Training in progress, step 6800
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 4902257696
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:863fe3e3806ace2e3acf927592677fab360b3fd8b48ff71f8204001c88af0fdd
|
| 3 |
size 4902257696
|
model-00002-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4915960368
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:07612fab458191fccc1a2960aa38044042d3106115511aeb3fe8e2d3efc018b7
|
| 3 |
size 4915960368
|
model-00003-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4983068496
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b59b9259fef69fbfc24a830e98675de31c42fde5f1460f7e1d82ebd4250d915e
|
| 3 |
size 4983068496
|
model-00004-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1580230264
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e48615c8bb9426b01c30f6f680bf2089005289004c1ab9b64032769a4ee42082
|
| 3 |
size 1580230264
|
trainer_log.jsonl
CHANGED
|
@@ -2022,3 +2022,43 @@
|
|
| 2022 |
{"current_steps": 6590, "total_steps": 8169, "loss": 0.1509, "lr": 4.387758956013342e-06, "epoch": 5.646958011996572, "percentage": 80.67, "elapsed_time": "1 day, 15:53:23", "remaining_time": "9:33:28"}
|
| 2023 |
{"current_steps": 6595, "total_steps": 8169, "loss": 0.1446, "lr": 4.361086976555336e-06, "epoch": 5.651242502142245, "percentage": 80.73, "elapsed_time": "1 day, 15:56:06", "remaining_time": "9:31:52"}
|
| 2024 |
{"current_steps": 6600, "total_steps": 8169, "loss": 0.1429, "lr": 4.334486386731487e-06, "epoch": 5.655526992287918, "percentage": 80.79, "elapsed_time": "1 day, 15:58:47", "remaining_time": "9:30:15"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2022 |
{"current_steps": 6590, "total_steps": 8169, "loss": 0.1509, "lr": 4.387758956013342e-06, "epoch": 5.646958011996572, "percentage": 80.67, "elapsed_time": "1 day, 15:53:23", "remaining_time": "9:33:28"}
|
| 2023 |
{"current_steps": 6595, "total_steps": 8169, "loss": 0.1446, "lr": 4.361086976555336e-06, "epoch": 5.651242502142245, "percentage": 80.73, "elapsed_time": "1 day, 15:56:06", "remaining_time": "9:31:52"}
|
| 2024 |
{"current_steps": 6600, "total_steps": 8169, "loss": 0.1429, "lr": 4.334486386731487e-06, "epoch": 5.655526992287918, "percentage": 80.79, "elapsed_time": "1 day, 15:58:47", "remaining_time": "9:30:15"}
|
| 2025 |
+
{"current_steps": 6605, "total_steps": 8169, "loss": 0.1259, "lr": 4.307957307970085e-06, "epoch": 5.65981148243359, "percentage": 80.85, "elapsed_time": "1 day, 16:02:51", "remaining_time": "9:28:58"}
|
| 2026 |
+
{"current_steps": 6610, "total_steps": 8169, "loss": 0.1147, "lr": 4.2814998613729755e-06, "epoch": 5.664095972579263, "percentage": 80.92, "elapsed_time": "1 day, 16:05:45", "remaining_time": "9:27:24"}
|
| 2027 |
+
{"current_steps": 6615, "total_steps": 8169, "loss": 0.1371, "lr": 4.255114167715005e-06, "epoch": 5.668380462724936, "percentage": 80.98, "elapsed_time": "1 day, 16:08:38", "remaining_time": "9:25:50"}
|
| 2028 |
+
{"current_steps": 6620, "total_steps": 8169, "loss": 0.1305, "lr": 4.228800347443491e-06, "epoch": 5.672664952870608, "percentage": 81.04, "elapsed_time": "1 day, 16:11:38", "remaining_time": "9:24:17"}
|
| 2029 |
+
{"current_steps": 6625, "total_steps": 8169, "loss": 0.1459, "lr": 4.202558520677651e-06, "epoch": 5.676949443016281, "percentage": 81.1, "elapsed_time": "1 day, 16:14:31", "remaining_time": "9:22:43"}
|
| 2030 |
+
{"current_steps": 6630, "total_steps": 8169, "loss": 0.1379, "lr": 4.17638880720806e-06, "epoch": 5.681233933161954, "percentage": 81.16, "elapsed_time": "1 day, 16:17:18", "remaining_time": "9:21:07"}
|
| 2031 |
+
