liangyuch commited on
Commit
70e28ef
·
verified ·
1 Parent(s): 42fe294

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 sha256:40d325fe6ecbcf084cd8cb1c9d4aea3f476c74d7519c8d335eca781cfa51fc4b
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb7395f9a8769832c59d5267f088b81035df74506d1b79d4ff62acb06abb67c8
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:15da75a939dbe763d593795c67becfcf02ac40f8f62a0dd7c4be9c1cd7da0ecf
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20af83944a10ea6fbb8544e6dc0796154cad5fcb1c4364fd732de8442eab92dd
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:16e191ee5698a0dba9b0ee10874ee86611ff66c34e148f50528d34f3c1d34e50
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6906b5b2b1b4e743592c729a1754d86a1894c63ce556842e078fa39486874d2
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:c4ad1b367b6ce4be4585e17c209a4d3e313de2c6b1c9754d0593578208913571
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0a3ed6baa2e0922f92fc38d07ba7ac46249cf30d286332ee0e82ced84dd3000
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -194,3 +194,172 @@
194
  {"current_steps": 194, "total_steps": 519, "loss": 0.6169, "lr": 7.914381735794282e-06, "epoch": 1.1213872832369942, "percentage": 37.38, "elapsed_time": "0:20:48", "remaining_time": "0:34:51"}
195
  {"current_steps": 195, "total_steps": 519, "loss": 0.4591, "lr": 7.886984784545565e-06, "epoch": 1.1271676300578035, "percentage": 37.57, "elapsed_time": "0:20:52", "remaining_time": "0:34:41"}
196
  {"current_steps": 196, "total_steps": 519, "loss": 0.5845, "lr": 7.859457183469119e-06, "epoch": 1.1329479768786128, "percentage": 37.76, "elapsed_time": "0:20:57", "remaining_time": "0:34:32"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
194
  {"current_steps": 194, "total_steps": 519, "loss": 0.6169, "lr": 7.914381735794282e-06, "epoch": 1.1213872832369942, "percentage": 37.38, "elapsed_time": "0:20:48", "remaining_time": "0:34:51"}
195
  {"current_steps": 195, "total_steps": 519, "loss": 0.4591, "lr": 7.886984784545565e-06, "epoch": 1.1271676300578035, "percentage": 37.57, "elapsed_time": "0:20:52", "remaining_time": "0:34:41"}
196
  {"current_steps": 196, "total_steps": 519, "loss": 0.5845, "lr": 7.859457183469119e-06, "epoch": 1.1329479768786128, "percentage": 37.76, "elapsed_time": "0:20:57", "remaining_time": "0:34:32"}
197
+ {"current_steps": 197, "total_steps": 519, "loss": 0.5812, "lr": 7.831800178320153e-06, "epoch": 1.138728323699422, "percentage": 37.96, "elapsed_time": "0:21:02", "remaining_time": "0:34:23"}
198
+ {"current_steps": 198, "total_steps": 519, "loss": 0.6572, "lr": 7.804015020710028e-06, "epoch": 1.1445086705202312, "percentage": 38.15, "elapsed_time": "0:21:07", "remaining_time": "0:34:15"}
199
+ {"current_steps": 199, "total_steps": 519, "loss": 0.6755, "lr": 7.776102968049616e-06, "epoch": 1.1502890173410405, "percentage": 38.34, "elapsed_time": "0:21:13", "remaining_time": "0:34:08"}
200
+ {"current_steps": 200, "total_steps": 519, "loss": 0.554, "lr": 7.748065283492397e-06, "epoch": 1.1560693641618498, "percentage": 38.54, "elapsed_time": "0:21:18", "remaining_time": "0:33:59"}
201
+ {"current_steps": 201, "total_steps": 519, "loss": 0.5776, "lr": 7.719903235877289e-06, "epoch": 1.1618497109826589, "percentage": 38.73, "elapsed_time": "0:21:28", "remaining_time": "0:33:59"}
202
+ {"current_steps": 202, "total_steps": 519, "loss": 0.8012, "lr": 7.691618099671235e-06, "epoch": 1.1676300578034682, "percentage": 38.92, "elapsed_time": "0:21:36", "remaining_time": "0:33:54"}
203
+ {"current_steps": 203, "total_steps": 519, "loss": 0.8115, "lr": 7.663211154911523e-06, "epoch": 1.1734104046242775, "percentage": 39.11, "elapsed_time": "0:21:44", "remaining_time": "0:33:50"}
204
+ {"current_steps": 204, "total_steps": 519, "loss": 0.6142, "lr": 7.634683687147857e-06, "epoch": 1.1791907514450868, "percentage": 39.31, "elapsed_time": "0:21:49", "remaining_time": "0:33:41"}
205
+ {"current_steps": 205, "total_steps": 519, "loss": 0.7304, "lr": 7.606036987384185e-06, "epoch": 1.1849710982658959, "percentage": 39.5, "elapsed_time": "0:21:56", "remaining_time": "0:33:37"}
206
+ {"current_steps": 206, "total_steps": 519, "loss": 0.8352, "lr": 7.577272352020269e-06, "epoch": 1.1907514450867052, "percentage": 39.69, "elapsed_time": "0:22:02", "remaining_time": "0:33:29"}
207
+ {"current_steps": 207, "total_steps": 519, "loss": 0.645, "lr": 7.5483910827930186e-06, "epoch": 1.1965317919075145, "percentage": 39.88, "elapsed_time": "0:22:08", "remaining_time": "0:33:22"}
