ryanmarten commited on
Commit
2eaa7cd
·
verified ·
1 Parent(s): d7a71cb

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:fca25bf42b4bc5e1c25abd6a9b6368ede85157c830d283016131411e346393b6
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:811088c05ec9f1c6fadd3b5f6f26e718c7a23d6bc5048161caad3658ed7fc74f
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:769418db572b72b7c16a9044c7c6261d7033ddf2011b16607014d894eeede3fc
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3215191b56c6e9e91b6ac2bd5b094db6835ccaa7a8a02ed82a0d5bbc194f39e6
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:b193b14d03f15afaf7bf6910a027f8fd24ea5302ff9449e5967d3f6bfe2c3591
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7eb121d7fd1bd84098c70705756ae00c3e99567e56f6bf4a3362e5ab2a4fb3e
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4b3f5cbd95dbd8938e6a1914e2e0c94a6e39c707d416745276b73aea6dc23c8a
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46359eac96f1c67007f3e1adf53343f07117c9060d5107c0a223f3545c4210c6
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -312,3 +312,80 @@
312
  {"current_steps": 312, "total_steps": 390, "loss": 0.4059, "lr": 4.679111137620442e-06, "epoch": 3.9936, "percentage": 80.0, "elapsed_time": "13:03:36", "remaining_time": "3:15:54"}
313
  {"current_steps": 313, "total_steps": 390, "loss": 0.3754, "lr": 4.5646621393177e-06, "epoch": 4.0064, "percentage": 80.26, "elapsed_time": "13:07:09", "remaining_time": "3:13:38"}
314
  {"current_steps": 314, "total_steps": 390, "loss": 0.3787, "lr": 4.451449654204685e-06, "epoch": 4.0192, "percentage": 80.51, "elapsed_time": "13:09:44", "remaining_time": "3:11:08"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
312
  {"current_steps": 312, "total_steps": 390, "loss": 0.4059, "lr": 4.679111137620442e-06, "epoch": 3.9936, "percentage": 80.0, "elapsed_time": "13:03:36", "remaining_time": "3:15:54"}
313
  {"current_steps": 313, "total_steps": 390, "loss": 0.3754, "lr": 4.5646621393177e-06, "epoch": 4.0064, "percentage": 80.26, "elapsed_time": "13:07:09", "remaining_time": "3:13:38"}
314
  {"current_steps": 314, "total_steps": 390, "loss": 0.3787, "lr": 4.451449654204685e-06, "epoch": 4.0192, "percentage": 80.51, "elapsed_time": "13:09:44", "remaining_time": "3:11:08"}
315
+ {"current_steps": 315, "total_steps": 390, "loss": 0.3474, "lr": 4.339482751647557e-06, "epoch": 4.032, "percentage": 80.77, "elapsed_time": "13:12:12", "remaining_time": "3:08:37"}
316
+ {"current_steps": 316, "total_steps": 390, "loss": 0.3439, "lr": 4.228770401229824e-06, "epoch": 4.0448, "percentage": 81.03, "elapsed_time": "13:14:31", "remaining_time": "3:06:03"}
317
+ {"current_steps": 317, "total_steps": 390, "loss": 0.3725, "lr": 4.119321472033779e-06, "epoch": 4.0576, "percentage": 81.28, "elapsed_time": "13:17:13", "remaining_time": "3:03:35"}
318
+ {"current_steps": 318, "total_steps": 390, "loss": 0.3587, "lr": 4.011144731929981e-06, "epoch": 4.0704, "percentage": 81.54, "elapsed_time": "13:19:36", "remaining_time": "3:01:02"}
319
+ {"current_steps": 319, "total_steps": 390, "loss": 0.3593, "lr": 3.904248846874894e-06, "epoch": 4.0832, "percentage": 81.79, "elapsed_time": "13:22:11", "remaining_time": "2:58:32"}
320
+ {"current_steps": 320, "total_steps": 390, "loss": 0.3442, "lr": 3.7986423802166705e-06, "epoch": 4.096, "percentage": 82.05, "elapsed_time": "13:24:34", "remaining_time": "2:55:59"}
