ryanmarten commited on
Commit
205efaa
·
verified ·
1 Parent(s): e12e6dc

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:da0d64a50aaebaa876fb6f78b3f18d7f3e4e38722de35a1c32670db927ce513a
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c91d18e7826f6a637630b2f711a88fd3cf361bfd108da9ee77d9d03f5e958346
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:87e7dad299c4732ff65d52d06ac96e3b9548917e2f621f09a49ca09e79d73026
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:119995e6035f2665c0c1f7a5d5a85c0f323de7f4d5e2ce9f4d6a7c55e4357c15
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:882bec17f576e5d8f48f5b818b6cd924db5bcfab3f152c34d334ca3ba5f6408b
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4dd700edb60f8048b139395fab475fc5e3088cdee436003f0a27fa07e741bf1
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:89850a89ac6f38ae35f64d16af0083b9389fae677a86c8ba0a06d27380e05f76
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5439744d6f274d556e198313ecca85a8a11bee84b5c587f35fa7634854401906
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -311,3 +311,81 @@
311
  {"current_steps": 311, "total_steps": 390, "loss": 0.408, "lr": 4.794787480690597e-06, "epoch": 3.9808, "percentage": 79.74, "elapsed_time": "13:50:32", "remaining_time": "3:30:58"}
312
  {"current_steps": 312, "total_steps": 390, "loss": 0.4116, "lr": 4.679111137620442e-06, "epoch": 3.9936, "percentage": 80.0, "elapsed_time": "13:53:05", "remaining_time": "3:28:16"}
313
  {"current_steps": 313, "total_steps": 390, "loss": 0.3876, "lr": 4.5646621393177e-06, "epoch": 4.0064, "percentage": 80.26, "elapsed_time": "13:56:45", "remaining_time": "3:25:50"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
311
  {"current_steps": 311, "total_steps": 390, "loss": 0.408, "lr": 4.794787480690597e-06, "epoch": 3.9808, "percentage": 79.74, "elapsed_time": "13:50:32", "remaining_time": "3:30:58"}
312
  {"current_steps": 312, "total_steps": 390, "loss": 0.4116, "lr": 4.679111137620442e-06, "epoch": 3.9936, "percentage": 80.0, "elapsed_time": "13:53:05", "remaining_time": "3:28:16"}
313
  {"current_steps": 313, "total_steps": 390, "loss": 0.3876, "lr": 4.5646621393177e-06, "epoch": 4.0064, "percentage": 80.26, "elapsed_time": "13:56:45", "remaining_time": "3:25:50"}
314
+ {"current_steps": 314, "total_steps": 390, "loss": 0.3907, "lr": 4.451449654204685e-06, "epoch": 4.0192, "percentage": 80.51, "elapsed_time": "13:59:28", "remaining_time": "3:23:11"}
315
+ {"current_steps": 315, "total_steps": 390, "loss": 0.3655, "lr": 4.339482751647557e-06, "epoch": 4.032, "percentage": 80.77, "elapsed_time": "14:02:08", "remaining_time": "3:20:30"}
316
+ {"current_steps": 316, "total_steps": 390, "loss": 0.3704, "lr": 4.228770401229824e-06, "epoch": 4.0448, "percentage": 81.03, "elapsed_time": "14:04:50", "remaining_time": "3:17:50"}
317
+ {"current_steps": 317, "total_steps": 390, "loss": 0.3568, "lr": 4.119321472033779e-06, "epoch": 4.0576, "percentage": 81.28, "elapsed_time": "14:07:18", "remaining_time": "3:15:07"}
318
+ {"current_steps": 318, "total_steps": 390, "loss": 0.3849, "lr": 4.011144731929981e-06, "epoch": 4.0704, "percentage": 81.54, "elapsed_time": "14:10:01", "remaining_time": "3:12:27"}
319
+ {"current_steps": 319, "total_steps": 390, "loss": 0.3623, "lr": 3.904248846874894e-06, "epoch": 4.0832, "percentage": 81.79, "elapsed_time": "14:12:32", "remaining_time": "3:09:45"}
