ryanmarten commited on
Commit
b9b1901
·
verified ·
1 Parent(s): 54f57df

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:e643d15976537ade72e24d0ce8c6f569ac0b22a093d92fbb568c0337ed5ee772
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:321b4d399888fda08a5141aeb55a43c7025701ded5a1ebd406990c361825f080
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1760c9ce7d6d2e302a6ca5a47a7e9a18b8408f98c6d53b25a9e6f3511577e4ff
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7bf279caf51af05b376ff7c59e316b5d1259b2c2ee4d79054c40061dc253e325
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:fcc5823d0046c438c60c20c3dcbe823a9c713bc030d27f117036abbf08117838
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:227bb96e46a3ba9ab7d6a7ff52c85be5029b8569fe79da29bf7837c2d2ad24a5
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:c55b5ae6bfb226fc1a147b006918caaa34e820446be8bbcf47f1d662b7eff217
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7523f4bb04439912f952b7210bfaa5b970c5aad5026bfc831239bf823c718a3f
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -311,3 +311,81 @@
311
  {"current_steps": 311, "total_steps": 390, "loss": 0.368, "lr": 4.794787480690597e-06, "epoch": 3.9808, "percentage": 79.74, "elapsed_time": "12:52:23", "remaining_time": "3:16:12"}
312
  {"current_steps": 312, "total_steps": 390, "loss": 0.3788, "lr": 4.679111137620442e-06, "epoch": 3.9936, "percentage": 80.0, "elapsed_time": "12:54:57", "remaining_time": "3:13:44"}
313
  {"current_steps": 313, "total_steps": 390, "loss": 0.3429, "lr": 4.5646621393177e-06, "epoch": 4.0064, "percentage": 80.26, "elapsed_time": "12:58:08", "remaining_time": "3:11:25"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
311
  {"current_steps": 311, "total_steps": 390, "loss": 0.368, "lr": 4.794787480690597e-06, "epoch": 3.9808, "percentage": 79.74, "elapsed_time": "12:52:23", "remaining_time": "3:16:12"}
312
  {"current_steps": 312, "total_steps": 390, "loss": 0.3788, "lr": 4.679111137620442e-06, "epoch": 3.9936, "percentage": 80.0, "elapsed_time": "12:54:57", "remaining_time": "3:13:44"}
313
  {"current_steps": 313, "total_steps": 390, "loss": 0.3429, "lr": 4.5646621393177e-06, "epoch": 4.0064, "percentage": 80.26, "elapsed_time": "12:58:08", "remaining_time": "3:11:25"}
314
+ {"current_steps": 314, "total_steps": 390, "loss": 0.3471, "lr": 4.451449654204685e-06, "epoch": 4.0192, "percentage": 80.51, "elapsed_time": "13:00:34", "remaining_time": "3:08:55"}
315
+ {"current_steps": 315, "total_steps": 390, "loss": 0.3582, "lr": 4.339482751647557e-06, "epoch": 4.032, "percentage": 80.77, "elapsed_time": "13:03:07", "remaining_time": "3:06:27"}
316
+ {"current_steps": 316, "total_steps": 390, "loss": 0.3564, "lr": 4.228770401229824e-06, "epoch": 4.0448, "percentage": 81.03, "elapsed_time": "13:05:32", "remaining_time": "3:03:57"}
317
+ {"current_steps": 317, "total_steps": 390, "loss": 0.3321, "lr": 4.119321472033779e-06, "epoch": 4.0576, "percentage": 81.28, "elapsed_time": "13:07:48", "remaining_time": "3:01:25"}
318
+ {"current_steps": 318, "total_steps": 390, "loss": 0.3325, "lr": 4.011144731929981e-06, "epoch": 4.0704, "percentage": 81.54, "elapsed_time": "13:10:10", "remaining_time": "2:58:54"}
319
+ {"current_steps": 319, "total_steps": 390, "loss": 0.3276, "lr": 3.904248846874894e-06, "epoch": 4.0832, "percentage": 81.79, "elapsed_time": "13:12:43", "remaining_time": "2:56:26"}
