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 4976698672
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:215e070bc76ac1c69acc31ac6fb7db162010ef8d5205dd69747da9a4fd91b92b
|
| 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:f9e87d4511b5991fb7670f400a6706ed539e9e6e2dee887dd26ebdec53e52c47
|
| 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:d28cfccdd51ad3e91486d30dea512e1f6301913cc16534110ee84b40f3c71859
|
| 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 sha256:02ff5ec3b1828df2e7b4e86c47bbd37bd52fd23c96a1f970f958c21f4ee916de
|
| 3 |
size 1168138808
|
trainer_log.jsonl
CHANGED
|
@@ -98,3 +98,104 @@
|
|
| 98 |
{"current_steps": 980, "total_steps": 3984, "loss": 0.7328, "lr": 5e-06, "epoch": 0.9835654246644084, "percentage": 24.6, "elapsed_time": "8:46:27", "remaining_time": "1 day, 2:53:44"}
|
| 99 |
{"current_steps": 990, "total_steps": 3984, "loss": 0.7331, "lr": 5e-06, "epoch": 0.9936018065487392, "percentage": 24.85, "elapsed_time": "8:51:49", "remaining_time": "1 day, 2:48:23"}
|
| 100 |
{"current_steps": 996, "total_steps": 3984, "eval_loss": 0.7301905751228333, "epoch": 0.9996236356793377, "percentage": 25.0, "elapsed_time": "9:06:59", "remaining_time": "1 day, 3:20:57"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 98 |
{"current_steps": 980, "total_steps": 3984, "loss": 0.7328, "lr": 5e-06, "epoch": 0.9835654246644084, "percentage": 24.6, "elapsed_time": "8:46:27", "remaining_time": "1 day, 2:53:44"}
|
| 99 |
{"current_steps": 990, "total_steps": 3984, "loss": 0.7331, "lr": 5e-06, "epoch": 0.9936018065487392, "percentage": 24.85, "elapsed_time": "8:51:49", "remaining_time": "1 day, 2:48:23"}
|
| 100 |
{"current_steps": 996, "total_steps": 3984, "eval_loss": 0.7301905751228333, "epoch": 0.9996236356793377, "percentage": 25.0, "elapsed_time": "9:06:59", "remaining_time": "1 day, 3:20:57"}
|
| 101 |
+
{"current_steps": 1000, "total_steps": 3984, "loss": 0.7624, "lr": 5e-06, "epoch": 1.0036381884330698, "percentage": 25.1, "elapsed_time": "9:10:09", "remaining_time": "1 day, 3:21:39"}
|
| 102 |
+
{"current_steps": 1010, "total_steps": 3984, "loss": 0.6938, "lr": 5e-06, "epoch": 1.0136745703174006, "percentage": 25.35, "elapsed_time": "9:15:31", "remaining_time": "1 day, 3:15:47"}
|
| 103 |
+
{"current_steps": 1020, "total_steps": 3984, "loss": 0.6956, "lr": 5e-06, "epoch": 1.0237109522017314, "percentage": 25.6, "elapsed_time": "9:20:52", "remaining_time": "1 day, 3:09:48"}
|
| 104 |
+
{"current_steps": 1030, "total_steps": 3984, "loss": 0.6893, "lr": 5e-06, "epoch": 1.033747334086062, "percentage": 25.85, "elapsed_time": "9:26:14", "remaining_time": "1 day, 3:03:57"}
|
| 105 |
+
{"current_steps": 1040, "total_steps": 3984, "loss": 0.691, "lr": 5e-06, "epoch": 1.0437837159703927, "percentage": 26.1, "elapsed_time": "9:31:35", "remaining_time": "1 day, 2:58:03"}
|
| 106 |
+
{"current_steps": 1050, "total_steps": 3984, "loss": 0.689, "lr": 5e-06, "epoch": 1.0538200978547234, "percentage": 26.36, "elapsed_time": "9:36:54", "remaining_time": "1 day, 2:52:02"}
|
| 107 |
+
