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 4976698672
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:15a0893e752938e4bd4e41d5ca60da81ccf8d89513100bf5474099c1a2b073c7
|
| 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:a13129faad2bba549ecf4e5f107ef01a6a79dc8fa6ed776bd8bce75db53d2ec5
|
| 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:bb3c8799be9fa4a67f1e946d74ae49c9c658fe5d03fc2a0d1926a69dbc2f8ff2
|
| 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 sha256:12cd86df6c18a010c14237d23aa64e4e8fe3d3bd8ece7535aa55404f39b45c0d
|
| 3 |
size 1168138808
|
trainer_log.jsonl
CHANGED
|
@@ -128,3 +128,44 @@
|
|
| 128 |
{"current_steps": 1260, "total_steps": 1688, "loss": 0.5709, "lr": 5e-06, "epoch": 2.9804849201655825, "percentage": 74.64, "elapsed_time": "10:20:41", "remaining_time": "3:30:50"}
|
| 129 |
{"current_steps": 1268, "total_steps": 1688, "eval_loss": 0.6412045359611511, "epoch": 2.9994086339444115, "percentage": 75.12, "elapsed_time": "10:28:26", "remaining_time": "3:28:09"}
|
| 130 |
{"current_steps": 1270, "total_steps": 1688, "loss": 0.5734, "lr": 5e-06, "epoch": 3.0041395623891187, "percentage": 75.24, "elapsed_time": "10:30:16", "remaining_time": "3:27:26"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 128 |
{"current_steps": 1260, "total_steps": 1688, "loss": 0.5709, "lr": 5e-06, "epoch": 2.9804849201655825, "percentage": 74.64, "elapsed_time": "10:20:41", "remaining_time": "3:30:50"}
|
| 129 |
{"current_steps": 1268, "total_steps": 1688, "eval_loss": 0.6412045359611511, "epoch": 2.9994086339444115, "percentage": 75.12, "elapsed_time": "10:28:26", "remaining_time": "3:28:09"}
|
| 130 |
{"current_steps": 1270, "total_steps": 1688, "loss": 0.5734, "lr": 5e-06, "epoch": 3.0041395623891187, "percentage": 75.24, "elapsed_time": "10:30:16", "remaining_time": "3:27:26"}
|
| 131 |
+
{"current_steps": 1280, "total_steps": 1688, "loss": 0.5192, "lr": 5e-06, "epoch": 3.0277942046126554, "percentage": 75.83, "elapsed_time": "10:35:07", "remaining_time": "3:22:26"}
|
| 132 |
+
{"current_steps": 1290, "total_steps": 1688, "loss": 0.5252, "lr": 5e-06, "epoch": 3.0514488468361916, "percentage": 76.42, "elapsed_time": "10:39:59", "remaining_time": "3:17:27"}
|
| 133 |
+
{"current_steps": 1300, "total_steps": 1688, "loss": 0.518, "lr": 5e-06, "epoch": 3.075103489059728, "percentage": 77.01, "elapsed_time": "10:44:50", "remaining_time": "3:12:27"}
|
| 134 |
+
{"current_steps": 1310, "total_steps": 1688, "loss": 0.523, "lr": 5e-06, "epoch": 3.0987581312832644, "percentage": 77.61, "elapsed_time": "10:49:42", "remaining_time": "3:07:28"}
|
| 135 |
+
{"current_steps": 1320, "total_steps": 1688, "loss": 0.5206, "lr": 5e-06, "epoch": 3.1224127735068006, "percentage": 78.2, "elapsed_time": "10:54:33", "remaining_time": "3:02:29"}
|
| 136 |
+
{"current_steps": 1330, "total_steps": 1688, "loss": 0.5243, "lr": 5e-06, "epoch": 3.146067415730337, "percentage": 78.79, "elapsed_time": "10:59:24", "remaining_time": "2:57:29"}
|
| 137 |
+
{"current_steps": 1340, "total_steps": 1688, "loss": 0.5252, "lr": 5e-06, "epoch": 3.1697220579538734, "percentage": 79.38, "elapsed_time": "11:04:16", "remaining_time": "2:52:30"}
|
| 138 |
+
