sedrickkeh commited on
Commit
f33918c
·
verified ·
1 Parent(s): 70aacc0

Training in progress, epoch 2

Browse files
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2f3c971660901a1655ee18c29f3c53e3dc71935e9e4c7275a11efdccfc6b94dd
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:024c2d73eabf54f5f55226b1d195c55bbf6e4807bc0beeab660cbe1dd13cc039
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:ea615d92e25de72d20fe37daf50e674ce5448f14772bbd012547d33e2638b481
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed2cecdd15b1833b4a648a310b13a3614ba662972c7bfbd991c7ac6ac98da89d
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:dca65352e4675b8c82bb0a8db1b8c2c43f1e375990c7619700ce6d3c87cb7fea
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad7dc21ff9389f0f5853cd8d141f233cc2694bc8cb3ee7e499e4c8118e2f0324
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:24eb1b719b3e939488a63aa320db2f244c67c1215c41830be868bfc7fbfb2a7f
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90ff5d2f65305dadbceb26838c7d57c74945ef155a3d1e71606ce13ed21b7040
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -332,3 +332,168 @@
332
  {"current_steps": 332, "total_steps": 498, "loss": 0.9373, "lr": 3.021986242574707e-06, "epoch": 1.994, "percentage": 66.67, "elapsed_time": "5:06:37", "remaining_time": "2:33:18"}
333
  {"current_steps": 333, "total_steps": 498, "loss": 1.2604, "lr": 2.989833054244232e-06, "epoch": 2.002, "percentage": 66.87, "elapsed_time": "5:08:40", "remaining_time": "2:32:56"}
334
  {"current_steps": 334, "total_steps": 498, "loss": 0.7464, "lr": 2.95777871532002e-06, "epoch": 2.008, "percentage": 67.07, "elapsed_time": "5:09:41", "remaining_time": "2:32:03"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
332
  {"current_steps": 332, "total_steps": 498, "loss": 0.9373, "lr": 3.021986242574707e-06, "epoch": 1.994, "percentage": 66.67, "elapsed_time": "5:06:37", "remaining_time": "2:33:18"}
333
  {"current_steps": 333, "total_steps": 498, "loss": 1.2604, "lr": 2.989833054244232e-06, "epoch": 2.002, "percentage": 66.87, "elapsed_time": "5:08:40", "remaining_time": "2:32:56"}
334
  {"current_steps": 334, "total_steps": 498, "loss": 0.7464, "lr": 2.95777871532002e-06, "epoch": 2.008, "percentage": 67.07, "elapsed_time": "5:09:41", "remaining_time": "2:32:03"}
335
+ {"current_steps": 335, "total_steps": 498, "loss": 0.7502, "lr": 2.9258248020653617e-06, "epoch": 2.014, "percentage": 67.27, "elapsed_time": "5:10:43", "remaining_time": "2:31:11"}
336
+ {"current_steps": 336, "total_steps": 498, "loss": 0.8084, "lr": 2.893972885805148e-06, "epoch": 2.02, "percentage": 67.47, "elapsed_time": "5:11:48", "remaining_time": "2:30:20"}
337
+ {"current_steps": 337, "total_steps": 498, "loss": 0.7463, "lr": 2.862224532848591e-06, "epoch": 2.026, "percentage": 67.67, "elapsed_time": "5:12:42", "remaining_time": "2:29:23"}
338
+ {"current_steps": 338, "total_steps": 498, "loss": 0.7751, "lr": 2.83058130441221e-06, "epoch": 2.032, "percentage": 67.87, "elapsed_time": "5:13:35", "remaining_time": "2:28:26"}
339
+ {"current_steps": 339, "total_steps": 498, "loss": 0.7935, "lr": 2.799044756543054e-06, "epoch": 2.038, "percentage": 68.07, "elapsed_time": "5:14:35", "remaining_time": "2:27:33"}
340
+ {"current_steps": 340, "total_steps": 498, "loss": 0.7491, "lr": 2.7676164400421864e-06, "epoch": 2.044, "percentage": 68.27, "elapsed_time": "5:15:32", "remaining_time": "2:26:38"}
341
+ {"current_steps": 341, "total_steps": 498, "loss": 0.8321, "lr": 2.7362979003884154e-06, "epoch": 2.05, "percentage": 68.47, "elapsed_time": "5:16:25", "remaining_time": "2:25:41"}
342
+ {"current_steps": 342, "total_steps": 498, "loss": 0.7378, "lr": 2.705090677662311e-06, "epoch": 2.056, "percentage": 68.67, "elapsed_time": "5:17:16", "remaining_time": "2:24:43"}
343
+ {"current_steps": 343, "total_steps": 498, "loss": 0.9362, "lr": 2.6739963064704634e-06, "epoch": 2.062, "percentage": 68.88, "elapsed_time": "5:18:18", "remaining_time": "2:23:50"}
344
+ {"current_steps": 344, "total_steps": 498, "loss": 0.7629, "lr": 2.6430163158700116e-06, "epoch": 2.068, "percentage": 69.08, "elapsed_time": "5:19:05", "remaining_time": "2:22:50"}
