442e-06, "epoch": 3.9936, "percentage": 80.0, "elapsed_time": "7:21:15", "remaining_time": "1:50:18"}
313
  {"current_steps": 313, "total_steps": 390, "loss": 0.2138, "lr": 4.5646621393177e-06, "epoch": 4.0064, "percentage": 80.26, "elapsed_time": "7:23:36", "remaining_time": "1:49:07"}
314
  {"current_steps": 314, "total_steps": 390, "loss": 0.1962, "lr": 4.451449654204685e-06, "epoch": 4.0192, "percentage": 80.51, "elapsed_time": "7:25:08", "remaining_time": "1:47:44"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
312
  {"current_steps": 312, "total_steps": 390, "loss": 0.2458, "lr": 4.679111137620442e-06, "epoch": 3.9936, "percentage": 80.0, "elapsed_time": "7:21:15", "remaining_time": "1:50:18"}
313
  {"current_steps": 313, "total_steps": 390, "loss": 0.2138, "lr": 4.5646621393177e-06, "epoch": 4.0064, "percentage": 80.26, "elapsed_time": "7:23:36", "remaining_time": "1:49:07"}
314
  {"current_steps": 314, "total_steps": 390, "loss": 0.1962, "lr": 4.451449654204685e-06, "epoch": 4.0192, "percentage": 80.51, "elapsed_time": "7:25:08", "remaining_time": "1:47:44"}
315
+ {"current_steps": 315, "total_steps": 390, "loss": 0.1998, "lr": 4.339482751647557e-06, "epoch": 4.032, "percentage": 80.77, "elapsed_time": "7:26:27", "remaining_time": "1:46:17"}
316
+ {"current_steps": 316, "total_steps": 390, "loss": 0.1673, "lr": 4.228770401229824e-06, "epoch": 4.0448, "percentage": 81.03, "elapsed_time": "7:27:46", "remaining_time": "1:44:51"}
317
+ {"current_steps": 317, "total_steps": 390, "loss": 0.1973, "lr": 4.119321472033779e-06, "epoch": 4.0576, "percentage": 81.28, "elapsed_time": "7:29:22", "remaining_time": "1:43:29"}
318
+ {"current_steps": 318, "total_steps": 390, "loss": 0.198, "lr": 4.011144731929981e-06, "epoch": 4.0704, "percentage": 81.54, "elapsed_time": "7:30:49", "remaining_time": "1:42:04"}
319
+ {"current_steps": 319, "total_steps": 390, "loss": 0.1846, "lr": 3.904248846874894e-06, "epoch": 4.0832, "percentage": 81.79, "elapsed_time": "7:32:08", "remaining_time": "1:40:38"}
320
+ {"current_steps": 320, "total_steps": 390, "loss": 0.2104, "lr": 3.7986423802166705e-06, "epoch": 4.096, "percentage": 82.05, "elapsed_time": "7:33:47", "remaining_time": "1:39:16"}
321
+ {"current_steps": 321, "total_steps": 390, "loss": 0.1738, "lr": 3.694333792009115e-06, "epoch": 4.1088, "percentage": 82.31, "elapsed_time": "7:35:11", "remaining_time": "1:37:50"}
322
+ {"current_steps": 322, "total_steps": 390, "loss": 0.1564, "lr": 3.5913314383339937e-06, "epoch": 4.1216, "percentage": 82.56, "elapsed_time": "7:36:26", "remaining_time": "1:36:23"}
323
+ {"current_steps": 323, "total_steps": 390, "loss": 0.1881, "lr": 3.4896435706316e-06, "epoch": 4.1344, "percentage": 82.82, "elapsed_time": "7:37:55", "remaining_time": "1:34:59"}
324
+ {"current_steps": 324, "total_steps": 390, "loss": 0.1909, "lr": 3.3892783350397675e-06, "epoch": 4.1472, "percentage": 83.08, "elapsed_time": "7:39:23", "remaining_time": "1:33:34"}
325
+ {"current_steps": 325, "total_steps": 390, "loss": 0.1797, "lr": 3.290243771741275e-06, "epoch": 4.16, "percentage": 83.33, "elapsed_time": "7:40:53", "remaining_time": "1:32:10"}
