penfever commited on
Commit
a8b2c32
·
verified ·
1 Parent(s): a3ecd52

Training in progress, step 7600

Browse files
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6e2c45306981e5c74f700425c572edf461ef9fcf600583b67e22e52837ec5f06
3
  size 4902257696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49ef4dabce61f82c1cd07f89e02230788e4c1ccf5c7442b429b0208643f6c72e
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:db8f15a5201ab6cc445c8a4a097991d0614fda600812bd1269e0419f37d47f03
3
  size 4915960368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e3e55adff8d1f3dca1a69ea662001c57a2528f88635674bc75f438f2d2053c2
3
  size 4915960368
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1bacb5fb4250e7fc9e487028d3308866772a5f2dc36ab8dd98da2e931a3b16fe
3
  size 4983068496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b30c4e745da4439dbea48c719f961d77a21b5040d7e7b6a03c05b9e50d90fe4f
3
  size 4983068496
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:57a55495ae17b6bb8c82dad01a9f10f2eeed43cc8c5b989fcf6ce5d0b78df101
3
  size 1580230264
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb9a05f23c9eb49df4bb81e7a0f00d11e09f17b5bfbe6a575898f6a3f2ea24c3
3
  size 1580230264
run_summary.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "agent_name": null,
3
- "training_start": null,
4
  "training_end": null,
5
  "created_by": "DCAgent",
6
  "base_model_name": "Qwen/Qwen3-8B",
 
1
  {
2
  "agent_name": null,
3
+ "training_start": "2025-12-06T15:38:59Z",
4
  "training_end": null,
5
  "created_by": "DCAgent",
6
  "base_model_name": "Qwen/Qwen3-8B",
trainer_log.jsonl CHANGED
@@ -1479,3 +1479,75 @@
1479
  {"current_steps": 7395, "total_steps": 8603, "loss": 0.1657, "lr": 2.358945216396855e-06, "epoch": 6.017094017094017, "percentage": 85.96, "elapsed_time": "1 day, 21:28:07", "remaining_time": "7:25:39"}
1480
  {"current_steps": 7400, "total_steps": 8603, "loss": 0.1706, "lr": 2.3398629201439427e-06, "epoch": 6.021164021164021, "percentage": 86.02, "elapsed_time": "1 day, 21:31:10", "remaining_time": "7:24:00"}
1481
  {"current_steps": 7405, "total_steps": 8603, "loss": 0.1833, "lr": 2.3208533227076257e-06, "epoch": 6.025234025234025, "percentage": 86.07, "elapsed_time": "1 day, 21:35:18", "remaining_time": "7:22:31"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1479
  {"current_steps": 7395, "total_steps": 8603, "loss": 0.1657, "lr": 2.358945216396855e-06, "epoch": 6.017094017094017, "percentage": 85.96, "elapsed_time": "1 day, 21:28:07", "remaining_time": "7:25:39"}
1480
  {"current_steps": 7400, "total_steps": 8603, "loss": 0.1706, "lr": 2.3398629201439427e-06, "epoch": 6.021164021164021, "percentage": 86.02, "elapsed_time": "1 day, 21:31:10", "remaining_time": "7:24:00"}
1481
  {"current_steps": 7405, "total_steps": 8603, "loss": 0.1833, "lr": 2.3208533227076257e-06, "epoch": 6.025234025234025, "percentage": 86.07, "elapsed_time": "1 day, 21:35:18", "remaining_time": "7:22:31"}
1482
