ryanmarten commited on
Commit
47482f0
·
verified ·
1 Parent(s): 623114f

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 sha256:39d6b3d620bbb72301429c850a9f82d91057e51a72a944b70e5e6bb379074f9b
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4b4d1503c15f007f170307b4cc3777c51bc65e83ed0e2c92e469347ef3a51f1
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:76994eb5918bff84fadd630bfe6beef6896ef9091202b7c964581549ae654dc2
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f96f827eae0d0c46844238c3eb3072e724d2ed57417eb6fa099d54b68e394d9
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:08a20303d78612b599dc0df48d90c44c558514ed9216b7081502816c703c5a8d
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:892602aa1b6d5e357f055d3c3ccd1f5f56f56237367a9a7498e8a03eae12f78f
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:d5cd2ab5640f59a883107f0d694728e4aa0f013ca407af22b55031f861a57bd2
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33b8a9cd87a5e74a3a99ace88ab0f0b3c612a5b58b62aafc4ca7c53eacf6c057
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -316,3 +316,76 @@
316
  {"current_steps": 316, "total_steps": 390, "loss": 0.1324, "lr": 4.228770401229824e-06, "epoch": 4.0448, "percentage": 81.03, "elapsed_time": "4:41:23", "remaining_time": "1:05:53"}
317
  {"current_steps": 317, "total_steps": 390, "loss": 0.1354, "lr": 4.119321472033779e-06, "epoch": 4.0576, "percentage": 81.28, "elapsed_time": "4:42:21", "remaining_time": "1:05:01"}
318
  {"current_steps": 318, "total_steps": 390, "loss": 0.1374, "lr": 4.011144731929981e-06, "epoch": 4.0704, "percentage": 81.54, "elapsed_time": "4:43:16", "remaining_time": "1:04:08"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
316
  {"current_steps": 316, "total_steps": 390, "loss": 0.1324, "lr": 4.228770401229824e-06, "epoch": 4.0448, "percentage": 81.03, "elapsed_time": "4:41:23", "remaining_time": "1:05:53"}
317
  {"current_steps": 317, "total_steps": 390, "loss": 0.1354, "lr": 4.119321472033779e-06, "epoch": 4.0576, "percentage": 81.28, "elapsed_time": "4:42:21", "remaining_time": "1:05:01"}
318
  {"current_steps": 318, "total_steps": 390, "loss": 0.1374, "lr": 4.011144731929981e-06, "epoch": 4.0704, "percentage": 81.54, "elapsed_time": "4:43:16", "remaining_time": "1:04:08"}
319
+ {"current_steps": 319, "total_steps": 390, "loss": 0.1503, "lr": 3.904248846874894e-06, "epoch": 4.0832, "percentage": 81.79, "elapsed_time": "4:44:08", "remaining_time": "1:03:14"}
320
+ {"current_steps": 320, "total_steps": 390, "loss": 0.1595, "lr": 3.7986423802166705e-06, "epoch": 4.096, "percentage": 82.05, "elapsed_time": "4:45:01", "remaining_time": "1:02:21"}
321
+ {"current_steps": 321, "total_steps": 390, "loss": 0.1502, "lr": 3.694333792009115e-06, "epoch": 4.1088, "percentage": 82.31, "elapsed_time": "4:45:59", "remaining_time": "1:01:28"}
322
+ {"current_steps": 322, "total_steps": 390, "loss": 0.15, "lr": 3.5913314383339937e-06, "epoch": 4.1216, "percentage": 82.56, "elapsed_time": "4:46:52", "remaining_time": "1:00:34"}
323
+ {"current_steps": 323, "total_steps": 390, "loss": 0.1404, "lr": 3.4896435706316e-06, "epoch": 4.1344, "percentage": 82.82, "elapsed_time": "4:47:47", "remaining_time": "0:59:41"}