326
+ {"current_steps": 326, "total_steps": 390, "loss": 0.1912, "lr": 3.1925478143197418e-06, "epoch": 4.1728, "percentage": 83.59, "elapsed_time": "7:42:12", "remaining_time": "1:30:44"}
327
+ {"current_steps": 327, "total_steps": 390, "loss": 0.1935, "lr": 3.0961982891241083e-06, "epoch": 4.1856, "percentage": 83.85, "elapsed_time": "7:43:37", "remaining_time": "1:29:19"}
328
+ {"current_steps": 328, "total_steps": 390, "loss": 0.1738, "lr": 3.001202914641628e-06, "epoch": 4.1984, "percentage": 84.1, "elapsed_time": "7:44:55", "remaining_time": "1:27:52"}
329
+ {"current_steps": 329, "total_steps": 390, "loss": 0.1667, "lr": 2.907569300879596e-06, "epoch": 4.2112, "percentage": 84.36, "elapsed_time": "7:46:00", "remaining_time": "1:26:24"}
330
+ {"current_steps": 330, "total_steps": 390, "loss": 0.1739, "lr": 2.815304948755664e-06, "epoch": 4.224, "percentage": 84.62, "elapsed_time": "7:47:26", "remaining_time": "1:24:59"}
331
+ {"current_steps": 331, "total_steps": 390, "loss": 0.1841, "lr": 2.7244172494969978e-06, "epoch": 4.2368, "percentage": 84.87, "elapsed_time": "7:48:50", "remaining_time": "1:23:34"}
332
+ {"current_steps": 332, "total_steps": 390, "loss": 0.1831, "lr": 2.6349134840481294e-06, "epoch": 4.2496, "percentage": 85.13, "elapsed_time": "7:50:17", "remaining_time": "1:22:09"}
333
+ {"current_steps": 333, "total_steps": 390, "loss": 0.186, "lr": 2.546800822487714e-06, "epoch": 4.2624, "percentage": 85.38, "elapsed_time": "7:51:34", "remaining_time": "1:20:43"}
334
+ {"current_steps": 334, "total_steps": 390, "loss": 0.1797, "lr": 2.4600863234541338e-06, "epoch": 4.2752, "percentage": 85.64, "elapsed_time": "7:52:59", "remaining_time": "1:19:18"}
335
+ {"current_steps": 335, "total_steps": 390, "loss": 0.207, "lr": 2.374776933580025e-06, "epoch": 4.288, "percentage": 85.9, "elapsed_time": "7:54:25", "remaining_time": "1:17:53"}
336
+ {"current_steps": 336, "total_steps": 390, "loss": 0.193, "lr": 2.2908794869358044e-06, "epoch": 4.3008, "percentage": 86.15, "elapsed_time": "7:55:56", "remaining_time": "1:16:29"}
337
+ {"current_steps": 337, "total_steps": 390, "loss": 0.1853, "lr": 2.2084007044821764e-06, "epoch": 4.3136, "percentage": 86.41, "elapsed_time": "7:57:33", "remaining_time": "1:15:06"}
338
+ {"current_steps": 338, "total_steps": 390, "loss": 0.1656, "lr": 2.127347193531757e-06, "epoch": 4.3264, "percentage": 86.67, "elapsed_time": "7:58:52", "remaining_time": "1:13:40"}
339
+ {"current_steps": 339, "total_steps": 390, "loss": 0.171, "lr": 2.0477254472197237e-06, "epoch": 4.3392, "percentage": 86.92, "elapsed_time": "8:00:22", "remaining_time": "1:12:16"}
340
+ {"current_steps": 340, "total_steps": 390, "loss": 0.192, "lr": 1.96954184398368e-06, "epoch": 4.352, "percentage": 87.18, "elapsed_time": "8:01:54", "remaining_time": "1:10:52"}
341
+ {"current_steps": 341, "total_steps": 390, "loss": 0.1748, "lr": 1.8928026470526917e-06, "epoch": 4.3648, "percentage": 87.44, "elapsed_time": "8:03:14", "remaining_time": "1:09:26"}
342
