ryanmarten commited on
Commit
1818eed
·
verified ·
1 Parent(s): d1f90bb

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 sha256:55c3af944bf91cd227ae1a6bf687c8108070158a24a2677295b890db9b1b7c8f
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:248dbcae007131e56fac62873bab7f6d6edfee587eb11c8c53075c0b7480b454
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2d721c5e69862eeaee0819a6579a6f0690dbf9924b80651d38418ac8446d3558
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02cc62c37c8a25b8c1a80d5a464af3baf80c1030dc9b42817985aedd437061c2
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2ec3cf724edcd232fc59775d298b0bbacd3bafd2d260c7adfe2d3f2f64a48df7
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49721f59b91068438dbe5acf48f4403f5e4f4fe39e28bd38a84c9ba9362b14a7
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:fda041eb2afa33d120332624859f5e19960e7aed88582d7e061c6df7fbad55ea
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f268a3f647daae7b3270d385d1caa22b38d05c7f5f6d857ede93e180c909498f
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -312,3 +312,80 @@
312
  {"current_steps": 312, "total_steps": 390, "loss": 0.2808, "lr": 4.679111137620442e-06, "epoch": 3.9936, "percentage": 80.0, "elapsed_time": "13:48:07", "remaining_time": "3:27:01"}
313
  {"current_steps": 313, "total_steps": 390, "loss": 0.2595, "lr": 4.5646621393177e-06, "epoch": 4.0064, "percentage": 80.26, "elapsed_time": "13:51:26", "remaining_time": "3:24:32"}
314
  {"current_steps": 314, "total_steps": 390, "loss": 0.2489, "lr": 4.451449654204685e-06, "epoch": 4.0192, "percentage": 80.51, "elapsed_time": "13:53:57", "remaining_time": "3:21:50"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
312
  {"current_steps": 312, "total_steps": 390, "loss": 0.2808, "lr": 4.679111137620442e-06, "epoch": 3.9936, "percentage": 80.0, "elapsed_time": "13:48:07", "remaining_time": "3:27:01"}
313
  {"current_steps": 313, "total_steps": 390, "loss": 0.2595, "lr": 4.5646621393177e-06, "epoch": 4.0064, "percentage": 80.26, "elapsed_time": "13:51:26", "remaining_time": "3:24:32"}
314
  {"current_steps": 314, "total_steps": 390, "loss": 0.2489, "lr": 4.451449654204685e-06, "epoch": 4.0192, "percentage": 80.51, "elapsed_time": "13:53:57", "remaining_time": "3:21:50"}
315
+ {"current_steps": 315, "total_steps": 390, "loss": 0.2378, "lr": 4.339482751647557e-06, "epoch": 4.032, "percentage": 80.77, "elapsed_time": "13:56:37", "remaining_time": "3:19:11"}
316
+ {"current_steps": 316, "total_steps": 390, "loss": 0.2431, "lr": 4.228770401229824e-06, "epoch": 4.0448, "percentage": 81.03, "elapsed_time": "13:59:07", "remaining_time": "3:16:30"}
317
+ {"current_steps": 317, "total_steps": 390, "loss": 0.2481, "lr": 4.119321472033779e-06, "epoch": 4.0576, "percentage": 81.28, "elapsed_time": "14:01:51", "remaining_time": "3:13:52"}
318
+ {"current_steps": 318, "total_steps": 390, "loss": 0.2513, "lr": 4.011144731929981e-06, "epoch": 4.0704, "percentage": 81.54, "elapsed_time": "14:04:34", "remaining_time": "3:11:13"}
319
+ {"current_steps": 319, "total_steps": 390, "loss": 0.2428, "lr": 3.904248846874894e-06, "epoch": 4.0832, "percentage": 81.79, "elapsed_time": "14:07:06", "remaining_time": "3:08:32"}
320
+ {"current_steps": 320, "total_steps": 390, "loss": 0.2281, "lr": 3.7986423802166705e-06, "epoch": 4.096, "percentage": 82.05, "elapsed_time": "14:09:36", "remaining_time": "3:05:51"}
