neginr commited on
Commit
dbfeeb1
·
verified ·
1 Parent(s): 02fb525

Training in progress, epoch 1

Browse files
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0f696450ea9889eb7888bf9318eb8762e50618d562b0edacc394cf6ae4a8cc76
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9730f89d08dfa12709bfaa4dadc2f6e3d2dfdd68da63b6176983a6c0f5d3be8
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:f788c81eb730119e62b0975bb2d882008a7f5f5bc142fcc3d8b397ee2337a4e7
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56542a30f5db7b9bc703b1f9edd6fbea2df1b7506de46d06755c5d7be4836415
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5c3c5b7eb80e3582eb5f1874fe421a3b2b515460f8b9c5db7423cac851348518
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:085f03322cbd8ce6ae38cb56348ce87003c3606b2535f68725fa80cab1eb8f4d
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:ccf7ef8851ecb6ed5828bf6ae99f8ce53c6f055a4092f464848f7b93bb22cb80
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af4ca1d9a295fc9c7a490a21d8e228555fc4949c7ac7034e6929edfcde4dcb9f
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -252,3 +252,252 @@
252
  {"current_steps": 252, "total_steps": 1245, "loss": 0.533, "lr": 3.8744335805680355e-05, "epoch": 1.0110330992978938, "percentage": 20.24, "elapsed_time": "2:15:58", "remaining_time": "8:55:49"}
253
  {"current_steps": 253, "total_steps": 1245, "loss": 0.5436, "lr": 3.872469741279475e-05, "epoch": 1.0150451354062187, "percentage": 20.32, "elapsed_time": "2:16:30", "remaining_time": "8:55:15"}
254
  {"current_steps": 254, "total_steps": 1245, "loss": 0.5331, "lr": 3.87049116943074e-05, "epoch": 1.0190571715145436, "percentage": 20.4, "elapsed_time": "2:17:00", "remaining_time": "8:54:31"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
252
  {"current_steps": 252, "total_steps": 1245, "loss": 0.533, "lr": 3.8744335805680355e-05, "epoch": 1.0110330992978938, "percentage": 20.24, "elapsed_time": "2:15:58", "remaining_time": "8:55:49"}
253
  {"current_steps": 253, "total_steps": 1245, "loss": 0.5436, "lr": 3.872469741279475e-05, "epoch": 1.0150451354062187, "percentage": 20.32, "elapsed_time": "2:16:30", "remaining_time": "8:55:15"}
254
  {"current_steps": 254, "total_steps": 1245, "loss": 0.5331, "lr": 3.87049116943074e-05, "epoch": 1.0190571715145436, "percentage": 20.4, "elapsed_time": "2:17:00", "remaining_time": "8:54:31"}
255
+ {"current_steps": 255, "total_steps": 1245, "loss": 0.4977, "lr": 3.8684978805891994e-05, "epoch": 1.0230692076228687, "percentage": 20.48, "elapsed_time": "2:17:31", "remaining_time": "8:53:56"}
256
+ {"current_steps": 256, "total_steps": 1245, "loss": 0.5232, "lr": 3.866489890438019e-05, "epoch": 1.0270812437311936, "percentage": 20.56, "elapsed_time": "2:18:03", "remaining_time": "8:53:19"}
257
+ {"current_steps": 257, "total_steps": 1245, "loss": 0.5132, "lr": 3.8644672147760286e-05, "epoch": 1.0310932798395185, "percentage": 20.64, "elapsed_time": "2:18:37", "remaining_time": "8:52:56"}
258
+ {"current_steps": 258, "total_steps": 1245, "loss": 0.5133, "lr": 3.862429869517607e-05, "epoch": 1.0351053159478436, "percentage": 20.72, "elapsed_time": "2:19:07", "remaining_time": "8:52:15"}
259
+ {"current_steps": 259, "total_steps": 1245, "loss": 0.5062, "lr": 3.860377870692553e-05, "epoch": 1.0391173520561685, "percentage": 20.8, "elapsed_time": "2:19:38", "remaining_time": "8:51:37"}
260
+ {"current_steps": 260, "total_steps": 1245, "loss": 0.4916, "lr": 3.858311234445957e-05, "epoch": 1.0431293881644934, "percentage": 20.88, "elapsed_time": "2:20:11", "remaining_time": "8:51:07"}
261
+ {"current_steps": 261, "total_steps": 1245, "loss": 0.5126, "lr": 3.856229977038078e-05, "epoch": 1.0471414242728185, "percentage": 20.96, "elapsed_time": "2:20:38", "remaining_time": "8:50:15"}
262
+ {"current_steps": 262, "total_steps": 1245, "loss": 0.5063, "lr": 3.854134114844215e-05, "epoch": 1.0511534603811434, "percentage": 21.04, "elapsed_time": "2:21:09", "remaining_time": "8:49:35"}
263
+ {"current_steps": 263, "total_steps": 1245, "loss": 0.5211, "lr": 3.852023664354576e-05, "epoch": 1.0551654964894683, "percentage": 21.12, "elapsed_time": "2:21:38", "remaining_time": "8:48:50"}
264
+ {"current_steps": 264, "total_steps": 1245, "loss": 0.5248, "lr": 3.849898642174149e-05, "epoch": 1.0591775325977935, "percentage": 21.2, "elapsed_time": "2:22:08", "remaining_time": "8:48:12"}
265
+ {"current_steps": 265, "total_steps": 1245, "loss": 0.5295, "lr": 3.8477590650225735e-05, "epoch": 1.0631895687061184, "percentage": 21.29, "elapsed_time": "2:22:35", "remaining_time": "8:47:20"}
266
+ {"current_steps": 266, "total_steps": 1245, "loss": 0.5136, "lr": 3.845604949734006e-05, "epoch": 1.0672016048144433, "percentage": 21.37, "elapsed_time": "2:23:12", "remaining_time": "8:47:03"}
267
+ {"current_steps": 267, "total_steps": 1245, "loss": 0.5122, "lr": 3.8434363132569883e-05, "epoch": 1.0712136409227684, "percentage": 21.45, "elapsed_time": "2:23:46", "remaining_time": "8:46:39"}
268
+ {"current_steps": 268, "total_steps": 1245, "loss": 0.5323, "lr": 3.841253172654316e-05, "epoch": 1.0752256770310933, "percentage": 21.53, "elapsed_time": "2:24:20", "remaining_time": "8:46:12"}
269
+ {"current_steps": 269, "total_steps": 1245, "loss": 0.5106, "lr": 3.839055545102902e-05, "epoch": 1.0792377131394182, "percentage": 21.61, "elapsed_time": "2:24:51", "remaining_time": "8:45:34"}
270
+ {"current_steps": 270, "total_steps": 1245, "loss": 0.4919, "lr": 3.8368434478936426e-05, "epoch": 1.0832497492477433, "percentage": 21.69, "elapsed_time": "2:25:22", "remaining_time": "8:44:57"}
271
+ {"current_steps": 271, "total_steps": 1245, "loss": 0.5296, "lr": 3.834616898431281e-05, "epoch": 1.0872617853560682, "percentage": 21.77, "elapsed_time": "2:25:55", "remaining_time": "8:44:27"}
272
+ {"current_steps": 272, "total_steps": 1245, "loss": 0.5175, "lr": 3.832375914234272e-05, "epoch": 1.0912738214643931, "percentage": 21.85, "elapsed_time": "2:26:31", "remaining_time": "8:44:08"}
273
+ {"current_steps": 273, "total_steps": 1245, "loss": 0.5147, "lr": 3.83012051293464e-05, "epoch": 1.0952858575727182, "percentage": 21.93, "elapsed_time": "2:27:02", "remaining_time": "8:43:30"}
274
+ {"current_steps": 274, "total_steps": 1245, "loss": 0.4999, "lr": 3.8278507122778444e-05, "epoch": 1.0992978936810431, "percentage": 22.01, "elapsed_time": "2:27:29", "remaining_time": "8:42:41"}
275
+ {"current_steps": 275, "total_steps": 1245, "loss": 0.5293, "lr": 3.825566530122638e-05, "epoch": 1.103309929789368, "percentage": 22.09, "elapsed_time": "2:27:59", "remaining_time": "8:41:59"}