+ {"current_steps": 7410, "total_steps": 8603, "loss": 0.1771, "lr": 2.3019165023418433e-06, "epoch": 6.029304029304029, "percentage": 86.13, "elapsed_time": "1 day, 21:38:16", "remaining_time": "7:20:51"}
1483
+ {"current_steps": 7415, "total_steps": 8603, "loss": 0.1656, "lr": 2.2830525370009405e-06, "epoch": 6.0333740333740336, "percentage": 86.19, "elapsed_time": "1 day, 21:41:09", "remaining_time": "7:19:10"}
1484
+ {"current_steps": 7420, "total_steps": 8603, "loss": 0.1517, "lr": 2.2642615043393512e-06, "epoch": 6.037444037444037, "percentage": 86.25, "elapsed_time": "1 day, 21:43:38", "remaining_time": "7:17:25"}
1485
+ {"current_steps": 7425, "total_steps": 8603, "loss": 0.1573, "lr": 2.2455434817112853e-06, "epoch": 6.041514041514041, "percentage": 86.31, "elapsed_time": "1 day, 21:46:30", "remaining_time": "7:15:44"}
1486
+ {"current_steps": 7430, "total_steps": 8603, "loss": 0.166, "lr": 2.226898546170384e-06, "epoch": 6.045584045584046, "percentage": 86.37, "elapsed_time": "1 day, 21:49:21", "remaining_time": "7:14:02"}
1487
+ {"current_steps": 7435, "total_steps": 8603, "loss": 0.1616, "lr": 2.2083267744694494e-06, "epoch": 6.04965404965405, "percentage": 86.42, "elapsed_time": "1 day, 21:52:07", "remaining_time": "7:12:20"}
1488
+ {"current_steps": 7440, "total_steps": 8603, "loss": 0.1609, "lr": 2.1898282430600727e-06, "epoch": 6.0537240537240535, "percentage": 86.48, "elapsed_time": "1 day, 21:54:53", "remaining_time": "7:10:38"}
1489
+ {"current_steps": 7445, "total_steps": 8603, "loss": 0.1573, "lr": 2.171403028092367e-06, "epoch": 6.057794057794058, "percentage": 86.54, "elapsed_time": "1 day, 21:57:42", "remaining_time": "7:08:56"}
1490
+ {"current_steps": 7405, "total_steps": 8603, "loss": 0.1834, "lr": 2.3208533227076257e-06, "epoch": 6.025234025234025, "percentage": 86.07, "elapsed_time": "0:03:08", "remaining_time": "0:00:30"}
1491
+ {"current_steps": 7410, "total_steps": 8603, "loss": 0.1771, "lr": 2.3019165023418433e-06, "epoch": 6.029304029304029, "percentage": 86.13, "elapsed_time": "0:06:06", "remaining_time": "0:00:58"}
1492
+ {"current_steps": 7415, "total_steps": 8603, "loss": 0.1655, "lr": 2.2830525370009405e-06, "epoch": 6.0333740333740336, "percentage": 86.19, "elapsed_time": "0:08:58", "remaining_time": "0:01:26"}
1493
+ {"current_steps": 7420, "total_steps": 8603, "loss": 0.1516, "lr": 2.2642615043393512e-06, "epoch": 6.037444037444037, "percentage": 86.25, "elapsed_time": "0:11:28", "remaining_time": "0:01:49"}
1494
+ {"current_steps": 7425, "total_steps": 8603, "loss": 0.1572, "lr": 2.2455434817112853e-06, "epoch": 6.041514041514041, "percentage": 86.31, "elapsed_time": "0:14:20", "remaining_time": "0:02:16"}
1495
+ {"current_steps": 7430, "total_steps": 8603, "loss": 0.166, "lr": 2.226898546170384e-06, "epoch": 6.045584045584046, "percentage": 86.37, "elapsed_time": "0:17:11", "remaining_time": "0:02:42"}
1496
