ryanmarten commited on
Commit
d942f10
·
verified ·
1 Parent(s): 403b76a

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:c6d8101cdce6e694c4af88437f69bcf37a6a205cf425bc251ea9c9ace2982c66
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be65528abe8122101b62b3fbabcf5a8c6fd9e167f80e5ca9ef757592b19842dd
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8ad22355b681c07868e40fae0524e91a495aae2e5b57621eecec2770687b0ad9
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b7d1ddbd429240470fb07036301c9dde2830b1d9b483149ca88a3969fab1c99
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:37a708249a46acdc8f53ccf6c5a65471edf3f59e0f547521bc6ebf0bcbfe3d6f
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eca8cfc81cccfdd6159ab747e5e44add657277361f3c516fd15e74d86f680b96
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:52e64d0de4d60ea932a165f35507488bdcdaf4dd2ffa47038ce2f96a2d4b3aaf
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84db5e95e009ba920a48bb6bb550bc22a46f04b07e32c7ef2cbecf2f9eca1a00
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -314,3 +314,78 @@
314
  {"current_steps": 314, "total_steps": 390, "loss": 0.2344, "lr": 4.451449654204685e-06, "epoch": 4.0192, "percentage": 80.51, "elapsed_time": "8:50:20", "remaining_time": "2:08:21"}
315
  {"current_steps": 315, "total_steps": 390, "loss": 0.2562, "lr": 4.339482751647557e-06, "epoch": 4.032, "percentage": 80.77, "elapsed_time": "8:52:01", "remaining_time": "2:06:40"}
316
  {"current_steps": 316, "total_steps": 390, "loss": 0.2649, "lr": 4.228770401229824e-06, "epoch": 4.0448, "percentage": 81.03, "elapsed_time": "8:53:39", "remaining_time": "2:04:58"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
314
  {"current_steps": 314, "total_steps": 390, "loss": 0.2344, "lr": 4.451449654204685e-06, "epoch": 4.0192, "percentage": 80.51, "elapsed_time": "8:50:20", "remaining_time": "2:08:21"}
315
  {"current_steps": 315, "total_steps": 390, "loss": 0.2562, "lr": 4.339482751647557e-06, "epoch": 4.032, "percentage": 80.77, "elapsed_time": "8:52:01", "remaining_time": "2:06:40"}
316
  {"current_steps": 316, "total_steps": 390, "loss": 0.2649, "lr": 4.228770401229824e-06, "epoch": 4.0448, "percentage": 81.03, "elapsed_time": "8:53:39", "remaining_time": "2:04:58"}
317
+ {"current_steps": 317, "total_steps": 390, "loss": 0.2444, "lr": 4.119321472033779e-06, "epoch": 4.0576, "percentage": 81.28, "elapsed_time": "8:55:17", "remaining_time": "2:03:16"}
318
+ {"current_steps": 318, "total_steps": 390, "loss": 0.2567, "lr": 4.011144731929981e-06, "epoch": 4.0704, "percentage": 81.54, "elapsed_time": "8:57:04", "remaining_time": "2:01:36"}
319
+ {"current_steps": 319, "total_steps": 390, "loss": 0.2688, "lr": 3.904248846874894e-06, "epoch": 4.0832, "percentage": 81.79, "elapsed_time": "8:58:51", "remaining_time": "1:59:56"}
320
+ {"current_steps": 320, "total_steps": 390, "loss": 0.253, "lr": 3.7986423802166705e-06, "epoch": 4.096, "percentage": 82.05, "elapsed_time": "9:00:29", "remaining_time": "1:58:13"}
321
+ {"current_steps": 321, "total_steps": 390, "loss": 0.2513, "lr": 3.694333792009115e-06, "epoch": 4.1088, "percentage": 82.31, "elapsed_time": "9:02:06", "remaining_time": "1:56:31"}
322