276
+ {"current_steps": 276, "total_steps": 1245, "loss": 0.5008, "lr": 3.823267984440928e-05, "epoch": 1.1073219658976932, "percentage": 22.17, "elapsed_time": "2:28:34", "remaining_time": "8:41:39"}
277
+ {"current_steps": 277, "total_steps": 1245, "loss": 0.5278, "lr": 3.8209550933176324e-05, "epoch": 1.111334002006018, "percentage": 22.25, "elapsed_time": "2:29:11", "remaining_time": "8:41:20"}
278
+ {"current_steps": 278, "total_steps": 1245, "loss": 0.5061, "lr": 3.8186278749505395e-05, "epoch": 1.115346038114343, "percentage": 22.33, "elapsed_time": "2:29:41", "remaining_time": "8:40:42"}
279
+ {"current_steps": 279, "total_steps": 1245, "loss": 0.5105, "lr": 3.816286347650163e-05, "epoch": 1.119358074222668, "percentage": 22.41, "elapsed_time": "2:30:15", "remaining_time": "8:40:13"}
280
+ {"current_steps": 280, "total_steps": 1245, "loss": 0.5171, "lr": 3.813930529839601e-05, "epoch": 1.123370110330993, "percentage": 22.49, "elapsed_time": "2:30:47", "remaining_time": "8:39:42"}
281
+ {"current_steps": 281, "total_steps": 1245, "loss": 0.5136, "lr": 3.8115604400543885e-05, "epoch": 1.127382146439318, "percentage": 22.57, "elapsed_time": "2:31:18", "remaining_time": "8:39:05"}
282
+ {"current_steps": 282, "total_steps": 1245, "loss": 0.5389, "lr": 3.8091760969423507e-05, "epoch": 1.131394182547643, "percentage": 22.65, "elapsed_time": "2:31:54", "remaining_time": "8:38:45"}
283
+ {"current_steps": 283, "total_steps": 1245, "loss": 0.5361, "lr": 3.80677751926346e-05, "epoch": 1.135406218655968, "percentage": 22.73, "elapsed_time": "2:32:29", "remaining_time": "8:38:22"}
284
+ {"current_steps": 284, "total_steps": 1245, "loss": 0.5081, "lr": 3.804364725889683e-05, "epoch": 1.1394182547642928, "percentage": 22.81, "elapsed_time": "2:32:58", "remaining_time": "8:37:37"}
285
+ {"current_steps": 285, "total_steps": 1245, "loss": 0.539, "lr": 3.801937735804838e-05, "epoch": 1.143430290872618, "percentage": 22.89, "elapsed_time": "2:33:27", "remaining_time": "8:36:53"}
286
+ {"current_steps": 286, "total_steps": 1245, "loss": 0.4983, "lr": 3.7994965681044436e-05, "epoch": 1.1474423269809428, "percentage": 22.97, "elapsed_time": "2:33:58", "remaining_time": "8:36:16"}
287
+ {"current_steps": 287, "total_steps": 1245, "loss": 0.5259, "lr": 3.7970412419955626e-05, "epoch": 1.1514543630892677, "percentage": 23.05, "elapsed_time": "2:34:32", "remaining_time": "8:35:51"}
288
+ {"current_steps": 288, "total_steps": 1245, "loss": 0.5368, "lr": 3.794571776796662e-05, "epoch": 1.1554663991975929, "percentage": 23.13, "elapsed_time": "2:35:03", "remaining_time": "8:35:15"}
289
+ {"current_steps": 289, "total_steps": 1245, "loss": 0.5094, "lr": 3.792088191937451e-05, "epoch": 1.1594784353059178, "percentage": 23.21, "elapsed_time": "2:35:34", "remaining_time": "8:34:37"}
290
+ {"current_steps": 290, "total_steps": 1245, "loss": 0.5228, "lr": 3.7895905069587326e-05, "epoch": 1.1634904714142427, "percentage": 23.29, "elapsed_time": "2:36:02", "remaining_time": "8:33:53"}
291
+ {"current_steps": 291, "total_steps": 1245, "loss": 0.5245, "lr": 3.78707874151225e-05, "epoch": 1.1675025075225678, "percentage": 23.37, "elapsed_time": "2:36:31", "remaining_time": "8:33:08"}
292
+ {"current_steps": 292, "total_steps": 1245, "loss": 0.5219, "lr": 3.784552915360532e-05, "epoch": 1.1715145436308927, "percentage": 23.45, "elapsed_time": "2:37:05", "remaining_time": "8:32:41"}
293
+ {"current_steps": 293, "total_steps": 1245, "loss": 0.4938, "lr": 3.782013048376736e-05, "epoch": 1.1755265797392176, "percentage": 23.53, "elapsed_time": "2:37:41", "remaining_time": "8:32:23"}
294
+ {"current_steps": 294, "total_steps": 1245, "loss": 0.5216, "lr": 3.7794591605444915e-05, "epoch": 1.1795386158475427, "percentage": 23.61, "elapsed_time": "2:38:15", "remaining_time": "8:31:54"}
295
+ {"current_steps": 295, "total_steps": 1245, "loss": 0.5114, "lr": 3.776891271957745e-05, "epoch": 1.1835506519558676, "percentage": 23.69, "elapsed_time": "2:38:47", "remaining_time": "8:31:20"}
296
+ {"current_steps": 296, "total_steps": 1245, "loss": 0.5208, "lr": 3.7743094028206e-05, "epoch": 1.1875626880641925, "percentage": 23.78, "elapsed_time": "2:39:16", "remaining_time": "8:30:38"}
297
+ {"current_steps": 297, "total_steps": 1245, "loss": 0.5313, "lr": 3.77171357344716e-05, "epoch": 1.1915747241725176, "percentage": 23.86, "elapsed_time": "2:39:54", "remaining_time": "8:30:25"}
298
+ {"current_steps": 298, "total_steps": 1245, "loss": 0.4958, "lr": 3.769103804261366e-05, "epoch": 1.1955867602808425, "percentage": 23.94, "elapsed_time": "2:40:22", "remaining_time": "8:29:38"}
299
+ {"current_steps": 299, "total_steps": 1245, "loss": 0.5052, "lr": 3.766480115796837e-05, "epoch": 1.1995987963891674, "percentage": 24.02, "elapsed_time": "2:40:51", "remaining_time": "8:28:57"}
300
+ {"current_steps": 300, "total_steps": 1245, "loss": 0.5048, "lr": 3.76384252869671e-05, "epoch": 1.2036108324974926, "percentage": 24.1, "elapsed_time": "2:41:25", "remaining_time": "8:28:29"}
301
+ {"current_steps": 301, "total_steps": 1245, "loss": 0.5282, "lr": 3.761191063713476e-05, "epoch": 1.2076228686058175, "percentage": 24.18, "elapsed_time": "2:41:58", "remaining_time": "8:28:00"}
302
+ {"current_steps": 302, "total_steps": 1245, "loss": 0.4951, "lr": 3.758525741708816e-05, "epoch": 1.2116349047141424, "percentage": 24.26, "elapsed_time": "2:42:33", "remaining_time": "8:27:35"}
303
+ {"current_steps": 303, "total_steps": 1245, "loss": 0.4934, "lr": 3.755846583653439e-05, "epoch": 1.2156469408224675, "percentage": 24.34, "elapsed_time": "2:43:05", "remaining_time": "8:27:00"}
304
+ {"current_steps": 304, "total_steps": 1245, "loss": 0.5151, "lr": 3.753153610626914e-05, "epoch": 1.2196589769307924, "percentage": 24.42, "elapsed_time": "2:43:38", "remaining_time": "8:26:30"}
305
+ {"current_steps": 305, "total_steps": 1245, "loss": 0.5098, "lr": 3.7504468438175076e-05, "epoch": 1.2236710130391173, "percentage": 24.5, "elapsed_time": "2:44:10", "remaining_time": "8:25:58"}
306
+ {"current_steps": 306, "total_steps": 1245, "loss": 0.5244, "lr": 3.7477263045220155e-05, "epoch": 1.2276830491474424, "percentage": 24.58, "elapsed_time": "2:44:44", "remaining_time": "8:25:30"}
307
+ {"current_steps": 307, "total_steps": 1245, "loss": 0.5129, "lr": 3.744992014145595e-05, "epoch": 1.2316950852557673, "percentage": 24.66, "elapsed_time": "2:45:09", "remaining_time": "8:24:37"}
308