+ {"current_steps": 342, "total_steps": 390, "loss": 0.1786, "lr": 1.817514003945524e-06, "epoch": 4.3776, "percentage": 87.69, "elapsed_time": "8:04:43", "remaining_time": "1:08:01"}
343
+ {"current_steps": 343, "total_steps": 390, "loss": 0.1764, "lr": 1.743681945978184e-06, "epoch": 4.3904, "percentage": 87.95, "elapsed_time": "8:06:10", "remaining_time": "1:06:37"}
344
+ {"current_steps": 344, "total_steps": 390, "loss": 0.1891, "lr": 1.6713123877807413e-06, "epoch": 4.4032, "percentage": 88.21, "elapsed_time": "8:07:35", "remaining_time": "1:05:12"}
345
+ {"current_steps": 345, "total_steps": 390, "loss": 0.159, "lr": 1.6004111268235156e-06, "epoch": 4.416, "percentage": 88.46, "elapsed_time": "8:08:50", "remaining_time": "1:03:45"}
346
+ {"current_steps": 346, "total_steps": 390, "loss": 0.1711, "lr": 1.5309838429526714e-06, "epoch": 4.4288, "percentage": 88.72, "elapsed_time": "8:10:04", "remaining_time": "1:02:19"}
347
+ {"current_steps": 347, "total_steps": 390, "loss": 0.1812, "lr": 1.4630360979351644e-06, "epoch": 4.4416, "percentage": 88.97, "elapsed_time": "8:11:25", "remaining_time": "1:00:53"}
348
+ {"current_steps": 348, "total_steps": 390, "loss": 0.1901, "lr": 1.396573335013236e-06, "epoch": 4.4544, "percentage": 89.23, "elapsed_time": "8:12:56", "remaining_time": "0:59:29"}
349
+ {"current_steps": 349, "total_steps": 390, "loss": 0.1785, "lr": 1.3316008784683265e-06, "epoch": 4.4672, "percentage": 89.49, "elapsed_time": "8:14:07", "remaining_time": "0:58:02"}
350
+ {"current_steps": 350, "total_steps": 390, "loss": 0.1915, "lr": 1.2681239331945695e-06, "epoch": 4.48, "percentage": 89.74, "elapsed_time": "8:15:31", "remaining_time": "0:56:37"}
351
+ {"current_steps": 351, "total_steps": 390, "loss": 0.1843, "lr": 1.2061475842818337e-06, "epoch": 4.4928, "percentage": 90.0, "elapsed_time": "8:16:54", "remaining_time": "0:55:12"}
352
+ {"current_steps": 352, "total_steps": 390, "loss": 0.1543, "lr": 1.1456767966083393e-06, "epoch": 4.5056, "percentage": 90.26, "elapsed_time": "8:18:15", "remaining_time": "0:53:47"}
353
+ {"current_steps": 353, "total_steps": 390, "loss": 0.197, "lr": 1.086716414442952e-06, "epoch": 4.5184, "percentage": 90.51, "elapsed_time": "8:19:44", "remaining_time": "0:52:22"}
354
+ {"current_steps": 354, "total_steps": 390, "loss": 0.1775, "lr": 1.0292711610570904e-06, "epoch": 4.5312, "percentage": 90.77, "elapsed_time": "8:21:04", "remaining_time": "0:50:57"}
355
+ {"current_steps": 355, "total_steps": 390, "loss": 0.1881, "lr": 9.733456383463658e-07, "epoch": 4.5440000000000005, "percentage": 91.03, "elapsed_time": "8:22:36", "remaining_time": "0:49:33"}
356
+ {"current_steps": 356, "total_steps": 390, "loss": 0.177, "lr": 9.189443264619102e-07, "epoch": 4.5568, "percentage": 91.28, "elapsed_time": "8:23:51", "remaining_time": "0:48:07"}
357
+ {"current_steps": 357, "total_steps": 390, "loss": 0.1703, "lr": 8.660715834514977e-07, "epoch": 4.5696, "percentage": 91.54, "elapsed_time": "8:25:21", "remaining_time": "0:46:42"}
358
+ {"current_steps": 358, "total_steps": 390, "loss": 0.2016, "lr": 8.147316449103959e-07, "epoch": 4.5824, "percentage": 91.79, "elapsed_time": "8:27:03", "remaining_time": "0:45:19"}