345
+ {"current_steps": 345, "total_steps": 498, "loss": 0.6881, "lr": 2.61215222929347e-06, "epoch": 2.074, "percentage": 69.28, "elapsed_time": "5:19:58", "remaining_time": "2:21:53"}
346
+ {"current_steps": 346, "total_steps": 498, "loss": 0.8796, "lr": 2.5814055644738013e-06, "epoch": 2.08, "percentage": 69.48, "elapsed_time": "5:20:54", "remaining_time": "2:20:58"}
347
+ {"current_steps": 347, "total_steps": 498, "loss": 0.7191, "lr": 2.5507778333697817e-06, "epoch": 2.086, "percentage": 69.68, "elapsed_time": "5:21:46", "remaining_time": "2:20:01"}
348
+ {"current_steps": 348, "total_steps": 498, "loss": 0.7626, "lr": 2.520270542091663e-06, "epoch": 2.092, "percentage": 69.88, "elapsed_time": "5:22:38", "remaining_time": "2:19:04"}
349
+ {"current_steps": 349, "total_steps": 498, "loss": 0.804, "lr": 2.4898851908270903e-06, "epoch": 2.098, "percentage": 70.08, "elapsed_time": "5:23:35", "remaining_time": "2:18:08"}
350
+ {"current_steps": 350, "total_steps": 498, "loss": 0.7554, "lr": 2.4596232737673544e-06, "epoch": 2.104, "percentage": 70.28, "elapsed_time": "5:24:30", "remaining_time": "2:17:13"}
351
+ {"current_steps": 351, "total_steps": 498, "loss": 0.7417, "lr": 2.429486279033892e-06, "epoch": 2.11, "percentage": 70.48, "elapsed_time": "5:25:22", "remaining_time": "2:16:16"}
352
+ {"current_steps": 352, "total_steps": 498, "loss": 0.8689, "lr": 2.3994756886051267e-06, "epoch": 2.116, "percentage": 70.68, "elapsed_time": "5:26:21", "remaining_time": "2:15:21"}
353
+ {"current_steps": 353, "total_steps": 498, "loss": 0.7424, "lr": 2.3695929782435845e-06, "epoch": 2.122, "percentage": 70.88, "elapsed_time": "5:27:19", "remaining_time": "2:14:27"}
354
+ {"current_steps": 354, "total_steps": 498, "loss": 0.8748, "lr": 2.339839617423318e-06, "epoch": 2.128, "percentage": 71.08, "elapsed_time": "5:28:17", "remaining_time": "2:13:32"}
355
+ {"current_steps": 355, "total_steps": 498, "loss": 0.6957, "lr": 2.3102170692576593e-06, "epoch": 2.134, "percentage": 71.29, "elapsed_time": "5:29:11", "remaining_time": "2:12:36"}
356
+ {"current_steps": 356, "total_steps": 498, "loss": 0.8587, "lr": 2.280726790427258e-06, "epoch": 2.14, "percentage": 71.49, "elapsed_time": "5:30:05", "remaining_time": "2:11:39"}
357
+ {"current_steps": 357, "total_steps": 498, "loss": 0.7431, "lr": 2.2513702311084595e-06, "epoch": 2.146, "percentage": 71.69, "elapsed_time": "5:30:59", "remaining_time": "2:10:43"}
358
+ {"current_steps": 358, "total_steps": 498, "loss": 0.8245, "lr": 2.2221488349019903e-06, "epoch": 2.152, "percentage": 71.89, "elapsed_time": "5:31:45", "remaining_time": "2:09:44"}
359
+ {"current_steps": 359, "total_steps": 498, "loss": 0.7456, "lr": 2.1930640387619616e-06, "epoch": 2.158, "percentage": 72.09, "elapsed_time": "5:32:38", "remaining_time": "2:08:47"}
360
+ {"current_steps": 360, "total_steps": 498, "loss": 0.79, "lr": 2.1641172729252206e-06, "epoch": 2.164, "percentage": 72.29, "elapsed_time": "5:33:32", "remaining_time": "2:07:51"}
361
+ {"current_steps": 361, "total_steps": 498, "loss": 0.6949, "lr": 2.1353099608410095e-06, "epoch": 2.17, "percentage": 72.49, "elapsed_time": "5:34:24", "remaining_time": "2:06:54"}
362
+ {"current_steps": 362, "total_steps": 498, "loss": 0.8474, "lr": 2.1066435191009717e-06, "epoch": 2.176, "percentage": 72.69, "elapsed_time": "5:35:22", "remaining_time": "2:05:59"}
363
+ {"current_steps": 363, "total_steps": 498, "loss": 0.7613, "lr": 2.078119357369487e-06, "epoch": 2.182, "percentage": 72.89, "elapsed_time": "5:36:23", "remaining_time": "2:05:06"}
364
+ {"current_steps": 364, "total_steps": 498, "loss": 0.7985, "lr": 2.04973887831436e-06, "epoch": 2.188, "percentage": 73.09, "elapsed_time": "5:37:21", "remaining_time": "2:04:11"}
365
+ {"current_steps": 365, "total_steps": 498, "loss": 0.7873, "lr": 2.0215034775378336e-06, "epoch": 2.194, "percentage": 73.29, "elapsed_time": "5:38:14", "remaining_time": "2:03:14"}
366
+ {"current_steps": 366, "total_steps": 498, "loss": 0.8465, "lr": 1.9934145435079705e-06, "epoch": 2.2, "percentage": 73.49, "elapsed_time": "5:39:16", "remaining_time": "2:02:21"}
367
