EtashGuha commited on
Commit
bc38ffb
·
verified ·
1 Parent(s): de07b95

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 sha256:6a6dcf6ca3d9100cc7370bb87a8391b496645341b682df4625f62d05b30b3c1f
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a3d0d07ee5728ab1406efd5ddc1465d621b22602e4ee8e6f535e7b7ab4f38e7
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:d2031334122b4ef3c65f25f1ce6dfe139eef47c530b5a025520af73b1157b80a
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4df022142f91bd2607634da06213f9d003e70cf6e46b36062268ddc6c932adff
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:85fff735a6c88a3483fa14fa6ea278a77267b35bed4c6c1c570a98341a619cea
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f89089beb7aea54d5315923320f56958d1f014e5462623c07c926a74b55cf37
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:67bc89c04f6daf55e642a7fb423fe99649e1fea822c348590be887239b304588
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:23358d4d2a3672b739c7917f2884a77bb403676802f2fc0b55ec25246d55449b
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -313,3 +313,79 @@
313
  {"current_steps": 313, "total_steps": 390, "loss": 0.4033, "lr": 4.5646621393177e-06, "epoch": 4.0064, "percentage": 80.26, "elapsed_time": "4:01:19", "remaining_time": "0:59:22"}
314
  {"current_steps": 314, "total_steps": 390, "loss": 0.3765, "lr": 4.451449654204685e-06, "epoch": 4.0192, "percentage": 80.51, "elapsed_time": "4:02:03", "remaining_time": "0:58:35"}
315
  {"current_steps": 315, "total_steps": 390, "loss": 0.3773, "lr": 4.339482751647557e-06, "epoch": 4.032, "percentage": 80.77, "elapsed_time": "4:02:49", "remaining_time": "0:57:48"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
313
  {"current_steps": 313, "total_steps": 390, "loss": 0.4033, "lr": 4.5646621393177e-06, "epoch": 4.0064, "percentage": 80.26, "elapsed_time": "4:01:19", "remaining_time": "0:59:22"}
314
  {"current_steps": 314, "total_steps": 390, "loss": 0.3765, "lr": 4.451449654204685e-06, "epoch": 4.0192, "percentage": 80.51, "elapsed_time": "4:02:03", "remaining_time": "0:58:35"}
315
  {"current_steps": 315, "total_steps": 390, "loss": 0.3773, "lr": 4.339482751647557e-06, "epoch": 4.032, "percentage": 80.77, "elapsed_time": "4:02:49", "remaining_time": "0:57:48"}
316
+ {"current_steps": 316, "total_steps": 390, "loss": 0.3727, "lr": 4.228770401229824e-06, "epoch": 4.0448, "percentage": 81.03, "elapsed_time": "4:03:32", "remaining_time": "0:57:01"}
317
+ {"current_steps": 317, "total_steps": 390, "loss": 0.3861, "lr": 4.119321472033779e-06, "epoch": 4.0576, "percentage": 81.28, "elapsed_time": "4:04:16", "remaining_time": "0:56:15"}
318
+ {"current_steps": 318, "total_steps": 390, "loss": 0.3771, "lr": 4.011144731929981e-06, "epoch": 4.0704, "percentage": 81.54, "elapsed_time": "4:05:01", "remaining_time": "0:55:28"}
319
+ {"current_steps": 319, "total_steps": 390, "loss": 0.369, "lr": 3.904248846874894e-06, "epoch": 4.0832, "percentage": 81.79, "elapsed_time": "4:05:47", "remaining_time": "0:54:42"}
320
+ {"current_steps": 320, "total_steps": 390, "loss": 0.3764, "lr": 3.7986423802166705e-06, "epoch": 4.096, "percentage": 82.05, "elapsed_time": "4:06:30", "remaining_time": "0:53:55"}
321
