sedrickkeh commited on
Commit
a0112b9
·
verified ·
1 Parent(s): cfaad29

Training in progress, epoch 3

Browse files
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b6163a7aaa3d2f6d276305db90b18d820129c62ee122da08b20afdd033c46210
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54254d4fe3f8ec04dc852889c84487ddb116e854b3db3f9a64b58cc804925214
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:15f0d14f52310afbe4f6032dab226bac2da93dc4324bc3bc3b7f58d2ceaa2031
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d650622c04e386604f10d8fe8729b1110f3ecb33949a009df974b912a6d672f5
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:95b5cd4c969a1691d6303e25ad547f860944230180943af68fefd68d9359a949
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:544bcc139381a687fcc5c904af510968da1ec362069cebf6ae1973be77a40fab
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:c89da067a82fb5ea5adefeb89fbb82e6ba2e38880ea91d36c1a0ca55f5513c01
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29efb5b60fe500e2df41a87fc25a63c0dbdb431d0088d1fd641fd0b7d47d04ba
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -250,3 +250,127 @@
250
  {"current_steps": 250, "total_steps": 375, "loss": 0.8254, "lr": 3.0275298806603102e-06, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "3:50:41", "remaining_time": "1:55:20"}
251
  {"current_steps": 251, "total_steps": 375, "loss": 0.7948, "lr": 2.984785276497507e-06, "epoch": 2.008, "percentage": 66.93, "elapsed_time": "3:52:43", "remaining_time": "1:54:58"}
252
  {"current_steps": 252, "total_steps": 375, "loss": 0.7709, "lr": 2.9422158013581658e-06, "epoch": 2.016, "percentage": 67.2, "elapsed_time": "3:53:34", "remaining_time": "1:54:00"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
250
  {"current_steps": 250, "total_steps": 375, "loss": 0.8254, "lr": 3.0275298806603102e-06, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "3:50:41", "remaining_time": "1:55:20"}
251
  {"current_steps": 251, "total_steps": 375, "loss": 0.7948, "lr": 2.984785276497507e-06, "epoch": 2.008, "percentage": 66.93, "elapsed_time": "3:52:43", "remaining_time": "1:54:58"}
252
  {"current_steps": 252, "total_steps": 375, "loss": 0.7709, "lr": 2.9422158013581658e-06, "epoch": 2.016, "percentage": 67.2, "elapsed_time": "3:53:34", "remaining_time": "1:54:00"}
253
+ {"current_steps": 253, "total_steps": 375, "loss": 0.7659, "lr": 2.899825154674674e-06, "epoch": 2.024, "percentage": 67.47, "elapsed_time": "3:54:36", "remaining_time": "1:53:07"}
254
+ {"current_steps": 254, "total_steps": 375, "loss": 0.7978, "lr": 2.8576170203386144e-06, "epoch": 2.032, "percentage": 67.73, "elapsed_time": "3:55:28", "remaining_time": "1:52:10"}
255
+ {"current_steps": 255, "total_steps": 375, "loss": 0.8075, "lr": 2.8155950663806234e-06, "epoch": 2.04, "percentage": 68.0, "elapsed_time": "3:56:31", "remaining_time": "1:51:18"}
256
+ {"current_steps": 256, "total_steps": 375, "loss": 0.7967, "lr": 2.7737629446516325e-06, "epoch": 2.048, "percentage": 68.27, "elapsed_time": "3:57:19", "remaining_time": "1:50:18"}
257
+ {"current_steps": 257, "total_steps": 375, "loss": 0.7637, "lr": 2.732124290505501e-06, "epoch": 2.056, "percentage": 68.53, "elapsed_time": "3:58:09", "remaining_time": "1:49:20"}
