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:
|
| 3 |
size 4877660776
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ce964af0f8e6a7efd6988432d50990bc1a2f34fca57e4d4aa154ecceade30e4c
|
| 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:
|
| 3 |
size 4932751008
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:36e4307de9e87412f16b552becef4342f4534f96469c96d7dd931fa33748e519
|
| 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:
|
| 3 |
size 4330865200
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:13d87dd96f07c2a1048e775532eb31d7de3bae81ed05a26b9704a2e651903c66
|
| 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:
|
| 3 |
size 1089994880
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:efba5d3022af93fb22c3901033a5cc02286b4ea12b028c57e980d33e2b01c8fa
|
| 3 |
size 1089994880
|
trainer_log.jsonl
CHANGED
|
@@ -146,3 +146,151 @@
|
|
| 146 |
{"current_steps": 146, "total_steps": 441, "loss": 0.688, "lr": 6.78319538157411e-05, "epoch": 0.9902501059771089, "percentage": 33.11, "elapsed_time": "4:21:42", "remaining_time": "8:48:47"}
|
| 147 |
{"current_steps": 147, "total_steps": 441, "loss": 0.6996, "lr": 6.760316045928449e-05, "epoch": 0.9970326409495549, "percentage": 33.33, "elapsed_time": "4:23:29", "remaining_time": "8:46:59"}
|
| 148 |
{"current_steps": 148, "total_steps": 441, "loss": 1.0973, "lr": 6.737262983848554e-05, "epoch": 1.0038151759220009, "percentage": 33.56, "elapsed_time": "4:26:21", "remaining_time": "8:47:18"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 146 |
{"current_steps": 146, "total_steps": 441, "loss": 0.688, "lr": 6.78319538157411e-05, "epoch": 0.9902501059771089, "percentage": 33.11, "elapsed_time": "4:21:42", "remaining_time": "8:48:47"}
|
| 147 |
{"current_steps": 147, "total_steps": 441, "loss": 0.6996, "lr": 6.760316045928449e-05, "epoch": 0.9970326409495549, "percentage": 33.33, "elapsed_time": "4:23:29", "remaining_time": "8:46:59"}
|
| 148 |
{"current_steps": 148, "total_steps": 441, "loss": 1.0973, "lr": 6.737262983848554e-05, "epoch": 1.0038151759220009, "percentage": 33.56, "elapsed_time": "4:26:21", "remaining_time": "8:47:18"}
|
| 149 |
+
{"current_steps": 149, "total_steps": 441, "loss": 0.6724, "lr": 6.714037646228529e-05, "epoch": 1.0105977108944468, "percentage": 33.79, "elapsed_time": "4:28:08", "remaining_time": "8:45:28"}
|
| 150 |
+
{"current_steps": 150, "total_steps": 441, "loss": 0.6904, "lr": 6.690641494805011e-05, "epoch": 1.0173802458668928, "percentage": 34.01, "elapsed_time": "4:29:54", "remaining_time": "8:43:37"}
|
| 151 |
+
{"current_steps": 151, "total_steps": 441, "loss": 0.6763, "lr": 6.667076002065168e-05, "epoch": 1.0241627808393388, "percentage": 34.24, "elapsed_time": "4:31:41", "remaining_time": "8:41:47"}
|
| 152 |
+
{"current_steps": 152, "total_steps": 441, "loss": 0.6928, "lr": 6.643342651154028e-05, "epoch": 1.0309453158117847, "percentage": 34.47, "elapsed_time": "4:33:28", "remaining_time": "8:39:57"}
|
| 153 |
+
{"current_steps": 153, "total_steps": 441, "loss": 0.6914, "lr": 6.619442935781141e-05, "epoch": 1.0377278507842307, "percentage": 34.69, "elapsed_time": "4:35:16", "remaining_time": "8:38:09"}
|
| 154 |
+
{"current_steps": 154, "total_steps": 441, "loss": 0.6778, "lr": 6.595378360126555e-05, "epoch": 1.0445103857566767, "percentage": 34.92, "elapsed_time": "4:37:03", "remaining_time": "8:36:20"}
|
| 155 |
+
{"current_steps": 155, "total_steps": 441, "loss": 0.6776, "lr": 6.571150438746157e-05, "epoch": 1.0512929207291226, "percentage": 35.15, "elapsed_time": "4:38:50", "remaining_time": "8:34:30"}
|
| 156 |
+
{"current_steps": 156, "total_steps": 441, "loss": 0.6792, "lr": 6.546760696476354e-05, "epoch": 1.0580754557015684, "percentage": 35.37, "elapsed_time": "4:40:37", "remaining_time": "8:32:41"}
|
| 157 |
+
{"current_steps": 157, "total_steps": 441, "loss": 0.6813, "lr": 6.52221066833809e-05, "epoch": 1.0648579906740143, "percentage": 35.6, "elapsed_time": "4:42:25", "remaining_time": "8:30:52"}
|
| 158 |
+