{"current_steps": 1350, "total_steps": 1688, "loss": 0.5239, "lr": 5e-06, "epoch": 3.19337670017741, "percentage": 79.98, "elapsed_time": "11:09:07", "remaining_time": "2:47:31"}
|
| 139 |
+
{"current_steps": 1360, "total_steps": 1688, "loss": 0.5284, "lr": 5e-06, "epoch": 3.2170313424009462, "percentage": 80.57, "elapsed_time": "11:13:59", "remaining_time": "2:42:32"}
|
| 140 |
+
{"current_steps": 1370, "total_steps": 1688, "loss": 0.5247, "lr": 5e-06, "epoch": 3.2406859846244824, "percentage": 81.16, "elapsed_time": "11:18:50", "remaining_time": "2:37:34"}
|
| 141 |
+
{"current_steps": 1380, "total_steps": 1688, "loss": 0.5256, "lr": 5e-06, "epoch": 3.264340626848019, "percentage": 81.75, "elapsed_time": "11:23:42", "remaining_time": "2:32:35"}
|
| 142 |
+
{"current_steps": 1390, "total_steps": 1688, "loss": 0.5251, "lr": 5e-06, "epoch": 3.2879952690715553, "percentage": 82.35, "elapsed_time": "11:28:33", "remaining_time": "2:27:37"}
|
| 143 |
+
{"current_steps": 1400, "total_steps": 1688, "loss": 0.5264, "lr": 5e-06, "epoch": 3.311649911295092, "percentage": 82.94, "elapsed_time": "11:33:25", "remaining_time": "2:22:38"}
|
| 144 |
+
{"current_steps": 1410, "total_steps": 1688, "loss": 0.5246, "lr": 5e-06, "epoch": 3.335304553518628, "percentage": 83.53, "elapsed_time": "11:38:17", "remaining_time": "2:17:40"}
|
| 145 |
+
{"current_steps": 1420, "total_steps": 1688, "loss": 0.5337, "lr": 5e-06, "epoch": 3.3589591957421643, "percentage": 84.12, "elapsed_time": "11:43:09", "remaining_time": "2:12:42"}
|
| 146 |
+
{"current_steps": 1430, "total_steps": 1688, "loss": 0.5293, "lr": 5e-06, "epoch": 3.382613837965701, "percentage": 84.72, "elapsed_time": "11:48:01", "remaining_time": "2:07:44"}
|
| 147 |
+
{"current_steps": 1440, "total_steps": 1688, "loss": 0.5237, "lr": 5e-06, "epoch": 3.406268480189237, "percentage": 85.31, "elapsed_time": "11:52:52", "remaining_time": "2:02:46"}
|
| 148 |
+
{"current_steps": 1450, "total_steps": 1688, "loss": 0.5271, "lr": 5e-06, "epoch": 3.4299231224127738, "percentage": 85.9, "elapsed_time": "11:57:44", "remaining_time": "1:57:48"}
|
| 149 |
+
{"current_steps": 1460, "total_steps": 1688, "loss": 0.5257, "lr": 5e-06, "epoch": 3.45357776463631, "percentage": 86.49, "elapsed_time": "12:02:36", "remaining_time": "1:52:50"}
|
| 150 |
+
{"current_steps": 1470, "total_steps": 1688, "loss": 0.5282, "lr": 5e-06, "epoch": 3.477232406859846, "percentage": 87.09, "elapsed_time": "12:07:27", "remaining_time": "1:47:52"}
|
| 151 |
+
{"current_steps": 1480, "total_steps": 1688, "loss": 0.5307, "lr": 5e-06, "epoch": 3.5008870490833828, "percentage": 87.68, "elapsed_time": "12:12:19", "remaining_time": "1:42:55"}
|
| 152 |
+
{"current_steps": 1490, "total_steps": 1688, "loss": 0.529, "lr": 5e-06, "epoch": 3.524541691306919, "percentage": 88.27, "elapsed_time": "12:17:10", "remaining_time": "1:37:57"}
|
| 153 |
+
{"current_steps": 1500, "total_steps": 1688, "loss": 0.5339, "lr": 5e-06, "epoch": 3.5481963335304556, "percentage": 88.86, "elapsed_time": "12:22:02", "remaining_time": "1:33:00"}
|
| 154 |
+
{"current_steps": 1510, "total_steps": 1688, "loss": 0.5304, "lr": 5e-06, "epoch": 3.571850975753992, "percentage": 89.45, "elapsed_time": "12:26:53", "remaining_time": "1:28:02"}
|
| 155 |
+
