sedrickkeh commited on
Commit
4b4e4c5
·
verified ·
1 Parent(s): 01bff98

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 sha256:70a8f3663e44b4235897265801544fac50ff60c14aafb702f4e6227ebce39665
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2557489fbf3c609c6af607c46ecbe22798239a679183bfc1af3ca6b5d95d6432
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:23e920cc2a681bb8ae05b8e0dd2cb7337fb4510ae2261b14d5ef7a8f7dfe5761
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5dc114b2684cf4715469b3c923b550fec20aebb85a9064be89275219dcfe6558
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:06d3cb0f22b2bfd2a31a894a5d3e30b2723826d2c4e347ca454fe49ecabdbaaf
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab3260ae411e40178798d4d446ca83b67bf9ad4b63d899f67f8ec03268d6e48e
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:450c249f9c7baf52e8985f65174e0859b799e39ba74ce4be020f2df4cf13d4b1
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:40b84d5da9ed43b1973cbeaae626ff6a3a20b4694a7918c1ab3f79c9caf74754
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -183,3 +183,176 @@
183
  {"current_steps": 183, "total_steps": 522, "loss": 0.4572, "lr": 1.6442118690370272e-05, "epoch": 1.0497131931166348, "percentage": 35.06, "elapsed_time": "0:50:08", "remaining_time": "1:32:52"}
184
  {"current_steps": 184, "total_steps": 522, "loss": 0.4421, "lr": 1.639074132633091e-05, "epoch": 1.0554493307839388, "percentage": 35.25, "elapsed_time": "0:50:25", "remaining_time": "1:32:37"}
185
  {"current_steps": 185, "total_steps": 522, "loss": 0.4006, "lr": 1.6339077212127294e-05, "epoch": 1.0611854684512427, "percentage": 35.44, "elapsed_time": "0:50:39", "remaining_time": "1:32:17"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
183
  {"current_steps": 183, "total_steps": 522, "loss": 0.4572, "lr": 1.6442118690370272e-05, "epoch": 1.0497131931166348, "percentage": 35.06, "elapsed_time": "0:50:08", "remaining_time": "1:32:52"}
184
  {"current_steps": 184, "total_steps": 522, "loss": 0.4421, "lr": 1.639074132633091e-05, "epoch": 1.0554493307839388, "percentage": 35.25, "elapsed_time": "0:50:25", "remaining_time": "1:32:37"}
185
  {"current_steps": 185, "total_steps": 522, "loss": 0.4006, "lr": 1.6339077212127294e-05, "epoch": 1.0611854684512427, "percentage": 35.44, "elapsed_time": "0:50:39", "remaining_time": "1:32:17"}
186
+ {"current_steps": 186, "total_steps": 522, "loss": 0.4775, "lr": 1.628712866590885e-05, "epoch": 1.066921606118547, "percentage": 35.63, "elapsed_time": "0:50:52", "remaining_time": "1:31:54"}
187
+ {"current_steps": 187, "total_steps": 522, "loss": 0.4448, "lr": 1.6234898018587336e-05, "epoch": 1.0726577437858509, "percentage": 35.82, "elapsed_time": "0:51:10", "remaining_time": "1:31:41"}
188
+ {"current_steps": 188, "total_steps": 522, "loss": 0.4897, "lr": 1.6182387613732295e-05, "epoch": 1.0783938814531548, "percentage": 36.02, "elapsed_time": "0:51:29", "remaining_time": "1:31:29"}
189
+ {"current_steps": 189, "total_steps": 522, "loss": 0.3727, "lr": 1.6129599807465873e-05, "epoch": 1.0841300191204588, "percentage": 36.21, "elapsed_time": "0:51:46", "remaining_time": "1:31:12"}
190
+ {"current_steps": 190, "total_steps": 522, "loss": 0.5011, "lr": 1.607653696835713e-05, "epoch": 1.089866156787763, "percentage": 36.4, "elapsed_time": "0:52:06", "remaining_time": "1:31:03"}
191
+ {"current_steps": 191, "total_steps": 522, "loss": 0.4083, "lr": 1.602320147731573e-05, "epoch": 1.095602294455067, "percentage": 36.59, "elapsed_time": "0:52:21", "remaining_time": "1:30:43"}
192
+ {"current_steps": 192, "total_steps": 522, "loss": 0.4053, "lr": 1.596959572748514e-05, "epoch": 1.101338432122371, "percentage": 36.78, "elapsed_time": "0:52:36", "remaining_time": "1:30:24"}
193
+ {"current_steps": 193, "total_steps": 522, "loss": 0.4421, "lr": 1.5915722124135227e-05, "epoch": 1.107074569789675, "percentage": 36.97, "elapsed_time": "0:52:49", "remaining_time": "1:30:03"}
194
+ {"current_steps": 194, "total_steps": 522, "loss": 0.4458, "lr": 1.586158308455435e-05, "epoch": 1.1128107074569789, "percentage": 37.16, "elapsed_time": "0:53:05", "remaining_time": "1:29:45"}
195
+ {"current_steps": 195, "total_steps": 522, "loss": 0.4402, "lr": 1.580718103794089e-05, "epoch": 1.118546845124283, "percentage": 37.36, "elapsed_time": "0:53:20", "remaining_time": "1:29:26"}
196
+ {"current_steps": 196, "total_steps": 522, "loss": 0.3781, "lr": 1.5752518425294258e-05, "epoch": 1.124282982791587, "percentage": 37.55, "elapsed_time": "0:53:32", "remaining_time": "1:29:03"}
197