321
+ {"current_steps": 321, "total_steps": 390, "loss": 0.2359, "lr": 3.694333792009115e-06, "epoch": 4.1088, "percentage": 82.31, "elapsed_time": "14:12:03", "remaining_time": "3:03:09"}
322
+ {"current_steps": 322, "total_steps": 390, "loss": 0.2507, "lr": 3.5913314383339937e-06, "epoch": 4.1216, "percentage": 82.56, "elapsed_time": "14:14:45", "remaining_time": "3:00:30"}
323
+ {"current_steps": 323, "total_steps": 390, "loss": 0.2364, "lr": 3.4896435706316e-06, "epoch": 4.1344, "percentage": 82.82, "elapsed_time": "14:17:04", "remaining_time": "2:57:46"}
324
+ {"current_steps": 324, "total_steps": 390, "loss": 0.2385, "lr": 3.3892783350397675e-06, "epoch": 4.1472, "percentage": 83.08, "elapsed_time": "14:19:39", "remaining_time": "2:55:06"}
325
+ {"current_steps": 325, "total_steps": 390, "loss": 0.2424, "lr": 3.290243771741275e-06, "epoch": 4.16, "percentage": 83.33, "elapsed_time": "14:22:14", "remaining_time": "2:52:26"}
326
+ {"current_steps": 326, "total_steps": 390, "loss": 0.2325, "lr": 3.1925478143197418e-06, "epoch": 4.1728, "percentage": 83.59, "elapsed_time": "14:24:47", "remaining_time": "2:49:46"}
327
+ {"current_steps": 327, "total_steps": 390, "loss": 0.2416, "lr": 3.0961982891241083e-06, "epoch": 4.1856, "percentage": 83.85, "elapsed_time": "14:27:37", "remaining_time": "2:47:09"}
328
+ {"current_steps": 328, "total_steps": 390, "loss": 0.2551, "lr": 3.001202914641628e-06, "epoch": 4.1984, "percentage": 84.1, "elapsed_time": "14:30:28", "remaining_time": "2:44:32"}
329
+ {"current_steps": 329, "total_steps": 390, "loss": 0.2362, "lr": 2.907569300879596e-06, "epoch": 4.2112, "percentage": 84.36, "elapsed_time": "14:32:55", "remaining_time": "2:41:51"}
330
+ {"current_steps": 330, "total_steps": 390, "loss": 0.2484, "lr": 2.815304948755664e-06, "epoch": 4.224, "percentage": 84.62, "elapsed_time": "14:35:40", "remaining_time": "2:39:12"}
331
+ {"current_steps": 331, "total_steps": 390, "loss": 0.2457, "lr": 2.7244172494969978e-06, "epoch": 4.2368, "percentage": 84.87, "elapsed_time": "14:38:21", "remaining_time": "2:36:33"}
332
+ {"current_steps": 332, "total_steps": 390, "loss": 0.2427, "lr": 2.6349134840481294e-06, "epoch": 4.2496, "percentage": 85.13, "elapsed_time": "14:40:58", "remaining_time": "2:33:54"}
333
+ {"current_steps": 333, "total_steps": 390, "loss": 0.2558, "lr": 2.546800822487714e-06, "epoch": 4.2624, "percentage": 85.38, "elapsed_time": "14:43:47", "remaining_time": "2:31:16"}
334
+ {"current_steps": 334, "total_steps": 390, "loss": 0.2438, "lr": 2.4600863234541338e-06, "epoch": 4.2752, "percentage": 85.64, "elapsed_time": "14:46:29", "remaining_time": "2:28:37"}
335
+ {"current_steps": 335, "total_steps": 390, "loss": 0.2294, "lr": 2.374776933580025e-06, "epoch": 4.288, "percentage": 85.9, "elapsed_time": "14:49:08", "remaining_time": "2:25:58"}
336
+ {"current_steps": 336, "total_steps": 390, "loss": 0.2299, "lr": 2.2908794869358044e-06, "epoch": 4.3008, "percentage": 86.15, "elapsed_time": "14:51:43", "remaining_time": "2:23:18"}
337
+ {"current_steps": 337, "total_steps": 390, "loss": 0.2388, "lr": 2.2084007044821764e-06, "epoch": 4.3136, "percentage": 86.41, "elapsed_time": "14:54:12", "remaining_time": "2:20:37"}
338
