Training in progress, epoch 3
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 4903351912
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2c7f8f8b6f91fd40d8dc476c8ddfe9491857dd1aaa164d50e4f1c8053182e752
|
| 3 |
size 4903351912
|
model-00002-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4947570872
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0c97464595d8639e5cf313db1224eb1d682f47a135a6c9b28db61804a9cc084f
|
| 3 |
size 4947570872
|
model-00003-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4962221464
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4ef76753ab40932db4e54f6255ed72b53adef62e6a5ecabb8ad2830153be7008
|
| 3 |
size 4962221464
|
model-00004-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3670322200
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e18152bde130eb4ff99622ad54de468e56cb9a86bd9136ee0eb6e2b53ffb6c8e
|
| 3 |
size 3670322200
|
trainer_log.jsonl
CHANGED
|
@@ -134,3 +134,47 @@
|
|
| 134 |
{"current_steps": 1320, "total_steps": 1772, "loss": 0.4899, "lr": 5e-06, "epoch": 2.9788434414668545, "percentage": 74.49, "elapsed_time": "16:58:47", "remaining_time": "5:48:51"}
|
| 135 |
{"current_steps": 1329, "total_steps": 1772, "eval_loss": 0.6006776094436646, "epoch": 2.9991537376586743, "percentage": 75.0, "elapsed_time": "17:11:53", "remaining_time": "5:43:57"}
|
| 136 |
{"current_steps": 1330, "total_steps": 1772, "loss": 0.5325, "lr": 5e-06, "epoch": 3.0014104372355432, "percentage": 75.06, "elapsed_time": "17:13:32", "remaining_time": "5:43:28"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 134 |
{"current_steps": 1320, "total_steps": 1772, "loss": 0.4899, "lr": 5e-06, "epoch": 2.9788434414668545, "percentage": 74.49, "elapsed_time": "16:58:47", "remaining_time": "5:48:51"}
|
| 135 |
{"current_steps": 1329, "total_steps": 1772, "eval_loss": 0.6006776094436646, "epoch": 2.9991537376586743, "percentage": 75.0, "elapsed_time": "17:11:53", "remaining_time": "5:43:57"}
|
| 136 |
{"current_steps": 1330, "total_steps": 1772, "loss": 0.5325, "lr": 5e-06, "epoch": 3.0014104372355432, "percentage": 75.06, "elapsed_time": "17:13:32", "remaining_time": "5:43:28"}
|
| 137 |
+
{"current_steps": 1340, "total_steps": 1772, "loss": 0.4154, "lr": 5e-06, "epoch": 3.0239774330042315, "percentage": 75.62, "elapsed_time": "17:21:10", "remaining_time": "5:35:39"}
|
| 138 |
+
{"current_steps": 1350, "total_steps": 1772, "loss": 0.4178, "lr": 5e-06, "epoch": 3.0465444287729198, "percentage": 76.19, "elapsed_time": "17:28:47", "remaining_time": "5:27:50"}
|
| 139 |
+
{"current_steps": 1360, "total_steps": 1772, "loss": 0.4179, "lr": 5e-06, "epoch": 3.069111424541608, "percentage": 76.75, "elapsed_time": "17:36:24", "remaining_time": "5:20:01"}
|
| 140 |
+
{"current_steps": 1370, "total_steps": 1772, "loss": 0.4199, "lr": 5e-06, "epoch": 3.0916784203102963, "percentage": 77.31, "elapsed_time": "17:44:01", "remaining_time": "5:12:12"}
|
| 141 |
+
{"current_steps": 1380, "total_steps": 1772, "loss": 0.4172, "lr": 5e-06, "epoch": 3.1142454160789845, "percentage": 77.88, "elapsed_time": "17:51:38", "remaining_time": "5:04:24"}
|
| 142 |
+
{"current_steps": 1390, "total_steps": 1772, "loss": 0.4196, "lr": 5e-06, "epoch": 3.136812411847673, "percentage": 78.44, "elapsed_time": "17:59:15", "remaining_time": "4:56:36"}
|
| 143 |
+
{"current_steps": 1400, "total_steps": 1772, "loss": 0.4217, "lr": 5e-06, "epoch": 3.159379407616361, "percentage": 79.01, "elapsed_time": "18:06:52", "remaining_time": "4:48:47"}
|
| 144 |
+