320
+ {"current_steps": 320, "total_steps": 390, "loss": 0.3617, "lr": 3.7986423802166705e-06, "epoch": 4.096, "percentage": 82.05, "elapsed_time": "14:15:10", "remaining_time": "3:07:04"}
321
+ {"current_steps": 321, "total_steps": 390, "loss": 0.36, "lr": 3.694333792009115e-06, "epoch": 4.1088, "percentage": 82.31, "elapsed_time": "14:17:55", "remaining_time": "3:04:24"}
322
+ {"current_steps": 322, "total_steps": 390, "loss": 0.3638, "lr": 3.5913314383339937e-06, "epoch": 4.1216, "percentage": 82.56, "elapsed_time": "14:20:30", "remaining_time": "3:01:43"}
323
+ {"current_steps": 323, "total_steps": 390, "loss": 0.3797, "lr": 3.4896435706316e-06, "epoch": 4.1344, "percentage": 82.82, "elapsed_time": "14:23:13", "remaining_time": "2:59:03"}
324
+ {"current_steps": 324, "total_steps": 390, "loss": 0.3631, "lr": 3.3892783350397675e-06, "epoch": 4.1472, "percentage": 83.08, "elapsed_time": "14:25:56", "remaining_time": "2:56:23"}
325
+ {"current_steps": 325, "total_steps": 390, "loss": 0.3633, "lr": 3.290243771741275e-06, "epoch": 4.16, "percentage": 83.33, "elapsed_time": "14:28:32", "remaining_time": "2:53:42"}
326
+ {"current_steps": 326, "total_steps": 390, "loss": 0.3532, "lr": 3.1925478143197418e-06, "epoch": 4.1728, "percentage": 83.59, "elapsed_time": "14:31:22", "remaining_time": "2:51:04"}
327
+ {"current_steps": 327, "total_steps": 390, "loss": 0.3592, "lr": 3.0961982891241083e-06, "epoch": 4.1856, "percentage": 83.85, "elapsed_time": "14:33:50", "remaining_time": "2:48:21"}
328
+ {"current_steps": 328, "total_steps": 390, "loss": 0.3689, "lr": 3.001202914641628e-06, "epoch": 4.1984, "percentage": 84.1, "elapsed_time": "14:36:30", "remaining_time": "2:45:40"}
329
+ {"current_steps": 329, "total_steps": 390, "loss": 0.3749, "lr": 2.907569300879596e-06, "epoch": 4.2112, "percentage": 84.36, "elapsed_time": "14:39:10", "remaining_time": "2:43:00"}
330
+ {"current_steps": 330, "total_steps": 390, "loss": 0.3666, "lr": 2.815304948755664e-06, "epoch": 4.224, "percentage": 84.62, "elapsed_time": "14:41:50", "remaining_time": "2:40:20"}
331
+ {"current_steps": 331, "total_steps": 390, "loss": 0.3546, "lr": 2.7244172494969978e-06, "epoch": 4.2368, "percentage": 84.87, "elapsed_time": "14:44:33", "remaining_time": "2:37:40"}
332
+ {"current_steps": 332, "total_steps": 390, "loss": 0.3678, "lr": 2.6349134840481294e-06, "epoch": 4.2496, "percentage": 85.13, "elapsed_time": "14:47:16", "remaining_time": "2:35:00"}
333
+ {"current_steps": 333, "total_steps": 390, "loss": 0.3565, "lr": 2.546800822487714e-06, "epoch": 4.2624, "percentage": 85.38, "elapsed_time": "14:49:51", "remaining_time": "2:32:19"}
334
+ {"current_steps": 334, "total_steps": 390, "loss": 0.3691, "lr": 2.4600863234541338e-06, "epoch": 4.2752, "percentage": 85.64, "elapsed_time": "14:52:23", "remaining_time": "2:29:37"}
335
+ {"current_steps": 335, "total_steps": 390, "loss": 0.3505, "lr": 2.374776933580025e-06, "epoch": 4.288, "percentage": 85.9, "elapsed_time": "14:55:03", "remaining_time": "2:26:57"}
336
+ {"current_steps": 336, "total_steps": 390, "loss": 0.3358, "lr": 2.2908794869358044e-06, "epoch": 4.3008, "percentage": 86.15, "elapsed_time": "14:57:41", "remaining_time": "2:24:16"}
337
+ {"current_steps": 337, "total_steps": 390, "loss": 0.3459, "lr": 2.2084007044821764e-06, "epoch": 4.3136, "percentage": 86.41, "elapsed_time": "15:00:15", "remaining_time": "2:21:35"}