{"current_steps": 1060, "total_steps": 3984, "loss": 0.6911, "lr": 5e-06, "epoch": 1.0638564797390542, "percentage": 26.61, "elapsed_time": "9:42:15", "remaining_time": "1 day, 2:46:09"}
|
| 108 |
+
{"current_steps": 1070, "total_steps": 3984, "loss": 0.6968, "lr": 5e-06, "epoch": 1.0738928616233847, "percentage": 26.86, "elapsed_time": "9:47:36", "remaining_time": "1 day, 2:40:15"}
|
| 109 |
+
{"current_steps": 1080, "total_steps": 3984, "loss": 0.6947, "lr": 5e-06, "epoch": 1.0839292435077155, "percentage": 27.11, "elapsed_time": "9:52:55", "remaining_time": "1 day, 2:34:19"}
|
| 110 |
+
{"current_steps": 1090, "total_steps": 3984, "loss": 0.692, "lr": 5e-06, "epoch": 1.0939656253920462, "percentage": 27.36, "elapsed_time": "9:58:18", "remaining_time": "1 day, 2:28:31"}
|
| 111 |
+
{"current_steps": 1100, "total_steps": 3984, "loss": 0.6924, "lr": 5e-06, "epoch": 1.1040020072763768, "percentage": 27.61, "elapsed_time": "10:03:40", "remaining_time": "1 day, 2:22:43"}
|
| 112 |
+
{"current_steps": 1110, "total_steps": 3984, "loss": 0.6905, "lr": 5e-06, "epoch": 1.1140383891607075, "percentage": 27.86, "elapsed_time": "10:09:03", "remaining_time": "1 day, 2:16:58"}
|
| 113 |
+
{"current_steps": 1120, "total_steps": 3984, "loss": 0.6959, "lr": 5e-06, "epoch": 1.1240747710450383, "percentage": 28.11, "elapsed_time": "10:14:26", "remaining_time": "1 day, 2:11:11"}
|
| 114 |
+
{"current_steps": 1130, "total_steps": 3984, "loss": 0.6901, "lr": 5e-06, "epoch": 1.134111152929369, "percentage": 28.36, "elapsed_time": "10:19:48", "remaining_time": "1 day, 2:05:25"}
|
| 115 |
+
{"current_steps": 1140, "total_steps": 3984, "loss": 0.6921, "lr": 5e-06, "epoch": 1.1441475348136996, "percentage": 28.61, "elapsed_time": "10:25:09", "remaining_time": "1 day, 1:59:35"}
|
| 116 |
+
{"current_steps": 1150, "total_steps": 3984, "loss": 0.6954, "lr": 5e-06, "epoch": 1.1541839166980303, "percentage": 28.87, "elapsed_time": "10:30:31", "remaining_time": "1 day, 1:53:49"}
|
| 117 |
+
{"current_steps": 1160, "total_steps": 3984, "loss": 0.6893, "lr": 5e-06, "epoch": 1.164220298582361, "percentage": 29.12, "elapsed_time": "10:35:53", "remaining_time": "1 day, 1:48:04"}
|
| 118 |
+
{"current_steps": 1170, "total_steps": 3984, "loss": 0.6936, "lr": 5e-06, "epoch": 1.1742566804666918, "percentage": 29.37, "elapsed_time": "10:41:15", "remaining_time": "1 day, 1:42:18"}
|
| 119 |
+
{"current_steps": 1180, "total_steps": 3984, "loss": 0.6969, "lr": 5e-06, "epoch": 1.1842930623510224, "percentage": 29.62, "elapsed_time": "10:46:37", "remaining_time": "1 day, 1:36:33"}
|
| 120 |
+
{"current_steps": 1190, "total_steps": 3984, "loss": 0.6965, "lr": 5e-06, "epoch": 1.1943294442353531, "percentage": 29.87, "elapsed_time": "10:52:00", "remaining_time": "1 day, 1:30:50"}
|
| 121 |
+
{"current_steps": 1200, "total_steps": 3984, "loss": 0.6927, "lr": 5e-06, "epoch": 1.204365826119684, "percentage": 30.12, "elapsed_time": "10:57:22", "remaining_time": "1 day, 1:25:07"}
|
| 122 |
+
{"current_steps": 1210, "total_steps": 3984, "loss": 0.6916, "lr": 5e-06, "epoch": 1.2144022080040147, "percentage": 30.37, "elapsed_time": "11:02:45", "remaining_time": "1 day, 1:19:24"}
