penfever commited on
Commit
0ed64b4
·
verified ·
1 Parent(s): d850639

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 sha256:2c8a4b24bb63a32345621f6b272b6eaf0e5feb30219699790516046f86484513
3
  size 4902257696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f83b76202119189b08cf4bc8966d9d1ea3400209dd9c1666486aad4e56317c15
3
  size 4902257696
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:01fe14bff8706d203c2b6d04c72176421c31076b70c5687f78ab6bdefa81fb83
3
  size 4915960368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e876585ade0ff8eab8abcea137ea1e3f833388288d75a102d5aad710fe217ea
3
  size 4915960368
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:906921c60559d7cc7695832c474399b3ffd5ffa8b9a33fa34301cd0faeee029d
3
  size 4983068496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5861755947cde3bde8d86a4a496244199a6740a8917442556a4609328822ce11
3
  size 4983068496
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:688a70e298915964acb7c361e2192d40731840d5b820f8f9295f2b376fbe557c
3
  size 1580230264
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d55b390f114eadc25bcc71f057fc35f279d251dc3a20ae6b0650259dfa8e6fb
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": "2025-12-06T13:25:18Z",
4
  "training_end": null,
5
  "created_by": "DCAgent",
6
  "base_model_name": "Qwen/Qwen3-8B",
trainer_log.jsonl CHANGED
@@ -1521,3 +1521,91 @@
1521
  {"current_steps": 7605, "total_steps": 9128, "loss": 0.1958, "lr": 3.3016160465083293e-06, "epoch": 5.832374376678175, "percentage": 83.32, "elapsed_time": "1 day, 23:01:26", "remaining_time": "9:25:01"}
1522
  {"current_steps": 7610, "total_steps": 9128, "loss": 0.1879, "lr": 3.280599155807229e-06, "epoch": 5.836210203298811, "percentage": 83.37, "elapsed_time": "1 day, 23:03:10", "remaining_time": "9:23:09"}
1523
  {"current_steps": 7615, "total_steps": 9128, "loss": 0.1799, "lr": 3.2596433938112495e-06, "epoch": 5.840046029919447, "percentage": 83.42, "elapsed_time": "1 day, 23:04:56", "remaining_time": "9:21:16"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1521
  {"current_steps": 7605, "total_steps": 9128, "loss": 0.1958, "lr": 3.3016160465083293e-06, "epoch": 5.832374376678175, "percentage": 83.32, "elapsed_time": "1 day, 23:01:26", "remaining_time": "9:25:01"}
1522
  {"current_steps": 7610, "total_steps": 9128, "loss": 0.1879, "lr": 3.280599155807229e-06, "epoch": 5.836210203298811, "percentage": 83.37, "elapsed_time": "1 day, 23:03:10", "remaining_time": "9:23:09"}
1523
  {"current_steps": 7615, "total_steps": 9128, "loss": 0.1799, "lr": 3.2596433938112495e-06, "epoch": 5.840046029919447, "percentage": 83.42, "elapsed_time": "1 day, 23:04:56", "remaining_time": "9:21:16"}
1524
+ {"current_steps": 7620, "total_steps": 9128, "loss": 0.196, "lr": 3.238748837137866e-06, "epoch": 5.843881856540085, "percentage": 83.48, "elapsed_time": "1 day, 23:06:32", "remaining_time": "9:19:22"}
1525