+ {"current_steps": 367, "total_steps": 498, "loss": 0.7078, "lr": 1.965473457490372e-06, "epoch": 2.206, "percentage": 73.69, "elapsed_time": "5:40:03", "remaining_time": "2:01:23"}
368
+ {"current_steps": 368, "total_steps": 498, "loss": 0.7788, "lr": 1.9376815934802496e-06, "epoch": 2.212, "percentage": 73.9, "elapsed_time": "5:40:55", "remaining_time": "2:00:26"}
369
+ {"current_steps": 369, "total_steps": 498, "loss": 0.8697, "lr": 1.9100403181348687e-06, "epoch": 2.218, "percentage": 74.1, "elapsed_time": "5:41:54", "remaining_time": "1:59:31"}
370
+ {"current_steps": 370, "total_steps": 498, "loss": 0.7119, "lr": 1.8825509907063328e-06, "epoch": 2.224, "percentage": 74.3, "elapsed_time": "5:42:38", "remaining_time": "1:58:32"}
371
+ {"current_steps": 371, "total_steps": 498, "loss": 0.7846, "lr": 1.8552149629747557e-06, "epoch": 2.23, "percentage": 74.5, "elapsed_time": "5:43:37", "remaining_time": "1:57:37"}
372
+ {"current_steps": 372, "total_steps": 498, "loss": 0.8005, "lr": 1.8280335791817733e-06, "epoch": 2.2359999999999998, "percentage": 74.7, "elapsed_time": "5:44:34", "remaining_time": "1:56:42"}
373
+ {"current_steps": 373, "total_steps": 498, "loss": 0.8352, "lr": 1.8010081759644538e-06, "epoch": 2.242, "percentage": 74.9, "elapsed_time": "5:45:36", "remaining_time": "1:55:49"}
374
+ {"current_steps": 374, "total_steps": 498, "loss": 0.8064, "lr": 1.7741400822895633e-06, "epoch": 2.248, "percentage": 75.1, "elapsed_time": "5:46:29", "remaining_time": "1:54:52"}
375
+ {"current_steps": 375, "total_steps": 498, "loss": 0.8362, "lr": 1.747430619388209e-06, "epoch": 2.254, "percentage": 75.3, "elapsed_time": "5:47:22", "remaining_time": "1:53:56"}
376
+ {"current_steps": 376, "total_steps": 498, "loss": 0.8408, "lr": 1.7208811006908798e-06, "epoch": 2.26, "percentage": 75.5, "elapsed_time": "5:48:20", "remaining_time": "1:53:01"}
377
+ {"current_steps": 377, "total_steps": 498, "loss": 0.7427, "lr": 1.6944928317628512e-06, "epoch": 2.266, "percentage": 75.7, "elapsed_time": "5:49:15", "remaining_time": "1:52:05"}
378
+ {"current_steps": 378, "total_steps": 498, "loss": 0.8121, "lr": 1.6682671102399806e-06, "epoch": 2.2720000000000002, "percentage": 75.9, "elapsed_time": "5:50:09", "remaining_time": "1:51:09"}
379
+ {"current_steps": 379, "total_steps": 498, "loss": 0.7566, "lr": 1.642205225764908e-06, "epoch": 2.278, "percentage": 76.1, "elapsed_time": "5:50:59", "remaining_time": "1:50:12"}
380
+ {"current_steps": 380, "total_steps": 498, "loss": 0.8505, "lr": 1.6163084599236278e-06, "epoch": 2.284, "percentage": 76.31, "elapsed_time": "5:51:53", "remaining_time": "1:49:16"}
381
+ {"current_steps": 381, "total_steps": 498, "loss": 0.7285, "lr": 1.5905780861824748e-06, "epoch": 2.29, "percentage": 76.51, "elapsed_time": "5:52:45", "remaining_time": "1:48:19"}
382
+ {"current_steps": 382, "total_steps": 498, "loss": 0.779, "lr": 1.5650153698254916e-06, "epoch": 2.296, "percentage": 76.71, "elapsed_time": "5:53:37", "remaining_time": "1:47:23"}
383
+ {"current_steps": 383, "total_steps": 498, "loss": 0.8963, "lr": 1.5396215678922222e-06, "epoch": 2.302, "percentage": 76.91, "elapsed_time": "5:54:37", "remaining_time": "1:46:28"}
384
+ {"current_steps": 384, "total_steps": 498, "loss": 0.6954, "lr": 1.514397929115884e-06, "epoch": 2.308, "percentage": 77.11, "elapsed_time": "5:55:28", "remaining_time": "1:45:31"}
385
+ {"current_steps": 385, "total_steps": 498, "loss": 0.8091, "lr": 1.4893456938619743e-06, "epoch": 2.314, "percentage": 77.31, "elapsed_time": "5:56:20", "remaining_time": "1:44:35"}
386
+ {"current_steps": 386, "total_steps": 498, "loss": 0.7894, "lr": 1.4644660940672628e-06, "epoch": 2.32, "percentage": 77.51, "elapsed_time": "5:57:11", "remaining_time": "1:43:38"}
387
+ {"current_steps": 387, "total_steps": 498, "loss": 0.7593, "lr": 1.439760353179223e-06, "epoch": 2.326, "percentage": 77.71, "elapsed_time": "5:58:17", "remaining_time": "1:42:46"}
388
+ {"current_steps": 388, "total_steps": 498, "loss": 0.8326, "lr": 1.4152296860958641e-06, "epoch": 2.332, "percentage": 77.91, "elapsed_time": "5:59:27", "remaining_time": "1:41:54"}
389