+ {"current_steps": 338, "total_steps": 390, "loss": 0.2315, "lr": 2.127347193531757e-06, "epoch": 4.3264, "percentage": 86.67, "elapsed_time": "14:56:54", "remaining_time": "2:17:59"}
339
+ {"current_steps": 339, "total_steps": 390, "loss": 0.2409, "lr": 2.0477254472197237e-06, "epoch": 4.3392, "percentage": 86.92, "elapsed_time": "14:59:26", "remaining_time": "2:15:18"}
340
+ {"current_steps": 340, "total_steps": 390, "loss": 0.2491, "lr": 1.96954184398368e-06, "epoch": 4.352, "percentage": 87.18, "elapsed_time": "15:02:04", "remaining_time": "2:12:39"}
341
+ {"current_steps": 341, "total_steps": 390, "loss": 0.236, "lr": 1.8928026470526917e-06, "epoch": 4.3648, "percentage": 87.44, "elapsed_time": "15:04:48", "remaining_time": "2:10:01"}
342
+ {"current_steps": 342, "total_steps": 390, "loss": 0.237, "lr": 1.817514003945524e-06, "epoch": 4.3776, "percentage": 87.69, "elapsed_time": "15:07:19", "remaining_time": "2:07:20"}
343
+ {"current_steps": 343, "total_steps": 390, "loss": 0.2512, "lr": 1.743681945978184e-06, "epoch": 4.3904, "percentage": 87.95, "elapsed_time": "15:09:53", "remaining_time": "2:04:40"}
344
+ {"current_steps": 344, "total_steps": 390, "loss": 0.2459, "lr": 1.6713123877807413e-06, "epoch": 4.4032, "percentage": 88.21, "elapsed_time": "15:12:29", "remaining_time": "2:02:01"}
345
+ {"current_steps": 345, "total_steps": 390, "loss": 0.24, "lr": 1.6004111268235156e-06, "epoch": 4.416, "percentage": 88.46, "elapsed_time": "15:15:15", "remaining_time": "1:59:22"}
346
+ {"current_steps": 346, "total_steps": 390, "loss": 0.249, "lr": 1.5309838429526714e-06, "epoch": 4.4288, "percentage": 88.72, "elapsed_time": "15:18:03", "remaining_time": "1:56:44"}
347
+ {"current_steps": 347, "total_steps": 390, "loss": 0.2422, "lr": 1.4630360979351644e-06, "epoch": 4.4416, "percentage": 88.97, "elapsed_time": "15:20:32", "remaining_time": "1:54:04"}
348
+ {"current_steps": 348, "total_steps": 390, "loss": 0.2299, "lr": 1.396573335013236e-06, "epoch": 4.4544, "percentage": 89.23, "elapsed_time": "15:23:06", "remaining_time": "1:51:24"}
349
+ {"current_steps": 349, "total_steps": 390, "loss": 0.2497, "lr": 1.3316008784683265e-06, "epoch": 4.4672, "percentage": 89.49, "elapsed_time": "15:25:58", "remaining_time": "1:48:46"}
350
+ {"current_steps": 350, "total_steps": 390, "loss": 0.2401, "lr": 1.2681239331945695e-06, "epoch": 4.48, "percentage": 89.74, "elapsed_time": "15:28:35", "remaining_time": "1:46:07"}
351
+ {"current_steps": 351, "total_steps": 390, "loss": 0.2461, "lr": 1.2061475842818337e-06, "epoch": 4.4928, "percentage": 90.0, "elapsed_time": "15:31:18", "remaining_time": "1:43:28"}
352
+ {"current_steps": 352, "total_steps": 390, "loss": 0.25, "lr": 1.1456767966083393e-06, "epoch": 4.5056, "percentage": 90.26, "elapsed_time": "15:34:05", "remaining_time": "1:40:50"}
353
+ {"current_steps": 353, "total_steps": 390, "loss": 0.2401, "lr": 1.086716414442952e-06, "epoch": 4.5184, "percentage": 90.51, "elapsed_time": "15:36:36", "remaining_time": "1:38:10"}
354
+ {"current_steps": 354, "total_steps": 390, "loss": 0.2493, "lr": 1.0292711610570904e-06, "epoch": 4.5312, "percentage": 90.77, "elapsed_time": "15:39:06", "remaining_time": "1:35:30"}
355
+ {"current_steps": 355, "total_steps": 390, "loss": 0.2485, "lr": 9.733456383463658e-07, "epoch": 4.5440000000000005, "percentage": 91.03, "elapsed_time": "15:41:47", "remaining_time": "1:32:51"}
356