321
+ {"current_steps": 321, "total_steps": 390, "loss": 0.3589, "lr": 3.694333792009115e-06, "epoch": 4.1088, "percentage": 82.31, "elapsed_time": "13:27:00", "remaining_time": "2:53:28"}
322
+ {"current_steps": 322, "total_steps": 390, "loss": 0.3482, "lr": 3.5913314383339937e-06, "epoch": 4.1216, "percentage": 82.56, "elapsed_time": "13:29:28", "remaining_time": "2:50:56"}
323
+ {"current_steps": 323, "total_steps": 390, "loss": 0.3303, "lr": 3.4896435706316e-06, "epoch": 4.1344, "percentage": 82.82, "elapsed_time": "13:31:42", "remaining_time": "2:48:22"}
324
+ {"current_steps": 324, "total_steps": 390, "loss": 0.3611, "lr": 3.3892783350397675e-06, "epoch": 4.1472, "percentage": 83.08, "elapsed_time": "13:34:14", "remaining_time": "2:45:51"}
325
+ {"current_steps": 325, "total_steps": 390, "loss": 0.3943, "lr": 3.290243771741275e-06, "epoch": 4.16, "percentage": 83.33, "elapsed_time": "13:36:45", "remaining_time": "2:43:21"}
326
+ {"current_steps": 326, "total_steps": 390, "loss": 0.3556, "lr": 3.1925478143197418e-06, "epoch": 4.1728, "percentage": 83.59, "elapsed_time": "13:39:28", "remaining_time": "2:40:52"}
327
+ {"current_steps": 327, "total_steps": 390, "loss": 0.3638, "lr": 3.0961982891241083e-06, "epoch": 4.1856, "percentage": 83.85, "elapsed_time": "13:42:03", "remaining_time": "2:38:22"}
328
+ {"current_steps": 328, "total_steps": 390, "loss": 0.3674, "lr": 3.001202914641628e-06, "epoch": 4.1984, "percentage": 84.1, "elapsed_time": "13:44:34", "remaining_time": "2:35:51"}
329
+ {"current_steps": 329, "total_steps": 390, "loss": 0.3643, "lr": 2.907569300879596e-06, "epoch": 4.2112, "percentage": 84.36, "elapsed_time": "13:47:13", "remaining_time": "2:33:22"}
330
+ {"current_steps": 330, "total_steps": 390, "loss": 0.3536, "lr": 2.815304948755664e-06, "epoch": 4.224, "percentage": 84.62, "elapsed_time": "13:49:44", "remaining_time": "2:30:51"}
331
+ {"current_steps": 331, "total_steps": 390, "loss": 0.3371, "lr": 2.7244172494969978e-06, "epoch": 4.2368, "percentage": 84.87, "elapsed_time": "13:52:07", "remaining_time": "2:28:19"}
332
+ {"current_steps": 332, "total_steps": 390, "loss": 0.3408, "lr": 2.6349134840481294e-06, "epoch": 4.2496, "percentage": 85.13, "elapsed_time": "13:54:24", "remaining_time": "2:25:46"}
333
+ {"current_steps": 333, "total_steps": 390, "loss": 0.3513, "lr": 2.546800822487714e-06, "epoch": 4.2624, "percentage": 85.38, "elapsed_time": "13:56:49", "remaining_time": "2:23:14"}
334
+ {"current_steps": 334, "total_steps": 390, "loss": 0.3471, "lr": 2.4600863234541338e-06, "epoch": 4.2752, "percentage": 85.64, "elapsed_time": "13:59:15", "remaining_time": "2:20:42"}
335
+ {"current_steps": 335, "total_steps": 390, "loss": 0.3523, "lr": 2.374776933580025e-06, "epoch": 4.288, "percentage": 85.9, "elapsed_time": "14:01:50", "remaining_time": "2:18:12"}
336
+ {"current_steps": 336, "total_steps": 390, "loss": 0.3508, "lr": 2.2908794869358044e-06, "epoch": 4.3008, "percentage": 86.15, "elapsed_time": "14:04:29", "remaining_time": "2:15:43"}
337
+ {"current_steps": 337, "total_steps": 390, "loss": 0.3723, "lr": 2.2084007044821764e-06, "epoch": 4.3136, "percentage": 86.41, "elapsed_time": "14:07:09", "remaining_time": "2:13:14"}
338
+ {"current_steps": 338, "total_steps": 390, "loss": 0.3459, "lr": 2.127347193531757e-06, "epoch": 4.3264, "percentage": 86.67, "elapsed_time": "14:09:33", "remaining_time": "2:10:42"}
