ryanmarten commited on
Commit
bff0297
·
verified ·
1 Parent(s): 3e48f94

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 sha256:0dc8d2d3c6342ce1a8b475fe116fe15e1ea559f507fb8764297d57f18b1d25e3
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f70925a7cfa31d7fa9d7f03e1641c9c32312588a72d9fdeedfb8330e6ba91307
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3b0e57ed16c65b3b4739304bfa03c825565ae4f587c8bf1cc97256e156b6df92
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b41a7c10206ff704e3286dfd923e025998c52bd4713ba4efbd63e49469cd089b
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:b9289bd50691d7c5d0436fa4d319dcaabbf817a357fc4f2ca465a24c828443ec
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c85ca5952201dff64470d6c715ff8fceb2bf46f1e3fe6a377a2bdcec37ac71d5
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4566ef8c3b3efee31b435e4cfc5d7908b20d0a5ddab1d4cad142e7d5887edf7c
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:972a6f059f317a34fb9a236e08e348033fac82ef8d6de13fbd122a2f014adc53
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -312,3 +312,80 @@
312
  {"current_steps": 312, "total_steps": 390, "loss": 0.4309, "lr": 4.679111137620442e-06, "epoch": 3.9936, "percentage": 80.0, "elapsed_time": "14:08:02", "remaining_time": "3:32:00"}
313
  {"current_steps": 313, "total_steps": 390, "loss": 0.4119, "lr": 4.5646621393177e-06, "epoch": 4.0064, "percentage": 80.26, "elapsed_time": "14:11:29", "remaining_time": "3:29:28"}
314
  {"current_steps": 314, "total_steps": 390, "loss": 0.3861, "lr": 4.451449654204685e-06, "epoch": 4.0192, "percentage": 80.51, "elapsed_time": "14:14:10", "remaining_time": "3:26:44"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
312
  {"current_steps": 312, "total_steps": 390, "loss": 0.4309, "lr": 4.679111137620442e-06, "epoch": 3.9936, "percentage": 80.0, "elapsed_time": "14:08:02", "remaining_time": "3:32:00"}
313
  {"current_steps": 313, "total_steps": 390, "loss": 0.4119, "lr": 4.5646621393177e-06, "epoch": 4.0064, "percentage": 80.26, "elapsed_time": "14:11:29", "remaining_time": "3:29:28"}
314
  {"current_steps": 314, "total_steps": 390, "loss": 0.3861, "lr": 4.451449654204685e-06, "epoch": 4.0192, "percentage": 80.51, "elapsed_time": "14:14:10", "remaining_time": "3:26:44"}
315
+ {"current_steps": 315, "total_steps": 390, "loss": 0.394, "lr": 4.339482751647557e-06, "epoch": 4.032, "percentage": 80.77, "elapsed_time": "14:16:58", "remaining_time": "3:24:02"}
316
+ {"current_steps": 316, "total_steps": 390, "loss": 0.3927, "lr": 4.228770401229824e-06, "epoch": 4.0448, "percentage": 81.03, "elapsed_time": "14:19:43", "remaining_time": "3:21:19"}
317
+ {"current_steps": 317, "total_steps": 390, "loss": 0.3888, "lr": 4.119321472033779e-06, "epoch": 4.0576, "percentage": 81.28, "elapsed_time": "14:22:12", "remaining_time": "3:18:33"}
318
+ {"current_steps": 318, "total_steps": 390, "loss": 0.3796, "lr": 4.011144731929981e-06, "epoch": 4.0704, "percentage": 81.54, "elapsed_time": "14:25:02", "remaining_time": "3:15:51"}
319
+ {"current_steps": 319, "total_steps": 390, "loss": 0.3957, "lr": 3.904248846874894e-06, "epoch": 4.0832, "percentage": 81.79, "elapsed_time": "14:27:37", "remaining_time": "3:13:06"}
320
+ {"current_steps": 320, "total_steps": 390, "loss": 0.3721, "lr": 3.7986423802166705e-06, "epoch": 4.096, "percentage": 82.05, "elapsed_time": "14:30:09", "remaining_time": "3:10:20"}