320
+ {"current_steps": 320, "total_steps": 390, "loss": 0.3245, "lr": 3.7986423802166705e-06, "epoch": 4.096, "percentage": 82.05, "elapsed_time": "13:14:55", "remaining_time": "2:53:53"}
321
+ {"current_steps": 321, "total_steps": 390, "loss": 0.3351, "lr": 3.694333792009115e-06, "epoch": 4.1088, "percentage": 82.31, "elapsed_time": "13:17:14", "remaining_time": "2:51:22"}
322
+ {"current_steps": 322, "total_steps": 390, "loss": 0.3528, "lr": 3.5913314383339937e-06, "epoch": 4.1216, "percentage": 82.56, "elapsed_time": "13:19:54", "remaining_time": "2:48:55"}
323
+ {"current_steps": 323, "total_steps": 390, "loss": 0.351, "lr": 3.4896435706316e-06, "epoch": 4.1344, "percentage": 82.82, "elapsed_time": "13:22:24", "remaining_time": "2:46:26"}
324
+ {"current_steps": 324, "total_steps": 390, "loss": 0.309, "lr": 3.3892783350397675e-06, "epoch": 4.1472, "percentage": 83.08, "elapsed_time": "13:24:50", "remaining_time": "2:43:57"}
325
+ {"current_steps": 325, "total_steps": 390, "loss": 0.3427, "lr": 3.290243771741275e-06, "epoch": 4.16, "percentage": 83.33, "elapsed_time": "13:27:05", "remaining_time": "2:41:25"}
326
+ {"current_steps": 326, "total_steps": 390, "loss": 0.3617, "lr": 3.1925478143197418e-06, "epoch": 4.1728, "percentage": 83.59, "elapsed_time": "13:29:39", "remaining_time": "2:38:57"}
327
+ {"current_steps": 327, "total_steps": 390, "loss": 0.3619, "lr": 3.0961982891241083e-06, "epoch": 4.1856, "percentage": 83.85, "elapsed_time": "13:32:12", "remaining_time": "2:36:28"}
328
+ {"current_steps": 328, "total_steps": 390, "loss": 0.3471, "lr": 3.001202914641628e-06, "epoch": 4.1984, "percentage": 84.1, "elapsed_time": "13:34:43", "remaining_time": "2:34:00"}
329
+ {"current_steps": 329, "total_steps": 390, "loss": 0.3311, "lr": 2.907569300879596e-06, "epoch": 4.2112, "percentage": 84.36, "elapsed_time": "13:37:09", "remaining_time": "2:31:30"}
330
+ {"current_steps": 330, "total_steps": 390, "loss": 0.3817, "lr": 2.815304948755664e-06, "epoch": 4.224, "percentage": 84.62, "elapsed_time": "13:39:47", "remaining_time": "2:29:03"}
331
+ {"current_steps": 331, "total_steps": 390, "loss": 0.3361, "lr": 2.7244172494969978e-06, "epoch": 4.2368, "percentage": 84.87, "elapsed_time": "13:42:11", "remaining_time": "2:26:33"}
332
+ {"current_steps": 332, "total_steps": 390, "loss": 0.3233, "lr": 2.6349134840481294e-06, "epoch": 4.2496, "percentage": 85.13, "elapsed_time": "13:44:36", "remaining_time": "2:24:03"}
333
+ {"current_steps": 333, "total_steps": 390, "loss": 0.347, "lr": 2.546800822487714e-06, "epoch": 4.2624, "percentage": 85.38, "elapsed_time": "13:47:02", "remaining_time": "2:21:33"}
334
+ {"current_steps": 334, "total_steps": 390, "loss": 0.3553, "lr": 2.4600863234541338e-06, "epoch": 4.2752, "percentage": 85.64, "elapsed_time": "13:49:27", "remaining_time": "2:19:04"}
335
+ {"current_steps": 335, "total_steps": 390, "loss": 0.3484, "lr": 2.374776933580025e-06, "epoch": 4.288, "percentage": 85.9, "elapsed_time": "13:52:01", "remaining_time": "2:16:36"}
336
+ {"current_steps": 336, "total_steps": 390, "loss": 0.3388, "lr": 2.2908794869358044e-06, "epoch": 4.3008, "percentage": 86.15, "elapsed_time": "13:54:45", "remaining_time": "2:14:09"}
337
+ {"current_steps": 337, "total_steps": 390, "loss": 0.3554, "lr": 2.2084007044821764e-06, "epoch": 4.3136, "percentage": 86.41, "elapsed_time": "13:57:25", "remaining_time": "2:11:42"}