+ {"current_steps": 389, "total_steps": 498, "loss": 0.8052, "lr": 1.3908752991059854e-06, "epoch": 2.338, "percentage": 78.11, "elapsed_time": "6:00:23", "remaining_time": "1:40:59"}
390
+ {"current_steps": 390, "total_steps": 498, "loss": 0.8043, "lr": 1.3666983898298659e-06, "epoch": 2.344, "percentage": 78.31, "elapsed_time": "6:01:20", "remaining_time": "1:40:03"}
391
+ {"current_steps": 391, "total_steps": 498, "loss": 0.7374, "lr": 1.3427001471603623e-06, "epoch": 2.35, "percentage": 78.51, "elapsed_time": "6:02:12", "remaining_time": "1:39:07"}
392
+ {"current_steps": 392, "total_steps": 498, "loss": 0.871, "lr": 1.3188817512044544e-06, "epoch": 2.356, "percentage": 78.71, "elapsed_time": "6:03:09", "remaining_time": "1:38:12"}
393
+ {"current_steps": 393, "total_steps": 498, "loss": 0.7358, "lr": 1.2952443732252058e-06, "epoch": 2.362, "percentage": 78.92, "elapsed_time": "6:04:06", "remaining_time": "1:37:16"}
394
+ {"current_steps": 394, "total_steps": 498, "loss": 0.7017, "lr": 1.2717891755841722e-06, "epoch": 2.368, "percentage": 79.12, "elapsed_time": "6:04:51", "remaining_time": "1:36:18"}
395
+ {"current_steps": 395, "total_steps": 498, "loss": 0.8144, "lr": 1.2485173116842432e-06, "epoch": 2.374, "percentage": 79.32, "elapsed_time": "6:05:41", "remaining_time": "1:35:21"}
396
+ {"current_steps": 396, "total_steps": 498, "loss": 0.7471, "lr": 1.225429925912921e-06, "epoch": 2.38, "percentage": 79.52, "elapsed_time": "6:06:36", "remaining_time": "1:34:25"}
397
+ {"current_steps": 397, "total_steps": 498, "loss": 0.8123, "lr": 1.2025281535860433e-06, "epoch": 2.386, "percentage": 79.72, "elapsed_time": "6:07:33", "remaining_time": "1:33:30"}
398
+ {"current_steps": 398, "total_steps": 498, "loss": 0.7882, "lr": 1.1798131208919628e-06, "epoch": 2.392, "percentage": 79.92, "elapsed_time": "6:08:22", "remaining_time": "1:32:33"}
399
+ {"current_steps": 399, "total_steps": 498, "loss": 0.8712, "lr": 1.1572859448361602e-06, "epoch": 2.398, "percentage": 80.12, "elapsed_time": "6:09:20", "remaining_time": "1:31:38"}
400
+ {"current_steps": 400, "total_steps": 498, "loss": 0.7635, "lr": 1.134947733186315e-06, "epoch": 2.404, "percentage": 80.32, "elapsed_time": "6:10:19", "remaining_time": "1:30:43"}
401
+ {"current_steps": 401, "total_steps": 498, "loss": 0.7843, "lr": 1.1127995844178385e-06, "epoch": 2.41, "percentage": 80.52, "elapsed_time": "6:11:13", "remaining_time": "1:29:47"}
402
+ {"current_steps": 402, "total_steps": 498, "loss": 0.8381, "lr": 1.0908425876598512e-06, "epoch": 2.416, "percentage": 80.72, "elapsed_time": "6:12:17", "remaining_time": "1:28:54"}
403
+ {"current_steps": 403, "total_steps": 498, "loss": 0.7518, "lr": 1.069077822641622e-06, "epoch": 2.422, "percentage": 80.92, "elapsed_time": "6:13:14", "remaining_time": "1:27:59"}
404
+ {"current_steps": 404, "total_steps": 498, "loss": 0.7886, "lr": 1.047506359639483e-06, "epoch": 2.428, "percentage": 81.12, "elapsed_time": "6:14:07", "remaining_time": "1:27:02"}
405
+ {"current_steps": 405, "total_steps": 498, "loss": 0.7454, "lr": 1.0261292594241873e-06, "epoch": 2.434, "percentage": 81.33, "elapsed_time": "6:15:02", "remaining_time": "1:26:07"}
406
+ {"current_steps": 406, "total_steps": 498, "loss": 0.7773, "lr": 1.004947573208756e-06, "epoch": 2.44, "percentage": 81.53, "elapsed_time": "6:15:56", "remaining_time": "1:25:11"}
407
+ {"current_steps": 407, "total_steps": 498, "loss": 0.7395, "lr": 9.83962342596776e-07, "epoch": 2.446, "percentage": 81.73, "elapsed_time": "6:16:42", "remaining_time": "1:24:13"}
408
+ {"current_steps": 408, "total_steps": 498, "loss": 0.7972, "lr": 9.631745995311881e-07, "epoch": 2.452, "percentage": 81.93, "elapsed_time": "6:17:31", "remaining_time": "1:23:16"}
409
+ {"current_steps": 409, "total_steps": 498, "loss": 0.7628, "lr": 9.42585366243537e-07, "epoch": 2.458, "percentage": 82.13, "elapsed_time": "6:18:25", "remaining_time": "1:22:20"}
410
+ {"current_steps": 410, "total_steps": 498, "loss": 0.8116, "lr": 9.221956552036992e-07, "epoch": 2.464, "percentage": 82.33, "elapsed_time": "6:19:27", "remaining_time": "1:21:26"}
411