{"current_steps": 158, "total_steps": 441, "loss": 0.6758, "lr": 6.497501899440255e-05, "epoch": 1.0716405256464603, "percentage": 35.83, "elapsed_time": "4:44:12", "remaining_time": "8:29:03"}
|
| 159 |
+
{"current_steps": 159, "total_steps": 441, "loss": 0.6846, "lr": 6.472635944882421e-05, "epoch": 1.0784230606189062, "percentage": 36.05, "elapsed_time": "4:45:59", "remaining_time": "8:27:14"}
|
| 160 |
+
{"current_steps": 160, "total_steps": 441, "loss": 0.6659, "lr": 6.447614369656987e-05, "epoch": 1.0852055955913522, "percentage": 36.28, "elapsed_time": "4:47:46", "remaining_time": "8:25:24"}
|
| 161 |
+
{"current_steps": 161, "total_steps": 441, "loss": 0.6688, "lr": 6.422438748550667e-05, "epoch": 1.0919881305637982, "percentage": 36.51, "elapsed_time": "4:49:33", "remaining_time": "8:23:35"}
|
| 162 |
+
{"current_steps": 162, "total_steps": 441, "loss": 0.675, "lr": 6.397110666045388e-05, "epoch": 1.0987706655362441, "percentage": 36.73, "elapsed_time": "4:51:21", "remaining_time": "8:21:46"}
|
| 163 |
+
{"current_steps": 163, "total_steps": 441, "loss": 0.6714, "lr": 6.371631716218563e-05, "epoch": 1.10555320050869, "percentage": 36.96, "elapsed_time": "4:53:08", "remaining_time": "8:19:57"}
|
| 164 |
+
{"current_steps": 164, "total_steps": 441, "loss": 0.6818, "lr": 6.346003502642762e-05, "epoch": 1.112335735481136, "percentage": 37.19, "elapsed_time": "4:54:55", "remaining_time": "8:18:07"}
|
| 165 |
+
{"current_steps": 165, "total_steps": 441, "loss": 0.6663, "lr": 6.320227638284793e-05, "epoch": 1.119118270453582, "percentage": 37.41, "elapsed_time": "4:56:42", "remaining_time": "8:16:18"}
|
| 166 |
+
{"current_steps": 166, "total_steps": 441, "loss": 0.6784, "lr": 6.294305745404185e-05, "epoch": 1.125900805426028, "percentage": 37.64, "elapsed_time": "4:58:30", "remaining_time": "8:14:30"}
|
| 167 |
+
{"current_steps": 167, "total_steps": 441, "loss": 0.6867, "lr": 6.268239455451083e-05, "epoch": 1.132683340398474, "percentage": 37.87, "elapsed_time": "5:00:17", "remaining_time": "8:12:42"}
|
| 168 |
+
{"current_steps": 168, "total_steps": 441, "loss": 0.6672, "lr": 6.242030408963576e-05, "epoch": 1.13946587537092, "percentage": 38.1, "elapsed_time": "5:02:05", "remaining_time": "8:10:53"}
|
| 169 |
+
{"current_steps": 169, "total_steps": 441, "loss": 0.6651, "lr": 6.215680255464442e-05, "epoch": 1.1462484103433659, "percentage": 38.32, "elapsed_time": "5:03:52", "remaining_time": "8:09:05"}
|
| 170 |
+
{"current_steps": 170, "total_steps": 441, "loss": 0.6669, "lr": 6.18919065335733e-05, "epoch": 1.1530309453158119, "percentage": 38.55, "elapsed_time": "5:05:40", "remaining_time": "8:07:16"}
|
| 171 |
+
{"current_steps": 171, "total_steps": 441, "loss": 0.6636, "lr": 6.162563269822391e-05, "epoch": 1.1598134802882578, "percentage": 38.78, "elapsed_time": "5:07:27", "remaining_time": "8:05:27"}
|
| 172 |
+
{"current_steps": 172, "total_steps": 441, "loss": 0.675, "lr": 6.135799780711345e-05, "epoch": 1.1665960152607038, "percentage": 39.0, "elapsed_time": "5:09:15", "remaining_time": "8:03:40"}
|
| 173 |
+
{"current_steps": 173, "total_steps": 441, "loss": 0.6833, "lr": 6.10890187044201e-05, "epoch": 1.1733785502331497, "percentage": 39.23, "elapsed_time": "5:11:02", "remaining_time": "8:01:51"}
|
| 174 |
+
{"current_steps": 174, "total_steps": 441, "loss": 0.6682, "lr": 6.0818712318922894e-05, "epoch": 1.1801610852055955, "percentage": 39.46, "elapsed_time": "5:12:50", "remaining_time": "8:00:03"}
|
| 175 |
+
{"current_steps": 175, "total_steps": 441, "loss": 0.683, "lr": 6.054709566293627e-05, "epoch": 1.1869436201780414, "percentage": 39.68, "elapsed_time": "5:14:38", "remaining_time": "7:58:14"}
|
| 176 |
+
{"current_steps": 176, "total_steps": 441, "loss": 0.6638, "lr": 6.0274185831239325e-05, "epoch": 1.1937261551504874, "percentage": 39.91, "elapsed_time": "5:16:25", "remaining_time": "7:56:25"}
|
| 177 |
+
{"current_steps": 177, "total_steps": 441, "loss": 0.6725, "lr": 6.000000000000001e-05, "epoch": 1.2005086901229334, "percentage": 40.14, "elapsed_time": "5:18:13", "remaining_time": "7:54:38"}
|
| 178 |
+