258
+ {"current_steps": 258, "total_steps": 375, "loss": 0.7999, "lr": 2.6906827224831024e-06, "epoch": 2.064, "percentage": 68.8, "elapsed_time": "3:59:11", "remaining_time": "1:48:28"}
259
+ {"current_steps": 259, "total_steps": 375, "loss": 0.8002, "lr": 2.6494418419978485e-06, "epoch": 2.072, "percentage": 69.07, "elapsed_time": "4:00:08", "remaining_time": "1:47:33"}
260
+ {"current_steps": 260, "total_steps": 375, "loss": 0.7841, "lr": 2.608405233022724e-06, "epoch": 2.08, "percentage": 69.33, "elapsed_time": "4:01:05", "remaining_time": "1:46:38"}
261
+ {"current_steps": 261, "total_steps": 375, "loss": 0.7808, "lr": 2.5675764617788233e-06, "epoch": 2.088, "percentage": 69.6, "elapsed_time": "4:02:00", "remaining_time": "1:45:42"}
262
+ {"current_steps": 262, "total_steps": 375, "loss": 0.7758, "lr": 2.526959076425434e-06, "epoch": 2.096, "percentage": 69.87, "elapsed_time": "4:02:53", "remaining_time": "1:44:45"}
263
+ {"current_steps": 263, "total_steps": 375, "loss": 0.8111, "lr": 2.4865566067516896e-06, "epoch": 2.104, "percentage": 70.13, "elapsed_time": "4:03:49", "remaining_time": "1:43:49"}
264
+ {"current_steps": 264, "total_steps": 375, "loss": 0.7976, "lr": 2.4463725638698182e-06, "epoch": 2.112, "percentage": 70.4, "elapsed_time": "4:04:50", "remaining_time": "1:42:56"}
265
+ {"current_steps": 265, "total_steps": 375, "loss": 0.7903, "lr": 2.406410439910017e-06, "epoch": 2.12, "percentage": 70.67, "elapsed_time": "4:05:53", "remaining_time": "1:42:03"}
266
+ {"current_steps": 266, "total_steps": 375, "loss": 0.8107, "lr": 2.366673707716973e-06, "epoch": 2.128, "percentage": 70.93, "elapsed_time": "4:06:48", "remaining_time": "1:41:08"}
267
+ {"current_steps": 267, "total_steps": 375, "loss": 0.7231, "lr": 2.327165820548059e-06, "epoch": 2.136, "percentage": 71.2, "elapsed_time": "4:07:37", "remaining_time": "1:40:09"}
268
+ {"current_steps": 268, "total_steps": 375, "loss": 0.7503, "lr": 2.287890211773238e-06, "epoch": 2.144, "percentage": 71.47, "elapsed_time": "4:08:38", "remaining_time": "1:39:16"}
269
+ {"current_steps": 269, "total_steps": 375, "loss": 0.8206, "lr": 2.2488502945766893e-06, "epoch": 2.152, "percentage": 71.73, "elapsed_time": "4:09:33", "remaining_time": "1:38:20"}
270
+ {"current_steps": 270, "total_steps": 375, "loss": 0.7817, "lr": 2.210049461660189e-06, "epoch": 2.16, "percentage": 72.0, "elapsed_time": "4:10:38", "remaining_time": "1:37:28"}
271
+ {"current_steps": 271, "total_steps": 375, "loss": 0.7855, "lr": 2.1714910849482777e-06, "epoch": 2.168, "percentage": 72.27, "elapsed_time": "4:11:36", "remaining_time": "1:36:33"}
272
+ {"current_steps": 272, "total_steps": 375, "loss": 0.8024, "lr": 2.1331785152952243e-06, "epoch": 2.176, "percentage": 72.53, "elapsed_time": "4:12:35", "remaining_time": "1:35:38"}
273
+ {"current_steps": 273, "total_steps": 375, "loss": 0.7472, "lr": 2.0951150821938278e-06, "epoch": 2.184, "percentage": 72.8, "elapsed_time": "4:13:16", "remaining_time": "1:34:37"}
274
+ {"current_steps": 274, "total_steps": 375, "loss": 0.7666, "lr": 2.0573040934860717e-06, "epoch": 2.192, "percentage": 73.07, "elapsed_time": "4:14:05", "remaining_time": "1:33:39"}