+ {"current_steps": 411, "total_steps": 498, "loss": 0.8279, "lr": 9.020064690701069e-07, "epoch": 2.4699999999999998, "percentage": 82.53, "elapsed_time": "6:20:30", "remaining_time": "1:20:32"}
412
+ {"current_steps": 412, "total_steps": 498, "loss": 0.8178, "lr": 8.820188006404268e-07, "epoch": 2.476, "percentage": 82.73, "elapsed_time": "6:21:22", "remaining_time": "1:19:36"}
413
+ {"current_steps": 413, "total_steps": 498, "loss": 0.8169, "lr": 8.622336328027553e-07, "epoch": 2.482, "percentage": 82.93, "elapsed_time": "6:22:18", "remaining_time": "1:18:40"}
414
+ {"current_steps": 414, "total_steps": 498, "loss": 0.8104, "lr": 8.426519384872733e-07, "epoch": 2.488, "percentage": 83.13, "elapsed_time": "6:23:22", "remaining_time": "1:17:47"}
415
+ {"current_steps": 415, "total_steps": 498, "loss": 0.7281, "lr": 8.232746806184116e-07, "epoch": 2.4939999999999998, "percentage": 83.33, "elapsed_time": "6:24:16", "remaining_time": "1:16:51"}
416
+ {"current_steps": 416, "total_steps": 498, "loss": 0.7757, "lr": 8.041028120674894e-07, "epoch": 2.5, "percentage": 83.53, "elapsed_time": "6:25:07", "remaining_time": "1:15:54"}
417
+ {"current_steps": 417, "total_steps": 498, "loss": 0.8185, "lr": 7.851372756058662e-07, "epoch": 2.5060000000000002, "percentage": 83.73, "elapsed_time": "6:26:05", "remaining_time": "1:14:59"}
418
+ {"current_steps": 418, "total_steps": 498, "loss": 0.8264, "lr": 7.663790038585794e-07, "epoch": 2.512, "percentage": 83.94, "elapsed_time": "6:27:06", "remaining_time": "1:14:05"}
419
+ {"current_steps": 419, "total_steps": 498, "loss": 0.6955, "lr": 7.478289192584765e-07, "epoch": 2.518, "percentage": 84.14, "elapsed_time": "6:28:00", "remaining_time": "1:13:09"}
420
+ {"current_steps": 420, "total_steps": 498, "loss": 0.8344, "lr": 7.294879340008632e-07, "epoch": 2.524, "percentage": 84.34, "elapsed_time": "6:28:54", "remaining_time": "1:12:13"}
421
+ {"current_steps": 421, "total_steps": 498, "loss": 0.7613, "lr": 7.113569499986401e-07, "epoch": 2.5300000000000002, "percentage": 84.54, "elapsed_time": "6:29:45", "remaining_time": "1:11:17"}
422
+ {"current_steps": 422, "total_steps": 498, "loss": 0.6928, "lr": 6.934368588379553e-07, "epoch": 2.536, "percentage": 84.74, "elapsed_time": "6:30:33", "remaining_time": "1:10:20"}
423
+ {"current_steps": 423, "total_steps": 498, "loss": 0.7997, "lr": 6.757285417343601e-07, "epoch": 2.542, "percentage": 84.94, "elapsed_time": "6:31:27", "remaining_time": "1:09:24"}
424
+ {"current_steps": 424, "total_steps": 498, "loss": 0.7461, "lr": 6.582328694894729e-07, "epoch": 2.548, "percentage": 85.14, "elapsed_time": "6:32:29", "remaining_time": "1:08:30"}
425
+ {"current_steps": 425, "total_steps": 498, "loss": 0.8448, "lr": 6.409507024481615e-07, "epoch": 2.5540000000000003, "percentage": 85.34, "elapsed_time": "6:33:22", "remaining_time": "1:07:33"}
426
+ {"current_steps": 426, "total_steps": 498, "loss": 0.8036, "lr": 6.238828904562316e-07, "epoch": 2.56, "percentage": 85.54, "elapsed_time": "6:34:16", "remaining_time": "1:06:38"}
427
+ {"current_steps": 427, "total_steps": 498, "loss": 0.7716, "lr": 6.070302728186428e-07, "epoch": 2.566, "percentage": 85.74, "elapsed_time": "6:35:13", "remaining_time": "1:05:42"}
428
+ {"current_steps": 428, "total_steps": 498, "loss": 0.7355, "lr": 5.903936782582253e-07, "epoch": 2.572, "percentage": 85.94, "elapsed_time": "6:36:09", "remaining_time": "1:04:47"}
429
+ {"current_steps": 429, "total_steps": 498, "loss": 0.818, "lr": 5.739739248749398e-07, "epoch": 2.578, "percentage": 86.14, "elapsed_time": "6:37:05", "remaining_time": "1:03:52"}
430
+ {"current_steps": 430, "total_steps": 498, "loss": 0.7708, "lr": 5.577718201056392e-07, "epoch": 2.584, "percentage": 86.35, "elapsed_time": "6:37:58", "remaining_time": "1:02:56"}
431
+ {"current_steps": 431, "total_steps": 498, "loss": 0.7872, "lr": 5.41788160684365e-07, "epoch": 2.59, "percentage": 86.55, "elapsed_time": "6:38:57", "remaining_time": "1:02:01"}
432
+ {"current_steps": 432, "total_steps": 498, "loss": 0.8138, "lr": 5.260237326031698e-07, "epoch": 2.596, "percentage": 86.75, "elapsed_time": "6:39:52", "remaining_time": "1:01:05"}
433