+ {"current_steps": 308, "total_steps": 1245, "loss": 0.5093, "lr": 3.742243994201595e-05, "epoch": 1.2357071213640922, "percentage": 24.74, "elapsed_time": "2:45:40", "remaining_time": "8:24:00"}
309
+ {"current_steps": 309, "total_steps": 1245, "loss": 0.5301, "lr": 3.7394822663113915e-05, "epoch": 1.2397191574724173, "percentage": 24.82, "elapsed_time": "2:46:11", "remaining_time": "8:23:25"}
310
+ {"current_steps": 310, "total_steps": 1245, "loss": 0.5071, "lr": 3.7367068522042115e-05, "epoch": 1.2437311935807422, "percentage": 24.9, "elapsed_time": "2:46:46", "remaining_time": "8:23:00"}
311
+ {"current_steps": 311, "total_steps": 1245, "loss": 0.512, "lr": 3.7339177737169664e-05, "epoch": 1.2477432296890671, "percentage": 24.98, "elapsed_time": "2:47:23", "remaining_time": "8:22:41"}
312
+ {"current_steps": 312, "total_steps": 1245, "loss": 0.5028, "lr": 3.731115052794079e-05, "epoch": 1.2517552657973923, "percentage": 25.06, "elapsed_time": "2:47:53", "remaining_time": "8:22:03"}
313
+ {"current_steps": 313, "total_steps": 1245, "loss": 0.5163, "lr": 3.72829871148731e-05, "epoch": 1.2557673019057172, "percentage": 25.14, "elapsed_time": "2:48:23", "remaining_time": "8:21:24"}
314
+ {"current_steps": 314, "total_steps": 1245, "loss": 0.4973, "lr": 3.725468771955584e-05, "epoch": 1.259779338014042, "percentage": 25.22, "elapsed_time": "2:48:59", "remaining_time": "8:21:03"}
315
+ {"current_steps": 315, "total_steps": 1245, "loss": 0.5268, "lr": 3.7226252564648183e-05, "epoch": 1.2637913741223672, "percentage": 25.3, "elapsed_time": "2:49:35", "remaining_time": "8:20:40"}
316
+ {"current_steps": 316, "total_steps": 1245, "loss": 0.5323, "lr": 3.719768187387744e-05, "epoch": 1.267803410230692, "percentage": 25.38, "elapsed_time": "2:50:08", "remaining_time": "8:20:12"}
317
+ {"current_steps": 317, "total_steps": 1245, "loss": 0.5238, "lr": 3.716897587203733e-05, "epoch": 1.271815446339017, "percentage": 25.46, "elapsed_time": "2:50:41", "remaining_time": "8:19:40"}
318
+ {"current_steps": 318, "total_steps": 1245, "loss": 0.5192, "lr": 3.714013478498618e-05, "epoch": 1.2758274824473421, "percentage": 25.54, "elapsed_time": "2:51:12", "remaining_time": "8:19:05"}
319
+ {"current_steps": 319, "total_steps": 1245, "loss": 0.5062, "lr": 3.711115883964516e-05, "epoch": 1.279839518555667, "percentage": 25.62, "elapsed_time": "2:51:39", "remaining_time": "8:18:17"}
320
+ {"current_steps": 320, "total_steps": 1245, "loss": 0.5334, "lr": 3.7082048263996554e-05, "epoch": 1.283851554663992, "percentage": 25.7, "elapsed_time": "2:52:09", "remaining_time": "8:17:38"}
321
+ {"current_steps": 321, "total_steps": 1245, "loss": 0.5307, "lr": 3.705280328708185e-05, "epoch": 1.287863590772317, "percentage": 25.78, "elapsed_time": "2:52:40", "remaining_time": "8:17:03"}
322
+ {"current_steps": 322, "total_steps": 1245, "loss": 0.5283, "lr": 3.702342413900003e-05, "epoch": 1.291875626880642, "percentage": 25.86, "elapsed_time": "2:53:10", "remaining_time": "8:16:24"}
323
+ {"current_steps": 323, "total_steps": 1245, "loss": 0.4959, "lr": 3.6993911050905754e-05, "epoch": 1.2958876629889668, "percentage": 25.94, "elapsed_time": "2:53:40", "remaining_time": "8:15:45"}
324
+ {"current_steps": 324, "total_steps": 1245, "loss": 0.4886, "lr": 3.696426425500747e-05, "epoch": 1.299899699097292, "percentage": 26.02, "elapsed_time": "2:54:05", "remaining_time": "8:14:51"}
325
+ {"current_steps": 325, "total_steps": 1245, "loss": 0.4892, "lr": 3.6934483984565684e-05, "epoch": 1.3039117352056169, "percentage": 26.1, "elapsed_time": "2:54:25", "remaining_time": "8:13:45"}
326
+ {"current_steps": 326, "total_steps": 1245, "loss": 0.5291, "lr": 3.690457047389106e-05, "epoch": 1.3079237713139418, "percentage": 26.18, "elapsed_time": "2:54:55", "remaining_time": "8:13:06"}
327
+ {"current_steps": 327, "total_steps": 1245, "loss": 0.5123, "lr": 3.687452395834259e-05, "epoch": 1.311935807422267, "percentage": 26.27, "elapsed_time": "2:55:27", "remaining_time": "8:12:34"}
328
+ {"current_steps": 328, "total_steps": 1245, "loss": 0.517, "lr": 3.684434467432573e-05, "epoch": 1.3159478435305918, "percentage": 26.35, "elapsed_time": "2:55:53", "remaining_time": "8:11:44"}
329
+ {"current_steps": 329, "total_steps": 1245, "loss": 0.5128, "lr": 3.681403285929061e-05, "epoch": 1.3199598796389167, "percentage": 26.43, "elapsed_time": "2:56:23", "remaining_time": "8:11:07"}
330
+ {"current_steps": 330, "total_steps": 1245, "loss": 0.5173, "lr": 3.678358875173005e-05, "epoch": 1.3239719157472418, "percentage": 26.51, "elapsed_time": "2:56:53", "remaining_time": "8:10:29"}
331
+ {"current_steps": 331, "total_steps": 1245, "loss": 0.4942, "lr": 3.6753012591177774e-05, "epoch": 1.3279839518555667, "percentage": 26.59, "elapsed_time": "2:57:22", "remaining_time": "8:09:46"}
332
+ {"current_steps": 332, "total_steps": 1245, "loss": 0.5051, "lr": 3.672230461820651e-05, "epoch": 1.3319959879638916, "percentage": 26.67, "elapsed_time": "2:57:57", "remaining_time": "8:09:22"}
333
+ {"current_steps": 333, "total_steps": 1245, "loss": 0.5504, "lr": 3.669146507442606e-05, "epoch": 1.3360080240722167, "percentage": 26.75, "elapsed_time": "2:58:31", "remaining_time": "8:08:56"}
334
+ {"current_steps": 334, "total_steps": 1245, "loss": 0.5027, "lr": 3.6660494202481426e-05, "epoch": 1.3400200601805417, "percentage": 26.83, "elapsed_time": "2:59:00", "remaining_time": "8:08:14"}
335
+ {"current_steps": 335, "total_steps": 1245, "loss": 0.5327, "lr": 3.662939224605091e-05, "epoch": 1.3440320962888666, "percentage": 26.91, "elapsed_time": "2:59:29", "remaining_time": "8:07:33"}
336
+ {"current_steps": 336, "total_steps": 1245, "loss": 0.5157, "lr": 3.6598159449844175e-05, "epoch": 1.3480441323971917, "percentage": 26.99, "elapsed_time": "3:00:01", "remaining_time": "8:07:03"}
337
+ {"current_steps": 337, "total_steps": 1245, "loss": 0.5071, "lr": 3.6566796059600334e-05, "epoch": 1.3520561685055166, "percentage": 27.07, "elapsed_time": "3:00:30", "remaining_time": "8:06:20"}
338
+ {"current_steps": 338, "total_steps": 1245, "loss": 0.5051, "lr": 3.653530232208601e-05, "epoch": 1.3560682046138415, "percentage": 27.15, "elapsed_time": "3:01:06", "remaining_time": "8:05:59"}
339
+ {"current_steps": 339, "total_steps": 1245, "loss": 0.5026, "lr": 3.650367848509339e-05, "epoch": 1.3600802407221666, "percentage": 27.23, "elapsed_time": "3:01:42", "remaining_time": "8:05:37"}
340
+ {"current_steps": 340, "total_steps": 1245, "loss": 0.512, "lr": 3.64719247974383e-05, "epoch": 1.3640922768304915, "percentage": 27.31, "elapsed_time": "3:02:14", "remaining_time": "8:05:05"}