{"current_steps": 6635, "total_steps": 8169, "loss": 0.1413, "lr": 4.150291326496101e-06, "epoch": 5.685518423307626, "percentage": 81.22, "elapsed_time": "1 day, 16:20:13", "remaining_time": "9:19:33"}
|
| 2032 |
+
{"current_steps": 6640, "total_steps": 8169, "loss": 0.1435, "lr": 4.1242661976734434e-06, "epoch": 5.689802913453299, "percentage": 81.28, "elapsed_time": "1 day, 16:23:06", "remaining_time": "9:17:58"}
|
| 2033 |
+
{"current_steps": 6645, "total_steps": 8169, "loss": 0.1448, "lr": 4.09831353954145e-06, "epoch": 5.694087403598972, "percentage": 81.34, "elapsed_time": "1 day, 16:25:48", "remaining_time": "9:16:20"}
|
| 2034 |
+
{"current_steps": 6650, "total_steps": 8169, "loss": 0.1395, "lr": 4.072433470570696e-06, "epoch": 5.698371893744644, "percentage": 81.41, "elapsed_time": "1 day, 16:28:39", "remaining_time": "9:14:45"}
|
| 2035 |
+
{"current_steps": 6655, "total_steps": 8169, "loss": 0.1398, "lr": 4.046626108900369e-06, "epoch": 5.702656383890317, "percentage": 81.47, "elapsed_time": "1 day, 16:31:37", "remaining_time": "9:13:11"}
|
| 2036 |
+
{"current_steps": 6660, "total_steps": 8169, "loss": 0.1521, "lr": 4.0208915723377724e-06, "epoch": 5.70694087403599, "percentage": 81.53, "elapsed_time": "1 day, 16:34:24", "remaining_time": "9:11:34"}
|
| 2037 |
+
{"current_steps": 6665, "total_steps": 8169, "loss": 0.1351, "lr": 3.995229978357771e-06, "epoch": 5.711225364181662, "percentage": 81.59, "elapsed_time": "1 day, 16:37:09", "remaining_time": "9:09:57"}
|
| 2038 |
+
{"current_steps": 6670, "total_steps": 8169, "loss": 0.1341, "lr": 3.969641444102241e-06, "epoch": 5.715509854327335, "percentage": 81.65, "elapsed_time": "1 day, 16:39:58", "remaining_time": "9:08:21"}
|
| 2039 |
+
{"current_steps": 6675, "total_steps": 8169, "loss": 0.1405, "lr": 3.944126086379578e-06, "epoch": 5.719794344473008, "percentage": 81.71, "elapsed_time": "1 day, 16:42:45", "remaining_time": "9:06:44"}
|
| 2040 |
+
{"current_steps": 6680, "total_steps": 8169, "loss": 0.1452, "lr": 3.9186840216641075e-06, "epoch": 5.72407883461868, "percentage": 81.77, "elapsed_time": "1 day, 16:45:29", "remaining_time": "9:05:06"}
|
| 2041 |
+
{"current_steps": 6685, "total_steps": 8169, "loss": 0.1431, "lr": 3.893315366095609e-06, "epoch": 5.728363324764353, "percentage": 81.83, "elapsed_time": "1 day, 16:48:23", "remaining_time": "9:03:31"}
|
| 2042 |
+
{"current_steps": 6690, "total_steps": 8169, "loss": 0.1347, "lr": 3.868020235478735e-06, "epoch": 5.732647814910026, "percentage": 81.89, "elapsed_time": "1 day, 16:51:08", "remaining_time": "9:01:53"}
|
| 2043 |
+
{"current_steps": 6695, "total_steps": 8169, "loss": 0.1345, "lr": 3.842798745282521e-06, "epoch": 5.736932305055698, "percentage": 81.96, "elapsed_time": "1 day, 16:54:05", "remaining_time": "9:00:18"}
|
| 2044 |
+
{"current_steps": 6700, "total_steps": 8169, "loss": 0.141, "lr": 3.817651010639833e-06, "epoch": 5.741216795201371, "percentage": 82.02, "elapsed_time": "1 day, 16:56:57", "remaining_time": "8:58:41"}
|
| 2045 |
+
{"current_steps": 6705, "total_steps": 8169, "loss": 0.1484, "lr": 3.7925771463468564e-06, "epoch": 5.745501285347044, "percentage": 82.08, "elapsed_time": "1 day, 16:59:34", "remaining_time": "8:57:01"}
|
| 2046 |
+
{"current_steps": 6710, "total_steps": 8169, "loss": 0.1523, "lr": 3.7675772668625765e-06, "epoch": 5.749785775492716, "percentage": 82.14, "elapsed_time": "1 day, 17:02:20", "remaining_time": "8:55:24"}
|
| 2047 |
+
{"current_steps": 6715, "total_steps": 8169, "loss": 0.1497, "lr": 3.742651486308233e-06, "epoch": 5.754070265638389, "percentage": 82.2, "elapsed_time": "1 day, 17:05:11", "remaining_time": "8:53:47"}
|
| 2048 |
+