275
+ {"current_steps": 275, "total_steps": 375, "loss": 0.7913, "lr": 2.0197488350756618e-06, "epoch": 2.2, "percentage": 73.33, "elapsed_time": "4:15:00", "remaining_time": "1:32:43"}
276
+ {"current_steps": 276, "total_steps": 375, "loss": 0.7855, "lr": 1.98245257064247e-06, "epoch": 2.208, "percentage": 73.6, "elapsed_time": "4:15:59", "remaining_time": "1:31:49"}
277
+ {"current_steps": 277, "total_steps": 375, "loss": 0.7948, "lr": 1.945418541358911e-06, "epoch": 2.216, "percentage": 73.87, "elapsed_time": "4:16:56", "remaining_time": "1:30:54"}
278
+ {"current_steps": 278, "total_steps": 375, "loss": 0.7953, "lr": 1.9086499656082685e-06, "epoch": 2.224, "percentage": 74.13, "elapsed_time": "4:17:53", "remaining_time": "1:29:59"}
279
+ {"current_steps": 279, "total_steps": 375, "loss": 0.7723, "lr": 1.872150038705015e-06, "epoch": 2.232, "percentage": 74.4, "elapsed_time": "4:18:41", "remaining_time": "1:29:00"}
280
+ {"current_steps": 280, "total_steps": 375, "loss": 0.7863, "lr": 1.835921932617119e-06, "epoch": 2.24, "percentage": 74.67, "elapsed_time": "4:19:42", "remaining_time": "1:28:06"}
281
+ {"current_steps": 281, "total_steps": 375, "loss": 0.7459, "lr": 1.7999687956903955e-06, "epoch": 2.248, "percentage": 74.93, "elapsed_time": "4:20:38", "remaining_time": "1:27:11"}
282
+ {"current_steps": 282, "total_steps": 375, "loss": 0.7549, "lr": 1.7642937523749038e-06, "epoch": 2.2560000000000002, "percentage": 75.2, "elapsed_time": "4:21:27", "remaining_time": "1:26:13"}
283
+ {"current_steps": 283, "total_steps": 375, "loss": 0.7945, "lr": 1.7288999029534177e-06, "epoch": 2.2640000000000002, "percentage": 75.47, "elapsed_time": "4:22:23", "remaining_time": "1:25:17"}
284
+ {"current_steps": 284, "total_steps": 375, "loss": 0.8004, "lr": 1.6937903232720076e-06, "epoch": 2.2720000000000002, "percentage": 75.73, "elapsed_time": "4:23:18", "remaining_time": "1:24:22"}
285
+ {"current_steps": 285, "total_steps": 375, "loss": 0.7723, "lr": 1.6589680644727347e-06, "epoch": 2.2800000000000002, "percentage": 76.0, "elapsed_time": "4:24:12", "remaining_time": "1:23:26"}
286
+ {"current_steps": 286, "total_steps": 375, "loss": 0.7721, "lr": 1.6244361527284953e-06, "epoch": 2.288, "percentage": 76.27, "elapsed_time": "4:24:58", "remaining_time": "1:22:27"}
287
+ {"current_steps": 287, "total_steps": 375, "loss": 0.7891, "lr": 1.5901975889800387e-06, "epoch": 2.296, "percentage": 76.53, "elapsed_time": "4:25:58", "remaining_time": "1:21:33"}
288
+ {"current_steps": 288, "total_steps": 375, "loss": 0.7585, "lr": 1.556255348675174e-06, "epoch": 2.304, "percentage": 76.8, "elapsed_time": "4:26:57", "remaining_time": "1:20:38"}
289
+ {"current_steps": 289, "total_steps": 375, "loss": 0.7672, "lr": 1.522612381510195e-06, "epoch": 2.312, "percentage": 77.07, "elapsed_time": "4:28:03", "remaining_time": "1:19:46"}
290
+ {"current_steps": 290, "total_steps": 375, "loss": 0.7861, "lr": 1.489271611173538e-06, "epoch": 2.32, "percentage": 77.33, "elapsed_time": "4:29:01", "remaining_time": "1:18:50"}
291
+ {"current_steps": 291, "total_steps": 375, "loss": 0.791, "lr": 1.4562359350917054e-06, "epoch": 2.328, "percentage": 77.6, "elapsed_time": "4:29:56", "remaining_time": "1:17:55"}