+ {"current_steps": 433, "total_steps": 498, "loss": 0.7579, "lr": 5.104793110734668e-07, "epoch": 2.602, "percentage": 86.95, "elapsed_time": "6:40:44", "remaining_time": "1:00:09"}
434
+ {"current_steps": 434, "total_steps": 498, "loss": 0.7697, "lr": 4.951556604879049e-07, "epoch": 2.608, "percentage": 87.15, "elapsed_time": "6:41:29", "remaining_time": "0:59:12"}
435
+ {"current_steps": 435, "total_steps": 498, "loss": 0.8134, "lr": 4.800535343827834e-07, "epoch": 2.614, "percentage": 87.35, "elapsed_time": "6:42:19", "remaining_time": "0:58:16"}
436
+ {"current_steps": 436, "total_steps": 498, "loss": 0.8371, "lr": 4.651736754009972e-07, "epoch": 2.62, "percentage": 87.55, "elapsed_time": "6:43:21", "remaining_time": "0:57:21"}
437
+ {"current_steps": 437, "total_steps": 498, "loss": 0.6842, "lr": 4.5051681525551726e-07, "epoch": 2.626, "percentage": 87.75, "elapsed_time": "6:44:14", "remaining_time": "0:56:25"}
438
+ {"current_steps": 438, "total_steps": 498, "loss": 0.8512, "lr": 4.3608367469340553e-07, "epoch": 2.632, "percentage": 87.95, "elapsed_time": "6:45:09", "remaining_time": "0:55:30"}
439
+ {"current_steps": 439, "total_steps": 498, "loss": 0.8017, "lr": 4.218749634603769e-07, "epoch": 2.638, "percentage": 88.15, "elapsed_time": "6:46:07", "remaining_time": "0:54:34"}
440
+ {"current_steps": 440, "total_steps": 498, "loss": 0.7429, "lr": 4.078913802658946e-07, "epoch": 2.644, "percentage": 88.35, "elapsed_time": "6:46:56", "remaining_time": "0:53:38"}
441
+ {"current_steps": 441, "total_steps": 498, "loss": 0.9286, "lr": 3.941336127488149e-07, "epoch": 2.65, "percentage": 88.55, "elapsed_time": "6:47:58", "remaining_time": "0:52:43"}
442
+ {"current_steps": 442, "total_steps": 498, "loss": 0.7965, "lr": 3.8060233744356634e-07, "epoch": 2.656, "percentage": 88.76, "elapsed_time": "6:48:59", "remaining_time": "0:51:49"}
443
+ {"current_steps": 443, "total_steps": 498, "loss": 0.6891, "lr": 3.672982197468894e-07, "epoch": 2.662, "percentage": 88.96, "elapsed_time": "6:50:01", "remaining_time": "0:50:54"}
444
+ {"current_steps": 444, "total_steps": 498, "loss": 0.8237, "lr": 3.542219138851094e-07, "epoch": 2.668, "percentage": 89.16, "elapsed_time": "6:51:09", "remaining_time": "0:50:00"}
445
+ {"current_steps": 445, "total_steps": 498, "loss": 0.8458, "lr": 3.413740628819673e-07, "epoch": 2.674, "percentage": 89.36, "elapsed_time": "6:52:06", "remaining_time": "0:49:04"}
446
+ {"current_steps": 446, "total_steps": 498, "loss": 0.6672, "lr": 3.287552985270015e-07, "epoch": 2.68, "percentage": 89.56, "elapsed_time": "6:53:00", "remaining_time": "0:48:09"}
447
+ {"current_steps": 447, "total_steps": 498, "loss": 0.9044, "lr": 3.1636624134447347e-07, "epoch": 2.686, "percentage": 89.76, "elapsed_time": "6:54:01", "remaining_time": "0:47:14"}
448
+ {"current_steps": 448, "total_steps": 498, "loss": 0.7871, "lr": 3.0420750056286195e-07, "epoch": 2.692, "percentage": 89.96, "elapsed_time": "6:54:54", "remaining_time": "0:46:18"}
449
+ {"current_steps": 449, "total_steps": 498, "loss": 0.8072, "lr": 2.9227967408489653e-07, "epoch": 2.698, "percentage": 90.16, "elapsed_time": "6:55:51", "remaining_time": "0:45:23"}
450
+ {"current_steps": 450, "total_steps": 498, "loss": 0.8227, "lr": 2.8058334845816214e-07, "epoch": 2.7039999999999997, "percentage": 90.36, "elapsed_time": "6:56:54", "remaining_time": "0:44:28"}
451
+ {"current_steps": 451, "total_steps": 498, "loss": 0.7586, "lr": 2.691190988462522e-07, "epoch": 2.71, "percentage": 90.56, "elapsed_time": "6:57:44", "remaining_time": "0:43:31"}
452
+ {"current_steps": 452, "total_steps": 498, "loss": 0.8312, "lr": 2.5788748900048676e-07, "epoch": 2.716, "percentage": 90.76, "elapsed_time": "6:58:43", "remaining_time": "0:42:36"}
453
+ {"current_steps": 453, "total_steps": 498, "loss": 0.8476, "lr": 2.468890712321864e-07, "epoch": 2.722, "percentage": 90.96, "elapsed_time": "6:59:42", "remaining_time": "0:41:41"}
454
+ {"current_steps": 454, "total_steps": 498, "loss": 0.7627, "lr": 2.3612438638551837e-07, "epoch": 2.7279999999999998, "percentage": 91.16, "elapsed_time": "7:00:46", "remaining_time": "0:40:46"}
455
+ {"current_steps": 455, "total_steps": 498, "loss": 0.7599, "lr": 2.2559396381089836e-07, "epoch": 2.734, "percentage": 91.37, "elapsed_time": "7:01:45", "remaining_time": "0:39:51"}
