ryanmarten commited on
Commit
0a717c1
·
verified ·
1 Parent(s): ae45db5

Training in progress, epoch 2

Browse files
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8c5ea0452a712a9573209f711abe0c32f612258f0c1aada898967953834241f1
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:853f61fc073e49c4c073c1b9e87d6340ba590bd5b5feddf32ed45ec61a944c37
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3821ff2311e5726f08585ec497859aa4bcd6cc145d4fa36005ada8da2534e1c2
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:449169069bb788ad2cbb9d324f439e79020566dea446183e7a88be7e292ff4bd
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ace206dcd8b8fa3b55a0f48f96a33a3dae36964b339cfeb2733015ee8e1678d7
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:baa1ca31da61db8871b04506856ce0b1165a8888c509e621a8b108ee51929924
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dbda001c85a29bd1c17927101ca90553ddbd51d26ff7e00b809a3367a1fbd2ca
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6f647a11e02f4dd03cb611b546715122cde930b6c78df28fa1f8f54bd5efee1
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -1396,3 +1396,183 @@
1396
  {"current_steps": 653, "total_steps": 1230, "loss": 0.2469, "lr": 2.133284032321232e-05, "epoch": 2.6481012658227847, "percentage": 53.09, "elapsed_time": "15:22:50", "remaining_time": "13:35:25"}
1397
  {"current_steps": 744, "total_steps": 1230, "loss": 0.1671, "lr": 1.619217781670663e-05, "epoch": 3.0182278481012657, "percentage": 60.49, "elapsed_time": "17:34:06", "remaining_time": "11:28:34"}
1398
  {"current_steps": 654, "total_steps": 1230, "loss": 0.249, "lr": 2.1276202534492566e-05, "epoch": 2.6521518987341772, "percentage": 53.17, "elapsed_time": "15:24:14", "remaining_time": "13:34:00"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1396
  {"current_steps": 653, "total_steps": 1230, "loss": 0.2469, "lr": 2.133284032321232e-05, "epoch": 2.6481012658227847, "percentage": 53.09, "elapsed_time": "15:22:50", "remaining_time": "13:35:25"}
1397
  {"current_steps": 744, "total_steps": 1230, "loss": 0.1671, "lr": 1.619217781670663e-05, "epoch": 3.0182278481012657, "percentage": 60.49, "elapsed_time": "17:34:06", "remaining_time": "11:28:34"}
1398
  {"current_steps": 654, "total_steps": 1230, "loss": 0.249, "lr": 2.1276202534492566e-05, "epoch": 2.6521518987341772, "percentage": 53.17, "elapsed_time": "15:24:14", "remaining_time": "13:34:00"}
1399
+ {"current_steps": 745, "total_steps": 1230, "loss": 0.1894, "lr": 1.6136472761995373e-05, "epoch": 3.022278481012658, "percentage": 60.57, "elapsed_time": "17:35:40", "remaining_time": "11:27:14"}
1400
+ {"current_steps": 655, "total_steps": 1230, "loss": 0.2593, "lr": 2.121955446741306e-05, "epoch": 2.6562025316455697, "percentage": 53.25, "elapsed_time": "15:25:42", "remaining_time": "13:32:38"}
1401
+ {"current_steps": 746, "total_steps": 1230, "loss": 0.16, "lr": 1.608079882360134e-05, "epoch": 3.0263291139240507, "percentage": 60.65, "elapsed_time": "17:37:02", "remaining_time": "11:25:48"}
1402
+ {"current_steps": 656, "total_steps": 1230, "loss": 0.2111, "lr": 2.1162896578209517e-05, "epoch": 2.660253164556962, "percentage": 53.33, "elapsed_time": "15:26:56", "remaining_time": "13:31:04"}
1403
+ {"current_steps": 747, "total_steps": 1230, "loss": 0.1759, "lr": 1.60251564499148e-05, "epoch": 3.030379746835443, "percentage": 60.73, "elapsed_time": "17:38:21", "remaining_time": "11:24:19"}
1404
+ {"current_steps": 748, "total_steps": 1230, "loss": 0.1707, "lr": 1.596954608907176e-05, "epoch": 3.0344303797468353, "percentage": 60.81, "elapsed_time": "17:39:36", "remaining_time": "11:22:47"}
1405
+ {"current_steps": 657, "total_steps": 1230, "loss": 0.2574, "lr": 2.1106229323196813e-05, "epoch": 2.6643037974683543, "percentage": 53.41, "elapsed_time": "15:28:32", "remaining_time": "13:29:49"}
1406
