neginr commited on
Commit
a23551a
·
verified ·
1 Parent(s): 6d8de39

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 sha256:733c581c1d25f052620c2879a027e056882617a9e328672cddfc327885b02c2e
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94fab5c1a8d567ec30a12a2098c1c43aa61f6d02e4f1426e6feab64768bbe358
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:071b728c4e6cf805ce0630418c94d1b6ad842a0671143d9d30f793a2b1ad46be
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c165bd2a8922393c9e03b8138ba933a335eb3fab729414981d1df31400d0ce93
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:33d320e7cb44a3141c5db360ed5b6bb09ac0061dac1e1091f1804642f673b7cf
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9dd9e9192f5a6205c4481373ca8776bd0ea0a0b9fb2dc48e9417fdedd4d27e08
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:41ee802bf255f52896f404732f462adc8fdfc1c095d2039b7a87813ded04f338
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c0f0ccf874be46fc52e8bf8e33072afa6c5d71cbeb6a0c1e06ac615c6e3c186
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -317,3 +317,75 @@
317
  {"current_steps": 317, "total_steps": 390, "loss": 0.0886, "lr": 4.119321472033779e-06, "epoch": 4.0576, "percentage": 81.28, "elapsed_time": "2:23:35", "remaining_time": "0:33:04"}
318
  {"current_steps": 318, "total_steps": 390, "loss": 0.12, "lr": 4.011144731929981e-06, "epoch": 4.0704, "percentage": 81.54, "elapsed_time": "2:24:01", "remaining_time": "0:32:36"}
319
  {"current_steps": 319, "total_steps": 390, "loss": 0.1027, "lr": 3.904248846874894e-06, "epoch": 4.0832, "percentage": 81.79, "elapsed_time": "2:24:21", "remaining_time": "0:32:07"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
317
  {"current_steps": 317, "total_steps": 390, "loss": 0.0886, "lr": 4.119321472033779e-06, "epoch": 4.0576, "percentage": 81.28, "elapsed_time": "2:23:35", "remaining_time": "0:33:04"}
318
  {"current_steps": 318, "total_steps": 390, "loss": 0.12, "lr": 4.011144731929981e-06, "epoch": 4.0704, "percentage": 81.54, "elapsed_time": "2:24:01", "remaining_time": "0:32:36"}
319
  {"current_steps": 319, "total_steps": 390, "loss": 0.1027, "lr": 3.904248846874894e-06, "epoch": 4.0832, "percentage": 81.79, "elapsed_time": "2:24:21", "remaining_time": "0:32:07"}
320
+ {"current_steps": 320, "total_steps": 390, "loss": 0.1095, "lr": 3.7986423802166705e-06, "epoch": 4.096, "percentage": 82.05, "elapsed_time": "2:24:48", "remaining_time": "0:31:40"}
321
+ {"current_steps": 321, "total_steps": 390, "loss": 0.112, "lr": 3.694333792009115e-06, "epoch": 4.1088, "percentage": 82.31, "elapsed_time": "2:25:08", "remaining_time": "0:31:12"}
322
+ {"current_steps": 322, "total_steps": 390, "loss": 0.1211, "lr": 3.5913314383339937e-06, "epoch": 4.1216, "percentage": 82.56, "elapsed_time": "2:25:35", "remaining_time": "0:30:44"}
323
+ {"current_steps": 323, "total_steps": 390, "loss": 0.094, "lr": 3.4896435706316e-06, "epoch": 4.1344, "percentage": 82.82, "elapsed_time": "2:25:58", "remaining_time": "0:30:16"}
324
+ {"current_steps": 324, "total_steps": 390, "loss": 0.0977, "lr": 3.3892783350397675e-06, "epoch": 4.1472, "percentage": 83.08, "elapsed_time": "2:26:25", "remaining_time": "0:29:49"}