292
+ {"current_steps": 292, "total_steps": 375, "loss": 0.7861, "lr": 1.423508224177474e-06, "epoch": 2.336, "percentage": 77.87, "elapsed_time": "4:30:50", "remaining_time": "1:16:59"}
293
+ {"current_steps": 293, "total_steps": 375, "loss": 0.7965, "lr": 1.3910913225803946e-06, "epoch": 2.344, "percentage": 78.13, "elapsed_time": "4:31:47", "remaining_time": "1:16:03"}
294
+ {"current_steps": 294, "total_steps": 375, "loss": 0.7815, "lr": 1.35898804743963e-06, "epoch": 2.352, "percentage": 78.4, "elapsed_time": "4:32:44", "remaining_time": "1:15:08"}
295
+ {"current_steps": 295, "total_steps": 375, "loss": 0.8028, "lr": 1.3272011886391368e-06, "epoch": 2.36, "percentage": 78.67, "elapsed_time": "4:33:44", "remaining_time": "1:14:14"}
296
+ {"current_steps": 296, "total_steps": 375, "loss": 0.7692, "lr": 1.295733508565213e-06, "epoch": 2.368, "percentage": 78.93, "elapsed_time": "4:34:33", "remaining_time": "1:13:16"}
297
+ {"current_steps": 297, "total_steps": 375, "loss": 0.7546, "lr": 1.2645877418664394e-06, "epoch": 2.376, "percentage": 79.2, "elapsed_time": "4:35:28", "remaining_time": "1:12:20"}
298
+ {"current_steps": 298, "total_steps": 375, "loss": 0.798, "lr": 1.2337665952160266e-06, "epoch": 2.384, "percentage": 79.47, "elapsed_time": "4:36:23", "remaining_time": "1:11:25"}
299
+ {"current_steps": 299, "total_steps": 375, "loss": 0.7849, "lr": 1.2032727470765982e-06, "epoch": 2.392, "percentage": 79.73, "elapsed_time": "4:37:15", "remaining_time": "1:10:28"}
300
+ {"current_steps": 300, "total_steps": 375, "loss": 0.8045, "lr": 1.1731088474674235e-06, "epoch": 2.4, "percentage": 80.0, "elapsed_time": "4:38:21", "remaining_time": "1:09:35"}
301
+ {"current_steps": 301, "total_steps": 375, "loss": 0.7841, "lr": 1.1432775177341165e-06, "epoch": 2.408, "percentage": 80.27, "elapsed_time": "4:39:12", "remaining_time": "1:08:38"}
302
+ {"current_steps": 302, "total_steps": 375, "loss": 0.7993, "lr": 1.11378135032084e-06, "epoch": 2.416, "percentage": 80.53, "elapsed_time": "4:40:14", "remaining_time": "1:07:44"}
303
+ {"current_steps": 303, "total_steps": 375, "loss": 0.7655, "lr": 1.08462290854501e-06, "epoch": 2.424, "percentage": 80.8, "elapsed_time": "4:41:02", "remaining_time": "1:06:46"}
304
+ {"current_steps": 304, "total_steps": 375, "loss": 0.7607, "lr": 1.0558047263745297e-06, "epoch": 2.432, "percentage": 81.07, "elapsed_time": "4:41:50", "remaining_time": "1:05:49"}
305
+ {"current_steps": 305, "total_steps": 375, "loss": 0.7425, "lr": 1.0273293082075914e-06, "epoch": 2.44, "percentage": 81.33, "elapsed_time": "4:42:44", "remaining_time": "1:04:53"}
306
+ {"current_steps": 306, "total_steps": 375, "loss": 0.8086, "lr": 9.991991286550207e-07, "epoch": 2.448, "percentage": 81.6, "elapsed_time": "4:43:33", "remaining_time": "1:03:56"}
307
+ {"current_steps": 307, "total_steps": 375, "loss": 0.7751, "lr": 9.71416632325235e-07, "epoch": 2.456, "percentage": 81.87, "elapsed_time": "4:44:17", "remaining_time": "1:02:58"}
308
+ {"current_steps": 308, "total_steps": 375, "loss": 0.8141, "lr": 9.439842336117954e-07, "epoch": 2.464, "percentage": 82.13, "elapsed_time": "4:45:19", "remaining_time": "1:02:04"}