+ {"current_steps": 7625, "total_steps": 9128, "loss": 0.1817, "lr": 3.217915562180802e-06, "epoch": 5.847717683160721, "percentage": 83.53, "elapsed_time": "1 day, 23:08:13", "remaining_time": "9:17:29"}
1526
+ {"current_steps": 7630, "total_steps": 9128, "loss": 0.1929, "lr": 3.1971436451097302e-06, "epoch": 5.851553509781358, "percentage": 83.59, "elapsed_time": "1 day, 23:09:55", "remaining_time": "9:15:35"}
1527
+ {"current_steps": 7635, "total_steps": 9128, "loss": 0.1976, "lr": 3.1764331618699673e-06, "epoch": 5.855389336401995, "percentage": 83.64, "elapsed_time": "1 day, 23:11:35", "remaining_time": "9:13:42"}
1528
+ {"current_steps": 7640, "total_steps": 9128, "loss": 0.1957, "lr": 3.155784188182229e-06, "epoch": 5.859225163022631, "percentage": 83.7, "elapsed_time": "1 day, 23:13:17", "remaining_time": "9:11:49"}
1529
+ {"current_steps": 7645, "total_steps": 9128, "loss": 0.2079, "lr": 3.1351967995423594e-06, "epoch": 5.863060989643268, "percentage": 83.75, "elapsed_time": "1 day, 23:14:54", "remaining_time": "9:09:55"}
1530
+ {"current_steps": 7650, "total_steps": 9128, "loss": 0.19, "lr": 3.114671071221005e-06, "epoch": 5.866896816263905, "percentage": 83.81, "elapsed_time": "1 day, 23:16:30", "remaining_time": "9:08:01"}
1531
+ {"current_steps": 7655, "total_steps": 9128, "loss": 0.2056, "lr": 3.094207078263405e-06, "epoch": 5.870732642884541, "percentage": 83.86, "elapsed_time": "1 day, 23:18:14", "remaining_time": "9:06:08"}
1532
+ {"current_steps": 7660, "total_steps": 9128, "loss": 0.2008, "lr": 3.073804895489061e-06, "epoch": 5.874568469505179, "percentage": 83.92, "elapsed_time": "1 day, 23:19:56", "remaining_time": "9:04:15"}
1533
+ {"current_steps": 7665, "total_steps": 9128, "loss": 0.1972, "lr": 3.0534645974914933e-06, "epoch": 5.878404296125815, "percentage": 83.97, "elapsed_time": "1 day, 23:21:34", "remaining_time": "9:02:21"}
1534
+ {"current_steps": 7670, "total_steps": 9128, "loss": 0.2063, "lr": 3.0331862586379813e-06, "epoch": 5.882240122746452, "percentage": 84.03, "elapsed_time": "1 day, 23:23:21", "remaining_time": "9:00:29"}
1535
+ {"current_steps": 7675, "total_steps": 9128, "loss": 0.1943, "lr": 3.0129699530692335e-06, "epoch": 5.886075949367089, "percentage": 84.08, "elapsed_time": "1 day, 23:25:00", "remaining_time": "8:58:36"}
1536
+ {"current_steps": 7680, "total_steps": 9128, "loss": 0.197, "lr": 2.992815754699194e-06, "epoch": 5.889911775987725, "percentage": 84.14, "elapsed_time": "1 day, 23:26:35", "remaining_time": "8:56:42"}
1537
+ {"current_steps": 7685, "total_steps": 9128, "loss": 0.2012, "lr": 2.9727237372147177e-06, "epoch": 5.893747602608362, "percentage": 84.19, "elapsed_time": "1 day, 23:28:14", "remaining_time": "8:54:48"}
1538
+ {"current_steps": 7690, "total_steps": 9128, "loss": 0.1892, "lr": 2.952693974075298e-06, "epoch": 5.897583429228999, "percentage": 84.25, "elapsed_time": "1 day, 23:29:54", "remaining_time": "8:52:55"}
1539
+ {"current_steps": 7695, "total_steps": 9128, "loss": 0.185, "lr": 2.932726538512851e-06, "epoch": 5.9014192558496354, "percentage": 84.3, "elapsed_time": "1 day, 23:31:40", "remaining_time": "8:51:03"}
