sedrickkeh commited on
Commit
07a2c16
·
verified ·
1 Parent(s): 171f065

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:f5f6f53eda40e8f9f7d41b54d1e314ed8ca8323233e509f4e51b876bdad8f3f0
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f11e54099794ae11456f3957bfce79a6ee075a2b5ce1509ec5603694095b00e1
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:97b46fc65db3a146665553f60cffd6760c389fca0c278cefd044e2987277472d
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e60410aab2a121ee30ee376e60bc0f1ec7660af1743d11361957d7c0a8e4b6d2
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:460bb808bf272c8ac1ca7c2c6c879f2f08e14306e3e084d0135615c60572ca64
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8de622084f990bc14bf437de2ea2d7f6b1c4e2bd5bed2881df2bf9de4a41f319
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:edbf49ac81206c76de63e48438e22ee10d89b0fa2ee10a59b67d98d7ab88d356
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:123d3cf9f470ab88be0bc7c7bcc3588f223827f581e7e438c6278aaacccdc584
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -173,3 +173,176 @@
173
  {"current_steps": 173, "total_steps": 519, "loss": 0.4422, "lr": 6.746416039582474e-05, "epoch": 0.9985569985569985, "percentage": 33.33, "elapsed_time": "2:32:01", "remaining_time": "5:04:03"}
174
  {"current_steps": 174, "total_steps": 519, "loss": 0.7579, "lr": 6.726790555959383e-05, "epoch": 1.0043290043290043, "percentage": 33.53, "elapsed_time": "2:34:09", "remaining_time": "5:05:39"}
175
  {"current_steps": 175, "total_steps": 519, "loss": 0.4294, "lr": 6.707041672061271e-05, "epoch": 1.0101010101010102, "percentage": 33.72, "elapsed_time": "2:35:03", "remaining_time": "5:04:47"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
173
  {"current_steps": 173, "total_steps": 519, "loss": 0.4422, "lr": 6.746416039582474e-05, "epoch": 0.9985569985569985, "percentage": 33.33, "elapsed_time": "2:32:01", "remaining_time": "5:04:03"}
174
  {"current_steps": 174, "total_steps": 519, "loss": 0.7579, "lr": 6.726790555959383e-05, "epoch": 1.0043290043290043, "percentage": 33.53, "elapsed_time": "2:34:09", "remaining_time": "5:05:39"}
175
  {"current_steps": 175, "total_steps": 519, "loss": 0.4294, "lr": 6.707041672061271e-05, "epoch": 1.0101010101010102, "percentage": 33.72, "elapsed_time": "2:35:03", "remaining_time": "5:04:47"}
176
+ {"current_steps": 176, "total_steps": 519, "loss": 0.4276, "lr": 6.687170281619302e-05, "epoch": 1.0158730158730158, "percentage": 33.91, "elapsed_time": "2:36:09", "remaining_time": "5:04:18"}
177
+ {"current_steps": 177, "total_steps": 519, "loss": 0.4262, "lr": 6.667177283908654e-05, "epoch": 1.0216450216450217, "percentage": 34.1, "elapsed_time": "2:37:00", "remaining_time": "5:03:23"}
178
+ {"current_steps": 178, "total_steps": 519, "loss": 0.4242, "lr": 6.647063583707802e-05, "epoch": 1.0274170274170273, "percentage": 34.3, "elapsed_time": "2:37:52", "remaining_time": "5:02:26"}
179
+ {"current_steps": 179, "total_steps": 519, "loss": 0.4237, "lr": 6.62683009125759e-05, "epoch": 1.0331890331890332, "percentage": 34.49, "elapsed_time": "2:38:44", "remaining_time": "5:01:31"}
180
+ {"current_steps": 180, "total_steps": 519, "loss": 0.4195, "lr": 6.606477722220036e-05, "epoch": 1.0389610389610389, "percentage": 34.68, "elapsed_time": "2:39:36", "remaining_time": "5:00:35"}
181
+ {"current_steps": 181, "total_steps": 519, "loss": 0.418, "lr": 6.586007397636885e-05, "epoch": 1.0447330447330447, "percentage": 34.87, "elapsed_time": "2:40:27", "remaining_time": "4:59:39"}
182
+ {"current_steps": 182, "total_steps": 519, "loss": 0.4257, "lr": 6.565420043887931e-05, "epoch": 1.0505050505050506, "percentage": 35.07, "elapsed_time": "2:41:19", "remaining_time": "4:58:43"}
183
+ {"current_steps": 183, "total_steps": 519, "loss": 0.4236, "lr": 6.544716592649105e-05, "epoch": 1.0562770562770563, "percentage": 35.26, "elapsed_time": "2:42:11", "remaining_time": "4:57:47"}
184
+ {"current_steps": 184, "total_steps": 519, "loss": 0.4232, "lr": 6.523897980850294e-05, "epoch": 1.0620490620490621, "percentage": 35.45, "elapsed_time": "2:43:03", "remaining_time": "4:56:51"}
185
+ {"current_steps": 185, "total_steps": 519, "loss": 0.4259, "lr": 6.502965150632955e-05, "epoch": 1.0678210678210678, "percentage": 35.65, "elapsed_time": "2:43:55", "remaining_time": "4:55:56"}
186
+ {"current_steps": 186, "total_steps": 519, "loss": 0.4258, "lr": 6.48191904930747e-05, "epoch": 1.0735930735930737, "percentage": 35.84, "elapsed_time": "2:44:47", "remaining_time": "4:55:01"}
187