{"current_steps": 1410, "total_steps": 1772, "loss": 0.4228, "lr": 5e-06, "epoch": 3.1819464033850493, "percentage": 79.57, "elapsed_time": "18:14:29", "remaining_time": "4:40:59"}
|
| 145 |
+
{"current_steps": 1420, "total_steps": 1772, "loss": 0.4264, "lr": 5e-06, "epoch": 3.2045133991537376, "percentage": 80.14, "elapsed_time": "18:22:06", "remaining_time": "4:33:12"}
|
| 146 |
+
{"current_steps": 1430, "total_steps": 1772, "loss": 0.4236, "lr": 5e-06, "epoch": 3.227080394922426, "percentage": 80.7, "elapsed_time": "18:29:43", "remaining_time": "4:25:24"}
|
| 147 |
+
{"current_steps": 1440, "total_steps": 1772, "loss": 0.429, "lr": 5e-06, "epoch": 3.249647390691114, "percentage": 81.26, "elapsed_time": "18:37:20", "remaining_time": "4:17:36"}
|
| 148 |
+
{"current_steps": 1450, "total_steps": 1772, "loss": 0.4315, "lr": 5e-06, "epoch": 3.272214386459803, "percentage": 81.83, "elapsed_time": "18:44:57", "remaining_time": "4:09:49"}
|
| 149 |
+
{"current_steps": 1460, "total_steps": 1772, "loss": 0.4311, "lr": 5e-06, "epoch": 3.294781382228491, "percentage": 82.39, "elapsed_time": "18:52:34", "remaining_time": "4:02:01"}
|
| 150 |
+
{"current_steps": 1470, "total_steps": 1772, "loss": 0.429, "lr": 5e-06, "epoch": 3.3173483779971793, "percentage": 82.96, "elapsed_time": "19:00:11", "remaining_time": "3:54:14"}
|
| 151 |
+
{"current_steps": 1480, "total_steps": 1772, "loss": 0.4268, "lr": 5e-06, "epoch": 3.3399153737658676, "percentage": 83.52, "elapsed_time": "19:07:49", "remaining_time": "3:46:27"}
|
| 152 |
+
{"current_steps": 1490, "total_steps": 1772, "loss": 0.4291, "lr": 5e-06, "epoch": 3.362482369534556, "percentage": 84.09, "elapsed_time": "19:15:26", "remaining_time": "3:38:40"}
|
| 153 |
+
{"current_steps": 1500, "total_steps": 1772, "loss": 0.4369, "lr": 5e-06, "epoch": 3.385049365303244, "percentage": 84.65, "elapsed_time": "19:23:03", "remaining_time": "3:30:54"}
|
| 154 |
+
{"current_steps": 1510, "total_steps": 1772, "loss": 0.4289, "lr": 5e-06, "epoch": 3.4076163610719323, "percentage": 85.21, "elapsed_time": "19:30:40", "remaining_time": "3:23:07"}
|
| 155 |
+
{"current_steps": 1520, "total_steps": 1772, "loss": 0.4285, "lr": 5e-06, "epoch": 3.4301833568406206, "percentage": 85.78, "elapsed_time": "19:38:16", "remaining_time": "3:15:20"}
|
| 156 |
+
{"current_steps": 1530, "total_steps": 1772, "loss": 0.4339, "lr": 5e-06, "epoch": 3.452750352609309, "percentage": 86.34, "elapsed_time": "19:45:54", "remaining_time": "3:07:34"}
|
| 157 |
+
{"current_steps": 1540, "total_steps": 1772, "loss": 0.4298, "lr": 5e-06, "epoch": 3.475317348377997, "percentage": 86.91, "elapsed_time": "19:53:31", "remaining_time": "2:59:48"}
|
| 158 |
+
{"current_steps": 1550, "total_steps": 1772, "loss": 0.4367, "lr": 5e-06, "epoch": 3.4978843441466854, "percentage": 87.47, "elapsed_time": "20:01:08", "remaining_time": "2:52:02"}
|
| 159 |
+
{"current_steps": 1560, "total_steps": 1772, "loss": 0.4333, "lr": 5e-06, "epoch": 3.5204513399153736, "percentage": 88.04, "elapsed_time": "20:08:45", "remaining_time": "2:44:16"}
|
| 160 |
+
{"current_steps": 1570, "total_steps": 1772, "loss": 0.4381, "lr": 5e-06, "epoch": 3.543018335684062, "percentage": 88.6, "elapsed_time": "20:16:22", "remaining_time": "2:36:30"}
|
| 161 |
+
{"current_steps": 1580, "total_steps": 1772, "loss": 0.4287, "lr": 5e-06, "epoch": 3.56558533145275, "percentage": 89.16, "elapsed_time": "20:23:59", "remaining_time": "2:28:44"}
|
| 162 |
+
{"current_steps": 1590, "total_steps": 1772, "loss": 0.4288, "lr": 5e-06, "epoch": 3.5881523272214384, "percentage": 89.73, "elapsed_time": "20:31:36", "remaining_time": "2:20:58"}
