Training in progress, step 7800
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 sha256:0d26dcf3c0e529af9a7eea6fb8d8117c65107476d338908f4deb6e97c73127de
|
| 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:c8479b81cd172cf5cfa2215f8b62851d0cc4686e39ea12a3bf1c8178bf1fe493
|
| 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 sha256:66e90da1eb6ecf2f4a7b4b28d6ecc771e33ea40003bba510ea80f240f15eebdd
|
| 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 sha256:9b435329eaba1200040187e6db7600e9d1d6c9a7dae4fb45e290f7d3af25c96a
|
| 3 |
size 1580230264
|
trainer_log.jsonl
CHANGED
|
@@ -1532,3 +1532,43 @@
|
|
| 1532 |
{"current_steps": 7590, "total_steps": 9625, "loss": 0.1609, "lr": 5.209477477732172e-06, "epoch": 5.520189159694434, "percentage": 78.86, "elapsed_time": "3:02:43", "remaining_time": "0:48:59"}
|
| 1533 |
{"current_steps": 7595, "total_steps": 9625, "loss": 0.1276, "lr": 5.185088355142529e-06, "epoch": 5.523826846125864, "percentage": 78.91, "elapsed_time": "3:04:41", "remaining_time": "0:49:21"}
|
| 1534 |
{"current_steps": 7600, "total_steps": 9625, "loss": 0.1633, "lr": 5.160747951998979e-06, "epoch": 5.5274645325572935, "percentage": 78.96, "elapsed_time": "3:07:38", "remaining_time": "0:49:59"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1532 |
{"current_steps": 7590, "total_steps": 9625, "loss": 0.1609, "lr": 5.209477477732172e-06, "epoch": 5.520189159694434, "percentage": 78.86, "elapsed_time": "3:02:43", "remaining_time": "0:48:59"}
|
| 1533 |
{"current_steps": 7595, "total_steps": 9625, "loss": 0.1276, "lr": 5.185088355142529e-06, "epoch": 5.523826846125864, "percentage": 78.91, "elapsed_time": "3:04:41", "remaining_time": "0:49:21"}
|
| 1534 |
{"current_steps": 7600, "total_steps": 9625, "loss": 0.1633, "lr": 5.160747951998979e-06, "epoch": 5.5274645325572935, "percentage": 78.96, "elapsed_time": "3:07:38", "remaining_time": "0:49:59"}
|
| 1535 |
+
{"current_steps": 7605, "total_steps": 9625, "loss": 0.1586, "lr": 5.136456348345926e-06, "epoch": 5.531102218988723, "percentage": 79.01, "elapsed_time": "3:11:35", "remaining_time": "0:50:53"}
|
| 1536 |
+
{"current_steps": 7610, "total_steps": 9625, "loss": 0.1615, "lr": 5.112213624067317e-06, "epoch": 5.534739905420153, "percentage": 79.06, "elapsed_time": "3:14:24", "remaining_time": "0:51:28"}
|
| 1537 |
+
{"current_steps": 7615, "total_steps": 9625, "loss": 0.1579, "lr": 5.088019858886353e-06, "epoch": 5.5383775918515825, "percentage": 79.12, "elapsed_time": "3:17:21", "remaining_time": "0:52:05"}
|
| 1538 |
+
{"current_steps": 7620, "total_steps": 9625, "loss": 0.1571, "lr": 5.06387513236521e-06, "epoch": 5.542015278283012, "percentage": 79.17, "elapsed_time": "3:20:19", "remaining_time": "0:52:42"}
|
| 1539 |
+
{"current_steps": 7625, "total_steps": 9625, "loss": 0.1648, "lr": 5.039779523904824e-06, "epoch": 5.545652964714441, "percentage": 79.22, "elapsed_time": "3:23:04", "remaining_time": "0:53:15"}
|
| 1540 |
+
{"current_steps": 7630, "total_steps": 9625, "loss": 0.1546, "lr": 5.015733112744592e-06, "epoch": 5.5492906511458715, "percentage": 79.27, "elapsed_time": "3:25:38", "remaining_time": "0:53:46"}
|
| 1541 |
+
{"current_steps": 7635, "total_steps": 9625, "loss": 0.1289, "lr": 4.991735977962131e-06, "epoch": 5.552928337577301, "percentage": 79.32, "elapsed_time": "3:27:57", "remaining_time": "0:54:12"}
|
| 1542 |
+
