yuzhounie commited on
Commit
f9f2255
·
verified ·
1 Parent(s): 9843417

Training in progress, step 366

Browse files
model-00001-of-00006.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:12c9a3aac0fe1a3b7ae85bf60328212e49ef81b52ec54043b4188d1fc35f6e9f
3
  size 4986211280
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:acd5a27104a5f909df36e9616020e51b327ba110d180cd55eae334438873e7c9
3
  size 4986211280
model-00002-of-00006.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4a6b75ecc32886f9fb5a82ad02512a1377aa626688027eb5c9932502892e4a3c
3
  size 4954847344
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:534fdcebc4e9dff2282ba45c3f950f1a2c73373fb39effb779f8f30b32b5f3f3
3
  size 4954847344
model-00003-of-00006.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6435465b368f32be72d340e1f8993295954b628fc18b831a27176c7ab25b6ef9
3
  size 4954847392
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52ccdcda824007338b63b4e82b94ba7d903d0b600a7a6e199185d8b2e2184e6a
3
  size 4954847392
model-00004-of-00006.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3bf1c92a32870ba09b95ef4d61585d5a6448ff9fcb2cbdae668d737307835979
3
  size 4954847392
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e01f8d931915a78acbeec65bd2eb3c5380cf121f1944b740561365c91c76658
3
  size 4954847392
model-00005-of-00006.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:22f24dc7132d1a9ac06a252c92133877e9a27d9d251e455fb55ff4648f9a2610
3
  size 4954847392
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f25e3dcbf13d496cecb70217f0260abe99cca6c08b2b4ce95123e8978bba3dff
3
  size 4954847392
model-00006-of-00006.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b90254a42bc66c2e8224de869cd641f758184d02f86a9f06c64a3e9b253264e5
3
  size 4734533160
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc95ed35ea34d1dd68e9e4f8ab0dbd1b8bace949a7030761db10ec6c41169339
3
  size 4734533160
trainer_log.jsonl CHANGED
@@ -302,3 +302,66 @@
302
  {"current_steps": 302, "total_steps": 366, "loss": 0.3973, "lr": 9.325824311285564e-07, "epoch": 2.4583901773533423, "percentage": 82.51, "elapsed_time": "6:35:39", "remaining_time": "1:23:50"}
303
  {"current_steps": 303, "total_steps": 366, "loss": 0.4261, "lr": 9.050006215123419e-07, "epoch": 2.466575716234652, "percentage": 82.79, "elapsed_time": "6:36:56", "remaining_time": "1:22:31"}
304
  {"current_steps": 304, "total_steps": 366, "loss": 0.4053, "lr": 8.777921982911996e-07, "epoch": 2.4747612551159617, "percentage": 83.06, "elapsed_time": "6:38:01", "remaining_time": "1:21:10"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
302
  {"current_steps": 302, "total_steps": 366, "loss": 0.3973, "lr": 9.325824311285564e-07, "epoch": 2.4583901773533423, "percentage": 82.51, "elapsed_time": "6:35:39", "remaining_time": "1:23:50"}
303
  {"current_steps": 303, "total_steps": 366, "loss": 0.4261, "lr": 9.050006215123419e-07, "epoch": 2.466575716234652, "percentage": 82.79, "elapsed_time": "6:36:56", "remaining_time": "1:22:31"}
304
  {"current_steps": 304, "total_steps": 366, "loss": 0.4053, "lr": 8.777921982911996e-07, "epoch": 2.4747612551159617, "percentage": 83.06, "elapsed_time": "6:38:01", "remaining_time": "1:21:10"}