309
+ {"current_steps": 309, "total_steps": 375, "loss": 0.762, "lr": 9.169043164835867e-07, "epoch": 2.472, "percentage": 82.4, "elapsed_time": "4:46:14", "remaining_time": "1:01:08"}
310
+ {"current_steps": 310, "total_steps": 375, "loss": 0.8327, "lr": 8.901792342776439e-07, "epoch": 2.48, "percentage": 82.67, "elapsed_time": "4:47:11", "remaining_time": "1:00:13"}
311
+ {"current_steps": 311, "total_steps": 375, "loss": 0.8251, "lr": 8.638113094946382e-07, "epoch": 2.488, "percentage": 82.93, "elapsed_time": "4:48:04", "remaining_time": "0:59:16"}
312
+ {"current_steps": 312, "total_steps": 375, "loss": 0.7605, "lr": 8.378028335970451e-07, "epoch": 2.496, "percentage": 83.2, "elapsed_time": "4:49:04", "remaining_time": "0:58:22"}
313
+ {"current_steps": 313, "total_steps": 375, "loss": 0.7836, "lr": 8.121560668100065e-07, "epoch": 2.504, "percentage": 83.47, "elapsed_time": "4:49:53", "remaining_time": "0:57:25"}
314
+ {"current_steps": 314, "total_steps": 375, "loss": 0.7888, "lr": 7.868732379249122e-07, "epoch": 2.512, "percentage": 83.73, "elapsed_time": "4:50:45", "remaining_time": "0:56:29"}
315
+ {"current_steps": 315, "total_steps": 375, "loss": 0.7476, "lr": 7.619565441057075e-07, "epoch": 2.52, "percentage": 84.0, "elapsed_time": "4:51:38", "remaining_time": "0:55:32"}
316
+ {"current_steps": 316, "total_steps": 375, "loss": 0.776, "lr": 7.37408150697953e-07, "epoch": 2.528, "percentage": 84.27, "elapsed_time": "4:52:25", "remaining_time": "0:54:35"}
317
+ {"current_steps": 317, "total_steps": 375, "loss": 0.7841, "lr": 7.132301910406503e-07, "epoch": 2.536, "percentage": 84.53, "elapsed_time": "4:53:30", "remaining_time": "0:53:42"}
318
+ {"current_steps": 318, "total_steps": 375, "loss": 0.8141, "lr": 6.894247662808456e-07, "epoch": 2.544, "percentage": 84.8, "elapsed_time": "4:54:32", "remaining_time": "0:52:47"}
319
+ {"current_steps": 319, "total_steps": 375, "loss": 0.8007, "lr": 6.659939451910341e-07, "epoch": 2.552, "percentage": 85.07, "elapsed_time": "4:55:30", "remaining_time": "0:51:52"}
320
+ {"current_steps": 320, "total_steps": 375, "loss": 0.7884, "lr": 6.429397639893758e-07, "epoch": 2.56, "percentage": 85.33, "elapsed_time": "4:56:25", "remaining_time": "0:50:56"}
321
+ {"current_steps": 321, "total_steps": 375, "loss": 0.7697, "lr": 6.202642261627411e-07, "epoch": 2.568, "percentage": 85.6, "elapsed_time": "4:57:16", "remaining_time": "0:50:00"}
322
+ {"current_steps": 322, "total_steps": 375, "loss": 0.7715, "lr": 5.979693022926025e-07, "epoch": 2.576, "percentage": 85.87, "elapsed_time": "4:58:13", "remaining_time": "0:49:05"}
323
+ {"current_steps": 323, "total_steps": 375, "loss": 0.785, "lr": 5.760569298837825e-07, "epoch": 2.584, "percentage": 86.13, "elapsed_time": "4:59:00", "remaining_time": "0:48:08"}
324
+ {"current_steps": 324, "total_steps": 375, "loss": 0.8025, "lr": 5.54529013196079e-07, "epoch": 2.592, "percentage": 86.4, "elapsed_time": "4:59:56", "remaining_time": "0:47:12"}
325
+ {"current_steps": 325, "total_steps": 375, "loss": 0.8007, "lr": 5.333874230787772e-07, "epoch": 2.6, "percentage": 86.67, "elapsed_time": "5:01:02", "remaining_time": "0:46:18"}