341
+ {"current_steps": 341, "total_steps": 1245, "loss": 0.4954, "lr": 3.644004150895821e-05, "epoch": 1.3681043129388164, "percentage": 27.39, "elapsed_time": "3:02:43", "remaining_time": "8:04:24"}
342
+ {"current_steps": 342, "total_steps": 1245, "loss": 0.52, "lr": 3.640802887051027e-05, "epoch": 1.3721163490471415, "percentage": 27.47, "elapsed_time": "3:03:14", "remaining_time": "8:03:49"}
343
+ {"current_steps": 343, "total_steps": 1245, "loss": 0.5362, "lr": 3.637588713396942e-05, "epoch": 1.3761283851554664, "percentage": 27.55, "elapsed_time": "3:03:47", "remaining_time": "8:03:20"}
344
+ {"current_steps": 344, "total_steps": 1245, "loss": 0.5258, "lr": 3.6343616552226267e-05, "epoch": 1.3801404212637913, "percentage": 27.63, "elapsed_time": "3:04:17", "remaining_time": "8:02:41"}
345
+ {"current_steps": 345, "total_steps": 1245, "loss": 0.521, "lr": 3.631121737918521e-05, "epoch": 1.3841524573721165, "percentage": 27.71, "elapsed_time": "3:04:50", "remaining_time": "8:02:11"}
346
+ {"current_steps": 346, "total_steps": 1245, "loss": 0.5233, "lr": 3.627868986976239e-05, "epoch": 1.3881644934804414, "percentage": 27.79, "elapsed_time": "3:05:25", "remaining_time": "8:01:47"}
347
+ {"current_steps": 347, "total_steps": 1245, "loss": 0.529, "lr": 3.6246034279883706e-05, "epoch": 1.3921765295887663, "percentage": 27.87, "elapsed_time": "3:05:58", "remaining_time": "8:01:17"}
348
+ {"current_steps": 348, "total_steps": 1245, "loss": 0.5165, "lr": 3.621325086648278e-05, "epoch": 1.3961885656970914, "percentage": 27.95, "elapsed_time": "3:06:29", "remaining_time": "8:00:41"}
349
+ {"current_steps": 349, "total_steps": 1245, "loss": 0.5353, "lr": 3.6180339887498953e-05, "epoch": 1.4002006018054163, "percentage": 28.03, "elapsed_time": "3:06:59", "remaining_time": "8:00:04"}
350
+ {"current_steps": 350, "total_steps": 1245, "loss": 0.5214, "lr": 3.6147301601875254e-05, "epoch": 1.4042126379137412, "percentage": 28.11, "elapsed_time": "3:07:34", "remaining_time": "7:59:40"}
351
+ {"current_steps": 351, "total_steps": 1245, "loss": 0.521, "lr": 3.611413626955635e-05, "epoch": 1.4082246740220663, "percentage": 28.19, "elapsed_time": "3:08:06", "remaining_time": "7:59:07"}
352
+ {"current_steps": 352, "total_steps": 1245, "loss": 0.508, "lr": 3.6080844151486505e-05, "epoch": 1.4122367101303912, "percentage": 28.27, "elapsed_time": "3:08:32", "remaining_time": "7:58:19"}
353
+ {"current_steps": 353, "total_steps": 1245, "loss": 0.5432, "lr": 3.6047425509607566e-05, "epoch": 1.416248746238716, "percentage": 28.35, "elapsed_time": "3:09:04", "remaining_time": "7:57:47"}
354
+ {"current_steps": 354, "total_steps": 1245, "loss": 0.5151, "lr": 3.601388060685681e-05, "epoch": 1.4202607823470412, "percentage": 28.43, "elapsed_time": "3:09:41", "remaining_time": "7:57:25"}
355
+ {"current_steps": 355, "total_steps": 1245, "loss": 0.5319, "lr": 3.598020970716499e-05, "epoch": 1.4242728184553661, "percentage": 28.51, "elapsed_time": "3:10:16", "remaining_time": "7:57:00"}
356
+ {"current_steps": 356, "total_steps": 1245, "loss": 0.4964, "lr": 3.594641307545414e-05, "epoch": 1.428284854563691, "percentage": 28.59, "elapsed_time": "3:10:44", "remaining_time": "7:56:18"}
357
+ {"current_steps": 357, "total_steps": 1245, "loss": 0.5049, "lr": 3.591249097763562e-05, "epoch": 1.4322968906720162, "percentage": 28.67, "elapsed_time": "3:11:18", "remaining_time": "7:55:52"}
358
+ {"current_steps": 358, "total_steps": 1245, "loss": 0.5011, "lr": 3.58784436806079e-05, "epoch": 1.436308926780341, "percentage": 28.76, "elapsed_time": "3:12:01", "remaining_time": "7:55:45"}
359
+ {"current_steps": 359, "total_steps": 1245, "loss": 0.5153, "lr": 3.584427145225455e-05, "epoch": 1.440320962888666, "percentage": 28.84, "elapsed_time": "3:12:27", "remaining_time": "7:54:59"}
360
+ {"current_steps": 360, "total_steps": 1245, "loss": 0.512, "lr": 3.5809974561442074e-05, "epoch": 1.444332998996991, "percentage": 28.92, "elapsed_time": "3:13:02", "remaining_time": "7:54:33"}
361
+ {"current_steps": 361, "total_steps": 1245, "loss": 0.5248, "lr": 3.5775553278017824e-05, "epoch": 1.448345035105316, "percentage": 29.0, "elapsed_time": "3:13:31", "remaining_time": "7:53:53"}
362
+ {"current_steps": 362, "total_steps": 1245, "loss": 0.5309, "lr": 3.574100787280788e-05, "epoch": 1.4523570712136409, "percentage": 29.08, "elapsed_time": "3:13:57", "remaining_time": "7:53:06"}
363
+ {"current_steps": 363, "total_steps": 1245, "loss": 0.4956, "lr": 3.57063386176149e-05, "epoch": 1.456369107321966, "percentage": 29.16, "elapsed_time": "3:14:27", "remaining_time": "7:52:29"}
364
+ {"current_steps": 364, "total_steps": 1245, "loss": 0.5152, "lr": 3.5671545785216004e-05, "epoch": 1.460381143430291, "percentage": 29.24, "elapsed_time": "3:14:57", "remaining_time": "7:51:51"}
365
+ {"current_steps": 365, "total_steps": 1245, "loss": 0.5269, "lr": 3.56366296493606e-05, "epoch": 1.4643931795386158, "percentage": 29.32, "elapsed_time": "3:15:31", "remaining_time": "7:51:22"}
366
+ {"current_steps": 366, "total_steps": 1245, "loss": 0.5334, "lr": 3.560159048476825e-05, "epoch": 1.468405215646941, "percentage": 29.4, "elapsed_time": "3:16:03", "remaining_time": "7:50:51"}
367
+ {"current_steps": 367, "total_steps": 1245, "loss": 0.5287, "lr": 3.556642856712652e-05, "epoch": 1.4724172517552658, "percentage": 29.48, "elapsed_time": "3:16:40", "remaining_time": "7:50:30"}
368
+ {"current_steps": 368, "total_steps": 1245, "loss": 0.5135, "lr": 3.5531144173088774e-05, "epoch": 1.4764292878635907, "percentage": 29.56, "elapsed_time": "3:17:12", "remaining_time": "7:49:59"}
369
+ {"current_steps": 369, "total_steps": 1245, "loss": 0.5194, "lr": 3.5495737580272024e-05, "epoch": 1.4804413239719159, "percentage": 29.64, "elapsed_time": "3:17:42", "remaining_time": "7:49:21"}
370
+ {"current_steps": 370, "total_steps": 1245, "loss": 0.5233, "lr": 3.546020906725474e-05, "epoch": 1.4844533600802408, "percentage": 29.72, "elapsed_time": "3:18:13", "remaining_time": "7:48:46"}
371
+ {"current_steps": 371, "total_steps": 1245, "loss": 0.5223, "lr": 3.542455891357467e-05, "epoch": 1.4884653961885657, "percentage": 29.8, "elapsed_time": "3:18:51", "remaining_time": "7:48:27"}
372
+ {"current_steps": 372, "total_steps": 1245, "loss": 0.5172, "lr": 3.5388787399726605e-05, "epoch": 1.4924774322968908, "percentage": 29.88, "elapsed_time": "3:19:19", "remaining_time": "7:47:46"}
373
+ {"current_steps": 373, "total_steps": 1245, "loss": 0.501, "lr": 3.535289480716023e-05, "epoch": 1.4964894684052157, "percentage": 29.96, "elapsed_time": "3:19:48", "remaining_time": "7:47:06"}