305
+ {"current_steps": 305, "total_steps": 366, "loss": 0.4035, "lr": 8.509596423580712e-07, "epoch": 2.4829467939972716, "percentage": 83.33, "elapsed_time": "6:39:15", "remaining_time": "1:19:51"}
306
+ {"current_steps": 306, "total_steps": 366, "loss": 0.3895, "lr": 8.245054003339247e-07, "epoch": 2.491132332878581, "percentage": 83.61, "elapsed_time": "6:40:13", "remaining_time": "1:18:28"}
307
+ {"current_steps": 307, "total_steps": 366, "loss": 0.4015, "lr": 7.984318843446593e-07, "epoch": 2.499317871759891, "percentage": 83.88, "elapsed_time": "6:41:54", "remaining_time": "1:17:14"}
308
+ {"current_steps": 308, "total_steps": 366, "loss": 0.4006, "lr": 7.727414718011706e-07, "epoch": 2.5075034106412004, "percentage": 84.15, "elapsed_time": "6:43:30", "remaining_time": "1:15:59"}
309
+ {"current_steps": 309, "total_steps": 366, "loss": 0.4164, "lr": 7.474365051825749e-07, "epoch": 2.5156889495225103, "percentage": 84.43, "elapsed_time": "6:44:50", "remaining_time": "1:14:40"}
310
+ {"current_steps": 310, "total_steps": 366, "loss": 0.3882, "lr": 7.225192918226215e-07, "epoch": 2.52387448840382, "percentage": 84.7, "elapsed_time": "6:45:55", "remaining_time": "1:13:19"}
311
+ {"current_steps": 311, "total_steps": 366, "loss": 0.4149, "lr": 6.979921036993042e-07, "epoch": 2.5320600272851297, "percentage": 84.97, "elapsed_time": "6:47:21", "remaining_time": "1:12:02"}
312
+ {"current_steps": 312, "total_steps": 366, "loss": 0.4117, "lr": 6.738571772276997e-07, "epoch": 2.540245566166439, "percentage": 85.25, "elapsed_time": "6:48:41", "remaining_time": "1:10:44"}
313
+ {"current_steps": 313, "total_steps": 366, "loss": 0.3916, "lr": 6.501167130560515e-07, "epoch": 2.548431105047749, "percentage": 85.52, "elapsed_time": "6:49:54", "remaining_time": "1:09:24"}
314
+ {"current_steps": 314, "total_steps": 366, "loss": 0.411, "lr": 6.267728758651131e-07, "epoch": 2.5566166439290585, "percentage": 85.79, "elapsed_time": "6:51:11", "remaining_time": "1:08:05"}
315
+ {"current_steps": 315, "total_steps": 366, "loss": 0.3826, "lr": 6.038277941707671e-07, "epoch": 2.5648021828103684, "percentage": 86.07, "elapsed_time": "6:52:13", "remaining_time": "1:06:44"}
316
+ {"current_steps": 316, "total_steps": 366, "loss": 0.4027, "lr": 5.812835601299438e-07, "epoch": 2.572987721691678, "percentage": 86.34, "elapsed_time": "6:53:24", "remaining_time": "1:05:24"}
317
+ {"current_steps": 317, "total_steps": 366, "loss": 0.4123, "lr": 5.591422293498633e-07, "epoch": 2.581173260572988, "percentage": 86.61, "elapsed_time": "6:54:44", "remaining_time": "1:04:06"}
318
+ {"current_steps": 318, "total_steps": 366, "loss": 0.3929, "lr": 5.374058207005945e-07, "epoch": 2.5893587994542973, "percentage": 86.89, "elapsed_time": "6:55:59", "remaining_time": "1:02:47"}
319
+ {"current_steps": 319, "total_steps": 366, "loss": 0.3874, "lr": 5.160763161309768e-07, "epoch": 2.597544338335607, "percentage": 87.16, "elapsed_time": "6:57:07", "remaining_time": "1:01:27"}
320
+ {"current_steps": 320, "total_steps": 366, "loss": 0.4153, "lr": 4.951556604879049e-07, "epoch": 2.6057298772169166, "percentage": 87.43, "elapsed_time": "6:58:24", "remaining_time": "1:00:08"}