326
+ {"current_steps": 326, "total_steps": 375, "loss": 0.7889, "lr": 5.126339968080696e-07, "epoch": 2.608, "percentage": 86.93, "elapsed_time": "5:02:02", "remaining_time": "0:45:23"}
327
+ {"current_steps": 327, "total_steps": 375, "loss": 0.7641, "lr": 4.922705379273862e-07, "epoch": 2.616, "percentage": 87.2, "elapsed_time": "5:02:56", "remaining_time": "0:44:28"}
328
+ {"current_steps": 328, "total_steps": 375, "loss": 0.7979, "lr": 4.7229881609066387e-07, "epoch": 2.624, "percentage": 87.47, "elapsed_time": "5:04:01", "remaining_time": "0:43:33"}
329
+ {"current_steps": 329, "total_steps": 375, "loss": 0.7858, "lr": 4.5272056690855494e-07, "epoch": 2.632, "percentage": 87.73, "elapsed_time": "5:05:01", "remaining_time": "0:42:38"}
330
+ {"current_steps": 330, "total_steps": 375, "loss": 0.8095, "lr": 4.335374917975982e-07, "epoch": 2.64, "percentage": 88.0, "elapsed_time": "5:06:01", "remaining_time": "0:41:43"}
331
+ {"current_steps": 331, "total_steps": 375, "loss": 0.7669, "lr": 4.147512578323615e-07, "epoch": 2.648, "percentage": 88.27, "elapsed_time": "5:06:52", "remaining_time": "0:40:47"}
332
+ {"current_steps": 332, "total_steps": 375, "loss": 0.7788, "lr": 3.9636349760056427e-07, "epoch": 2.656, "percentage": 88.53, "elapsed_time": "5:07:46", "remaining_time": "0:39:51"}
333
+ {"current_steps": 333, "total_steps": 375, "loss": 0.7382, "lr": 3.783758090611983e-07, "epoch": 2.664, "percentage": 88.8, "elapsed_time": "5:08:35", "remaining_time": "0:38:55"}
334
+ {"current_steps": 334, "total_steps": 375, "loss": 0.767, "lr": 3.6078975540566716e-07, "epoch": 2.672, "percentage": 89.07, "elapsed_time": "5:09:39", "remaining_time": "0:38:00"}
335
+ {"current_steps": 335, "total_steps": 375, "loss": 0.7928, "lr": 3.4360686492193263e-07, "epoch": 2.68, "percentage": 89.33, "elapsed_time": "5:10:36", "remaining_time": "0:37:05"}
336
+ {"current_steps": 336, "total_steps": 375, "loss": 0.8181, "lr": 3.268286308617041e-07, "epoch": 2.6879999999999997, "percentage": 89.6, "elapsed_time": "5:11:41", "remaining_time": "0:36:10"}
337
+ {"current_steps": 337, "total_steps": 375, "loss": 0.7943, "lr": 3.104565113106689e-07, "epoch": 2.6959999999999997, "percentage": 89.87, "elapsed_time": "5:12:38", "remaining_time": "0:35:15"}
338
+ {"current_steps": 338, "total_steps": 375, "loss": 0.7605, "lr": 2.9449192906178205e-07, "epoch": 2.7039999999999997, "percentage": 90.13, "elapsed_time": "5:13:31", "remaining_time": "0:34:19"}
339
+ {"current_steps": 339, "total_steps": 375, "loss": 0.8095, "lr": 2.789362714916172e-07, "epoch": 2.7119999999999997, "percentage": 90.4, "elapsed_time": "5:14:24", "remaining_time": "0:33:23"}
340
+ {"current_steps": 340, "total_steps": 375, "loss": 0.7988, "lr": 2.6379089043980064e-07, "epoch": 2.7199999999999998, "percentage": 90.67, "elapsed_time": "5:15:24", "remaining_time": "0:32:28"}
341
+ {"current_steps": 341, "total_steps": 375, "loss": 0.7819, "lr": 2.4905710209153224e-07, "epoch": 2.7279999999999998, "percentage": 90.93, "elapsed_time": "5:16:15", "remaining_time": "0:31:32"}
342
+ {"current_steps": 342, "total_steps": 375, "loss": 0.7597, "lr": 2.3473618686320477e-07, "epoch": 2.7359999999999998, "percentage": 91.2, "elapsed_time": "5:17:09", "remaining_time": "0:30:36"}