+ {"current_steps": 322, "total_steps": 390, "loss": 0.2523, "lr": 3.5913314383339937e-06, "epoch": 4.1216, "percentage": 82.56, "elapsed_time": "9:03:46", "remaining_time": "1:54:50"}
323
+ {"current_steps": 323, "total_steps": 390, "loss": 0.2537, "lr": 3.4896435706316e-06, "epoch": 4.1344, "percentage": 82.82, "elapsed_time": "9:05:24", "remaining_time": "1:53:08"}
324
+ {"current_steps": 324, "total_steps": 390, "loss": 0.2288, "lr": 3.3892783350397675e-06, "epoch": 4.1472, "percentage": 83.08, "elapsed_time": "9:07:16", "remaining_time": "1:51:28"}
325
+ {"current_steps": 325, "total_steps": 390, "loss": 0.2313, "lr": 3.290243771741275e-06, "epoch": 4.16, "percentage": 83.33, "elapsed_time": "9:08:51", "remaining_time": "1:49:46"}
326
+ {"current_steps": 326, "total_steps": 390, "loss": 0.2257, "lr": 3.1925478143197418e-06, "epoch": 4.1728, "percentage": 83.59, "elapsed_time": "9:10:39", "remaining_time": "1:48:06"}
327
+ {"current_steps": 327, "total_steps": 390, "loss": 0.2397, "lr": 3.0961982891241083e-06, "epoch": 4.1856, "percentage": 83.85, "elapsed_time": "9:12:08", "remaining_time": "1:46:22"}
328
+ {"current_steps": 328, "total_steps": 390, "loss": 0.2639, "lr": 3.001202914641628e-06, "epoch": 4.1984, "percentage": 84.1, "elapsed_time": "9:13:47", "remaining_time": "1:44:40"}
329
+ {"current_steps": 329, "total_steps": 390, "loss": 0.2302, "lr": 2.907569300879596e-06, "epoch": 4.2112, "percentage": 84.36, "elapsed_time": "9:15:20", "remaining_time": "1:42:58"}
330
+ {"current_steps": 330, "total_steps": 390, "loss": 0.2585, "lr": 2.815304948755664e-06, "epoch": 4.224, "percentage": 84.62, "elapsed_time": "9:16:56", "remaining_time": "1:41:15"}
331
+ {"current_steps": 331, "total_steps": 390, "loss": 0.2633, "lr": 2.7244172494969978e-06, "epoch": 4.2368, "percentage": 84.87, "elapsed_time": "9:18:40", "remaining_time": "1:39:34"}
332
+ {"current_steps": 332, "total_steps": 390, "loss": 0.2346, "lr": 2.6349134840481294e-06, "epoch": 4.2496, "percentage": 85.13, "elapsed_time": "9:20:13", "remaining_time": "1:37:52"}
333
+ {"current_steps": 333, "total_steps": 390, "loss": 0.2697, "lr": 2.546800822487714e-06, "epoch": 4.2624, "percentage": 85.38, "elapsed_time": "9:21:57", "remaining_time": "1:36:11"}
334
+ {"current_steps": 334, "total_steps": 390, "loss": 0.2539, "lr": 2.4600863234541338e-06, "epoch": 4.2752, "percentage": 85.64, "elapsed_time": "9:23:46", "remaining_time": "1:34:31"}
335
+ {"current_steps": 335, "total_steps": 390, "loss": 0.2475, "lr": 2.374776933580025e-06, "epoch": 4.288, "percentage": 85.9, "elapsed_time": "9:25:34", "remaining_time": "1:32:51"}
336
+ {"current_steps": 336, "total_steps": 390, "loss": 0.2352, "lr": 2.2908794869358044e-06, "epoch": 4.3008, "percentage": 86.15, "elapsed_time": "9:27:04", "remaining_time": "1:31:08"}
337
+ {"current_steps": 337, "total_steps": 390, "loss": 0.2406, "lr": 2.2084007044821764e-06, "epoch": 4.3136, "percentage": 86.41, "elapsed_time": "9:28:31", "remaining_time": "1:29:24"}
338
+ {"current_steps": 338, "total_steps": 390, "loss": 0.2469, "lr": 2.127347193531757e-06, "epoch": 4.3264, "percentage": 86.67, "elapsed_time": "9:30:09", "remaining_time": "1:27:42"}
339
+ {"current_steps": 339, "total_steps": 390, "loss": 0.2089, "lr": 2.0477254472197237e-06, "epoch": 4.3392, "percentage": 86.92, "elapsed_time": "9:32:01", "remaining_time": "1:26:03"}
