Training in progress, step 1500
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 4976698672
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:63b19b0f5ebfb3f0f935582c2a72de5fc35c6ea9962e6e0513c360981a750659
|
| 3 |
size 4976698672
|
model-00002-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4999802720
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3778500e1c01b1f46b426dad59f1a3d178f42cb8b6ceb2760636c5f824d595de
|
| 3 |
size 4999802720
|
model-00003-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4915916176
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b19f0187449463265c4373d049e7402ab9cc6109e26baf2893f1cd539bd51756
|
| 3 |
size 4915916176
|
model-00004-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1168138808
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9bd09ac45ea2785d982784364f1862842ab8d712bb88f6ff36ca97f008a028cc
|
| 3 |
size 1168138808
|
trainer_log.jsonl
CHANGED
|
@@ -118,3 +118,64 @@
|
|
| 118 |
{"current_steps": 990, "total_steps": 1548, "loss": 0.3983, "lr": 3.4634970993825854e-06, "epoch": 0.6392767777867463, "percentage": 63.95, "elapsed_time": "4:04:29", "remaining_time": "2:17:48"}
|
| 119 |
{"current_steps": 1000, "total_steps": 1548, "loss": 0.4121, "lr": 3.356589721766034e-06, "epoch": 0.6457341189765115, "percentage": 64.6, "elapsed_time": "4:06:34", "remaining_time": "2:15:07"}
|
| 120 |
{"current_steps": 1000, "total_steps": 1548, "eval_loss": 0.35134828090667725, "epoch": 0.6457341189765115, "percentage": 64.6, "elapsed_time": "4:08:26", "remaining_time": "2:16:08"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 118 |
{"current_steps": 990, "total_steps": 1548, "loss": 0.3983, "lr": 3.4634970993825854e-06, "epoch": 0.6392767777867463, "percentage": 63.95, "elapsed_time": "4:04:29", "remaining_time": "2:17:48"}
|
| 119 |
{"current_steps": 1000, "total_steps": 1548, "loss": 0.4121, "lr": 3.356589721766034e-06, "epoch": 0.6457341189765115, "percentage": 64.6, "elapsed_time": "4:06:34", "remaining_time": "2:15:07"}
|
| 120 |
{"current_steps": 1000, "total_steps": 1548, "eval_loss": 0.35134828090667725, "epoch": 0.6457341189765115, "percentage": 64.6, "elapsed_time": "4:08:26", "remaining_time": "2:16:08"}
|
| 121 |
+
{"current_steps": 1010, "total_steps": 1548, "loss": 0.3869, "lr": 3.250518187907469e-06, "epoch": 0.6521914601662765, "percentage": 65.25, "elapsed_time": "4:11:44", "remaining_time": "2:14:05"}
|
| 122 |
+
{"current_steps": 1020, "total_steps": 1548, "loss": 0.3753, "lr": 3.1453364461304795e-06, "epoch": 0.6586488013560416, "percentage": 65.89, "elapsed_time": "4:13:50", "remaining_time": "2:11:23"}
|
| 123 |
+
{"current_steps": 1030, "total_steps": 1548, "loss": 0.3915, "lr": 3.0410979922075344e-06, "epoch": 0.6651061425458068, "percentage": 66.54, "elapsed_time": "4:15:55", "remaining_time": "2:08:42"}
|
| 124 |
+
{"current_steps": 1040, "total_steps": 1548, "loss": 0.4089, "lr": 2.9378558421518645e-06, "epoch": 0.6715634837355718, "percentage": 67.18, "elapsed_time": "4:18:01", "remaining_time": "2:06:02"}