{"current_steps": 178, "total_steps": 441, "loss": 0.6692, "lr": 5.972455542569402e-05, "epoch": 1.2072912250953793, "percentage": 40.36, "elapsed_time": "5:20:01", "remaining_time": "7:52:50"}
|
| 179 |
+
{"current_steps": 179, "total_steps": 441, "loss": 0.6623, "lr": 5.944786944401875e-05, "epoch": 1.2140737600678253, "percentage": 40.59, "elapsed_time": "5:21:48", "remaining_time": "7:51:01"}
|
| 180 |
+
{"current_steps": 180, "total_steps": 441, "loss": 0.6842, "lr": 5.916995946880228e-05, "epoch": 1.2208562950402713, "percentage": 40.82, "elapsed_time": "5:23:36", "remaining_time": "7:49:14"}
|
| 181 |
+
{"current_steps": 181, "total_steps": 441, "loss": 0.6786, "lr": 5.889084299090732e-05, "epoch": 1.2276388300127172, "percentage": 41.04, "elapsed_time": "5:25:27", "remaining_time": "7:47:30"}
|
| 182 |
+
{"current_steps": 182, "total_steps": 441, "loss": 0.6726, "lr": 5.861053757713043e-05, "epoch": 1.2344213649851632, "percentage": 41.27, "elapsed_time": "5:27:17", "remaining_time": "7:45:46"}
|
| 183 |
+
{"current_steps": 183, "total_steps": 441, "loss": 0.6742, "lr": 5.832906086909642e-05, "epoch": 1.2412038999576092, "percentage": 41.5, "elapsed_time": "5:29:04", "remaining_time": "7:43:57"}
|
| 184 |
+
{"current_steps": 184, "total_steps": 441, "loss": 0.6636, "lr": 5.8046430582148034e-05, "epoch": 1.2479864349300551, "percentage": 41.72, "elapsed_time": "5:30:51", "remaining_time": "7:42:07"}
|
| 185 |
+
{"current_steps": 185, "total_steps": 441, "loss": 0.6745, "lr": 5.776266450423097e-05, "epoch": 1.254768969902501, "percentage": 41.95, "elapsed_time": "5:32:39", "remaining_time": "7:40:19"}
|
| 186 |
+
{"current_steps": 186, "total_steps": 441, "loss": 0.692, "lr": 5.747778049477438e-05, "epoch": 1.261551504874947, "percentage": 42.18, "elapsed_time": "5:34:26", "remaining_time": "7:38:31"}
|
| 187 |
+
{"current_steps": 187, "total_steps": 441, "loss": 0.6851, "lr": 5.7191796483566874e-05, "epoch": 1.268334039847393, "percentage": 42.4, "elapsed_time": "5:36:13", "remaining_time": "7:36:41"}
|
| 188 |
+
{"current_steps": 188, "total_steps": 441, "loss": 0.6694, "lr": 5.6904730469627985e-05, "epoch": 1.275116574819839, "percentage": 42.63, "elapsed_time": "5:38:00", "remaining_time": "7:34:52"}
|
| 189 |
+
{"current_steps": 189, "total_steps": 441, "loss": 0.6674, "lr": 5.661660052007547e-05, "epoch": 1.281899109792285, "percentage": 42.86, "elapsed_time": "5:39:47", "remaining_time": "7:33:03"}
|
| 190 |
+
{"current_steps": 190, "total_steps": 441, "loss": 0.6574, "lr": 5.632742476898813e-05, "epoch": 1.288681644764731, "percentage": 43.08, "elapsed_time": "5:41:34", "remaining_time": "7:31:14"}
|
| 191 |
+
{"current_steps": 191, "total_steps": 441, "loss": 0.6651, "lr": 5.6037221416264554e-05, "epoch": 1.2954641797371766, "percentage": 43.31, "elapsed_time": "5:43:21", "remaining_time": "7:29:25"}
|
| 192 |
+
{"current_steps": 192, "total_steps": 441, "loss": 0.6741, "lr": 5.574600872647766e-05, "epoch": 1.3022467147096228, "percentage": 43.54, "elapsed_time": "5:45:08", "remaining_time": "7:27:35"}
|
| 193 |
+
{"current_steps": 193, "total_steps": 441, "loss": 0.6735, "lr": 5.5453805027725145e-05, "epoch": 1.3090292496820686, "percentage": 43.76, "elapsed_time": "5:46:54", "remaining_time": "7:25:45"}
|
| 194 |
+
{"current_steps": 194, "total_steps": 441, "loss": 0.6648, "lr": 5.516062871047602e-05, "epoch": 1.3158117846545148, "percentage": 43.99, "elapsed_time": "5:48:40", "remaining_time": "7:23:56"}
|
| 195 |
+
{"current_steps": 195, "total_steps": 441, "loss": 0.682, "lr": 5.48664982264131e-05, "epoch": 1.3225943196269605, "percentage": 44.22, "elapsed_time": "5:50:27", "remaining_time": "7:22:07"}
|
| 196 |
+
{"current_steps": 196, "total_steps": 441, "loss": 0.6748, "lr": 5.4571432087271775e-05, "epoch": 1.3293768545994065, "percentage": 44.44, "elapsed_time": "5:52:15", "remaining_time": "7:20:18"}
|
| 197 |
+
{"current_steps": 197, "total_steps": 441, "loss": 0.677, "lr": 5.427544886367488e-05, "epoch": 1.3361593895718524, "percentage": 44.67, "elapsed_time": "5:54:01", "remaining_time": "7:18:29"}
|