208
+ {"current_steps": 208, "total_steps": 519, "loss": 0.5238, "lr": 7.519394486717583e-06, "epoch": 1.2023121387283238, "percentage": 40.08, "elapsed_time": "0:22:13", "remaining_time": "0:33:13"}
209
+ {"current_steps": 209, "total_steps": 519, "loss": 0.74, "lr": 7.4902838760282024e-06, "epoch": 1.208092485549133, "percentage": 40.27, "elapsed_time": "0:22:19", "remaining_time": "0:33:07"}
210
+ {"current_steps": 210, "total_steps": 519, "loss": 0.5637, "lr": 7.461060568118822e-06, "epoch": 1.2138728323699421, "percentage": 40.46, "elapsed_time": "0:22:23", "remaining_time": "0:32:57"}
211
+ {"current_steps": 211, "total_steps": 519, "loss": 0.6129, "lr": 7.43172588548347e-06, "epoch": 1.2196531791907514, "percentage": 40.66, "elapsed_time": "0:22:31", "remaining_time": "0:32:53"}
212
+ {"current_steps": 212, "total_steps": 519, "loss": 0.7279, "lr": 7.402281155656415e-06, "epoch": 1.2254335260115607, "percentage": 40.85, "elapsed_time": "0:22:39", "remaining_time": "0:32:49"}
213
+ {"current_steps": 213, "total_steps": 519, "loss": 1.027, "lr": 7.3727277111520864e-06, "epoch": 1.2312138728323698, "percentage": 41.04, "elapsed_time": "0:22:47", "remaining_time": "0:32:44"}
214
+ {"current_steps": 214, "total_steps": 519, "loss": 0.5618, "lr": 7.343066889404769e-06, "epoch": 1.2369942196531791, "percentage": 41.23, "elapsed_time": "0:22:52", "remaining_time": "0:32:36"}
215
+ {"current_steps": 215, "total_steps": 519, "loss": 0.4959, "lr": 7.313300032708081e-06, "epoch": 1.2427745664739884, "percentage": 41.43, "elapsed_time": "0:22:57", "remaining_time": "0:32:27"}
216
+ {"current_steps": 216, "total_steps": 519, "loss": 0.6419, "lr": 7.283428488154227e-06, "epoch": 1.2485549132947977, "percentage": 41.62, "elapsed_time": "0:23:01", "remaining_time": "0:32:18"}
217
+ {"current_steps": 217, "total_steps": 519, "loss": 0.5864, "lr": 7.253453607573037e-06, "epoch": 1.254335260115607, "percentage": 41.81, "elapsed_time": "0:23:06", "remaining_time": "0:32:09"}
218
+ {"current_steps": 218, "total_steps": 519, "loss": 0.5748, "lr": 7.223376747470792e-06, "epoch": 1.260115606936416, "percentage": 42.0, "elapsed_time": "0:23:12", "remaining_time": "0:32:03"}
219
+ {"current_steps": 219, "total_steps": 519, "loss": 0.4877, "lr": 7.193199268968825e-06, "epoch": 1.2658959537572254, "percentage": 42.2, "elapsed_time": "0:23:17", "remaining_time": "0:31:54"}
220
+ {"current_steps": 220, "total_steps": 519, "loss": 0.488, "lr": 7.162922537741937e-06, "epoch": 1.2716763005780347, "percentage": 42.39, "elapsed_time": "0:23:21", "remaining_time": "0:31:44"}
221
+ {"current_steps": 221, "total_steps": 519, "loss": 0.496, "lr": 7.1325479239565875e-06, "epoch": 1.2774566473988438, "percentage": 42.58, "elapsed_time": "0:23:26", "remaining_time": "0:31:36"}
222
+ {"current_steps": 222, "total_steps": 519, "loss": 0.5555, "lr": 7.102076802208887e-06, "epoch": 1.2832369942196533, "percentage": 42.77, "elapsed_time": "0:23:33", "remaining_time": "0:31:30"}
223
+ {"current_steps": 223, "total_steps": 519, "loss": 0.6871, "lr": 7.071510551462395e-06, "epoch": 1.2890173410404624, "percentage": 42.97, "elapsed_time": "0:23:40", "remaining_time": "0:31:25"}
224
+ {"current_steps": 224, "total_steps": 519, "loss": 0.6442, "lr": 7.040850554985706e-06, "epoch": 1.2947976878612717, "percentage": 43.16, "elapsed_time": "0:23:47", "remaining_time": "0:31:20"}
225
+ {"current_steps": 225, "total_steps": 519, "loss": 0.6255, "lr": 7.01009820028986e-06, "epoch": 1.300578034682081, "percentage": 43.35, "elapsed_time": "0:23:53", "remaining_time": "0:31:13"}
226
+ {"current_steps": 226, "total_steps": 519, "loss": 0.7973, "lr": 6.9792548790655465e-06, "epoch": 1.30635838150289, "percentage": 43.55, "elapsed_time": "0:24:02", "remaining_time": "0:31:10"}
227
+ {"current_steps": 227, "total_steps": 519, "loss": 0.5421, "lr": 6.948321987120122e-06, "epoch": 1.3121387283236994, "percentage": 43.74, "elapsed_time": "0:24:07", "remaining_time": "0:31:02"}
228
+ {"current_steps": 228, "total_steps": 519, "loss": 0.431, "lr": 6.9173009243144485e-06, "epoch": 1.3179190751445087, "percentage": 43.93, "elapsed_time": "0:24:11", "remaining_time": "0:30:52"}
229
+ {"current_steps": 229, "total_steps": 519, "loss": 0.558, "lr": 6.886193094499537e-06, "epoch": 1.323699421965318, "percentage": 44.12, "elapsed_time": "0:24:15", "remaining_time": "0:30:43"}
230