+ {"current_steps": 7435, "total_steps": 8603, "loss": 0.1616, "lr": 2.2083267744694494e-06, "epoch": 6.04965404965405, "percentage": 86.42, "elapsed_time": "0:19:57", "remaining_time": "0:03:08"}
1497
+ {"current_steps": 7440, "total_steps": 8603, "loss": 0.1608, "lr": 2.1898282430600727e-06, "epoch": 6.0537240537240535, "percentage": 86.48, "elapsed_time": "0:22:43", "remaining_time": "0:03:33"}
1498
+ {"current_steps": 7445, "total_steps": 8603, "loss": 0.1573, "lr": 2.171403028092367e-06, "epoch": 6.057794057794058, "percentage": 86.54, "elapsed_time": "0:25:33", "remaining_time": "0:03:58"}
1499
+ {"current_steps": 7450, "total_steps": 8603, "loss": 0.1591, "lr": 2.153051205414631e-06, "epoch": 6.061864061864062, "percentage": 86.6, "elapsed_time": "0:28:15", "remaining_time": "0:04:22"}
1500
+ {"current_steps": 7455, "total_steps": 8603, "loss": 0.1616, "lr": 2.1347728505730392e-06, "epoch": 6.065934065934066, "percentage": 86.66, "elapsed_time": "0:31:00", "remaining_time": "0:04:46"}
1501
+ {"current_steps": 7460, "total_steps": 8603, "loss": 0.1588, "lr": 2.116568038811333e-06, "epoch": 6.07000407000407, "percentage": 86.71, "elapsed_time": "0:33:57", "remaining_time": "0:05:12"}
1502
+ {"current_steps": 7465, "total_steps": 8603, "loss": 0.1678, "lr": 2.098436845070504e-06, "epoch": 6.074074074074074, "percentage": 86.77, "elapsed_time": "0:36:48", "remaining_time": "0:05:36"}
1503
+ {"current_steps": 7470, "total_steps": 8603, "loss": 0.1842, "lr": 2.080379343988497e-06, "epoch": 6.078144078144078, "percentage": 86.83, "elapsed_time": "0:39:37", "remaining_time": "0:06:00"}
1504
+ {"current_steps": 7475, "total_steps": 8603, "loss": 0.1285, "lr": 2.0623956098999056e-06, "epoch": 6.082214082214082, "percentage": 86.89, "elapsed_time": "0:42:09", "remaining_time": "0:06:21"}
1505
+ {"current_steps": 7480, "total_steps": 8603, "loss": 0.1535, "lr": 2.044485716835638e-06, "epoch": 6.086284086284087, "percentage": 86.95, "elapsed_time": "0:45:01", "remaining_time": "0:06:45"}
1506
+ {"current_steps": 7485, "total_steps": 8603, "loss": 0.1584, "lr": 2.026649738522648e-06, "epoch": 6.09035409035409, "percentage": 87.0, "elapsed_time": "0:47:53", "remaining_time": "0:07:09"}
1507
+ {"current_steps": 7490, "total_steps": 8603, "loss": 0.1651, "lr": 2.00888774838361e-06, "epoch": 6.094424094424094, "percentage": 87.06, "elapsed_time": "0:50:37", "remaining_time": "0:07:31"}
1508
+ {"current_steps": 7495, "total_steps": 8603, "loss": 0.1589, "lr": 1.9911998195366267e-06, "epoch": 6.098494098494099, "percentage": 87.12, "elapsed_time": "0:53:35", "remaining_time": "0:07:55"}
1509
+ {"current_steps": 7500, "total_steps": 8603, "loss": 0.1597, "lr": 1.9735860247949245e-06, "epoch": 6.102564102564102, "percentage": 87.18, "elapsed_time": "0:56:36", "remaining_time": "0:08:19"}
1510
+ {"current_steps": 7505, "total_steps": 8603, "loss": 0.1407, "lr": 1.956046436666539e-06, "epoch": 6.1066341066341066, "percentage": 87.24, "elapsed_time": "0:59:34", "remaining_time": "0:08:42"}
1511