{"current_steps": 1520, "total_steps": 1688, "loss": 0.5284, "lr": 5e-06, "epoch": 3.595505617977528, "percentage": 90.05, "elapsed_time": "12:31:45", "remaining_time": "1:23:05"}
|
| 156 |
+
{"current_steps": 1530, "total_steps": 1688, "loss": 0.5227, "lr": 5e-06, "epoch": 3.619160260201064, "percentage": 90.64, "elapsed_time": "12:36:36", "remaining_time": "1:18:07"}
|
| 157 |
+
{"current_steps": 1540, "total_steps": 1688, "loss": 0.5322, "lr": 5e-06, "epoch": 3.642814902424601, "percentage": 91.23, "elapsed_time": "12:41:27", "remaining_time": "1:13:10"}
|
| 158 |
+
{"current_steps": 1550, "total_steps": 1688, "loss": 0.5277, "lr": 5e-06, "epoch": 3.6664695446481375, "percentage": 91.82, "elapsed_time": "12:46:19", "remaining_time": "1:08:13"}
|
| 159 |
+
{"current_steps": 1560, "total_steps": 1688, "loss": 0.5334, "lr": 5e-06, "epoch": 3.6901241868716737, "percentage": 92.42, "elapsed_time": "12:51:10", "remaining_time": "1:03:16"}
|
| 160 |
+
{"current_steps": 1570, "total_steps": 1688, "loss": 0.536, "lr": 5e-06, "epoch": 3.71377882909521, "percentage": 93.01, "elapsed_time": "12:56:01", "remaining_time": "0:58:19"}
|
| 161 |
+
{"current_steps": 1580, "total_steps": 1688, "loss": 0.534, "lr": 5e-06, "epoch": 3.737433471318746, "percentage": 93.6, "elapsed_time": "13:00:53", "remaining_time": "0:53:22"}
|
| 162 |
+
{"current_steps": 1590, "total_steps": 1688, "loss": 0.5281, "lr": 5e-06, "epoch": 3.7610881135422827, "percentage": 94.19, "elapsed_time": "13:05:44", "remaining_time": "0:48:25"}
|
| 163 |
+
{"current_steps": 1600, "total_steps": 1688, "loss": 0.5316, "lr": 5e-06, "epoch": 3.7847427557658193, "percentage": 94.79, "elapsed_time": "13:10:35", "remaining_time": "0:43:28"}
|
| 164 |
+
{"current_steps": 1610, "total_steps": 1688, "loss": 0.5353, "lr": 5e-06, "epoch": 3.8083973979893555, "percentage": 95.38, "elapsed_time": "13:15:25", "remaining_time": "0:38:32"}
|
| 165 |
+
{"current_steps": 1620, "total_steps": 1688, "loss": 0.5281, "lr": 5e-06, "epoch": 3.8320520402128917, "percentage": 95.97, "elapsed_time": "13:20:17", "remaining_time": "0:33:35"}
|
| 166 |
+
{"current_steps": 1630, "total_steps": 1688, "loss": 0.5304, "lr": 5e-06, "epoch": 3.855706682436428, "percentage": 96.56, "elapsed_time": "13:25:08", "remaining_time": "0:28:38"}
|
| 167 |
+
{"current_steps": 1640, "total_steps": 1688, "loss": 0.5349, "lr": 5e-06, "epoch": 3.8793613246599645, "percentage": 97.16, "elapsed_time": "13:29:58", "remaining_time": "0:23:42"}
|
| 168 |
+
{"current_steps": 1650, "total_steps": 1688, "loss": 0.5306, "lr": 5e-06, "epoch": 3.903015966883501, "percentage": 97.75, "elapsed_time": "13:34:50", "remaining_time": "0:18:45"}
|
| 169 |
+
{"current_steps": 1660, "total_steps": 1688, "loss": 0.5288, "lr": 5e-06, "epoch": 3.9266706091070374, "percentage": 98.34, "elapsed_time": "13:39:41", "remaining_time": "0:13:49"}
|
| 170 |
+
{"current_steps": 1670, "total_steps": 1688, "loss": 0.5289, "lr": 5e-06, "epoch": 3.9503252513305736, "percentage": 98.93, "elapsed_time": "13:44:32", "remaining_time": "0:08:53"}
|
| 171 |
+
{"current_steps": 1680, "total_steps": 1688, "loss": 0.5291, "lr": 5e-06, "epoch": 3.9739798935541097, "percentage": 99.53, "elapsed_time": "13:49:23", "remaining_time": "0:03:56"}
|