+ {"current_steps": 187, "total_steps": 519, "loss": 0.421, "lr": 6.460760629310277e-05, "epoch": 1.0793650793650793, "percentage": 36.03, "elapsed_time": "2:45:38", "remaining_time": "4:54:05"}
188
+ {"current_steps": 188, "total_steps": 519, "loss": 0.4185, "lr": 6.439490848160778e-05, "epoch": 1.0851370851370852, "percentage": 36.22, "elapsed_time": "2:46:30", "remaining_time": "4:53:10"}
189
+ {"current_steps": 189, "total_steps": 519, "loss": 0.4285, "lr": 6.418110668417987e-05, "epoch": 1.0909090909090908, "percentage": 36.42, "elapsed_time": "2:47:22", "remaining_time": "4:52:14"}
190
+ {"current_steps": 190, "total_steps": 519, "loss": 0.4179, "lr": 6.396621057636989e-05, "epoch": 1.0966810966810967, "percentage": 36.61, "elapsed_time": "2:48:18", "remaining_time": "4:51:26"}
191
+ {"current_steps": 191, "total_steps": 519, "loss": 0.4189, "lr": 6.375022988325141e-05, "epoch": 1.1024531024531024, "percentage": 36.8, "elapsed_time": "2:49:24", "remaining_time": "4:50:54"}
192
+ {"current_steps": 192, "total_steps": 519, "loss": 0.4219, "lr": 6.353317437898067e-05, "epoch": 1.1082251082251082, "percentage": 36.99, "elapsed_time": "2:50:16", "remaining_time": "4:49:59"}
193
+ {"current_steps": 193, "total_steps": 519, "loss": 0.4209, "lr": 6.331505388635425e-05, "epoch": 1.113997113997114, "percentage": 37.19, "elapsed_time": "2:51:08", "remaining_time": "4:49:04"}
194
+ {"current_steps": 194, "total_steps": 519, "loss": 0.416, "lr": 6.309587827636452e-05, "epoch": 1.1197691197691197, "percentage": 37.38, "elapsed_time": "2:51:59", "remaining_time": "4:48:08"}
195
+ {"current_steps": 195, "total_steps": 519, "loss": 0.4173, "lr": 6.287565746775295e-05, "epoch": 1.1255411255411256, "percentage": 37.57, "elapsed_time": "2:52:51", "remaining_time": "4:47:13"}
196
+ {"current_steps": 196, "total_steps": 519, "loss": 0.4202, "lr": 6.265440142656122e-05, "epoch": 1.1313131313131313, "percentage": 37.76, "elapsed_time": "2:53:43", "remaining_time": "4:46:17"}
197
+ {"current_steps": 197, "total_steps": 519, "loss": 0.4131, "lr": 6.243212016568022e-05, "epoch": 1.1370851370851371, "percentage": 37.96, "elapsed_time": "2:54:35", "remaining_time": "4:45:22"}
198
+ {"current_steps": 198, "total_steps": 519, "loss": 0.4163, "lr": 6.220882374439692e-05, "epoch": 1.1428571428571428, "percentage": 38.15, "elapsed_time": "2:55:27", "remaining_time": "4:44:26"}
199
+ {"current_steps": 199, "total_steps": 519, "loss": 0.4107, "lr": 6.198452226793918e-05, "epoch": 1.1486291486291487, "percentage": 38.34, "elapsed_time": "2:56:18", "remaining_time": "4:43:31"}
200
+ {"current_steps": 200, "total_steps": 519, "loss": 0.4154, "lr": 6.175922588701831e-05, "epoch": 1.1544011544011543, "percentage": 38.54, "elapsed_time": "2:57:10", "remaining_time": "4:42:36"}
201
+ {"current_steps": 201, "total_steps": 519, "loss": 0.4173, "lr": 6.153294479736988e-05, "epoch": 1.1601731601731602, "percentage": 38.73, "elapsed_time": "2:58:02", "remaining_time": "4:41:41"}
202
+ {"current_steps": 202, "total_steps": 519, "loss": 0.4185, "lr": 6.130568923929218e-05, "epoch": 1.1659451659451658, "percentage": 38.92, "elapsed_time": "2:58:54", "remaining_time": "4:40:45"}
203
+ {"current_steps": 203, "total_steps": 519, "loss": 0.4159, "lr": 6.107746949718286e-05, "epoch": 1.1717171717171717, "percentage": 39.11, "elapsed_time": "2:59:46", "remaining_time": "4:39:50"}
204
+ {"current_steps": 204, "total_steps": 519, "loss": 0.4108, "lr": 6.084829589907348e-05, "epoch": 1.1774891774891776, "percentage": 39.31, "elapsed_time": "3:00:38", "remaining_time": "4:38:55"}
205
+ {"current_steps": 205, "total_steps": 519, "loss": 0.4091, "lr": 6.061817881616215e-05, "epoch": 1.1832611832611832, "percentage": 39.5, "elapsed_time": "3:01:35", "remaining_time": "4:38:09"}
206
+ {"current_steps": 206, "total_steps": 519, "loss": 0.4122, "lr": 6.038712866234415e-05, "epoch": 1.189033189033189, "percentage": 39.69, "elapsed_time": "3:02:38", "remaining_time": "4:37:30"}
207
+ {"current_steps": 207, "total_steps": 519, "loss": 0.4157, "lr": 6.015515589374066e-05, "epoch": 1.1948051948051948, "percentage": 39.88, "elapsed_time": "3:03:30", "remaining_time": "4:36:35"}
208
+ {"current_steps": 208, "total_steps": 519, "loss": 0.4151, "lr": 5.992227100822562e-05, "epoch": 1.2005772005772006, "percentage": 40.08, "elapsed_time": "3:04:22", "remaining_time": "4:35:40"}
209
+ {"current_steps": 209, "total_steps": 519, "loss": 0.4114, "lr": 5.968848454495058e-05, "epoch": 1.2063492063492063, "percentage": 40.27, "elapsed_time": "3:05:13", "remaining_time": "4:34:44"}
210