325
+ {"current_steps": 325, "total_steps": 390, "loss": 0.0886, "lr": 3.290243771741275e-06, "epoch": 4.16, "percentage": 83.33, "elapsed_time": "2:26:46", "remaining_time": "0:29:21"}
326
+ {"current_steps": 326, "total_steps": 390, "loss": 0.111, "lr": 3.1925478143197418e-06, "epoch": 4.1728, "percentage": 83.59, "elapsed_time": "2:27:16", "remaining_time": "0:28:54"}
327
+ {"current_steps": 327, "total_steps": 390, "loss": 0.1091, "lr": 3.0961982891241083e-06, "epoch": 4.1856, "percentage": 83.85, "elapsed_time": "2:27:44", "remaining_time": "0:28:27"}
328
+ {"current_steps": 328, "total_steps": 390, "loss": 0.131, "lr": 3.001202914641628e-06, "epoch": 4.1984, "percentage": 84.1, "elapsed_time": "2:28:18", "remaining_time": "0:28:02"}
329
+ {"current_steps": 329, "total_steps": 390, "loss": 0.1065, "lr": 2.907569300879596e-06, "epoch": 4.2112, "percentage": 84.36, "elapsed_time": "2:28:49", "remaining_time": "0:27:35"}
330
+ {"current_steps": 330, "total_steps": 390, "loss": 0.1019, "lr": 2.815304948755664e-06, "epoch": 4.224, "percentage": 84.62, "elapsed_time": "2:29:13", "remaining_time": "0:27:07"}
331
+ {"current_steps": 331, "total_steps": 390, "loss": 0.0993, "lr": 2.7244172494969978e-06, "epoch": 4.2368, "percentage": 84.87, "elapsed_time": "2:29:37", "remaining_time": "0:26:40"}
332
+ {"current_steps": 332, "total_steps": 390, "loss": 0.1006, "lr": 2.6349134840481294e-06, "epoch": 4.2496, "percentage": 85.13, "elapsed_time": "2:30:04", "remaining_time": "0:26:13"}
333
+ {"current_steps": 333, "total_steps": 390, "loss": 0.1009, "lr": 2.546800822487714e-06, "epoch": 4.2624, "percentage": 85.38, "elapsed_time": "2:30:31", "remaining_time": "0:25:45"}
334
+ {"current_steps": 334, "total_steps": 390, "loss": 0.1022, "lr": 2.4600863234541338e-06, "epoch": 4.2752, "percentage": 85.64, "elapsed_time": "2:30:55", "remaining_time": "0:25:18"}
335
+ {"current_steps": 335, "total_steps": 390, "loss": 0.0964, "lr": 2.374776933580025e-06, "epoch": 4.288, "percentage": 85.9, "elapsed_time": "2:31:23", "remaining_time": "0:24:51"}
336
+ {"current_steps": 336, "total_steps": 390, "loss": 0.1009, "lr": 2.2908794869358044e-06, "epoch": 4.3008, "percentage": 86.15, "elapsed_time": "2:31:50", "remaining_time": "0:24:24"}
337
+ {"current_steps": 337, "total_steps": 390, "loss": 0.0807, "lr": 2.2084007044821764e-06, "epoch": 4.3136, "percentage": 86.41, "elapsed_time": "2:32:13", "remaining_time": "0:23:56"}
338
+ {"current_steps": 338, "total_steps": 390, "loss": 0.0933, "lr": 2.127347193531757e-06, "epoch": 4.3264, "percentage": 86.67, "elapsed_time": "2:32:40", "remaining_time": "0:23:29"}
339
+ {"current_steps": 339, "total_steps": 390, "loss": 0.1056, "lr": 2.0477254472197237e-06, "epoch": 4.3392, "percentage": 86.92, "elapsed_time": "2:33:01", "remaining_time": "0:23:01"}
340
+ {"current_steps": 340, "total_steps": 390, "loss": 0.1014, "lr": 1.96954184398368e-06, "epoch": 4.352, "percentage": 87.18, "elapsed_time": "2:33:24", "remaining_time": "0:22:33"}
341