339
+ {"current_steps": 339, "total_steps": 390, "loss": 0.3708, "lr": 2.0477254472197237e-06, "epoch": 4.3392, "percentage": 86.92, "elapsed_time": "14:12:06", "remaining_time": "2:08:11"}
340
+ {"current_steps": 340, "total_steps": 390, "loss": 0.3403, "lr": 1.96954184398368e-06, "epoch": 4.352, "percentage": 87.18, "elapsed_time": "14:14:33", "remaining_time": "2:05:40"}
341
+ {"current_steps": 341, "total_steps": 390, "loss": 0.3557, "lr": 1.8928026470526917e-06, "epoch": 4.3648, "percentage": 87.44, "elapsed_time": "14:17:08", "remaining_time": "2:03:10"}
342
+ {"current_steps": 342, "total_steps": 390, "loss": 0.3765, "lr": 1.817514003945524e-06, "epoch": 4.3776, "percentage": 87.69, "elapsed_time": "14:19:42", "remaining_time": "2:00:39"}
343
+ {"current_steps": 343, "total_steps": 390, "loss": 0.3553, "lr": 1.743681945978184e-06, "epoch": 4.3904, "percentage": 87.95, "elapsed_time": "14:22:04", "remaining_time": "1:58:07"}
344
+ {"current_steps": 344, "total_steps": 390, "loss": 0.3454, "lr": 1.6713123877807413e-06, "epoch": 4.4032, "percentage": 88.21, "elapsed_time": "14:24:34", "remaining_time": "1:55:36"}
345
+ {"current_steps": 345, "total_steps": 390, "loss": 0.3595, "lr": 1.6004111268235156e-06, "epoch": 4.416, "percentage": 88.46, "elapsed_time": "14:27:05", "remaining_time": "1:53:05"}
346
+ {"current_steps": 346, "total_steps": 390, "loss": 0.3561, "lr": 1.5309838429526714e-06, "epoch": 4.4288, "percentage": 88.72, "elapsed_time": "14:29:47", "remaining_time": "1:50:36"}
347
+ {"current_steps": 347, "total_steps": 390, "loss": 0.3597, "lr": 1.4630360979351644e-06, "epoch": 4.4416, "percentage": 88.97, "elapsed_time": "14:32:19", "remaining_time": "1:48:05"}
348
+ {"current_steps": 348, "total_steps": 390, "loss": 0.3388, "lr": 1.396573335013236e-06, "epoch": 4.4544, "percentage": 89.23, "elapsed_time": "14:34:35", "remaining_time": "1:45:33"}
349
+ {"current_steps": 349, "total_steps": 390, "loss": 0.3502, "lr": 1.3316008784683265e-06, "epoch": 4.4672, "percentage": 89.49, "elapsed_time": "14:37:07", "remaining_time": "1:43:02"}
350
+ {"current_steps": 350, "total_steps": 390, "loss": 0.3571, "lr": 1.2681239331945695e-06, "epoch": 4.48, "percentage": 89.74, "elapsed_time": "14:39:46", "remaining_time": "1:40:32"}
351
+ {"current_steps": 351, "total_steps": 390, "loss": 0.347, "lr": 1.2061475842818337e-06, "epoch": 4.4928, "percentage": 90.0, "elapsed_time": "14:42:03", "remaining_time": "1:38:00"}
352
+ {"current_steps": 352, "total_steps": 390, "loss": 0.3631, "lr": 1.1456767966083393e-06, "epoch": 4.5056, "percentage": 90.26, "elapsed_time": "14:44:34", "remaining_time": "1:35:29"}
353
+ {"current_steps": 353, "total_steps": 390, "loss": 0.3465, "lr": 1.086716414442952e-06, "epoch": 4.5184, "percentage": 90.51, "elapsed_time": "14:47:07", "remaining_time": "1:32:59"}
354
+ {"current_steps": 354, "total_steps": 390, "loss": 0.3726, "lr": 1.0292711610570904e-06, "epoch": 4.5312, "percentage": 90.77, "elapsed_time": "14:49:22", "remaining_time": "1:30:26"}
355
+ {"current_steps": 355, "total_steps": 390, "loss": 0.3436, "lr": 9.733456383463658e-07, "epoch": 4.5440000000000005, "percentage": 91.03, "elapsed_time": "14:51:57", "remaining_time": "1:27:56"}
356