+ {"current_steps": 321, "total_steps": 390, "loss": 0.4005, "lr": 3.694333792009115e-06, "epoch": 4.1088, "percentage": 82.31, "elapsed_time": "4:07:15", "remaining_time": "0:53:08"}
322
+ {"current_steps": 322, "total_steps": 390, "loss": 0.394, "lr": 3.5913314383339937e-06, "epoch": 4.1216, "percentage": 82.56, "elapsed_time": "4:08:01", "remaining_time": "0:52:22"}
323
+ {"current_steps": 323, "total_steps": 390, "loss": 0.3886, "lr": 3.4896435706316e-06, "epoch": 4.1344, "percentage": 82.82, "elapsed_time": "4:08:45", "remaining_time": "0:51:35"}
324
+ {"current_steps": 324, "total_steps": 390, "loss": 0.3909, "lr": 3.3892783350397675e-06, "epoch": 4.1472, "percentage": 83.08, "elapsed_time": "4:09:30", "remaining_time": "0:50:49"}
325
+ {"current_steps": 325, "total_steps": 390, "loss": 0.3787, "lr": 3.290243771741275e-06, "epoch": 4.16, "percentage": 83.33, "elapsed_time": "4:10:14", "remaining_time": "0:50:02"}
326
+ {"current_steps": 326, "total_steps": 390, "loss": 0.3882, "lr": 3.1925478143197418e-06, "epoch": 4.1728, "percentage": 83.59, "elapsed_time": "4:10:59", "remaining_time": "0:49:16"}
327
+ {"current_steps": 327, "total_steps": 390, "loss": 0.3778, "lr": 3.0961982891241083e-06, "epoch": 4.1856, "percentage": 83.85, "elapsed_time": "4:11:44", "remaining_time": "0:48:29"}
328
+ {"current_steps": 328, "total_steps": 390, "loss": 0.3829, "lr": 3.001202914641628e-06, "epoch": 4.1984, "percentage": 84.1, "elapsed_time": "4:12:28", "remaining_time": "0:47:43"}
329
+ {"current_steps": 329, "total_steps": 390, "loss": 0.3909, "lr": 2.907569300879596e-06, "epoch": 4.2112, "percentage": 84.36, "elapsed_time": "4:13:13", "remaining_time": "0:46:56"}
330
+ {"current_steps": 330, "total_steps": 390, "loss": 0.3809, "lr": 2.815304948755664e-06, "epoch": 4.224, "percentage": 84.62, "elapsed_time": "4:13:58", "remaining_time": "0:46:10"}
331
+ {"current_steps": 331, "total_steps": 390, "loss": 0.3684, "lr": 2.7244172494969978e-06, "epoch": 4.2368, "percentage": 84.87, "elapsed_time": "4:14:43", "remaining_time": "0:45:24"}
332
+ {"current_steps": 332, "total_steps": 390, "loss": 0.3754, "lr": 2.6349134840481294e-06, "epoch": 4.2496, "percentage": 85.13, "elapsed_time": "4:15:27", "remaining_time": "0:44:37"}
333
+ {"current_steps": 333, "total_steps": 390, "loss": 0.3697, "lr": 2.546800822487714e-06, "epoch": 4.2624, "percentage": 85.38, "elapsed_time": "4:16:13", "remaining_time": "0:43:51"}
334
+ {"current_steps": 334, "total_steps": 390, "loss": 0.3777, "lr": 2.4600863234541338e-06, "epoch": 4.2752, "percentage": 85.64, "elapsed_time": "4:16:56", "remaining_time": "0:43:04"}
335
+ {"current_steps": 335, "total_steps": 390, "loss": 0.385, "lr": 2.374776933580025e-06, "epoch": 4.288, "percentage": 85.9, "elapsed_time": "4:17:40", "remaining_time": "0:42:18"}
336
+ {"current_steps": 336, "total_steps": 390, "loss": 0.3766, "lr": 2.2908794869358044e-06, "epoch": 4.3008, "percentage": 86.15, "elapsed_time": "4:18:25", "remaining_time": "0:41:31"}
337
+ {"current_steps": 337, "total_steps": 390, "loss": 0.3821, "lr": 2.2084007044821764e-06, "epoch": 4.3136, "percentage": 86.41, "elapsed_time": "4:19:12", "remaining_time": "0:40:45"}
338
+ {"current_steps": 338, "total_steps": 390, "loss": 0.3587, "lr": 2.127347193531757e-06, "epoch": 4.3264, "percentage": 86.67, "elapsed_time": "4:19:56", "remaining_time": "0:39:59"}
339