|
| 125 |
+
{"current_steps": 1050, "total_steps": 1548, "loss": 0.4112, "lr": 2.835662505253344e-06, "epoch": 0.678020824925337, "percentage": 67.83, "elapsed_time": "4:20:05", "remaining_time": "2:03:21"}
|
| 126 |
+
{"current_steps": 1050, "total_steps": 1548, "eval_loss": 0.34539544582366943, "epoch": 0.678020824925337, "percentage": 67.83, "elapsed_time": "4:21:57", "remaining_time": "2:04:14"}
|
| 127 |
+
{"current_steps": 1060, "total_steps": 1548, "loss": 0.3993, "lr": 2.7345699573721014e-06, "epoch": 0.6844781661151021, "percentage": 68.48, "elapsed_time": "4:24:04", "remaining_time": "2:01:34"}
|
| 128 |
+
{"current_steps": 1070, "total_steps": 1548, "loss": 0.388, "lr": 2.634629614503428e-06, "epoch": 0.6909355073048672, "percentage": 69.12, "elapsed_time": "4:26:10", "remaining_time": "1:58:54"}
|
| 129 |
+
{"current_steps": 1080, "total_steps": 1548, "loss": 0.3992, "lr": 2.5358923066274354e-06, "epoch": 0.6973928484946323, "percentage": 69.77, "elapsed_time": "4:28:15", "remaining_time": "1:56:14"}
|
| 130 |
+
{"current_steps": 1090, "total_steps": 1548, "loss": 0.3801, "lr": 2.4384082518567643e-06, "epoch": 0.7038501896843975, "percentage": 70.41, "elapsed_time": "4:30:21", "remaining_time": "1:53:36"}
|
| 131 |
+
{"current_steps": 1100, "total_steps": 1548, "loss": 0.4041, "lr": 2.3422270308954936e-06, "epoch": 0.7103075308741625, "percentage": 71.06, "elapsed_time": "4:32:26", "remaining_time": "1:50:57"}
|
| 132 |
+
{"current_steps": 1100, "total_steps": 1548, "eval_loss": 0.3457443118095398, "epoch": 0.7103075308741625, "percentage": 71.06, "elapsed_time": "4:34:18", "remaining_time": "1:51:43"}
|
| 133 |
+
{"current_steps": 1110, "total_steps": 1548, "loss": 0.3909, "lr": 2.2473975618222304e-06, "epoch": 0.7167648720639277, "percentage": 71.71, "elapsed_time": "4:36:24", "remaining_time": "1:49:04"}
|
| 134 |
+
{"current_steps": 1120, "total_steps": 1548, "loss": 0.3952, "lr": 2.1539680752102217e-06, "epoch": 0.7232222132536928, "percentage": 72.35, "elapsed_time": "4:38:31", "remaining_time": "1:46:26"}
|
| 135 |
+
{"current_steps": 1130, "total_steps": 1548, "loss": 0.3736, "lr": 2.0619860895971266e-06, "epoch": 0.7296795544434579, "percentage": 73.0, "elapsed_time": "4:40:36", "remaining_time": "1:43:47"}
|
| 136 |
+
{"current_steps": 1140, "total_steps": 1548, "loss": 0.4042, "lr": 1.9714983873169376e-06, "epoch": 0.736136895633223, "percentage": 73.64, "elapsed_time": "4:42:42", "remaining_time": "1:41:10"}
|
| 137 |
+
{"current_steps": 1150, "total_steps": 1548, "loss": 0.3852, "lr": 1.8825509907063328e-06, "epoch": 0.7425942368229881, "percentage": 74.29, "elapsed_time": "4:44:48", "remaining_time": "1:38:34"}
|
| 138 |
+
{"current_steps": 1150, "total_steps": 1548, "eval_loss": 0.33838221430778503, "epoch": 0.7425942368229881, "percentage": 74.29, "elapsed_time": "4:46:40", "remaining_time": "1:39:12"}
