ryanmarten commited on
Commit
928ce26
·
verified ·
1 Parent(s): 0e5a594

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 sha256:8ef606a6a1dbd2cc6781510d5f8cf52263d2499e1c2cee5c30cd6917f53ba851
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bffa063f995c08be51ea6a41709f84b74b7281d8355153a97468b9ed1db2a444
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:a5ec3a4ad88368590bbd27925a6518fca821ea5c86fae32dafe2332d1e1a9c62
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:754c817229c821c5b781eb471a0b3c3d0c2e061ce477b1fcb2e5b178b8f15f29
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:67b7c037426baaf551dc663a3862693762c7d59c7d4488887c33cb7a3415f6d1
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7fa9ed602eb738fe285a18f27578b98a65195167f900b73e28a227f1ea34a193
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8f8d75e889d5b031ac146a2b7e624e6c4c712a003ef227ae50e2e98662c9545c
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6aa73c34a012c00d72a3e8f7bd37ba512e9157747b63f7f179edb91a3ffc701
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -311,3 +311,81 @@
311
  {"current_steps": 311, "total_steps": 390, "loss": 0.4118, "lr": 4.794787480690597e-06, "epoch": 3.9808, "percentage": 79.74, "elapsed_time": "11:14:50", "remaining_time": "2:51:25"}
312
  {"current_steps": 312, "total_steps": 390, "loss": 0.4171, "lr": 4.679111137620442e-06, "epoch": 3.9936, "percentage": 80.0, "elapsed_time": "11:17:25", "remaining_time": "2:49:21"}
313
  {"current_steps": 313, "total_steps": 390, "loss": 0.4324, "lr": 4.5646621393177e-06, "epoch": 4.0064, "percentage": 80.26, "elapsed_time": "11:21:34", "remaining_time": "2:47:40"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
311
  {"current_steps": 311, "total_steps": 390, "loss": 0.4118, "lr": 4.794787480690597e-06, "epoch": 3.9808, "percentage": 79.74, "elapsed_time": "11:14:50", "remaining_time": "2:51:25"}
312
  {"current_steps": 312, "total_steps": 390, "loss": 0.4171, "lr": 4.679111137620442e-06, "epoch": 3.9936, "percentage": 80.0, "elapsed_time": "11:17:25", "remaining_time": "2:49:21"}
313
  {"current_steps": 313, "total_steps": 390, "loss": 0.4324, "lr": 4.5646621393177e-06, "epoch": 4.0064, "percentage": 80.26, "elapsed_time": "11:21:34", "remaining_time": "2:47:40"}
314
+ {"current_steps": 314, "total_steps": 390, "loss": 0.3922, "lr": 4.451449654204685e-06, "epoch": 4.0192, "percentage": 80.51, "elapsed_time": "11:23:34", "remaining_time": "2:45:27"}
315
+ {"current_steps": 315, "total_steps": 390, "loss": 0.3989, "lr": 4.339482751647557e-06, "epoch": 4.032, "percentage": 80.77, "elapsed_time": "11:25:50", "remaining_time": "2:43:17"}
316
+ {"current_steps": 316, "total_steps": 390, "loss": 0.3995, "lr": 4.228770401229824e-06, "epoch": 4.0448, "percentage": 81.03, "elapsed_time": "11:28:01", "remaining_time": "2:41:07"}
317
+ {"current_steps": 317, "total_steps": 390, "loss": 0.3965, "lr": 4.119321472033779e-06, "epoch": 4.0576, "percentage": 81.28, "elapsed_time": "11:30:12", "remaining_time": "2:38:56"}
318
+ {"current_steps": 318, "total_steps": 390, "loss": 0.4094, "lr": 4.011144731929981e-06, "epoch": 4.0704, "percentage": 81.54, "elapsed_time": "11:32:25", "remaining_time": "2:36:46"}
319
+ {"current_steps": 319, "total_steps": 390, "loss": 0.3859, "lr": 3.904248846874894e-06, "epoch": 4.0832, "percentage": 81.79, "elapsed_time": "11:34:23", "remaining_time": "2:34:33"}