+ {"current_steps": 230, "total_steps": 519, "loss": 0.5622, "lr": 6.854999905453022e-06, "epoch": 1.3294797687861273, "percentage": 44.32, "elapsed_time": "0:24:23", "remaining_time": "0:30:38"}
231
+ {"current_steps": 231, "total_steps": 519, "loss": 0.6397, "lr": 6.823722768815446e-06, "epoch": 1.3352601156069364, "percentage": 44.51, "elapsed_time": "0:24:28", "remaining_time": "0:30:31"}
232
+ {"current_steps": 232, "total_steps": 519, "loss": 0.6297, "lr": 6.792363100026383e-06, "epoch": 1.3410404624277457, "percentage": 44.7, "elapsed_time": "0:24:34", "remaining_time": "0:30:24"}
233
+ {"current_steps": 233, "total_steps": 519, "loss": 0.6461, "lr": 6.760922318260384e-06, "epoch": 1.346820809248555, "percentage": 44.89, "elapsed_time": "0:24:42", "remaining_time": "0:30:19"}
234
+ {"current_steps": 234, "total_steps": 519, "loss": 0.6102, "lr": 6.729401846362743e-06, "epoch": 1.352601156069364, "percentage": 45.09, "elapsed_time": "0:24:48", "remaining_time": "0:30:13"}
235
+ {"current_steps": 235, "total_steps": 519, "loss": 0.7174, "lr": 6.697803110785115e-06, "epoch": 1.3583815028901733, "percentage": 45.28, "elapsed_time": "0:24:51", "remaining_time": "0:30:02"}
236
+ {"current_steps": 236, "total_steps": 519, "loss": 0.4992, "lr": 6.666127541520958e-06, "epoch": 1.3641618497109826, "percentage": 45.47, "elapsed_time": "0:24:56", "remaining_time": "0:29:53"}
237
+ {"current_steps": 237, "total_steps": 519, "loss": 0.5653, "lr": 6.634376572040826e-06, "epoch": 1.369942196531792, "percentage": 45.66, "elapsed_time": "0:25:02", "remaining_time": "0:29:48"}
238
+ {"current_steps": 238, "total_steps": 519, "loss": 0.4559, "lr": 6.602551639227486e-06, "epoch": 1.3757225433526012, "percentage": 45.86, "elapsed_time": "0:25:05", "remaining_time": "0:29:37"}
239
+ {"current_steps": 239, "total_steps": 519, "loss": 0.8661, "lr": 6.570654183310901e-06, "epoch": 1.3815028901734103, "percentage": 46.05, "elapsed_time": "0:25:12", "remaining_time": "0:29:32"}
240
+ {"current_steps": 240, "total_steps": 519, "loss": 0.6934, "lr": 6.538685647803049e-06, "epoch": 1.3872832369942196, "percentage": 46.24, "elapsed_time": "0:25:19", "remaining_time": "0:29:26"}
241
+ {"current_steps": 241, "total_steps": 519, "loss": 0.5452, "lr": 6.506647479432604e-06, "epoch": 1.393063583815029, "percentage": 46.44, "elapsed_time": "0:25:25", "remaining_time": "0:29:20"}
242
+ {"current_steps": 242, "total_steps": 519, "loss": 0.539, "lr": 6.474541128079452e-06, "epoch": 1.3988439306358382, "percentage": 46.63, "elapsed_time": "0:25:29", "remaining_time": "0:29:10"}
243
+ {"current_steps": 243, "total_steps": 519, "loss": 0.5844, "lr": 6.442368046709087e-06, "epoch": 1.4046242774566475, "percentage": 46.82, "elapsed_time": "0:25:34", "remaining_time": "0:29:02"}
244
+ {"current_steps": 244, "total_steps": 519, "loss": 0.4744, "lr": 6.410129691306855e-06, "epoch": 1.4104046242774566, "percentage": 47.01, "elapsed_time": "0:25:38", "remaining_time": "0:28:53"}
245
+ {"current_steps": 245, "total_steps": 519, "loss": 0.7489, "lr": 6.377827520812061e-06, "epoch": 1.416184971098266, "percentage": 47.21, "elapsed_time": "0:25:46", "remaining_time": "0:28:49"}
246
+ {"current_steps": 246, "total_steps": 519, "loss": 0.7182, "lr": 6.34546299705195e-06, "epoch": 1.4219653179190752, "percentage": 47.4, "elapsed_time": "0:25:56", "remaining_time": "0:28:47"}
247
+ {"current_steps": 247, "total_steps": 519, "loss": 0.4366, "lr": 6.31303758467555e-06, "epoch": 1.4277456647398843, "percentage": 47.59, "elapsed_time": "0:26:00", "remaining_time": "0:28:37"}
248
+ {"current_steps": 248, "total_steps": 519, "loss": 0.6675, "lr": 6.280552751087384e-06, "epoch": 1.4335260115606936, "percentage": 47.78, "elapsed_time": "0:26:05", "remaining_time": "0:28:30"}
249
+ {"current_steps": 249, "total_steps": 519, "loss": 0.6042, "lr": 6.248009966381074e-06, "epoch": 1.439306358381503, "percentage": 47.98, "elapsed_time": "0:26:11", "remaining_time": "0:28:23"}
250
+ {"current_steps": 250, "total_steps": 519, "loss": 0.7219, "lr": 6.215410703272805e-06, "epoch": 1.4450867052023122, "percentage": 48.17, "elapsed_time": "0:26:17", "remaining_time": "0:28:16"}
251
+ {"current_steps": 251, "total_steps": 519, "loss": 0.4372, "lr": 6.182756437034677e-06, "epoch": 1.4508670520231215, "percentage": 48.36, "elapsed_time": "0:26:22", "remaining_time": "0:28:09"}
252
+ {"current_steps": 252, "total_steps": 519, "loss": 0.496, "lr": 6.150048645427944e-06, "epoch": 1.4566473988439306, "percentage": 48.55, "elapsed_time": "0:26:27", "remaining_time": "0:28:01"}
253