|
| 139 |
+
{"current_steps": 1160, "total_steps": 1548, "loss": 0.3756, "lr": 1.7951891386975684e-06, "epoch": 0.7490515780127532, "percentage": 74.94, "elapsed_time": "4:48:45", "remaining_time": "1:36:35"}
|
| 140 |
+
{"current_steps": 1170, "total_steps": 1548, "loss": 0.3561, "lr": 1.7094572638098122e-06, "epoch": 0.7555089192025184, "percentage": 75.58, "elapsed_time": "4:50:52", "remaining_time": "1:33:58"}
|
| 141 |
+
{"current_steps": 1180, "total_steps": 1548, "loss": 0.3755, "lr": 1.6253989695506207e-06, "epoch": 0.7619662603922834, "percentage": 76.23, "elapsed_time": "4:52:58", "remaining_time": "1:31:22"}
|
| 142 |
+
{"current_steps": 1190, "total_steps": 1548, "loss": 0.3709, "lr": 1.5430570082390545e-06, "epoch": 0.7684236015820486, "percentage": 76.87, "elapsed_time": "4:55:05", "remaining_time": "1:28:46"}
|
| 143 |
+
{"current_steps": 1200, "total_steps": 1548, "loss": 0.3656, "lr": 1.462473259261713e-06, "epoch": 0.7748809427718137, "percentage": 77.52, "elapsed_time": "4:57:12", "remaining_time": "1:26:11"}
|
| 144 |
+
{"current_steps": 1200, "total_steps": 1548, "eval_loss": 0.33403000235557556, "epoch": 0.7748809427718137, "percentage": 77.52, "elapsed_time": "4:59:04", "remaining_time": "1:26:43"}
|
| 145 |
+
{"current_steps": 1210, "total_steps": 1548, "loss": 0.3842, "lr": 1.3836887077727424e-06, "epoch": 0.7813382839615788, "percentage": 78.17, "elapsed_time": "5:01:10", "remaining_time": "1:24:07"}
|
| 146 |
+
{"current_steps": 1220, "total_steps": 1548, "loss": 0.3773, "lr": 1.3067434238486527e-06, "epoch": 0.7877956251513439, "percentage": 78.81, "elapsed_time": "5:03:16", "remaining_time": "1:21:32"}
|
| 147 |
+
{"current_steps": 1230, "total_steps": 1548, "loss": 0.3769, "lr": 1.2316765421085513e-06, "epoch": 0.7942529663411091, "percentage": 79.46, "elapsed_time": "5:05:24", "remaining_time": "1:18:57"}
|
| 148 |
+
{"current_steps": 1240, "total_steps": 1548, "loss": 0.3586, "lr": 1.1585262418101468e-06, "epoch": 0.8007103075308741, "percentage": 80.1, "elapsed_time": "5:07:30", "remaining_time": "1:16:22"}
|
| 149 |
+
{"current_steps": 1250, "total_steps": 1548, "loss": 0.384, "lr": 1.0873297274316568e-06, "epoch": 0.8071676487206393, "percentage": 80.75, "elapsed_time": "5:09:36", "remaining_time": "1:13:48"}
|
| 150 |
+
{"current_steps": 1250, "total_steps": 1548, "eval_loss": 0.3302658796310425, "epoch": 0.8071676487206393, "percentage": 80.75, "elapsed_time": "5:11:28", "remaining_time": "1:14:15"}
|
| 151 |
+
{"current_steps": 1260, "total_steps": 1548, "loss": 0.3816, "lr": 1.0181232097494904e-06, "epoch": 0.8136249899104044, "percentage": 81.4, "elapsed_time": "5:13:36", "remaining_time": "1:11:40"}
|
| 152 |
+
{"current_steps": 1270, "total_steps": 1548, "loss": 0.3651, "lr": 9.509418874213316e-07, "epoch": 0.8200823311001695, "percentage": 82.04, "elapsed_time": "5:15:42", "remaining_time": "1:09:06"}
|
| 153 |
+