+ {"current_steps": 339, "total_steps": 390, "loss": 0.3869, "lr": 2.0477254472197237e-06, "epoch": 4.3392, "percentage": 86.92, "elapsed_time": "4:20:41", "remaining_time": "0:39:13"}
340
+ {"current_steps": 340, "total_steps": 390, "loss": 0.3602, "lr": 1.96954184398368e-06, "epoch": 4.352, "percentage": 87.18, "elapsed_time": "4:21:24", "remaining_time": "0:38:26"}
341
+ {"current_steps": 341, "total_steps": 390, "loss": 0.368, "lr": 1.8928026470526917e-06, "epoch": 4.3648, "percentage": 87.44, "elapsed_time": "4:22:08", "remaining_time": "0:37:40"}
342
+ {"current_steps": 342, "total_steps": 390, "loss": 0.3676, "lr": 1.817514003945524e-06, "epoch": 4.3776, "percentage": 87.69, "elapsed_time": "4:22:53", "remaining_time": "0:36:53"}
343
+ {"current_steps": 343, "total_steps": 390, "loss": 0.3768, "lr": 1.743681945978184e-06, "epoch": 4.3904, "percentage": 87.95, "elapsed_time": "4:23:38", "remaining_time": "0:36:07"}
344
+ {"current_steps": 344, "total_steps": 390, "loss": 0.3546, "lr": 1.6713123877807413e-06, "epoch": 4.4032, "percentage": 88.21, "elapsed_time": "4:24:21", "remaining_time": "0:35:21"}
345
+ {"current_steps": 345, "total_steps": 390, "loss": 0.367, "lr": 1.6004111268235156e-06, "epoch": 4.416, "percentage": 88.46, "elapsed_time": "4:25:04", "remaining_time": "0:34:34"}
346
+ {"current_steps": 346, "total_steps": 390, "loss": 0.3672, "lr": 1.5309838429526714e-06, "epoch": 4.4288, "percentage": 88.72, "elapsed_time": "4:25:50", "remaining_time": "0:33:48"}
347
+ {"current_steps": 347, "total_steps": 390, "loss": 0.3625, "lr": 1.4630360979351644e-06, "epoch": 4.4416, "percentage": 88.97, "elapsed_time": "4:26:33", "remaining_time": "0:33:01"}
348
+ {"current_steps": 348, "total_steps": 390, "loss": 0.3763, "lr": 1.396573335013236e-06, "epoch": 4.4544, "percentage": 89.23, "elapsed_time": "4:27:20", "remaining_time": "0:32:15"}
349
+ {"current_steps": 349, "total_steps": 390, "loss": 0.3738, "lr": 1.3316008784683265e-06, "epoch": 4.4672, "percentage": 89.49, "elapsed_time": "4:28:05", "remaining_time": "0:31:29"}
350
+ {"current_steps": 350, "total_steps": 390, "loss": 0.3837, "lr": 1.2681239331945695e-06, "epoch": 4.48, "percentage": 89.74, "elapsed_time": "4:28:48", "remaining_time": "0:30:43"}
351
+ {"current_steps": 351, "total_steps": 390, "loss": 0.3718, "lr": 1.2061475842818337e-06, "epoch": 4.4928, "percentage": 90.0, "elapsed_time": "4:29:33", "remaining_time": "0:29:57"}
352
+ {"current_steps": 352, "total_steps": 390, "loss": 0.377, "lr": 1.1456767966083393e-06, "epoch": 4.5056, "percentage": 90.26, "elapsed_time": "4:30:19", "remaining_time": "0:29:10"}
353
+ {"current_steps": 353, "total_steps": 390, "loss": 0.3783, "lr": 1.086716414442952e-06, "epoch": 4.5184, "percentage": 90.51, "elapsed_time": "4:31:06", "remaining_time": "0:28:24"}
354
+ {"current_steps": 354, "total_steps": 390, "loss": 0.3833, "lr": 1.0292711610570904e-06, "epoch": 4.5312, "percentage": 90.77, "elapsed_time": "4:31:50", "remaining_time": "0:27:38"}
355
+ {"current_steps": 355, "total_steps": 390, "loss": 0.3824, "lr": 9.733456383463658e-07, "epoch": 4.5440000000000005, "percentage": 91.03, "elapsed_time": "4:32:35", "remaining_time": "0:26:52"}
356
+ {"current_steps": 356, "total_steps": 390, "loss": 0.3795, "lr": 9.189443264619102e-07, "epoch": 4.5568, "percentage": 91.28, "elapsed_time": "4:33:20", "remaining_time": "0:26:06"}