| 198 |
+
{"current_steps": 198, "total_steps": 441, "loss": 0.6652, "lr": 5.397856718396394e-05, "epoch": 1.3429419245442984, "percentage": 44.9, "elapsed_time": "5:55:47", "remaining_time": "7:16:39"}
|
| 199 |
+
{"current_steps": 199, "total_steps": 441, "loss": 0.6664, "lr": 5.368080573302676e-05, "epoch": 1.3497244595167444, "percentage": 45.12, "elapsed_time": "5:57:34", "remaining_time": "7:14:50"}
|
| 200 |
+
{"current_steps": 200, "total_steps": 441, "loss": 0.6675, "lr": 5.3382183251121415e-05, "epoch": 1.3565069944891903, "percentage": 45.35, "elapsed_time": "5:59:21", "remaining_time": "7:13:01"}
|
| 201 |
+
{"current_steps": 201, "total_steps": 441, "loss": 0.6706, "lr": 5.3082718532696874e-05, "epoch": 1.3632895294616363, "percentage": 45.58, "elapsed_time": "6:01:07", "remaining_time": "7:11:12"}
|
| 202 |
+
{"current_steps": 202, "total_steps": 441, "loss": 0.6631, "lr": 5.2782430425210004e-05, "epoch": 1.3700720644340822, "percentage": 45.8, "elapsed_time": "6:02:54", "remaining_time": "7:09:22"}
|
| 203 |
+
{"current_steps": 203, "total_steps": 441, "loss": 0.665, "lr": 5.2481337827939486e-05, "epoch": 1.3768545994065282, "percentage": 46.03, "elapsed_time": "6:04:41", "remaining_time": "7:07:34"}
|
| 204 |
+
{"current_steps": 204, "total_steps": 441, "loss": 0.6737, "lr": 5.217945969079629e-05, "epoch": 1.3836371343789742, "percentage": 46.26, "elapsed_time": "6:06:28", "remaining_time": "7:05:45"}
|
| 205 |
+
{"current_steps": 205, "total_steps": 441, "loss": 0.6773, "lr": 5.1876815013131e-05, "epoch": 1.3904196693514201, "percentage": 46.49, "elapsed_time": "6:08:14", "remaining_time": "7:03:55"}
|
| 206 |
+
{"current_steps": 206, "total_steps": 441, "loss": 0.674, "lr": 5.157342284253812e-05, "epoch": 1.397202204323866, "percentage": 46.71, "elapsed_time": "6:10:01", "remaining_time": "7:02:07"}
|
| 207 |
+
{"current_steps": 207, "total_steps": 441, "loss": 0.6817, "lr": 5.1269302273657195e-05, "epoch": 1.403984739296312, "percentage": 46.94, "elapsed_time": "6:11:48", "remaining_time": "7:00:18"}
|
| 208 |
+
{"current_steps": 208, "total_steps": 441, "loss": 0.6536, "lr": 5.0964472446971114e-05, "epoch": 1.410767274268758, "percentage": 47.17, "elapsed_time": "6:13:36", "remaining_time": "6:58:30"}
|
| 209 |
+
{"current_steps": 209, "total_steps": 441, "loss": 0.6694, "lr": 5.06589525476014e-05, "epoch": 1.417549809241204, "percentage": 47.39, "elapsed_time": "6:15:23", "remaining_time": "6:56:42"}
|
| 210 |
+
{"current_steps": 210, "total_steps": 441, "loss": 0.6607, "lr": 5.0352761804100835e-05, "epoch": 1.4243323442136497, "percentage": 47.62, "elapsed_time": "6:17:10", "remaining_time": "6:54:53"}
|
| 211 |
+
{"current_steps": 211, "total_steps": 441, "loss": 0.6591, "lr": 5.004591948724317e-05, "epoch": 1.431114879186096, "percentage": 47.85, "elapsed_time": "6:18:57", "remaining_time": "6:53:04"}
|
| 212 |
+
{"current_steps": 212, "total_steps": 441, "loss": 0.6698, "lr": 4.9738444908810365e-05, "epoch": 1.4378974141585417, "percentage": 48.07, "elapsed_time": "6:20:43", "remaining_time": "6:51:15"}
|
| 213 |
+
{"current_steps": 213, "total_steps": 441, "loss": 0.6543, "lr": 4.94303574203771e-05, "epoch": 1.4446799491309876, "percentage": 48.3, "elapsed_time": "6:22:31", "remaining_time": "6:49:27"}
|
| 214 |
+
{"current_steps": 214, "total_steps": 441, "loss": 0.6696, "lr": 4.9121676412092874e-05, "epoch": 1.4514624841034336, "percentage": 48.53, "elapsed_time": "6:24:19", "remaining_time": "6:47:39"}
|
| 215 |
+
{"current_steps": 215, "total_steps": 441, "loss": 0.6745, "lr": 4.881242131146163e-05, "epoch": 1.4582450190758796, "percentage": 48.75, "elapsed_time": "6:26:07", "remaining_time": "6:45:52"}
|
| 216 |
+
{"current_steps": 216, "total_steps": 441, "loss": 0.6702, "lr": 4.8502611582119065e-05, "epoch": 1.4650275540483255, "percentage": 48.98, "elapsed_time": "6:27:56", "remaining_time": "6:44:06"}
|
| 217 |
+
{"current_steps": 217, "total_steps": 441, "loss": 0.6739, "lr": 4.819226672260763e-05, "epoch": 1.4718100890207715, "percentage": 49.21, "elapsed_time": "6:29:45", "remaining_time": "6:42:19"}