343
+ {"current_steps": 343, "total_steps": 375, "loss": 0.7797, "lr": 2.208293892911284e-07, "epoch": 2.7439999999999998, "percentage": 91.47, "elapsed_time": "5:18:08", "remaining_time": "0:29:40"}
344
+ {"current_steps": 344, "total_steps": 375, "loss": 0.787, "lr": 2.0733791792338197e-07, "epoch": 2.752, "percentage": 91.73, "elapsed_time": "5:19:01", "remaining_time": "0:28:44"}
345
+ {"current_steps": 345, "total_steps": 375, "loss": 0.8194, "lr": 1.9426294521477874e-07, "epoch": 2.76, "percentage": 92.0, "elapsed_time": "5:20:01", "remaining_time": "0:27:49"}
346
+ {"current_steps": 346, "total_steps": 375, "loss": 0.7881, "lr": 1.8160560742498223e-07, "epoch": 2.768, "percentage": 92.27, "elapsed_time": "5:20:53", "remaining_time": "0:26:53"}
347
+ {"current_steps": 347, "total_steps": 375, "loss": 0.7567, "lr": 1.6936700451975818e-07, "epoch": 2.776, "percentage": 92.53, "elapsed_time": "5:21:52", "remaining_time": "0:25:58"}
348
+ {"current_steps": 348, "total_steps": 375, "loss": 0.7683, "lr": 1.5754820007538473e-07, "epoch": 2.784, "percentage": 92.8, "elapsed_time": "5:22:37", "remaining_time": "0:25:01"}
349
+ {"current_steps": 349, "total_steps": 375, "loss": 0.7094, "lr": 1.461502211862237e-07, "epoch": 2.792, "percentage": 93.07, "elapsed_time": "5:23:11", "remaining_time": "0:24:04"}
350
+ {"current_steps": 350, "total_steps": 375, "loss": 0.8263, "lr": 1.3517405837546404e-07, "epoch": 2.8, "percentage": 93.33, "elapsed_time": "5:24:01", "remaining_time": "0:23:08"}
351
+ {"current_steps": 351, "total_steps": 375, "loss": 0.7728, "lr": 1.2462066550903818e-07, "epoch": 2.808, "percentage": 93.6, "elapsed_time": "5:24:50", "remaining_time": "0:22:12"}
352
+ {"current_steps": 352, "total_steps": 375, "loss": 0.8048, "lr": 1.1449095971273305e-07, "epoch": 2.816, "percentage": 93.87, "elapsed_time": "5:25:45", "remaining_time": "0:21:17"}
353
+ {"current_steps": 353, "total_steps": 375, "loss": 0.8227, "lr": 1.0478582129248516e-07, "epoch": 2.824, "percentage": 94.13, "elapsed_time": "5:26:46", "remaining_time": "0:20:21"}
354
+ {"current_steps": 354, "total_steps": 375, "loss": 0.7782, "lr": 9.550609365787888e-08, "epoch": 2.832, "percentage": 94.4, "elapsed_time": "5:27:45", "remaining_time": "0:19:26"}
355
+ {"current_steps": 355, "total_steps": 375, "loss": 0.7619, "lr": 8.66525832488535e-08, "epoch": 2.84, "percentage": 94.67, "elapsed_time": "5:28:37", "remaining_time": "0:18:30"}
356
+ {"current_steps": 356, "total_steps": 375, "loss": 0.7714, "lr": 7.822605946561923e-08, "epoch": 2.848, "percentage": 94.93, "elapsed_time": "5:29:17", "remaining_time": "0:17:34"}
357
+ {"current_steps": 357, "total_steps": 375, "loss": 0.7252, "lr": 7.022725460179459e-08, "epoch": 2.856, "percentage": 95.2, "elapsed_time": "5:30:03", "remaining_time": "0:16:38"}
358
+ {"current_steps": 358, "total_steps": 375, "loss": 0.8099, "lr": 6.265686378076729e-08, "epoch": 2.864, "percentage": 95.47, "elapsed_time": "5:31:07", "remaining_time": "0:15:43"}
359
+ {"current_steps": 359, "total_steps": 375, "loss": 0.7717, "lr": 5.5515544895284324e-08, "epoch": 2.872, "percentage": 95.73, "elapsed_time": "5:31:57", "remaining_time": "0:14:47"}