1540
+ {"current_steps": 7700, "total_steps": 9128, "loss": 0.1942, "lr": 2.9128215035313976e-06, "epoch": 5.905255082470273, "percentage": 84.36, "elapsed_time": "1 day, 23:33:22", "remaining_time": "8:49:10"}
1541
+ {"current_steps": 7705, "total_steps": 9128, "loss": 0.1894, "lr": 2.8929789419067964e-06, "epoch": 5.909090909090909, "percentage": 84.41, "elapsed_time": "1 day, 23:35:04", "remaining_time": "8:47:17"}
1542
+ {"current_steps": 7710, "total_steps": 9128, "loss": 0.2028, "lr": 2.8731989261865247e-06, "epoch": 5.912926735711546, "percentage": 84.47, "elapsed_time": "1 day, 23:36:41", "remaining_time": "8:45:23"}
1543
+ {"current_steps": 7715, "total_steps": 9128, "loss": 0.1939, "lr": 2.8534815286893614e-06, "epoch": 5.916762562332183, "percentage": 84.52, "elapsed_time": "1 day, 23:38:21", "remaining_time": "8:43:30"}
1544
+ {"current_steps": 7720, "total_steps": 9128, "loss": 0.1978, "lr": 2.83382682150515e-06, "epoch": 5.920598388952819, "percentage": 84.57, "elapsed_time": "1 day, 23:40:02", "remaining_time": "8:41:37"}
1545
+ {"current_steps": 7725, "total_steps": 9128, "loss": 0.195, "lr": 2.8142348764945325e-06, "epoch": 5.924434215573456, "percentage": 84.63, "elapsed_time": "1 day, 23:41:36", "remaining_time": "8:39:43"}
1546
+ {"current_steps": 7730, "total_steps": 9128, "loss": 0.1978, "lr": 2.7947057652886635e-06, "epoch": 5.928270042194093, "percentage": 84.68, "elapsed_time": "1 day, 23:43:21", "remaining_time": "8:37:50"}
1547
+ {"current_steps": 7735, "total_steps": 9128, "loss": 0.1922, "lr": 2.775239559288996e-06, "epoch": 5.9321058688147295, "percentage": 84.74, "elapsed_time": "1 day, 23:45:10", "remaining_time": "8:35:59"}
1548
+ {"current_steps": 7740, "total_steps": 9128, "loss": 0.1835, "lr": 2.7558363296669786e-06, "epoch": 5.935941695435366, "percentage": 84.79, "elapsed_time": "1 day, 23:46:54", "remaining_time": "8:34:07"}
1549
+ {"current_steps": 7745, "total_steps": 9128, "loss": 0.1933, "lr": 2.736496147363792e-06, "epoch": 5.939777522056003, "percentage": 84.85, "elapsed_time": "1 day, 23:48:37", "remaining_time": "8:32:14"}
1550
+ {"current_steps": 7750, "total_steps": 9128, "loss": 0.1919, "lr": 2.717219083090139e-06, "epoch": 5.94361334867664, "percentage": 84.9, "elapsed_time": "1 day, 23:50:17", "remaining_time": "8:30:21"}
1551
+ {"current_steps": 7755, "total_steps": 9128, "loss": 0.1834, "lr": 2.6980052073259313e-06, "epoch": 5.947449175297277, "percentage": 84.96, "elapsed_time": "1 day, 23:51:58", "remaining_time": "8:28:28"}
1552
+ {"current_steps": 7760, "total_steps": 9128, "loss": 0.1827, "lr": 2.6788545903200545e-06, "epoch": 5.951285001917913, "percentage": 85.01, "elapsed_time": "1 day, 23:53:40", "remaining_time": "8:26:35"}
1553
+ {"current_steps": 7765, "total_steps": 9128, "loss": 0.1866, "lr": 2.6597673020901193e-06, "epoch": 5.95512082853855, "percentage": 85.07, "elapsed_time": "1 day, 23:55:17", "remaining_time": "8:24:42"}