|
| 218 |
+
{"current_steps": 218, "total_steps": 441, "loss": 0.6678, "lr": 4.788140626514933e-05, "epoch": 1.4785926239932174, "percentage": 49.43, "elapsed_time": "6:31:35", "remaining_time": "6:40:34"}
|
| 219 |
+
{"current_steps": 219, "total_steps": 441, "loss": 0.6578, "lr": 4.7570049774416414e-05, "epoch": 1.4853751589656634, "percentage": 49.66, "elapsed_time": "6:33:25", "remaining_time": "6:38:48"}
|
| 220 |
+
{"current_steps": 220, "total_steps": 441, "loss": 0.6687, "lr": 4.7258216846300106e-05, "epoch": 1.4921576939381094, "percentage": 49.89, "elapsed_time": "6:35:11", "remaining_time": "6:36:59"}
|
| 221 |
+
{"current_steps": 221, "total_steps": 441, "loss": 0.6695, "lr": 4.694592710667723e-05, "epoch": 1.4989402289105553, "percentage": 50.11, "elapsed_time": "6:36:57", "remaining_time": "6:35:10"}
|
| 222 |
+
{"current_steps": 222, "total_steps": 441, "loss": 0.6655, "lr": 4.663320021017497e-05, "epoch": 1.5057227638830013, "percentage": 50.34, "elapsed_time": "6:38:44", "remaining_time": "6:33:21"}
|
| 223 |
+
{"current_steps": 223, "total_steps": 441, "loss": 0.6727, "lr": 4.6320055838934e-05, "epoch": 1.5125052988554473, "percentage": 50.57, "elapsed_time": "6:40:31", "remaining_time": "6:31:32"}
|
| 224 |
+
{"current_steps": 224, "total_steps": 441, "loss": 0.6606, "lr": 4.6006513701369616e-05, "epoch": 1.5192878338278932, "percentage": 50.79, "elapsed_time": "6:42:17", "remaining_time": "6:29:43"}
|
| 225 |
+
{"current_steps": 225, "total_steps": 441, "loss": 0.6759, "lr": 4.5692593530931416e-05, "epoch": 1.526070368800339, "percentage": 51.02, "elapsed_time": "6:44:05", "remaining_time": "6:27:55"}
|
| 226 |
+
{"current_steps": 226, "total_steps": 441, "loss": 0.6624, "lr": 4.5378315084861276e-05, "epoch": 1.5328529037727852, "percentage": 51.25, "elapsed_time": "6:45:52", "remaining_time": "6:26:06"}
|
| 227 |
+
{"current_steps": 227, "total_steps": 441, "loss": 0.6599, "lr": 4.506369814294998e-05, "epoch": 1.539635438745231, "percentage": 51.47, "elapsed_time": "6:47:39", "remaining_time": "6:24:18"}
|
| 228 |
+
{"current_steps": 228, "total_steps": 441, "loss": 0.6764, "lr": 4.474876250629221e-05, "epoch": 1.546417973717677, "percentage": 51.7, "elapsed_time": "6:49:25", "remaining_time": "6:22:29"}
|
| 229 |
+
{"current_steps": 229, "total_steps": 441, "loss": 0.6643, "lr": 4.4433527996040443e-05, "epoch": 1.5532005086901228, "percentage": 51.93, "elapsed_time": "6:51:12", "remaining_time": "6:20:41"}
|
| 230 |
+
{"current_steps": 230, "total_steps": 441, "loss": 0.6644, "lr": 4.411801445215739e-05, "epoch": 1.559983043662569, "percentage": 52.15, "elapsed_time": "6:52:59", "remaining_time": "6:18:52"}
|
| 231 |
+
{"current_steps": 231, "total_steps": 441, "loss": 0.6559, "lr": 4.38022417321673e-05, "epoch": 1.5667655786350148, "percentage": 52.38, "elapsed_time": "6:54:46", "remaining_time": "6:17:04"}
|
| 232 |
+
{"current_steps": 232, "total_steps": 441, "loss": 0.6733, "lr": 4.348622970990634e-05, "epoch": 1.573548113607461, "percentage": 52.61, "elapsed_time": "6:56:36", "remaining_time": "6:15:18"}
|
| 233 |
+
{"current_steps": 233, "total_steps": 441, "loss": 0.6609, "lr": 4.316999827427154e-05, "epoch": 1.5803306485799067, "percentage": 52.83, "elapsed_time": "6:58:29", "remaining_time": "6:13:34"}
|
| 234 |
+
{"current_steps": 234, "total_steps": 441, "loss": 0.6681, "lr": 4.2853567327969296e-05, "epoch": 1.5871131835523526, "percentage": 53.06, "elapsed_time": "7:00:18", "remaining_time": "6:11:48"}
|
| 235 |
+
{"current_steps": 235, "total_steps": 441, "loss": 0.6822, "lr": 4.2536956786262585e-05, "epoch": 1.5938957185247986, "percentage": 53.29, "elapsed_time": "7:02:05", "remaining_time": "6:10:00"}
|
| 236 |
+
{"current_steps": 236, "total_steps": 441, "loss": 0.6636, "lr": 4.222018657571761e-05, "epoch": 1.6006782534972446, "percentage": 53.51, "elapsed_time": "7:03:52", "remaining_time": "6:08:11"}
|
| 237 |
+
{"current_steps": 237, "total_steps": 441, "loss": 0.6701, "lr": 4.19032766329497e-05, "epoch": 1.6074607884696905, "percentage": 53.74, "elapsed_time": "7:05:39", "remaining_time": "6:06:23"}