338
+ {"current_steps": 338, "total_steps": 390, "loss": 0.365, "lr": 2.127347193531757e-06, "epoch": 4.3264, "percentage": 86.67, "elapsed_time": "15:03:04", "remaining_time": "2:18:56"}
339
+ {"current_steps": 339, "total_steps": 390, "loss": 0.3719, "lr": 2.0477254472197237e-06, "epoch": 4.3392, "percentage": 86.92, "elapsed_time": "15:05:49", "remaining_time": "2:16:16"}
340
+ {"current_steps": 340, "total_steps": 390, "loss": 0.3638, "lr": 1.96954184398368e-06, "epoch": 4.352, "percentage": 87.18, "elapsed_time": "15:08:23", "remaining_time": "2:13:35"}
341
+ {"current_steps": 341, "total_steps": 390, "loss": 0.3766, "lr": 1.8928026470526917e-06, "epoch": 4.3648, "percentage": 87.44, "elapsed_time": "15:11:04", "remaining_time": "2:10:55"}
342
+ {"current_steps": 342, "total_steps": 390, "loss": 0.3641, "lr": 1.817514003945524e-06, "epoch": 4.3776, "percentage": 87.69, "elapsed_time": "15:13:37", "remaining_time": "2:08:13"}
343
+ {"current_steps": 343, "total_steps": 390, "loss": 0.3641, "lr": 1.743681945978184e-06, "epoch": 4.3904, "percentage": 87.95, "elapsed_time": "15:16:19", "remaining_time": "2:05:33"}
344
+ {"current_steps": 344, "total_steps": 390, "loss": 0.3655, "lr": 1.6713123877807413e-06, "epoch": 4.4032, "percentage": 88.21, "elapsed_time": "15:19:02", "remaining_time": "2:02:53"}
345
+ {"current_steps": 345, "total_steps": 390, "loss": 0.3449, "lr": 1.6004111268235156e-06, "epoch": 4.416, "percentage": 88.46, "elapsed_time": "15:21:45", "remaining_time": "2:00:13"}
346
+ {"current_steps": 346, "total_steps": 390, "loss": 0.3616, "lr": 1.5309838429526714e-06, "epoch": 4.4288, "percentage": 88.72, "elapsed_time": "15:24:27", "remaining_time": "1:57:33"}
347
+ {"current_steps": 347, "total_steps": 390, "loss": 0.3578, "lr": 1.4630360979351644e-06, "epoch": 4.4416, "percentage": 88.97, "elapsed_time": "15:26:58", "remaining_time": "1:54:52"}
348
+ {"current_steps": 348, "total_steps": 390, "loss": 0.3554, "lr": 1.396573335013236e-06, "epoch": 4.4544, "percentage": 89.23, "elapsed_time": "15:29:30", "remaining_time": "1:52:10"}
349
+ {"current_steps": 349, "total_steps": 390, "loss": 0.3595, "lr": 1.3316008784683265e-06, "epoch": 4.4672, "percentage": 89.49, "elapsed_time": "15:32:05", "remaining_time": "1:49:30"}
350
+ {"current_steps": 350, "total_steps": 390, "loss": 0.342, "lr": 1.2681239331945695e-06, "epoch": 4.48, "percentage": 89.74, "elapsed_time": "15:34:40", "remaining_time": "1:46:49"}
351
+ {"current_steps": 351, "total_steps": 390, "loss": 0.351, "lr": 1.2061475842818337e-06, "epoch": 4.4928, "percentage": 90.0, "elapsed_time": "15:37:19", "remaining_time": "1:44:08"}
352
+ {"current_steps": 352, "total_steps": 390, "loss": 0.3624, "lr": 1.1456767966083393e-06, "epoch": 4.5056, "percentage": 90.26, "elapsed_time": "15:40:00", "remaining_time": "1:41:28"}
353
+ {"current_steps": 353, "total_steps": 390, "loss": 0.3569, "lr": 1.086716414442952e-06, "epoch": 4.5184, "percentage": 90.51, "elapsed_time": "15:42:40", "remaining_time": "1:38:48"}
354
+ {"current_steps": 354, "total_steps": 390, "loss": 0.3686, "lr": 1.0292711610570904e-06, "epoch": 4.5312, "percentage": 90.77, "elapsed_time": "15:45:22", "remaining_time": "1:36:08"}
355
+ {"current_steps": 355, "total_steps": 390, "loss": 0.3511, "lr": 9.733456383463658e-07, "epoch": 4.5440000000000005, "percentage": 91.03, "elapsed_time": "15:47:51", "remaining_time": "1:33:27"}