321
+ {"current_steps": 321, "total_steps": 366, "loss": 0.3866, "lr": 4.7464576133899043e-07, "epoch": 2.6139154160982265, "percentage": 87.7, "elapsed_time": "6:59:30", "remaining_time": "0:58:48"}
322
+ {"current_steps": 322, "total_steps": 366, "loss": 0.4131, "lr": 4.545484887986368e-07, "epoch": 2.622100954979536, "percentage": 87.98, "elapsed_time": "7:00:38", "remaining_time": "0:57:28"}
323
+ {"current_steps": 323, "total_steps": 366, "loss": 0.4046, "lr": 4.348656753575092e-07, "epoch": 2.630286493860846, "percentage": 88.25, "elapsed_time": "7:01:58", "remaining_time": "0:56:10"}
324
+ {"current_steps": 324, "total_steps": 366, "loss": 0.4142, "lr": 4.1559911571545544e-07, "epoch": 2.6384720327421554, "percentage": 88.52, "elapsed_time": "7:03:09", "remaining_time": "0:54:51"}
325
+ {"current_steps": 325, "total_steps": 366, "loss": 0.405, "lr": 3.9675056661785563e-07, "epoch": 2.6466575716234653, "percentage": 88.8, "elapsed_time": "7:04:27", "remaining_time": "0:53:32"}
326
+ {"current_steps": 326, "total_steps": 366, "loss": 0.3924, "lr": 3.783217466954503e-07, "epoch": 2.6548431105047747, "percentage": 89.07, "elapsed_time": "7:05:41", "remaining_time": "0:52:13"}
327
+ {"current_steps": 327, "total_steps": 366, "loss": 0.405, "lr": 3.603143363076217e-07, "epoch": 2.6630286493860846, "percentage": 89.34, "elapsed_time": "7:06:53", "remaining_time": "0:50:54"}
328
+ {"current_steps": 328, "total_steps": 366, "loss": 0.3855, "lr": 3.427299773891868e-07, "epoch": 2.6712141882673945, "percentage": 89.62, "elapsed_time": "7:07:38", "remaining_time": "0:49:32"}
329
+ {"current_steps": 329, "total_steps": 366, "loss": 0.3987, "lr": 3.255702733006766e-07, "epoch": 2.679399727148704, "percentage": 89.89, "elapsed_time": "7:08:56", "remaining_time": "0:48:14"}
330
+ {"current_steps": 330, "total_steps": 366, "loss": 0.3946, "lr": 3.088367886821481e-07, "epoch": 2.6875852660300135, "percentage": 90.16, "elapsed_time": "7:10:14", "remaining_time": "0:46:56"}
331
+ {"current_steps": 331, "total_steps": 366, "loss": 0.4186, "lr": 2.925310493105099e-07, "epoch": 2.6957708049113234, "percentage": 90.44, "elapsed_time": "7:11:41", "remaining_time": "0:45:38"}
332
+ {"current_steps": 332, "total_steps": 366, "loss": 0.4052, "lr": 2.7665454196040665e-07, "epoch": 2.7039563437926333, "percentage": 90.71, "elapsed_time": "7:12:50", "remaining_time": "0:44:19"}
333
+ {"current_steps": 333, "total_steps": 366, "loss": 0.3807, "lr": 2.6120871426864866e-07, "epoch": 2.7121418826739427, "percentage": 90.98, "elapsed_time": "7:14:05", "remaining_time": "0:43:01"}
334
+ {"current_steps": 334, "total_steps": 366, "loss": 0.4101, "lr": 2.4619497460222184e-07, "epoch": 2.720327421555252, "percentage": 91.26, "elapsed_time": "7:15:18", "remaining_time": "0:41:42"}
335
+ {"current_steps": 335, "total_steps": 366, "loss": 0.3873, "lr": 2.316146919298623e-07, "epoch": 2.728512960436562, "percentage": 91.53, "elapsed_time": "7:16:40", "remaining_time": "0:40:24"}
336