374
+ {"current_steps": 374, "total_steps": 1245, "loss": 0.5233, "lr": 3.531688141827783e-05, "epoch": 1.5005015045135406, "percentage": 30.04, "elapsed_time": "3:20:18", "remaining_time": "7:46:28"}
375
+ {"current_steps": 375, "total_steps": 1245, "loss": 0.5215, "lr": 3.528074751643215e-05, "epoch": 1.5045135406218657, "percentage": 30.12, "elapsed_time": "3:20:52", "remaining_time": "7:46:01"}
376
+ {"current_steps": 376, "total_steps": 1245, "loss": 0.5073, "lr": 3.524449338592412e-05, "epoch": 1.5085255767301906, "percentage": 30.2, "elapsed_time": "3:21:24", "remaining_time": "7:45:28"}
377
+ {"current_steps": 377, "total_steps": 1245, "loss": 0.5305, "lr": 3.520811931200063e-05, "epoch": 1.5125376128385155, "percentage": 30.28, "elapsed_time": "3:21:50", "remaining_time": "7:44:44"}
378
+ {"current_steps": 378, "total_steps": 1245, "loss": 0.5327, "lr": 3.5171625580852256e-05, "epoch": 1.5165496489468406, "percentage": 30.36, "elapsed_time": "3:22:23", "remaining_time": "7:44:11"}
379
+ {"current_steps": 379, "total_steps": 1245, "loss": 0.5078, "lr": 3.513501247961106e-05, "epoch": 1.5205616850551655, "percentage": 30.44, "elapsed_time": "3:22:52", "remaining_time": "7:43:34"}
380
+ {"current_steps": 380, "total_steps": 1245, "loss": 0.5164, "lr": 3.509828029634832e-05, "epoch": 1.5245737211634904, "percentage": 30.52, "elapsed_time": "3:23:23", "remaining_time": "7:42:59"}
381
+ {"current_steps": 381, "total_steps": 1245, "loss": 0.5345, "lr": 3.5061429320072225e-05, "epoch": 1.5285857572718156, "percentage": 30.6, "elapsed_time": "3:23:55", "remaining_time": "7:42:25"}
382
+ {"current_steps": 382, "total_steps": 1245, "loss": 0.5061, "lr": 3.502445984072562e-05, "epoch": 1.5325977933801405, "percentage": 30.68, "elapsed_time": "3:24:19", "remaining_time": "7:41:35"}
383
+ {"current_steps": 383, "total_steps": 1245, "loss": 0.5227, "lr": 3.4987372149183745e-05, "epoch": 1.5366098294884654, "percentage": 30.76, "elapsed_time": "3:24:44", "remaining_time": "7:40:47"}
384
+ {"current_steps": 384, "total_steps": 1245, "loss": 0.521, "lr": 3.495016653725194e-05, "epoch": 1.5406218655967905, "percentage": 30.84, "elapsed_time": "3:25:16", "remaining_time": "7:40:15"}
385
+ {"current_steps": 385, "total_steps": 1245, "loss": 0.5168, "lr": 3.4912843297663315e-05, "epoch": 1.5446339017051154, "percentage": 30.92, "elapsed_time": "3:25:49", "remaining_time": "7:39:46"}
386
+ {"current_steps": 386, "total_steps": 1245, "loss": 0.5134, "lr": 3.48754027240765e-05, "epoch": 1.5486459378134403, "percentage": 31.0, "elapsed_time": "3:26:23", "remaining_time": "7:39:17"}
387
+ {"current_steps": 387, "total_steps": 1245, "loss": 0.5028, "lr": 3.483784511107328e-05, "epoch": 1.5526579739217654, "percentage": 31.08, "elapsed_time": "3:26:51", "remaining_time": "7:38:37"}
388
+ {"current_steps": 388, "total_steps": 1245, "loss": 0.5136, "lr": 3.480017075415632e-05, "epoch": 1.5566700100300903, "percentage": 31.16, "elapsed_time": "3:27:25", "remaining_time": "7:38:09"}
389
+ {"current_steps": 389, "total_steps": 1245, "loss": 0.5282, "lr": 3.476237994974682e-05, "epoch": 1.5606820461384152, "percentage": 31.24, "elapsed_time": "3:27:54", "remaining_time": "7:37:31"}
390
+ {"current_steps": 390, "total_steps": 1245, "loss": 0.499, "lr": 3.4724472995182194e-05, "epoch": 1.5646940822467403, "percentage": 31.33, "elapsed_time": "3:28:21", "remaining_time": "7:36:47"}
391
+ {"current_steps": 391, "total_steps": 1245, "loss": 0.5083, "lr": 3.468645018871371e-05, "epoch": 1.5687061183550652, "percentage": 31.41, "elapsed_time": "3:28:52", "remaining_time": "7:36:13"}
392
+ {"current_steps": 392, "total_steps": 1245, "loss": 0.5206, "lr": 3.464831182950418e-05, "epoch": 1.5727181544633901, "percentage": 31.49, "elapsed_time": "3:29:23", "remaining_time": "7:35:39"}
393
+ {"current_steps": 393, "total_steps": 1245, "loss": 0.5295, "lr": 3.4610058217625554e-05, "epoch": 1.5767301905717153, "percentage": 31.57, "elapsed_time": "3:29:56", "remaining_time": "7:35:07"}
394
+ {"current_steps": 394, "total_steps": 1245, "loss": 0.504, "lr": 3.4571689654056605e-05, "epoch": 1.5807422266800402, "percentage": 31.65, "elapsed_time": "3:30:29", "remaining_time": "7:34:39"}
395
+ {"current_steps": 395, "total_steps": 1245, "loss": 0.5058, "lr": 3.4533206440680546e-05, "epoch": 1.584754262788365, "percentage": 31.73, "elapsed_time": "3:31:04", "remaining_time": "7:34:11"}
396
+ {"current_steps": 396, "total_steps": 1245, "loss": 0.523, "lr": 3.449460888028264e-05, "epoch": 1.5887662988966902, "percentage": 31.81, "elapsed_time": "3:31:33", "remaining_time": "7:33:34"}
397
+ {"current_steps": 397, "total_steps": 1245, "loss": 0.5244, "lr": 3.4455897276547836e-05, "epoch": 1.592778335005015, "percentage": 31.89, "elapsed_time": "3:32:06", "remaining_time": "7:33:03"}
398
+ {"current_steps": 398, "total_steps": 1245, "loss": 0.5284, "lr": 3.441707193405838e-05, "epoch": 1.59679037111334, "percentage": 31.97, "elapsed_time": "3:32:37", "remaining_time": "7:32:29"}
399
+ {"current_steps": 399, "total_steps": 1245, "loss": 0.4915, "lr": 3.437813315829141e-05, "epoch": 1.6008024072216651, "percentage": 32.05, "elapsed_time": "3:33:11", "remaining_time": "7:32:01"}
400
+ {"current_steps": 400, "total_steps": 1245, "loss": 0.5259, "lr": 3.433908125561655e-05, "epoch": 1.60481444332999, "percentage": 32.13, "elapsed_time": "3:33:45", "remaining_time": "7:31:33"}
401
+ {"current_steps": 401, "total_steps": 1245, "loss": 0.5272, "lr": 3.429991653329351e-05, "epoch": 1.608826479438315, "percentage": 32.21, "elapsed_time": "3:34:16", "remaining_time": "7:30:59"}
402
+ {"current_steps": 402, "total_steps": 1245, "loss": 0.5429, "lr": 3.426063929946966e-05, "epoch": 1.61283851554664, "percentage": 32.29, "elapsed_time": "3:34:51", "remaining_time": "7:30:33"}
403
+ {"current_steps": 403, "total_steps": 1245, "loss": 0.5181, "lr": 3.422124986317761e-05, "epoch": 1.616850551654965, "percentage": 32.37, "elapsed_time": "3:35:26", "remaining_time": "7:30:08"}
404
+ {"current_steps": 404, "total_steps": 1245, "loss": 0.5232, "lr": 3.418174853433278e-05, "epoch": 1.6208625877632898, "percentage": 32.45, "elapsed_time": "3:35:56", "remaining_time": "7:29:30"}
405
+ {"current_steps": 405, "total_steps": 1245, "loss": 0.5093, "lr": 3.4142135623730954e-05, "epoch": 1.624874623871615, "percentage": 32.53, "elapsed_time": "3:36:28", "remaining_time": "7:28:59"}
406
