ryanmarten commited on
Commit
9f77a11
·
verified ·
1 Parent(s): b53a004

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 sha256:875efa837cd331fd43d2993bbd83b08257739e0b1276bd7e34b7b56d5805abfe
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9cccb7e691895bebfc0a4700ffd7384c681dcd55f9c1991507eae829910b9af
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6aa8588cff67881cfb47f3c32ca19e582c93e4b0c43e2df5e32053bfffecac28
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2116f0e7575b0ba9d2a3726c90084cfe8a5953fd65cf0e980b56d6a600940a57
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:e9eb5a9229148887c187aa6cb1ee0f36fe8dc1547d199252f609a0b2e3f81832
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e12822746a0c35399243e195d3c8caf97c96be53872cb031baabb91c7faa6f3
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:b71e8b7f634c37d8877b40f84751f01f9eca8d41ea2e5eea88d07f88e1efa655
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14b584029df48faac0cc4d45b56ff49ac0ffdfa22614d2e81c8390db84001a02
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -312,3 +312,81 @@
312
  {"current_steps": 311, "total_steps": 390, "loss": 0.442, "lr": 4.794787480690597e-06, "epoch": 3.9808, "percentage": 79.74, "elapsed_time": "14:06:56", "remaining_time": "3:35:08"}
313
  {"current_steps": 312, "total_steps": 390, "loss": 0.448, "lr": 4.679111137620442e-06, "epoch": 3.9936, "percentage": 80.0, "elapsed_time": "14:09:31", "remaining_time": "3:32:22"}
314
  {"current_steps": 313, "total_steps": 390, "loss": 0.4229, "lr": 4.5646621393177e-06, "epoch": 4.0064, "percentage": 80.26, "elapsed_time": "14:13:07", "remaining_time": "3:29:52"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
312
  {"current_steps": 311, "total_steps": 390, "loss": 0.442, "lr": 4.794787480690597e-06, "epoch": 3.9808, "percentage": 79.74, "elapsed_time": "14:06:56", "remaining_time": "3:35:08"}
313
  {"current_steps": 312, "total_steps": 390, "loss": 0.448, "lr": 4.679111137620442e-06, "epoch": 3.9936, "percentage": 80.0, "elapsed_time": "14:09:31", "remaining_time": "3:32:22"}
314
  {"current_steps": 313, "total_steps": 390, "loss": 0.4229, "lr": 4.5646621393177e-06, "epoch": 4.0064, "percentage": 80.26, "elapsed_time": "14:13:07", "remaining_time": "3:29:52"}
315
+ {"current_steps": 314, "total_steps": 390, "loss": 0.4092, "lr": 4.451449654204685e-06, "epoch": 4.0192, "percentage": 80.51, "elapsed_time": "14:15:53", "remaining_time": "3:27:09"}
316
+ {"current_steps": 315, "total_steps": 390, "loss": 0.4061, "lr": 4.339482751647557e-06, "epoch": 4.032, "percentage": 80.77, "elapsed_time": "14:18:35", "remaining_time": "3:24:25"}
317
+ {"current_steps": 316, "total_steps": 390, "loss": 0.4082, "lr": 4.228770401229824e-06, "epoch": 4.0448, "percentage": 81.03, "elapsed_time": "14:21:14", "remaining_time": "3:21:41"}
318
+ {"current_steps": 317, "total_steps": 390, "loss": 0.4184, "lr": 4.119321472033779e-06, "epoch": 4.0576, "percentage": 81.28, "elapsed_time": "14:24:05", "remaining_time": "3:18:59"}
319
+ {"current_steps": 318, "total_steps": 390, "loss": 0.4122, "lr": 4.011144731929981e-06, "epoch": 4.0704, "percentage": 81.54, "elapsed_time": "14:26:48", "remaining_time": "3:16:15"}
320
+ {"current_steps": 319, "total_steps": 390, "loss": 0.4147, "lr": 3.904248846874894e-06, "epoch": 4.0832, "percentage": 81.79, "elapsed_time": "14:29:26", "remaining_time": "3:13:30"}