|
| 123 |
+
{"current_steps": 1220, "total_steps": 3984, "loss": 0.6954, "lr": 5e-06, "epoch": 1.2244385898883452, "percentage": 30.62, "elapsed_time": "11:08:07", "remaining_time": "1 day, 1:13:40"}
|
| 124 |
+
{"current_steps": 1230, "total_steps": 3984, "loss": 0.6914, "lr": 5e-06, "epoch": 1.234474971772676, "percentage": 30.87, "elapsed_time": "11:13:29", "remaining_time": "1 day, 1:07:56"}
|
| 125 |
+
{"current_steps": 1240, "total_steps": 3984, "loss": 0.6934, "lr": 5e-06, "epoch": 1.2445113536570067, "percentage": 31.12, "elapsed_time": "11:18:51", "remaining_time": "1 day, 1:02:14"}
|
| 126 |
+
{"current_steps": 1250, "total_steps": 3984, "loss": 0.6933, "lr": 5e-06, "epoch": 1.2545477355413372, "percentage": 31.38, "elapsed_time": "11:24:13", "remaining_time": "1 day, 0:56:32"}
|
| 127 |
+
{"current_steps": 1260, "total_steps": 3984, "loss": 0.6946, "lr": 5e-06, "epoch": 1.264584117425668, "percentage": 31.63, "elapsed_time": "11:29:35", "remaining_time": "1 day, 0:50:49"}
|
| 128 |
+
{"current_steps": 1270, "total_steps": 3984, "loss": 0.6946, "lr": 5e-06, "epoch": 1.2746204993099988, "percentage": 31.88, "elapsed_time": "11:34:57", "remaining_time": "1 day, 0:45:08"}
|
| 129 |
+
{"current_steps": 1280, "total_steps": 3984, "loss": 0.6908, "lr": 5e-06, "epoch": 1.2846568811943295, "percentage": 32.13, "elapsed_time": "11:40:20", "remaining_time": "1 day, 0:39:29"}
|
| 130 |
+
{"current_steps": 1290, "total_steps": 3984, "loss": 0.6875, "lr": 5e-06, "epoch": 1.29469326307866, "percentage": 32.38, "elapsed_time": "11:45:43", "remaining_time": "1 day, 0:33:49"}
|
| 131 |
+
{"current_steps": 1300, "total_steps": 3984, "loss": 0.695, "lr": 5e-06, "epoch": 1.3047296449629908, "percentage": 32.63, "elapsed_time": "11:51:06", "remaining_time": "1 day, 0:28:10"}
|
| 132 |
+
{"current_steps": 1310, "total_steps": 3984, "loss": 0.696, "lr": 5e-06, "epoch": 1.3147660268473216, "percentage": 32.88, "elapsed_time": "11:56:28", "remaining_time": "1 day, 0:22:28"}
|
| 133 |
+
{"current_steps": 1320, "total_steps": 3984, "loss": 0.6919, "lr": 5e-06, "epoch": 1.3248024087316521, "percentage": 33.13, "elapsed_time": "12:01:49", "remaining_time": "1 day, 0:16:45"}
|
| 134 |
+
{"current_steps": 1330, "total_steps": 3984, "loss": 0.6868, "lr": 5e-06, "epoch": 1.3348387906159829, "percentage": 33.38, "elapsed_time": "12:07:10", "remaining_time": "1 day, 0:11:04"}
|
| 135 |
+
{"current_steps": 1340, "total_steps": 3984, "loss": 0.6953, "lr": 5e-06, "epoch": 1.3448751725003136, "percentage": 33.63, "elapsed_time": "12:12:33", "remaining_time": "1 day, 0:05:25"}
|
| 136 |
+
{"current_steps": 1350, "total_steps": 3984, "loss": 0.6868, "lr": 5e-06, "epoch": 1.3549115543846444, "percentage": 33.89, "elapsed_time": "12:17:55", "remaining_time": "23:59:46"}
|
| 137 |
+
{"current_steps": 1360, "total_steps": 3984, "loss": 0.6963, "lr": 5e-06, "epoch": 1.3649479362689751, "percentage": 34.14, "elapsed_time": "12:23:15", "remaining_time": "23:54:03"}
|
| 138 |
+