338
+ {"current_steps": 338, "total_steps": 390, "loss": 0.3124, "lr": 2.127347193531757e-06, "epoch": 4.3264, "percentage": 86.67, "elapsed_time": "13:59:43", "remaining_time": "2:09:11"}
339
+ {"current_steps": 339, "total_steps": 390, "loss": 0.3389, "lr": 2.0477254472197237e-06, "epoch": 4.3392, "percentage": 86.92, "elapsed_time": "14:02:15", "remaining_time": "2:06:42"}
340
+ {"current_steps": 340, "total_steps": 390, "loss": 0.3627, "lr": 1.96954184398368e-06, "epoch": 4.352, "percentage": 87.18, "elapsed_time": "14:04:38", "remaining_time": "2:04:12"}
341
+ {"current_steps": 341, "total_steps": 390, "loss": 0.32, "lr": 1.8928026470526917e-06, "epoch": 4.3648, "percentage": 87.44, "elapsed_time": "14:07:05", "remaining_time": "2:01:43"}
342
+ {"current_steps": 342, "total_steps": 390, "loss": 0.3464, "lr": 1.817514003945524e-06, "epoch": 4.3776, "percentage": 87.69, "elapsed_time": "14:09:26", "remaining_time": "1:59:13"}
343
+ {"current_steps": 343, "total_steps": 390, "loss": 0.3678, "lr": 1.743681945978184e-06, "epoch": 4.3904, "percentage": 87.95, "elapsed_time": "14:11:51", "remaining_time": "1:56:43"}
344
+ {"current_steps": 344, "total_steps": 390, "loss": 0.3263, "lr": 1.6713123877807413e-06, "epoch": 4.4032, "percentage": 88.21, "elapsed_time": "14:14:35", "remaining_time": "1:54:16"}
345
+ {"current_steps": 345, "total_steps": 390, "loss": 0.3458, "lr": 1.6004111268235156e-06, "epoch": 4.416, "percentage": 88.46, "elapsed_time": "14:17:04", "remaining_time": "1:51:47"}
346
+ {"current_steps": 346, "total_steps": 390, "loss": 0.3465, "lr": 1.5309838429526714e-06, "epoch": 4.4288, "percentage": 88.72, "elapsed_time": "14:19:38", "remaining_time": "1:49:19"}
347
+ {"current_steps": 347, "total_steps": 390, "loss": 0.3572, "lr": 1.4630360979351644e-06, "epoch": 4.4416, "percentage": 88.97, "elapsed_time": "14:21:57", "remaining_time": "1:46:48"}
348
+ {"current_steps": 348, "total_steps": 390, "loss": 0.348, "lr": 1.396573335013236e-06, "epoch": 4.4544, "percentage": 89.23, "elapsed_time": "14:24:26", "remaining_time": "1:44:19"}
349
+ {"current_steps": 349, "total_steps": 390, "loss": 0.3435, "lr": 1.3316008784683265e-06, "epoch": 4.4672, "percentage": 89.49, "elapsed_time": "14:26:52", "remaining_time": "1:41:50"}
350
+ {"current_steps": 350, "total_steps": 390, "loss": 0.3479, "lr": 1.2681239331945695e-06, "epoch": 4.48, "percentage": 89.74, "elapsed_time": "14:29:36", "remaining_time": "1:39:23"}
351
+ {"current_steps": 351, "total_steps": 390, "loss": 0.3378, "lr": 1.2061475842818337e-06, "epoch": 4.4928, "percentage": 90.0, "elapsed_time": "14:32:03", "remaining_time": "1:36:53"}
352
+ {"current_steps": 352, "total_steps": 390, "loss": 0.3552, "lr": 1.1456767966083393e-06, "epoch": 4.5056, "percentage": 90.26, "elapsed_time": "14:34:23", "remaining_time": "1:34:23"}
353
+ {"current_steps": 353, "total_steps": 390, "loss": 0.3679, "lr": 1.086716414442952e-06, "epoch": 4.5184, "percentage": 90.51, "elapsed_time": "14:37:00", "remaining_time": "1:31:55"}
354
+ {"current_steps": 354, "total_steps": 390, "loss": 0.3625, "lr": 1.0292711610570904e-06, "epoch": 4.5312, "percentage": 90.77, "elapsed_time": "14:39:38", "remaining_time": "1:29:27"}
355
+ {"current_steps": 355, "total_steps": 390, "loss": 0.3352, "lr": 9.733456383463658e-07, "epoch": 4.5440000000000005, "percentage": 91.03, "elapsed_time": "14:42:10", "remaining_time": "1:26:58"}