+ {"current_steps": 253, "total_steps": 519, "loss": 0.5174, "lr": 6.117288808636141e-06, "epoch": 1.4624277456647399, "percentage": 48.75, "elapsed_time": "0:26:33", "remaining_time": "0:27:55"}
254
+ {"current_steps": 254, "total_steps": 519, "loss": 0.645, "lr": 6.0844784091980955e-06, "epoch": 1.4682080924855492, "percentage": 48.94, "elapsed_time": "0:26:39", "remaining_time": "0:27:48"}
255
+ {"current_steps": 255, "total_steps": 519, "loss": 0.5536, "lr": 6.05161893194083e-06, "epoch": 1.4739884393063583, "percentage": 49.13, "elapsed_time": "0:26:46", "remaining_time": "0:27:42"}
256
+ {"current_steps": 256, "total_steps": 519, "loss": 0.6477, "lr": 6.018711863912381e-06, "epoch": 1.4797687861271676, "percentage": 49.33, "elapsed_time": "0:26:52", "remaining_time": "0:27:36"}
257
+ {"current_steps": 257, "total_steps": 519, "loss": 0.5217, "lr": 5.985758694314486e-06, "epoch": 1.4855491329479769, "percentage": 49.52, "elapsed_time": "0:27:00", "remaining_time": "0:27:32"}
258
+ {"current_steps": 258, "total_steps": 519, "loss": 0.6152, "lr": 5.9527609144352075e-06, "epoch": 1.4913294797687862, "percentage": 49.71, "elapsed_time": "0:27:05", "remaining_time": "0:27:24"}
259
+ {"current_steps": 259, "total_steps": 519, "loss": 0.5029, "lr": 5.9197200175814275e-06, "epoch": 1.4971098265895955, "percentage": 49.9, "elapsed_time": "0:27:12", "remaining_time": "0:27:18"}
260
+ {"current_steps": 260, "total_steps": 519, "loss": 0.5836, "lr": 5.8866374990112785e-06, "epoch": 1.5028901734104045, "percentage": 50.1, "elapsed_time": "0:27:18", "remaining_time": "0:27:11"}
261
+ {"current_steps": 261, "total_steps": 519, "loss": 0.8393, "lr": 5.853514855866481e-06, "epoch": 1.5086705202312138, "percentage": 50.29, "elapsed_time": "0:27:27", "remaining_time": "0:27:08"}
262
+ {"current_steps": 262, "total_steps": 519, "loss": 0.6995, "lr": 5.8203535871045735e-06, "epoch": 1.5144508670520231, "percentage": 50.48, "elapsed_time": "0:27:34", "remaining_time": "0:27:03"}
263
+ {"current_steps": 263, "total_steps": 519, "loss": 0.5861, "lr": 5.787155193431095e-06, "epoch": 1.5202312138728322, "percentage": 50.67, "elapsed_time": "0:27:40", "remaining_time": "0:26:56"}
264
+ {"current_steps": 264, "total_steps": 519, "loss": 0.5841, "lr": 5.75392117723166e-06, "epoch": 1.5260115606936417, "percentage": 50.87, "elapsed_time": "0:27:45", "remaining_time": "0:26:48"}
265
+ {"current_steps": 265, "total_steps": 519, "loss": 0.5483, "lr": 5.7206530425039785e-06, "epoch": 1.5317919075144508, "percentage": 51.06, "elapsed_time": "0:27:50", "remaining_time": "0:26:41"}
266
+ {"current_steps": 266, "total_steps": 519, "loss": 0.601, "lr": 5.687352294789776e-06, "epoch": 1.5375722543352601, "percentage": 51.25, "elapsed_time": "0:27:58", "remaining_time": "0:26:36"}
267
+ {"current_steps": 267, "total_steps": 519, "loss": 0.8358, "lr": 5.654020441106682e-06, "epoch": 1.5433526011560694, "percentage": 51.45, "elapsed_time": "0:28:04", "remaining_time": "0:26:30"}
268
+ {"current_steps": 268, "total_steps": 519, "loss": 0.5428, "lr": 5.620658989880011e-06, "epoch": 1.5491329479768785, "percentage": 51.64, "elapsed_time": "0:28:08", "remaining_time": "0:26:21"}
269
+ {"current_steps": 269, "total_steps": 519, "loss": 0.4783, "lr": 5.587269450874513e-06, "epoch": 1.5549132947976878, "percentage": 51.83, "elapsed_time": "0:28:13", "remaining_time": "0:26:13"}
270
+ {"current_steps": 270, "total_steps": 519, "loss": 0.6543, "lr": 5.5538533351260395e-06, "epoch": 1.560693641618497, "percentage": 52.02, "elapsed_time": "0:28:20", "remaining_time": "0:26:08"}
271
+ {"current_steps": 271, "total_steps": 519, "loss": 0.6379, "lr": 5.52041215487317e-06, "epoch": 1.5664739884393064, "percentage": 52.22, "elapsed_time": "0:28:27", "remaining_time": "0:26:02"}
272
+ {"current_steps": 272, "total_steps": 519, "loss": 0.5354, "lr": 5.486947423488774e-06, "epoch": 1.5722543352601157, "percentage": 52.41, "elapsed_time": "0:28:33", "remaining_time": "0:25:55"}
273
+ {"current_steps": 273, "total_steps": 519, "loss": 0.6359, "lr": 5.453460655411515e-06, "epoch": 1.5780346820809248, "percentage": 52.6, "elapsed_time": "0:28:37", "remaining_time": "0:25:47"}
274
+ {"current_steps": 274, "total_steps": 519, "loss": 0.442, "lr": 5.4199533660773276e-06, "epoch": 1.583815028901734, "percentage": 52.79, "elapsed_time": "0:28:40", "remaining_time": "0:25:38"}
275
+ {"current_steps": 275, "total_steps": 519, "loss": 0.6612, "lr": 5.3864270718508305e-06, "epoch": 1.5895953757225434, "percentage": 52.99, "elapsed_time": "0:28:48", "remaining_time": "0:25:33"}