+ {"current_steps": 406, "total_steps": 1245, "loss": 0.5108, "lr": 3.410241144304584e-05, "epoch": 1.6288866599799399, "percentage": 32.61, "elapsed_time": "3:36:58", "remaining_time": "7:28:23"}
407
+ {"current_steps": 407, "total_steps": 1245, "loss": 0.5474, "lr": 3.406257630482661e-05, "epoch": 1.6328986960882648, "percentage": 32.69, "elapsed_time": "3:37:26", "remaining_time": "7:27:41"}
408
+ {"current_steps": 408, "total_steps": 1245, "loss": 0.5448, "lr": 3.402263052249547e-05, "epoch": 1.63691073219659, "percentage": 32.77, "elapsed_time": "3:37:54", "remaining_time": "7:27:01"}
409
+ {"current_steps": 409, "total_steps": 1245, "loss": 0.5144, "lr": 3.398257441034515e-05, "epoch": 1.6409227683049148, "percentage": 32.85, "elapsed_time": "3:38:26", "remaining_time": "7:26:29"}
410
+ {"current_steps": 410, "total_steps": 1245, "loss": 0.5216, "lr": 3.394240828353647e-05, "epoch": 1.6449348044132397, "percentage": 32.93, "elapsed_time": "3:39:03", "remaining_time": "7:26:07"}
411
+ {"current_steps": 411, "total_steps": 1245, "loss": 0.5046, "lr": 3.390213245809582e-05, "epoch": 1.6489468405215648, "percentage": 33.01, "elapsed_time": "3:39:36", "remaining_time": "7:25:38"}
412
+ {"current_steps": 412, "total_steps": 1245, "loss": 0.5161, "lr": 3.3861747250912724e-05, "epoch": 1.6529588766298897, "percentage": 33.09, "elapsed_time": "3:40:14", "remaining_time": "7:25:17"}
413
+ {"current_steps": 413, "total_steps": 1245, "loss": 0.507, "lr": 3.38212529797373e-05, "epoch": 1.6569709127382146, "percentage": 33.17, "elapsed_time": "3:40:42", "remaining_time": "7:24:36"}
414
+ {"current_steps": 414, "total_steps": 1245, "loss": 0.5012, "lr": 3.378064996317779e-05, "epoch": 1.6609829488465397, "percentage": 33.25, "elapsed_time": "3:41:04", "remaining_time": "7:23:45"}
415
+ {"current_steps": 415, "total_steps": 1245, "loss": 0.5272, "lr": 3.373993852069804e-05, "epoch": 1.6649949849548646, "percentage": 33.33, "elapsed_time": "3:41:35", "remaining_time": "7:23:11"}
416
+ {"current_steps": 416, "total_steps": 1245, "loss": 0.5068, "lr": 3.369911897261499e-05, "epoch": 1.6690070210631895, "percentage": 33.41, "elapsed_time": "3:42:09", "remaining_time": "7:22:43"}
417
+ {"current_steps": 417, "total_steps": 1245, "loss": 0.5146, "lr": 3.365819164009614e-05, "epoch": 1.6730190571715147, "percentage": 33.49, "elapsed_time": "3:42:40", "remaining_time": "7:22:07"}
418
+ {"current_steps": 418, "total_steps": 1245, "loss": 0.5127, "lr": 3.361715684515707e-05, "epoch": 1.6770310932798396, "percentage": 33.57, "elapsed_time": "3:43:08", "remaining_time": "7:21:28"}
419
+ {"current_steps": 419, "total_steps": 1245, "loss": 0.5042, "lr": 3.357601491065884e-05, "epoch": 1.6810431293881645, "percentage": 33.65, "elapsed_time": "3:43:43", "remaining_time": "7:21:01"}
420
+ {"current_steps": 420, "total_steps": 1245, "loss": 0.5166, "lr": 3.353476616030549e-05, "epoch": 1.6850551654964896, "percentage": 33.73, "elapsed_time": "3:44:14", "remaining_time": "7:20:27"}
421
+ {"current_steps": 421, "total_steps": 1245, "loss": 0.5128, "lr": 3.349341091864149e-05, "epoch": 1.6890672016048145, "percentage": 33.82, "elapsed_time": "3:44:43", "remaining_time": "7:19:50"}
422
+ {"current_steps": 422, "total_steps": 1245, "loss": 0.5093, "lr": 3.345194951104918e-05, "epoch": 1.6930792377131394, "percentage": 33.9, "elapsed_time": "3:45:14", "remaining_time": "7:19:15"}
423
+ {"current_steps": 423, "total_steps": 1245, "loss": 0.533, "lr": 3.341038226374622e-05, "epoch": 1.6970912738214645, "percentage": 33.98, "elapsed_time": "3:45:43", "remaining_time": "7:18:38"}
424
+ {"current_steps": 424, "total_steps": 1245, "loss": 0.4988, "lr": 3.3368709503783e-05, "epoch": 1.7011033099297894, "percentage": 34.06, "elapsed_time": "3:46:13", "remaining_time": "7:18:02"}
425
+ {"current_steps": 425, "total_steps": 1245, "loss": 0.5124, "lr": 3.3326931559040084e-05, "epoch": 1.7051153460381143, "percentage": 34.14, "elapsed_time": "3:46:44", "remaining_time": "7:17:27"}
426
+ {"current_steps": 426, "total_steps": 1245, "loss": 0.5082, "lr": 3.328504875822564e-05, "epoch": 1.7091273821464394, "percentage": 34.22, "elapsed_time": "3:47:17", "remaining_time": "7:16:58"}
427
+ {"current_steps": 427, "total_steps": 1245, "loss": 0.5249, "lr": 3.3243061430872826e-05, "epoch": 1.7131394182547643, "percentage": 34.3, "elapsed_time": "3:47:53", "remaining_time": "7:16:34"}
428
+ {"current_steps": 428, "total_steps": 1245, "loss": 0.5136, "lr": 3.320096990733724e-05, "epoch": 1.7171514543630892, "percentage": 34.38, "elapsed_time": "3:48:30", "remaining_time": "7:16:11"}
429
+ {"current_steps": 429, "total_steps": 1245, "loss": 0.5354, "lr": 3.315877451879426e-05, "epoch": 1.7211634904714144, "percentage": 34.46, "elapsed_time": "3:48:58", "remaining_time": "7:15:31"}
430
+ {"current_steps": 430, "total_steps": 1245, "loss": 0.5022, "lr": 3.3116475597236486e-05, "epoch": 1.7251755265797393, "percentage": 34.54, "elapsed_time": "3:49:29", "remaining_time": "7:14:57"}
431
+ {"current_steps": 431, "total_steps": 1245, "loss": 0.4845, "lr": 3.3074073475471125e-05, "epoch": 1.7291875626880642, "percentage": 34.62, "elapsed_time": "3:50:04", "remaining_time": "7:14:31"}
432
+ {"current_steps": 432, "total_steps": 1245, "loss": 0.5207, "lr": 3.303156848711734e-05, "epoch": 1.7331995987963893, "percentage": 34.7, "elapsed_time": "3:50:36", "remaining_time": "7:14:00"}
433
+ {"current_steps": 433, "total_steps": 1245, "loss": 0.5256, "lr": 3.298896096660367e-05, "epoch": 1.7372116349047142, "percentage": 34.78, "elapsed_time": "3:51:04", "remaining_time": "7:13:20"}
434
+ {"current_steps": 434, "total_steps": 1245, "loss": 0.4944, "lr": 3.2946251249165366e-05, "epoch": 1.741223671013039, "percentage": 34.86, "elapsed_time": "3:51:35", "remaining_time": "7:12:46"}
435
+ {"current_steps": 435, "total_steps": 1245, "loss": 0.4948, "lr": 3.290343967084176e-05, "epoch": 1.7452357071213642, "percentage": 34.94, "elapsed_time": "3:52:07", "remaining_time": "7:12:13"}
436
+ {"current_steps": 436, "total_steps": 1245, "loss": 0.4979, "lr": 3.2860526568473605e-05, "epoch": 1.7492477432296891, "percentage": 35.02, "elapsed_time": "3:52:40", "remaining_time": "7:11:43"}
437
+ {"current_steps": 437, "total_steps": 1245, "loss": 0.5072, "lr": 3.2817512279700486e-05, "epoch": 1.753259779338014, "percentage": 35.1, "elapsed_time": "3:53:15", "remaining_time": "7:11:18"}
438
+ {"current_steps": 438, "total_steps": 1245, "loss": 0.517, "lr": 3.277439714295809e-05, "epoch": 1.7572718154463391, "percentage": 35.18, "elapsed_time": "3:53:51", "remaining_time": "7:10:51"}