+ {"current_steps": 210, "total_steps": 519, "loss": 0.4111, "lr": 5.945380708386776e-05, "epoch": 1.2121212121212122, "percentage": 40.46, "elapsed_time": "3:06:05", "remaining_time": "4:33:49"}
211
+ {"current_steps": 211, "total_steps": 519, "loss": 0.4199, "lr": 5.921824924525132e-05, "epoch": 1.2178932178932178, "percentage": 40.66, "elapsed_time": "3:06:57", "remaining_time": "4:32:54"}
212
+ {"current_steps": 212, "total_steps": 519, "loss": 0.413, "lr": 5.898182168921669e-05, "epoch": 1.2236652236652237, "percentage": 40.85, "elapsed_time": "3:07:49", "remaining_time": "4:31:58"}
213
+ {"current_steps": 213, "total_steps": 519, "loss": 0.4055, "lr": 5.874453511523815e-05, "epoch": 1.2294372294372296, "percentage": 41.04, "elapsed_time": "3:08:40", "remaining_time": "4:31:03"}
214
+ {"current_steps": 214, "total_steps": 519, "loss": 0.4181, "lr": 5.8506400261664645e-05, "epoch": 1.2352092352092352, "percentage": 41.23, "elapsed_time": "3:09:32", "remaining_time": "4:30:08"}
215
+ {"current_steps": 215, "total_steps": 519, "loss": 0.4178, "lr": 5.826742790523382e-05, "epoch": 1.240981240981241, "percentage": 41.43, "elapsed_time": "3:10:24", "remaining_time": "4:29:13"}
216
+ {"current_steps": 216, "total_steps": 519, "loss": 0.4069, "lr": 5.80276288605843e-05, "epoch": 1.2467532467532467, "percentage": 41.62, "elapsed_time": "3:11:16", "remaining_time": "4:28:18"}
217
+ {"current_steps": 217, "total_steps": 519, "loss": 0.4185, "lr": 5.7787013979766334e-05, "epoch": 1.2525252525252526, "percentage": 41.81, "elapsed_time": "3:12:08", "remaining_time": "4:27:23"}
218
+ {"current_steps": 218, "total_steps": 519, "loss": 0.4118, "lr": 5.75455941517506e-05, "epoch": 1.2582972582972582, "percentage": 42.0, "elapsed_time": "3:12:59", "remaining_time": "4:26:28"}
219
+ {"current_steps": 219, "total_steps": 519, "loss": 0.4095, "lr": 5.7303380301935495e-05, "epoch": 1.2640692640692641, "percentage": 42.2, "elapsed_time": "3:13:51", "remaining_time": "4:25:33"}
220
+ {"current_steps": 220, "total_steps": 519, "loss": 0.4093, "lr": 5.70603833916527e-05, "epoch": 1.2698412698412698, "percentage": 42.39, "elapsed_time": "3:14:53", "remaining_time": "4:24:52"}
221
+ {"current_steps": 221, "total_steps": 519, "loss": 0.4044, "lr": 5.68166144176711e-05, "epoch": 1.2756132756132756, "percentage": 42.58, "elapsed_time": "3:15:54", "remaining_time": "4:24:10"}
222
+ {"current_steps": 222, "total_steps": 519, "loss": 0.4125, "lr": 5.657208441169916e-05, "epoch": 1.2813852813852815, "percentage": 42.77, "elapsed_time": "3:16:46", "remaining_time": "4:23:15"}
223
+ {"current_steps": 223, "total_steps": 519, "loss": 0.4101, "lr": 5.6326804439885645e-05, "epoch": 1.2871572871572872, "percentage": 42.97, "elapsed_time": "3:17:38", "remaining_time": "4:22:19"}
224
+ {"current_steps": 224, "total_steps": 519, "loss": 0.4041, "lr": 5.608078560231888e-05, "epoch": 1.2929292929292928, "percentage": 43.16, "elapsed_time": "3:18:29", "remaining_time": "4:21:24"}
225
+ {"current_steps": 225, "total_steps": 519, "loss": 0.4121, "lr": 5.583403903252437e-05, "epoch": 1.2987012987012987, "percentage": 43.35, "elapsed_time": "3:19:21", "remaining_time": "4:20:29"}
226
+ {"current_steps": 226, "total_steps": 519, "loss": 0.4059, "lr": 5.558657589696098e-05, "epoch": 1.3044733044733046, "percentage": 43.55, "elapsed_time": "3:20:13", "remaining_time": "4:19:34"}
227
+ {"current_steps": 227, "total_steps": 519, "loss": 0.4034, "lr": 5.533840739451559e-05, "epoch": 1.3102453102453102, "percentage": 43.74, "elapsed_time": "3:21:05", "remaining_time": "4:18:39"}
228
+ {"current_steps": 228, "total_steps": 519, "loss": 0.41, "lr": 5.5089544755996294e-05, "epoch": 1.316017316017316, "percentage": 43.93, "elapsed_time": "3:21:56", "remaining_time": "4:17:44"}
229
+ {"current_steps": 229, "total_steps": 519, "loss": 0.406, "lr": 5.483999924362417e-05, "epoch": 1.3217893217893217, "percentage": 44.12, "elapsed_time": "3:22:48", "remaining_time": "4:16:49"}
230
+ {"current_steps": 230, "total_steps": 519, "loss": 0.4046, "lr": 5.458978215052357e-05, "epoch": 1.3275613275613276, "percentage": 44.32, "elapsed_time": "3:23:40", "remaining_time": "4:15:55"}
231
+ {"current_steps": 231, "total_steps": 519, "loss": 0.4036, "lr": 5.433890480021107e-05, "epoch": 1.3333333333333333, "percentage": 44.51, "elapsed_time": "3:24:32", "remaining_time": "4:15:00"}
232
+ {"current_steps": 232, "total_steps": 519, "loss": 0.4027, "lr": 5.408737854608307e-05, "epoch": 1.3391053391053391, "percentage": 44.7, "elapsed_time": "3:25:24", "remaining_time": "4:14:05"}
233
+ {"current_steps": 233, "total_steps": 519, "loss": 0.4018, "lr": 5.3835214770901945e-05, "epoch": 1.3448773448773448, "percentage": 44.89, "elapsed_time": "3:26:15", "remaining_time": "4:13:10"}