+ {"current_steps": 356, "total_steps": 390, "loss": 0.3432, "lr": 9.189443264619102e-07, "epoch": 4.5568, "percentage": 91.28, "elapsed_time": "14:54:22", "remaining_time": "1:25:25"}
357
+ {"current_steps": 357, "total_steps": 390, "loss": 0.3466, "lr": 8.660715834514977e-07, "epoch": 4.5696, "percentage": 91.54, "elapsed_time": "14:57:01", "remaining_time": "1:22:55"}
358
+ {"current_steps": 358, "total_steps": 390, "loss": 0.3439, "lr": 8.147316449103959e-07, "epoch": 4.5824, "percentage": 91.79, "elapsed_time": "14:59:22", "remaining_time": "1:20:23"}
359
+ {"current_steps": 359, "total_steps": 390, "loss": 0.3749, "lr": 7.649286236420806e-07, "epoch": 4.5952, "percentage": 92.05, "elapsed_time": "15:01:45", "remaining_time": "1:17:52"}
360
+ {"current_steps": 360, "total_steps": 390, "loss": 0.3456, "lr": 7.166665093287539e-07, "epoch": 4.608, "percentage": 92.31, "elapsed_time": "15:04:17", "remaining_time": "1:15:21"}
361
+ {"current_steps": 361, "total_steps": 390, "loss": 0.3294, "lr": 6.69949168211721e-07, "epoch": 4.6208, "percentage": 92.56, "elapsed_time": "15:06:38", "remaining_time": "1:12:49"}
362
+ {"current_steps": 362, "total_steps": 390, "loss": 0.352, "lr": 6.247803427816945e-07, "epoch": 4.6336, "percentage": 92.82, "elapsed_time": "15:09:03", "remaining_time": "1:10:18"}
363
+ {"current_steps": 363, "total_steps": 390, "loss": 0.3386, "lr": 5.811636514789598e-07, "epoch": 4.6464, "percentage": 93.08, "elapsed_time": "15:11:32", "remaining_time": "1:07:48"}
364
+ {"current_steps": 364, "total_steps": 390, "loss": 0.3615, "lr": 5.391025884035239e-07, "epoch": 4.6592, "percentage": 93.33, "elapsed_time": "15:14:02", "remaining_time": "1:05:17"}
365
+ {"current_steps": 365, "total_steps": 390, "loss": 0.3531, "lr": 4.986005230351954e-07, "epoch": 4.672, "percentage": 93.59, "elapsed_time": "15:16:29", "remaining_time": "1:02:46"}
366
+ {"current_steps": 366, "total_steps": 390, "loss": 0.3622, "lr": 4.5966069996365993e-07, "epoch": 4.6848, "percentage": 93.85, "elapsed_time": "15:19:03", "remaining_time": "1:00:15"}
367
+ {"current_steps": 367, "total_steps": 390, "loss": 0.3644, "lr": 4.22286238628562e-07, "epoch": 4.6975999999999996, "percentage": 94.1, "elapsed_time": "15:21:42", "remaining_time": "0:57:45"}
368
+ {"current_steps": 368, "total_steps": 390, "loss": 0.3481, "lr": 3.8648013306960664e-07, "epoch": 4.7104, "percentage": 94.36, "elapsed_time": "15:24:14", "remaining_time": "0:55:15"}
369
+ {"current_steps": 369, "total_steps": 390, "loss": 0.3658, "lr": 3.522452516867048e-07, "epoch": 4.7232, "percentage": 94.62, "elapsed_time": "15:27:02", "remaining_time": "0:52:45"}
370
+ {"current_steps": 370, "total_steps": 390, "loss": 0.3298, "lr": 3.1958433701019697e-07, "epoch": 4.736, "percentage": 94.87, "elapsed_time": "15:29:30", "remaining_time": "0:50:14"}
371
+ {"current_steps": 371, "total_steps": 390, "loss": 0.3666, "lr": 2.8850000548115155e-07, "epoch": 4.7488, "percentage": 95.13, "elapsed_time": "15:32:06", "remaining_time": "0:47:44"}
372
+ {"current_steps": 372, "total_steps": 390, "loss": 0.355, "lr": 2.5899474724174313e-07, "epoch": 4.7616, "percentage": 95.38, "elapsed_time": "15:34:30", "remaining_time": "0:45:13"}
373
+ {"current_steps": 373, "total_steps": 390, "loss": 0.342, "lr": 2.3107092593579905e-07, "epoch": 4.7744, "percentage": 95.64, "elapsed_time": "15:37:16", "remaining_time": "0:42:43"}