{"current_steps": 1370, "total_steps": 3984, "loss": 0.6842, "lr": 5e-06, "epoch": 1.3749843181533057, "percentage": 34.39, "elapsed_time": "12:28:35", "remaining_time": "23:48:20"}
|
| 139 |
+
{"current_steps": 1380, "total_steps": 3984, "loss": 0.6938, "lr": 5e-06, "epoch": 1.3850207000376364, "percentage": 34.64, "elapsed_time": "12:33:57", "remaining_time": "23:42:40"}
|
| 140 |
+
{"current_steps": 1390, "total_steps": 3984, "loss": 0.6944, "lr": 5e-06, "epoch": 1.3950570819219672, "percentage": 34.89, "elapsed_time": "12:39:18", "remaining_time": "23:37:00"}
|
| 141 |
+
{"current_steps": 1400, "total_steps": 3984, "loss": 0.691, "lr": 5e-06, "epoch": 1.4050934638062977, "percentage": 35.14, "elapsed_time": "12:44:38", "remaining_time": "23:31:19"}
|
| 142 |
+
{"current_steps": 1410, "total_steps": 3984, "loss": 0.6897, "lr": 5e-06, "epoch": 1.4151298456906285, "percentage": 35.39, "elapsed_time": "12:50:00", "remaining_time": "23:25:41"}
|
| 143 |
+
{"current_steps": 1420, "total_steps": 3984, "loss": 0.6914, "lr": 5e-06, "epoch": 1.4251662275749593, "percentage": 35.64, "elapsed_time": "12:55:22", "remaining_time": "23:20:02"}
|
| 144 |
+
{"current_steps": 1430, "total_steps": 3984, "loss": 0.6949, "lr": 5e-06, "epoch": 1.43520260945929, "percentage": 35.89, "elapsed_time": "13:00:44", "remaining_time": "23:14:25"}
|
| 145 |
+
{"current_steps": 1440, "total_steps": 3984, "loss": 0.6891, "lr": 5e-06, "epoch": 1.4452389913436205, "percentage": 36.14, "elapsed_time": "13:06:07", "remaining_time": "23:08:48"}
|
| 146 |
+
{"current_steps": 1450, "total_steps": 3984, "loss": 0.691, "lr": 5e-06, "epoch": 1.4552753732279513, "percentage": 36.4, "elapsed_time": "13:11:29", "remaining_time": "23:03:11"}
|
| 147 |
+
{"current_steps": 1460, "total_steps": 3984, "loss": 0.6916, "lr": 5e-06, "epoch": 1.465311755112282, "percentage": 36.65, "elapsed_time": "13:16:50", "remaining_time": "22:57:33"}
|
| 148 |
+
{"current_steps": 1470, "total_steps": 3984, "loss": 0.6914, "lr": 5e-06, "epoch": 1.4753481369966126, "percentage": 36.9, "elapsed_time": "13:22:12", "remaining_time": "22:51:56"}
|
| 149 |
+
{"current_steps": 1480, "total_steps": 3984, "loss": 0.6877, "lr": 5e-06, "epoch": 1.4853845188809434, "percentage": 37.15, "elapsed_time": "13:27:31", "remaining_time": "22:46:15"}
|
| 150 |
+
{"current_steps": 1490, "total_steps": 3984, "loss": 0.6885, "lr": 5e-06, "epoch": 1.4954209007652741, "percentage": 37.4, "elapsed_time": "13:32:53", "remaining_time": "22:40:37"}
|
| 151 |
+
{"current_steps": 1500, "total_steps": 3984, "loss": 0.6945, "lr": 5e-06, "epoch": 1.5054572826496049, "percentage": 37.65, "elapsed_time": "13:38:12", "remaining_time": "22:34:57"}
|
| 152 |
+
{"current_steps": 1510, "total_steps": 3984, "loss": 0.696, "lr": 5e-06, "epoch": 1.5154936645339356, "percentage": 37.9, "elapsed_time": "13:43:34", "remaining_time": "22:29:21"}
|
| 153 |
+
{"current_steps": 1520, "total_steps": 3984, "loss": 0.6939, "lr": 5e-06, "epoch": 1.5255300464182662, "percentage": 38.15, "elapsed_time": "13:48:54", "remaining_time": "22:23:42"}
|
| 154 |
+