234
+ {"current_steps": 234, "total_steps": 519, "loss": 0.4083, "lr": 5.358242488628092e-05, "epoch": 1.3506493506493507, "percentage": 45.09, "elapsed_time": "3:27:07", "remaining_time": "4:12:15"}
235
+ {"current_steps": 235, "total_steps": 519, "loss": 0.4058, "lr": 5.332902033216766e-05, "epoch": 1.3564213564213565, "percentage": 45.28, "elapsed_time": "3:28:10", "remaining_time": "4:11:34"}
236
+ {"current_steps": 236, "total_steps": 519, "loss": 0.4051, "lr": 5.3075012576326607e-05, "epoch": 1.3621933621933622, "percentage": 45.47, "elapsed_time": "3:29:08", "remaining_time": "4:10:46"}
237
+ {"current_steps": 237, "total_steps": 519, "loss": 0.3998, "lr": 5.2820413113819885e-05, "epoch": 1.3679653679653678, "percentage": 45.66, "elapsed_time": "3:29:59", "remaining_time": "4:09:52"}
238
+ {"current_steps": 238, "total_steps": 519, "loss": 0.404, "lr": 5.256523346648721e-05, "epoch": 1.3737373737373737, "percentage": 45.86, "elapsed_time": "3:30:51", "remaining_time": "4:08:57"}
239
+ {"current_steps": 239, "total_steps": 519, "loss": 0.4019, "lr": 5.230948518242439e-05, "epoch": 1.3795093795093796, "percentage": 46.05, "elapsed_time": "3:31:43", "remaining_time": "4:08:02"}
240
+ {"current_steps": 240, "total_steps": 519, "loss": 0.4076, "lr": 5.205317983546083e-05, "epoch": 1.3852813852813852, "percentage": 46.24, "elapsed_time": "3:32:35", "remaining_time": "4:07:07"}
241
+ {"current_steps": 241, "total_steps": 519, "loss": 0.4, "lr": 5.179632902463562e-05, "epoch": 1.391053391053391, "percentage": 46.44, "elapsed_time": "3:33:26", "remaining_time": "4:06:13"}
242
+ {"current_steps": 242, "total_steps": 519, "loss": 0.4179, "lr": 5.1538944373672694e-05, "epoch": 1.3968253968253967, "percentage": 46.63, "elapsed_time": "3:34:18", "remaining_time": "4:05:18"}
243
+ {"current_steps": 243, "total_steps": 519, "loss": 0.4097, "lr": 5.128103753045484e-05, "epoch": 1.4025974025974026, "percentage": 46.82, "elapsed_time": "3:35:10", "remaining_time": "4:04:23"}
244
+ {"current_steps": 244, "total_steps": 519, "loss": 0.4046, "lr": 5.1022620166496486e-05, "epoch": 1.4083694083694085, "percentage": 47.01, "elapsed_time": "3:36:02", "remaining_time": "4:03:29"}
245
+ {"current_steps": 245, "total_steps": 519, "loss": 0.4007, "lr": 5.07637039764156e-05, "epoch": 1.4141414141414141, "percentage": 47.21, "elapsed_time": "3:36:54", "remaining_time": "4:02:34"}
246
+ {"current_steps": 246, "total_steps": 519, "loss": 0.4113, "lr": 5.05043006774044e-05, "epoch": 1.4199134199134198, "percentage": 47.4, "elapsed_time": "3:37:45", "remaining_time": "4:01:39"}
247
+ {"current_steps": 247, "total_steps": 519, "loss": 0.4063, "lr": 5.024442200869907e-05, "epoch": 1.4256854256854257, "percentage": 47.59, "elapsed_time": "3:38:37", "remaining_time": "4:00:45"}
248
+ {"current_steps": 248, "total_steps": 519, "loss": 0.4044, "lr": 4.9984079731048594e-05, "epoch": 1.4314574314574315, "percentage": 47.78, "elapsed_time": "3:39:29", "remaining_time": "3:59:50"}
249
+ {"current_steps": 249, "total_steps": 519, "loss": 0.4021, "lr": 4.972328562618244e-05, "epoch": 1.4372294372294372, "percentage": 47.98, "elapsed_time": "3:40:22", "remaining_time": "3:58:57"}
250
+ {"current_steps": 250, "total_steps": 519, "loss": 0.3967, "lr": 4.946205149627742e-05, "epoch": 1.443001443001443, "percentage": 48.17, "elapsed_time": "3:41:27", "remaining_time": "3:58:16"}
251
+ {"current_steps": 251, "total_steps": 519, "loss": 0.4055, "lr": 4.920038916342355e-05, "epoch": 1.4487734487734487, "percentage": 48.36, "elapsed_time": "3:42:23", "remaining_time": "3:57:27"}
252
+ {"current_steps": 252, "total_steps": 519, "loss": 0.3919, "lr": 4.893831046908913e-05, "epoch": 1.4545454545454546, "percentage": 48.55, "elapsed_time": "3:43:15", "remaining_time": "3:56:32"}
253
+ {"current_steps": 253, "total_steps": 519, "loss": 0.4066, "lr": 4.8675827273584764e-05, "epoch": 1.4603174603174602, "percentage": 48.75, "elapsed_time": "3:44:07", "remaining_time": "3:55:38"}
254
+ {"current_steps": 254, "total_steps": 519, "loss": 0.409, "lr": 4.841295145552664e-05, "epoch": 1.466089466089466, "percentage": 48.94, "elapsed_time": "3:44:58", "remaining_time": "3:54:43"}
255
+ {"current_steps": 255, "total_steps": 519, "loss": 0.4068, "lr": 4.8149694911299046e-05, "epoch": 1.4718614718614718, "percentage": 49.13, "elapsed_time": "3:45:50", "remaining_time": "3:53:48"}
256
+ {"current_steps": 256, "total_steps": 519, "loss": 0.4008, "lr": 4.788606955451589e-05, "epoch": 1.4776334776334776, "percentage": 49.33, "elapsed_time": "3:46:42", "remaining_time": "3:52:54"}