{"current_steps": 7640, "total_steps": 9625, "loss": 0.1545, "lr": 4.967788198473e-06, "epoch": 5.55656602400873, "percentage": 79.38, "elapsed_time": "3:30:54", "remaining_time": "0:54:47"}
|
| 1543 |
+
{"current_steps": 7645, "total_steps": 9625, "loss": 0.1648, "lr": 4.943889853030452e-06, "epoch": 5.56020371044016, "percentage": 79.43, "elapsed_time": "3:33:47", "remaining_time": "0:55:22"}
|
| 1544 |
+
{"current_steps": 7650, "total_steps": 9625, "loss": 0.1567, "lr": 4.920041020225186e-06, "epoch": 5.56384139687159, "percentage": 79.48, "elapsed_time": "3:36:28", "remaining_time": "0:55:53"}
|
| 1545 |
+
{"current_steps": 7655, "total_steps": 9625, "loss": 0.154, "lr": 4.896241778485065e-06, "epoch": 5.567479083303019, "percentage": 79.53, "elapsed_time": "3:39:17", "remaining_time": "0:56:26"}
|
| 1546 |
+
{"current_steps": 7660, "total_steps": 9625, "loss": 0.1572, "lr": 4.872492206074881e-06, "epoch": 5.571116769734449, "percentage": 79.58, "elapsed_time": "3:42:04", "remaining_time": "0:56:58"}
|
| 1547 |
+
{"current_steps": 7665, "total_steps": 9625, "loss": 0.1779, "lr": 4.84879238109607e-06, "epoch": 5.574754456165879, "percentage": 79.64, "elapsed_time": "3:44:43", "remaining_time": "0:57:27"}
|
| 1548 |
+
{"current_steps": 7670, "total_steps": 9625, "loss": 0.2177, "lr": 4.825142381486492e-06, "epoch": 5.578392142597308, "percentage": 79.69, "elapsed_time": "3:47:02", "remaining_time": "0:57:52"}
|
| 1549 |
+
{"current_steps": 7675, "total_steps": 9625, "loss": 0.2142, "lr": 4.8015422850201285e-06, "epoch": 5.582029829028738, "percentage": 79.74, "elapsed_time": "3:49:16", "remaining_time": "0:58:15"}
|
| 1550 |
+
{"current_steps": 7680, "total_steps": 9625, "loss": 0.2099, "lr": 4.7779921693068755e-06, "epoch": 5.585667515460168, "percentage": 79.79, "elapsed_time": "3:51:38", "remaining_time": "0:58:39"}
|
| 1551 |
+
{"current_steps": 7685, "total_steps": 9625, "loss": 0.2009, "lr": 4.754492111792262e-06, "epoch": 5.589305201891597, "percentage": 79.84, "elapsed_time": "3:53:56", "remaining_time": "0:59:03"}
|
| 1552 |
+
{"current_steps": 7690, "total_steps": 9625, "loss": 0.2212, "lr": 4.731042189757182e-06, "epoch": 5.5929428883230266, "percentage": 79.9, "elapsed_time": "3:56:18", "remaining_time": "0:59:27"}
|
| 1553 |
+
{"current_steps": 7695, "total_steps": 9625, "loss": 0.2012, "lr": 4.707642480317676e-06, "epoch": 5.596580574754456, "percentage": 79.95, "elapsed_time": "3:58:41", "remaining_time": "0:59:52"}
|
| 1554 |
+
{"current_steps": 7700, "total_steps": 9625, "loss": 0.2078, "lr": 4.684293060424654e-06, "epoch": 5.600218261185885, "percentage": 80.0, "elapsed_time": "4:01:01", "remaining_time": "1:00:15"}
|
| 1555 |
+
{"current_steps": 7705, "total_steps": 9625, "loss": 0.2052, "lr": 4.660994006863631e-06, "epoch": 5.6038559476173155, "percentage": 80.05, "elapsed_time": "4:03:12", "remaining_time": "1:00:36"}
|
| 1556 |
+
{"current_steps": 7710, "total_steps": 9625, "loss": 0.2175, "lr": 4.637745396254516e-06, "epoch": 5.607493634048745, "percentage": 80.1, "elapsed_time": "4:05:44", "remaining_time": "1:01:02"}
|
| 1557 |
+
{"current_steps": 7715, "total_steps": 9625, "loss": 0.2098, "lr": 4.614547305051307e-06, "epoch": 5.611131320480174, "percentage": 80.16, "elapsed_time": "4:07:53", "remaining_time": "1:01:22"}
|
| 1558 |
+
{"current_steps": 7720, "total_steps": 9625, "loss": 0.2005, "lr": 4.59139980954189e-06, "epoch": 5.6147690069116045, "percentage": 80.21, "elapsed_time": "4:10:30", "remaining_time": "1:01:49"}