321
+ {"current_steps": 321, "total_steps": 390, "loss": 0.389, "lr": 3.694333792009115e-06, "epoch": 4.1088, "percentage": 82.31, "elapsed_time": "14:33:04", "remaining_time": "3:07:40"}
322
+ {"current_steps": 322, "total_steps": 390, "loss": 0.3882, "lr": 3.5913314383339937e-06, "epoch": 4.1216, "percentage": 82.56, "elapsed_time": "14:35:49", "remaining_time": "3:04:57"}
323
+ {"current_steps": 323, "total_steps": 390, "loss": 0.3883, "lr": 3.4896435706316e-06, "epoch": 4.1344, "percentage": 82.82, "elapsed_time": "14:38:36", "remaining_time": "3:02:14"}
324
+ {"current_steps": 324, "total_steps": 390, "loss": 0.3838, "lr": 3.3892783350397675e-06, "epoch": 4.1472, "percentage": 83.08, "elapsed_time": "14:41:25", "remaining_time": "2:59:32"}
325
+ {"current_steps": 325, "total_steps": 390, "loss": 0.4069, "lr": 3.290243771741275e-06, "epoch": 4.16, "percentage": 83.33, "elapsed_time": "14:44:07", "remaining_time": "2:56:49"}
326
+ {"current_steps": 326, "total_steps": 390, "loss": 0.3933, "lr": 3.1925478143197418e-06, "epoch": 4.1728, "percentage": 83.59, "elapsed_time": "14:46:37", "remaining_time": "2:54:03"}
327
+ {"current_steps": 327, "total_steps": 390, "loss": 0.3846, "lr": 3.0961982891241083e-06, "epoch": 4.1856, "percentage": 83.85, "elapsed_time": "14:49:31", "remaining_time": "2:51:22"}
328
+ {"current_steps": 328, "total_steps": 390, "loss": 0.3886, "lr": 3.001202914641628e-06, "epoch": 4.1984, "percentage": 84.1, "elapsed_time": "14:52:16", "remaining_time": "2:48:39"}
329
+ {"current_steps": 329, "total_steps": 390, "loss": 0.3948, "lr": 2.907569300879596e-06, "epoch": 4.2112, "percentage": 84.36, "elapsed_time": "14:55:01", "remaining_time": "2:45:56"}
330
+ {"current_steps": 330, "total_steps": 390, "loss": 0.3792, "lr": 2.815304948755664e-06, "epoch": 4.224, "percentage": 84.62, "elapsed_time": "14:57:33", "remaining_time": "2:43:11"}
331
+ {"current_steps": 331, "total_steps": 390, "loss": 0.4172, "lr": 2.7244172494969978e-06, "epoch": 4.2368, "percentage": 84.87, "elapsed_time": "15:00:19", "remaining_time": "2:40:28"}
332
+ {"current_steps": 332, "total_steps": 390, "loss": 0.3785, "lr": 2.6349134840481294e-06, "epoch": 4.2496, "percentage": 85.13, "elapsed_time": "15:03:08", "remaining_time": "2:37:46"}
333
+ {"current_steps": 333, "total_steps": 390, "loss": 0.3855, "lr": 2.546800822487714e-06, "epoch": 4.2624, "percentage": 85.38, "elapsed_time": "15:05:52", "remaining_time": "2:35:03"}
334
+ {"current_steps": 334, "total_steps": 390, "loss": 0.3905, "lr": 2.4600863234541338e-06, "epoch": 4.2752, "percentage": 85.64, "elapsed_time": "15:08:45", "remaining_time": "2:32:21"}
335
+ {"current_steps": 335, "total_steps": 390, "loss": 0.3769, "lr": 2.374776933580025e-06, "epoch": 4.288, "percentage": 85.9, "elapsed_time": "15:11:34", "remaining_time": "2:29:39"}
336
+ {"current_steps": 336, "total_steps": 390, "loss": 0.3667, "lr": 2.2908794869358044e-06, "epoch": 4.3008, "percentage": 86.15, "elapsed_time": "15:14:23", "remaining_time": "2:26:57"}
337
+ {"current_steps": 337, "total_steps": 390, "loss": 0.387, "lr": 2.2084007044821764e-06, "epoch": 4.3136, "percentage": 86.41, "elapsed_time": "15:17:10", "remaining_time": "2:24:14"}
338
+ {"current_steps": 338, "total_steps": 390, "loss": 0.3801, "lr": 2.127347193531757e-06, "epoch": 4.3264, "percentage": 86.67, "elapsed_time": "15:19:45", "remaining_time": "2:21:30"}