324
+ {"current_steps": 324, "total_steps": 390, "loss": 0.1187, "lr": 3.3892783350397675e-06, "epoch": 4.1472, "percentage": 83.08, "elapsed_time": "4:48:40", "remaining_time": "0:58:48"}
325
+ {"current_steps": 325, "total_steps": 390, "loss": 0.1432, "lr": 3.290243771741275e-06, "epoch": 4.16, "percentage": 83.33, "elapsed_time": "4:49:42", "remaining_time": "0:57:56"}
326
+ {"current_steps": 326, "total_steps": 390, "loss": 0.1103, "lr": 3.1925478143197418e-06, "epoch": 4.1728, "percentage": 83.59, "elapsed_time": "4:50:24", "remaining_time": "0:57:00"}
327
+ {"current_steps": 327, "total_steps": 390, "loss": 0.157, "lr": 3.0961982891241083e-06, "epoch": 4.1856, "percentage": 83.85, "elapsed_time": "4:51:23", "remaining_time": "0:56:08"}
328
+ {"current_steps": 328, "total_steps": 390, "loss": 0.1246, "lr": 3.001202914641628e-06, "epoch": 4.1984, "percentage": 84.1, "elapsed_time": "4:52:10", "remaining_time": "0:55:13"}
329
+ {"current_steps": 329, "total_steps": 390, "loss": 0.1198, "lr": 2.907569300879596e-06, "epoch": 4.2112, "percentage": 84.36, "elapsed_time": "4:53:02", "remaining_time": "0:54:19"}
330
+ {"current_steps": 330, "total_steps": 390, "loss": 0.1283, "lr": 2.815304948755664e-06, "epoch": 4.224, "percentage": 84.62, "elapsed_time": "4:53:49", "remaining_time": "0:53:25"}
331
+ {"current_steps": 331, "total_steps": 390, "loss": 0.1648, "lr": 2.7244172494969978e-06, "epoch": 4.2368, "percentage": 84.87, "elapsed_time": "4:54:49", "remaining_time": "0:52:33"}
332
+ {"current_steps": 332, "total_steps": 390, "loss": 0.1231, "lr": 2.6349134840481294e-06, "epoch": 4.2496, "percentage": 85.13, "elapsed_time": "4:55:36", "remaining_time": "0:51:38"}
333
+ {"current_steps": 333, "total_steps": 390, "loss": 0.1239, "lr": 2.546800822487714e-06, "epoch": 4.2624, "percentage": 85.38, "elapsed_time": "4:56:22", "remaining_time": "0:50:43"}
334
+ {"current_steps": 334, "total_steps": 390, "loss": 0.1518, "lr": 2.4600863234541338e-06, "epoch": 4.2752, "percentage": 85.64, "elapsed_time": "4:57:31", "remaining_time": "0:49:53"}
335
+ {"current_steps": 335, "total_steps": 390, "loss": 0.1558, "lr": 2.374776933580025e-06, "epoch": 4.288, "percentage": 85.9, "elapsed_time": "4:58:29", "remaining_time": "0:49:00"}
336
+ {"current_steps": 336, "total_steps": 390, "loss": 0.1419, "lr": 2.2908794869358044e-06, "epoch": 4.3008, "percentage": 86.15, "elapsed_time": "4:59:21", "remaining_time": "0:48:06"}
337
+ {"current_steps": 337, "total_steps": 390, "loss": 0.1175, "lr": 2.2084007044821764e-06, "epoch": 4.3136, "percentage": 86.41, "elapsed_time": "5:00:03", "remaining_time": "0:47:11"}
338
+ {"current_steps": 338, "total_steps": 390, "loss": 0.1366, "lr": 2.127347193531757e-06, "epoch": 4.3264, "percentage": 86.67, "elapsed_time": "5:00:57", "remaining_time": "0:46:18"}
339
+ {"current_steps": 339, "total_steps": 390, "loss": 0.133, "lr": 2.0477254472197237e-06, "epoch": 4.3392, "percentage": 86.92, "elapsed_time": "5:01:52", "remaining_time": "0:45:24"}
340
+ {"current_steps": 340, "total_steps": 390, "loss": 0.1473, "lr": 1.96954184398368e-06, "epoch": 4.352, "percentage": 87.18, "elapsed_time": "5:02:47", "remaining_time": "0:44:31"}