257
+ {"current_steps": 257, "total_steps": 519, "loss": 0.4045, "lr": 4.762208731548166e-05, "epoch": 1.4834054834054835, "percentage": 49.52, "elapsed_time": "3:47:34", "remaining_time": "3:51:59"}
258
+ {"current_steps": 258, "total_steps": 519, "loss": 0.3988, "lr": 4.735776014065142e-05, "epoch": 1.4891774891774892, "percentage": 49.71, "elapsed_time": "3:48:25", "remaining_time": "3:51:05"}
259
+ {"current_steps": 259, "total_steps": 519, "loss": 0.3978, "lr": 4.709309999209023e-05, "epoch": 1.494949494949495, "percentage": 49.9, "elapsed_time": "3:49:17", "remaining_time": "3:50:11"}
260
+ {"current_steps": 260, "total_steps": 519, "loss": 0.3936, "lr": 4.682811884693185e-05, "epoch": 1.5007215007215007, "percentage": 50.1, "elapsed_time": "3:50:09", "remaining_time": "3:49:16"}
261
+ {"current_steps": 261, "total_steps": 519, "loss": 0.3969, "lr": 4.656282869683659e-05, "epoch": 1.5064935064935066, "percentage": 50.29, "elapsed_time": "3:51:01", "remaining_time": "3:48:22"}
262
+ {"current_steps": 262, "total_steps": 519, "loss": 0.3992, "lr": 4.629724154744876e-05, "epoch": 1.5122655122655124, "percentage": 50.48, "elapsed_time": "3:51:53", "remaining_time": "3:47:27"}
263
+ {"current_steps": 263, "total_steps": 519, "loss": 0.3947, "lr": 4.603136941785328e-05, "epoch": 1.518037518037518, "percentage": 50.67, "elapsed_time": "3:52:45", "remaining_time": "3:46:33"}
264
+ {"current_steps": 264, "total_steps": 519, "loss": 0.3984, "lr": 4.576522434003183e-05, "epoch": 1.5238095238095237, "percentage": 50.87, "elapsed_time": "3:53:39", "remaining_time": "3:45:41"}
265
+ {"current_steps": 265, "total_steps": 519, "loss": 0.3915, "lr": 4.549881835831821e-05, "epoch": 1.5295815295815296, "percentage": 51.06, "elapsed_time": "3:54:46", "remaining_time": "3:45:01"}
266
+ {"current_steps": 266, "total_steps": 519, "loss": 0.3952, "lr": 4.523216352885345e-05, "epoch": 1.5353535353535355, "percentage": 51.25, "elapsed_time": "3:55:39", "remaining_time": "3:44:08"}
267
+ {"current_steps": 267, "total_steps": 519, "loss": 0.3976, "lr": 4.496527191904009e-05, "epoch": 1.5411255411255411, "percentage": 51.45, "elapsed_time": "3:56:31", "remaining_time": "3:43:13"}
268
+ {"current_steps": 268, "total_steps": 519, "loss": 0.4057, "lr": 4.4698155606996104e-05, "epoch": 1.5468975468975468, "percentage": 51.64, "elapsed_time": "3:57:22", "remaining_time": "3:42:19"}
269
+ {"current_steps": 269, "total_steps": 519, "loss": 0.4074, "lr": 4.4430826681008316e-05, "epoch": 1.5526695526695526, "percentage": 51.83, "elapsed_time": "3:58:14", "remaining_time": "3:41:25"}
270
+ {"current_steps": 270, "total_steps": 519, "loss": 0.3951, "lr": 4.416329723898536e-05, "epoch": 1.5584415584415585, "percentage": 52.02, "elapsed_time": "3:59:06", "remaining_time": "3:40:30"}
271
+ {"current_steps": 271, "total_steps": 519, "loss": 0.394, "lr": 4.389557938791019e-05, "epoch": 1.5642135642135642, "percentage": 52.22, "elapsed_time": "3:59:58", "remaining_time": "3:39:36"}
272
+ {"current_steps": 272, "total_steps": 519, "loss": 0.3993, "lr": 4.362768524329212e-05, "epoch": 1.56998556998557, "percentage": 52.41, "elapsed_time": "4:00:49", "remaining_time": "3:38:41"}
273
+ {"current_steps": 273, "total_steps": 519, "loss": 0.4013, "lr": 4.335962692861862e-05, "epoch": 1.5757575757575757, "percentage": 52.6, "elapsed_time": "4:01:41", "remaining_time": "3:37:47"}
274
+ {"current_steps": 274, "total_steps": 519, "loss": 0.3932, "lr": 4.3091416574806644e-05, "epoch": 1.5815295815295816, "percentage": 52.79, "elapsed_time": "4:02:33", "remaining_time": "3:36:53"}
275
+ {"current_steps": 275, "total_steps": 519, "loss": 0.4066, "lr": 4.2823066319653606e-05, "epoch": 1.5873015873015874, "percentage": 52.99, "elapsed_time": "4:03:25", "remaining_time": "3:35:59"}
276
+ {"current_steps": 276, "total_steps": 519, "loss": 0.3953, "lr": 4.2554588307288166e-05, "epoch": 1.593073593073593, "percentage": 53.18, "elapsed_time": "4:04:17", "remaining_time": "3:35:04"}
277
+ {"current_steps": 277, "total_steps": 519, "loss": 0.3908, "lr": 4.2285994687620586e-05, "epoch": 1.5988455988455987, "percentage": 53.37, "elapsed_time": "4:05:09", "remaining_time": "3:34:10"}
278
+ {"current_steps": 278, "total_steps": 519, "loss": 0.4048, "lr": 4.20172976157929e-05, "epoch": 1.6046176046176046, "percentage": 53.56, "elapsed_time": "4:06:00", "remaining_time": "3:33:16"}
279
+ {"current_steps": 279, "total_steps": 519, "loss": 0.3994, "lr": 4.174850925162887e-05, "epoch": 1.6103896103896105, "percentage": 53.76, "elapsed_time": "4:06:57", "remaining_time": "3:32:26"}