1554
+ {"current_steps": 7605, "total_steps": 9128, "loss": 0.1957, "lr": 3.3016160465083293e-06, "epoch": 5.832374376678175, "percentage": 83.32, "elapsed_time": "0:01:52", "remaining_time": "0:00:22"}
1555
+ {"current_steps": 7610, "total_steps": 9128, "loss": 0.1879, "lr": 3.280599155807229e-06, "epoch": 5.836210203298811, "percentage": 83.37, "elapsed_time": "0:03:38", "remaining_time": "0:00:43"}
1556
+ {"current_steps": 7615, "total_steps": 9128, "loss": 0.1798, "lr": 3.2596433938112495e-06, "epoch": 5.840046029919447, "percentage": 83.42, "elapsed_time": "0:05:24", "remaining_time": "0:01:04"}
1557
+ {"current_steps": 7620, "total_steps": 9128, "loss": 0.1961, "lr": 3.238748837137866e-06, "epoch": 5.843881856540085, "percentage": 83.48, "elapsed_time": "0:07:02", "remaining_time": "0:01:23"}
1558
+ {"current_steps": 7625, "total_steps": 9128, "loss": 0.1819, "lr": 3.217915562180802e-06, "epoch": 5.847717683160721, "percentage": 83.53, "elapsed_time": "0:08:44", "remaining_time": "0:01:43"}
1559
+ {"current_steps": 7630, "total_steps": 9128, "loss": 0.1928, "lr": 3.1971436451097302e-06, "epoch": 5.851553509781358, "percentage": 83.59, "elapsed_time": "0:10:28", "remaining_time": "0:02:03"}
1560
+ {"current_steps": 7635, "total_steps": 9128, "loss": 0.1977, "lr": 3.1764331618699673e-06, "epoch": 5.855389336401995, "percentage": 83.64, "elapsed_time": "0:12:09", "remaining_time": "0:02:22"}
1561
+ {"current_steps": 7640, "total_steps": 9128, "loss": 0.1957, "lr": 3.155784188182229e-06, "epoch": 5.859225163022631, "percentage": 83.7, "elapsed_time": "0:13:51", "remaining_time": "0:02:41"}
1562
+ {"current_steps": 7645, "total_steps": 9128, "loss": 0.2079, "lr": 3.1351967995423594e-06, "epoch": 5.863060989643268, "percentage": 83.75, "elapsed_time": "0:15:30", "remaining_time": "0:03:00"}
1563
+ {"current_steps": 7650, "total_steps": 9128, "loss": 0.1901, "lr": 3.114671071221005e-06, "epoch": 5.866896816263905, "percentage": 83.81, "elapsed_time": "0:17:07", "remaining_time": "0:03:18"}
1564
+ {"current_steps": 7655, "total_steps": 9128, "loss": 0.2057, "lr": 3.094207078263405e-06, "epoch": 5.870732642884541, "percentage": 83.86, "elapsed_time": "0:18:54", "remaining_time": "0:03:38"}
1565
+ {"current_steps": 7660, "total_steps": 9128, "loss": 0.2007, "lr": 3.073804895489061e-06, "epoch": 5.874568469505179, "percentage": 83.92, "elapsed_time": "0:20:37", "remaining_time": "0:03:57"}
1566
+ {"current_steps": 7665, "total_steps": 9128, "loss": 0.1972, "lr": 3.0534645974914933e-06, "epoch": 5.878404296125815, "percentage": 83.97, "elapsed_time": "0:22:17", "remaining_time": "0:04:15"}
1567
+ {"current_steps": 7670, "total_steps": 9128, "loss": 0.2063, "lr": 3.0331862586379813e-06, "epoch": 5.882240122746452, "percentage": 84.03, "elapsed_time": "0:24:06", "remaining_time": "0:04:34"}
1568
+ {"current_steps": 7675, "total_steps": 9128, "loss": 0.1943, "lr": 3.0129699530692335e-06, "epoch": 5.886075949367089, "percentage": 84.08, "elapsed_time": "0:25:46", "remaining_time": "0:04:52"}