{"current_steps": 6720, "total_steps": 8169, "loss": 0.1481, "lr": 3.7177999184668267e-06, "epoch": 5.758354755784062, "percentage": 82.26, "elapsed_time": "1 day, 17:07:58", "remaining_time": "8:52:09"}
|
| 2049 |
+
{"current_steps": 6725, "total_steps": 8169, "loss": 0.1379, "lr": 3.693022676782578e-06, "epoch": 5.762639245929734, "percentage": 82.32, "elapsed_time": "1 day, 17:10:43", "remaining_time": "8:50:31"}
|
| 2050 |
+
{"current_steps": 6730, "total_steps": 8169, "loss": 0.1414, "lr": 3.6683198743604176e-06, "epoch": 5.766923736075407, "percentage": 82.38, "elapsed_time": "1 day, 17:13:39", "remaining_time": "8:48:54"}
|
| 2051 |
+
{"current_steps": 6735, "total_steps": 8169, "loss": 0.1384, "lr": 3.6436916239654775e-06, "epoch": 5.77120822622108, "percentage": 82.45, "elapsed_time": "1 day, 17:16:27", "remaining_time": "8:47:16"}
|
| 2052 |
+
{"current_steps": 6740, "total_steps": 8169, "loss": 0.131, "lr": 3.619138038022558e-06, "epoch": 5.775492716366752, "percentage": 82.51, "elapsed_time": "1 day, 17:19:26", "remaining_time": "8:45:41"}
|
| 2053 |
+
{"current_steps": 6745, "total_steps": 8169, "loss": 0.1419, "lr": 3.594659228615638e-06, "epoch": 5.779777206512425, "percentage": 82.57, "elapsed_time": "1 day, 17:22:19", "remaining_time": "8:44:04"}
|
| 2054 |
+
{"current_steps": 6750, "total_steps": 8169, "loss": 0.1349, "lr": 3.5702553074873515e-06, "epoch": 5.784061696658098, "percentage": 82.63, "elapsed_time": "1 day, 17:25:02", "remaining_time": "8:42:24"}
|
| 2055 |
+
{"current_steps": 6755, "total_steps": 8169, "loss": 0.139, "lr": 3.5459263860384676e-06, "epoch": 5.78834618680377, "percentage": 82.69, "elapsed_time": "1 day, 17:27:58", "remaining_time": "8:40:47"}
|
| 2056 |
+
{"current_steps": 6760, "total_steps": 8169, "loss": 0.1421, "lr": 3.521672575327393e-06, "epoch": 5.792630676949443, "percentage": 82.75, "elapsed_time": "1 day, 17:30:50", "remaining_time": "8:39:10"}
|
| 2057 |
+
{"current_steps": 6765, "total_steps": 8169, "loss": 0.1535, "lr": 3.4974939860696667e-06, "epoch": 5.796915167095116, "percentage": 82.81, "elapsed_time": "1 day, 17:33:33", "remaining_time": "8:37:30"}
|
| 2058 |
+
{"current_steps": 6770, "total_steps": 8169, "loss": 0.1525, "lr": 3.473390728637447e-06, "epoch": 5.8011996572407885, "percentage": 82.87, "elapsed_time": "1 day, 17:36:25", "remaining_time": "8:35:52"}
|
| 2059 |
+
{"current_steps": 6775, "total_steps": 8169, "loss": 0.1471, "lr": 3.4493629130590246e-06, "epoch": 5.805484147386461, "percentage": 82.94, "elapsed_time": "1 day, 17:39:09", "remaining_time": "8:34:13"}
|
| 2060 |
+
{"current_steps": 6780, "total_steps": 8169, "loss": 0.1394, "lr": 3.425410649018288e-06, "epoch": 5.809768637532134, "percentage": 83.0, "elapsed_time": "1 day, 17:41:53", "remaining_time": "8:32:33"}
|
| 2061 |
+
{"current_steps": 6785, "total_steps": 8169, "loss": 0.1374, "lr": 3.4015340458542667e-06, "epoch": 5.8140531276778065, "percentage": 83.06, "elapsed_time": "1 day, 17:44:39", "remaining_time": "8:30:53"}
|
| 2062 |
+
{"current_steps": 6790, "total_steps": 8169, "loss": 0.1411, "lr": 3.3777332125605876e-06, "epoch": 5.818337617823479, "percentage": 83.12, "elapsed_time": "1 day, 17:47:28", "remaining_time": "8:29:15"}
|
| 2063 |
+
{"current_steps": 6795, "total_steps": 8169, "loss": 0.1388, "lr": 3.354008257785004e-06, "epoch": 5.822622107969152, "percentage": 83.18, "elapsed_time": "1 day, 17:50:18", "remaining_time": "8:27:36"}
|
| 2064 |
+
{"current_steps": 6800, "total_steps": 8169, "loss": 0.1341, "lr": 3.3303592898288996e-06, "epoch": 5.8269065981148245, "percentage": 83.24, "elapsed_time": "1 day, 17:53:11", "remaining_time": "8:25:57"}
|