+ {"current_steps": 341, "total_steps": 390, "loss": 0.1053, "lr": 1.8928026470526917e-06, "epoch": 4.3648, "percentage": 87.44, "elapsed_time": "2:33:53", "remaining_time": "0:22:06"}
342
+ {"current_steps": 342, "total_steps": 390, "loss": 0.1063, "lr": 1.817514003945524e-06, "epoch": 4.3776, "percentage": 87.69, "elapsed_time": "2:34:16", "remaining_time": "0:21:39"}
343
+ {"current_steps": 343, "total_steps": 390, "loss": 0.0981, "lr": 1.743681945978184e-06, "epoch": 4.3904, "percentage": 87.95, "elapsed_time": "2:34:40", "remaining_time": "0:21:11"}
344
+ {"current_steps": 344, "total_steps": 390, "loss": 0.1042, "lr": 1.6713123877807413e-06, "epoch": 4.4032, "percentage": 88.21, "elapsed_time": "2:35:05", "remaining_time": "0:20:44"}
345
+ {"current_steps": 345, "total_steps": 390, "loss": 0.0959, "lr": 1.6004111268235156e-06, "epoch": 4.416, "percentage": 88.46, "elapsed_time": "2:35:32", "remaining_time": "0:20:17"}
346
+ {"current_steps": 346, "total_steps": 390, "loss": 0.1113, "lr": 1.5309838429526714e-06, "epoch": 4.4288, "percentage": 88.72, "elapsed_time": "2:36:00", "remaining_time": "0:19:50"}
347
+ {"current_steps": 347, "total_steps": 390, "loss": 0.0899, "lr": 1.4630360979351644e-06, "epoch": 4.4416, "percentage": 88.97, "elapsed_time": "2:36:24", "remaining_time": "0:19:22"}
348
+ {"current_steps": 348, "total_steps": 390, "loss": 0.0991, "lr": 1.396573335013236e-06, "epoch": 4.4544, "percentage": 89.23, "elapsed_time": "2:36:50", "remaining_time": "0:18:55"}
349
+ {"current_steps": 349, "total_steps": 390, "loss": 0.0874, "lr": 1.3316008784683265e-06, "epoch": 4.4672, "percentage": 89.49, "elapsed_time": "2:37:11", "remaining_time": "0:18:28"}
350
+ {"current_steps": 350, "total_steps": 390, "loss": 0.102, "lr": 1.2681239331945695e-06, "epoch": 4.48, "percentage": 89.74, "elapsed_time": "2:37:36", "remaining_time": "0:18:00"}
351
+ {"current_steps": 351, "total_steps": 390, "loss": 0.1007, "lr": 1.2061475842818337e-06, "epoch": 4.4928, "percentage": 90.0, "elapsed_time": "2:38:00", "remaining_time": "0:17:33"}
352
+ {"current_steps": 352, "total_steps": 390, "loss": 0.0894, "lr": 1.1456767966083393e-06, "epoch": 4.5056, "percentage": 90.26, "elapsed_time": "2:38:27", "remaining_time": "0:17:06"}
353
+ {"current_steps": 353, "total_steps": 390, "loss": 0.0838, "lr": 1.086716414442952e-06, "epoch": 4.5184, "percentage": 90.51, "elapsed_time": "2:38:48", "remaining_time": "0:16:38"}
354
+ {"current_steps": 354, "total_steps": 390, "loss": 0.105, "lr": 1.0292711610570904e-06, "epoch": 4.5312, "percentage": 90.77, "elapsed_time": "2:39:19", "remaining_time": "0:16:12"}
355
+ {"current_steps": 355, "total_steps": 390, "loss": 0.1135, "lr": 9.733456383463658e-07, "epoch": 4.5440000000000005, "percentage": 91.03, "elapsed_time": "2:39:50", "remaining_time": "0:15:45"}
356
+ {"current_steps": 356, "total_steps": 390, "loss": 0.1011, "lr": 9.189443264619102e-07, "epoch": 4.5568, "percentage": 91.28, "elapsed_time": "2:40:13", "remaining_time": "0:15:18"}
357
+ {"current_steps": 357, "total_steps": 390, "loss": 0.0995, "lr": 8.660715834514977e-07, "epoch": 4.5696, "percentage": 91.54, "elapsed_time": "2:40:41", "remaining_time": "0:14:51"}
358