+ {"current_steps": 336, "total_steps": 366, "loss": 0.4159, "lr": 2.1746919569723858e-07, "epoch": 2.736698499317872, "percentage": 91.8, "elapsed_time": "7:17:43", "remaining_time": "0:39:04"}
337
+ {"current_steps": 337, "total_steps": 366, "loss": 0.4098, "lr": 2.037597757057297e-07, "epoch": 2.7448840381991815, "percentage": 92.08, "elapsed_time": "7:18:52", "remaining_time": "0:37:46"}
338
+ {"current_steps": 338, "total_steps": 366, "loss": 0.3932, "lr": 1.9048768199481983e-07, "epoch": 2.753069577080491, "percentage": 92.35, "elapsed_time": "7:20:01", "remaining_time": "0:36:27"}
339
+ {"current_steps": 339, "total_steps": 366, "loss": 0.4107, "lr": 1.776541247281177e-07, "epoch": 2.761255115961801, "percentage": 92.62, "elapsed_time": "7:21:19", "remaining_time": "0:35:08"}
340
+ {"current_steps": 340, "total_steps": 366, "loss": 0.4037, "lr": 1.6526027408301227e-07, "epoch": 2.7694406548431107, "percentage": 92.9, "elapsed_time": "7:22:22", "remaining_time": "0:33:49"}
341
+ {"current_steps": 341, "total_steps": 366, "loss": 0.4109, "lr": 1.5330726014397668e-07, "epoch": 2.77762619372442, "percentage": 93.17, "elapsed_time": "7:23:42", "remaining_time": "0:32:31"}
342
+ {"current_steps": 342, "total_steps": 366, "loss": 0.411, "lr": 1.417961727995254e-07, "epoch": 2.7858117326057297, "percentage": 93.44, "elapsed_time": "7:24:38", "remaining_time": "0:31:12"}
343
+ {"current_steps": 343, "total_steps": 366, "loss": 0.4278, "lr": 1.307280616428336e-07, "epoch": 2.7939972714870396, "percentage": 93.72, "elapsed_time": "7:26:15", "remaining_time": "0:29:55"}
344
+ {"current_steps": 344, "total_steps": 366, "loss": 0.4309, "lr": 1.2010393587603975e-07, "epoch": 2.8021828103683495, "percentage": 93.99, "elapsed_time": "7:27:39", "remaining_time": "0:28:37"}
345
+ {"current_steps": 345, "total_steps": 366, "loss": 0.4018, "lr": 1.0992476421822052e-07, "epoch": 2.810368349249659, "percentage": 94.26, "elapsed_time": "7:28:51", "remaining_time": "0:27:19"}
346
+ {"current_steps": 346, "total_steps": 366, "loss": 0.3798, "lr": 1.0019147481706626e-07, "epoch": 2.8185538881309684, "percentage": 94.54, "elapsed_time": "7:29:55", "remaining_time": "0:26:00"}
347
+ {"current_steps": 347, "total_steps": 366, "loss": 0.3934, "lr": 9.090495516424713e-08, "epoch": 2.8267394270122783, "percentage": 94.81, "elapsed_time": "7:31:18", "remaining_time": "0:24:42"}
348
+ {"current_steps": 348, "total_steps": 366, "loss": 0.4083, "lr": 8.206605201449447e-08, "epoch": 2.8349249658935882, "percentage": 95.08, "elapsed_time": "7:32:37", "remaining_time": "0:23:24"}
349
+ {"current_steps": 349, "total_steps": 366, "loss": 0.4198, "lr": 7.367557130838921e-08, "epoch": 2.8431105047748977, "percentage": 95.36, "elapsed_time": "7:33:54", "remaining_time": "0:22:06"}
350
+ {"current_steps": 350, "total_steps": 366, "loss": 0.4052, "lr": 6.573427809888067e-08, "epoch": 2.851296043656207, "percentage": 95.63, "elapsed_time": "7:35:27", "remaining_time": "0:20:49"}
351
+ {"current_steps": 351, "total_steps": 366, "loss": 0.4049, "lr": 5.824289648152126e-08, "epoch": 2.859481582537517, "percentage": 95.9, "elapsed_time": "7:36:27", "remaining_time": "0:19:30"}
352