+ {"current_steps": 356, "total_steps": 390, "loss": 0.2486, "lr": 9.189443264619102e-07, "epoch": 4.5568, "percentage": 91.28, "elapsed_time": "15:44:31", "remaining_time": "1:30:12"}
357
+ {"current_steps": 357, "total_steps": 390, "loss": 0.2442, "lr": 8.660715834514977e-07, "epoch": 4.5696, "percentage": 91.54, "elapsed_time": "15:47:16", "remaining_time": "1:27:33"}
358
+ {"current_steps": 358, "total_steps": 390, "loss": 0.2502, "lr": 8.147316449103959e-07, "epoch": 4.5824, "percentage": 91.79, "elapsed_time": "15:49:53", "remaining_time": "1:24:54"}
359
+ {"current_steps": 359, "total_steps": 390, "loss": 0.2465, "lr": 7.649286236420806e-07, "epoch": 4.5952, "percentage": 92.05, "elapsed_time": "15:52:22", "remaining_time": "1:22:14"}
360
+ {"current_steps": 360, "total_steps": 390, "loss": 0.2344, "lr": 7.166665093287539e-07, "epoch": 4.608, "percentage": 92.31, "elapsed_time": "15:55:02", "remaining_time": "1:19:35"}
361
+ {"current_steps": 361, "total_steps": 390, "loss": 0.238, "lr": 6.69949168211721e-07, "epoch": 4.6208, "percentage": 92.56, "elapsed_time": "15:57:31", "remaining_time": "1:16:55"}
362
+ {"current_steps": 362, "total_steps": 390, "loss": 0.2521, "lr": 6.247803427816945e-07, "epoch": 4.6336, "percentage": 92.82, "elapsed_time": "16:00:19", "remaining_time": "1:14:16"}
363
+ {"current_steps": 363, "total_steps": 390, "loss": 0.2334, "lr": 5.811636514789598e-07, "epoch": 4.6464, "percentage": 93.08, "elapsed_time": "16:02:40", "remaining_time": "1:11:36"}
364
+ {"current_steps": 364, "total_steps": 390, "loss": 0.2483, "lr": 5.391025884035239e-07, "epoch": 4.6592, "percentage": 93.33, "elapsed_time": "16:05:19", "remaining_time": "1:08:57"}
365
+ {"current_steps": 365, "total_steps": 390, "loss": 0.2284, "lr": 4.986005230351954e-07, "epoch": 4.672, "percentage": 93.59, "elapsed_time": "16:07:52", "remaining_time": "1:06:17"}
366
+ {"current_steps": 366, "total_steps": 390, "loss": 0.2265, "lr": 4.5966069996365993e-07, "epoch": 4.6848, "percentage": 93.85, "elapsed_time": "16:10:25", "remaining_time": "1:03:38"}
367
+ {"current_steps": 367, "total_steps": 390, "loss": 0.2443, "lr": 4.22286238628562e-07, "epoch": 4.6975999999999996, "percentage": 94.1, "elapsed_time": "16:12:54", "remaining_time": "1:00:58"}
368
+ {"current_steps": 368, "total_steps": 390, "loss": 0.2428, "lr": 3.8648013306960664e-07, "epoch": 4.7104, "percentage": 94.36, "elapsed_time": "16:15:31", "remaining_time": "0:58:19"}
369
+ {"current_steps": 369, "total_steps": 390, "loss": 0.2408, "lr": 3.522452516867048e-07, "epoch": 4.7232, "percentage": 94.62, "elapsed_time": "16:18:02", "remaining_time": "0:55:39"}
370
+ {"current_steps": 370, "total_steps": 390, "loss": 0.2447, "lr": 3.1958433701019697e-07, "epoch": 4.736, "percentage": 94.87, "elapsed_time": "16:20:38", "remaining_time": "0:53:00"}
371
+ {"current_steps": 371, "total_steps": 390, "loss": 0.2437, "lr": 2.8850000548115155e-07, "epoch": 4.7488, "percentage": 95.13, "elapsed_time": "16:23:14", "remaining_time": "0:50:21"}
372
+ {"current_steps": 372, "total_steps": 390, "loss": 0.2328, "lr": 2.5899474724174313e-07, "epoch": 4.7616, "percentage": 95.38, "elapsed_time": "16:25:44", "remaining_time": "0:47:41"}
373
+ {"current_steps": 373, "total_steps": 390, "loss": 0.2417, "lr": 2.3107092593579905e-07, "epoch": 4.7744, "percentage": 95.64, "elapsed_time": "16:28:14", "remaining_time": "0:45:02"}