357
+ {"current_steps": 357, "total_steps": 390, "loss": 0.3763, "lr": 8.660715834514977e-07, "epoch": 4.5696, "percentage": 91.54, "elapsed_time": "4:34:06", "remaining_time": "0:25:20"}
358
+ {"current_steps": 358, "total_steps": 390, "loss": 0.3791, "lr": 8.147316449103959e-07, "epoch": 4.5824, "percentage": 91.79, "elapsed_time": "4:34:50", "remaining_time": "0:24:33"}
359
+ {"current_steps": 359, "total_steps": 390, "loss": 0.3636, "lr": 7.649286236420806e-07, "epoch": 4.5952, "percentage": 92.05, "elapsed_time": "4:35:35", "remaining_time": "0:23:47"}
360
+ {"current_steps": 360, "total_steps": 390, "loss": 0.3853, "lr": 7.166665093287539e-07, "epoch": 4.608, "percentage": 92.31, "elapsed_time": "4:36:18", "remaining_time": "0:23:01"}
361
+ {"current_steps": 361, "total_steps": 390, "loss": 0.3699, "lr": 6.69949168211721e-07, "epoch": 4.6208, "percentage": 92.56, "elapsed_time": "4:37:02", "remaining_time": "0:22:15"}
362
+ {"current_steps": 362, "total_steps": 390, "loss": 0.3878, "lr": 6.247803427816945e-07, "epoch": 4.6336, "percentage": 92.82, "elapsed_time": "4:37:45", "remaining_time": "0:21:29"}
363
+ {"current_steps": 363, "total_steps": 390, "loss": 0.371, "lr": 5.811636514789598e-07, "epoch": 4.6464, "percentage": 93.08, "elapsed_time": "4:38:30", "remaining_time": "0:20:42"}
364
+ {"current_steps": 364, "total_steps": 390, "loss": 0.3764, "lr": 5.391025884035239e-07, "epoch": 4.6592, "percentage": 93.33, "elapsed_time": "4:39:14", "remaining_time": "0:19:56"}
365
+ {"current_steps": 365, "total_steps": 390, "loss": 0.3792, "lr": 4.986005230351954e-07, "epoch": 4.672, "percentage": 93.59, "elapsed_time": "4:39:58", "remaining_time": "0:19:10"}
366
+ {"current_steps": 366, "total_steps": 390, "loss": 0.3851, "lr": 4.5966069996365993e-07, "epoch": 4.6848, "percentage": 93.85, "elapsed_time": "4:40:43", "remaining_time": "0:18:24"}
367
+ {"current_steps": 367, "total_steps": 390, "loss": 0.3775, "lr": 4.22286238628562e-07, "epoch": 4.6975999999999996, "percentage": 94.1, "elapsed_time": "4:41:28", "remaining_time": "0:17:38"}
368
+ {"current_steps": 368, "total_steps": 390, "loss": 0.3837, "lr": 3.8648013306960664e-07, "epoch": 4.7104, "percentage": 94.36, "elapsed_time": "4:42:12", "remaining_time": "0:16:52"}
369
+ {"current_steps": 369, "total_steps": 390, "loss": 0.3755, "lr": 3.522452516867048e-07, "epoch": 4.7232, "percentage": 94.62, "elapsed_time": "4:42:56", "remaining_time": "0:16:06"}
370
+ {"current_steps": 370, "total_steps": 390, "loss": 0.3678, "lr": 3.1958433701019697e-07, "epoch": 4.736, "percentage": 94.87, "elapsed_time": "4:43:39", "remaining_time": "0:15:19"}
371
+ {"current_steps": 371, "total_steps": 390, "loss": 0.3583, "lr": 2.8850000548115155e-07, "epoch": 4.7488, "percentage": 95.13, "elapsed_time": "4:44:24", "remaining_time": "0:14:33"}
372
+ {"current_steps": 372, "total_steps": 390, "loss": 0.3862, "lr": 2.5899474724174313e-07, "epoch": 4.7616, "percentage": 95.38, "elapsed_time": "4:45:08", "remaining_time": "0:13:47"}
373
+ {"current_steps": 373, "total_steps": 390, "loss": 0.3798, "lr": 2.3107092593579905e-07, "epoch": 4.7744, "percentage": 95.64, "elapsed_time": "4:45:53", "remaining_time": "0:13:01"}
374