341
+ {"current_steps": 341, "total_steps": 390, "loss": 0.1529, "lr": 1.8928026470526917e-06, "epoch": 4.3648, "percentage": 87.44, "elapsed_time": "5:03:42", "remaining_time": "0:43:38"}
342
+ {"current_steps": 342, "total_steps": 390, "loss": 0.1389, "lr": 1.817514003945524e-06, "epoch": 4.3776, "percentage": 87.69, "elapsed_time": "5:04:33", "remaining_time": "0:42:44"}
343
+ {"current_steps": 343, "total_steps": 390, "loss": 0.1676, "lr": 1.743681945978184e-06, "epoch": 4.3904, "percentage": 87.95, "elapsed_time": "5:05:25", "remaining_time": "0:41:51"}
344
+ {"current_steps": 344, "total_steps": 390, "loss": 0.1264, "lr": 1.6713123877807413e-06, "epoch": 4.4032, "percentage": 88.21, "elapsed_time": "5:06:18", "remaining_time": "0:40:57"}
345
+ {"current_steps": 345, "total_steps": 390, "loss": 0.1754, "lr": 1.6004111268235156e-06, "epoch": 4.416, "percentage": 88.46, "elapsed_time": "5:07:23", "remaining_time": "0:40:05"}
346
+ {"current_steps": 346, "total_steps": 390, "loss": 0.1308, "lr": 1.5309838429526714e-06, "epoch": 4.4288, "percentage": 88.72, "elapsed_time": "5:08:18", "remaining_time": "0:39:12"}
347
+ {"current_steps": 347, "total_steps": 390, "loss": 0.1363, "lr": 1.4630360979351644e-06, "epoch": 4.4416, "percentage": 88.97, "elapsed_time": "5:09:16", "remaining_time": "0:38:19"}
348
+ {"current_steps": 348, "total_steps": 390, "loss": 0.1551, "lr": 1.396573335013236e-06, "epoch": 4.4544, "percentage": 89.23, "elapsed_time": "5:10:27", "remaining_time": "0:37:28"}
349
+ {"current_steps": 349, "total_steps": 390, "loss": 0.1564, "lr": 1.3316008784683265e-06, "epoch": 4.4672, "percentage": 89.49, "elapsed_time": "5:11:25", "remaining_time": "0:36:35"}
350
+ {"current_steps": 350, "total_steps": 390, "loss": 0.1429, "lr": 1.2681239331945695e-06, "epoch": 4.48, "percentage": 89.74, "elapsed_time": "5:12:23", "remaining_time": "0:35:42"}
351
+ {"current_steps": 351, "total_steps": 390, "loss": 0.1276, "lr": 1.2061475842818337e-06, "epoch": 4.4928, "percentage": 90.0, "elapsed_time": "5:13:10", "remaining_time": "0:34:47"}
352
+ {"current_steps": 352, "total_steps": 390, "loss": 0.141, "lr": 1.1456767966083393e-06, "epoch": 4.5056, "percentage": 90.26, "elapsed_time": "5:13:53", "remaining_time": "0:33:53"}
353
+ {"current_steps": 353, "total_steps": 390, "loss": 0.1394, "lr": 1.086716414442952e-06, "epoch": 4.5184, "percentage": 90.51, "elapsed_time": "5:14:46", "remaining_time": "0:32:59"}
354
+ {"current_steps": 354, "total_steps": 390, "loss": 0.1603, "lr": 1.0292711610570904e-06, "epoch": 4.5312, "percentage": 90.77, "elapsed_time": "5:15:44", "remaining_time": "0:32:06"}
355
+ {"current_steps": 355, "total_steps": 390, "loss": 0.1437, "lr": 9.733456383463658e-07, "epoch": 4.5440000000000005, "percentage": 91.03, "elapsed_time": "5:16:46", "remaining_time": "0:31:13"}
356
+ {"current_steps": 356, "total_steps": 390, "loss": 0.1317, "lr": 9.189443264619102e-07, "epoch": 4.5568, "percentage": 91.28, "elapsed_time": "5:17:34", "remaining_time": "0:30:19"}
357
+ {"current_steps": 357, "total_steps": 390, "loss": 0.1242, "lr": 8.660715834514977e-07, "epoch": 4.5696, "percentage": 91.54, "elapsed_time": "5:18:32", "remaining_time": "0:29:26"}