320
+ {"current_steps": 320, "total_steps": 390, "loss": 0.4026, "lr": 3.7986423802166705e-06, "epoch": 4.096, "percentage": 82.05, "elapsed_time": "11:36:41", "remaining_time": "2:32:24"}
321
+ {"current_steps": 321, "total_steps": 390, "loss": 0.4083, "lr": 3.694333792009115e-06, "epoch": 4.1088, "percentage": 82.31, "elapsed_time": "11:38:47", "remaining_time": "2:30:12"}
322
+ {"current_steps": 322, "total_steps": 390, "loss": 0.3871, "lr": 3.5913314383339937e-06, "epoch": 4.1216, "percentage": 82.56, "elapsed_time": "11:40:57", "remaining_time": "2:28:01"}
323
+ {"current_steps": 323, "total_steps": 390, "loss": 0.3884, "lr": 3.4896435706316e-06, "epoch": 4.1344, "percentage": 82.82, "elapsed_time": "11:43:06", "remaining_time": "2:25:50"}
324
+ {"current_steps": 324, "total_steps": 390, "loss": 0.3944, "lr": 3.3892783350397675e-06, "epoch": 4.1472, "percentage": 83.08, "elapsed_time": "11:45:10", "remaining_time": "2:23:38"}
325
+ {"current_steps": 325, "total_steps": 390, "loss": 0.4087, "lr": 3.290243771741275e-06, "epoch": 4.16, "percentage": 83.33, "elapsed_time": "11:47:34", "remaining_time": "2:21:30"}
326
+ {"current_steps": 326, "total_steps": 390, "loss": 0.3881, "lr": 3.1925478143197418e-06, "epoch": 4.1728, "percentage": 83.59, "elapsed_time": "11:49:57", "remaining_time": "2:19:22"}
327
+ {"current_steps": 327, "total_steps": 390, "loss": 0.4189, "lr": 3.0961982891241083e-06, "epoch": 4.1856, "percentage": 83.85, "elapsed_time": "11:52:04", "remaining_time": "2:17:11"}
328
+ {"current_steps": 328, "total_steps": 390, "loss": 0.3855, "lr": 3.001202914641628e-06, "epoch": 4.1984, "percentage": 84.1, "elapsed_time": "11:54:08", "remaining_time": "2:14:59"}
329
+ {"current_steps": 329, "total_steps": 390, "loss": 0.3973, "lr": 2.907569300879596e-06, "epoch": 4.2112, "percentage": 84.36, "elapsed_time": "11:56:27", "remaining_time": "2:12:50"}
330
+ {"current_steps": 330, "total_steps": 390, "loss": 0.3672, "lr": 2.815304948755664e-06, "epoch": 4.224, "percentage": 84.62, "elapsed_time": "11:58:37", "remaining_time": "2:10:39"}
331
+ {"current_steps": 331, "total_steps": 390, "loss": 0.3766, "lr": 2.7244172494969978e-06, "epoch": 4.2368, "percentage": 84.87, "elapsed_time": "12:00:48", "remaining_time": "2:08:28"}
332
+ {"current_steps": 332, "total_steps": 390, "loss": 0.3921, "lr": 2.6349134840481294e-06, "epoch": 4.2496, "percentage": 85.13, "elapsed_time": "12:02:59", "remaining_time": "2:06:18"}
333
+ {"current_steps": 333, "total_steps": 390, "loss": 0.3735, "lr": 2.546800822487714e-06, "epoch": 4.2624, "percentage": 85.38, "elapsed_time": "12:05:00", "remaining_time": "2:04:06"}
334
+ {"current_steps": 334, "total_steps": 390, "loss": 0.3763, "lr": 2.4600863234541338e-06, "epoch": 4.2752, "percentage": 85.64, "elapsed_time": "12:07:12", "remaining_time": "2:01:55"}
335
+ {"current_steps": 335, "total_steps": 390, "loss": 0.3829, "lr": 2.374776933580025e-06, "epoch": 4.288, "percentage": 85.9, "elapsed_time": "12:09:27", "remaining_time": "1:59:45"}
336
+ {"current_steps": 336, "total_steps": 390, "loss": 0.38, "lr": 2.2908794869358044e-06, "epoch": 4.3008, "percentage": 86.15, "elapsed_time": "12:11:39", "remaining_time": "1:57:35"}
337
+ {"current_steps": 337, "total_steps": 390, "loss": 0.3949, "lr": 2.2084007044821764e-06, "epoch": 4.3136, "percentage": 86.41, "elapsed_time": "12:13:40", "remaining_time": "1:55:23"}