276
+ {"current_steps": 276, "total_steps": 519, "loss": 0.7303, "lr": 5.352883289956701e-06, "epoch": 1.5953757225433525, "percentage": 53.18, "elapsed_time": "0:28:55", "remaining_time": "0:25:27"}
277
+ {"current_steps": 277, "total_steps": 519, "loss": 0.6552, "lr": 5.319323538411021e-06, "epoch": 1.601156069364162, "percentage": 53.37, "elapsed_time": "0:29:02", "remaining_time": "0:25:21"}
278
+ {"current_steps": 278, "total_steps": 519, "loss": 0.7785, "lr": 5.285749335952573e-06, "epoch": 1.606936416184971, "percentage": 53.56, "elapsed_time": "0:29:08", "remaining_time": "0:25:15"}
279
+ {"current_steps": 279, "total_steps": 519, "loss": 0.6865, "lr": 5.252162201974112e-06, "epoch": 1.6127167630057804, "percentage": 53.76, "elapsed_time": "0:29:16", "remaining_time": "0:25:10"}
280
+ {"current_steps": 280, "total_steps": 519, "loss": 0.645, "lr": 5.218563656453609e-06, "epoch": 1.6184971098265897, "percentage": 53.95, "elapsed_time": "0:29:19", "remaining_time": "0:25:01"}
281
+ {"current_steps": 281, "total_steps": 519, "loss": 0.512, "lr": 5.184955219885457e-06, "epoch": 1.6242774566473988, "percentage": 54.14, "elapsed_time": "0:29:22", "remaining_time": "0:24:52"}
282
+ {"current_steps": 282, "total_steps": 519, "loss": 0.694, "lr": 5.15133841321167e-06, "epoch": 1.630057803468208, "percentage": 54.34, "elapsed_time": "0:29:29", "remaining_time": "0:24:46"}
283
+ {"current_steps": 283, "total_steps": 519, "loss": 0.4881, "lr": 5.117714757753045e-06, "epoch": 1.6358381502890174, "percentage": 54.53, "elapsed_time": "0:29:33", "remaining_time": "0:24:39"}
284
+ {"current_steps": 284, "total_steps": 519, "loss": 0.5103, "lr": 5.084085775140324e-06, "epoch": 1.6416184971098264, "percentage": 54.72, "elapsed_time": "0:29:37", "remaining_time": "0:24:31"}
285
+ {"current_steps": 285, "total_steps": 519, "loss": 0.4349, "lr": 5.050452987245325e-06, "epoch": 1.647398843930636, "percentage": 54.91, "elapsed_time": "0:29:41", "remaining_time": "0:24:22"}
286
+ {"current_steps": 286, "total_steps": 519, "loss": 0.5836, "lr": 5.016817916112075e-06, "epoch": 1.653179190751445, "percentage": 55.11, "elapsed_time": "0:29:48", "remaining_time": "0:24:17"}
287
+ {"current_steps": 287, "total_steps": 519, "loss": 0.624, "lr": 4.9831820838879255e-06, "epoch": 1.6589595375722543, "percentage": 55.3, "elapsed_time": "0:29:54", "remaining_time": "0:24:10"}
288
+ {"current_steps": 288, "total_steps": 519, "loss": 0.6247, "lr": 4.949547012754676e-06, "epoch": 1.6647398843930636, "percentage": 55.49, "elapsed_time": "0:30:00", "remaining_time": "0:24:04"}
289
+ {"current_steps": 289, "total_steps": 519, "loss": 0.5317, "lr": 4.915914224859677e-06, "epoch": 1.6705202312138727, "percentage": 55.68, "elapsed_time": "0:30:07", "remaining_time": "0:23:58"}
290
+ {"current_steps": 290, "total_steps": 519, "loss": 0.8422, "lr": 4.882285242246958e-06, "epoch": 1.6763005780346822, "percentage": 55.88, "elapsed_time": "0:30:11", "remaining_time": "0:23:50"}
291
+ {"current_steps": 291, "total_steps": 519, "loss": 0.6278, "lr": 4.848661586788334e-06, "epoch": 1.6820809248554913, "percentage": 56.07, "elapsed_time": "0:30:19", "remaining_time": "0:23:45"}
292
+ {"current_steps": 292, "total_steps": 519, "loss": 0.7546, "lr": 4.815044780114544e-06, "epoch": 1.6878612716763006, "percentage": 56.26, "elapsed_time": "0:30:24", "remaining_time": "0:23:38"}
293
+ {"current_steps": 293, "total_steps": 519, "loss": 0.6156, "lr": 4.781436343546392e-06, "epoch": 1.69364161849711, "percentage": 56.45, "elapsed_time": "0:30:31", "remaining_time": "0:23:32"}
294
+ {"current_steps": 294, "total_steps": 519, "loss": 0.5466, "lr": 4.7478377980258885e-06, "epoch": 1.699421965317919, "percentage": 56.65, "elapsed_time": "0:30:37", "remaining_time": "0:23:26"}
295
+ {"current_steps": 295, "total_steps": 519, "loss": 0.5173, "lr": 4.714250664047428e-06, "epoch": 1.7052023121387283, "percentage": 56.84, "elapsed_time": "0:30:44", "remaining_time": "0:23:20"}
296
+ {"current_steps": 296, "total_steps": 519, "loss": 0.5619, "lr": 4.68067646158898e-06, "epoch": 1.7109826589595376, "percentage": 57.03, "elapsed_time": "0:30:49", "remaining_time": "0:23:13"}
297
+ {"current_steps": 297, "total_steps": 519, "loss": 0.5851, "lr": 4.647116710043302e-06, "epoch": 1.7167630057803467, "percentage": 57.23, "elapsed_time": "0:30:55", "remaining_time": "0:23:07"}
298