358
+ {"current_steps": 358, "total_steps": 390, "loss": 0.1468, "lr": 8.147316449103959e-07, "epoch": 4.5824, "percentage": 91.79, "elapsed_time": "5:19:34", "remaining_time": "0:28:33"}
359
+ {"current_steps": 359, "total_steps": 390, "loss": 0.1215, "lr": 7.649286236420806e-07, "epoch": 4.5952, "percentage": 92.05, "elapsed_time": "5:20:23", "remaining_time": "0:27:39"}
360
+ {"current_steps": 360, "total_steps": 390, "loss": 0.1299, "lr": 7.166665093287539e-07, "epoch": 4.608, "percentage": 92.31, "elapsed_time": "5:21:22", "remaining_time": "0:26:46"}
361
+ {"current_steps": 361, "total_steps": 390, "loss": 0.1381, "lr": 6.69949168211721e-07, "epoch": 4.6208, "percentage": 92.56, "elapsed_time": "5:22:09", "remaining_time": "0:25:52"}
362
+ {"current_steps": 362, "total_steps": 390, "loss": 0.1371, "lr": 6.247803427816945e-07, "epoch": 4.6336, "percentage": 92.82, "elapsed_time": "5:22:59", "remaining_time": "0:24:58"}
363
+ {"current_steps": 363, "total_steps": 390, "loss": 0.1551, "lr": 5.811636514789598e-07, "epoch": 4.6464, "percentage": 93.08, "elapsed_time": "5:23:51", "remaining_time": "0:24:05"}
364
+ {"current_steps": 364, "total_steps": 390, "loss": 0.1214, "lr": 5.391025884035239e-07, "epoch": 4.6592, "percentage": 93.33, "elapsed_time": "5:24:36", "remaining_time": "0:23:11"}
365
+ {"current_steps": 365, "total_steps": 390, "loss": 0.1266, "lr": 4.986005230351954e-07, "epoch": 4.672, "percentage": 93.59, "elapsed_time": "5:25:19", "remaining_time": "0:22:16"}
366
+ {"current_steps": 366, "total_steps": 390, "loss": 0.1231, "lr": 4.5966069996365993e-07, "epoch": 4.6848, "percentage": 93.85, "elapsed_time": "5:26:01", "remaining_time": "0:21:22"}
367
+ {"current_steps": 367, "total_steps": 390, "loss": 0.1411, "lr": 4.22286238628562e-07, "epoch": 4.6975999999999996, "percentage": 94.1, "elapsed_time": "5:26:52", "remaining_time": "0:20:29"}
368
+ {"current_steps": 368, "total_steps": 390, "loss": 0.1375, "lr": 3.8648013306960664e-07, "epoch": 4.7104, "percentage": 94.36, "elapsed_time": "5:27:40", "remaining_time": "0:19:35"}
369
+ {"current_steps": 369, "total_steps": 390, "loss": 0.136, "lr": 3.522452516867048e-07, "epoch": 4.7232, "percentage": 94.62, "elapsed_time": "5:28:28", "remaining_time": "0:18:41"}
370
+ {"current_steps": 370, "total_steps": 390, "loss": 0.1307, "lr": 3.1958433701019697e-07, "epoch": 4.736, "percentage": 94.87, "elapsed_time": "5:29:19", "remaining_time": "0:17:48"}
371
+ {"current_steps": 371, "total_steps": 390, "loss": 0.1346, "lr": 2.8850000548115155e-07, "epoch": 4.7488, "percentage": 95.13, "elapsed_time": "5:30:15", "remaining_time": "0:16:54"}
372
+ {"current_steps": 372, "total_steps": 390, "loss": 0.158, "lr": 2.5899474724174313e-07, "epoch": 4.7616, "percentage": 95.38, "elapsed_time": "5:31:08", "remaining_time": "0:16:01"}
373
+ {"current_steps": 373, "total_steps": 390, "loss": 0.1263, "lr": 2.3107092593579905e-07, "epoch": 4.7744, "percentage": 95.64, "elapsed_time": "5:31:56", "remaining_time": "0:15:07"}
374
+ {"current_steps": 374, "total_steps": 390, "loss": 0.1193, "lr": 2.0473077851942858e-07, "epoch": 4.7872, "percentage": 95.9, "elapsed_time": "5:32:43", "remaining_time": "0:14:14"}