+ {"current_steps": 197, "total_steps": 522, "loss": 0.5061, "lr": 1.569759769930537e-05, "epoch": 1.130019120458891, "percentage": 37.74, "elapsed_time": "0:53:50", "remaining_time": "1:28:48"}
198
+ {"current_steps": 198, "total_steps": 522, "loss": 0.4414, "lr": 1.564242132424657e-05, "epoch": 1.135755258126195, "percentage": 37.93, "elapsed_time": "0:54:06", "remaining_time": "1:28:33"}
199
+ {"current_steps": 199, "total_steps": 522, "loss": 0.3934, "lr": 1.5586991775861103e-05, "epoch": 1.1414913957934991, "percentage": 38.12, "elapsed_time": "0:54:18", "remaining_time": "1:28:08"}
200
+ {"current_steps": 200, "total_steps": 522, "loss": 0.4114, "lr": 1.5531311541251995e-05, "epoch": 1.147227533460803, "percentage": 38.31, "elapsed_time": "0:54:30", "remaining_time": "1:27:45"}
201
+ {"current_steps": 201, "total_steps": 522, "loss": 0.4159, "lr": 1.5475383118770473e-05, "epoch": 1.152963671128107, "percentage": 38.51, "elapsed_time": "0:54:47", "remaining_time": "1:27:30"}
202
+ {"current_steps": 202, "total_steps": 522, "loss": 0.4859, "lr": 1.5419209017903855e-05, "epoch": 1.158699808795411, "percentage": 38.7, "elapsed_time": "0:55:00", "remaining_time": "1:27:08"}
203
+ {"current_steps": 203, "total_steps": 522, "loss": 0.402, "lr": 1.536279175916296e-05, "epoch": 1.1644359464627152, "percentage": 38.89, "elapsed_time": "0:55:15", "remaining_time": "1:26:50"}
204
+ {"current_steps": 204, "total_steps": 522, "loss": 0.4958, "lr": 1.5306133873969008e-05, "epoch": 1.1701720841300192, "percentage": 39.08, "elapsed_time": "0:55:32", "remaining_time": "1:26:34"}
205
+ {"current_steps": 205, "total_steps": 522, "loss": 0.4438, "lr": 1.5249237904540041e-05, "epoch": 1.1759082217973231, "percentage": 39.27, "elapsed_time": "0:55:48", "remaining_time": "1:26:17"}
206
+ {"current_steps": 206, "total_steps": 522, "loss": 0.4239, "lr": 1.519210640377685e-05, "epoch": 1.181644359464627, "percentage": 39.46, "elapsed_time": "0:56:03", "remaining_time": "1:25:59"}
207
+ {"current_steps": 207, "total_steps": 522, "loss": 0.4288, "lr": 1.513474193514842e-05, "epoch": 1.1873804971319313, "percentage": 39.66, "elapsed_time": "0:56:17", "remaining_time": "1:25:39"}
208
+ {"current_steps": 208, "total_steps": 522, "loss": 0.4277, "lr": 1.5077147072576932e-05, "epoch": 1.1931166347992352, "percentage": 39.85, "elapsed_time": "0:56:33", "remaining_time": "1:25:23"}
209
+ {"current_steps": 209, "total_steps": 522, "loss": 0.4359, "lr": 1.5019324400322244e-05, "epoch": 1.1988527724665392, "percentage": 40.04, "elapsed_time": "0:56:49", "remaining_time": "1:25:05"}
210
+ {"current_steps": 210, "total_steps": 522, "loss": 0.4269, "lr": 1.4961276512865954e-05, "epoch": 1.2045889101338432, "percentage": 40.23, "elapsed_time": "0:57:07", "remaining_time": "1:24:51"}
211
+ {"current_steps": 211, "total_steps": 522, "loss": 0.4509, "lr": 1.4903006014794983e-05, "epoch": 1.2103250478011471, "percentage": 40.42, "elapsed_time": "0:57:24", "remaining_time": "1:24:36"}
212
+ {"current_steps": 212, "total_steps": 522, "loss": 0.443, "lr": 1.4844515520684703e-05, "epoch": 1.2160611854684513, "percentage": 40.61, "elapsed_time": "0:57:38", "remaining_time": "1:24:17"}
213
+ {"current_steps": 213, "total_steps": 522, "loss": 0.4079, "lr": 1.4785807654981627e-05, "epoch": 1.2217973231357553, "percentage": 40.8, "elapsed_time": "0:57:49", "remaining_time": "1:23:53"}
214
+ {"current_steps": 214, "total_steps": 522, "loss": 0.4102, "lr": 1.4726885051885654e-05, "epoch": 1.2275334608030593, "percentage": 41.0, "elapsed_time": "0:58:02", "remaining_time": "1:23:32"}
215
+ {"current_steps": 215, "total_steps": 522, "loss": 0.4577, "lr": 1.4667750355231863e-05, "epoch": 1.2332695984703632, "percentage": 41.19, "elapsed_time": "0:58:19", "remaining_time": "1:23:16"}
216
+ {"current_steps": 216, "total_steps": 522, "loss": 0.4538, "lr": 1.4608406218371894e-05, "epoch": 1.2390057361376674, "percentage": 41.38, "elapsed_time": "0:58:34", "remaining_time": "1:22:58"}
217
+ {"current_steps": 217, "total_steps": 522, "loss": 0.3844, "lr": 1.4548855304054888e-05, "epoch": 1.2447418738049714, "percentage": 41.57, "elapsed_time": "0:58:50", "remaining_time": "1:22:41"}
218
+ {"current_steps": 218, "total_steps": 522, "loss": 0.3947, "lr": 1.4489100284308018e-05, "epoch": 1.2504780114722753, "percentage": 41.76, "elapsed_time": "0:59:01", "remaining_time": "1:22:18"}
219
+ {"current_steps": 219, "total_steps": 522, "loss": 0.4645, "lr": 1.4429143840316586e-05, "epoch": 1.2562141491395793, "percentage": 41.95, "elapsed_time": "0:59:15", "remaining_time": "1:21:59"}
220