356
+ {"current_steps": 356, "total_steps": 390, "loss": 0.3598, "lr": 9.189443264619102e-07, "epoch": 4.5568, "percentage": 91.28, "elapsed_time": "14:44:43", "remaining_time": "1:24:29"}
357
+ {"current_steps": 357, "total_steps": 390, "loss": 0.3536, "lr": 8.660715834514977e-07, "epoch": 4.5696, "percentage": 91.54, "elapsed_time": "14:47:15", "remaining_time": "1:22:00"}
358
+ {"current_steps": 358, "total_steps": 390, "loss": 0.3488, "lr": 8.147316449103959e-07, "epoch": 4.5824, "percentage": 91.79, "elapsed_time": "14:49:52", "remaining_time": "1:19:32"}
359
+ {"current_steps": 359, "total_steps": 390, "loss": 0.3383, "lr": 7.649286236420806e-07, "epoch": 4.5952, "percentage": 92.05, "elapsed_time": "14:52:17", "remaining_time": "1:17:02"}
360
+ {"current_steps": 360, "total_steps": 390, "loss": 0.3362, "lr": 7.166665093287539e-07, "epoch": 4.608, "percentage": 92.31, "elapsed_time": "14:54:47", "remaining_time": "1:14:33"}
361
+ {"current_steps": 361, "total_steps": 390, "loss": 0.3325, "lr": 6.69949168211721e-07, "epoch": 4.6208, "percentage": 92.56, "elapsed_time": "14:57:19", "remaining_time": "1:12:05"}
362
+ {"current_steps": 362, "total_steps": 390, "loss": 0.3331, "lr": 6.247803427816945e-07, "epoch": 4.6336, "percentage": 92.82, "elapsed_time": "14:59:46", "remaining_time": "1:09:35"}
363
+ {"current_steps": 363, "total_steps": 390, "loss": 0.3366, "lr": 5.811636514789598e-07, "epoch": 4.6464, "percentage": 93.08, "elapsed_time": "15:02:00", "remaining_time": "1:07:05"}
364
+ {"current_steps": 364, "total_steps": 390, "loss": 0.3307, "lr": 5.391025884035239e-07, "epoch": 4.6592, "percentage": 93.33, "elapsed_time": "15:04:22", "remaining_time": "1:04:35"}
365
+ {"current_steps": 365, "total_steps": 390, "loss": 0.354, "lr": 4.986005230351954e-07, "epoch": 4.672, "percentage": 93.59, "elapsed_time": "15:06:54", "remaining_time": "1:02:07"}
366
+ {"current_steps": 366, "total_steps": 390, "loss": 0.337, "lr": 4.5966069996365993e-07, "epoch": 4.6848, "percentage": 93.85, "elapsed_time": "15:09:22", "remaining_time": "0:59:37"}
367
+ {"current_steps": 367, "total_steps": 390, "loss": 0.3379, "lr": 4.22286238628562e-07, "epoch": 4.6975999999999996, "percentage": 94.1, "elapsed_time": "15:11:49", "remaining_time": "0:57:08"}
368
+ {"current_steps": 368, "total_steps": 390, "loss": 0.3454, "lr": 3.8648013306960664e-07, "epoch": 4.7104, "percentage": 94.36, "elapsed_time": "15:14:20", "remaining_time": "0:54:39"}
369
+ {"current_steps": 369, "total_steps": 390, "loss": 0.3378, "lr": 3.522452516867048e-07, "epoch": 4.7232, "percentage": 94.62, "elapsed_time": "15:16:51", "remaining_time": "0:52:10"}
370
+ {"current_steps": 370, "total_steps": 390, "loss": 0.3434, "lr": 3.1958433701019697e-07, "epoch": 4.736, "percentage": 94.87, "elapsed_time": "15:19:22", "remaining_time": "0:49:41"}
371
+ {"current_steps": 371, "total_steps": 390, "loss": 0.3522, "lr": 2.8850000548115155e-07, "epoch": 4.7488, "percentage": 95.13, "elapsed_time": "15:22:01", "remaining_time": "0:47:13"}
372
+ {"current_steps": 372, "total_steps": 390, "loss": 0.34, "lr": 2.5899474724174313e-07, "epoch": 4.7616, "percentage": 95.38, "elapsed_time": "15:24:26", "remaining_time": "0:44:43"}
373
+ {"current_steps": 373, "total_steps": 390, "loss": 0.3521, "lr": 2.3107092593579905e-07, "epoch": 4.7744, "percentage": 95.64, "elapsed_time": "15:26:58", "remaining_time": "0:42:14"}