{"current_steps": 1530, "total_steps": 3984, "loss": 0.6906, "lr": 5e-06, "epoch": 1.535566428302597, "percentage": 38.4, "elapsed_time": "13:54:16", "remaining_time": "22:18:07"}
|
| 155 |
+
{"current_steps": 1540, "total_steps": 3984, "loss": 0.69, "lr": 5e-06, "epoch": 1.5456028101869275, "percentage": 38.65, "elapsed_time": "13:59:38", "remaining_time": "22:12:31"}
|
| 156 |
+
{"current_steps": 1550, "total_steps": 3984, "loss": 0.6854, "lr": 5e-06, "epoch": 1.5556391920712582, "percentage": 38.91, "elapsed_time": "14:04:59", "remaining_time": "22:06:54"}
|
| 157 |
+
{"current_steps": 1560, "total_steps": 3984, "loss": 0.6925, "lr": 5e-06, "epoch": 1.565675573955589, "percentage": 39.16, "elapsed_time": "14:10:21", "remaining_time": "22:01:18"}
|
| 158 |
+
{"current_steps": 1570, "total_steps": 3984, "loss": 0.6883, "lr": 5e-06, "epoch": 1.5757119558399197, "percentage": 39.41, "elapsed_time": "14:15:41", "remaining_time": "21:55:42"}
|
| 159 |
+
{"current_steps": 1580, "total_steps": 3984, "loss": 0.6919, "lr": 5e-06, "epoch": 1.5857483377242505, "percentage": 39.66, "elapsed_time": "14:21:02", "remaining_time": "21:50:06"}
|
| 160 |
+
{"current_steps": 1590, "total_steps": 3984, "loss": 0.691, "lr": 5e-06, "epoch": 1.5957847196085813, "percentage": 39.91, "elapsed_time": "14:26:24", "remaining_time": "21:44:31"}
|
| 161 |
+
{"current_steps": 1600, "total_steps": 3984, "loss": 0.6906, "lr": 5e-06, "epoch": 1.6058211014929118, "percentage": 40.16, "elapsed_time": "14:31:48", "remaining_time": "21:38:59"}
|
| 162 |
+
{"current_steps": 1610, "total_steps": 3984, "loss": 0.6855, "lr": 5e-06, "epoch": 1.6158574833772426, "percentage": 40.41, "elapsed_time": "14:37:10", "remaining_time": "21:33:25"}
|
| 163 |
+
{"current_steps": 1620, "total_steps": 3984, "loss": 0.6886, "lr": 5e-06, "epoch": 1.625893865261573, "percentage": 40.66, "elapsed_time": "14:42:32", "remaining_time": "21:27:50"}
|
| 164 |
+
{"current_steps": 1630, "total_steps": 3984, "loss": 0.6911, "lr": 5e-06, "epoch": 1.6359302471459038, "percentage": 40.91, "elapsed_time": "14:47:53", "remaining_time": "21:22:16"}
|
| 165 |
+
{"current_steps": 1640, "total_steps": 3984, "loss": 0.6837, "lr": 5e-06, "epoch": 1.6459666290302346, "percentage": 41.16, "elapsed_time": "14:53:14", "remaining_time": "21:16:40"}
|
| 166 |
+
{"current_steps": 1650, "total_steps": 3984, "loss": 0.6889, "lr": 5e-06, "epoch": 1.6560030109145654, "percentage": 41.42, "elapsed_time": "14:58:32", "remaining_time": "21:11:01"}
|
| 167 |
+
{"current_steps": 1660, "total_steps": 3984, "loss": 0.6977, "lr": 5e-06, "epoch": 1.6660393927988961, "percentage": 41.67, "elapsed_time": "15:03:50", "remaining_time": "21:05:22"}
|
| 168 |
+
{"current_steps": 1670, "total_steps": 3984, "loss": 0.6898, "lr": 5e-06, "epoch": 1.6760757746832267, "percentage": 41.92, "elapsed_time": "15:09:09", "remaining_time": "20:59:45"}
|
| 169 |
+
{"current_steps": 1680, "total_steps": 3984, "loss": 0.6903, "lr": 5e-06, "epoch": 1.6861121565675574, "percentage": 42.17, "elapsed_time": "15:14:31", "remaining_time": "20:54:11"}
|
| 170 |
+