+ {"current_steps": 220, "total_steps": 522, "loss": 0.452, "lr": 1.4368988662303733e-05, "epoch": 1.2619502868068833, "percentage": 42.15, "elapsed_time": "0:59:33", "remaining_time": "1:21:44"}
221
+ {"current_steps": 221, "total_steps": 522, "loss": 0.441, "lr": 1.4308637449409705e-05, "epoch": 1.2676864244741874, "percentage": 42.34, "elapsed_time": "0:59:49", "remaining_time": "1:21:28"}
222
+ {"current_steps": 222, "total_steps": 522, "loss": 0.457, "lr": 1.4248092909570774e-05, "epoch": 1.2734225621414914, "percentage": 42.53, "elapsed_time": "1:00:06", "remaining_time": "1:21:14"}
223
+ {"current_steps": 223, "total_steps": 522, "loss": 0.474, "lr": 1.4187357759397716e-05, "epoch": 1.2791586998087954, "percentage": 42.72, "elapsed_time": "1:00:22", "remaining_time": "1:20:57"}
224
+ {"current_steps": 224, "total_steps": 522, "loss": 0.4418, "lr": 1.4126434724053915e-05, "epoch": 1.2848948374760996, "percentage": 42.91, "elapsed_time": "1:00:37", "remaining_time": "1:20:39"}
225
+ {"current_steps": 225, "total_steps": 522, "loss": 0.4143, "lr": 1.4065326537133094e-05, "epoch": 1.2906309751434035, "percentage": 43.1, "elapsed_time": "1:00:51", "remaining_time": "1:20:20"}
226
+ {"current_steps": 226, "total_steps": 522, "loss": 0.4301, "lr": 1.4004035940536671e-05, "epoch": 1.2963671128107075, "percentage": 43.3, "elapsed_time": "1:01:06", "remaining_time": "1:20:01"}
227
+ {"current_steps": 227, "total_steps": 522, "loss": 0.439, "lr": 1.39425656843507e-05, "epoch": 1.3021032504780115, "percentage": 43.49, "elapsed_time": "1:01:19", "remaining_time": "1:19:41"}
228
+ {"current_steps": 228, "total_steps": 522, "loss": 0.4653, "lr": 1.3880918526722497e-05, "epoch": 1.3078393881453154, "percentage": 43.68, "elapsed_time": "1:01:38", "remaining_time": "1:19:28"}
229
+ {"current_steps": 229, "total_steps": 522, "loss": 0.4895, "lr": 1.3819097233736888e-05, "epoch": 1.3135755258126194, "percentage": 43.87, "elapsed_time": "1:01:55", "remaining_time": "1:19:14"}
230
+ {"current_steps": 230, "total_steps": 522, "loss": 0.407, "lr": 1.3757104579292082e-05, "epoch": 1.3193116634799236, "percentage": 44.06, "elapsed_time": "1:02:10", "remaining_time": "1:18:55"}
231
+ {"current_steps": 231, "total_steps": 522, "loss": 0.3897, "lr": 1.3694943344975214e-05, "epoch": 1.3250478011472275, "percentage": 44.25, "elapsed_time": "1:02:26", "remaining_time": "1:18:38"}
232
+ {"current_steps": 232, "total_steps": 522, "loss": 0.4569, "lr": 1.3632616319937522e-05, "epoch": 1.3307839388145315, "percentage": 44.44, "elapsed_time": "1:02:44", "remaining_time": "1:18:25"}
233
+ {"current_steps": 233, "total_steps": 522, "loss": 0.4563, "lr": 1.3570126300769233e-05, "epoch": 1.3365200764818357, "percentage": 44.64, "elapsed_time": "1:03:01", "remaining_time": "1:18:10"}
234
+ {"current_steps": 234, "total_steps": 522, "loss": 0.454, "lr": 1.3507476091374042e-05, "epoch": 1.3422562141491396, "percentage": 44.83, "elapsed_time": "1:03:20", "remaining_time": "1:17:57"}
235
+ {"current_steps": 235, "total_steps": 522, "loss": 0.4314, "lr": 1.344466850284333e-05, "epoch": 1.3479923518164436, "percentage": 45.02, "elapsed_time": "1:03:36", "remaining_time": "1:17:41"}
236
+ {"current_steps": 236, "total_steps": 522, "loss": 0.4783, "lr": 1.3381706353330015e-05, "epoch": 1.3537284894837476, "percentage": 45.21, "elapsed_time": "1:03:54", "remaining_time": "1:17:27"}
237
+ {"current_steps": 237, "total_steps": 522, "loss": 0.3658, "lr": 1.331859246792211e-05, "epoch": 1.3594646271510515, "percentage": 45.4, "elapsed_time": "1:04:09", "remaining_time": "1:17:09"}
238
+ {"current_steps": 238, "total_steps": 522, "loss": 0.456, "lr": 1.3255329678515959e-05, "epoch": 1.3652007648183555, "percentage": 45.59, "elapsed_time": "1:04:27", "remaining_time": "1:16:54"}
239
+ {"current_steps": 239, "total_steps": 522, "loss": 0.4056, "lr": 1.3191920823689178e-05, "epoch": 1.3709369024856597, "percentage": 45.79, "elapsed_time": "1:04:44", "remaining_time": "1:16:39"}
240
+ {"current_steps": 240, "total_steps": 522, "loss": 0.4938, "lr": 1.3128368748573272e-05, "epoch": 1.3766730401529637, "percentage": 45.98, "elapsed_time": "1:04:59", "remaining_time": "1:16:21"}
241
+ {"current_steps": 241, "total_steps": 522, "loss": 0.4354, "lr": 1.3064676304726001e-05, "epoch": 1.3824091778202676, "percentage": 46.17, "elapsed_time": "1:05:15", "remaining_time": "1:16:05"}
242
+ {"current_steps": 242, "total_steps": 522, "loss": 0.4009, "lr": 1.300084635000341e-05, "epoch": 1.3881453154875718, "percentage": 46.36, "elapsed_time": "1:05:32", "remaining_time": "1:15:49"}
243