{"current_steps": 1280, "total_steps": 1548, "loss": 0.3573, "lr": 8.858199290839859e-07, "epoch": 0.8265396722899346, "percentage": 82.69, "elapsed_time": "5:17:49", "remaining_time": "1:06:32"}
|
| 154 |
+
{"current_steps": 1290, "total_steps": 1548, "loss": 0.383, "lr": 8.22790455975106e-07, "epoch": 0.8329970134796998, "percentage": 83.33, "elapsed_time": "5:19:56", "remaining_time": "1:03:59"}
|
| 155 |
+
{"current_steps": 1300, "total_steps": 1548, "loss": 0.3605, "lr": 7.61885525087619e-07, "epoch": 0.8394543546694648, "percentage": 83.98, "elapsed_time": "5:22:02", "remaining_time": "1:01:26"}
|
| 156 |
+
{"current_steps": 1300, "total_steps": 1548, "eval_loss": 0.327566921710968, "epoch": 0.8394543546694648, "percentage": 83.98, "elapsed_time": "5:23:54", "remaining_time": "1:01:47"}
|
| 157 |
+
{"current_steps": 1310, "total_steps": 1548, "loss": 0.3508, "lr": 7.031361128654402e-07, "epoch": 0.84591169585923, "percentage": 84.63, "elapsed_time": "5:25:59", "remaining_time": "0:59:13"}
|
| 158 |
+
{"current_steps": 1320, "total_steps": 1548, "loss": 0.3806, "lr": 6.465720994487523e-07, "epoch": 0.852369037048995, "percentage": 85.27, "elapsed_time": "5:28:07", "remaining_time": "0:56:40"}
|
| 159 |
+
{"current_steps": 1330, "total_steps": 1548, "loss": 0.3838, "lr": 5.922222534768707e-07, "epoch": 0.8588263782387602, "percentage": 85.92, "elapsed_time": "5:30:11", "remaining_time": "0:54:07"}
|
| 160 |
+
{"current_steps": 1340, "total_steps": 1548, "loss": 0.3627, "lr": 5.401142174564195e-07, "epoch": 0.8652837194285253, "percentage": 86.56, "elapsed_time": "5:32:16", "remaining_time": "0:51:34"}
|
| 161 |
+
{"current_steps": 1350, "total_steps": 1548, "loss": 0.3593, "lr": 4.902744937022658e-07, "epoch": 0.8717410606182904, "percentage": 87.21, "elapsed_time": "5:34:21", "remaining_time": "0:49:02"}
|
| 162 |
+
{"current_steps": 1350, "total_steps": 1548, "eval_loss": 0.3246610164642334, "epoch": 0.8717410606182904, "percentage": 87.21, "elapsed_time": "5:36:13", "remaining_time": "0:49:18"}
|
| 163 |
+
{"current_steps": 1360, "total_steps": 1548, "loss": 0.3804, "lr": 4.4272843085835515e-07, "epoch": 0.8781984018080555, "percentage": 87.86, "elapsed_time": "5:38:18", "remaining_time": "0:46:46"}
|
| 164 |
+
{"current_steps": 1370, "total_steps": 1548, "loss": 0.3764, "lr": 3.9750021100531e-07, "epoch": 0.8846557429978207, "percentage": 88.5, "elapsed_time": "5:40:25", "remaining_time": "0:44:13"}
|
| 165 |
+
{"current_steps": 1380, "total_steps": 1548, "loss": 0.3743, "lr": 3.546128373613472e-07, "epoch": 0.8911130841875857, "percentage": 89.15, "elapsed_time": "5:42:31", "remaining_time": "0:41:41"}
|
| 166 |
+
{"current_steps": 1390, "total_steps": 1548, "loss": 0.3566, "lr": 3.1408812258276575e-07, "epoch": 0.8975704253773509, "percentage": 89.79, "elapsed_time": "5:44:39", "remaining_time": "0:39:10"}
|
| 167 |
+
{"current_steps": 1400, "total_steps": 1548, "loss": 0.3624, "lr": 2.7594667766995933e-07, "epoch": 0.904027766567116, "percentage": 90.44, "elapsed_time": "5:46:45", "remaining_time": "0:36:39"}