|
| 238 |
+
{"current_steps": 238, "total_steps": 441, "loss": 0.6786, "lr": 4.1586246903368496e-05, "epoch": 1.6142433234421365, "percentage": 53.97, "elapsed_time": "7:07:25", "remaining_time": "6:04:34"}
|
| 239 |
+
{"current_steps": 239, "total_steps": 441, "loss": 0.6791, "lr": 4.126911733992272e-05, "epoch": 1.6210258584145825, "percentage": 54.2, "elapsed_time": "7:09:12", "remaining_time": "6:02:45"}
|
| 240 |
+
{"current_steps": 240, "total_steps": 441, "loss": 0.6591, "lr": 4.0951907901844296e-05, "epoch": 1.6278083933870284, "percentage": 54.42, "elapsed_time": "7:10:59", "remaining_time": "6:00:57"}
|
| 241 |
+
{"current_steps": 241, "total_steps": 441, "loss": 0.6607, "lr": 4.063463855339232e-05, "epoch": 1.6345909283594744, "percentage": 54.65, "elapsed_time": "7:12:46", "remaining_time": "5:59:08"}
|
| 242 |
+
{"current_steps": 242, "total_steps": 441, "loss": 0.6636, "lr": 4.031732926259639e-05, "epoch": 1.6413734633319204, "percentage": 54.88, "elapsed_time": "7:14:32", "remaining_time": "5:57:19"}
|
| 243 |
+
{"current_steps": 243, "total_steps": 441, "loss": 0.6582, "lr": 4e-05, "epoch": 1.6481559983043663, "percentage": 55.1, "elapsed_time": "7:16:19", "remaining_time": "5:55:31"}
|
| 244 |
+
{"current_steps": 244, "total_steps": 441, "loss": 0.6581, "lr": 3.9682670737403624e-05, "epoch": 1.654938533276812, "percentage": 55.33, "elapsed_time": "7:18:06", "remaining_time": "5:53:43"}
|
| 245 |
+
{"current_steps": 245, "total_steps": 441, "loss": 0.6597, "lr": 3.9365361446607684e-05, "epoch": 1.6617210682492582, "percentage": 55.56, "elapsed_time": "7:19:53", "remaining_time": "5:51:55"}
|
| 246 |
+
{"current_steps": 246, "total_steps": 441, "loss": 0.6609, "lr": 3.904809209815571e-05, "epoch": 1.668503603221704, "percentage": 55.78, "elapsed_time": "7:21:40", "remaining_time": "5:50:06"}
|
| 247 |
+
{"current_steps": 247, "total_steps": 441, "loss": 0.6588, "lr": 3.87308826600773e-05, "epoch": 1.6752861381941502, "percentage": 56.01, "elapsed_time": "7:23:27", "remaining_time": "5:48:17"}
|
| 248 |
+
{"current_steps": 248, "total_steps": 441, "loss": 0.6688, "lr": 3.841375309663151e-05, "epoch": 1.682068673166596, "percentage": 56.24, "elapsed_time": "7:25:13", "remaining_time": "5:46:29"}
|
| 249 |
+
{"current_steps": 249, "total_steps": 441, "loss": 0.6711, "lr": 3.809672336705031e-05, "epoch": 1.688851208139042, "percentage": 56.46, "elapsed_time": "7:27:01", "remaining_time": "5:44:41"}
|
| 250 |
+
{"current_steps": 250, "total_steps": 441, "loss": 0.676, "lr": 3.7779813424282404e-05, "epoch": 1.6956337431114878, "percentage": 56.69, "elapsed_time": "7:28:51", "remaining_time": "5:42:55"}
|
| 251 |
+
{"current_steps": 251, "total_steps": 441, "loss": 0.6694, "lr": 3.746304321373742e-05, "epoch": 1.702416278083934, "percentage": 56.92, "elapsed_time": "7:30:44", "remaining_time": "5:41:11"}
|
| 252 |
+
{"current_steps": 252, "total_steps": 441, "loss": 0.6545, "lr": 3.714643267203071e-05, "epoch": 1.7091988130563798, "percentage": 57.14, "elapsed_time": "7:32:39", "remaining_time": "5:39:29"}
|
| 253 |
+
{"current_steps": 253, "total_steps": 441, "loss": 0.6766, "lr": 3.683000172572846e-05, "epoch": 1.7159813480288257, "percentage": 57.37, "elapsed_time": "7:34:29", "remaining_time": "5:37:43"}
|
| 254 |
+
{"current_steps": 254, "total_steps": 441, "loss": 0.6574, "lr": 3.6513770290093674e-05, "epoch": 1.7227638830012717, "percentage": 57.6, "elapsed_time": "7:36:17", "remaining_time": "5:35:56"}
|
| 255 |
+
{"current_steps": 255, "total_steps": 441, "loss": 0.6635, "lr": 3.6197758267832705e-05, "epoch": 1.7295464179737177, "percentage": 57.82, "elapsed_time": "7:38:07", "remaining_time": "5:34:09"}
|
| 256 |
+
{"current_steps": 256, "total_steps": 441, "loss": 0.6676, "lr": 3.5881985547842627e-05, "epoch": 1.7363289529461636, "percentage": 58.05, "elapsed_time": "7:39:56", "remaining_time": "5:32:22"}
|
| 257 |
+