280
+ {"current_steps": 280, "total_steps": 519, "loss": 0.3954, "lr": 4.1479641759083653e-05, "epoch": 1.6161616161616161, "percentage": 53.95, "elapsed_time": "4:08:02", "remaining_time": "3:31:43"}
281
+ {"current_steps": 281, "total_steps": 519, "loss": 0.3934, "lr": 4.121070730569336e-05, "epoch": 1.6219336219336218, "percentage": 54.14, "elapsed_time": "4:08:55", "remaining_time": "3:30:50"}
282
+ {"current_steps": 282, "total_steps": 519, "loss": 0.3929, "lr": 4.094171806202436e-05, "epoch": 1.6277056277056277, "percentage": 54.34, "elapsed_time": "4:09:47", "remaining_time": "3:29:55"}
283
+ {"current_steps": 283, "total_steps": 519, "loss": 0.3921, "lr": 4.067268620112259e-05, "epoch": 1.6334776334776335, "percentage": 54.53, "elapsed_time": "4:10:39", "remaining_time": "3:29:01"}
284
+ {"current_steps": 284, "total_steps": 519, "loss": 0.3863, "lr": 4.04036238979626e-05, "epoch": 1.6392496392496394, "percentage": 54.72, "elapsed_time": "4:11:30", "remaining_time": "3:28:07"}
285
+ {"current_steps": 285, "total_steps": 519, "loss": 0.3903, "lr": 4.01345433288966e-05, "epoch": 1.645021645021645, "percentage": 54.91, "elapsed_time": "4:12:22", "remaining_time": "3:27:12"}
286
+ {"current_steps": 286, "total_steps": 519, "loss": 0.3941, "lr": 3.9865456671103404e-05, "epoch": 1.6507936507936507, "percentage": 55.11, "elapsed_time": "4:13:14", "remaining_time": "3:26:18"}
287
+ {"current_steps": 287, "total_steps": 519, "loss": 0.3914, "lr": 3.959637610203741e-05, "epoch": 1.6565656565656566, "percentage": 55.3, "elapsed_time": "4:14:06", "remaining_time": "3:25:24"}
288
+ {"current_steps": 288, "total_steps": 519, "loss": 0.3865, "lr": 3.932731379887742e-05, "epoch": 1.6623376623376624, "percentage": 55.49, "elapsed_time": "4:14:58", "remaining_time": "3:24:30"}
289
+ {"current_steps": 289, "total_steps": 519, "loss": 0.3946, "lr": 3.905828193797566e-05, "epoch": 1.668109668109668, "percentage": 55.68, "elapsed_time": "4:15:50", "remaining_time": "3:23:36"}
290
+ {"current_steps": 290, "total_steps": 519, "loss": 0.3905, "lr": 3.878929269430667e-05, "epoch": 1.6738816738816737, "percentage": 55.88, "elapsed_time": "4:16:41", "remaining_time": "3:22:42"}
291
+ {"current_steps": 291, "total_steps": 519, "loss": 0.3893, "lr": 3.852035824091635e-05, "epoch": 1.6796536796536796, "percentage": 56.07, "elapsed_time": "4:17:33", "remaining_time": "3:21:48"}
292
+ {"current_steps": 292, "total_steps": 519, "loss": 0.3942, "lr": 3.8251490748371136e-05, "epoch": 1.6854256854256855, "percentage": 56.26, "elapsed_time": "4:18:25", "remaining_time": "3:20:53"}
293
+ {"current_steps": 293, "total_steps": 519, "loss": 0.3901, "lr": 3.798270238420711e-05, "epoch": 1.6911976911976911, "percentage": 56.45, "elapsed_time": "4:19:17", "remaining_time": "3:19:59"}
294
+ {"current_steps": 294, "total_steps": 519, "loss": 0.3906, "lr": 3.771400531237942e-05, "epoch": 1.696969696969697, "percentage": 56.65, "elapsed_time": "4:20:15", "remaining_time": "3:19:10"}
295
+ {"current_steps": 295, "total_steps": 519, "loss": 0.3954, "lr": 3.744541169271184e-05, "epoch": 1.7027417027417027, "percentage": 56.84, "elapsed_time": "4:21:20", "remaining_time": "3:18:26"}
296
+ {"current_steps": 296, "total_steps": 519, "loss": 0.3943, "lr": 3.7176933680346414e-05, "epoch": 1.7085137085137085, "percentage": 57.03, "elapsed_time": "4:22:13", "remaining_time": "3:17:33"}
297
+ {"current_steps": 297, "total_steps": 519, "loss": 0.3927, "lr": 3.6908583425193376e-05, "epoch": 1.7142857142857144, "percentage": 57.23, "elapsed_time": "4:23:05", "remaining_time": "3:16:39"}
298
+ {"current_steps": 298, "total_steps": 519, "loss": 0.3899, "lr": 3.66403730713814e-05, "epoch": 1.72005772005772, "percentage": 57.42, "elapsed_time": "4:23:57", "remaining_time": "3:15:44"}
299
+ {"current_steps": 299, "total_steps": 519, "loss": 0.3893, "lr": 3.637231475670789e-05, "epoch": 1.7258297258297257, "percentage": 57.61, "elapsed_time": "4:24:48", "remaining_time": "3:14:50"}
300
+ {"current_steps": 300, "total_steps": 519, "loss": 0.3785, "lr": 3.6104420612089814e-05, "epoch": 1.7316017316017316, "percentage": 57.8, "elapsed_time": "4:25:40", "remaining_time": "3:13:56"}
301
+ {"current_steps": 301, "total_steps": 519, "loss": 0.3933, "lr": 3.583670276101464e-05, "epoch": 1.7373737373737375, "percentage": 58.0, "elapsed_time": "4:26:32", "remaining_time": "3:13:02"}
302
+ {"current_steps": 302, "total_steps": 519, "loss": 0.3972, "lr": 3.556917331899169e-05, "epoch": 1.743145743145743, "percentage": 58.19, "elapsed_time": "4:27:24", "remaining_time": "3:12:08"}