359
+ {"current_steps": 359, "total_steps": 390, "loss": 0.1976, "lr": 7.649286236420806e-07, "epoch": 4.5952, "percentage": 92.05, "elapsed_time": "8:28:31", "remaining_time": "0:43:54"}
360
+ {"current_steps": 360, "total_steps": 390, "loss": 0.1684, "lr": 7.166665093287539e-07, "epoch": 4.608, "percentage": 92.31, "elapsed_time": "8:29:47", "remaining_time": "0:42:28"}
361
+ {"current_steps": 361, "total_steps": 390, "loss": 0.1792, "lr": 6.69949168211721e-07, "epoch": 4.6208, "percentage": 92.56, "elapsed_time": "8:31:10", "remaining_time": "0:41:03"}
362
+ {"current_steps": 362, "total_steps": 390, "loss": 0.1775, "lr": 6.247803427816945e-07, "epoch": 4.6336, "percentage": 92.82, "elapsed_time": "8:32:34", "remaining_time": "0:39:38"}
363
+ {"current_steps": 363, "total_steps": 390, "loss": 0.1692, "lr": 5.811636514789598e-07, "epoch": 4.6464, "percentage": 93.08, "elapsed_time": "8:34:02", "remaining_time": "0:38:14"}
364
+ {"current_steps": 364, "total_steps": 390, "loss": 0.1695, "lr": 5.391025884035239e-07, "epoch": 4.6592, "percentage": 93.33, "elapsed_time": "8:35:18", "remaining_time": "0:36:48"}
365
+ {"current_steps": 365, "total_steps": 390, "loss": 0.1655, "lr": 4.986005230351954e-07, "epoch": 4.672, "percentage": 93.59, "elapsed_time": "8:36:38", "remaining_time": "0:35:23"}
366
+ {"current_steps": 366, "total_steps": 390, "loss": 0.1718, "lr": 4.5966069996365993e-07, "epoch": 4.6848, "percentage": 93.85, "elapsed_time": "8:38:02", "remaining_time": "0:33:58"}
367
+ {"current_steps": 367, "total_steps": 390, "loss": 0.1832, "lr": 4.22286238628562e-07, "epoch": 4.6975999999999996, "percentage": 94.1, "elapsed_time": "8:39:21", "remaining_time": "0:32:32"}
368
+ {"current_steps": 368, "total_steps": 390, "loss": 0.1742, "lr": 3.8648013306960664e-07, "epoch": 4.7104, "percentage": 94.36, "elapsed_time": "8:40:44", "remaining_time": "0:31:07"}
369
+ {"current_steps": 369, "total_steps": 390, "loss": 0.1609, "lr": 3.522452516867048e-07, "epoch": 4.7232, "percentage": 94.62, "elapsed_time": "8:42:00", "remaining_time": "0:29:42"}
370
+ {"current_steps": 370, "total_steps": 390, "loss": 0.1932, "lr": 3.1958433701019697e-07, "epoch": 4.736, "percentage": 94.87, "elapsed_time": "8:43:33", "remaining_time": "0:28:18"}
371
+ {"current_steps": 371, "total_steps": 390, "loss": 0.1811, "lr": 2.8850000548115155e-07, "epoch": 4.7488, "percentage": 95.13, "elapsed_time": "8:44:58", "remaining_time": "0:26:53"}
372
+ {"current_steps": 372, "total_steps": 390, "loss": 0.174, "lr": 2.5899474724174313e-07, "epoch": 4.7616, "percentage": 95.38, "elapsed_time": "8:46:34", "remaining_time": "0:25:28"}
373
+ {"current_steps": 373, "total_steps": 390, "loss": 0.1869, "lr": 2.3107092593579905e-07, "epoch": 4.7744, "percentage": 95.64, "elapsed_time": "8:47:53", "remaining_time": "0:24:03"}
374
+ {"current_steps": 374, "total_steps": 390, "loss": 0.1966, "lr": 2.0473077851942858e-07, "epoch": 4.7872, "percentage": 95.9, "elapsed_time": "8:49:18", "remaining_time": "0:22:38"}
375