+ {"current_steps": 298, "total_steps": 519, "loss": 0.5937, "lr": 4.613572928149172e-06, "epoch": 1.7225433526011562, "percentage": 57.42, "elapsed_time": "0:31:01", "remaining_time": "0:23:00"}
299
+ {"current_steps": 299, "total_steps": 519, "loss": 0.6134, "lr": 4.580046633922675e-06, "epoch": 1.7283236994219653, "percentage": 57.61, "elapsed_time": "0:31:07", "remaining_time": "0:22:53"}
300
+ {"current_steps": 300, "total_steps": 519, "loss": 0.4924, "lr": 4.546539344588486e-06, "epoch": 1.7341040462427746, "percentage": 57.8, "elapsed_time": "0:31:13", "remaining_time": "0:22:47"}
301
+ {"current_steps": 301, "total_steps": 519, "loss": 0.5567, "lr": 4.513052576511227e-06, "epoch": 1.739884393063584, "percentage": 58.0, "elapsed_time": "0:31:18", "remaining_time": "0:22:40"}
302
+ {"current_steps": 302, "total_steps": 519, "loss": 0.5906, "lr": 4.47958784512683e-06, "epoch": 1.745664739884393, "percentage": 58.19, "elapsed_time": "0:31:24", "remaining_time": "0:22:34"}
303
+ {"current_steps": 303, "total_steps": 519, "loss": 0.5195, "lr": 4.446146664873961e-06, "epoch": 1.7514450867052023, "percentage": 58.38, "elapsed_time": "0:31:31", "remaining_time": "0:22:28"}
304
+ {"current_steps": 304, "total_steps": 519, "loss": 0.6441, "lr": 4.41273054912549e-06, "epoch": 1.7572254335260116, "percentage": 58.57, "elapsed_time": "0:31:37", "remaining_time": "0:22:21"}
305
+ {"current_steps": 305, "total_steps": 519, "loss": 0.6661, "lr": 4.379341010119992e-06, "epoch": 1.7630057803468207, "percentage": 58.77, "elapsed_time": "0:31:43", "remaining_time": "0:22:15"}
306
+ {"current_steps": 306, "total_steps": 519, "loss": 0.7531, "lr": 4.34597955889332e-06, "epoch": 1.7687861271676302, "percentage": 58.96, "elapsed_time": "0:31:51", "remaining_time": "0:22:10"}
307
+ {"current_steps": 307, "total_steps": 519, "loss": 0.6333, "lr": 4.312647705210226e-06, "epoch": 1.7745664739884393, "percentage": 59.15, "elapsed_time": "0:31:58", "remaining_time": "0:22:04"}
308
+ {"current_steps": 308, "total_steps": 519, "loss": 0.6065, "lr": 4.279346957496023e-06, "epoch": 1.7803468208092486, "percentage": 59.34, "elapsed_time": "0:32:01", "remaining_time": "0:21:56"}
309
+ {"current_steps": 309, "total_steps": 519, "loss": 0.593, "lr": 4.246078822768339e-06, "epoch": 1.7861271676300579, "percentage": 59.54, "elapsed_time": "0:32:06", "remaining_time": "0:21:49"}
310
+ {"current_steps": 310, "total_steps": 519, "loss": 0.7998, "lr": 4.212844806568906e-06, "epoch": 1.791907514450867, "percentage": 59.73, "elapsed_time": "0:32:14", "remaining_time": "0:21:44"}
311
+ {"current_steps": 311, "total_steps": 519, "loss": 0.4884, "lr": 4.17964641289543e-06, "epoch": 1.7976878612716765, "percentage": 59.92, "elapsed_time": "0:32:21", "remaining_time": "0:21:38"}
312
+ {"current_steps": 312, "total_steps": 519, "loss": 0.5413, "lr": 4.1464851441335215e-06, "epoch": 1.8034682080924855, "percentage": 60.12, "elapsed_time": "0:32:29", "remaining_time": "0:21:33"}
313
+ {"current_steps": 313, "total_steps": 519, "loss": 0.5272, "lr": 4.113362500988722e-06, "epoch": 1.8092485549132948, "percentage": 60.31, "elapsed_time": "0:32:33", "remaining_time": "0:21:25"}
314
+ {"current_steps": 314, "total_steps": 519, "loss": 0.5272, "lr": 4.080279982418574e-06, "epoch": 1.8150289017341041, "percentage": 60.5, "elapsed_time": "0:32:39", "remaining_time": "0:21:19"}
315
+ {"current_steps": 315, "total_steps": 519, "loss": 0.5185, "lr": 4.047239085564794e-06, "epoch": 1.8208092485549132, "percentage": 60.69, "elapsed_time": "0:32:46", "remaining_time": "0:21:13"}
316
+ {"current_steps": 316, "total_steps": 519, "loss": 0.5437, "lr": 4.014241305685514e-06, "epoch": 1.8265895953757225, "percentage": 60.89, "elapsed_time": "0:32:53", "remaining_time": "0:21:07"}
317
+ {"current_steps": 317, "total_steps": 519, "loss": 0.4712, "lr": 3.98128813608762e-06, "epoch": 1.8323699421965318, "percentage": 61.08, "elapsed_time": "0:32:59", "remaining_time": "0:21:01"}
318
+ {"current_steps": 318, "total_steps": 519, "loss": 0.5713, "lr": 3.948381068059171e-06, "epoch": 1.838150289017341, "percentage": 61.27, "elapsed_time": "0:33:06", "remaining_time": "0:20:55"}
319
+ {"current_steps": 319, "total_steps": 519, "loss": 0.4117, "lr": 3.915521590801907e-06, "epoch": 1.8439306358381504, "percentage": 61.46, "elapsed_time": "0:33:10", "remaining_time": "0:20:48"}
320
+ {"current_steps": 320, "total_steps": 519, "loss": 0.5622, "lr": 3.88271119136386e-06, "epoch": 1.8497109826589595, "percentage": 61.66, "elapsed_time": "0:33:17", "remaining_time": "0:20:42"}