340
+ {"current_steps": 340, "total_steps": 390, "loss": 0.2863, "lr": 1.96954184398368e-06, "epoch": 4.352, "percentage": 87.18, "elapsed_time": "9:33:47", "remaining_time": "1:24:22"}
341
+ {"current_steps": 341, "total_steps": 390, "loss": 0.2616, "lr": 1.8928026470526917e-06, "epoch": 4.3648, "percentage": 87.44, "elapsed_time": "9:35:14", "remaining_time": "1:22:39"}
342
+ {"current_steps": 342, "total_steps": 390, "loss": 0.2722, "lr": 1.817514003945524e-06, "epoch": 4.3776, "percentage": 87.69, "elapsed_time": "9:37:03", "remaining_time": "1:20:59"}
343
+ {"current_steps": 343, "total_steps": 390, "loss": 0.2568, "lr": 1.743681945978184e-06, "epoch": 4.3904, "percentage": 87.95, "elapsed_time": "9:38:31", "remaining_time": "1:19:16"}
344
+ {"current_steps": 344, "total_steps": 390, "loss": 0.1929, "lr": 1.6713123877807413e-06, "epoch": 4.4032, "percentage": 88.21, "elapsed_time": "9:40:09", "remaining_time": "1:17:34"}
345
+ {"current_steps": 345, "total_steps": 390, "loss": 0.2475, "lr": 1.6004111268235156e-06, "epoch": 4.416, "percentage": 88.46, "elapsed_time": "9:41:52", "remaining_time": "1:15:53"}
346
+ {"current_steps": 346, "total_steps": 390, "loss": 0.2545, "lr": 1.5309838429526714e-06, "epoch": 4.4288, "percentage": 88.72, "elapsed_time": "9:43:23", "remaining_time": "1:14:11"}
347
+ {"current_steps": 347, "total_steps": 390, "loss": 0.2507, "lr": 1.4630360979351644e-06, "epoch": 4.4416, "percentage": 88.97, "elapsed_time": "9:45:08", "remaining_time": "1:12:30"}
348
+ {"current_steps": 348, "total_steps": 390, "loss": 0.2216, "lr": 1.396573335013236e-06, "epoch": 4.4544, "percentage": 89.23, "elapsed_time": "9:46:45", "remaining_time": "1:10:48"}
349
+ {"current_steps": 349, "total_steps": 390, "loss": 0.2208, "lr": 1.3316008784683265e-06, "epoch": 4.4672, "percentage": 89.49, "elapsed_time": "9:48:31", "remaining_time": "1:09:08"}
350
+ {"current_steps": 350, "total_steps": 390, "loss": 0.2337, "lr": 1.2681239331945695e-06, "epoch": 4.48, "percentage": 89.74, "elapsed_time": "9:50:14", "remaining_time": "1:07:27"}
351
+ {"current_steps": 351, "total_steps": 390, "loss": 0.2195, "lr": 1.2061475842818337e-06, "epoch": 4.4928, "percentage": 90.0, "elapsed_time": "9:51:48", "remaining_time": "1:05:45"}
352
+ {"current_steps": 352, "total_steps": 390, "loss": 0.2401, "lr": 1.1456767966083393e-06, "epoch": 4.5056, "percentage": 90.26, "elapsed_time": "9:53:24", "remaining_time": "1:04:03"}
353
+ {"current_steps": 353, "total_steps": 390, "loss": 0.241, "lr": 1.086716414442952e-06, "epoch": 4.5184, "percentage": 90.51, "elapsed_time": "9:55:03", "remaining_time": "1:02:22"}
354
+ {"current_steps": 354, "total_steps": 390, "loss": 0.255, "lr": 1.0292711610570904e-06, "epoch": 4.5312, "percentage": 90.77, "elapsed_time": "9:56:45", "remaining_time": "1:00:41"}
355
+ {"current_steps": 355, "total_steps": 390, "loss": 0.2556, "lr": 9.733456383463658e-07, "epoch": 4.5440000000000005, "percentage": 91.03, "elapsed_time": "9:58:21", "remaining_time": "0:58:59"}
356
+ {"current_steps": 356, "total_steps": 390, "loss": 0.2563, "lr": 9.189443264619102e-07, "epoch": 4.5568, "percentage": 91.28, "elapsed_time": "10:00:11", "remaining_time": "0:57:19"}
357