374
+ {"current_steps": 374, "total_steps": 390, "loss": 0.3583, "lr": 2.0473077851942858e-07, "epoch": 4.7872, "percentage": 95.9, "elapsed_time": "15:39:48", "remaining_time": "0:40:12"}
375
+ {"current_steps": 375, "total_steps": 390, "loss": 0.3503, "lr": 1.799764150818306e-07, "epoch": 4.8, "percentage": 96.15, "elapsed_time": "15:42:19", "remaining_time": "0:37:41"}
376
+ {"current_steps": 376, "total_steps": 390, "loss": 0.342, "lr": 1.5680981867625566e-07, "epoch": 4.8128, "percentage": 96.41, "elapsed_time": "15:44:59", "remaining_time": "0:35:11"}
377
+ {"current_steps": 377, "total_steps": 390, "loss": 0.3661, "lr": 1.3523284516113955e-07, "epoch": 4.8256, "percentage": 96.67, "elapsed_time": "15:47:35", "remaining_time": "0:32:40"}
378
+ {"current_steps": 378, "total_steps": 390, "loss": 0.3521, "lr": 1.1524722305144231e-07, "epoch": 4.8384, "percentage": 96.92, "elapsed_time": "15:49:59", "remaining_time": "0:30:09"}
379
+ {"current_steps": 379, "total_steps": 390, "loss": 0.3495, "lr": 9.685455338016347e-08, "epoch": 4.8512, "percentage": 97.18, "elapsed_time": "15:52:29", "remaining_time": "0:27:38"}
380
+ {"current_steps": 380, "total_steps": 390, "loss": 0.3204, "lr": 8.005630957010014e-08, "epoch": 4.864, "percentage": 97.44, "elapsed_time": "15:54:50", "remaining_time": "0:25:07"}
381
+ {"current_steps": 381, "total_steps": 390, "loss": 0.3746, "lr": 6.485383731580142e-08, "epoch": 4.8768, "percentage": 97.69, "elapsed_time": "15:57:24", "remaining_time": "0:22:36"}
382
+ {"current_steps": 382, "total_steps": 390, "loss": 0.3785, "lr": 5.1248354475768034e-08, "epoch": 4.8896, "percentage": 97.95, "elapsed_time": "16:00:10", "remaining_time": "0:20:06"}
383
+ {"current_steps": 383, "total_steps": 390, "loss": 0.3754, "lr": 3.924095097489922e-08, "epoch": 4.9024, "percentage": 98.21, "elapsed_time": "16:02:47", "remaining_time": "0:17:35"}
384
+ {"current_steps": 384, "total_steps": 390, "loss": 0.34, "lr": 2.8832588717164766e-08, "epoch": 4.9152000000000005, "percentage": 98.46, "elapsed_time": "16:05:07", "remaining_time": "0:15:04"}
385
+ {"current_steps": 385, "total_steps": 390, "loss": 0.3366, "lr": 2.0024101508555604e-08, "epoch": 4.928, "percentage": 98.72, "elapsed_time": "16:07:40", "remaining_time": "0:12:34"}
386
+ {"current_steps": 386, "total_steps": 390, "loss": 0.3698, "lr": 1.281619499029274e-08, "epoch": 4.9408, "percentage": 98.97, "elapsed_time": "16:10:27", "remaining_time": "0:10:03"}
387
+ {"current_steps": 387, "total_steps": 390, "loss": 0.3187, "lr": 7.209446582292501e-09, "epoch": 4.9536, "percentage": 99.23, "elapsed_time": "16:12:49", "remaining_time": "0:07:32"}
388
+ {"current_steps": 388, "total_steps": 390, "loss": 0.3696, "lr": 3.2043054369057523e-09, "epoch": 4.9664, "percentage": 99.49, "elapsed_time": "16:15:27", "remaining_time": "0:05:01"}
389
+ {"current_steps": 389, "total_steps": 390, "loss": 0.3557, "lr": 8.010924029533406e-10, "epoch": 4.9792, "percentage": 99.74, "elapsed_time": "16:17:55", "remaining_time": "0:02:30"}
390
+ {"current_steps": 390, "total_steps": 390, "loss": 0.3607, "lr": 0.0, "epoch": 4.992, "percentage": 100.0, "elapsed_time": "16:20:34", "remaining_time": "0:00:00"}
391
+ {"current_steps": 390, "total_steps": 390, "epoch": 4.992, "percentage": 100.0, "elapsed_time": "16:22:14", "remaining_time": "0:00:00"}