+ {"current_steps": 7510, "total_steps": 8603, "loss": 0.1402, "lr": 1.938581127354049e-06, "epoch": 6.110704110704111, "percentage": 87.3, "elapsed_time": "1:02:30", "remaining_time": "0:09:05"}
1512
+ {"current_steps": 7515, "total_steps": 8603, "loss": 0.1474, "lr": 1.92119016875425e-06, "epoch": 6.114774114774114, "percentage": 87.35, "elapsed_time": "1:05:26", "remaining_time": "0:09:28"}
1513
+ {"current_steps": 7520, "total_steps": 8603, "loss": 0.1424, "lr": 1.903873632457871e-06, "epoch": 6.118844118844119, "percentage": 87.41, "elapsed_time": "1:07:40", "remaining_time": "0:09:44"}
1514
+ {"current_steps": 7525, "total_steps": 8603, "loss": 0.1656, "lr": 1.8866315897492792e-06, "epoch": 6.122914122914123, "percentage": 87.47, "elapsed_time": "1:10:26", "remaining_time": "0:10:05"}
1515
+ {"current_steps": 7530, "total_steps": 8603, "loss": 0.1706, "lr": 1.8694641116061895e-06, "epoch": 6.1269841269841265, "percentage": 87.53, "elapsed_time": "1:13:17", "remaining_time": "0:10:26"}
1516
+ {"current_steps": 7535, "total_steps": 8603, "loss": 0.1694, "lr": 1.8523712686993644e-06, "epoch": 6.131054131054131, "percentage": 87.59, "elapsed_time": "1:16:09", "remaining_time": "0:10:47"}
1517
+ {"current_steps": 7540, "total_steps": 8603, "loss": 0.1644, "lr": 1.8353531313923213e-06, "epoch": 6.135124135124135, "percentage": 87.64, "elapsed_time": "1:19:00", "remaining_time": "0:11:08"}
1518
+ {"current_steps": 7545, "total_steps": 8603, "loss": 0.1604, "lr": 1.818409769741054e-06, "epoch": 6.13919413919414, "percentage": 87.7, "elapsed_time": "1:22:02", "remaining_time": "0:11:30"}
1519
+ {"current_steps": 7550, "total_steps": 8603, "loss": 0.1656, "lr": 1.8015412534937438e-06, "epoch": 6.143264143264143, "percentage": 87.76, "elapsed_time": "1:25:00", "remaining_time": "0:11:51"}
1520
+ {"current_steps": 7555, "total_steps": 8603, "loss": 0.1603, "lr": 1.7847476520904528e-06, "epoch": 6.147334147334147, "percentage": 87.82, "elapsed_time": "1:27:58", "remaining_time": "0:12:12"}
1521
+ {"current_steps": 7560, "total_steps": 8603, "loss": 0.1686, "lr": 1.7680290346628659e-06, "epoch": 6.151404151404152, "percentage": 87.88, "elapsed_time": "1:30:59", "remaining_time": "0:12:33"}
1522
+ {"current_steps": 7565, "total_steps": 8603, "loss": 0.1626, "lr": 1.7513854700339884e-06, "epoch": 6.155474155474155, "percentage": 87.93, "elapsed_time": "1:33:58", "remaining_time": "0:12:53"}
1523
+ {"current_steps": 7570, "total_steps": 8603, "loss": 0.1631, "lr": 1.7348170267178655e-06, "epoch": 6.15954415954416, "percentage": 87.99, "elapsed_time": "1:36:54", "remaining_time": "0:13:13"}
1524
+ {"current_steps": 7575, "total_steps": 8603, "loss": 0.161, "lr": 1.7183237729193081e-06, "epoch": 6.163614163614164, "percentage": 88.05, "elapsed_time": "1:39:38", "remaining_time": "0:13:31"}
1525
+ {"current_steps": 7580, "total_steps": 8603, "loss": 0.1525, "lr": 1.7019057765335945e-06, "epoch": 6.167684167684167, "percentage": 88.11, "elapsed_time": "1:42:20", "remaining_time": "0:13:48"}