339
+ {"current_steps": 339, "total_steps": 390, "loss": 0.3789, "lr": 2.0477254472197237e-06, "epoch": 4.3392, "percentage": 86.92, "elapsed_time": "15:22:32", "remaining_time": "2:18:47"}
340
+ {"current_steps": 340, "total_steps": 390, "loss": 0.3707, "lr": 1.96954184398368e-06, "epoch": 4.352, "percentage": 87.18, "elapsed_time": "15:25:11", "remaining_time": "2:16:03"}
341
+ {"current_steps": 341, "total_steps": 390, "loss": 0.375, "lr": 1.8928026470526917e-06, "epoch": 4.3648, "percentage": 87.44, "elapsed_time": "15:27:53", "remaining_time": "2:13:19"}
342
+ {"current_steps": 342, "total_steps": 390, "loss": 0.3927, "lr": 1.817514003945524e-06, "epoch": 4.3776, "percentage": 87.69, "elapsed_time": "15:30:38", "remaining_time": "2:10:36"}
343
+ {"current_steps": 343, "total_steps": 390, "loss": 0.3874, "lr": 1.743681945978184e-06, "epoch": 4.3904, "percentage": 87.95, "elapsed_time": "15:33:24", "remaining_time": "2:07:54"}
344
+ {"current_steps": 344, "total_steps": 390, "loss": 0.3809, "lr": 1.6713123877807413e-06, "epoch": 4.4032, "percentage": 88.21, "elapsed_time": "15:36:06", "remaining_time": "2:05:10"}
345
+ {"current_steps": 345, "total_steps": 390, "loss": 0.385, "lr": 1.6004111268235156e-06, "epoch": 4.416, "percentage": 88.46, "elapsed_time": "15:38:51", "remaining_time": "2:02:27"}
346
+ {"current_steps": 346, "total_steps": 390, "loss": 0.3851, "lr": 1.5309838429526714e-06, "epoch": 4.4288, "percentage": 88.72, "elapsed_time": "15:41:19", "remaining_time": "1:59:42"}
347
+ {"current_steps": 347, "total_steps": 390, "loss": 0.3883, "lr": 1.4630360979351644e-06, "epoch": 4.4416, "percentage": 88.97, "elapsed_time": "15:44:08", "remaining_time": "1:56:59"}
348
+ {"current_steps": 348, "total_steps": 390, "loss": 0.3904, "lr": 1.396573335013236e-06, "epoch": 4.4544, "percentage": 89.23, "elapsed_time": "15:46:50", "remaining_time": "1:54:16"}
349
+ {"current_steps": 349, "total_steps": 390, "loss": 0.3711, "lr": 1.3316008784683265e-06, "epoch": 4.4672, "percentage": 89.49, "elapsed_time": "15:49:25", "remaining_time": "1:51:32"}
350
+ {"current_steps": 350, "total_steps": 390, "loss": 0.3874, "lr": 1.2681239331945695e-06, "epoch": 4.48, "percentage": 89.74, "elapsed_time": "15:52:09", "remaining_time": "1:48:49"}
351
+ {"current_steps": 351, "total_steps": 390, "loss": 0.3839, "lr": 1.2061475842818337e-06, "epoch": 4.4928, "percentage": 90.0, "elapsed_time": "15:54:49", "remaining_time": "1:46:05"}
352
+ {"current_steps": 352, "total_steps": 390, "loss": 0.3905, "lr": 1.1456767966083393e-06, "epoch": 4.5056, "percentage": 90.26, "elapsed_time": "15:57:30", "remaining_time": "1:43:22"}
353
+ {"current_steps": 353, "total_steps": 390, "loss": 0.3972, "lr": 1.086716414442952e-06, "epoch": 4.5184, "percentage": 90.51, "elapsed_time": "16:00:05", "remaining_time": "1:40:37"}
354
+ {"current_steps": 354, "total_steps": 390, "loss": 0.3909, "lr": 1.0292711610570904e-06, "epoch": 4.5312, "percentage": 90.77, "elapsed_time": "16:02:48", "remaining_time": "1:37:54"}
355
+ {"current_steps": 355, "total_steps": 390, "loss": 0.3934, "lr": 9.733456383463658e-07, "epoch": 4.5440000000000005, "percentage": 91.03, "elapsed_time": "16:05:39", "remaining_time": "1:35:12"}
356