1569
+ {"current_steps": 7680, "total_steps": 9128, "loss": 0.197, "lr": 2.992815754699194e-06, "epoch": 5.889911775987725, "percentage": 84.14, "elapsed_time": "0:27:22", "remaining_time": "0:05:09"}
1570
+ {"current_steps": 7685, "total_steps": 9128, "loss": 0.2011, "lr": 2.9727237372147177e-06, "epoch": 5.893747602608362, "percentage": 84.19, "elapsed_time": "0:29:02", "remaining_time": "0:05:27"}
1571
+ {"current_steps": 7690, "total_steps": 9128, "loss": 0.1893, "lr": 2.952693974075298e-06, "epoch": 5.897583429228999, "percentage": 84.25, "elapsed_time": "0:30:44", "remaining_time": "0:05:44"}
1572
+ {"current_steps": 7695, "total_steps": 9128, "loss": 0.185, "lr": 2.932726538512851e-06, "epoch": 5.9014192558496354, "percentage": 84.3, "elapsed_time": "0:32:32", "remaining_time": "0:06:03"}
1573
+ {"current_steps": 7700, "total_steps": 9128, "loss": 0.1942, "lr": 2.9128215035313976e-06, "epoch": 5.905255082470273, "percentage": 84.36, "elapsed_time": "0:34:17", "remaining_time": "0:06:21"}
1574
+ {"current_steps": 7705, "total_steps": 9128, "loss": 0.1895, "lr": 2.8929789419067964e-06, "epoch": 5.909090909090909, "percentage": 84.41, "elapsed_time": "0:36:01", "remaining_time": "0:06:39"}
1575
+ {"current_steps": 7710, "total_steps": 9128, "loss": 0.2028, "lr": 2.8731989261865247e-06, "epoch": 5.912926735711546, "percentage": 84.47, "elapsed_time": "0:37:38", "remaining_time": "0:06:55"}
1576
+ {"current_steps": 7715, "total_steps": 9128, "loss": 0.194, "lr": 2.8534815286893614e-06, "epoch": 5.916762562332183, "percentage": 84.52, "elapsed_time": "0:39:19", "remaining_time": "0:07:12"}
1577
+ {"current_steps": 7720, "total_steps": 9128, "loss": 0.1978, "lr": 2.83382682150515e-06, "epoch": 5.920598388952819, "percentage": 84.57, "elapsed_time": "0:41:01", "remaining_time": "0:07:28"}
1578
+ {"current_steps": 7725, "total_steps": 9128, "loss": 0.1948, "lr": 2.8142348764945325e-06, "epoch": 5.924434215573456, "percentage": 84.63, "elapsed_time": "0:42:37", "remaining_time": "0:07:44"}
1579
+ {"current_steps": 7730, "total_steps": 9128, "loss": 0.1977, "lr": 2.7947057652886635e-06, "epoch": 5.928270042194093, "percentage": 84.68, "elapsed_time": "0:44:24", "remaining_time": "0:08:01"}
1580
+ {"current_steps": 7735, "total_steps": 9128, "loss": 0.1921, "lr": 2.775239559288996e-06, "epoch": 5.9321058688147295, "percentage": 84.74, "elapsed_time": "0:46:15", "remaining_time": "0:08:19"}
1581
+ {"current_steps": 7740, "total_steps": 9128, "loss": 0.1835, "lr": 2.7558363296669786e-06, "epoch": 5.935941695435366, "percentage": 84.79, "elapsed_time": "0:48:00", "remaining_time": "0:08:36"}
1582
+ {"current_steps": 7745, "total_steps": 9128, "loss": 0.1933, "lr": 2.736496147363792e-06, "epoch": 5.939777522056003, "percentage": 84.85, "elapsed_time": "0:49:45", "remaining_time": "0:08:53"}
1583
+ {"current_steps": 7750, "total_steps": 9128, "loss": 0.1918, "lr": 2.717219083090139e-06, "epoch": 5.94361334867664, "percentage": 84.9, "elapsed_time": "0:51:26", "remaining_time": "0:09:08"}