1526
+ {"current_steps": 7585, "total_steps": 8603, "loss": 0.1308, "lr": 1.6855631051462084e-06, "epoch": 6.171754171754172, "percentage": 88.17, "elapsed_time": "1:44:32", "remaining_time": "0:14:01"}
1527
+ {"current_steps": 7590, "total_steps": 8603, "loss": 0.157, "lr": 1.6692958260325599e-06, "epoch": 6.175824175824176, "percentage": 88.23, "elapsed_time": "1:47:24", "remaining_time": "0:14:20"}
1528
+ {"current_steps": 7595, "total_steps": 8603, "loss": 0.1578, "lr": 1.6531040061576909e-06, "epoch": 6.1798941798941796, "percentage": 88.28, "elapsed_time": "1:50:12", "remaining_time": "0:14:37"}
1529
+ {"current_steps": 7600, "total_steps": 8603, "loss": 0.158, "lr": 1.6369877121760237e-06, "epoch": 6.183964183964184, "percentage": 88.34, "elapsed_time": "1:53:09", "remaining_time": "0:14:56"}
1530
+ {"current_steps": 7605, "total_steps": 8603, "loss": 0.1574, "lr": 1.6209470104310666e-06, "epoch": 6.188034188034188, "percentage": 88.4, "elapsed_time": "1:57:14", "remaining_time": "0:15:23"}
1531
+ {"current_steps": 7610, "total_steps": 8603, "loss": 0.1613, "lr": 1.604981966955157e-06, "epoch": 6.192104192104192, "percentage": 88.46, "elapsed_time": "2:00:15", "remaining_time": "0:15:41"}
1532
+ {"current_steps": 7615, "total_steps": 8603, "loss": 0.1609, "lr": 1.5890926474691682e-06, "epoch": 6.196174196174196, "percentage": 88.52, "elapsed_time": "2:03:06", "remaining_time": "0:15:58"}
1533
+ {"current_steps": 7620, "total_steps": 8603, "loss": 0.1234, "lr": 1.5732791173822626e-06, "epoch": 6.2002442002442, "percentage": 88.57, "elapsed_time": "2:05:18", "remaining_time": "0:16:09"}
1534
+ {"current_steps": 7625, "total_steps": 8603, "loss": 0.1541, "lr": 1.55754144179161e-06, "epoch": 6.204314204314204, "percentage": 88.63, "elapsed_time": "2:07:52", "remaining_time": "0:16:24"}
1535
+ {"current_steps": 7630, "total_steps": 8603, "loss": 0.1545, "lr": 1.5418796854821239e-06, "epoch": 6.208384208384208, "percentage": 88.69, "elapsed_time": "2:10:44", "remaining_time": "0:16:40"}
1536
+ {"current_steps": 7635, "total_steps": 8603, "loss": 0.1608, "lr": 1.52629391292618e-06, "epoch": 6.212454212454213, "percentage": 88.75, "elapsed_time": "2:13:37", "remaining_time": "0:16:56"}
1537
+ {"current_steps": 7640, "total_steps": 8603, "loss": 0.1535, "lr": 1.5107841882833785e-06, "epoch": 6.216524216524217, "percentage": 88.81, "elapsed_time": "2:16:19", "remaining_time": "0:17:11"}
1538
+ {"current_steps": 7645, "total_steps": 8603, "loss": 0.1506, "lr": 1.4953505754002562e-06, "epoch": 6.22059422059422, "percentage": 88.86, "elapsed_time": "2:19:05", "remaining_time": "0:17:25"}
1539
+ {"current_steps": 7650, "total_steps": 8603, "loss": 0.1582, "lr": 1.4799931378100386e-06, "epoch": 6.224664224664225, "percentage": 88.92, "elapsed_time": "2:22:07", "remaining_time": "0:17:42"}
1540
+ {"current_steps": 7655, "total_steps": 8603, "loss": 0.1532, "lr": 1.4647119387323593e-06, "epoch": 6.228734228734229, "percentage": 88.98, "elapsed_time": "2:24:01", "remaining_time": "0:17:50"}