+ {"current_steps": 243, "total_steps": 522, "loss": 0.4139, "lr": 1.2936881748431601e-05, "epoch": 1.3938814531548758, "percentage": 46.55, "elapsed_time": "1:05:46", "remaining_time": "1:15:31"}
244
+ {"current_steps": 244, "total_steps": 522, "loss": 0.4831, "lr": 1.287278537007824e-05, "epoch": 1.3996175908221797, "percentage": 46.74, "elapsed_time": "1:06:04", "remaining_time": "1:15:16"}
245
+ {"current_steps": 245, "total_steps": 522, "loss": 0.4599, "lr": 1.280856009092376e-05, "epoch": 1.4053537284894837, "percentage": 46.93, "elapsed_time": "1:06:18", "remaining_time": "1:14:58"}
246
+ {"current_steps": 246, "total_steps": 522, "loss": 0.4387, "lr": 1.2744208792732324e-05, "epoch": 1.4110898661567877, "percentage": 47.13, "elapsed_time": "1:06:36", "remaining_time": "1:14:44"}
247
+ {"current_steps": 247, "total_steps": 522, "loss": 0.4513, "lr": 1.267973436292253e-05, "epoch": 1.4168260038240919, "percentage": 47.32, "elapsed_time": "1:06:55", "remaining_time": "1:14:30"}
248
+ {"current_steps": 248, "total_steps": 522, "loss": 0.4107, "lr": 1.2615139694437835e-05, "epoch": 1.4225621414913958, "percentage": 47.51, "elapsed_time": "1:07:13", "remaining_time": "1:14:16"}
249
+ {"current_steps": 249, "total_steps": 522, "loss": 0.4504, "lr": 1.2550427685616767e-05, "epoch": 1.4282982791586998, "percentage": 47.7, "elapsed_time": "1:07:29", "remaining_time": "1:13:59"}
250
+ {"current_steps": 250, "total_steps": 522, "loss": 0.4142, "lr": 1.2485601240062868e-05, "epoch": 1.4340344168260037, "percentage": 47.89, "elapsed_time": "1:07:49", "remaining_time": "1:13:47"}
251
+ {"current_steps": 251, "total_steps": 522, "loss": 0.4523, "lr": 1.2420663266514419e-05, "epoch": 1.439770554493308, "percentage": 48.08, "elapsed_time": "1:08:06", "remaining_time": "1:13:32"}
252
+ {"current_steps": 252, "total_steps": 522, "loss": 0.4543, "lr": 1.2355616678713909e-05, "epoch": 1.445506692160612, "percentage": 48.28, "elapsed_time": "1:08:23", "remaining_time": "1:13:16"}
253
+ {"current_steps": 253, "total_steps": 522, "loss": 0.3931, "lr": 1.229046439527732e-05, "epoch": 1.4512428298279159, "percentage": 48.47, "elapsed_time": "1:08:37", "remaining_time": "1:12:58"}
254
+ {"current_steps": 254, "total_steps": 522, "loss": 0.44, "lr": 1.2225209339563144e-05, "epoch": 1.4569789674952198, "percentage": 48.66, "elapsed_time": "1:08:52", "remaining_time": "1:12:40"}
255
+ {"current_steps": 255, "total_steps": 522, "loss": 0.4551, "lr": 1.2159854439541245e-05, "epoch": 1.4627151051625238, "percentage": 48.85, "elapsed_time": "1:09:09", "remaining_time": "1:12:24"}
256
+ {"current_steps": 256, "total_steps": 522, "loss": 0.443, "lr": 1.2094402627661447e-05, "epoch": 1.468451242829828, "percentage": 49.04, "elapsed_time": "1:09:28", "remaining_time": "1:12:11"}
257
+ {"current_steps": 257, "total_steps": 522, "loss": 0.4656, "lr": 1.2028856840721975e-05, "epoch": 1.474187380497132, "percentage": 49.23, "elapsed_time": "1:09:46", "remaining_time": "1:11:57"}
258
+ {"current_steps": 258, "total_steps": 522, "loss": 0.4234, "lr": 1.1963220019737691e-05, "epoch": 1.479923518164436, "percentage": 49.43, "elapsed_time": "1:10:03", "remaining_time": "1:11:40"}
259
+ {"current_steps": 259, "total_steps": 522, "loss": 0.4543, "lr": 1.1897495109808108e-05, "epoch": 1.48565965583174, "percentage": 49.62, "elapsed_time": "1:10:19", "remaining_time": "1:11:24"}
260
+ {"current_steps": 260, "total_steps": 522, "loss": 0.4546, "lr": 1.1831685059985263e-05, "epoch": 1.491395793499044, "percentage": 49.81, "elapsed_time": "1:10:34", "remaining_time": "1:11:07"}
261
+ {"current_steps": 261, "total_steps": 522, "loss": 0.4111, "lr": 1.1765792823141385e-05, "epoch": 1.497131931166348, "percentage": 50.0, "elapsed_time": "1:10:45", "remaining_time": "1:10:45"}
262
+ {"current_steps": 262, "total_steps": 522, "loss": 0.4134, "lr": 1.169982135583641e-05, "epoch": 1.502868068833652, "percentage": 50.19, "elapsed_time": "1:10:58", "remaining_time": "1:10:26"}
263
+ {"current_steps": 263, "total_steps": 522, "loss": 0.4397, "lr": 1.1633773618185302e-05, "epoch": 1.508604206500956, "percentage": 50.38, "elapsed_time": "1:11:13", "remaining_time": "1:10:08"}
264
+ {"current_steps": 264, "total_steps": 522, "loss": 0.4484, "lr": 1.1567652573725263e-05, "epoch": 1.51434034416826, "percentage": 50.57, "elapsed_time": "1:11:29", "remaining_time": "1:09:52"}
265
+ {"current_steps": 265, "total_steps": 522, "loss": 0.4027, "lr": 1.1501461189282734e-05, "epoch": 1.520076481835564, "percentage": 50.77, "elapsed_time": "1:11:46", "remaining_time": "1:09:36"}
266
+ {"current_steps": 266, "total_steps": 522, "loss": 0.4266, "lr": 1.1435202434840287e-05, "epoch": 1.525812619502868, "percentage": 50.96, "elapsed_time": "1:12:01", "remaining_time": "1:09:19"}