{"current_steps": 1690, "total_steps": 3984, "loss": 0.6911, "lr": 5e-06, "epoch": 1.696148538451888, "percentage": 42.42, "elapsed_time": "15:19:52", "remaining_time": "20:48:38"}
|
| 171 |
+
{"current_steps": 1700, "total_steps": 3984, "loss": 0.6896, "lr": 5e-06, "epoch": 1.7061849203362187, "percentage": 42.67, "elapsed_time": "15:25:13", "remaining_time": "20:43:04"}
|
| 172 |
+
{"current_steps": 1710, "total_steps": 3984, "loss": 0.6933, "lr": 5e-06, "epoch": 1.7162213022205495, "percentage": 42.92, "elapsed_time": "15:30:32", "remaining_time": "20:37:27"}
|
| 173 |
+
{"current_steps": 1720, "total_steps": 3984, "loss": 0.689, "lr": 5e-06, "epoch": 1.7262576841048802, "percentage": 43.17, "elapsed_time": "15:35:52", "remaining_time": "20:31:52"}
|
| 174 |
+
{"current_steps": 1730, "total_steps": 3984, "loss": 0.6882, "lr": 5e-06, "epoch": 1.736294065989211, "percentage": 43.42, "elapsed_time": "15:41:14", "remaining_time": "20:26:20"}
|
| 175 |
+
{"current_steps": 1740, "total_steps": 3984, "loss": 0.6905, "lr": 5e-06, "epoch": 1.7463304478735417, "percentage": 43.67, "elapsed_time": "15:46:36", "remaining_time": "20:20:48"}
|
| 176 |
+
{"current_steps": 1750, "total_steps": 3984, "loss": 0.6937, "lr": 5e-06, "epoch": 1.7563668297578723, "percentage": 43.93, "elapsed_time": "15:51:58", "remaining_time": "20:15:15"}
|
| 177 |
+
{"current_steps": 1760, "total_steps": 3984, "loss": 0.6877, "lr": 5e-06, "epoch": 1.7664032116422028, "percentage": 44.18, "elapsed_time": "15:57:19", "remaining_time": "20:09:43"}
|
| 178 |
+
{"current_steps": 1770, "total_steps": 3984, "loss": 0.686, "lr": 5e-06, "epoch": 1.7764395935265336, "percentage": 44.43, "elapsed_time": "16:02:41", "remaining_time": "20:04:11"}
|
| 179 |
+
{"current_steps": 1780, "total_steps": 3984, "loss": 0.6879, "lr": 5e-06, "epoch": 1.7864759754108643, "percentage": 44.68, "elapsed_time": "16:08:02", "remaining_time": "19:58:37"}
|
| 180 |
+
{"current_steps": 1790, "total_steps": 3984, "loss": 0.696, "lr": 5e-06, "epoch": 1.796512357295195, "percentage": 44.93, "elapsed_time": "16:13:24", "remaining_time": "19:53:06"}
|
| 181 |
+
{"current_steps": 1800, "total_steps": 3984, "loss": 0.6928, "lr": 5e-06, "epoch": 1.8065487391795259, "percentage": 45.18, "elapsed_time": "16:18:45", "remaining_time": "19:47:34"}
|
| 182 |
+
{"current_steps": 1810, "total_steps": 3984, "loss": 0.6894, "lr": 5e-06, "epoch": 1.8165851210638566, "percentage": 45.43, "elapsed_time": "16:24:04", "remaining_time": "19:41:58"}
|
| 183 |
+
{"current_steps": 1820, "total_steps": 3984, "loss": 0.6902, "lr": 5e-06, "epoch": 1.8266215029481871, "percentage": 45.68, "elapsed_time": "16:29:25", "remaining_time": "19:36:26"}
|
| 184 |
+
{"current_steps": 1830, "total_steps": 3984, "loss": 0.6873, "lr": 5e-06, "epoch": 1.836657884832518, "percentage": 45.93, "elapsed_time": "16:34:47", "remaining_time": "19:30:54"}
|
| 185 |
+
{"current_steps": 1840, "total_steps": 3984, "loss": 0.6912, "lr": 5e-06, "epoch": 1.8466942667168484, "percentage": 46.18, "elapsed_time": "16:40:08", "remaining_time": "19:25:23"}
|
| 186 |
+