|
| 168 |
+
{"current_steps": 1400, "total_steps": 1548, "eval_loss": 0.323292076587677, "epoch": 0.904027766567116, "percentage": 90.44, "elapsed_time": "5:48:37", "remaining_time": "0:36:51"}
|
| 169 |
+
{"current_steps": 1410, "total_steps": 1548, "loss": 0.3792, "lr": 2.402079014845943e-07, "epoch": 0.9104851077568811, "percentage": 91.09, "elapsed_time": "5:50:43", "remaining_time": "0:34:19"}
|
| 170 |
+
{"current_steps": 1420, "total_steps": 1548, "loss": 0.3812, "lr": 2.068899708832911e-07, "epoch": 0.9169424489466462, "percentage": 91.73, "elapsed_time": "5:52:49", "remaining_time": "0:31:48"}
|
| 171 |
+
{"current_steps": 1430, "total_steps": 1548, "loss": 0.3579, "lr": 1.7600983147280982e-07, "epoch": 0.9233997901364114, "percentage": 92.38, "elapsed_time": "5:54:54", "remaining_time": "0:29:17"}
|
| 172 |
+
{"current_steps": 1440, "total_steps": 1548, "loss": 0.3504, "lr": 1.475831889914642e-07, "epoch": 0.9298571313261764, "percentage": 93.02, "elapsed_time": "5:57:00", "remaining_time": "0:26:46"}
|
| 173 |
+
{"current_steps": 1450, "total_steps": 1548, "loss": 0.3734, "lr": 1.2162450132113202e-07, "epoch": 0.9363144725159416, "percentage": 93.67, "elapsed_time": "5:59:05", "remaining_time": "0:24:16"}
|
| 174 |
+
{"current_steps": 1450, "total_steps": 1548, "eval_loss": 0.3228907585144043, "epoch": 0.9363144725159416, "percentage": 93.67, "elapsed_time": "6:00:57", "remaining_time": "0:24:23"}
|
| 175 |
+
{"current_steps": 1460, "total_steps": 1548, "loss": 0.3687, "lr": 9.814697113392835e-08, "epoch": 0.9427718137057067, "percentage": 94.32, "elapsed_time": "6:03:00", "remaining_time": "0:21:52"}
|
| 176 |
+
{"current_steps": 1470, "total_steps": 1548, "loss": 0.3485, "lr": 7.716253917728622e-08, "epoch": 0.9492291548954718, "percentage": 94.96, "elapsed_time": "6:05:04", "remaining_time": "0:19:22"}
|
| 177 |
+
{"current_steps": 1480, "total_steps": 1548, "loss": 0.3713, "lr": 5.8681878200850805e-08, "epoch": 0.9556864960852369, "percentage": 95.61, "elapsed_time": "6:07:11", "remaining_time": "0:16:52"}
|
| 178 |
+
{"current_steps": 1490, "total_steps": 1548, "loss": 0.3499, "lr": 4.27143875282876e-08, "epoch": 0.962143837275002, "percentage": 96.25, "elapsed_time": "6:09:17", "remaining_time": "0:14:22"}
|
| 179 |
+
{"current_steps": 1500, "total_steps": 1548, "loss": 0.3609, "lr": 2.9268188276757035e-08, "epoch": 0.9686011784647671, "percentage": 96.9, "elapsed_time": "6:11:22", "remaining_time": "0:11:53"}
|
| 180 |
+
{"current_steps": 1500, "total_steps": 1548, "eval_loss": 0.3223486840724945, "epoch": 0.9686011784647671, "percentage": 96.9, "elapsed_time": "6:13:14", "remaining_time": "0:11:56"}
|
| 181 |
+
{"current_steps": 1510, "total_steps": 1548, "loss": 0.3609, "lr": 1.8350119226483442e-08, "epoch": 0.9750585196545323, "percentage": 97.55, "elapsed_time": "6:16:31", "remaining_time": "0:09:28"}
|