321
+ {"current_steps": 321, "total_steps": 519, "loss": 0.7968, "lr": 3.849951354572057e-06, "epoch": 1.8554913294797688, "percentage": 61.85, "elapsed_time": "0:33:25", "remaining_time": "0:20:36"}
322
+ {"current_steps": 322, "total_steps": 519, "loss": 0.6582, "lr": 3.817243562965324e-06, "epoch": 1.861271676300578, "percentage": 62.04, "elapsed_time": "0:33:31", "remaining_time": "0:20:30"}
323
+ {"current_steps": 323, "total_steps": 519, "loss": 0.541, "lr": 3.7845892967271963e-06, "epoch": 1.8670520231213872, "percentage": 62.24, "elapsed_time": "0:33:37", "remaining_time": "0:20:24"}
324
+ {"current_steps": 324, "total_steps": 519, "loss": 0.4909, "lr": 3.7519900336189265e-06, "epoch": 1.8728323699421965, "percentage": 62.43, "elapsed_time": "0:33:42", "remaining_time": "0:20:17"}
325
+ {"current_steps": 325, "total_steps": 519, "loss": 0.6899, "lr": 3.7194472489126176e-06, "epoch": 1.8786127167630058, "percentage": 62.62, "elapsed_time": "0:33:51", "remaining_time": "0:20:12"}
326
+ {"current_steps": 326, "total_steps": 519, "loss": 0.5595, "lr": 3.686962415324452e-06, "epoch": 1.8843930635838149, "percentage": 62.81, "elapsed_time": "0:33:56", "remaining_time": "0:20:05"}
327
+ {"current_steps": 327, "total_steps": 519, "loss": 0.606, "lr": 3.6545370029480515e-06, "epoch": 1.8901734104046244, "percentage": 63.01, "elapsed_time": "0:34:01", "remaining_time": "0:19:58"}
328
+ {"current_steps": 328, "total_steps": 519, "loss": 0.7158, "lr": 3.6221724791879406e-06, "epoch": 1.8959537572254335, "percentage": 63.2, "elapsed_time": "0:34:07", "remaining_time": "0:19:52"}
329
+ {"current_steps": 329, "total_steps": 519, "loss": 0.7594, "lr": 3.5898703086931474e-06, "epoch": 1.9017341040462428, "percentage": 63.39, "elapsed_time": "0:34:12", "remaining_time": "0:19:45"}
330
+ {"current_steps": 330, "total_steps": 519, "loss": 0.4859, "lr": 3.557631953290914e-06, "epoch": 1.907514450867052, "percentage": 63.58, "elapsed_time": "0:34:18", "remaining_time": "0:19:38"}
331
+ {"current_steps": 331, "total_steps": 519, "loss": 0.7508, "lr": 3.5254588719205494e-06, "epoch": 1.9132947976878611, "percentage": 63.78, "elapsed_time": "0:34:27", "remaining_time": "0:19:34"}
332
+ {"current_steps": 332, "total_steps": 519, "loss": 0.6455, "lr": 3.4933525205673977e-06, "epoch": 1.9190751445086707, "percentage": 63.97, "elapsed_time": "0:34:34", "remaining_time": "0:19:28"}
333
+ {"current_steps": 333, "total_steps": 519, "loss": 0.5611, "lr": 3.461314352196952e-06, "epoch": 1.9248554913294798, "percentage": 64.16, "elapsed_time": "0:34:39", "remaining_time": "0:19:21"}
334
+ {"current_steps": 334, "total_steps": 519, "loss": 0.4856, "lr": 3.429345816689101e-06, "epoch": 1.930635838150289, "percentage": 64.35, "elapsed_time": "0:34:46", "remaining_time": "0:19:15"}
335
+ {"current_steps": 335, "total_steps": 519, "loss": 0.5274, "lr": 3.397448360772516e-06, "epoch": 1.9364161849710984, "percentage": 64.55, "elapsed_time": "0:34:49", "remaining_time": "0:19:07"}
336
+ {"current_steps": 336, "total_steps": 519, "loss": 0.6099, "lr": 3.365623427959175e-06, "epoch": 1.9421965317919074, "percentage": 64.74, "elapsed_time": "0:34:56", "remaining_time": "0:19:02"}
337
+ {"current_steps": 337, "total_steps": 519, "loss": 0.6163, "lr": 3.3338724584790427e-06, "epoch": 1.9479768786127167, "percentage": 64.93, "elapsed_time": "0:35:02", "remaining_time": "0:18:55"}
338
+ {"current_steps": 338, "total_steps": 519, "loss": 0.6332, "lr": 3.302196889214886e-06, "epoch": 1.953757225433526, "percentage": 65.13, "elapsed_time": "0:35:10", "remaining_time": "0:18:49"}
339
+ {"current_steps": 339, "total_steps": 519, "loss": 0.6922, "lr": 3.270598153637259e-06, "epoch": 1.9595375722543351, "percentage": 65.32, "elapsed_time": "0:35:15", "remaining_time": "0:18:43"}
340
+ {"current_steps": 340, "total_steps": 519, "loss": 0.5322, "lr": 3.239077681739618e-06, "epoch": 1.9653179190751446, "percentage": 65.51, "elapsed_time": "0:35:20", "remaining_time": "0:18:36"}
341
+ {"current_steps": 341, "total_steps": 519, "loss": 0.5402, "lr": 3.2076368999736175e-06, "epoch": 1.9710982658959537, "percentage": 65.7, "elapsed_time": "0:35:27", "remaining_time": "0:18:30"}
342
+ {"current_steps": 342, "total_steps": 519, "loss": 0.6172, "lr": 3.176277231184556e-06, "epoch": 1.976878612716763, "percentage": 65.9, "elapsed_time": "0:35:31", "remaining_time": "0:18:23"}
343