374
+ {"current_steps": 374, "total_steps": 390, "loss": 0.246, "lr": 2.0473077851942858e-07, "epoch": 4.7872, "percentage": 95.9, "elapsed_time": "16:30:48", "remaining_time": "0:42:23"}
375
+ {"current_steps": 375, "total_steps": 390, "loss": 0.2451, "lr": 1.799764150818306e-07, "epoch": 4.8, "percentage": 96.15, "elapsed_time": "16:33:12", "remaining_time": "0:39:43"}
376
+ {"current_steps": 376, "total_steps": 390, "loss": 0.2377, "lr": 1.5680981867625566e-07, "epoch": 4.8128, "percentage": 96.41, "elapsed_time": "16:35:49", "remaining_time": "0:37:04"}
377
+ {"current_steps": 377, "total_steps": 390, "loss": 0.2499, "lr": 1.3523284516113955e-07, "epoch": 4.8256, "percentage": 96.67, "elapsed_time": "16:38:29", "remaining_time": "0:34:25"}
378
+ {"current_steps": 378, "total_steps": 390, "loss": 0.2416, "lr": 1.1524722305144231e-07, "epoch": 4.8384, "percentage": 96.92, "elapsed_time": "16:41:04", "remaining_time": "0:31:46"}
379
+ {"current_steps": 379, "total_steps": 390, "loss": 0.2433, "lr": 9.685455338016347e-08, "epoch": 4.8512, "percentage": 97.18, "elapsed_time": "16:43:30", "remaining_time": "0:29:07"}
380
+ {"current_steps": 380, "total_steps": 390, "loss": 0.2308, "lr": 8.005630957010014e-08, "epoch": 4.864, "percentage": 97.44, "elapsed_time": "16:46:15", "remaining_time": "0:26:28"}
381
+ {"current_steps": 381, "total_steps": 390, "loss": 0.2407, "lr": 6.485383731580142e-08, "epoch": 4.8768, "percentage": 97.69, "elapsed_time": "16:48:44", "remaining_time": "0:23:49"}
382
+ {"current_steps": 382, "total_steps": 390, "loss": 0.2431, "lr": 5.1248354475768034e-08, "epoch": 4.8896, "percentage": 97.95, "elapsed_time": "16:51:26", "remaining_time": "0:21:10"}
383
+ {"current_steps": 383, "total_steps": 390, "loss": 0.2432, "lr": 3.924095097489922e-08, "epoch": 4.9024, "percentage": 98.21, "elapsed_time": "16:54:01", "remaining_time": "0:18:31"}
384
+ {"current_steps": 384, "total_steps": 390, "loss": 0.2453, "lr": 2.8832588717164766e-08, "epoch": 4.9152000000000005, "percentage": 98.46, "elapsed_time": "16:56:42", "remaining_time": "0:15:53"}
385
+ {"current_steps": 385, "total_steps": 390, "loss": 0.2376, "lr": 2.0024101508555604e-08, "epoch": 4.928, "percentage": 98.72, "elapsed_time": "16:59:21", "remaining_time": "0:13:14"}
386
+ {"current_steps": 386, "total_steps": 390, "loss": 0.2395, "lr": 1.281619499029274e-08, "epoch": 4.9408, "percentage": 98.97, "elapsed_time": "17:01:48", "remaining_time": "0:10:35"}
387
+ {"current_steps": 387, "total_steps": 390, "loss": 0.242, "lr": 7.209446582292501e-09, "epoch": 4.9536, "percentage": 99.23, "elapsed_time": "17:04:24", "remaining_time": "0:07:56"}
388
+ {"current_steps": 388, "total_steps": 390, "loss": 0.2401, "lr": 3.2043054369057523e-09, "epoch": 4.9664, "percentage": 99.49, "elapsed_time": "17:07:02", "remaining_time": "0:05:17"}
389
+ {"current_steps": 389, "total_steps": 390, "loss": 0.2393, "lr": 8.010924029533406e-10, "epoch": 4.9792, "percentage": 99.74, "elapsed_time": "17:09:35", "remaining_time": "0:02:38"}
390
+ {"current_steps": 390, "total_steps": 390, "loss": 0.2371, "lr": 0.0, "epoch": 4.992, "percentage": 100.0, "elapsed_time": "17:12:02", "remaining_time": "0:00:00"}
391
+ {"current_steps": 390, "total_steps": 390, "epoch": 4.992, "percentage": 100.0, "elapsed_time": "17:14:01", "remaining_time": "0:00:00"}