+ {"current_steps": 357, "total_steps": 390, "loss": 0.255, "lr": 8.660715834514977e-07, "epoch": 4.5696, "percentage": 91.54, "elapsed_time": "10:01:48", "remaining_time": "0:55:37"}
358
+ {"current_steps": 358, "total_steps": 390, "loss": 0.2688, "lr": 8.147316449103959e-07, "epoch": 4.5824, "percentage": 91.79, "elapsed_time": "10:03:40", "remaining_time": "0:53:57"}
359
+ {"current_steps": 359, "total_steps": 390, "loss": 0.2309, "lr": 7.649286236420806e-07, "epoch": 4.5952, "percentage": 92.05, "elapsed_time": "10:05:11", "remaining_time": "0:52:15"}
360
+ {"current_steps": 360, "total_steps": 390, "loss": 0.2519, "lr": 7.166665093287539e-07, "epoch": 4.608, "percentage": 92.31, "elapsed_time": "10:06:55", "remaining_time": "0:50:34"}
361
+ {"current_steps": 361, "total_steps": 390, "loss": 0.2462, "lr": 6.69949168211721e-07, "epoch": 4.6208, "percentage": 92.56, "elapsed_time": "10:08:31", "remaining_time": "0:48:53"}
362
+ {"current_steps": 362, "total_steps": 390, "loss": 0.2308, "lr": 6.247803427816945e-07, "epoch": 4.6336, "percentage": 92.82, "elapsed_time": "10:10:13", "remaining_time": "0:47:12"}
363
+ {"current_steps": 363, "total_steps": 390, "loss": 0.2508, "lr": 5.811636514789598e-07, "epoch": 4.6464, "percentage": 93.08, "elapsed_time": "10:11:48", "remaining_time": "0:45:30"}
364
+ {"current_steps": 364, "total_steps": 390, "loss": 0.2541, "lr": 5.391025884035239e-07, "epoch": 4.6592, "percentage": 93.33, "elapsed_time": "10:13:33", "remaining_time": "0:43:49"}
365
+ {"current_steps": 365, "total_steps": 390, "loss": 0.2857, "lr": 4.986005230351954e-07, "epoch": 4.672, "percentage": 93.59, "elapsed_time": "10:15:30", "remaining_time": "0:42:09"}
366
+ {"current_steps": 366, "total_steps": 390, "loss": 0.2112, "lr": 4.5966069996365993e-07, "epoch": 4.6848, "percentage": 93.85, "elapsed_time": "10:17:01", "remaining_time": "0:40:27"}
367
+ {"current_steps": 367, "total_steps": 390, "loss": 0.2404, "lr": 4.22286238628562e-07, "epoch": 4.6975999999999996, "percentage": 94.1, "elapsed_time": "10:18:39", "remaining_time": "0:38:46"}
368
+ {"current_steps": 368, "total_steps": 390, "loss": 0.2636, "lr": 3.8648013306960664e-07, "epoch": 4.7104, "percentage": 94.36, "elapsed_time": "10:20:28", "remaining_time": "0:37:05"}
369
+ {"current_steps": 369, "total_steps": 390, "loss": 0.2664, "lr": 3.522452516867048e-07, "epoch": 4.7232, "percentage": 94.62, "elapsed_time": "10:22:19", "remaining_time": "0:35:25"}
370
+ {"current_steps": 370, "total_steps": 390, "loss": 0.2459, "lr": 3.1958433701019697e-07, "epoch": 4.736, "percentage": 94.87, "elapsed_time": "10:24:01", "remaining_time": "0:33:43"}
371
+ {"current_steps": 371, "total_steps": 390, "loss": 0.2411, "lr": 2.8850000548115155e-07, "epoch": 4.7488, "percentage": 95.13, "elapsed_time": "10:25:35", "remaining_time": "0:32:02"}
372
+ {"current_steps": 372, "total_steps": 390, "loss": 0.2575, "lr": 2.5899474724174313e-07, "epoch": 4.7616, "percentage": 95.38, "elapsed_time": "10:27:19", "remaining_time": "0:30:21"}
373
+ {"current_steps": 373, "total_steps": 390, "loss": 0.246, "lr": 2.3107092593579905e-07, "epoch": 4.7744, "percentage": 95.64, "elapsed_time": "10:29:09", "remaining_time": "0:28:40"}
374