+ {"current_steps": 749, "total_steps": 1230, "loss": 0.177, "lr": 1.591396818895043e-05, "epoch": 3.038481012658228, "percentage": 60.89, "elapsed_time": "17:40:57", "remaining_time": "11:21:20"}
1407
+ {"current_steps": 658, "total_steps": 1230, "loss": 0.2691, "lr": 2.1049553158765214e-05, "epoch": 2.668354430379747, "percentage": 53.5, "elapsed_time": "15:30:03", "remaining_time": "13:28:29"}
1408
+ {"current_steps": 659, "total_steps": 1230, "loss": 0.2424, "lr": 2.0992868541376764e-05, "epoch": 2.6724050632911394, "percentage": 53.58, "elapsed_time": "15:31:21", "remaining_time": "13:26:58"}
1409
+ {"current_steps": 750, "total_steps": 1230, "loss": 0.1943, "lr": 1.585842319716759e-05, "epoch": 3.0425316455696203, "percentage": 60.98, "elapsed_time": "17:42:31", "remaining_time": "11:20:00"}
1410
+ {"current_steps": 660, "total_steps": 1230, "loss": 0.2402, "lr": 2.093617592756158e-05, "epoch": 2.676455696202532, "percentage": 53.66, "elapsed_time": "15:32:42", "remaining_time": "13:25:31"}
1411
+ {"current_steps": 751, "total_steps": 1230, "loss": 0.1915, "lr": 1.5802911561074944e-05, "epoch": 3.046582278481013, "percentage": 61.06, "elapsed_time": "17:43:53", "remaining_time": "11:18:33"}
1412
+ {"current_steps": 661, "total_steps": 1230, "loss": 0.2543, "lr": 2.0879475773914167e-05, "epoch": 2.680506329113924, "percentage": 53.74, "elapsed_time": "15:34:02", "remaining_time": "13:24:01"}
1413
+ {"current_steps": 752, "total_steps": 1230, "loss": 0.1753, "lr": 1.5747433727755595e-05, "epoch": 3.050632911392405, "percentage": 61.14, "elapsed_time": "17:45:20", "remaining_time": "11:17:10"}
1414
+ {"current_steps": 662, "total_steps": 1230, "loss": 0.2383, "lr": 2.082276853708978e-05, "epoch": 2.6845569620253165, "percentage": 53.82, "elapsed_time": "15:35:24", "remaining_time": "13:22:35"}
1415
+ {"current_steps": 753, "total_steps": 1230, "loss": 0.1884, "lr": 1.5691990144020376e-05, "epoch": 3.0546835443037974, "percentage": 61.22, "elapsed_time": "17:46:36", "remaining_time": "11:15:39"}
1416
+ {"current_steps": 754, "total_steps": 1230, "loss": 0.1475, "lr": 1.5636581256404297e-05, "epoch": 3.05873417721519, "percentage": 61.3, "elapsed_time": "17:47:57", "remaining_time": "11:14:11"}
1417
+ {"current_steps": 663, "total_steps": 1230, "loss": 0.2519, "lr": 2.076605467380071e-05, "epoch": 2.688607594936709, "percentage": 53.9, "elapsed_time": "15:36:58", "remaining_time": "13:21:18"}
1418
+ {"current_steps": 664, "total_steps": 1230, "loss": 0.2426, "lr": 2.0709334640812613e-05, "epoch": 2.692658227848101, "percentage": 53.98, "elapsed_time": "15:38:11", "remaining_time": "13:19:43"}
1419
+ {"current_steps": 755, "total_steps": 1230, "loss": 0.1779, "lr": 1.558120751116291e-05, "epoch": 3.0627848101265824, "percentage": 61.38, "elapsed_time": "17:49:21", "remaining_time": "11:12:46"}
1420
+ {"current_steps": 756, "total_steps": 1230, "loss": 0.1596, "lr": 1.552586935426876e-05, "epoch": 3.0668354430379745, "percentage": 61.46, "elapsed_time": "17:50:32", "remaining_time": "11:11:13"}
1421
+ {"current_steps": 665, "total_steps": 1230, "loss": 0.2636, "lr": 2.0652608894940824e-05, "epoch": 2.6967088607594936, "percentage": 54.07, "elapsed_time": "15:39:44", "remaining_time": "13:18:25"}
1422
+ {"current_steps": 757, "total_steps": 1230, "loss": 0.17, "lr": 1.547056723140774e-05, "epoch": 3.070886075949367, "percentage": 61.54, "elapsed_time": "17:52:05", "remaining_time": "11:09:53"}
1423
+ {"current_steps": 666, "total_steps": 1230, "loss": 0.2389, "lr": 2.0595877893046722e-05, "epoch": 2.700759493670886, "percentage": 54.15, "elapsed_time": "15:41:12", "remaining_time": "13:17:03"}
1424
+ {"current_steps": 758, "total_steps": 1230, "loss": 0.172, "lr": 1.5415301587975565e-05, "epoch": 3.0749367088607595, "percentage": 61.63, "elapsed_time": "17:53:20", "remaining_time": "11:08:21"}