374
+ {"current_steps": 374, "total_steps": 390, "loss": 0.3176, "lr": 2.0473077851942858e-07, "epoch": 4.7872, "percentage": 95.9, "elapsed_time": "15:29:19", "remaining_time": "0:39:45"}
375
+ {"current_steps": 375, "total_steps": 390, "loss": 0.3345, "lr": 1.799764150818306e-07, "epoch": 4.8, "percentage": 96.15, "elapsed_time": "15:31:37", "remaining_time": "0:37:15"}
376
+ {"current_steps": 376, "total_steps": 390, "loss": 0.3617, "lr": 1.5680981867625566e-07, "epoch": 4.8128, "percentage": 96.41, "elapsed_time": "15:34:14", "remaining_time": "0:34:47"}
377
+ {"current_steps": 377, "total_steps": 390, "loss": 0.3259, "lr": 1.3523284516113955e-07, "epoch": 4.8256, "percentage": 96.67, "elapsed_time": "15:36:49", "remaining_time": "0:32:18"}
378
+ {"current_steps": 378, "total_steps": 390, "loss": 0.3434, "lr": 1.1524722305144231e-07, "epoch": 4.8384, "percentage": 96.92, "elapsed_time": "15:39:18", "remaining_time": "0:29:49"}
379
+ {"current_steps": 379, "total_steps": 390, "loss": 0.332, "lr": 9.685455338016347e-08, "epoch": 4.8512, "percentage": 97.18, "elapsed_time": "15:41:43", "remaining_time": "0:27:19"}
380
+ {"current_steps": 380, "total_steps": 390, "loss": 0.3262, "lr": 8.005630957010014e-08, "epoch": 4.864, "percentage": 97.44, "elapsed_time": "15:44:04", "remaining_time": "0:24:50"}
381
+ {"current_steps": 381, "total_steps": 390, "loss": 0.3182, "lr": 6.485383731580142e-08, "epoch": 4.8768, "percentage": 97.69, "elapsed_time": "15:46:39", "remaining_time": "0:22:21"}
382
+ {"current_steps": 382, "total_steps": 390, "loss": 0.3352, "lr": 5.1248354475768034e-08, "epoch": 4.8896, "percentage": 97.95, "elapsed_time": "15:49:16", "remaining_time": "0:19:52"}
383
+ {"current_steps": 383, "total_steps": 390, "loss": 0.3525, "lr": 3.924095097489922e-08, "epoch": 4.9024, "percentage": 98.21, "elapsed_time": "15:51:46", "remaining_time": "0:17:23"}
384
+ {"current_steps": 384, "total_steps": 390, "loss": 0.3381, "lr": 2.8832588717164766e-08, "epoch": 4.9152000000000005, "percentage": 98.46, "elapsed_time": "15:54:16", "remaining_time": "0:14:54"}
385
+ {"current_steps": 385, "total_steps": 390, "loss": 0.3303, "lr": 2.0024101508555604e-08, "epoch": 4.928, "percentage": 98.72, "elapsed_time": "15:56:39", "remaining_time": "0:12:25"}
386
+ {"current_steps": 386, "total_steps": 390, "loss": 0.3179, "lr": 1.281619499029274e-08, "epoch": 4.9408, "percentage": 98.97, "elapsed_time": "15:58:57", "remaining_time": "0:09:56"}
387
+ {"current_steps": 387, "total_steps": 390, "loss": 0.3524, "lr": 7.209446582292501e-09, "epoch": 4.9536, "percentage": 99.23, "elapsed_time": "16:01:27", "remaining_time": "0:07:27"}
388
+ {"current_steps": 388, "total_steps": 390, "loss": 0.3182, "lr": 3.2043054369057523e-09, "epoch": 4.9664, "percentage": 99.49, "elapsed_time": "16:03:50", "remaining_time": "0:04:58"}
389
+ {"current_steps": 389, "total_steps": 390, "loss": 0.3207, "lr": 8.010924029533406e-10, "epoch": 4.9792, "percentage": 99.74, "elapsed_time": "16:06:03", "remaining_time": "0:02:29"}
390
+ {"current_steps": 390, "total_steps": 390, "loss": 0.3288, "lr": 0.0, "epoch": 4.992, "percentage": 100.0, "elapsed_time": "16:08:26", "remaining_time": "0:00:00"}
391
+ {"current_steps": 390, "total_steps": 390, "epoch": 4.992, "percentage": 100.0, "elapsed_time": "16:10:05", "remaining_time": "0:00:00"}