+ {"current_steps": 358, "total_steps": 390, "loss": 0.1244, "lr": 8.147316449103959e-07, "epoch": 4.5824, "percentage": 91.79, "elapsed_time": "2:41:07", "remaining_time": "0:14:24"}
359
+ {"current_steps": 359, "total_steps": 390, "loss": 0.0858, "lr": 7.649286236420806e-07, "epoch": 4.5952, "percentage": 92.05, "elapsed_time": "2:41:26", "remaining_time": "0:13:56"}
360
+ {"current_steps": 360, "total_steps": 390, "loss": 0.1056, "lr": 7.166665093287539e-07, "epoch": 4.608, "percentage": 92.31, "elapsed_time": "2:41:53", "remaining_time": "0:13:29"}
361
+ {"current_steps": 361, "total_steps": 390, "loss": 0.1011, "lr": 6.69949168211721e-07, "epoch": 4.6208, "percentage": 92.56, "elapsed_time": "2:42:25", "remaining_time": "0:13:02"}
362
+ {"current_steps": 362, "total_steps": 390, "loss": 0.106, "lr": 6.247803427816945e-07, "epoch": 4.6336, "percentage": 92.82, "elapsed_time": "2:42:50", "remaining_time": "0:12:35"}
363
+ {"current_steps": 363, "total_steps": 390, "loss": 0.0949, "lr": 5.811636514789598e-07, "epoch": 4.6464, "percentage": 93.08, "elapsed_time": "2:43:15", "remaining_time": "0:12:08"}
364
+ {"current_steps": 364, "total_steps": 390, "loss": 0.0927, "lr": 5.391025884035239e-07, "epoch": 4.6592, "percentage": 93.33, "elapsed_time": "2:43:39", "remaining_time": "0:11:41"}
365
+ {"current_steps": 365, "total_steps": 390, "loss": 0.1128, "lr": 4.986005230351954e-07, "epoch": 4.672, "percentage": 93.59, "elapsed_time": "2:44:09", "remaining_time": "0:11:14"}
366
+ {"current_steps": 366, "total_steps": 390, "loss": 0.0936, "lr": 4.5966069996365993e-07, "epoch": 4.6848, "percentage": 93.85, "elapsed_time": "2:44:37", "remaining_time": "0:10:47"}
367
+ {"current_steps": 367, "total_steps": 390, "loss": 0.0891, "lr": 4.22286238628562e-07, "epoch": 4.6975999999999996, "percentage": 94.1, "elapsed_time": "2:44:56", "remaining_time": "0:10:20"}
368
+ {"current_steps": 368, "total_steps": 390, "loss": 0.0932, "lr": 3.8648013306960664e-07, "epoch": 4.7104, "percentage": 94.36, "elapsed_time": "2:45:26", "remaining_time": "0:09:53"}
369
+ {"current_steps": 369, "total_steps": 390, "loss": 0.1021, "lr": 3.522452516867048e-07, "epoch": 4.7232, "percentage": 94.62, "elapsed_time": "2:45:56", "remaining_time": "0:09:26"}
370
+ {"current_steps": 370, "total_steps": 390, "loss": 0.1177, "lr": 3.1958433701019697e-07, "epoch": 4.736, "percentage": 94.87, "elapsed_time": "2:46:23", "remaining_time": "0:08:59"}
371
+ {"current_steps": 371, "total_steps": 390, "loss": 0.0955, "lr": 2.8850000548115155e-07, "epoch": 4.7488, "percentage": 95.13, "elapsed_time": "2:46:47", "remaining_time": "0:08:32"}
372
+ {"current_steps": 372, "total_steps": 390, "loss": 0.0936, "lr": 2.5899474724174313e-07, "epoch": 4.7616, "percentage": 95.38, "elapsed_time": "2:47:16", "remaining_time": "0:08:05"}
373
+ {"current_steps": 373, "total_steps": 390, "loss": 0.1057, "lr": 2.3107092593579905e-07, "epoch": 4.7744, "percentage": 95.64, "elapsed_time": "2:47:39", "remaining_time": "0:07:38"}
374
+ {"current_steps": 374, "total_steps": 390, "loss": 0.1217, "lr": 2.0473077851942858e-07, "epoch": 4.7872, "percentage": 95.9, "elapsed_time": "2:48:09", "remaining_time": "0:07:11"}