267
+ {"current_steps": 267, "total_steps": 522, "loss": 0.4279, "lr": 1.136887928340336e-05, "epoch": 1.5315487571701722, "percentage": 51.15, "elapsed_time": "1:12:18", "remaining_time": "1:09:03"}
268
+ {"current_steps": 268, "total_steps": 522, "loss": 0.4179, "lr": 1.1302494710866859e-05, "epoch": 1.5372848948374762, "percentage": 51.34, "elapsed_time": "1:12:34", "remaining_time": "1:08:47"}
269
+ {"current_steps": 269, "total_steps": 522, "loss": 0.4769, "lr": 1.1236051695881634e-05, "epoch": 1.5430210325047802, "percentage": 51.53, "elapsed_time": "1:12:52", "remaining_time": "1:08:32"}
270
+ {"current_steps": 270, "total_steps": 522, "loss": 0.4599, "lr": 1.1169553219720828e-05, "epoch": 1.5487571701720841, "percentage": 51.72, "elapsed_time": "1:13:06", "remaining_time": "1:08:14"}
271
+ {"current_steps": 271, "total_steps": 522, "loss": 0.4515, "lr": 1.1103002266146096e-05, "epoch": 1.554493307839388, "percentage": 51.92, "elapsed_time": "1:13:22", "remaining_time": "1:07:58"}
272
+ {"current_steps": 272, "total_steps": 522, "loss": 0.4265, "lr": 1.103640182127375e-05, "epoch": 1.560229445506692, "percentage": 52.11, "elapsed_time": "1:13:40", "remaining_time": "1:07:42"}
273
+ {"current_steps": 273, "total_steps": 522, "loss": 0.4486, "lr": 1.0969754873440743e-05, "epoch": 1.565965583173996, "percentage": 52.3, "elapsed_time": "1:13:57", "remaining_time": "1:07:27"}
274
+ {"current_steps": 274, "total_steps": 522, "loss": 0.4834, "lr": 1.0903064413070611e-05, "epoch": 1.5717017208413002, "percentage": 52.49, "elapsed_time": "1:14:12", "remaining_time": "1:07:10"}
275
+ {"current_steps": 275, "total_steps": 522, "loss": 0.4084, "lr": 1.0836333432539272e-05, "epoch": 1.5774378585086042, "percentage": 52.68, "elapsed_time": "1:14:27", "remaining_time": "1:06:52"}
276
+ {"current_steps": 276, "total_steps": 522, "loss": 0.4574, "lr": 1.076956492604077e-05, "epoch": 1.5831739961759084, "percentage": 52.87, "elapsed_time": "1:14:48", "remaining_time": "1:06:40"}
277
+ {"current_steps": 277, "total_steps": 522, "loss": 0.44, "lr": 1.070276188945293e-05, "epoch": 1.5889101338432123, "percentage": 53.07, "elapsed_time": "1:15:05", "remaining_time": "1:06:25"}
278
+ {"current_steps": 278, "total_steps": 522, "loss": 0.428, "lr": 1.0635927320202928e-05, "epoch": 1.5946462715105163, "percentage": 53.26, "elapsed_time": "1:15:21", "remaining_time": "1:06:08"}
279
+ {"current_steps": 279, "total_steps": 522, "loss": 0.3999, "lr": 1.0569064217132791e-05, "epoch": 1.6003824091778203, "percentage": 53.45, "elapsed_time": "1:15:38", "remaining_time": "1:05:52"}
280
+ {"current_steps": 280, "total_steps": 522, "loss": 0.4629, "lr": 1.0502175580364857e-05, "epoch": 1.6061185468451242, "percentage": 53.64, "elapsed_time": "1:15:54", "remaining_time": "1:05:36"}
281
+ {"current_steps": 281, "total_steps": 522, "loss": 0.426, "lr": 1.0435264411167148e-05, "epoch": 1.6118546845124282, "percentage": 53.83, "elapsed_time": "1:16:09", "remaining_time": "1:05:18"}
282
+ {"current_steps": 282, "total_steps": 522, "loss": 0.4835, "lr": 1.036833371181871e-05, "epoch": 1.6175908221797322, "percentage": 54.02, "elapsed_time": "1:16:25", "remaining_time": "1:05:02"}
283
+ {"current_steps": 283, "total_steps": 522, "loss": 0.4303, "lr": 1.0301386485474888e-05, "epoch": 1.6233269598470363, "percentage": 54.21, "elapsed_time": "1:16:44", "remaining_time": "1:04:48"}
284
+ {"current_steps": 284, "total_steps": 522, "loss": 0.4528, "lr": 1.0234425736032607e-05, "epoch": 1.6290630975143403, "percentage": 54.41, "elapsed_time": "1:17:03", "remaining_time": "1:04:34"}
285
+ {"current_steps": 285, "total_steps": 522, "loss": 0.4054, "lr": 1.016745446799555e-05, "epoch": 1.6347992351816445, "percentage": 54.6, "elapsed_time": "1:17:18", "remaining_time": "1:04:17"}
286
+ {"current_steps": 286, "total_steps": 522, "loss": 0.4622, "lr": 1.010047568633938e-05, "epoch": 1.6405353728489485, "percentage": 54.79, "elapsed_time": "1:17:31", "remaining_time": "1:03:58"}
287
+ {"current_steps": 287, "total_steps": 522, "loss": 0.4443, "lr": 1.0033492396376879e-05, "epoch": 1.6462715105162524, "percentage": 54.98, "elapsed_time": "1:17:51", "remaining_time": "1:03:44"}
288
+ {"current_steps": 288, "total_steps": 522, "loss": 0.4255, "lr": 9.966507603623125e-06, "epoch": 1.6520076481835564, "percentage": 55.17, "elapsed_time": "1:18:05", "remaining_time": "1:03:27"}
289
+ {"current_steps": 289, "total_steps": 522, "loss": 0.439, "lr": 9.899524313660623e-06, "epoch": 1.6577437858508604, "percentage": 55.36, "elapsed_time": "1:18:22", "remaining_time": "1:03:11"}