321
+ {"current_steps": 320, "total_steps": 390, "loss": 0.4223, "lr": 3.7986423802166705e-06, "epoch": 4.096, "percentage": 82.05, "elapsed_time": "14:32:08", "remaining_time": "3:10:46"}
322
+ {"current_steps": 321, "total_steps": 390, "loss": 0.4017, "lr": 3.694333792009115e-06, "epoch": 4.1088, "percentage": 82.31, "elapsed_time": "14:34:49", "remaining_time": "3:08:02"}
323
+ {"current_steps": 322, "total_steps": 390, "loss": 0.4135, "lr": 3.5913314383339937e-06, "epoch": 4.1216, "percentage": 82.56, "elapsed_time": "14:37:24", "remaining_time": "3:05:17"}
324
+ {"current_steps": 323, "total_steps": 390, "loss": 0.4203, "lr": 3.4896435706316e-06, "epoch": 4.1344, "percentage": 82.82, "elapsed_time": "14:40:04", "remaining_time": "3:02:33"}
325
+ {"current_steps": 324, "total_steps": 390, "loss": 0.438, "lr": 3.3892783350397675e-06, "epoch": 4.1472, "percentage": 83.08, "elapsed_time": "14:42:49", "remaining_time": "2:59:49"}
326
+ {"current_steps": 325, "total_steps": 390, "loss": 0.4173, "lr": 3.290243771741275e-06, "epoch": 4.16, "percentage": 83.33, "elapsed_time": "14:45:27", "remaining_time": "2:57:05"}
327
+ {"current_steps": 326, "total_steps": 390, "loss": 0.4085, "lr": 3.1925478143197418e-06, "epoch": 4.1728, "percentage": 83.59, "elapsed_time": "14:48:10", "remaining_time": "2:54:22"}
328
+ {"current_steps": 327, "total_steps": 390, "loss": 0.4216, "lr": 3.0961982891241083e-06, "epoch": 4.1856, "percentage": 83.85, "elapsed_time": "14:50:59", "remaining_time": "2:51:39"}
329
+ {"current_steps": 328, "total_steps": 390, "loss": 0.4106, "lr": 3.001202914641628e-06, "epoch": 4.1984, "percentage": 84.1, "elapsed_time": "14:53:46", "remaining_time": "2:48:56"}
330
+ {"current_steps": 329, "total_steps": 390, "loss": 0.437, "lr": 2.907569300879596e-06, "epoch": 4.2112, "percentage": 84.36, "elapsed_time": "14:56:20", "remaining_time": "2:46:11"}
331
+ {"current_steps": 330, "total_steps": 390, "loss": 0.4056, "lr": 2.815304948755664e-06, "epoch": 4.224, "percentage": 84.62, "elapsed_time": "14:59:08", "remaining_time": "2:43:28"}
332
+ {"current_steps": 331, "total_steps": 390, "loss": 0.4022, "lr": 2.7244172494969978e-06, "epoch": 4.2368, "percentage": 84.87, "elapsed_time": "15:01:45", "remaining_time": "2:40:44"}
333
+ {"current_steps": 332, "total_steps": 390, "loss": 0.416, "lr": 2.6349134840481294e-06, "epoch": 4.2496, "percentage": 85.13, "elapsed_time": "15:04:25", "remaining_time": "2:38:00"}
334
+ {"current_steps": 333, "total_steps": 390, "loss": 0.4171, "lr": 2.546800822487714e-06, "epoch": 4.2624, "percentage": 85.38, "elapsed_time": "15:07:18", "remaining_time": "2:35:18"}
335
+ {"current_steps": 334, "total_steps": 390, "loss": 0.4228, "lr": 2.4600863234541338e-06, "epoch": 4.2752, "percentage": 85.64, "elapsed_time": "15:10:01", "remaining_time": "2:32:34"}
336
+ {"current_steps": 335, "total_steps": 390, "loss": 0.4026, "lr": 2.374776933580025e-06, "epoch": 4.288, "percentage": 85.9, "elapsed_time": "15:12:41", "remaining_time": "2:29:50"}
337
+ {"current_steps": 336, "total_steps": 390, "loss": 0.4114, "lr": 2.2908794869358044e-06, "epoch": 4.3008, "percentage": 86.15, "elapsed_time": "15:15:22", "remaining_time": "2:27:06"}
338
+ {"current_steps": 337, "total_steps": 390, "loss": 0.4204, "lr": 2.2084007044821764e-06, "epoch": 4.3136, "percentage": 86.41, "elapsed_time": "15:17:58", "remaining_time": "2:24:22"}