375
+ {"current_steps": 375, "total_steps": 390, "loss": 0.105, "lr": 1.799764150818306e-07, "epoch": 4.8, "percentage": 96.15, "elapsed_time": "2:48:41", "remaining_time": "0:06:44"}
376
+ {"current_steps": 376, "total_steps": 390, "loss": 0.0869, "lr": 1.5680981867625566e-07, "epoch": 4.8128, "percentage": 96.41, "elapsed_time": "2:49:04", "remaining_time": "0:06:17"}
377
+ {"current_steps": 377, "total_steps": 390, "loss": 0.1049, "lr": 1.3523284516113955e-07, "epoch": 4.8256, "percentage": 96.67, "elapsed_time": "2:49:31", "remaining_time": "0:05:50"}
378
+ {"current_steps": 378, "total_steps": 390, "loss": 0.1028, "lr": 1.1524722305144231e-07, "epoch": 4.8384, "percentage": 96.92, "elapsed_time": "2:49:56", "remaining_time": "0:05:23"}
379
+ {"current_steps": 379, "total_steps": 390, "loss": 0.1009, "lr": 9.685455338016347e-08, "epoch": 4.8512, "percentage": 97.18, "elapsed_time": "2:50:21", "remaining_time": "0:04:56"}
380
+ {"current_steps": 380, "total_steps": 390, "loss": 0.098, "lr": 8.005630957010014e-08, "epoch": 4.864, "percentage": 97.44, "elapsed_time": "2:50:46", "remaining_time": "0:04:29"}
381
+ {"current_steps": 381, "total_steps": 390, "loss": 0.1017, "lr": 6.485383731580142e-08, "epoch": 4.8768, "percentage": 97.69, "elapsed_time": "2:51:12", "remaining_time": "0:04:02"}
382
+ {"current_steps": 382, "total_steps": 390, "loss": 0.0889, "lr": 5.1248354475768034e-08, "epoch": 4.8896, "percentage": 97.95, "elapsed_time": "2:51:37", "remaining_time": "0:03:35"}
383
+ {"current_steps": 383, "total_steps": 390, "loss": 0.1047, "lr": 3.924095097489922e-08, "epoch": 4.9024, "percentage": 98.21, "elapsed_time": "2:52:03", "remaining_time": "0:03:08"}
384
+ {"current_steps": 384, "total_steps": 390, "loss": 0.1073, "lr": 2.8832588717164766e-08, "epoch": 4.9152000000000005, "percentage": 98.46, "elapsed_time": "2:52:28", "remaining_time": "0:02:41"}
385
+ {"current_steps": 385, "total_steps": 390, "loss": 0.0903, "lr": 2.0024101508555604e-08, "epoch": 4.928, "percentage": 98.72, "elapsed_time": "2:52:46", "remaining_time": "0:02:14"}
386
+ {"current_steps": 386, "total_steps": 390, "loss": 0.0797, "lr": 1.281619499029274e-08, "epoch": 4.9408, "percentage": 98.97, "elapsed_time": "2:53:13", "remaining_time": "0:01:47"}
387
+ {"current_steps": 387, "total_steps": 390, "loss": 0.0867, "lr": 7.209446582292501e-09, "epoch": 4.9536, "percentage": 99.23, "elapsed_time": "2:53:38", "remaining_time": "0:01:20"}
388
+ {"current_steps": 388, "total_steps": 390, "loss": 0.1016, "lr": 3.2043054369057523e-09, "epoch": 4.9664, "percentage": 99.49, "elapsed_time": "2:54:01", "remaining_time": "0:00:53"}
389
+ {"current_steps": 389, "total_steps": 390, "loss": 0.0865, "lr": 8.010924029533406e-10, "epoch": 4.9792, "percentage": 99.74, "elapsed_time": "2:54:22", "remaining_time": "0:00:26"}
390
+ {"current_steps": 390, "total_steps": 390, "loss": 0.1011, "lr": 0.0, "epoch": 4.992, "percentage": 100.0, "elapsed_time": "2:54:57", "remaining_time": "0:00:00"}
391
+ {"current_steps": 390, "total_steps": 390, "epoch": 4.992, "percentage": 100.0, "elapsed_time": "2:59:25", "remaining_time": "0:00:00"}