1584
+ {"current_steps": 7755, "total_steps": 9128, "loss": 0.1835, "lr": 2.6980052073259313e-06, "epoch": 5.947449175297277, "percentage": 84.96, "elapsed_time": "0:53:07", "remaining_time": "0:09:24"}
1585
+ {"current_steps": 7760, "total_steps": 9128, "loss": 0.1827, "lr": 2.6788545903200545e-06, "epoch": 5.951285001917913, "percentage": 85.01, "elapsed_time": "0:54:51", "remaining_time": "0:09:40"}
1586
+ {"current_steps": 7765, "total_steps": 9128, "loss": 0.1867, "lr": 2.6597673020901193e-06, "epoch": 5.95512082853855, "percentage": 85.07, "elapsed_time": "0:56:31", "remaining_time": "0:09:55"}
1587
+ {"current_steps": 7770, "total_steps": 9128, "loss": 0.1838, "lr": 2.6407434124221887e-06, "epoch": 5.958956655159187, "percentage": 85.12, "elapsed_time": "0:58:13", "remaining_time": "0:10:10"}
1588
+ {"current_steps": 7775, "total_steps": 9128, "loss": 0.2048, "lr": 2.621782990870536e-06, "epoch": 5.9627924817798235, "percentage": 85.18, "elapsed_time": "0:59:54", "remaining_time": "0:10:25"}
1589
+ {"current_steps": 7780, "total_steps": 9128, "loss": 0.1913, "lr": 2.6028861067573807e-06, "epoch": 5.966628308400461, "percentage": 85.23, "elapsed_time": "1:01:29", "remaining_time": "0:10:39"}
1590
+ {"current_steps": 7785, "total_steps": 9128, "loss": 0.1882, "lr": 2.584052829172645e-06, "epoch": 5.970464135021097, "percentage": 85.29, "elapsed_time": "1:03:14", "remaining_time": "0:10:54"}
1591
+ {"current_steps": 7790, "total_steps": 9128, "loss": 0.1808, "lr": 2.5652832269736916e-06, "epoch": 5.974299961641734, "percentage": 85.34, "elapsed_time": "1:04:51", "remaining_time": "0:11:08"}
1592
+ {"current_steps": 7795, "total_steps": 9128, "loss": 0.1899, "lr": 2.5465773687850792e-06, "epoch": 5.978135788262371, "percentage": 85.4, "elapsed_time": "1:06:30", "remaining_time": "0:11:22"}
1593
+ {"current_steps": 7800, "total_steps": 9128, "loss": 0.1896, "lr": 2.527935322998305e-06, "epoch": 5.981971614883007, "percentage": 85.45, "elapsed_time": "1:08:11", "remaining_time": "0:11:36"}
1594
+ {"current_steps": 7805, "total_steps": 9128, "loss": 0.1983, "lr": 2.5093571577715593e-06, "epoch": 5.985807441503644, "percentage": 85.51, "elapsed_time": "1:11:01", "remaining_time": "0:12:02"}
1595
+ {"current_steps": 7810, "total_steps": 9128, "loss": 0.1936, "lr": 2.4908429410294786e-06, "epoch": 5.989643268124281, "percentage": 85.56, "elapsed_time": "1:12:43", "remaining_time": "0:12:16"}
1596
+ {"current_steps": 7815, "total_steps": 9128, "loss": 0.1925, "lr": 2.4723927404628922e-06, "epoch": 5.9934790947449175, "percentage": 85.62, "elapsed_time": "1:14:23", "remaining_time": "0:12:29"}
1597
+ {"current_steps": 7820, "total_steps": 9128, "loss": 0.201, "lr": 2.4540066235285733e-06, "epoch": 5.997314921365554, "percentage": 85.67, "elapsed_time": "1:16:04", "remaining_time": "0:12:43"}
1598