+ {"current_steps": 374, "total_steps": 390, "loss": 0.3687, "lr": 2.0473077851942858e-07, "epoch": 4.7872, "percentage": 95.9, "elapsed_time": "4:46:40", "remaining_time": "0:12:15"}
375
+ {"current_steps": 375, "total_steps": 390, "loss": 0.3717, "lr": 1.799764150818306e-07, "epoch": 4.8, "percentage": 96.15, "elapsed_time": "4:47:25", "remaining_time": "0:11:29"}
376
+ {"current_steps": 376, "total_steps": 390, "loss": 0.381, "lr": 1.5680981867625566e-07, "epoch": 4.8128, "percentage": 96.41, "elapsed_time": "4:48:11", "remaining_time": "0:10:43"}
377
+ {"current_steps": 377, "total_steps": 390, "loss": 0.3684, "lr": 1.3523284516113955e-07, "epoch": 4.8256, "percentage": 96.67, "elapsed_time": "4:48:56", "remaining_time": "0:09:57"}
378
+ {"current_steps": 378, "total_steps": 390, "loss": 0.3766, "lr": 1.1524722305144231e-07, "epoch": 4.8384, "percentage": 96.92, "elapsed_time": "4:49:41", "remaining_time": "0:09:11"}
379
+ {"current_steps": 379, "total_steps": 390, "loss": 0.3823, "lr": 9.685455338016347e-08, "epoch": 4.8512, "percentage": 97.18, "elapsed_time": "4:50:26", "remaining_time": "0:08:25"}
380
+ {"current_steps": 380, "total_steps": 390, "loss": 0.3827, "lr": 8.005630957010014e-08, "epoch": 4.864, "percentage": 97.44, "elapsed_time": "4:51:09", "remaining_time": "0:07:39"}
381
+ {"current_steps": 381, "total_steps": 390, "loss": 0.3915, "lr": 6.485383731580142e-08, "epoch": 4.8768, "percentage": 97.69, "elapsed_time": "4:51:54", "remaining_time": "0:06:53"}
382
+ {"current_steps": 382, "total_steps": 390, "loss": 0.3702, "lr": 5.1248354475768034e-08, "epoch": 4.8896, "percentage": 97.95, "elapsed_time": "4:52:39", "remaining_time": "0:06:07"}
383
+ {"current_steps": 383, "total_steps": 390, "loss": 0.3746, "lr": 3.924095097489922e-08, "epoch": 4.9024, "percentage": 98.21, "elapsed_time": "4:53:23", "remaining_time": "0:05:21"}
384
+ {"current_steps": 384, "total_steps": 390, "loss": 0.3935, "lr": 2.8832588717164766e-08, "epoch": 4.9152000000000005, "percentage": 98.46, "elapsed_time": "4:54:08", "remaining_time": "0:04:35"}
385
+ {"current_steps": 385, "total_steps": 390, "loss": 0.3729, "lr": 2.0024101508555604e-08, "epoch": 4.928, "percentage": 98.72, "elapsed_time": "4:54:49", "remaining_time": "0:03:49"}
386
+ {"current_steps": 386, "total_steps": 390, "loss": 0.3823, "lr": 1.281619499029274e-08, "epoch": 4.9408, "percentage": 98.97, "elapsed_time": "4:55:34", "remaining_time": "0:03:03"}
387
+ {"current_steps": 387, "total_steps": 390, "loss": 0.3813, "lr": 7.209446582292501e-09, "epoch": 4.9536, "percentage": 99.23, "elapsed_time": "4:56:18", "remaining_time": "0:02:17"}
388
+ {"current_steps": 388, "total_steps": 390, "loss": 0.3819, "lr": 3.2043054369057523e-09, "epoch": 4.9664, "percentage": 99.49, "elapsed_time": "4:57:03", "remaining_time": "0:01:31"}
389
+ {"current_steps": 389, "total_steps": 390, "loss": 0.3696, "lr": 8.010924029533406e-10, "epoch": 4.9792, "percentage": 99.74, "elapsed_time": "4:57:49", "remaining_time": "0:00:45"}
390
+ {"current_steps": 390, "total_steps": 390, "loss": 0.3848, "lr": 0.0, "epoch": 4.992, "percentage": 100.0, "elapsed_time": "4:58:33", "remaining_time": "0:00:00"}
391
+ {"current_steps": 390, "total_steps": 390, "epoch": 4.992, "percentage": 100.0, "elapsed_time": "5:02:00", "remaining_time": "0:00:00"}