|
| 1559 |
+
{"current_steps": 7725, "total_steps": 9625, "loss": 0.2144, "lr": 4.568302985847755e-06, "epoch": 5.618406693343034, "percentage": 80.26, "elapsed_time": "4:12:40", "remaining_time": "1:02:08"}
|
| 1560 |
+
{"current_steps": 7730, "total_steps": 9625, "loss": 0.2047, "lr": 4.545256909923761e-06, "epoch": 5.622044379774463, "percentage": 80.31, "elapsed_time": "4:14:54", "remaining_time": "1:02:29"}
|
| 1561 |
+
{"current_steps": 7735, "total_steps": 9625, "loss": 0.1974, "lr": 4.5222616575578695e-06, "epoch": 5.6256820662058935, "percentage": 80.36, "elapsed_time": "4:16:40", "remaining_time": "1:02:43"}
|
| 1562 |
+
{"current_steps": 7740, "total_steps": 9625, "loss": 0.203, "lr": 4.499317304370909e-06, "epoch": 5.629319752637323, "percentage": 80.42, "elapsed_time": "4:18:19", "remaining_time": "1:02:54"}
|
| 1563 |
+
{"current_steps": 7745, "total_steps": 9625, "loss": 0.1971, "lr": 4.476423925816333e-06, "epoch": 5.632957439068752, "percentage": 80.47, "elapsed_time": "4:20:01", "remaining_time": "1:03:07"}
|
| 1564 |
+
{"current_steps": 7750, "total_steps": 9625, "loss": 0.2023, "lr": 4.4535815971799615e-06, "epoch": 5.636595125500182, "percentage": 80.52, "elapsed_time": "4:21:39", "remaining_time": "1:03:18"}
|
| 1565 |
+
{"current_steps": 7755, "total_steps": 9625, "loss": 0.2127, "lr": 4.430790393579733e-06, "epoch": 5.640232811931612, "percentage": 80.57, "elapsed_time": "4:23:15", "remaining_time": "1:03:28"}
|
| 1566 |
+
{"current_steps": 7760, "total_steps": 9625, "loss": 0.2036, "lr": 4.408050389965455e-06, "epoch": 5.643870498363041, "percentage": 80.62, "elapsed_time": "4:24:55", "remaining_time": "1:03:40"}
|
| 1567 |
+
{"current_steps": 7765, "total_steps": 9625, "loss": 0.2039, "lr": 4.3853616611185526e-06, "epoch": 5.647508184794471, "percentage": 80.68, "elapsed_time": "4:26:38", "remaining_time": "1:03:52"}
|
| 1568 |
+
{"current_steps": 7770, "total_steps": 9625, "loss": 0.1867, "lr": 4.362724281651862e-06, "epoch": 5.6511458712259, "percentage": 80.73, "elapsed_time": "4:28:19", "remaining_time": "1:04:03"}
|
| 1569 |
+
{"current_steps": 7775, "total_steps": 9625, "loss": 0.1948, "lr": 4.340138326009326e-06, "epoch": 5.65478355765733, "percentage": 80.78, "elapsed_time": "4:30:00", "remaining_time": "1:04:14"}
|
| 1570 |
+
{"current_steps": 7780, "total_steps": 9625, "loss": 0.1872, "lr": 4.317603868465794e-06, "epoch": 5.65842124408876, "percentage": 80.83, "elapsed_time": "4:31:36", "remaining_time": "1:04:24"}
|
| 1571 |
+
{"current_steps": 7785, "total_steps": 9625, "loss": 0.2033, "lr": 4.29512098312675e-06, "epoch": 5.662058930520189, "percentage": 80.88, "elapsed_time": "4:33:17", "remaining_time": "1:04:35"}
|
| 1572 |
+
{"current_steps": 7790, "total_steps": 9625, "loss": 0.2042, "lr": 4.272689743928087e-06, "epoch": 5.665696616951619, "percentage": 80.94, "elapsed_time": "4:34:56", "remaining_time": "1:04:45"}
|
| 1573 |
+
{"current_steps": 7795, "total_steps": 9625, "loss": 0.1954, "lr": 4.250310224635867e-06, "epoch": 5.669334303383049, "percentage": 80.99, "elapsed_time": "4:36:36", "remaining_time": "1:04:56"}
|
| 1574 |
+
{"current_steps": 7800, "total_steps": 9625, "loss": 0.1948, "lr": 4.2279824988460485e-06, "epoch": 5.672971989814478, "percentage": 81.04, "elapsed_time": "4:38:13", "remaining_time": "1:05:05"}
|