+ {"current_steps": 7825, "total_steps": 9128, "loss": 0.2057, "lr": 2.4356846574489977e-06, "epoch": 6.001534330648255, "percentage": 85.73, "elapsed_time": "1:18:44", "remaining_time": "0:13:06"}
1599
+ {"current_steps": 7830, "total_steps": 9128, "loss": 0.1814, "lr": 2.417426909212095e-06, "epoch": 6.005370157268891, "percentage": 85.78, "elapsed_time": "1:21:38", "remaining_time": "0:13:31"}
1600
+ {"current_steps": 7835, "total_steps": 9128, "loss": 0.1646, "lr": 2.39923344557101e-06, "epoch": 6.009205983889528, "percentage": 85.83, "elapsed_time": "1:24:23", "remaining_time": "0:13:55"}
1601
+ {"current_steps": 7840, "total_steps": 9128, "loss": 0.1722, "lr": 2.3811043330438444e-06, "epoch": 6.013041810510165, "percentage": 85.89, "elapsed_time": "1:27:25", "remaining_time": "0:14:21"}
1602
+ {"current_steps": 7845, "total_steps": 9128, "loss": 0.1655, "lr": 2.363039637913427e-06, "epoch": 6.0168776371308015, "percentage": 85.94, "elapsed_time": "1:30:29", "remaining_time": "0:14:47"}
1603
+ {"current_steps": 7850, "total_steps": 9128, "loss": 0.168, "lr": 2.345039426227067e-06, "epoch": 6.020713463751439, "percentage": 86.0, "elapsed_time": "1:33:35", "remaining_time": "0:15:14"}
1604
+ {"current_steps": 7855, "total_steps": 9128, "loss": 0.1821, "lr": 2.32710376379631e-06, "epoch": 6.024549290372075, "percentage": 86.05, "elapsed_time": "1:36:35", "remaining_time": "0:15:39"}
1605
+ {"current_steps": 7860, "total_steps": 9128, "loss": 0.1737, "lr": 2.309232716196701e-06, "epoch": 6.028385116992712, "percentage": 86.11, "elapsed_time": "1:39:34", "remaining_time": "0:16:03"}
1606
+ {"current_steps": 7865, "total_steps": 9128, "loss": 0.1643, "lr": 2.2914263487675402e-06, "epoch": 6.032220943613349, "percentage": 86.16, "elapsed_time": "1:42:24", "remaining_time": "0:16:26"}
1607
+ {"current_steps": 7870, "total_steps": 9128, "loss": 0.1484, "lr": 2.273684726611662e-06, "epoch": 6.036056770233985, "percentage": 86.22, "elapsed_time": "1:44:55", "remaining_time": "0:16:46"}
1608
+ {"current_steps": 7875, "total_steps": 9128, "loss": 0.1632, "lr": 2.25600791459516e-06, "epoch": 6.039892596854622, "percentage": 86.27, "elapsed_time": "1:47:52", "remaining_time": "0:17:09"}
1609
+ {"current_steps": 7880, "total_steps": 9128, "loss": 0.1582, "lr": 2.2383959773471765e-06, "epoch": 6.043728423475259, "percentage": 86.33, "elapsed_time": "1:50:45", "remaining_time": "0:17:32"}
1610
+ {"current_steps": 7885, "total_steps": 9128, "loss": 0.167, "lr": 2.220848979259682e-06, "epoch": 6.0475642500958955, "percentage": 86.38, "elapsed_time": "1:53:32", "remaining_time": "0:17:53"}
1611
+ {"current_steps": 7890, "total_steps": 9128, "loss": 0.1583, "lr": 2.2033669844871897e-06, "epoch": 6.051400076716533, "percentage": 86.44, "elapsed_time": "1:56:21", "remaining_time": "0:18:15"}
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a48d294a24f60a5e51970dc9b80b77a14efacf345a9a209002ff221637fc730f
3
- size 8529
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d541538bded6dcb9daa86b049742682f74610654e13a9df70777552de2e3e73
3
+ size 8657