439
+ {"current_steps": 439, "total_steps": 1245, "loss": 0.5279, "lr": 3.273118149747557e-05, "epoch": 1.7612838515546638, "percentage": 35.26, "elapsed_time": "3:54:23", "remaining_time": "7:10:19"}
440
+ {"current_steps": 440, "total_steps": 1245, "loss": 0.4813, "lr": 3.268786568327291e-05, "epoch": 1.765295887662989, "percentage": 35.34, "elapsed_time": "3:54:54", "remaining_time": "7:09:47"}
441
+ {"current_steps": 441, "total_steps": 1245, "loss": 0.5152, "lr": 3.26444500411582e-05, "epoch": 1.769307923771314, "percentage": 35.42, "elapsed_time": "3:55:26", "remaining_time": "7:09:14"}
442
+ {"current_steps": 442, "total_steps": 1245, "loss": 0.5077, "lr": 3.260093491272496e-05, "epoch": 1.7733199598796388, "percentage": 35.5, "elapsed_time": "3:55:56", "remaining_time": "7:08:37"}
443
+ {"current_steps": 443, "total_steps": 1245, "loss": 0.5054, "lr": 3.25573206403495e-05, "epoch": 1.7773319959879639, "percentage": 35.58, "elapsed_time": "3:56:29", "remaining_time": "7:08:09"}
444
+ {"current_steps": 444, "total_steps": 1245, "loss": 0.5128, "lr": 3.251360756718816e-05, "epoch": 1.781344032096289, "percentage": 35.66, "elapsed_time": "3:56:57", "remaining_time": "7:07:29"}
445
+ {"current_steps": 445, "total_steps": 1245, "loss": 0.5059, "lr": 3.246979603717467e-05, "epoch": 1.7853560682046137, "percentage": 35.74, "elapsed_time": "3:57:26", "remaining_time": "7:06:51"}
446
+ {"current_steps": 446, "total_steps": 1245, "loss": 0.5164, "lr": 3.242588639501741e-05, "epoch": 1.7893681043129388, "percentage": 35.82, "elapsed_time": "3:57:58", "remaining_time": "7:06:19"}
447
+ {"current_steps": 447, "total_steps": 1245, "loss": 0.5022, "lr": 3.238187898619669e-05, "epoch": 1.793380140421264, "percentage": 35.9, "elapsed_time": "3:58:30", "remaining_time": "7:05:47"}
448
+ {"current_steps": 448, "total_steps": 1245, "loss": 0.4899, "lr": 3.2337774156962045e-05, "epoch": 1.7973921765295886, "percentage": 35.98, "elapsed_time": "3:59:06", "remaining_time": "7:05:22"}
449
+ {"current_steps": 449, "total_steps": 1245, "loss": 0.5115, "lr": 3.2293572254329546e-05, "epoch": 1.8014042126379137, "percentage": 36.06, "elapsed_time": "3:59:33", "remaining_time": "7:04:41"}
450
+ {"current_steps": 450, "total_steps": 1245, "loss": 0.4831, "lr": 3.2249273626079005e-05, "epoch": 1.8054162487462388, "percentage": 36.14, "elapsed_time": "4:00:02", "remaining_time": "7:04:04"}
451
+ {"current_steps": 451, "total_steps": 1245, "loss": 0.504, "lr": 3.2204878620751274e-05, "epoch": 1.8094282848545635, "percentage": 36.22, "elapsed_time": "4:00:30", "remaining_time": "7:03:25"}
452
+ {"current_steps": 452, "total_steps": 1245, "loss": 0.4905, "lr": 3.2160387587645515e-05, "epoch": 1.8134403209628887, "percentage": 36.31, "elapsed_time": "4:01:04", "remaining_time": "7:02:56"}
453
+ {"current_steps": 453, "total_steps": 1245, "loss": 0.5176, "lr": 3.21158008768164e-05, "epoch": 1.8174523570712138, "percentage": 36.39, "elapsed_time": "4:01:35", "remaining_time": "7:02:23"}
454
+ {"current_steps": 454, "total_steps": 1245, "loss": 0.5126, "lr": 3.207111883907143e-05, "epoch": 1.8214643931795385, "percentage": 36.47, "elapsed_time": "4:02:04", "remaining_time": "7:01:45"}
455
+ {"current_steps": 455, "total_steps": 1245, "loss": 0.4925, "lr": 3.202634182596812e-05, "epoch": 1.8254764292878636, "percentage": 36.55, "elapsed_time": "4:02:31", "remaining_time": "7:01:04"}
456
+ {"current_steps": 456, "total_steps": 1245, "loss": 0.5044, "lr": 3.1981470189811244e-05, "epoch": 1.8294884653961887, "percentage": 36.63, "elapsed_time": "4:03:06", "remaining_time": "7:00:38"}
457
+ {"current_steps": 457, "total_steps": 1245, "loss": 0.517, "lr": 3.1936504283650076e-05, "epoch": 1.8335005015045134, "percentage": 36.71, "elapsed_time": "4:03:41", "remaining_time": "7:00:11"}
458
+ {"current_steps": 458, "total_steps": 1245, "loss": 0.4957, "lr": 3.189144446127561e-05, "epoch": 1.8375125376128385, "percentage": 36.79, "elapsed_time": "4:04:09", "remaining_time": "6:59:32"}
459
+ {"current_steps": 459, "total_steps": 1245, "loss": 0.5239, "lr": 3.184629107721775e-05, "epoch": 1.8415245737211636, "percentage": 36.87, "elapsed_time": "4:04:37", "remaining_time": "6:58:53"}
460
+ {"current_steps": 460, "total_steps": 1245, "loss": 0.5049, "lr": 3.1801044486742567e-05, "epoch": 1.8455366098294883, "percentage": 36.95, "elapsed_time": "4:05:12", "remaining_time": "6:58:26"}
461
+ {"current_steps": 461, "total_steps": 1245, "loss": 0.493, "lr": 3.1755705045849465e-05, "epoch": 1.8495486459378134, "percentage": 37.03, "elapsed_time": "4:05:48", "remaining_time": "6:58:02"}
462
+ {"current_steps": 462, "total_steps": 1245, "loss": 0.5165, "lr": 3.1710273111268396e-05, "epoch": 1.8535606820461386, "percentage": 37.11, "elapsed_time": "4:06:14", "remaining_time": "6:57:20"}
463
+ {"current_steps": 463, "total_steps": 1245, "loss": 0.5104, "lr": 3.1664749040457054e-05, "epoch": 1.8575727181544632, "percentage": 37.19, "elapsed_time": "4:06:45", "remaining_time": "6:56:46"}
464
+ {"current_steps": 464, "total_steps": 1245, "loss": 0.5002, "lr": 3.161913319159806e-05, "epoch": 1.8615847542627884, "percentage": 37.27, "elapsed_time": "4:07:21", "remaining_time": "6:56:21"}
465
+ {"current_steps": 465, "total_steps": 1245, "loss": 0.4981, "lr": 3.157342592359612e-05, "epoch": 1.8655967903711135, "percentage": 37.35, "elapsed_time": "4:07:56", "remaining_time": "6:55:54"}
466
+ {"current_steps": 466, "total_steps": 1245, "loss": 0.5055, "lr": 3.152762759607526e-05, "epoch": 1.8696088264794382, "percentage": 37.43, "elapsed_time": "4:08:29", "remaining_time": "6:55:24"}
467
+ {"current_steps": 467, "total_steps": 1245, "loss": 0.5226, "lr": 3.148173856937594e-05, "epoch": 1.8736208625877633, "percentage": 37.51, "elapsed_time": "4:09:01", "remaining_time": "6:54:51"}
468
+ {"current_steps": 468, "total_steps": 1245, "loss": 0.5305, "lr": 3.1435759204552246e-05, "epoch": 1.8776328986960884, "percentage": 37.59, "elapsed_time": "4:09:35", "remaining_time": "6:54:22"}
469
+ {"current_steps": 469, "total_steps": 1245, "loss": 0.4969, "lr": 3.138968986336904e-05, "epoch": 1.881644934804413, "percentage": 37.67, "elapsed_time": "4:10:03", "remaining_time": "6:53:43"}
470
+ {"current_steps": 470, "total_steps": 1245, "loss": 0.5265, "lr": 3.1343530908299116e-05, "epoch": 1.8856569709127382, "percentage": 37.75, "elapsed_time": "4:10:35", "remaining_time": "6:53:11"}
471