456
+ {"current_steps": 456, "total_steps": 498, "loss": 0.7736, "lr": 2.152983213389559e-07, "epoch": 2.74, "percentage": 91.57, "elapsed_time": "7:02:41", "remaining_time": "0:38:55"}
457
+ {"current_steps": 457, "total_steps": 498, "loss": 0.8125, "lr": 2.0523796525507622e-07, "epoch": 2.746, "percentage": 91.77, "elapsed_time": "7:03:41", "remaining_time": "0:38:00"}
458
+ {"current_steps": 458, "total_steps": 498, "loss": 0.7794, "lr": 1.9541339027450256e-07, "epoch": 2.752, "percentage": 91.97, "elapsed_time": "7:04:30", "remaining_time": "0:37:04"}
459
+ {"current_steps": 459, "total_steps": 498, "loss": 0.793, "lr": 1.8582507951800277e-07, "epoch": 2.758, "percentage": 92.17, "elapsed_time": "7:05:28", "remaining_time": "0:36:09"}
460
+ {"current_steps": 460, "total_steps": 498, "loss": 0.7349, "lr": 1.7647350448812105e-07, "epoch": 2.7640000000000002, "percentage": 92.37, "elapsed_time": "7:06:17", "remaining_time": "0:35:12"}
461
+ {"current_steps": 461, "total_steps": 498, "loss": 0.8252, "lr": 1.6735912504598384e-07, "epoch": 2.77, "percentage": 92.57, "elapsed_time": "7:07:14", "remaining_time": "0:34:17"}
462
+ {"current_steps": 462, "total_steps": 498, "loss": 0.8621, "lr": 1.5848238938869332e-07, "epoch": 2.776, "percentage": 92.77, "elapsed_time": "7:08:12", "remaining_time": "0:33:21"}
463
+ {"current_steps": 463, "total_steps": 498, "loss": 0.7701, "lr": 1.4984373402728014e-07, "epoch": 2.782, "percentage": 92.97, "elapsed_time": "7:09:09", "remaining_time": "0:32:26"}
464
+ {"current_steps": 464, "total_steps": 498, "loss": 0.7945, "lr": 1.4144358376524504e-07, "epoch": 2.7880000000000003, "percentage": 93.17, "elapsed_time": "7:10:01", "remaining_time": "0:31:30"}
465
+ {"current_steps": 465, "total_steps": 498, "loss": 0.7498, "lr": 1.3328235167766545e-07, "epoch": 2.794, "percentage": 93.37, "elapsed_time": "7:10:55", "remaining_time": "0:30:34"}
466
+ {"current_steps": 466, "total_steps": 498, "loss": 0.8173, "lr": 1.253604390908819e-07, "epoch": 2.8, "percentage": 93.57, "elapsed_time": "7:11:54", "remaining_time": "0:29:39"}
467
+ {"current_steps": 467, "total_steps": 498, "loss": 0.7292, "lr": 1.1767823556276648e-07, "epoch": 2.806, "percentage": 93.78, "elapsed_time": "7:12:40", "remaining_time": "0:28:43"}
468
+ {"current_steps": 468, "total_steps": 498, "loss": 0.8378, "lr": 1.10236118863562e-07, "epoch": 2.8120000000000003, "percentage": 93.98, "elapsed_time": "7:13:34", "remaining_time": "0:27:47"}
469
+ {"current_steps": 469, "total_steps": 498, "loss": 0.8025, "lr": 1.0303445495730868e-07, "epoch": 2.818, "percentage": 94.18, "elapsed_time": "7:14:31", "remaining_time": "0:26:52"}
470
+ {"current_steps": 470, "total_steps": 498, "loss": 0.8015, "lr": 9.607359798384785e-08, "epoch": 2.824, "percentage": 94.38, "elapsed_time": "7:15:23", "remaining_time": "0:25:56"}
471
+ {"current_steps": 471, "total_steps": 498, "loss": 0.6498, "lr": 8.935389024140485e-08, "epoch": 2.83, "percentage": 94.58, "elapsed_time": "7:16:12", "remaining_time": "0:25:00"}
472
+ {"current_steps": 472, "total_steps": 498, "loss": 0.8355, "lr": 8.287566216975795e-08, "epoch": 2.836, "percentage": 94.78, "elapsed_time": "7:17:11", "remaining_time": "0:24:04"}
473
+ {"current_steps": 473, "total_steps": 498, "loss": 0.8568, "lr": 7.663923233398928e-08, "epoch": 2.842, "percentage": 94.98, "elapsed_time": "7:18:10", "remaining_time": "0:23:09"}
474
+ {"current_steps": 474, "total_steps": 498, "loss": 0.7667, "lr": 7.064490740882057e-08, "epoch": 2.848, "percentage": 95.18, "elapsed_time": "7:18:59", "remaining_time": "0:22:13"}
475
+ {"current_steps": 475, "total_steps": 498, "loss": 0.7791, "lr": 6.489298216352913e-08, "epoch": 2.854, "percentage": 95.38, "elapsed_time": "7:19:52", "remaining_time": "0:21:17"}
476
+ {"current_steps": 476, "total_steps": 498, "loss": 0.8003, "lr": 5.938373944745612e-08, "epoch": 2.86, "percentage": 95.58, "elapsed_time": "7:20:38", "remaining_time": "0:20:21"}
477
+ {"current_steps": 477, "total_steps": 498, "loss": 0.8502, "lr": 5.411745017609493e-08, "epoch": 2.866, "percentage": 95.78, "elapsed_time": "7:21:34", "remaining_time": "0:19:26"}