+ {"current_steps": 356, "total_steps": 390, "loss": 0.3968, "lr": 9.189443264619102e-07, "epoch": 4.5568, "percentage": 91.28, "elapsed_time": "16:08:28", "remaining_time": "1:32:29"}
357
+ {"current_steps": 357, "total_steps": 390, "loss": 0.3724, "lr": 8.660715834514977e-07, "epoch": 4.5696, "percentage": 91.54, "elapsed_time": "16:11:20", "remaining_time": "1:29:47"}
358
+ {"current_steps": 358, "total_steps": 390, "loss": 0.3978, "lr": 8.147316449103959e-07, "epoch": 4.5824, "percentage": 91.79, "elapsed_time": "16:14:12", "remaining_time": "1:27:04"}
359
+ {"current_steps": 359, "total_steps": 390, "loss": 0.3954, "lr": 7.649286236420806e-07, "epoch": 4.5952, "percentage": 92.05, "elapsed_time": "16:16:53", "remaining_time": "1:24:21"}
360
+ {"current_steps": 360, "total_steps": 390, "loss": 0.3839, "lr": 7.166665093287539e-07, "epoch": 4.608, "percentage": 92.31, "elapsed_time": "16:19:51", "remaining_time": "1:21:39"}
361
+ {"current_steps": 361, "total_steps": 390, "loss": 0.3707, "lr": 6.69949168211721e-07, "epoch": 4.6208, "percentage": 92.56, "elapsed_time": "16:22:29", "remaining_time": "1:18:55"}
362
+ {"current_steps": 362, "total_steps": 390, "loss": 0.3802, "lr": 6.247803427816945e-07, "epoch": 4.6336, "percentage": 92.82, "elapsed_time": "16:25:12", "remaining_time": "1:16:12"}
363
+ {"current_steps": 363, "total_steps": 390, "loss": 0.3945, "lr": 5.811636514789598e-07, "epoch": 4.6464, "percentage": 93.08, "elapsed_time": "16:27:56", "remaining_time": "1:13:29"}
364
+ {"current_steps": 364, "total_steps": 390, "loss": 0.3801, "lr": 5.391025884035239e-07, "epoch": 4.6592, "percentage": 93.33, "elapsed_time": "16:30:41", "remaining_time": "1:10:45"}
365
+ {"current_steps": 365, "total_steps": 390, "loss": 0.4021, "lr": 4.986005230351954e-07, "epoch": 4.672, "percentage": 93.59, "elapsed_time": "16:33:18", "remaining_time": "1:08:02"}
366
+ {"current_steps": 366, "total_steps": 390, "loss": 0.3929, "lr": 4.5966069996365993e-07, "epoch": 4.6848, "percentage": 93.85, "elapsed_time": "16:36:02", "remaining_time": "1:05:18"}
367
+ {"current_steps": 367, "total_steps": 390, "loss": 0.3953, "lr": 4.22286238628562e-07, "epoch": 4.6975999999999996, "percentage": 94.1, "elapsed_time": "16:38:39", "remaining_time": "1:02:35"}
368
+ {"current_steps": 368, "total_steps": 390, "loss": 0.3622, "lr": 3.8648013306960664e-07, "epoch": 4.7104, "percentage": 94.36, "elapsed_time": "16:41:04", "remaining_time": "0:59:50"}
369
+ {"current_steps": 369, "total_steps": 390, "loss": 0.3887, "lr": 3.522452516867048e-07, "epoch": 4.7232, "percentage": 94.62, "elapsed_time": "16:43:44", "remaining_time": "0:57:07"}
370
+ {"current_steps": 370, "total_steps": 390, "loss": 0.3831, "lr": 3.1958433701019697e-07, "epoch": 4.736, "percentage": 94.87, "elapsed_time": "16:46:19", "remaining_time": "0:54:23"}
371
+ {"current_steps": 371, "total_steps": 390, "loss": 0.3798, "lr": 2.8850000548115155e-07, "epoch": 4.7488, "percentage": 95.13, "elapsed_time": "16:48:59", "remaining_time": "0:51:40"}
372
+ {"current_steps": 372, "total_steps": 390, "loss": 0.379, "lr": 2.5899474724174313e-07, "epoch": 4.7616, "percentage": 95.38, "elapsed_time": "16:51:32", "remaining_time": "0:48:56"}
373
+ {"current_steps": 373, "total_steps": 390, "loss": 0.3735, "lr": 2.3107092593579905e-07, "epoch": 4.7744, "percentage": 95.64, "elapsed_time": "16:54:18", "remaining_time": "0:46:13"}