356
+ {"current_steps": 356, "total_steps": 390, "loss": 0.3501, "lr": 9.189443264619102e-07, "epoch": 4.5568, "percentage": 91.28, "elapsed_time": "15:50:27", "remaining_time": "1:30:46"}
357
+ {"current_steps": 357, "total_steps": 390, "loss": 0.356, "lr": 8.660715834514977e-07, "epoch": 4.5696, "percentage": 91.54, "elapsed_time": "15:53:10", "remaining_time": "1:28:06"}
358
+ {"current_steps": 358, "total_steps": 390, "loss": 0.3636, "lr": 8.147316449103959e-07, "epoch": 4.5824, "percentage": 91.79, "elapsed_time": "15:56:00", "remaining_time": "1:25:27"}
359
+ {"current_steps": 359, "total_steps": 390, "loss": 0.3547, "lr": 7.649286236420806e-07, "epoch": 4.5952, "percentage": 92.05, "elapsed_time": "15:58:51", "remaining_time": "1:22:47"}
360
+ {"current_steps": 360, "total_steps": 390, "loss": 0.363, "lr": 7.166665093287539e-07, "epoch": 4.608, "percentage": 92.31, "elapsed_time": "16:01:36", "remaining_time": "1:20:08"}
361
+ {"current_steps": 361, "total_steps": 390, "loss": 0.3596, "lr": 6.69949168211721e-07, "epoch": 4.6208, "percentage": 92.56, "elapsed_time": "16:04:24", "remaining_time": "1:17:28"}
362
+ {"current_steps": 362, "total_steps": 390, "loss": 0.3824, "lr": 6.247803427816945e-07, "epoch": 4.6336, "percentage": 92.82, "elapsed_time": "16:07:07", "remaining_time": "1:14:48"}
363
+ {"current_steps": 363, "total_steps": 390, "loss": 0.3608, "lr": 5.811636514789598e-07, "epoch": 4.6464, "percentage": 93.08, "elapsed_time": "16:09:51", "remaining_time": "1:12:08"}
364
+ {"current_steps": 364, "total_steps": 390, "loss": 0.3594, "lr": 5.391025884035239e-07, "epoch": 4.6592, "percentage": 93.33, "elapsed_time": "16:12:44", "remaining_time": "1:09:28"}
365
+ {"current_steps": 365, "total_steps": 390, "loss": 0.3549, "lr": 4.986005230351954e-07, "epoch": 4.672, "percentage": 93.59, "elapsed_time": "16:15:23", "remaining_time": "1:06:48"}
366
+ {"current_steps": 366, "total_steps": 390, "loss": 0.3491, "lr": 4.5966069996365993e-07, "epoch": 4.6848, "percentage": 93.85, "elapsed_time": "16:18:01", "remaining_time": "1:04:07"}
367
+ {"current_steps": 367, "total_steps": 390, "loss": 0.3684, "lr": 4.22286238628562e-07, "epoch": 4.6975999999999996, "percentage": 94.1, "elapsed_time": "16:20:46", "remaining_time": "1:01:27"}
368
+ {"current_steps": 368, "total_steps": 390, "loss": 0.3566, "lr": 3.8648013306960664e-07, "epoch": 4.7104, "percentage": 94.36, "elapsed_time": "16:23:26", "remaining_time": "0:58:47"}
369
+ {"current_steps": 369, "total_steps": 390, "loss": 0.3655, "lr": 3.522452516867048e-07, "epoch": 4.7232, "percentage": 94.62, "elapsed_time": "16:26:03", "remaining_time": "0:56:07"}
370
+ {"current_steps": 370, "total_steps": 390, "loss": 0.3485, "lr": 3.1958433701019697e-07, "epoch": 4.736, "percentage": 94.87, "elapsed_time": "16:28:35", "remaining_time": "0:53:26"}
371
+ {"current_steps": 371, "total_steps": 390, "loss": 0.3554, "lr": 2.8850000548115155e-07, "epoch": 4.7488, "percentage": 95.13, "elapsed_time": "16:31:15", "remaining_time": "0:50:45"}
372
+ {"current_steps": 372, "total_steps": 390, "loss": 0.3421, "lr": 2.5899474724174313e-07, "epoch": 4.7616, "percentage": 95.38, "elapsed_time": "16:33:58", "remaining_time": "0:48:05"}
373
+ {"current_steps": 373, "total_steps": 390, "loss": 0.3692, "lr": 2.3107092593579905e-07, "epoch": 4.7744, "percentage": 95.64, "elapsed_time": "16:36:49", "remaining_time": "0:45:25"}