339
+ {"current_steps": 338, "total_steps": 390, "loss": 0.4249, "lr": 2.127347193531757e-06, "epoch": 4.3264, "percentage": 86.67, "elapsed_time": "15:20:48", "remaining_time": "2:21:39"}
340
+ {"current_steps": 339, "total_steps": 390, "loss": 0.3998, "lr": 2.0477254472197237e-06, "epoch": 4.3392, "percentage": 86.92, "elapsed_time": "15:23:24", "remaining_time": "2:18:55"}
341
+ {"current_steps": 340, "total_steps": 390, "loss": 0.4043, "lr": 1.96954184398368e-06, "epoch": 4.352, "percentage": 87.18, "elapsed_time": "15:26:11", "remaining_time": "2:16:12"}
342
+ {"current_steps": 341, "total_steps": 390, "loss": 0.4255, "lr": 1.8928026470526917e-06, "epoch": 4.3648, "percentage": 87.44, "elapsed_time": "15:28:51", "remaining_time": "2:13:28"}
343
+ {"current_steps": 342, "total_steps": 390, "loss": 0.4102, "lr": 1.817514003945524e-06, "epoch": 4.3776, "percentage": 87.69, "elapsed_time": "15:31:32", "remaining_time": "2:10:44"}
344
+ {"current_steps": 343, "total_steps": 390, "loss": 0.4184, "lr": 1.743681945978184e-06, "epoch": 4.3904, "percentage": 87.95, "elapsed_time": "15:34:15", "remaining_time": "2:08:01"}
345
+ {"current_steps": 344, "total_steps": 390, "loss": 0.4288, "lr": 1.6713123877807413e-06, "epoch": 4.4032, "percentage": 88.21, "elapsed_time": "15:36:55", "remaining_time": "2:05:17"}
346
+ {"current_steps": 345, "total_steps": 390, "loss": 0.4364, "lr": 1.6004111268235156e-06, "epoch": 4.416, "percentage": 88.46, "elapsed_time": "15:39:40", "remaining_time": "2:02:34"}
347
+ {"current_steps": 346, "total_steps": 390, "loss": 0.3962, "lr": 1.5309838429526714e-06, "epoch": 4.4288, "percentage": 88.72, "elapsed_time": "15:42:17", "remaining_time": "1:59:49"}
348
+ {"current_steps": 347, "total_steps": 390, "loss": 0.4039, "lr": 1.4630360979351644e-06, "epoch": 4.4416, "percentage": 88.97, "elapsed_time": "15:44:55", "remaining_time": "1:57:05"}
349
+ {"current_steps": 348, "total_steps": 390, "loss": 0.4121, "lr": 1.396573335013236e-06, "epoch": 4.4544, "percentage": 89.23, "elapsed_time": "15:47:43", "remaining_time": "1:54:22"}
350
+ {"current_steps": 349, "total_steps": 390, "loss": 0.4292, "lr": 1.3316008784683265e-06, "epoch": 4.4672, "percentage": 89.49, "elapsed_time": "15:50:25", "remaining_time": "1:51:39"}
351
+ {"current_steps": 350, "total_steps": 390, "loss": 0.421, "lr": 1.2681239331945695e-06, "epoch": 4.48, "percentage": 89.74, "elapsed_time": "15:53:00", "remaining_time": "1:48:54"}
352
+ {"current_steps": 351, "total_steps": 390, "loss": 0.4134, "lr": 1.2061475842818337e-06, "epoch": 4.4928, "percentage": 90.0, "elapsed_time": "15:55:33", "remaining_time": "1:46:10"}
353
+ {"current_steps": 352, "total_steps": 390, "loss": 0.4113, "lr": 1.1456767966083393e-06, "epoch": 4.5056, "percentage": 90.26, "elapsed_time": "15:58:19", "remaining_time": "1:43:27"}
354
+ {"current_steps": 353, "total_steps": 390, "loss": 0.4098, "lr": 1.086716414442952e-06, "epoch": 4.5184, "percentage": 90.51, "elapsed_time": "16:01:08", "remaining_time": "1:40:44"}
355
+ {"current_steps": 354, "total_steps": 390, "loss": 0.4252, "lr": 1.0292711610570904e-06, "epoch": 4.5312, "percentage": 90.77, "elapsed_time": "16:03:43", "remaining_time": "1:38:00"}
356
+ {"current_steps": 355, "total_steps": 390, "loss": 0.4083, "lr": 9.733456383463658e-07, "epoch": 4.5440000000000005, "percentage": 91.03, "elapsed_time": "16:06:26", "remaining_time": "1:35:17"}