478
+ {"current_steps": 478, "total_steps": 498, "loss": 0.667, "lr": 4.909437331777178e-08, "epoch": 2.872, "percentage": 95.98, "elapsed_time": "7:22:28", "remaining_time": "0:18:30"}
479
+ {"current_steps": 479, "total_steps": 498, "loss": 0.8964, "lr": 4.431475588090872e-08, "epoch": 2.878, "percentage": 96.18, "elapsed_time": "7:23:28", "remaining_time": "0:17:35"}
480
+ {"current_steps": 480, "total_steps": 498, "loss": 0.7143, "lr": 3.977883290187667e-08, "epoch": 2.884, "percentage": 96.39, "elapsed_time": "7:24:22", "remaining_time": "0:16:39"}
481
+ {"current_steps": 481, "total_steps": 498, "loss": 0.8222, "lr": 3.548682743344079e-08, "epoch": 2.89, "percentage": 96.59, "elapsed_time": "7:25:14", "remaining_time": "0:15:44"}
482
+ {"current_steps": 482, "total_steps": 498, "loss": 0.7455, "lr": 3.143895053378698e-08, "epoch": 2.896, "percentage": 96.79, "elapsed_time": "7:26:15", "remaining_time": "0:14:48"}
483
+ {"current_steps": 483, "total_steps": 498, "loss": 0.8795, "lr": 2.7635401256149163e-08, "epoch": 2.902, "percentage": 96.99, "elapsed_time": "7:27:08", "remaining_time": "0:13:53"}
484
+ {"current_steps": 484, "total_steps": 498, "loss": 0.6865, "lr": 2.4076366639015914e-08, "epoch": 2.908, "percentage": 97.19, "elapsed_time": "7:27:57", "remaining_time": "0:12:57"}
485
+ {"current_steps": 485, "total_steps": 498, "loss": 0.7257, "lr": 2.0762021696933975e-08, "epoch": 2.914, "percentage": 97.39, "elapsed_time": "7:28:44", "remaining_time": "0:12:01"}
486
+ {"current_steps": 486, "total_steps": 498, "loss": 0.8059, "lr": 1.769252941190458e-08, "epoch": 2.92, "percentage": 97.59, "elapsed_time": "7:29:38", "remaining_time": "0:11:06"}
487
+ {"current_steps": 487, "total_steps": 498, "loss": 0.8935, "lr": 1.4868040725365407e-08, "epoch": 2.926, "percentage": 97.79, "elapsed_time": "7:30:46", "remaining_time": "0:10:10"}
488
+ {"current_steps": 488, "total_steps": 498, "loss": 0.7953, "lr": 1.2288694530769862e-08, "epoch": 2.932, "percentage": 97.99, "elapsed_time": "7:31:40", "remaining_time": "0:09:15"}
489
+ {"current_steps": 489, "total_steps": 498, "loss": 0.7744, "lr": 9.954617666758648e-09, "epoch": 2.9379999999999997, "percentage": 98.19, "elapsed_time": "7:32:34", "remaining_time": "0:08:19"}
490
+ {"current_steps": 490, "total_steps": 498, "loss": 0.7164, "lr": 7.865924910916977e-09, "epoch": 2.944, "percentage": 98.39, "elapsed_time": "7:33:26", "remaining_time": "0:07:24"}
491
+ {"current_steps": 491, "total_steps": 498, "loss": 0.8194, "lr": 6.022718974137976e-09, "epoch": 2.95, "percentage": 98.59, "elapsed_time": "7:34:16", "remaining_time": "0:06:28"}
492
+ {"current_steps": 492, "total_steps": 498, "loss": 0.8323, "lr": 4.4250904955656095e-09, "epoch": 2.956, "percentage": 98.8, "elapsed_time": "7:35:12", "remaining_time": "0:05:33"}
493
+ {"current_steps": 493, "total_steps": 498, "loss": 0.7787, "lr": 3.0731180381399216e-09, "epoch": 2.9619999999999997, "percentage": 99.0, "elapsed_time": "7:36:14", "remaining_time": "0:04:37"}
494
+ {"current_steps": 494, "total_steps": 498, "loss": 0.8071, "lr": 1.9668680847356735e-09, "epoch": 2.968, "percentage": 99.2, "elapsed_time": "7:37:05", "remaining_time": "0:03:42"}
495
+ {"current_steps": 495, "total_steps": 498, "loss": 0.7125, "lr": 1.1063950348888519e-09, "epoch": 2.974, "percentage": 99.4, "elapsed_time": "7:37:56", "remaining_time": "0:02:46"}
496
+ {"current_steps": 496, "total_steps": 498, "loss": 0.7699, "lr": 4.91741202124918e-10, "epoch": 2.98, "percentage": 99.6, "elapsed_time": "7:38:45", "remaining_time": "0:01:50"}
497
+ {"current_steps": 497, "total_steps": 498, "loss": 0.8057, "lr": 1.22936811877139e-10, "epoch": 2.9859999999999998, "percentage": 99.8, "elapsed_time": "7:39:36", "remaining_time": "0:00:55"}
498
+ {"current_steps": 498, "total_steps": 498, "loss": 0.7188, "lr": 0.0, "epoch": 2.992, "percentage": 100.0, "elapsed_time": "7:40:27", "remaining_time": "0:00:00"}
499
+ {"current_steps": 498, "total_steps": 498, "epoch": 2.992, "percentage": 100.0, "elapsed_time": "7:42:37", "remaining_time": "0:00:00"}