{"current_steps": 257, "total_steps": 441, "loss": 0.6624, "lr": 3.556647200395956e-05, "epoch": 1.7431114879186096, "percentage": 58.28, "elapsed_time": "7:41:43", "remaining_time": "5:30:34"}
|
| 258 |
+
{"current_steps": 258, "total_steps": 441, "loss": 0.6526, "lr": 3.5251237493707804e-05, "epoch": 1.7498940228910556, "percentage": 58.5, "elapsed_time": "7:43:29", "remaining_time": "5:28:45"}
|
| 259 |
+
{"current_steps": 259, "total_steps": 441, "loss": 0.6752, "lr": 3.493630185705003e-05, "epoch": 1.7566765578635015, "percentage": 58.73, "elapsed_time": "7:45:16", "remaining_time": "5:26:57"}
|
| 260 |
+
{"current_steps": 260, "total_steps": 441, "loss": 0.6537, "lr": 3.462168491513873e-05, "epoch": 1.7634590928359475, "percentage": 58.96, "elapsed_time": "7:47:03", "remaining_time": "5:25:08"}
|
| 261 |
+
{"current_steps": 261, "total_steps": 441, "loss": 0.6699, "lr": 3.4307406469068604e-05, "epoch": 1.7702416278083932, "percentage": 59.18, "elapsed_time": "7:48:50", "remaining_time": "5:23:20"}
|
| 262 |
+
{"current_steps": 262, "total_steps": 441, "loss": 0.6505, "lr": 3.3993486298630384e-05, "epoch": 1.7770241627808394, "percentage": 59.41, "elapsed_time": "7:50:37", "remaining_time": "5:21:31"}
|
| 263 |
+
{"current_steps": 263, "total_steps": 441, "loss": 0.6646, "lr": 3.367994416106601e-05, "epoch": 1.7838066977532852, "percentage": 59.64, "elapsed_time": "7:52:23", "remaining_time": "5:19:43"}
|
| 264 |
+
{"current_steps": 264, "total_steps": 441, "loss": 0.6641, "lr": 3.3366799789825044e-05, "epoch": 1.7905892327257313, "percentage": 59.86, "elapsed_time": "7:54:12", "remaining_time": "5:17:56"}
|
| 265 |
+
{"current_steps": 265, "total_steps": 441, "loss": 0.6591, "lr": 3.305407289332279e-05, "epoch": 1.797371767698177, "percentage": 60.09, "elapsed_time": "7:56:01", "remaining_time": "5:16:08"}
|
| 266 |
+
{"current_steps": 266, "total_steps": 441, "loss": 0.6607, "lr": 3.27417831536999e-05, "epoch": 1.8041543026706233, "percentage": 60.32, "elapsed_time": "7:57:47", "remaining_time": "5:14:20"}
|
| 267 |
+
{"current_steps": 267, "total_steps": 441, "loss": 0.6578, "lr": 3.2429950225583606e-05, "epoch": 1.810936837643069, "percentage": 60.54, "elapsed_time": "7:59:34", "remaining_time": "5:12:31"}
|
| 268 |
+
{"current_steps": 268, "total_steps": 441, "loss": 0.6666, "lr": 3.2118593734850686e-05, "epoch": 1.8177193726155152, "percentage": 60.77, "elapsed_time": "8:01:20", "remaining_time": "5:10:43"}
|
| 269 |
+
{"current_steps": 269, "total_steps": 441, "loss": 0.6666, "lr": 3.180773327739238e-05, "epoch": 1.824501907587961, "percentage": 61.0, "elapsed_time": "8:03:08", "remaining_time": "5:08:55"}
|
| 270 |
+
{"current_steps": 270, "total_steps": 441, "loss": 0.6689, "lr": 3.1497388417880935e-05, "epoch": 1.831284442560407, "percentage": 61.22, "elapsed_time": "8:04:54", "remaining_time": "5:07:06"}
|
| 271 |
+
{"current_steps": 271, "total_steps": 441, "loss": 0.6618, "lr": 3.118757868853838e-05, "epoch": 1.8380669775328529, "percentage": 61.45, "elapsed_time": "8:06:41", "remaining_time": "5:05:18"}
|
| 272 |
+
{"current_steps": 272, "total_steps": 441, "loss": 0.6516, "lr": 3.087832358790715e-05, "epoch": 1.8448495125052988, "percentage": 61.68, "elapsed_time": "8:08:28", "remaining_time": "5:03:30"}
|
| 273 |
+
{"current_steps": 273, "total_steps": 441, "loss": 0.6632, "lr": 3.0569642579622905e-05, "epoch": 1.8516320474777448, "percentage": 61.9, "elapsed_time": "8:10:15", "remaining_time": "5:01:41"}
|
| 274 |
+
{"current_steps": 274, "total_steps": 441, "loss": 0.6652, "lr": 3.0261555091189648e-05, "epoch": 1.8584145824501908, "percentage": 62.13, "elapsed_time": "8:12:02", "remaining_time": "4:59:53"}
|
| 275 |
+
{"current_steps": 275, "total_steps": 441, "loss": 0.6544, "lr": 2.9954080512756836e-05, "epoch": 1.8651971174226367, "percentage": 62.36, "elapsed_time": "8:13:49", "remaining_time": "4:58:05"}
|
| 276 |
+
{"current_steps": 276, "total_steps": 441, "loss": 0.6744, "lr": 2.9647238195899168e-05, "epoch": 1.8719796523950827, "percentage": 62.59, "elapsed_time": "8:15:36", "remaining_time": "4:56:17"}
|
| 277 |
+