374
+ {"current_steps": 374, "total_steps": 390, "loss": 0.3697, "lr": 2.0473077851942858e-07, "epoch": 4.7872, "percentage": 95.9, "elapsed_time": "16:39:34", "remaining_time": "0:42:45"}
375
+ {"current_steps": 375, "total_steps": 390, "loss": 0.3693, "lr": 1.799764150818306e-07, "epoch": 4.8, "percentage": 96.15, "elapsed_time": "16:42:15", "remaining_time": "0:40:05"}
376
+ {"current_steps": 376, "total_steps": 390, "loss": 0.3468, "lr": 1.5680981867625566e-07, "epoch": 4.8128, "percentage": 96.41, "elapsed_time": "16:44:45", "remaining_time": "0:37:24"}
377
+ {"current_steps": 377, "total_steps": 390, "loss": 0.3758, "lr": 1.3523284516113955e-07, "epoch": 4.8256, "percentage": 96.67, "elapsed_time": "16:47:19", "remaining_time": "0:34:44"}
378
+ {"current_steps": 378, "total_steps": 390, "loss": 0.3614, "lr": 1.1524722305144231e-07, "epoch": 4.8384, "percentage": 96.92, "elapsed_time": "16:50:02", "remaining_time": "0:32:03"}
379
+ {"current_steps": 379, "total_steps": 390, "loss": 0.3686, "lr": 9.685455338016347e-08, "epoch": 4.8512, "percentage": 97.18, "elapsed_time": "16:52:46", "remaining_time": "0:29:23"}
380
+ {"current_steps": 380, "total_steps": 390, "loss": 0.3684, "lr": 8.005630957010014e-08, "epoch": 4.864, "percentage": 97.44, "elapsed_time": "16:55:36", "remaining_time": "0:26:43"}
381
+ {"current_steps": 381, "total_steps": 390, "loss": 0.3649, "lr": 6.485383731580142e-08, "epoch": 4.8768, "percentage": 97.69, "elapsed_time": "16:58:17", "remaining_time": "0:24:03"}
382
+ {"current_steps": 382, "total_steps": 390, "loss": 0.357, "lr": 5.1248354475768034e-08, "epoch": 4.8896, "percentage": 97.95, "elapsed_time": "17:00:53", "remaining_time": "0:21:22"}
383
+ {"current_steps": 383, "total_steps": 390, "loss": 0.3609, "lr": 3.924095097489922e-08, "epoch": 4.9024, "percentage": 98.21, "elapsed_time": "17:03:34", "remaining_time": "0:18:42"}
384
+ {"current_steps": 384, "total_steps": 390, "loss": 0.3485, "lr": 2.8832588717164766e-08, "epoch": 4.9152000000000005, "percentage": 98.46, "elapsed_time": "17:06:21", "remaining_time": "0:16:02"}
385
+ {"current_steps": 385, "total_steps": 390, "loss": 0.3441, "lr": 2.0024101508555604e-08, "epoch": 4.928, "percentage": 98.72, "elapsed_time": "17:08:59", "remaining_time": "0:13:21"}
386
+ {"current_steps": 386, "total_steps": 390, "loss": 0.3584, "lr": 1.281619499029274e-08, "epoch": 4.9408, "percentage": 98.97, "elapsed_time": "17:11:35", "remaining_time": "0:10:41"}
387
+ {"current_steps": 387, "total_steps": 390, "loss": 0.3438, "lr": 7.209446582292501e-09, "epoch": 4.9536, "percentage": 99.23, "elapsed_time": "17:14:05", "remaining_time": "0:08:00"}
388
+ {"current_steps": 388, "total_steps": 390, "loss": 0.3589, "lr": 3.2043054369057523e-09, "epoch": 4.9664, "percentage": 99.49, "elapsed_time": "17:16:43", "remaining_time": "0:05:20"}
389
+ {"current_steps": 389, "total_steps": 390, "loss": 0.3551, "lr": 8.010924029533406e-10, "epoch": 4.9792, "percentage": 99.74, "elapsed_time": "17:19:35", "remaining_time": "0:02:40"}
390
+ {"current_steps": 390, "total_steps": 390, "loss": 0.361, "lr": 0.0, "epoch": 4.992, "percentage": 100.0, "elapsed_time": "17:22:23", "remaining_time": "0:00:00"}
391
+ {"current_steps": 390, "total_steps": 390, "epoch": 4.992, "percentage": 100.0, "elapsed_time": "17:24:19", "remaining_time": "0:00:00"}