+ {"current_steps": 352, "total_steps": 366, "loss": 0.4082, "lr": 5.120210952844873e-08, "epoch": 2.867667121418827, "percentage": 96.17, "elapsed_time": "7:37:48", "remaining_time": "0:18:12"}
353
+ {"current_steps": 353, "total_steps": 366, "loss": 0.4097, "lr": 4.461255922609986e-08, "epoch": 2.8758526603001364, "percentage": 96.45, "elapsed_time": "7:39:02", "remaining_time": "0:16:54"}
354
+ {"current_steps": 354, "total_steps": 366, "loss": 0.399, "lr": 3.8474846416672874e-08, "epoch": 2.884038199181446, "percentage": 96.72, "elapsed_time": "7:40:16", "remaining_time": "0:15:36"}
355
+ {"current_steps": 355, "total_steps": 366, "loss": 0.3937, "lr": 3.278953074334512e-08, "epoch": 2.892223738062756, "percentage": 96.99, "elapsed_time": "7:41:32", "remaining_time": "0:14:18"}
356
+ {"current_steps": 356, "total_steps": 366, "loss": 0.3895, "lr": 2.75571305992417e-08, "epoch": 2.9004092769440657, "percentage": 97.27, "elapsed_time": "7:42:57", "remaining_time": "0:13:00"}
357
+ {"current_steps": 357, "total_steps": 366, "loss": 0.4154, "lr": 2.2778123080167136e-08, "epoch": 2.908594815825375, "percentage": 97.54, "elapsed_time": "7:44:18", "remaining_time": "0:11:42"}
358
+ {"current_steps": 358, "total_steps": 366, "loss": 0.3989, "lr": 1.845294394110686e-08, "epoch": 2.9167803547066846, "percentage": 97.81, "elapsed_time": "7:45:20", "remaining_time": "0:10:23"}
359
+ {"current_steps": 359, "total_steps": 366, "loss": 0.4218, "lr": 1.4581987556490095e-08, "epoch": 2.9249658935879945, "percentage": 98.09, "elapsed_time": "7:46:31", "remaining_time": "0:09:05"}
360
+ {"current_steps": 360, "total_steps": 366, "loss": 0.4093, "lr": 1.1165606884234182e-08, "epoch": 2.9331514324693044, "percentage": 98.36, "elapsed_time": "7:47:38", "remaining_time": "0:07:47"}
361
+ {"current_steps": 361, "total_steps": 366, "loss": 0.3715, "lr": 8.204113433559202e-09, "epoch": 2.941336971350614, "percentage": 98.63, "elapsed_time": "7:48:44", "remaining_time": "0:06:29"}
362
+ {"current_steps": 362, "total_steps": 366, "loss": 0.3921, "lr": 5.6977772365857105e-09, "epoch": 2.9495225102319234, "percentage": 98.91, "elapsed_time": "7:50:10", "remaining_time": "0:05:11"}
363
+ {"current_steps": 363, "total_steps": 366, "loss": 0.4069, "lr": 3.6468268237105364e-09, "epoch": 2.9577080491132333, "percentage": 99.18, "elapsed_time": "7:51:13", "remaining_time": "0:03:53"}
364
+ {"current_steps": 364, "total_steps": 366, "loss": 0.4078, "lr": 2.0514492027728928e-09, "epoch": 2.965893587994543, "percentage": 99.45, "elapsed_time": "7:52:20", "remaining_time": "0:02:35"}
365
+ {"current_steps": 365, "total_steps": 366, "loss": 0.3989, "lr": 9.117898419991333e-10, "epoch": 2.9740791268758526, "percentage": 99.73, "elapsed_time": "7:53:41", "remaining_time": "0:01:17"}
366
+ {"current_steps": 366, "total_steps": 366, "loss": 0.3826, "lr": 2.2795265674113721e-10, "epoch": 2.982264665757162, "percentage": 100.0, "elapsed_time": "7:54:59", "remaining_time": "0:00:00"}
367
+ {"current_steps": 366, "total_steps": 366, "epoch": 2.982264665757162, "percentage": 100.0, "elapsed_time": "7:59:12", "remaining_time": "0:00:00"}