357
+ {"current_steps": 356, "total_steps": 390, "loss": 0.3998, "lr": 9.189443264619102e-07, "epoch": 4.5568, "percentage": 91.28, "elapsed_time": "16:09:07", "remaining_time": "1:32:33"}
358
+ {"current_steps": 357, "total_steps": 390, "loss": 0.4105, "lr": 8.660715834514977e-07, "epoch": 4.5696, "percentage": 91.54, "elapsed_time": "16:11:51", "remaining_time": "1:29:50"}
359
+ {"current_steps": 358, "total_steps": 390, "loss": 0.4172, "lr": 8.147316449103959e-07, "epoch": 4.5824, "percentage": 91.79, "elapsed_time": "16:14:34", "remaining_time": "1:27:06"}
360
+ {"current_steps": 359, "total_steps": 390, "loss": 0.4091, "lr": 7.649286236420806e-07, "epoch": 4.5952, "percentage": 92.05, "elapsed_time": "16:17:07", "remaining_time": "1:24:22"}
361
+ {"current_steps": 360, "total_steps": 390, "loss": 0.4077, "lr": 7.166665093287539e-07, "epoch": 4.608, "percentage": 92.31, "elapsed_time": "16:19:56", "remaining_time": "1:21:39"}
362
+ {"current_steps": 361, "total_steps": 390, "loss": 0.4317, "lr": 6.69949168211721e-07, "epoch": 4.6208, "percentage": 92.56, "elapsed_time": "16:22:34", "remaining_time": "1:18:55"}
363
+ {"current_steps": 362, "total_steps": 390, "loss": 0.4306, "lr": 6.247803427816945e-07, "epoch": 4.6336, "percentage": 92.82, "elapsed_time": "16:25:17", "remaining_time": "1:16:12"}
364
+ {"current_steps": 363, "total_steps": 390, "loss": 0.4123, "lr": 5.811636514789598e-07, "epoch": 4.6464, "percentage": 93.08, "elapsed_time": "16:27:53", "remaining_time": "1:13:28"}
365
+ {"current_steps": 364, "total_steps": 390, "loss": 0.4072, "lr": 5.391025884035239e-07, "epoch": 4.6592, "percentage": 93.33, "elapsed_time": "16:30:34", "remaining_time": "1:10:45"}
366
+ {"current_steps": 365, "total_steps": 390, "loss": 0.4173, "lr": 4.986005230351954e-07, "epoch": 4.672, "percentage": 93.59, "elapsed_time": "16:33:14", "remaining_time": "1:08:01"}
367
+ {"current_steps": 366, "total_steps": 390, "loss": 0.4, "lr": 4.5966069996365993e-07, "epoch": 4.6848, "percentage": 93.85, "elapsed_time": "16:36:07", "remaining_time": "1:05:19"}
368
+ {"current_steps": 367, "total_steps": 390, "loss": 0.4123, "lr": 4.22286238628562e-07, "epoch": 4.6975999999999996, "percentage": 94.1, "elapsed_time": "16:38:48", "remaining_time": "1:02:35"}
369
+ {"current_steps": 368, "total_steps": 390, "loss": 0.4203, "lr": 3.8648013306960664e-07, "epoch": 4.7104, "percentage": 94.36, "elapsed_time": "16:41:32", "remaining_time": "0:59:52"}
370
+ {"current_steps": 369, "total_steps": 390, "loss": 0.4118, "lr": 3.522452516867048e-07, "epoch": 4.7232, "percentage": 94.62, "elapsed_time": "16:44:14", "remaining_time": "0:57:09"}
371
+ {"current_steps": 370, "total_steps": 390, "loss": 0.4079, "lr": 3.1958433701019697e-07, "epoch": 4.736, "percentage": 94.87, "elapsed_time": "16:46:47", "remaining_time": "0:54:25"}
372
+ {"current_steps": 371, "total_steps": 390, "loss": 0.3994, "lr": 2.8850000548115155e-07, "epoch": 4.7488, "percentage": 95.13, "elapsed_time": "16:49:10", "remaining_time": "0:51:40"}
373
+ {"current_steps": 372, "total_steps": 390, "loss": 0.4306, "lr": 2.5899474724174313e-07, "epoch": 4.7616, "percentage": 95.38, "elapsed_time": "16:51:46", "remaining_time": "0:48:57"}
374
+ {"current_steps": 373, "total_steps": 390, "loss": 0.4251, "lr": 2.3107092593579905e-07, "epoch": 4.7744, "percentage": 95.64, "elapsed_time": "16:54:31", "remaining_time": "0:46:14"}