374
+ {"current_steps": 374, "total_steps": 390, "loss": 0.3984, "lr": 2.0473077851942858e-07, "epoch": 4.7872, "percentage": 95.9, "elapsed_time": "16:57:05", "remaining_time": "0:43:30"}
375
+ {"current_steps": 375, "total_steps": 390, "loss": 0.3736, "lr": 1.799764150818306e-07, "epoch": 4.8, "percentage": 96.15, "elapsed_time": "16:59:47", "remaining_time": "0:40:47"}
376
+ {"current_steps": 376, "total_steps": 390, "loss": 0.3907, "lr": 1.5680981867625566e-07, "epoch": 4.8128, "percentage": 96.41, "elapsed_time": "17:02:31", "remaining_time": "0:38:04"}
377
+ {"current_steps": 377, "total_steps": 390, "loss": 0.3835, "lr": 1.3523284516113955e-07, "epoch": 4.8256, "percentage": 96.67, "elapsed_time": "17:05:19", "remaining_time": "0:35:21"}
378
+ {"current_steps": 378, "total_steps": 390, "loss": 0.3837, "lr": 1.1524722305144231e-07, "epoch": 4.8384, "percentage": 96.92, "elapsed_time": "17:08:00", "remaining_time": "0:32:38"}
379
+ {"current_steps": 379, "total_steps": 390, "loss": 0.3794, "lr": 9.685455338016347e-08, "epoch": 4.8512, "percentage": 97.18, "elapsed_time": "17:10:44", "remaining_time": "0:29:54"}
380
+ {"current_steps": 380, "total_steps": 390, "loss": 0.3907, "lr": 8.005630957010014e-08, "epoch": 4.864, "percentage": 97.44, "elapsed_time": "17:13:31", "remaining_time": "0:27:11"}
381
+ {"current_steps": 381, "total_steps": 390, "loss": 0.3876, "lr": 6.485383731580142e-08, "epoch": 4.8768, "percentage": 97.69, "elapsed_time": "17:16:16", "remaining_time": "0:24:28"}
382
+ {"current_steps": 382, "total_steps": 390, "loss": 0.3758, "lr": 5.1248354475768034e-08, "epoch": 4.8896, "percentage": 97.95, "elapsed_time": "17:19:09", "remaining_time": "0:21:45"}
383
+ {"current_steps": 383, "total_steps": 390, "loss": 0.3724, "lr": 3.924095097489922e-08, "epoch": 4.9024, "percentage": 98.21, "elapsed_time": "17:21:55", "remaining_time": "0:19:02"}
384
+ {"current_steps": 384, "total_steps": 390, "loss": 0.397, "lr": 2.8832588717164766e-08, "epoch": 4.9152000000000005, "percentage": 98.46, "elapsed_time": "17:24:29", "remaining_time": "0:16:19"}
385
+ {"current_steps": 385, "total_steps": 390, "loss": 0.3833, "lr": 2.0024101508555604e-08, "epoch": 4.928, "percentage": 98.72, "elapsed_time": "17:27:15", "remaining_time": "0:13:36"}
386
+ {"current_steps": 386, "total_steps": 390, "loss": 0.3896, "lr": 1.281619499029274e-08, "epoch": 4.9408, "percentage": 98.97, "elapsed_time": "17:29:53", "remaining_time": "0:10:52"}
387
+ {"current_steps": 387, "total_steps": 390, "loss": 0.3991, "lr": 7.209446582292501e-09, "epoch": 4.9536, "percentage": 99.23, "elapsed_time": "17:32:31", "remaining_time": "0:08:09"}
388
+ {"current_steps": 388, "total_steps": 390, "loss": 0.3827, "lr": 3.2043054369057523e-09, "epoch": 4.9664, "percentage": 99.49, "elapsed_time": "17:35:19", "remaining_time": "0:05:26"}
389
+ {"current_steps": 389, "total_steps": 390, "loss": 0.3851, "lr": 8.010924029533406e-10, "epoch": 4.9792, "percentage": 99.74, "elapsed_time": "17:38:12", "remaining_time": "0:02:43"}
390
+ {"current_steps": 390, "total_steps": 390, "loss": 0.3847, "lr": 0.0, "epoch": 4.992, "percentage": 100.0, "elapsed_time": "17:40:58", "remaining_time": "0:00:00"}
391
+ {"current_steps": 390, "total_steps": 390, "epoch": 4.992, "percentage": 100.0, "elapsed_time": "17:42:48", "remaining_time": "0:00:00"}