{"current_steps": 277, "total_steps": 441, "loss": 0.655, "lr": 2.9341047452398607e-05, "epoch": 1.8787621873675286, "percentage": 62.81, "elapsed_time": "8:17:23", "remaining_time": "4:54:28"}
|
| 278 |
+
{"current_steps": 278, "total_steps": 441, "loss": 0.6719, "lr": 2.9035527553028906e-05, "epoch": 1.8855447223399746, "percentage": 63.04, "elapsed_time": "8:19:09", "remaining_time": "4:52:40"}
|
| 279 |
+
{"current_steps": 279, "total_steps": 441, "loss": 0.6614, "lr": 2.873069772634281e-05, "epoch": 1.8923272573124206, "percentage": 63.27, "elapsed_time": "8:20:56", "remaining_time": "4:50:52"}
|
| 280 |
+
{"current_steps": 280, "total_steps": 441, "loss": 0.6564, "lr": 2.8426577157461897e-05, "epoch": 1.8991097922848663, "percentage": 63.49, "elapsed_time": "8:22:43", "remaining_time": "4:49:03"}
|
| 281 |
+
{"current_steps": 281, "total_steps": 441, "loss": 0.6683, "lr": 2.8123184986869022e-05, "epoch": 1.9058923272573125, "percentage": 63.72, "elapsed_time": "8:24:29", "remaining_time": "4:47:15"}
|
| 282 |
+
{"current_steps": 282, "total_steps": 441, "loss": 0.6655, "lr": 2.7820540309203728e-05, "epoch": 1.9126748622297582, "percentage": 63.95, "elapsed_time": "8:26:16", "remaining_time": "4:45:27"}
|
| 283 |
+
{"current_steps": 283, "total_steps": 441, "loss": 0.6605, "lr": 2.751866217206052e-05, "epoch": 1.9194573972022044, "percentage": 64.17, "elapsed_time": "8:28:03", "remaining_time": "4:43:38"}
|
| 284 |
+
{"current_steps": 284, "total_steps": 441, "loss": 0.6451, "lr": 2.721756957479001e-05, "epoch": 1.9262399321746502, "percentage": 64.4, "elapsed_time": "8:29:50", "remaining_time": "4:41:50"}
|
| 285 |
+
{"current_steps": 285, "total_steps": 441, "loss": 0.6717, "lr": 2.691728146730314e-05, "epoch": 1.9330224671470964, "percentage": 64.63, "elapsed_time": "8:31:37", "remaining_time": "4:40:02"}
|
| 286 |
+
{"current_steps": 286, "total_steps": 441, "loss": 0.6779, "lr": 2.6617816748878595e-05, "epoch": 1.939805002119542, "percentage": 64.85, "elapsed_time": "8:33:26", "remaining_time": "4:38:15"}
|
| 287 |
+
{"current_steps": 287, "total_steps": 441, "loss": 0.6642, "lr": 2.6319194266973256e-05, "epoch": 1.9465875370919883, "percentage": 65.08, "elapsed_time": "8:35:13", "remaining_time": "4:36:27"}
|
| 288 |
+
{"current_steps": 288, "total_steps": 441, "loss": 0.6673, "lr": 2.6021432816036073e-05, "epoch": 1.953370072064434, "percentage": 65.31, "elapsed_time": "8:37:01", "remaining_time": "4:34:40"}
|
| 289 |
+
{"current_steps": 289, "total_steps": 441, "loss": 0.6641, "lr": 2.5724551136325132e-05, "epoch": 1.96015260703688, "percentage": 65.53, "elapsed_time": "8:38:51", "remaining_time": "4:32:53"}
|
| 290 |
+
{"current_steps": 290, "total_steps": 441, "loss": 0.6524, "lr": 2.5428567912728225e-05, "epoch": 1.966935142009326, "percentage": 65.76, "elapsed_time": "8:40:39", "remaining_time": "4:31:06"}
|
| 291 |
+
{"current_steps": 291, "total_steps": 441, "loss": 0.6671, "lr": 2.5133501773586905e-05, "epoch": 1.973717676981772, "percentage": 65.99, "elapsed_time": "8:42:27", "remaining_time": "4:29:18"}
|
| 292 |
+
{"current_steps": 292, "total_steps": 441, "loss": 0.6609, "lr": 2.483937128952399e-05, "epoch": 1.9805002119542179, "percentage": 66.21, "elapsed_time": "8:44:15", "remaining_time": "4:27:31"}
|
| 293 |
+
{"current_steps": 293, "total_steps": 441, "loss": 0.67, "lr": 2.4546194972274852e-05, "epoch": 1.9872827469266638, "percentage": 66.44, "elapsed_time": "8:46:04", "remaining_time": "4:25:44"}
|
| 294 |
+
{"current_steps": 294, "total_steps": 441, "loss": 0.6613, "lr": 2.425399127352235e-05, "epoch": 1.9940652818991098, "percentage": 66.67, "elapsed_time": "8:47:51", "remaining_time": "4:23:55"}
|
| 295 |
+
{"current_steps": 295, "total_steps": 441, "loss": 1.0436, "lr": 2.3962778583735463e-05, "epoch": 2.0008478168715556, "percentage": 66.89, "elapsed_time": "8:50:50", "remaining_time": "4:22:43"}
|
| 296 |
+
{"current_steps": 296, "total_steps": 441, "loss": 0.6518, "lr": 2.3672575231011888e-05, "epoch": 2.0076303518440017, "percentage": 67.12, "elapsed_time": "8:52:36", "remaining_time": "4:20:54"}
|