+ {"current_steps": 343, "total_steps": 519, "loss": 0.5905, "lr": 3.14500009454698e-06, "epoch": 1.9826589595375723, "percentage": 66.09, "elapsed_time": "0:35:37", "remaining_time": "0:18:17"}
344
+ {"current_steps": 344, "total_steps": 519, "loss": 0.5682, "lr": 3.1138069055004628e-06, "epoch": 1.9884393063583814, "percentage": 66.28, "elapsed_time": "0:35:44", "remaining_time": "0:18:10"}
345
+ {"current_steps": 345, "total_steps": 519, "loss": 0.5831, "lr": 3.0826990756855528e-06, "epoch": 1.9942196531791907, "percentage": 66.47, "elapsed_time": "0:35:48", "remaining_time": "0:18:03"}
346
+ {"current_steps": 346, "total_steps": 519, "loss": 0.4161, "lr": 3.0516780128798794e-06, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "0:35:51", "remaining_time": "0:17:55"}
347
+ {"current_steps": 347, "total_steps": 519, "loss": 0.6286, "lr": 3.020745120934455e-06, "epoch": 2.005780346820809, "percentage": 66.86, "elapsed_time": "0:37:23", "remaining_time": "0:18:32"}
348
+ {"current_steps": 348, "total_steps": 519, "loss": 0.4853, "lr": 2.989901799710142e-06, "epoch": 2.0115606936416186, "percentage": 67.05, "elapsed_time": "0:37:30", "remaining_time": "0:18:25"}
349
+ {"current_steps": 349, "total_steps": 519, "loss": 0.6472, "lr": 2.9591494450142957e-06, "epoch": 2.0173410404624277, "percentage": 67.24, "elapsed_time": "0:37:37", "remaining_time": "0:18:19"}
350
+ {"current_steps": 350, "total_steps": 519, "loss": 0.4739, "lr": 2.9284894485376057e-06, "epoch": 2.023121387283237, "percentage": 67.44, "elapsed_time": "0:37:40", "remaining_time": "0:18:11"}
351
+ {"current_steps": 351, "total_steps": 519, "loss": 0.3969, "lr": 2.8979231977911127e-06, "epoch": 2.0289017341040463, "percentage": 67.63, "elapsed_time": "0:37:44", "remaining_time": "0:18:03"}
352
+ {"current_steps": 352, "total_steps": 519, "loss": 0.6153, "lr": 2.8674520760434145e-06, "epoch": 2.0346820809248554, "percentage": 67.82, "elapsed_time": "0:37:51", "remaining_time": "0:17:57"}
353
+ {"current_steps": 353, "total_steps": 519, "loss": 0.5254, "lr": 2.8370774622580644e-06, "epoch": 2.040462427745665, "percentage": 68.02, "elapsed_time": "0:37:54", "remaining_time": "0:17:49"}
354
+ {"current_steps": 354, "total_steps": 519, "loss": 0.4817, "lr": 2.806800731031176e-06, "epoch": 2.046242774566474, "percentage": 68.21, "elapsed_time": "0:38:01", "remaining_time": "0:17:43"}
355
+ {"current_steps": 355, "total_steps": 519, "loss": 0.5555, "lr": 2.7766232525292104e-06, "epoch": 2.052023121387283, "percentage": 68.4, "elapsed_time": "0:38:08", "remaining_time": "0:17:37"}
356
+ {"current_steps": 356, "total_steps": 519, "loss": 0.5369, "lr": 2.746546392426963e-06, "epoch": 2.0578034682080926, "percentage": 68.59, "elapsed_time": "0:38:14", "remaining_time": "0:17:30"}
357
+ {"current_steps": 357, "total_steps": 519, "loss": 0.5443, "lr": 2.7165715118457735e-06, "epoch": 2.0635838150289016, "percentage": 68.79, "elapsed_time": "0:38:18", "remaining_time": "0:17:23"}
358
+ {"current_steps": 358, "total_steps": 519, "loss": 0.5849, "lr": 2.6866999672919198e-06, "epoch": 2.069364161849711, "percentage": 68.98, "elapsed_time": "0:38:26", "remaining_time": "0:17:17"}
359
+ {"current_steps": 359, "total_steps": 519, "loss": 0.6346, "lr": 2.656933110595233e-06, "epoch": 2.0751445086705202, "percentage": 69.17, "elapsed_time": "0:38:31", "remaining_time": "0:17:10"}
360
+ {"current_steps": 360, "total_steps": 519, "loss": 0.4533, "lr": 2.6272722888479152e-06, "epoch": 2.0809248554913293, "percentage": 69.36, "elapsed_time": "0:38:36", "remaining_time": "0:17:03"}
361
+ {"current_steps": 361, "total_steps": 519, "loss": 0.5008, "lr": 2.5977188443435874e-06, "epoch": 2.086705202312139, "percentage": 69.56, "elapsed_time": "0:38:39", "remaining_time": "0:16:55"}
362
+ {"current_steps": 362, "total_steps": 519, "loss": 0.5568, "lr": 2.5682741145165325e-06, "epoch": 2.092485549132948, "percentage": 69.75, "elapsed_time": "0:38:42", "remaining_time": "0:16:47"}
363
+ {"current_steps": 363, "total_steps": 519, "loss": 0.5211, "lr": 2.53893943188118e-06, "epoch": 2.098265895953757, "percentage": 69.94, "elapsed_time": "0:38:48", "remaining_time": "0:16:40"}
364
+ {"current_steps": 364, "total_steps": 519, "loss": 0.5555, "lr": 2.5097161239717975e-06, "epoch": 2.1040462427745665, "percentage": 70.13, "elapsed_time": "0:38:55", "remaining_time": "0:16:34"}
365
+ {"current_steps": 365, "total_steps": 519, "loss": 0.6461, "lr": 2.4806055132824186e-06, "epoch": 2.1098265895953756, "percentage": 70.33, "elapsed_time": "0:39:01", "remaining_time": "0:16:27"}