{"current_steps": 1850, "total_steps": 3984, "loss": 0.6912, "lr": 5e-06, "epoch": 1.8567306486011792, "percentage": 46.44, "elapsed_time": "16:45:30", "remaining_time": "19:19:51"}
|
| 187 |
+
{"current_steps": 1860, "total_steps": 3984, "loss": 0.6876, "lr": 5e-06, "epoch": 1.86676703048551, "percentage": 46.69, "elapsed_time": "16:50:51", "remaining_time": "19:14:20"}
|
| 188 |
+
{"current_steps": 1870, "total_steps": 3984, "loss": 0.687, "lr": 5e-06, "epoch": 1.8768034123698407, "percentage": 46.94, "elapsed_time": "16:56:13", "remaining_time": "19:08:49"}
|
| 189 |
+
{"current_steps": 1880, "total_steps": 3984, "loss": 0.6853, "lr": 5e-06, "epoch": 1.8868397942541715, "percentage": 47.19, "elapsed_time": "17:01:34", "remaining_time": "19:03:17"}
|
| 190 |
+
{"current_steps": 1890, "total_steps": 3984, "loss": 0.6907, "lr": 5e-06, "epoch": 1.8968761761385022, "percentage": 47.44, "elapsed_time": "17:06:55", "remaining_time": "18:57:46"}
|
| 191 |
+
{"current_steps": 1900, "total_steps": 3984, "loss": 0.6879, "lr": 5e-06, "epoch": 1.9069125580228328, "percentage": 47.69, "elapsed_time": "17:12:14", "remaining_time": "18:52:12"}
|
| 192 |
+
{"current_steps": 1910, "total_steps": 3984, "loss": 0.6862, "lr": 5e-06, "epoch": 1.9169489399071633, "percentage": 47.94, "elapsed_time": "17:17:35", "remaining_time": "18:46:40"}
|
| 193 |
+
{"current_steps": 1920, "total_steps": 3984, "loss": 0.6936, "lr": 5e-06, "epoch": 1.926985321791494, "percentage": 48.19, "elapsed_time": "17:22:56", "remaining_time": "18:41:10"}
|
| 194 |
+
{"current_steps": 1930, "total_steps": 3984, "loss": 0.6877, "lr": 5e-06, "epoch": 1.9370217036758248, "percentage": 48.44, "elapsed_time": "17:28:16", "remaining_time": "18:35:37"}
|
| 195 |
+
{"current_steps": 1940, "total_steps": 3984, "loss": 0.6874, "lr": 5e-06, "epoch": 1.9470580855601556, "percentage": 48.69, "elapsed_time": "17:33:37", "remaining_time": "18:30:06"}
|
| 196 |
+
{"current_steps": 1950, "total_steps": 3984, "loss": 0.6876, "lr": 5e-06, "epoch": 1.9570944674444863, "percentage": 48.95, "elapsed_time": "17:38:59", "remaining_time": "18:24:36"}
|
| 197 |
+
{"current_steps": 1960, "total_steps": 3984, "loss": 0.6863, "lr": 5e-06, "epoch": 1.967130849328817, "percentage": 49.2, "elapsed_time": "17:44:19", "remaining_time": "18:19:04"}
|
| 198 |
+
{"current_steps": 1970, "total_steps": 3984, "loss": 0.6885, "lr": 5e-06, "epoch": 1.9771672312131476, "percentage": 49.45, "elapsed_time": "17:49:40", "remaining_time": "18:13:34"}
|
| 199 |
+
{"current_steps": 1980, "total_steps": 3984, "loss": 0.6877, "lr": 5e-06, "epoch": 1.9872036130974784, "percentage": 49.7, "elapsed_time": "17:55:01", "remaining_time": "18:08:03"}
|
| 200 |
+
{"current_steps": 1990, "total_steps": 3984, "loss": 0.6913, "lr": 5e-06, "epoch": 1.997239994981809, "percentage": 49.95, "elapsed_time": "18:00:22", "remaining_time": "18:02:32"}
|
| 201 |
+
{"current_steps": 1992, "total_steps": 3984, "eval_loss": 0.7165391445159912, "epoch": 1.999247271358675, "percentage": 50.0, "elapsed_time": "18:13:19", "remaining_time": "18:13:19"}
|