|
| 163 |
+
{"current_steps": 1600, "total_steps": 1772, "loss": 0.4322, "lr": 5e-06, "epoch": 3.610719322990127, "percentage": 90.29, "elapsed_time": "20:39:13", "remaining_time": "2:13:12"}
|
| 164 |
+
{"current_steps": 1610, "total_steps": 1772, "loss": 0.4353, "lr": 5e-06, "epoch": 3.6332863187588154, "percentage": 90.86, "elapsed_time": "20:46:50", "remaining_time": "2:05:27"}
|
| 165 |
+
{"current_steps": 1620, "total_steps": 1772, "loss": 0.4321, "lr": 5e-06, "epoch": 3.6558533145275036, "percentage": 91.42, "elapsed_time": "20:54:27", "remaining_time": "1:57:42"}
|
| 166 |
+
{"current_steps": 1630, "total_steps": 1772, "loss": 0.4352, "lr": 5e-06, "epoch": 3.678420310296192, "percentage": 91.99, "elapsed_time": "21:02:04", "remaining_time": "1:49:56"}
|
| 167 |
+
{"current_steps": 1640, "total_steps": 1772, "loss": 0.436, "lr": 5e-06, "epoch": 3.70098730606488, "percentage": 92.55, "elapsed_time": "21:09:41", "remaining_time": "1:42:11"}
|
| 168 |
+
{"current_steps": 1650, "total_steps": 1772, "loss": 0.4321, "lr": 5e-06, "epoch": 3.7235543018335684, "percentage": 93.12, "elapsed_time": "21:17:18", "remaining_time": "1:34:26"}
|
| 169 |
+
{"current_steps": 1660, "total_steps": 1772, "loss": 0.4308, "lr": 5e-06, "epoch": 3.7461212976022567, "percentage": 93.68, "elapsed_time": "21:24:55", "remaining_time": "1:26:41"}
|
| 170 |
+
{"current_steps": 1670, "total_steps": 1772, "loss": 0.4363, "lr": 5e-06, "epoch": 3.768688293370945, "percentage": 94.24, "elapsed_time": "21:32:32", "remaining_time": "1:18:56"}
|
| 171 |
+
{"current_steps": 1680, "total_steps": 1772, "loss": 0.4421, "lr": 5e-06, "epoch": 3.791255289139633, "percentage": 94.81, "elapsed_time": "21:40:09", "remaining_time": "1:11:11"}
|
| 172 |
+
{"current_steps": 1690, "total_steps": 1772, "loss": 0.4332, "lr": 5e-06, "epoch": 3.8138222849083214, "percentage": 95.37, "elapsed_time": "21:47:46", "remaining_time": "1:03:27"}
|
| 173 |
+
{"current_steps": 1700, "total_steps": 1772, "loss": 0.431, "lr": 5e-06, "epoch": 3.83638928067701, "percentage": 95.94, "elapsed_time": "21:55:23", "remaining_time": "0:55:42"}
|
| 174 |
+
{"current_steps": 1710, "total_steps": 1772, "loss": 0.4398, "lr": 5e-06, "epoch": 3.8589562764456984, "percentage": 96.5, "elapsed_time": "22:03:00", "remaining_time": "0:47:58"}
|
| 175 |
+
{"current_steps": 1720, "total_steps": 1772, "loss": 0.4387, "lr": 5e-06, "epoch": 3.8815232722143866, "percentage": 97.07, "elapsed_time": "22:10:37", "remaining_time": "0:40:13"}
|
| 176 |
+
{"current_steps": 1730, "total_steps": 1772, "loss": 0.4365, "lr": 5e-06, "epoch": 3.904090267983075, "percentage": 97.63, "elapsed_time": "22:18:14", "remaining_time": "0:32:29"}
|
| 177 |
+
{"current_steps": 1740, "total_steps": 1772, "loss": 0.4373, "lr": 5e-06, "epoch": 3.926657263751763, "percentage": 98.19, "elapsed_time": "22:25:51", "remaining_time": "0:24:45"}
|
| 178 |
+
{"current_steps": 1750, "total_steps": 1772, "loss": 0.4366, "lr": 5e-06, "epoch": 3.9492242595204514, "percentage": 98.76, "elapsed_time": "22:33:28", "remaining_time": "0:17:00"}
|
| 179 |
+
{"current_steps": 1760, "total_steps": 1772, "loss": 0.4362, "lr": 5e-06, "epoch": 3.9717912552891397, "percentage": 99.32, "elapsed_time": "22:41:06", "remaining_time": "0:09:16"}
|
| 180 |
+
{"current_steps": 1770, "total_steps": 1772, "loss": 0.4359, "lr": 5e-06, "epoch": 3.994358251057828, "percentage": 99.89, "elapsed_time": "22:48:43", "remaining_time": "0:01:32"}
|