338
+ {"current_steps": 338, "total_steps": 390, "loss": 0.3884, "lr": 2.127347193531757e-06, "epoch": 4.3264, "percentage": 86.67, "elapsed_time": "12:15:49", "remaining_time": "1:53:12"}
339
+ {"current_steps": 339, "total_steps": 390, "loss": 0.3856, "lr": 2.0477254472197237e-06, "epoch": 4.3392, "percentage": 86.92, "elapsed_time": "12:18:03", "remaining_time": "1:51:02"}
340
+ {"current_steps": 340, "total_steps": 390, "loss": 0.376, "lr": 1.96954184398368e-06, "epoch": 4.352, "percentage": 87.18, "elapsed_time": "12:20:03", "remaining_time": "1:48:49"}
341
+ {"current_steps": 341, "total_steps": 390, "loss": 0.3826, "lr": 1.8928026470526917e-06, "epoch": 4.3648, "percentage": 87.44, "elapsed_time": "12:22:21", "remaining_time": "1:46:40"}
342
+ {"current_steps": 342, "total_steps": 390, "loss": 0.3804, "lr": 1.817514003945524e-06, "epoch": 4.3776, "percentage": 87.69, "elapsed_time": "12:24:13", "remaining_time": "1:44:27"}
343
+ {"current_steps": 343, "total_steps": 390, "loss": 0.3877, "lr": 1.743681945978184e-06, "epoch": 4.3904, "percentage": 87.95, "elapsed_time": "12:26:17", "remaining_time": "1:42:15"}
344
+ {"current_steps": 344, "total_steps": 390, "loss": 0.3772, "lr": 1.6713123877807413e-06, "epoch": 4.4032, "percentage": 88.21, "elapsed_time": "12:28:25", "remaining_time": "1:40:04"}
345
+ {"current_steps": 345, "total_steps": 390, "loss": 0.4109, "lr": 1.6004111268235156e-06, "epoch": 4.416, "percentage": 88.46, "elapsed_time": "12:30:46", "remaining_time": "1:37:55"}
346
+ {"current_steps": 346, "total_steps": 390, "loss": 0.3562, "lr": 1.5309838429526714e-06, "epoch": 4.4288, "percentage": 88.72, "elapsed_time": "12:33:00", "remaining_time": "1:35:45"}
347
+ {"current_steps": 347, "total_steps": 390, "loss": 0.392, "lr": 1.4630360979351644e-06, "epoch": 4.4416, "percentage": 88.97, "elapsed_time": "12:35:07", "remaining_time": "1:33:34"}
348
+ {"current_steps": 348, "total_steps": 390, "loss": 0.3878, "lr": 1.396573335013236e-06, "epoch": 4.4544, "percentage": 89.23, "elapsed_time": "12:37:21", "remaining_time": "1:31:24"}
349
+ {"current_steps": 349, "total_steps": 390, "loss": 0.3548, "lr": 1.3316008784683265e-06, "epoch": 4.4672, "percentage": 89.49, "elapsed_time": "12:39:22", "remaining_time": "1:29:12"}
350
+ {"current_steps": 350, "total_steps": 390, "loss": 0.3756, "lr": 1.2681239331945695e-06, "epoch": 4.48, "percentage": 89.74, "elapsed_time": "12:41:23", "remaining_time": "1:27:00"}
351
+ {"current_steps": 351, "total_steps": 390, "loss": 0.3768, "lr": 1.2061475842818337e-06, "epoch": 4.4928, "percentage": 90.0, "elapsed_time": "12:43:41", "remaining_time": "1:24:51"}
352
+ {"current_steps": 352, "total_steps": 390, "loss": 0.3664, "lr": 1.1456767966083393e-06, "epoch": 4.5056, "percentage": 90.26, "elapsed_time": "12:45:55", "remaining_time": "1:22:41"}
353
+ {"current_steps": 353, "total_steps": 390, "loss": 0.3921, "lr": 1.086716414442952e-06, "epoch": 4.5184, "percentage": 90.51, "elapsed_time": "12:48:10", "remaining_time": "1:20:30"}
354
+ {"current_steps": 354, "total_steps": 390, "loss": 0.3642, "lr": 1.0292711610570904e-06, "epoch": 4.5312, "percentage": 90.77, "elapsed_time": "12:50:18", "remaining_time": "1:18:20"}
355
+ {"current_steps": 355, "total_steps": 390, "loss": 0.3781, "lr": 9.733456383463658e-07, "epoch": 4.5440000000000005, "percentage": 91.03, "elapsed_time": "12:52:40", "remaining_time": "1:16:10"}