+ {"current_steps": 471, "total_steps": 1245, "loss": 0.4925, "lr": 3.129728270252036e-05, "epoch": 1.8896690070210633, "percentage": 37.83, "elapsed_time": "4:11:05", "remaining_time": "6:52:36"}
472
+ {"current_steps": 472, "total_steps": 1245, "loss": 0.5333, "lr": 3.125094560991285e-05, "epoch": 1.893681043129388, "percentage": 37.91, "elapsed_time": "4:11:38", "remaining_time": "6:52:06"}
473
+ {"current_steps": 473, "total_steps": 1245, "loss": 0.5265, "lr": 3.1204519995056056e-05, "epoch": 1.8976930792377131, "percentage": 37.99, "elapsed_time": "4:12:06", "remaining_time": "6:51:29"}
474
+ {"current_steps": 474, "total_steps": 1245, "loss": 0.5172, "lr": 3.115800622322594e-05, "epoch": 1.9017051153460383, "percentage": 38.07, "elapsed_time": "4:12:35", "remaining_time": "6:50:52"}
475
+ {"current_steps": 475, "total_steps": 1245, "loss": 0.4986, "lr": 3.111140466039205e-05, "epoch": 1.905717151454363, "percentage": 38.15, "elapsed_time": "4:13:05", "remaining_time": "6:50:16"}
476
+ {"current_steps": 476, "total_steps": 1245, "loss": 0.5219, "lr": 3.10647156732147e-05, "epoch": 1.909729187562688, "percentage": 38.23, "elapsed_time": "4:13:38", "remaining_time": "6:49:46"}
477
+ {"current_steps": 477, "total_steps": 1245, "loss": 0.49, "lr": 3.101793962904205e-05, "epoch": 1.9137412236710132, "percentage": 38.31, "elapsed_time": "4:14:07", "remaining_time": "6:49:09"}
478
+ {"current_steps": 478, "total_steps": 1245, "loss": 0.5286, "lr": 3.097107689590723e-05, "epoch": 1.9177532597793379, "percentage": 38.39, "elapsed_time": "4:14:36", "remaining_time": "6:48:32"}
479
+ {"current_steps": 479, "total_steps": 1245, "loss": 0.499, "lr": 3.0924127842525415e-05, "epoch": 1.921765295887663, "percentage": 38.47, "elapsed_time": "4:15:12", "remaining_time": "6:48:07"}
480
+ {"current_steps": 480, "total_steps": 1245, "loss": 0.5078, "lr": 3.087709283829098e-05, "epoch": 1.925777331995988, "percentage": 38.55, "elapsed_time": "4:15:43", "remaining_time": "6:47:33"}
481
+ {"current_steps": 481, "total_steps": 1245, "loss": 0.5184, "lr": 3.082997225327452e-05, "epoch": 1.9297893681043128, "percentage": 38.63, "elapsed_time": "4:16:12", "remaining_time": "6:46:56"}
482
+ {"current_steps": 482, "total_steps": 1245, "loss": 0.5085, "lr": 3.078276645822001e-05, "epoch": 1.933801404212638, "percentage": 38.71, "elapsed_time": "4:16:46", "remaining_time": "6:46:27"}
483
+ {"current_steps": 483, "total_steps": 1245, "loss": 0.5086, "lr": 3.073547582454184e-05, "epoch": 1.937813440320963, "percentage": 38.8, "elapsed_time": "4:17:21", "remaining_time": "6:46:00"}
484
+ {"current_steps": 484, "total_steps": 1245, "loss": 0.5026, "lr": 3.0688100724321924e-05, "epoch": 1.9418254764292877, "percentage": 38.88, "elapsed_time": "4:17:49", "remaining_time": "6:45:23"}
485
+ {"current_steps": 485, "total_steps": 1245, "loss": 0.4971, "lr": 3.064064153030673e-05, "epoch": 1.9458375125376128, "percentage": 38.96, "elapsed_time": "4:18:18", "remaining_time": "6:44:45"}
486
+ {"current_steps": 486, "total_steps": 1245, "loss": 0.4921, "lr": 3.059309861590441e-05, "epoch": 1.949849548645938, "percentage": 39.04, "elapsed_time": "4:18:49", "remaining_time": "6:44:12"}
487
+ {"current_steps": 487, "total_steps": 1245, "loss": 0.5213, "lr": 3.0545472355181804e-05, "epoch": 1.9538615847542626, "percentage": 39.12, "elapsed_time": "4:19:18", "remaining_time": "6:43:35"}
488
+ {"current_steps": 488, "total_steps": 1245, "loss": 0.5103, "lr": 3.0497763122861516e-05, "epoch": 1.9578736208625878, "percentage": 39.2, "elapsed_time": "4:19:52", "remaining_time": "6:43:08"}
489
+ {"current_steps": 489, "total_steps": 1245, "loss": 0.5357, "lr": 3.0449971294318977e-05, "epoch": 1.9618856569709129, "percentage": 39.28, "elapsed_time": "4:20:24", "remaining_time": "6:42:34"}
490
+ {"current_steps": 490, "total_steps": 1245, "loss": 0.5342, "lr": 3.0402097245579493e-05, "epoch": 1.9658976930792376, "percentage": 39.36, "elapsed_time": "4:20:49", "remaining_time": "6:41:53"}
491
+ {"current_steps": 491, "total_steps": 1245, "loss": 0.5046, "lr": 3.0354141353315264e-05, "epoch": 1.9699097291875627, "percentage": 39.44, "elapsed_time": "4:21:23", "remaining_time": "6:41:24"}
492
+ {"current_steps": 492, "total_steps": 1245, "loss": 0.5144, "lr": 3.0306103994842435e-05, "epoch": 1.9739217652958878, "percentage": 39.52, "elapsed_time": "4:21:56", "remaining_time": "6:40:54"}
493
+ {"current_steps": 493, "total_steps": 1245, "loss": 0.514, "lr": 3.0257985548118127e-05, "epoch": 1.9779338014042125, "percentage": 39.6, "elapsed_time": "4:22:28", "remaining_time": "6:40:21"}
494
+ {"current_steps": 494, "total_steps": 1245, "loss": 0.4904, "lr": 3.0209786391737466e-05, "epoch": 1.9819458375125376, "percentage": 39.68, "elapsed_time": "4:22:58", "remaining_time": "6:39:46"}
495
+ {"current_steps": 495, "total_steps": 1245, "loss": 0.5057, "lr": 3.0161506904930592e-05, "epoch": 1.9859578736208627, "percentage": 39.76, "elapsed_time": "4:23:31", "remaining_time": "6:39:16"}
496
+ {"current_steps": 496, "total_steps": 1245, "loss": 0.5025, "lr": 3.0113147467559697e-05, "epoch": 1.9899699097291874, "percentage": 39.84, "elapsed_time": "4:24:06", "remaining_time": "6:38:50"}
497
+ {"current_steps": 497, "total_steps": 1245, "loss": 0.5145, "lr": 3.0064708460116007e-05, "epoch": 1.9939819458375125, "percentage": 39.92, "elapsed_time": "4:24:42", "remaining_time": "6:38:24"}
498
+ {"current_steps": 498, "total_steps": 1245, "loss": 0.5107, "lr": 3.0016190263716815e-05, "epoch": 1.9979939819458377, "percentage": 40.0, "elapsed_time": "4:25:15", "remaining_time": "6:37:53"}
499
+ {"current_steps": 499, "total_steps": 1245, "loss": 0.4323, "lr": 2.996759326010246e-05, "epoch": 2.0020060180541623, "percentage": 40.08, "elapsed_time": "4:27:43", "remaining_time": "6:40:14"}
500
+ {"current_steps": 500, "total_steps": 1245, "loss": 0.3692, "lr": 2.9918917831633362e-05, "epoch": 2.0060180541624875, "percentage": 40.16, "elapsed_time": "4:28:18", "remaining_time": "6:39:47"}
501
+ {"current_steps": 501, "total_steps": 1245, "loss": 0.3534, "lr": 2.987016436128694e-05, "epoch": 2.0100300902708126, "percentage": 40.24, "elapsed_time": "4:28:49", "remaining_time": "6:39:12"}
502
+ {"current_steps": 502, "total_steps": 1245, "loss": 0.3504, "lr": 2.982133323265469e-05, "epoch": 2.0140421263791373, "percentage": 40.32, "elapsed_time": "4:29:18", "remaining_time": "6:38:36"}
503
+ {"current_steps": 503, "total_steps": 1245, "loss": 0.3853, "lr": 2.9772424829939103e-05, "epoch": 2.0180541624874624, "percentage": 40.4, "elapsed_time": "4:29:54", "remaining_time": "6:38:09"}