303
+ {"current_steps": 303, "total_steps": 519, "loss": 0.3932, "lr": 3.530184439300392e-05, "epoch": 1.7489177489177488, "percentage": 58.38, "elapsed_time": "4:28:16", "remaining_time": "3:11:14"}
304
+ {"current_steps": 304, "total_steps": 519, "loss": 0.388, "lr": 3.503472808095993e-05, "epoch": 1.7546897546897546, "percentage": 58.57, "elapsed_time": "4:29:07", "remaining_time": "3:10:20"}
305
+ {"current_steps": 305, "total_steps": 519, "loss": 0.3871, "lr": 3.476783647114656e-05, "epoch": 1.7604617604617605, "percentage": 58.77, "elapsed_time": "4:29:59", "remaining_time": "3:09:26"}
306
+ {"current_steps": 306, "total_steps": 519, "loss": 0.4022, "lr": 3.4501181641681806e-05, "epoch": 1.7662337662337664, "percentage": 58.96, "elapsed_time": "4:30:51", "remaining_time": "3:08:32"}
307
+ {"current_steps": 307, "total_steps": 519, "loss": 0.387, "lr": 3.4234775659968185e-05, "epoch": 1.772005772005772, "percentage": 59.15, "elapsed_time": "4:31:43", "remaining_time": "3:07:38"}
308
+ {"current_steps": 308, "total_steps": 519, "loss": 0.3954, "lr": 3.396863058214671e-05, "epoch": 1.7777777777777777, "percentage": 59.34, "elapsed_time": "4:32:34", "remaining_time": "3:06:44"}
309
+ {"current_steps": 309, "total_steps": 519, "loss": 0.3876, "lr": 3.370275845255125e-05, "epoch": 1.7835497835497836, "percentage": 59.54, "elapsed_time": "4:33:34", "remaining_time": "3:05:55"}
310
+ {"current_steps": 310, "total_steps": 519, "loss": 0.3844, "lr": 3.343717130316344e-05, "epoch": 1.7893217893217894, "percentage": 59.73, "elapsed_time": "4:34:37", "remaining_time": "3:05:09"}
311
+ {"current_steps": 311, "total_steps": 519, "loss": 0.3869, "lr": 3.317188115306817e-05, "epoch": 1.795093795093795, "percentage": 59.92, "elapsed_time": "4:35:29", "remaining_time": "3:04:15"}
312
+ {"current_steps": 312, "total_steps": 519, "loss": 0.3953, "lr": 3.290690000790978e-05, "epoch": 1.8008658008658007, "percentage": 60.12, "elapsed_time": "4:36:21", "remaining_time": "3:03:21"}
313
+ {"current_steps": 313, "total_steps": 519, "loss": 0.3893, "lr": 3.2642239859348594e-05, "epoch": 1.8066378066378066, "percentage": 60.31, "elapsed_time": "4:37:13", "remaining_time": "3:02:27"}
314
+ {"current_steps": 314, "total_steps": 519, "loss": 0.3847, "lr": 3.237791268451835e-05, "epoch": 1.8124098124098125, "percentage": 60.5, "elapsed_time": "4:38:05", "remaining_time": "3:01:33"}
315
+ {"current_steps": 315, "total_steps": 519, "loss": 0.4011, "lr": 3.211393044548411e-05, "epoch": 1.8181818181818183, "percentage": 60.69, "elapsed_time": "4:38:57", "remaining_time": "3:00:39"}
316
+ {"current_steps": 316, "total_steps": 519, "loss": 0.3806, "lr": 3.185030508870096e-05, "epoch": 1.823953823953824, "percentage": 60.89, "elapsed_time": "4:39:48", "remaining_time": "2:59:45"}
317
+ {"current_steps": 317, "total_steps": 519, "loss": 0.385, "lr": 3.158704854447337e-05, "epoch": 1.8297258297258296, "percentage": 61.08, "elapsed_time": "4:40:40", "remaining_time": "2:58:51"}
318
+ {"current_steps": 318, "total_steps": 519, "loss": 0.3879, "lr": 3.1324172726415256e-05, "epoch": 1.8354978354978355, "percentage": 61.27, "elapsed_time": "4:41:32", "remaining_time": "2:57:57"}
319
+ {"current_steps": 319, "total_steps": 519, "loss": 0.3892, "lr": 3.106168953091088e-05, "epoch": 1.8412698412698414, "percentage": 61.46, "elapsed_time": "4:42:24", "remaining_time": "2:57:03"}
320
+ {"current_steps": 320, "total_steps": 519, "loss": 0.3821, "lr": 3.079961083657646e-05, "epoch": 1.847041847041847, "percentage": 61.66, "elapsed_time": "4:43:16", "remaining_time": "2:56:09"}
321
+ {"current_steps": 321, "total_steps": 519, "loss": 0.391, "lr": 3.0537948503722595e-05, "epoch": 1.8528138528138527, "percentage": 61.85, "elapsed_time": "4:44:08", "remaining_time": "2:55:15"}
322
+ {"current_steps": 322, "total_steps": 519, "loss": 0.3896, "lr": 3.027671437381757e-05, "epoch": 1.8585858585858586, "percentage": 62.04, "elapsed_time": "4:44:59", "remaining_time": "2:54:21"}
323
+ {"current_steps": 323, "total_steps": 519, "loss": 0.3927, "lr": 3.0015920268951412e-05, "epoch": 1.8643578643578644, "percentage": 62.24, "elapsed_time": "4:45:52", "remaining_time": "2:53:28"}
324
+ {"current_steps": 324, "total_steps": 519, "loss": 0.3837, "lr": 2.975557799130094e-05, "epoch": 1.87012987012987, "percentage": 62.43, "elapsed_time": "4:46:55", "remaining_time": "2:52:41"}
325
+ {"current_steps": 325, "total_steps": 519, "loss": 0.3975, "lr": 2.9495699322595615e-05, "epoch": 1.8759018759018757, "percentage": 62.62, "elapsed_time": "4:47:58", "remaining_time": "2:51:53"}