+ {"current_steps": 374, "total_steps": 390, "loss": 0.2368, "lr": 2.0473077851942858e-07, "epoch": 4.7872, "percentage": 95.9, "elapsed_time": "10:30:38", "remaining_time": "0:26:58"}
375
+ {"current_steps": 375, "total_steps": 390, "loss": 0.2543, "lr": 1.799764150818306e-07, "epoch": 4.8, "percentage": 96.15, "elapsed_time": "10:32:15", "remaining_time": "0:25:17"}
376
+ {"current_steps": 376, "total_steps": 390, "loss": 0.257, "lr": 1.5680981867625566e-07, "epoch": 4.8128, "percentage": 96.41, "elapsed_time": "10:33:45", "remaining_time": "0:23:35"}
377
+ {"current_steps": 377, "total_steps": 390, "loss": 0.242, "lr": 1.3523284516113955e-07, "epoch": 4.8256, "percentage": 96.67, "elapsed_time": "10:35:41", "remaining_time": "0:21:55"}
378
+ {"current_steps": 378, "total_steps": 390, "loss": 0.256, "lr": 1.1524722305144231e-07, "epoch": 4.8384, "percentage": 96.92, "elapsed_time": "10:37:23", "remaining_time": "0:20:14"}
379
+ {"current_steps": 379, "total_steps": 390, "loss": 0.2472, "lr": 9.685455338016347e-08, "epoch": 4.8512, "percentage": 97.18, "elapsed_time": "10:39:00", "remaining_time": "0:18:32"}
380
+ {"current_steps": 380, "total_steps": 390, "loss": 0.2447, "lr": 8.005630957010014e-08, "epoch": 4.864, "percentage": 97.44, "elapsed_time": "10:40:40", "remaining_time": "0:16:51"}
381
+ {"current_steps": 381, "total_steps": 390, "loss": 0.2347, "lr": 6.485383731580142e-08, "epoch": 4.8768, "percentage": 97.69, "elapsed_time": "10:42:06", "remaining_time": "0:15:10"}
382
+ {"current_steps": 382, "total_steps": 390, "loss": 0.2486, "lr": 5.1248354475768034e-08, "epoch": 4.8896, "percentage": 97.95, "elapsed_time": "10:43:56", "remaining_time": "0:13:29"}
383
+ {"current_steps": 383, "total_steps": 390, "loss": 0.2399, "lr": 3.924095097489922e-08, "epoch": 4.9024, "percentage": 98.21, "elapsed_time": "10:45:29", "remaining_time": "0:11:47"}
384
+ {"current_steps": 384, "total_steps": 390, "loss": 0.2511, "lr": 2.8832588717164766e-08, "epoch": 4.9152000000000005, "percentage": 98.46, "elapsed_time": "10:47:25", "remaining_time": "0:10:06"}
385
+ {"current_steps": 385, "total_steps": 390, "loss": 0.2418, "lr": 2.0024101508555604e-08, "epoch": 4.928, "percentage": 98.72, "elapsed_time": "10:49:05", "remaining_time": "0:08:25"}
386
+ {"current_steps": 386, "total_steps": 390, "loss": 0.2333, "lr": 1.281619499029274e-08, "epoch": 4.9408, "percentage": 98.97, "elapsed_time": "10:50:43", "remaining_time": "0:06:44"}
387
+ {"current_steps": 387, "total_steps": 390, "loss": 0.2689, "lr": 7.209446582292501e-09, "epoch": 4.9536, "percentage": 99.23, "elapsed_time": "10:52:34", "remaining_time": "0:05:03"}
388
+ {"current_steps": 388, "total_steps": 390, "loss": 0.2176, "lr": 3.2043054369057523e-09, "epoch": 4.9664, "percentage": 99.49, "elapsed_time": "10:53:51", "remaining_time": "0:03:22"}
389
+ {"current_steps": 389, "total_steps": 390, "loss": 0.259, "lr": 8.010924029533406e-10, "epoch": 4.9792, "percentage": 99.74, "elapsed_time": "10:55:36", "remaining_time": "0:01:41"}
390
+ {"current_steps": 390, "total_steps": 390, "loss": 0.2045, "lr": 0.0, "epoch": 4.992, "percentage": 100.0, "elapsed_time": "10:56:50", "remaining_time": "0:00:00"}
391
+ {"current_steps": 390, "total_steps": 390, "epoch": 4.992, "percentage": 100.0, "elapsed_time": "10:58:50", "remaining_time": "0:00:00"}