356
+ {"current_steps": 356, "total_steps": 390, "loss": 0.3795, "lr": 9.189443264619102e-07, "epoch": 4.5568, "percentage": 91.28, "elapsed_time": "12:54:50", "remaining_time": "1:14:00"}
357
+ {"current_steps": 357, "total_steps": 390, "loss": 0.3823, "lr": 8.660715834514977e-07, "epoch": 4.5696, "percentage": 91.54, "elapsed_time": "12:56:53", "remaining_time": "1:11:48"}
358
+ {"current_steps": 358, "total_steps": 390, "loss": 0.3895, "lr": 8.147316449103959e-07, "epoch": 4.5824, "percentage": 91.79, "elapsed_time": "12:59:14", "remaining_time": "1:09:39"}
359
+ {"current_steps": 359, "total_steps": 390, "loss": 0.3881, "lr": 7.649286236420806e-07, "epoch": 4.5952, "percentage": 92.05, "elapsed_time": "13:01:28", "remaining_time": "1:07:28"}
360
+ {"current_steps": 360, "total_steps": 390, "loss": 0.3442, "lr": 7.166665093287539e-07, "epoch": 4.608, "percentage": 92.31, "elapsed_time": "13:03:31", "remaining_time": "1:05:17"}
361
+ {"current_steps": 361, "total_steps": 390, "loss": 0.3847, "lr": 6.69949168211721e-07, "epoch": 4.6208, "percentage": 92.56, "elapsed_time": "13:05:33", "remaining_time": "1:03:06"}
362
+ {"current_steps": 362, "total_steps": 390, "loss": 0.38, "lr": 6.247803427816945e-07, "epoch": 4.6336, "percentage": 92.82, "elapsed_time": "13:07:47", "remaining_time": "1:00:56"}
363
+ {"current_steps": 363, "total_steps": 390, "loss": 0.3795, "lr": 5.811636514789598e-07, "epoch": 4.6464, "percentage": 93.08, "elapsed_time": "13:09:56", "remaining_time": "0:58:45"}
364
+ {"current_steps": 364, "total_steps": 390, "loss": 0.3742, "lr": 5.391025884035239e-07, "epoch": 4.6592, "percentage": 93.33, "elapsed_time": "13:12:07", "remaining_time": "0:56:34"}
365
+ {"current_steps": 365, "total_steps": 390, "loss": 0.4011, "lr": 4.986005230351954e-07, "epoch": 4.672, "percentage": 93.59, "elapsed_time": "13:14:22", "remaining_time": "0:54:24"}
366
+ {"current_steps": 366, "total_steps": 390, "loss": 0.374, "lr": 4.5966069996365993e-07, "epoch": 4.6848, "percentage": 93.85, "elapsed_time": "13:16:23", "remaining_time": "0:52:13"}
367
+ {"current_steps": 367, "total_steps": 390, "loss": 0.3811, "lr": 4.22286238628562e-07, "epoch": 4.6975999999999996, "percentage": 94.1, "elapsed_time": "13:18:32", "remaining_time": "0:50:02"}
368
+ {"current_steps": 368, "total_steps": 390, "loss": 0.398, "lr": 3.8648013306960664e-07, "epoch": 4.7104, "percentage": 94.36, "elapsed_time": "13:20:38", "remaining_time": "0:47:51"}
369
+ {"current_steps": 369, "total_steps": 390, "loss": 0.3869, "lr": 3.522452516867048e-07, "epoch": 4.7232, "percentage": 94.62, "elapsed_time": "13:22:45", "remaining_time": "0:45:41"}
370
+ {"current_steps": 370, "total_steps": 390, "loss": 0.3699, "lr": 3.1958433701019697e-07, "epoch": 4.736, "percentage": 94.87, "elapsed_time": "13:24:48", "remaining_time": "0:43:30"}
371
+ {"current_steps": 371, "total_steps": 390, "loss": 0.3903, "lr": 2.8850000548115155e-07, "epoch": 4.7488, "percentage": 95.13, "elapsed_time": "13:27:01", "remaining_time": "0:41:19"}
372
+ {"current_steps": 372, "total_steps": 390, "loss": 0.4013, "lr": 2.5899474724174313e-07, "epoch": 4.7616, "percentage": 95.38, "elapsed_time": "13:29:18", "remaining_time": "0:39:09"}
373
+ {"current_steps": 373, "total_steps": 390, "loss": 0.4131, "lr": 2.3107092593579905e-07, "epoch": 4.7744, "percentage": 95.64, "elapsed_time": "13:31:33", "remaining_time": "0:36:59"}