290
+ {"current_steps": 290, "total_steps": 522, "loss": 0.4339, "lr": 9.832545532004454e-06, "epoch": 1.6634799235181643, "percentage": 55.56, "elapsed_time": "1:18:38", "remaining_time": "1:02:54"}
291
+ {"current_steps": 291, "total_steps": 522, "loss": 0.3977, "lr": 9.765574263967397e-06, "epoch": 1.6692160611854685, "percentage": 55.75, "elapsed_time": "1:18:51", "remaining_time": "1:02:36"}
292
+ {"current_steps": 292, "total_steps": 522, "loss": 0.422, "lr": 9.698613514525117e-06, "epoch": 1.6749521988527725, "percentage": 55.94, "elapsed_time": "1:19:08", "remaining_time": "1:02:20"}
293
+ {"current_steps": 293, "total_steps": 522, "loss": 0.4903, "lr": 9.631666288181293e-06, "epoch": 1.6806883365200764, "percentage": 56.13, "elapsed_time": "1:19:24", "remaining_time": "1:02:03"}
294
+ {"current_steps": 294, "total_steps": 522, "loss": 0.5333, "lr": 9.564735588832857e-06, "epoch": 1.6864244741873806, "percentage": 56.32, "elapsed_time": "1:19:40", "remaining_time": "1:01:47"}
295
+ {"current_steps": 295, "total_steps": 522, "loss": 0.3805, "lr": 9.497824419635145e-06, "epoch": 1.6921606118546846, "percentage": 56.51, "elapsed_time": "1:19:53", "remaining_time": "1:01:28"}
296
+ {"current_steps": 296, "total_steps": 522, "loss": 0.4379, "lr": 9.430935782867214e-06, "epoch": 1.6978967495219885, "percentage": 56.7, "elapsed_time": "1:20:10", "remaining_time": "1:01:12"}
297
+ {"current_steps": 297, "total_steps": 522, "loss": 0.439, "lr": 9.364072679797074e-06, "epoch": 1.7036328871892925, "percentage": 56.9, "elapsed_time": "1:20:27", "remaining_time": "1:00:57"}
298
+ {"current_steps": 298, "total_steps": 522, "loss": 0.4748, "lr": 9.297238110547075e-06, "epoch": 1.7093690248565965, "percentage": 57.09, "elapsed_time": "1:20:46", "remaining_time": "1:00:43"}
299
+ {"current_steps": 299, "total_steps": 522, "loss": 0.4381, "lr": 9.230435073959232e-06, "epoch": 1.7151051625239004, "percentage": 57.28, "elapsed_time": "1:21:03", "remaining_time": "1:00:27"}
300
+ {"current_steps": 300, "total_steps": 522, "loss": 0.3894, "lr": 9.163666567460735e-06, "epoch": 1.7208413001912046, "percentage": 57.47, "elapsed_time": "1:21:19", "remaining_time": "1:00:10"}
301
+ {"current_steps": 301, "total_steps": 522, "loss": 0.4284, "lr": 9.096935586929392e-06, "epoch": 1.7265774378585086, "percentage": 57.66, "elapsed_time": "1:21:29", "remaining_time": "0:59:50"}
302
+ {"current_steps": 302, "total_steps": 522, "loss": 0.4843, "lr": 9.030245126559262e-06, "epoch": 1.7323135755258128, "percentage": 57.85, "elapsed_time": "1:21:44", "remaining_time": "0:59:33"}
303
+ {"current_steps": 303, "total_steps": 522, "loss": 0.3751, "lr": 8.963598178726254e-06, "epoch": 1.7380497131931167, "percentage": 58.05, "elapsed_time": "1:22:03", "remaining_time": "0:59:18"}
304
+ {"current_steps": 304, "total_steps": 522, "loss": 0.4418, "lr": 8.896997733853904e-06, "epoch": 1.7437858508604207, "percentage": 58.24, "elapsed_time": "1:22:18", "remaining_time": "0:59:01"}
305
+ {"current_steps": 305, "total_steps": 522, "loss": 0.4854, "lr": 8.830446780279175e-06, "epoch": 1.7495219885277247, "percentage": 58.43, "elapsed_time": "1:22:35", "remaining_time": "0:58:45"}
306
+ {"current_steps": 306, "total_steps": 522, "loss": 0.4132, "lr": 8.763948304118368e-06, "epoch": 1.7552581261950286, "percentage": 58.62, "elapsed_time": "1:22:52", "remaining_time": "0:58:30"}
307
+ {"current_steps": 307, "total_steps": 522, "loss": 0.4512, "lr": 8.697505289133146e-06, "epoch": 1.7609942638623326, "percentage": 58.81, "elapsed_time": "1:23:12", "remaining_time": "0:58:16"}
308
+ {"current_steps": 308, "total_steps": 522, "loss": 0.3694, "lr": 8.631120716596642e-06, "epoch": 1.7667304015296366, "percentage": 59.0, "elapsed_time": "1:23:32", "remaining_time": "0:58:02"}
309
+ {"current_steps": 309, "total_steps": 522, "loss": 0.4099, "lr": 8.564797565159715e-06, "epoch": 1.7724665391969407, "percentage": 59.2, "elapsed_time": "1:23:49", "remaining_time": "0:57:46"}
310
+ {"current_steps": 310, "total_steps": 522, "loss": 0.4327, "lr": 8.498538810717267e-06, "epoch": 1.7782026768642447, "percentage": 59.39, "elapsed_time": "1:24:06", "remaining_time": "0:57:30"}
311
+ {"current_steps": 311, "total_steps": 522, "loss": 0.4541, "lr": 8.432347426274739e-06, "epoch": 1.783938814531549, "percentage": 59.58, "elapsed_time": "1:24:20", "remaining_time": "0:57:13"}
312
+ {"current_steps": 312, "total_steps": 522, "loss": 0.4592, "lr": 8.366226381814698e-06, "epoch": 1.7896749521988529, "percentage": 59.77, "elapsed_time": "1:24:36", "remaining_time": "0:56:56"}