360
+ {"current_steps": 360, "total_steps": 375, "loss": 0.7815, "lr": 4.880391855028088e-08, "epoch": 2.88, "percentage": 96.0, "elapsed_time": "5:32:55", "remaining_time": "0:13:52"}
361
+ {"current_steps": 361, "total_steps": 375, "loss": 0.8232, "lr": 4.252256800894694e-08, "epoch": 2.888, "percentage": 96.27, "elapsed_time": "5:33:54", "remaining_time": "0:12:56"}
362
+ {"current_steps": 362, "total_steps": 375, "loss": 0.7802, "lr": 3.6672039142039426e-08, "epoch": 2.896, "percentage": 96.53, "elapsed_time": "5:34:49", "remaining_time": "0:12:01"}
363
+ {"current_steps": 363, "total_steps": 375, "loss": 0.7824, "lr": 3.125284038044407e-08, "epoch": 2.904, "percentage": 96.8, "elapsed_time": "5:35:44", "remaining_time": "0:11:05"}
364
+ {"current_steps": 364, "total_steps": 375, "loss": 0.7715, "lr": 2.6265442670991293e-08, "epoch": 2.912, "percentage": 97.07, "elapsed_time": "5:36:32", "remaining_time": "0:10:10"}
365
+ {"current_steps": 365, "total_steps": 375, "loss": 0.7895, "lr": 2.1710279435530058e-08, "epoch": 2.92, "percentage": 97.33, "elapsed_time": "5:37:23", "remaining_time": "0:09:14"}
366
+ {"current_steps": 366, "total_steps": 375, "loss": 0.8252, "lr": 1.7587746533260786e-08, "epoch": 2.928, "percentage": 97.6, "elapsed_time": "5:38:26", "remaining_time": "0:08:19"}
367
+ {"current_steps": 367, "total_steps": 375, "loss": 0.7914, "lr": 1.3898202226333424e-08, "epoch": 2.936, "percentage": 97.87, "elapsed_time": "5:39:25", "remaining_time": "0:07:23"}
368
+ {"current_steps": 368, "total_steps": 375, "loss": 0.775, "lr": 1.0641967148716236e-08, "epoch": 2.944, "percentage": 98.13, "elapsed_time": "5:40:18", "remaining_time": "0:06:28"}
369
+ {"current_steps": 369, "total_steps": 375, "loss": 0.8268, "lr": 7.819324278328099e-09, "epoch": 2.952, "percentage": 98.4, "elapsed_time": "5:41:09", "remaining_time": "0:05:32"}
370
+ {"current_steps": 370, "total_steps": 375, "loss": 0.785, "lr": 5.430518912448169e-09, "epoch": 2.96, "percentage": 98.67, "elapsed_time": "5:42:11", "remaining_time": "0:04:37"}
371
+ {"current_steps": 371, "total_steps": 375, "loss": 0.7683, "lr": 3.4757586464001513e-09, "epoch": 2.968, "percentage": 98.93, "elapsed_time": "5:43:07", "remaining_time": "0:03:41"}
372
+ {"current_steps": 372, "total_steps": 375, "loss": 0.7837, "lr": 1.9552133555084117e-09, "epoch": 2.976, "percentage": 99.2, "elapsed_time": "5:44:06", "remaining_time": "0:02:46"}
373
+ {"current_steps": 373, "total_steps": 375, "loss": 0.7784, "lr": 8.690151803386615e-10, "epoch": 2.984, "percentage": 99.47, "elapsed_time": "5:44:58", "remaining_time": "0:01:50"}
374
+ {"current_steps": 374, "total_steps": 375, "loss": 0.753, "lr": 2.1725851521103847e-10, "epoch": 2.992, "percentage": 99.73, "elapsed_time": "5:45:45", "remaining_time": "0:00:55"}
375
+ {"current_steps": 375, "total_steps": 375, "loss": 0.7939, "lr": 0.0, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "5:46:43", "remaining_time": "0:00:00"}
376
+ {"current_steps": 375, "total_steps": 375, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "5:48:51", "remaining_time": "0:00:00"}