375
+ {"current_steps": 375, "total_steps": 390, "loss": 0.1266, "lr": 1.799764150818306e-07, "epoch": 4.8, "percentage": 96.15, "elapsed_time": "5:33:37", "remaining_time": "0:13:20"}
376
+ {"current_steps": 376, "total_steps": 390, "loss": 0.137, "lr": 1.5680981867625566e-07, "epoch": 4.8128, "percentage": 96.41, "elapsed_time": "5:34:31", "remaining_time": "0:12:27"}
377
+ {"current_steps": 377, "total_steps": 390, "loss": 0.1353, "lr": 1.3523284516113955e-07, "epoch": 4.8256, "percentage": 96.67, "elapsed_time": "5:35:30", "remaining_time": "0:11:34"}
378
+ {"current_steps": 378, "total_steps": 390, "loss": 0.1159, "lr": 1.1524722305144231e-07, "epoch": 4.8384, "percentage": 96.92, "elapsed_time": "5:36:12", "remaining_time": "0:10:40"}
379
+ {"current_steps": 379, "total_steps": 390, "loss": 0.1375, "lr": 9.685455338016347e-08, "epoch": 4.8512, "percentage": 97.18, "elapsed_time": "5:36:56", "remaining_time": "0:09:46"}
380
+ {"current_steps": 380, "total_steps": 390, "loss": 0.1151, "lr": 8.005630957010014e-08, "epoch": 4.864, "percentage": 97.44, "elapsed_time": "5:37:45", "remaining_time": "0:08:53"}
381
+ {"current_steps": 381, "total_steps": 390, "loss": 0.1403, "lr": 6.485383731580142e-08, "epoch": 4.8768, "percentage": 97.69, "elapsed_time": "5:38:41", "remaining_time": "0:08:00"}
382
+ {"current_steps": 382, "total_steps": 390, "loss": 0.11, "lr": 5.1248354475768034e-08, "epoch": 4.8896, "percentage": 97.95, "elapsed_time": "5:39:26", "remaining_time": "0:07:06"}
383
+ {"current_steps": 383, "total_steps": 390, "loss": 0.147, "lr": 3.924095097489922e-08, "epoch": 4.9024, "percentage": 98.21, "elapsed_time": "5:40:26", "remaining_time": "0:06:13"}
384
+ {"current_steps": 384, "total_steps": 390, "loss": 0.133, "lr": 2.8832588717164766e-08, "epoch": 4.9152000000000005, "percentage": 98.46, "elapsed_time": "5:41:23", "remaining_time": "0:05:20"}
385
+ {"current_steps": 385, "total_steps": 390, "loss": 0.1375, "lr": 2.0024101508555604e-08, "epoch": 4.928, "percentage": 98.72, "elapsed_time": "5:42:08", "remaining_time": "0:04:26"}
386
+ {"current_steps": 386, "total_steps": 390, "loss": 0.1476, "lr": 1.281619499029274e-08, "epoch": 4.9408, "percentage": 98.97, "elapsed_time": "5:43:09", "remaining_time": "0:03:33"}
387
+ {"current_steps": 387, "total_steps": 390, "loss": 0.1213, "lr": 7.209446582292501e-09, "epoch": 4.9536, "percentage": 99.23, "elapsed_time": "5:43:50", "remaining_time": "0:02:39"}
388
+ {"current_steps": 388, "total_steps": 390, "loss": 0.1705, "lr": 3.2043054369057523e-09, "epoch": 4.9664, "percentage": 99.49, "elapsed_time": "5:44:51", "remaining_time": "0:01:46"}
389
+ {"current_steps": 389, "total_steps": 390, "loss": 0.1098, "lr": 8.010924029533406e-10, "epoch": 4.9792, "percentage": 99.74, "elapsed_time": "5:45:34", "remaining_time": "0:00:53"}
390
+ {"current_steps": 390, "total_steps": 390, "loss": 0.1474, "lr": 0.0, "epoch": 4.992, "percentage": 100.0, "elapsed_time": "5:46:28", "remaining_time": "0:00:00"}
391
+ {"current_steps": 390, "total_steps": 390, "epoch": 4.992, "percentage": 100.0, "elapsed_time": "5:48:15", "remaining_time": "0:00:00"}