313
+ {"current_steps": 313, "total_steps": 522, "loss": 0.4062, "lr": 8.300178644163593e-06, "epoch": 1.7954110898661568, "percentage": 59.96, "elapsed_time": "1:24:45", "remaining_time": "0:56:35"}
314
+ {"current_steps": 314, "total_steps": 522, "loss": 0.4568, "lr": 8.234207176858615e-06, "epoch": 1.8011472275334608, "percentage": 60.15, "elapsed_time": "1:25:00", "remaining_time": "0:56:18"}
315
+ {"current_steps": 315, "total_steps": 522, "loss": 0.4277, "lr": 8.168314940014742e-06, "epoch": 1.8068833652007648, "percentage": 60.34, "elapsed_time": "1:25:16", "remaining_time": "0:56:02"}
316
+ {"current_steps": 316, "total_steps": 522, "loss": 0.46, "lr": 8.102504890191892e-06, "epoch": 1.8126195028680687, "percentage": 60.54, "elapsed_time": "1:25:33", "remaining_time": "0:55:46"}
317
+ {"current_steps": 317, "total_steps": 522, "loss": 0.4223, "lr": 8.036779980262312e-06, "epoch": 1.8183556405353727, "percentage": 60.73, "elapsed_time": "1:25:50", "remaining_time": "0:55:30"}
318
+ {"current_steps": 318, "total_steps": 522, "loss": 0.4132, "lr": 7.971143159278025e-06, "epoch": 1.8240917782026769, "percentage": 60.92, "elapsed_time": "1:26:05", "remaining_time": "0:55:13"}
319
+ {"current_steps": 319, "total_steps": 522, "loss": 0.4391, "lr": 7.905597372338558e-06, "epoch": 1.8298279158699808, "percentage": 61.11, "elapsed_time": "1:26:19", "remaining_time": "0:54:56"}
320
+ {"current_steps": 320, "total_steps": 522, "loss": 0.3864, "lr": 7.840145560458756e-06, "epoch": 1.835564053537285, "percentage": 61.3, "elapsed_time": "1:26:33", "remaining_time": "0:54:38"}
321
+ {"current_steps": 321, "total_steps": 522, "loss": 0.414, "lr": 7.774790660436857e-06, "epoch": 1.841300191204589, "percentage": 61.49, "elapsed_time": "1:26:50", "remaining_time": "0:54:22"}
322
+ {"current_steps": 322, "total_steps": 522, "loss": 0.4179, "lr": 7.709535604722685e-06, "epoch": 1.847036328871893, "percentage": 61.69, "elapsed_time": "1:27:06", "remaining_time": "0:54:06"}
323
+ {"current_steps": 323, "total_steps": 522, "loss": 0.4631, "lr": 7.644383321286095e-06, "epoch": 1.852772466539197, "percentage": 61.88, "elapsed_time": "1:27:20", "remaining_time": "0:53:48"}
324
+ {"current_steps": 324, "total_steps": 522, "loss": 0.452, "lr": 7.579336733485584e-06, "epoch": 1.8585086042065009, "percentage": 62.07, "elapsed_time": "1:27:37", "remaining_time": "0:53:32"}
325
+ {"current_steps": 325, "total_steps": 522, "loss": 0.4218, "lr": 7.514398759937135e-06, "epoch": 1.8642447418738048, "percentage": 62.26, "elapsed_time": "1:27:51", "remaining_time": "0:53:15"}
326
+ {"current_steps": 326, "total_steps": 522, "loss": 0.4457, "lr": 7.449572314383237e-06, "epoch": 1.869980879541109, "percentage": 62.45, "elapsed_time": "1:28:09", "remaining_time": "0:52:59"}
327
+ {"current_steps": 327, "total_steps": 522, "loss": 0.4096, "lr": 7.384860305562171e-06, "epoch": 1.875717017208413, "percentage": 62.64, "elapsed_time": "1:28:24", "remaining_time": "0:52:43"}
328
+ {"current_steps": 328, "total_steps": 522, "loss": 0.4833, "lr": 7.320265637077473e-06, "epoch": 1.8814531548757172, "percentage": 62.84, "elapsed_time": "1:28:39", "remaining_time": "0:52:26"}
329
+ {"current_steps": 329, "total_steps": 522, "loss": 0.3945, "lr": 7.255791207267679e-06, "epoch": 1.8871892925430211, "percentage": 63.03, "elapsed_time": "1:28:56", "remaining_time": "0:52:10"}
330
+ {"current_steps": 330, "total_steps": 522, "loss": 0.4165, "lr": 7.191439909076243e-06, "epoch": 1.892925430210325, "percentage": 63.22, "elapsed_time": "1:29:11", "remaining_time": "0:51:53"}
331
+ {"current_steps": 331, "total_steps": 522, "loss": 0.408, "lr": 7.127214629921765e-06, "epoch": 1.898661567877629, "percentage": 63.41, "elapsed_time": "1:29:29", "remaining_time": "0:51:38"}
332
+ {"current_steps": 332, "total_steps": 522, "loss": 0.4069, "lr": 7.0631182515684e-06, "epoch": 1.904397705544933, "percentage": 63.6, "elapsed_time": "1:29:46", "remaining_time": "0:51:22"}
333
+ {"current_steps": 333, "total_steps": 522, "loss": 0.4033, "lr": 6.999153649996595e-06, "epoch": 1.910133843212237, "percentage": 63.79, "elapsed_time": "1:30:00", "remaining_time": "0:51:05"}
334
+ {"current_steps": 334, "total_steps": 522, "loss": 0.4244, "lr": 6.935323695274002e-06, "epoch": 1.915869980879541, "percentage": 63.98, "elapsed_time": "1:30:15", "remaining_time": "0:50:48"}
335
+ {"current_steps": 335, "total_steps": 522, "loss": 0.4935, "lr": 6.871631251426729e-06, "epoch": 1.9216061185468452, "percentage": 64.18, "elapsed_time": "1:30:33", "remaining_time": "0:50:32"}