+ {"current_steps": 375, "total_steps": 390, "loss": 0.1685, "lr": 1.799764150818306e-07, "epoch": 4.8, "percentage": 96.15, "elapsed_time": "8:50:34", "remaining_time": "0:21:13"}
376
+ {"current_steps": 376, "total_steps": 390, "loss": 0.1747, "lr": 1.5680981867625566e-07, "epoch": 4.8128, "percentage": 96.41, "elapsed_time": "8:51:57", "remaining_time": "0:19:48"}
377
+ {"current_steps": 377, "total_steps": 390, "loss": 0.1769, "lr": 1.3523284516113955e-07, "epoch": 4.8256, "percentage": 96.67, "elapsed_time": "8:53:30", "remaining_time": "0:18:23"}
378
+ {"current_steps": 378, "total_steps": 390, "loss": 0.1819, "lr": 1.1524722305144231e-07, "epoch": 4.8384, "percentage": 96.92, "elapsed_time": "8:54:58", "remaining_time": "0:16:58"}
379
+ {"current_steps": 379, "total_steps": 390, "loss": 0.1851, "lr": 9.685455338016347e-08, "epoch": 4.8512, "percentage": 97.18, "elapsed_time": "8:56:17", "remaining_time": "0:15:33"}
380
+ {"current_steps": 380, "total_steps": 390, "loss": 0.2033, "lr": 8.005630957010014e-08, "epoch": 4.864, "percentage": 97.44, "elapsed_time": "8:57:48", "remaining_time": "0:14:09"}
381
+ {"current_steps": 381, "total_steps": 390, "loss": 0.1928, "lr": 6.485383731580142e-08, "epoch": 4.8768, "percentage": 97.69, "elapsed_time": "8:59:21", "remaining_time": "0:12:44"}
382
+ {"current_steps": 382, "total_steps": 390, "loss": 0.1718, "lr": 5.1248354475768034e-08, "epoch": 4.8896, "percentage": 97.95, "elapsed_time": "9:00:49", "remaining_time": "0:11:19"}
383
+ {"current_steps": 383, "total_steps": 390, "loss": 0.1714, "lr": 3.924095097489922e-08, "epoch": 4.9024, "percentage": 98.21, "elapsed_time": "9:02:17", "remaining_time": "0:09:54"}
384
+ {"current_steps": 384, "total_steps": 390, "loss": 0.1991, "lr": 2.8832588717164766e-08, "epoch": 4.9152000000000005, "percentage": 98.46, "elapsed_time": "9:03:51", "remaining_time": "0:08:29"}
385
+ {"current_steps": 385, "total_steps": 390, "loss": 0.1627, "lr": 2.0024101508555604e-08, "epoch": 4.928, "percentage": 98.72, "elapsed_time": "9:05:05", "remaining_time": "0:07:04"}
386
+ {"current_steps": 386, "total_steps": 390, "loss": 0.1507, "lr": 1.281619499029274e-08, "epoch": 4.9408, "percentage": 98.97, "elapsed_time": "9:06:21", "remaining_time": "0:05:39"}
387
+ {"current_steps": 387, "total_steps": 390, "loss": 0.1865, "lr": 7.209446582292501e-09, "epoch": 4.9536, "percentage": 99.23, "elapsed_time": "9:07:54", "remaining_time": "0:04:14"}
388
+ {"current_steps": 388, "total_steps": 390, "loss": 0.1715, "lr": 3.2043054369057523e-09, "epoch": 4.9664, "percentage": 99.49, "elapsed_time": "9:09:22", "remaining_time": "0:02:49"}
389
+ {"current_steps": 389, "total_steps": 390, "loss": 0.1972, "lr": 8.010924029533406e-10, "epoch": 4.9792, "percentage": 99.74, "elapsed_time": "9:10:48", "remaining_time": "0:01:24"}
390
+ {"current_steps": 390, "total_steps": 390, "loss": 0.1909, "lr": 0.0, "epoch": 4.992, "percentage": 100.0, "elapsed_time": "9:12:08", "remaining_time": "0:00:00"}
391
+ {"current_steps": 390, "total_steps": 390, "epoch": 4.992, "percentage": 100.0, "elapsed_time": "9:13:47", "remaining_time": "0:00:00"}