374
+ {"current_steps": 374, "total_steps": 390, "loss": 0.3908, "lr": 2.0473077851942858e-07, "epoch": 4.7872, "percentage": 95.9, "elapsed_time": "13:33:48", "remaining_time": "0:34:48"}
375
+ {"current_steps": 375, "total_steps": 390, "loss": 0.4046, "lr": 1.799764150818306e-07, "epoch": 4.8, "percentage": 96.15, "elapsed_time": "13:35:58", "remaining_time": "0:32:38"}
376
+ {"current_steps": 376, "total_steps": 390, "loss": 0.3927, "lr": 1.5680981867625566e-07, "epoch": 4.8128, "percentage": 96.41, "elapsed_time": "13:38:04", "remaining_time": "0:30:27"}
377
+ {"current_steps": 377, "total_steps": 390, "loss": 0.3587, "lr": 1.3523284516113955e-07, "epoch": 4.8256, "percentage": 96.67, "elapsed_time": "13:40:18", "remaining_time": "0:28:17"}
378
+ {"current_steps": 378, "total_steps": 390, "loss": 0.3826, "lr": 1.1524722305144231e-07, "epoch": 4.8384, "percentage": 96.92, "elapsed_time": "13:42:28", "remaining_time": "0:26:06"}
379
+ {"current_steps": 379, "total_steps": 390, "loss": 0.3713, "lr": 9.685455338016347e-08, "epoch": 4.8512, "percentage": 97.18, "elapsed_time": "13:44:34", "remaining_time": "0:23:55"}
380
+ {"current_steps": 380, "total_steps": 390, "loss": 0.3928, "lr": 8.005630957010014e-08, "epoch": 4.864, "percentage": 97.44, "elapsed_time": "13:46:45", "remaining_time": "0:21:45"}
381
+ {"current_steps": 381, "total_steps": 390, "loss": 0.3938, "lr": 6.485383731580142e-08, "epoch": 4.8768, "percentage": 97.69, "elapsed_time": "13:49:00", "remaining_time": "0:19:34"}
382
+ {"current_steps": 382, "total_steps": 390, "loss": 0.3712, "lr": 5.1248354475768034e-08, "epoch": 4.8896, "percentage": 97.95, "elapsed_time": "13:51:12", "remaining_time": "0:17:24"}
383
+ {"current_steps": 383, "total_steps": 390, "loss": 0.3855, "lr": 3.924095097489922e-08, "epoch": 4.9024, "percentage": 98.21, "elapsed_time": "13:53:35", "remaining_time": "0:15:14"}
384
+ {"current_steps": 384, "total_steps": 390, "loss": 0.3839, "lr": 2.8832588717164766e-08, "epoch": 4.9152000000000005, "percentage": 98.46, "elapsed_time": "13:55:52", "remaining_time": "0:13:03"}
385
+ {"current_steps": 385, "total_steps": 390, "loss": 0.3607, "lr": 2.0024101508555604e-08, "epoch": 4.928, "percentage": 98.72, "elapsed_time": "13:58:01", "remaining_time": "0:10:53"}
386
+ {"current_steps": 386, "total_steps": 390, "loss": 0.4119, "lr": 1.281619499029274e-08, "epoch": 4.9408, "percentage": 98.97, "elapsed_time": "14:00:09", "remaining_time": "0:08:42"}
387
+ {"current_steps": 387, "total_steps": 390, "loss": 0.3742, "lr": 7.209446582292501e-09, "epoch": 4.9536, "percentage": 99.23, "elapsed_time": "14:02:32", "remaining_time": "0:06:31"}
388
+ {"current_steps": 388, "total_steps": 390, "loss": 0.3806, "lr": 3.2043054369057523e-09, "epoch": 4.9664, "percentage": 99.49, "elapsed_time": "14:04:46", "remaining_time": "0:04:21"}
389
+ {"current_steps": 389, "total_steps": 390, "loss": 0.4029, "lr": 8.010924029533406e-10, "epoch": 4.9792, "percentage": 99.74, "elapsed_time": "14:07:13", "remaining_time": "0:02:10"}
390
+ {"current_steps": 390, "total_steps": 390, "loss": 0.3779, "lr": 0.0, "epoch": 4.992, "percentage": 100.0, "elapsed_time": "14:09:19", "remaining_time": "0:00:00"}
391
+ {"current_steps": 390, "total_steps": 390, "epoch": 4.992, "percentage": 100.0, "elapsed_time": "14:11:14", "remaining_time": "0:00:00"}