336
+ {"current_steps": 336, "total_steps": 522, "loss": 0.3796, "lr": 6.808079176310826e-06, "epoch": 1.9273422562141491, "percentage": 64.37, "elapsed_time": "1:30:48", "remaining_time": "0:50:16"}
337
+ {"current_steps": 337, "total_steps": 522, "loss": 0.406, "lr": 6.744670321484044e-06, "epoch": 1.9330783938814533, "percentage": 64.56, "elapsed_time": "1:31:03", "remaining_time": "0:49:59"}
338
+ {"current_steps": 338, "total_steps": 522, "loss": 0.4365, "lr": 6.681407532077895e-06, "epoch": 1.9388145315487573, "percentage": 64.75, "elapsed_time": "1:31:21", "remaining_time": "0:49:44"}
339
+ {"current_steps": 339, "total_steps": 522, "loss": 0.4366, "lr": 6.618293646669987e-06, "epoch": 1.9445506692160612, "percentage": 64.94, "elapsed_time": "1:31:36", "remaining_time": "0:49:27"}
340
+ {"current_steps": 340, "total_steps": 522, "loss": 0.4551, "lr": 6.555331497156671e-06, "epoch": 1.9502868068833652, "percentage": 65.13, "elapsed_time": "1:31:52", "remaining_time": "0:49:10"}
341
+ {"current_steps": 341, "total_steps": 522, "loss": 0.4564, "lr": 6.492523908625958e-06, "epoch": 1.9560229445506692, "percentage": 65.33, "elapsed_time": "1:32:09", "remaining_time": "0:48:54"}
342
+ {"current_steps": 342, "total_steps": 522, "loss": 0.4411, "lr": 6.429873699230771e-06, "epoch": 1.9617590822179731, "percentage": 65.52, "elapsed_time": "1:32:24", "remaining_time": "0:48:38"}
343
+ {"current_steps": 343, "total_steps": 522, "loss": 0.3952, "lr": 6.3673836800624775e-06, "epoch": 1.967495219885277, "percentage": 65.71, "elapsed_time": "1:32:34", "remaining_time": "0:48:18"}
344
+ {"current_steps": 344, "total_steps": 522, "loss": 0.3802, "lr": 6.30505665502479e-06, "epoch": 1.9732313575525813, "percentage": 65.9, "elapsed_time": "1:32:47", "remaining_time": "0:48:00"}
345
+ {"current_steps": 345, "total_steps": 522, "loss": 0.4741, "lr": 6.242895420707917e-06, "epoch": 1.9789674952198852, "percentage": 66.09, "elapsed_time": "1:33:04", "remaining_time": "0:47:44"}
346
+ {"current_steps": 346, "total_steps": 522, "loss": 0.4568, "lr": 6.180902766263113e-06, "epoch": 1.9847036328871894, "percentage": 66.28, "elapsed_time": "1:33:21", "remaining_time": "0:47:29"}
347
+ {"current_steps": 347, "total_steps": 522, "loss": 0.4439, "lr": 6.119081473277502e-06, "epoch": 1.9904397705544934, "percentage": 66.48, "elapsed_time": "1:33:37", "remaining_time": "0:47:12"}
348
+ {"current_steps": 348, "total_steps": 522, "loss": 0.4076, "lr": 6.057434315649304e-06, "epoch": 1.9961759082217974, "percentage": 66.67, "elapsed_time": "1:33:54", "remaining_time": "0:46:57"}
349
+ {"current_steps": 349, "total_steps": 522, "loss": 0.6431, "lr": 5.9959640594633304e-06, "epoch": 2.0019120458891013, "percentage": 66.86, "elapsed_time": "1:35:00", "remaining_time": "0:47:05"}
350
+ {"current_steps": 350, "total_steps": 522, "loss": 0.4089, "lr": 5.934673462866907e-06, "epoch": 2.0076481835564053, "percentage": 67.05, "elapsed_time": "1:35:15", "remaining_time": "0:46:48"}
351
+ {"current_steps": 351, "total_steps": 522, "loss": 0.3998, "lr": 5.873565275946088e-06, "epoch": 2.0133843212237093, "percentage": 67.24, "elapsed_time": "1:35:31", "remaining_time": "0:46:32"}
352
+ {"current_steps": 352, "total_steps": 522, "loss": 0.3835, "lr": 5.812642240602289e-06, "epoch": 2.019120458891013, "percentage": 67.43, "elapsed_time": "1:35:45", "remaining_time": "0:46:14"}
353
+ {"current_steps": 353, "total_steps": 522, "loss": 0.3859, "lr": 5.7519070904292255e-06, "epoch": 2.024856596558317, "percentage": 67.62, "elapsed_time": "1:36:01", "remaining_time": "0:45:58"}
354
+ {"current_steps": 354, "total_steps": 522, "loss": 0.364, "lr": 5.6913625505902966e-06, "epoch": 2.0305927342256216, "percentage": 67.82, "elapsed_time": "1:36:17", "remaining_time": "0:45:42"}
355
+ {"current_steps": 355, "total_steps": 522, "loss": 0.3577, "lr": 5.631011337696272e-06, "epoch": 2.0363288718929256, "percentage": 68.01, "elapsed_time": "1:36:36", "remaining_time": "0:45:26"}
356
+ {"current_steps": 356, "total_steps": 522, "loss": 0.3708, "lr": 5.570856159683418e-06, "epoch": 2.0420650095602295, "percentage": 68.2, "elapsed_time": "1:36:51", "remaining_time": "0:45:10"}
357
+ {"current_steps": 357, "total_steps": 522, "loss": 0.3954, "lr": 5.510899715691984e-06, "epoch": 2.0478011472275335, "percentage": 68.39, "elapsed_time": "1:37:11", "remaining_time": "0:44:55"}
358
+ {"current_steps": 358, "total_steps": 522, "loss": 0.3767, "lr": 5.451144695945116e-06, "epoch": 2.0535372848948374, "percentage": 68.58, "elapsed_time": "1:37:31", "remaining_time": "0:44:40"}