375
+ {"current_steps": 374, "total_steps": 390, "loss": 0.4051, "lr": 2.0473077851942858e-07, "epoch": 4.7872, "percentage": 95.9, "elapsed_time": "16:57:18", "remaining_time": "0:43:31"}
376
+ {"current_steps": 375, "total_steps": 390, "loss": 0.4216, "lr": 1.799764150818306e-07, "epoch": 4.8, "percentage": 96.15, "elapsed_time": "17:00:02", "remaining_time": "0:40:48"}
377
+ {"current_steps": 376, "total_steps": 390, "loss": 0.4017, "lr": 1.5680981867625566e-07, "epoch": 4.8128, "percentage": 96.41, "elapsed_time": "17:02:36", "remaining_time": "0:38:04"}
378
+ {"current_steps": 377, "total_steps": 390, "loss": 0.4075, "lr": 1.3523284516113955e-07, "epoch": 4.8256, "percentage": 96.67, "elapsed_time": "17:05:12", "remaining_time": "0:35:21"}
379
+ {"current_steps": 378, "total_steps": 390, "loss": 0.4153, "lr": 1.1524722305144231e-07, "epoch": 4.8384, "percentage": 96.92, "elapsed_time": "17:07:45", "remaining_time": "0:32:37"}
380
+ {"current_steps": 379, "total_steps": 390, "loss": 0.4284, "lr": 9.685455338016347e-08, "epoch": 4.8512, "percentage": 97.18, "elapsed_time": "17:10:23", "remaining_time": "0:29:54"}
381
+ {"current_steps": 380, "total_steps": 390, "loss": 0.4379, "lr": 8.005630957010014e-08, "epoch": 4.864, "percentage": 97.44, "elapsed_time": "17:13:09", "remaining_time": "0:27:11"}
382
+ {"current_steps": 381, "total_steps": 390, "loss": 0.4223, "lr": 6.485383731580142e-08, "epoch": 4.8768, "percentage": 97.69, "elapsed_time": "17:15:58", "remaining_time": "0:24:28"}
383
+ {"current_steps": 382, "total_steps": 390, "loss": 0.4091, "lr": 5.1248354475768034e-08, "epoch": 4.8896, "percentage": 97.95, "elapsed_time": "17:18:43", "remaining_time": "0:21:45"}
384
+ {"current_steps": 383, "total_steps": 390, "loss": 0.4092, "lr": 3.924095097489922e-08, "epoch": 4.9024, "percentage": 98.21, "elapsed_time": "17:21:13", "remaining_time": "0:19:01"}
385
+ {"current_steps": 384, "total_steps": 390, "loss": 0.4231, "lr": 2.8832588717164766e-08, "epoch": 4.9152000000000005, "percentage": 98.46, "elapsed_time": "17:23:44", "remaining_time": "0:16:18"}
386
+ {"current_steps": 385, "total_steps": 390, "loss": 0.3954, "lr": 2.0024101508555604e-08, "epoch": 4.928, "percentage": 98.72, "elapsed_time": "17:26:28", "remaining_time": "0:13:35"}
387
+ {"current_steps": 386, "total_steps": 390, "loss": 0.4179, "lr": 1.281619499029274e-08, "epoch": 4.9408, "percentage": 98.97, "elapsed_time": "17:29:08", "remaining_time": "0:10:52"}
388
+ {"current_steps": 387, "total_steps": 390, "loss": 0.4213, "lr": 7.209446582292501e-09, "epoch": 4.9536, "percentage": 99.23, "elapsed_time": "17:31:47", "remaining_time": "0:08:09"}
389
+ {"current_steps": 388, "total_steps": 390, "loss": 0.416, "lr": 3.2043054369057523e-09, "epoch": 4.9664, "percentage": 99.49, "elapsed_time": "17:34:25", "remaining_time": "0:05:26"}
390
+ {"current_steps": 389, "total_steps": 390, "loss": 0.4095, "lr": 8.010924029533406e-10, "epoch": 4.9792, "percentage": 99.74, "elapsed_time": "17:36:59", "remaining_time": "0:02:43"}
391
+ {"current_steps": 390, "total_steps": 390, "loss": 0.4022, "lr": 0.0, "epoch": 4.992, "percentage": 100.0, "elapsed_time": "17:39:42", "remaining_time": "0:00:00"}
392
+ {"current_steps": 390, "total_steps": 390, "epoch": 4.992, "percentage": 100.0, "elapsed_time": "17:41:53", "remaining_time": "0:00:00"}