1541
+ {"current_steps": 7660, "total_steps": 8603, "loss": 0.1392, "lr": 1.4495070410730238e-06, "epoch": 6.232804232804233, "percentage": 89.04, "elapsed_time": "2:25:15", "remaining_time": "0:17:52"}
1542
+ {"current_steps": 7665, "total_steps": 8603, "loss": 0.1284, "lr": 1.4343785074237393e-06, "epoch": 6.236874236874237, "percentage": 89.1, "elapsed_time": "2:26:32", "remaining_time": "0:17:55"}
1543
+ {"current_steps": 7670, "total_steps": 8603, "loss": 0.1277, "lr": 1.4193264000618511e-06, "epoch": 6.240944240944241, "percentage": 89.15, "elapsed_time": "2:27:46", "remaining_time": "0:17:58"}
1544
+ {"current_steps": 7675, "total_steps": 8603, "loss": 0.1268, "lr": 1.4043507809500923e-06, "epoch": 6.245014245014245, "percentage": 89.21, "elapsed_time": "2:29:05", "remaining_time": "0:18:01"}
1545
+ {"current_steps": 7680, "total_steps": 8603, "loss": 0.1248, "lr": 1.3894517117363294e-06, "epoch": 6.249084249084249, "percentage": 89.27, "elapsed_time": "2:30:19", "remaining_time": "0:18:04"}
1546
+ {"current_steps": 7685, "total_steps": 8603, "loss": 0.1284, "lr": 1.3746292537533145e-06, "epoch": 6.253154253154253, "percentage": 89.33, "elapsed_time": "2:31:34", "remaining_time": "0:18:06"}
1547
+ {"current_steps": 7690, "total_steps": 8603, "loss": 0.1134, "lr": 1.3598834680184124e-06, "epoch": 6.257224257224257, "percentage": 89.39, "elapsed_time": "2:32:48", "remaining_time": "0:18:08"}
1548
+ {"current_steps": 7695, "total_steps": 8603, "loss": 0.1333, "lr": 1.3452144152333734e-06, "epoch": 6.261294261294261, "percentage": 89.45, "elapsed_time": "2:34:01", "remaining_time": "0:18:10"}
1549
+ {"current_steps": 7700, "total_steps": 8603, "loss": 0.1255, "lr": 1.330622155784067e-06, "epoch": 6.265364265364266, "percentage": 89.5, "elapsed_time": "2:35:17", "remaining_time": "0:18:12"}
1550
+ {"current_steps": 7705, "total_steps": 8603, "loss": 0.1178, "lr": 1.316106749740249e-06, "epoch": 6.269434269434269, "percentage": 89.56, "elapsed_time": "2:36:33", "remaining_time": "0:18:14"}
1551
+ {"current_steps": 7710, "total_steps": 8603, "loss": 0.1218, "lr": 1.3016682568552907e-06, "epoch": 6.273504273504273, "percentage": 89.62, "elapsed_time": "2:37:50", "remaining_time": "0:18:16"}
1552
+ {"current_steps": 7715, "total_steps": 8603, "loss": 0.1227, "lr": 1.2873067365659519e-06, "epoch": 6.277574277574278, "percentage": 89.68, "elapsed_time": "2:39:05", "remaining_time": "0:18:18"}
1553
+ {"current_steps": 7720, "total_steps": 8603, "loss": 0.1122, "lr": 1.273022247992135e-06, "epoch": 6.281644281644281, "percentage": 89.74, "elapsed_time": "2:40:19", "remaining_time": "0:18:20"}
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:db71d266db88e3d09c360567f8c03e83850f043b34d50ac9a95966a1b9e5f449
3
- size 8529
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03bb0d135b740d7e744815f37dffc75e2732389df5d3e6fb90307598587524be
3
+ size 8593