326
+ {"current_steps": 326, "total_steps": 519, "loss": 0.387, "lr": 2.923629602358441e-05, "epoch": 1.8816738816738816, "percentage": 62.81, "elapsed_time": "4:48:50", "remaining_time": "2:50:59"}
327
+ {"current_steps": 327, "total_steps": 519, "loss": 0.391, "lr": 2.8977379833503524e-05, "epoch": 1.8874458874458875, "percentage": 63.01, "elapsed_time": "4:49:42", "remaining_time": "2:50:06"}
328
+ {"current_steps": 328, "total_steps": 519, "loss": 0.3924, "lr": 2.871896246954518e-05, "epoch": 1.8932178932178934, "percentage": 63.2, "elapsed_time": "4:50:33", "remaining_time": "2:49:12"}
329
+ {"current_steps": 329, "total_steps": 519, "loss": 0.3861, "lr": 2.8461055626327313e-05, "epoch": 1.898989898989899, "percentage": 63.39, "elapsed_time": "4:51:25", "remaining_time": "2:48:18"}
330
+ {"current_steps": 330, "total_steps": 519, "loss": 0.3923, "lr": 2.8203670975364395e-05, "epoch": 1.9047619047619047, "percentage": 63.58, "elapsed_time": "4:52:17", "remaining_time": "2:47:24"}
331
+ {"current_steps": 331, "total_steps": 519, "loss": 0.3891, "lr": 2.7946820164539182e-05, "epoch": 1.9105339105339105, "percentage": 63.78, "elapsed_time": "4:53:09", "remaining_time": "2:46:30"}
332
+ {"current_steps": 332, "total_steps": 519, "loss": 0.3924, "lr": 2.7690514817575615e-05, "epoch": 1.9163059163059164, "percentage": 63.97, "elapsed_time": "4:54:01", "remaining_time": "2:45:36"}
333
+ {"current_steps": 333, "total_steps": 519, "loss": 0.3737, "lr": 2.7434766533512806e-05, "epoch": 1.922077922077922, "percentage": 64.16, "elapsed_time": "4:54:52", "remaining_time": "2:44:42"}
334
+ {"current_steps": 334, "total_steps": 519, "loss": 0.3948, "lr": 2.7179586886180128e-05, "epoch": 1.9278499278499277, "percentage": 64.35, "elapsed_time": "4:55:44", "remaining_time": "2:43:48"}
335
+ {"current_steps": 335, "total_steps": 519, "loss": 0.3866, "lr": 2.69249874236734e-05, "epoch": 1.9336219336219336, "percentage": 64.55, "elapsed_time": "4:56:36", "remaining_time": "2:42:54"}
336
+ {"current_steps": 336, "total_steps": 519, "loss": 0.3862, "lr": 2.667097966783234e-05, "epoch": 1.9393939393939394, "percentage": 64.74, "elapsed_time": "4:57:28", "remaining_time": "2:42:00"}
337
+ {"current_steps": 337, "total_steps": 519, "loss": 0.3802, "lr": 2.6417575113719087e-05, "epoch": 1.9451659451659453, "percentage": 64.93, "elapsed_time": "4:58:19", "remaining_time": "2:41:06"}
338
+ {"current_steps": 338, "total_steps": 519, "loss": 0.392, "lr": 2.616478522909807e-05, "epoch": 1.950937950937951, "percentage": 65.13, "elapsed_time": "4:59:11", "remaining_time": "2:40:13"}
339
+ {"current_steps": 339, "total_steps": 519, "loss": 0.3885, "lr": 2.5912621453916944e-05, "epoch": 1.9567099567099566, "percentage": 65.32, "elapsed_time": "5:00:15", "remaining_time": "2:39:26"}
340
+ {"current_steps": 340, "total_steps": 519, "loss": 0.3808, "lr": 2.566109519978894e-05, "epoch": 1.9624819624819625, "percentage": 65.51, "elapsed_time": "5:01:15", "remaining_time": "2:38:36"}
341
+ {"current_steps": 341, "total_steps": 519, "loss": 0.3752, "lr": 2.5410217849476447e-05, "epoch": 1.9682539682539684, "percentage": 65.7, "elapsed_time": "5:02:07", "remaining_time": "2:37:42"}
342
+ {"current_steps": 342, "total_steps": 519, "loss": 0.3763, "lr": 2.516000075637584e-05, "epoch": 1.974025974025974, "percentage": 65.9, "elapsed_time": "5:02:58", "remaining_time": "2:36:48"}
343
+ {"current_steps": 343, "total_steps": 519, "loss": 0.3814, "lr": 2.4910455244003702e-05, "epoch": 1.9797979797979797, "percentage": 66.09, "elapsed_time": "5:03:50", "remaining_time": "2:35:54"}
344
+ {"current_steps": 344, "total_steps": 519, "loss": 0.3886, "lr": 2.4661592605484422e-05, "epoch": 1.9855699855699855, "percentage": 66.28, "elapsed_time": "5:04:42", "remaining_time": "2:35:00"}
345
+ {"current_steps": 345, "total_steps": 519, "loss": 0.3856, "lr": 2.4413424103039035e-05, "epoch": 1.9913419913419914, "percentage": 66.47, "elapsed_time": "5:05:34", "remaining_time": "2:34:06"}
346
+ {"current_steps": 346, "total_steps": 519, "loss": 0.3812, "lr": 2.416596096747564e-05, "epoch": 1.997113997113997, "percentage": 66.67, "elapsed_time": "5:06:25", "remaining_time": "2:33:12"}
347
+ {"current_steps": 347, "total_steps": 519, "loss": 0.6364, "lr": 2.3919214397681137e-05, "epoch": 2.0028860028860027, "percentage": 66.86, "elapsed_time": "5:08:38", "remaining_time": "2:32:59"}
348
+ {"current_steps": 348, "total_steps": 519, "loss": 0.3528, "lr": 2.3673195560114365e-05, "epoch": 2.0086580086580086, "percentage": 67.05, "elapsed_time": "5:09:30", "remaining_time": "2:32:04"}