1425
+ {"current_steps": 667, "total_steps": 1230, "loss": 0.2557, "lr": 2.0539142092033985e-05, "epoch": 2.7048101265822786, "percentage": 54.23, "elapsed_time": "15:42:34", "remaining_time": "13:15:36"}
1426
+ {"current_steps": 759, "total_steps": 1230, "loss": 0.1731, "lr": 1.536007286907411e-05, "epoch": 3.078987341772152, "percentage": 61.71, "elapsed_time": "17:54:35", "remaining_time": "11:06:50"}
1427
+ {"current_steps": 668, "total_steps": 1230, "loss": 0.2573, "lr": 2.048240194884496e-05, "epoch": 2.708860759493671, "percentage": 54.31, "elapsed_time": "15:43:51", "remaining_time": "13:14:05"}
1428
+ {"current_steps": 760, "total_steps": 1230, "loss": 0.158, "lr": 1.5304881519507896e-05, "epoch": 3.083037974683544, "percentage": 61.79, "elapsed_time": "17:55:38", "remaining_time": "11:05:11"}
1429
+ {"current_steps": 669, "total_steps": 1230, "loss": 0.2547, "lr": 2.042565792045695e-05, "epoch": 2.712911392405063, "percentage": 54.39, "elapsed_time": "15:45:27", "remaining_time": "13:12:50"}
1430
+ {"current_steps": 761, "total_steps": 1230, "loss": 0.155, "lr": 1.5249727983780453e-05, "epoch": 3.0870886075949366, "percentage": 61.87, "elapsed_time": "17:56:49", "remaining_time": "11:03:38"}
1431
+ {"current_steps": 670, "total_steps": 1230, "loss": 0.2727, "lr": 2.036891046387857e-05, "epoch": 2.7169620253164557, "percentage": 54.47, "elapsed_time": "15:46:56", "remaining_time": "13:11:28"}
1432
+ {"current_steps": 762, "total_steps": 1230, "loss": 0.1729, "lr": 1.5194612706090786e-05, "epoch": 3.091139240506329, "percentage": 61.95, "elapsed_time": "17:58:07", "remaining_time": "11:02:09"}
1433
+ {"current_steps": 763, "total_steps": 1230, "loss": 0.1565, "lr": 1.5139536130329771e-05, "epoch": 3.0951898734177217, "percentage": 62.03, "elapsed_time": "17:59:20", "remaining_time": "11:00:37"}
1434
+ {"current_steps": 671, "total_steps": 1230, "loss": 0.2469, "lr": 2.0312160036146036e-05, "epoch": 2.721012658227848, "percentage": 54.55, "elapsed_time": "15:48:18", "remaining_time": "13:10:00"}
1435
+ {"current_steps": 764, "total_steps": 1230, "loss": 0.1713, "lr": 1.508449870007656e-05, "epoch": 3.0992405063291137, "percentage": 62.11, "elapsed_time": "18:00:38", "remaining_time": "10:59:08"}
1436
+ {"current_steps": 672, "total_steps": 1230, "loss": 0.2458, "lr": 2.025540709431948e-05, "epoch": 2.7250632911392403, "percentage": 54.63, "elapsed_time": "15:49:33", "remaining_time": "13:08:28"}
1437
+ {"current_steps": 765, "total_steps": 1230, "loss": 0.1746, "lr": 1.5029500858595056e-05, "epoch": 3.1032911392405063, "percentage": 62.2, "elapsed_time": "18:02:01", "remaining_time": "10:57:42"}
1438
+ {"current_steps": 673, "total_steps": 1230, "loss": 0.265, "lr": 2.0198652095479298e-05, "epoch": 2.729113924050633, "percentage": 54.72, "elapsed_time": "15:50:56", "remaining_time": "13:07:02"}
1439
+ {"current_steps": 766, "total_steps": 1230, "loss": 0.179, "lr": 1.4974543048830328e-05, "epoch": 3.1073417721518988, "percentage": 62.28, "elapsed_time": "18:03:22", "remaining_time": "10:56:15"}
1440
+ {"current_steps": 674, "total_steps": 1230, "loss": 0.2401, "lr": 2.014189549672245e-05, "epoch": 2.7331645569620253, "percentage": 54.8, "elapsed_time": "15:52:23", "remaining_time": "13:05:39"}
1441
+ {"current_steps": 675, "total_steps": 1230, "loss": 0.2498, "lr": 2.0085137755158776e-05, "epoch": 2.737215189873418, "percentage": 54.88, "elapsed_time": "15:53:30", "remaining_time": "13:03:59"}
1442
+ {"current_steps": 767, "total_steps": 1230, "loss": 0.1755, "lr": 1.4919625713405e-05, "epoch": 3.1113924050632913, "percentage": 62.36, "elapsed_time": "18:05:01", "remaining_time": "10:54:58"}
1443
+ {"current_steps": 676, "total_steps": 1230, "loss": 0.2421, "lr": 2.0028379327907327e-05, "epoch": 2.7412658227848103, "percentage": 54.96, "elapsed_time": "15:54:41", "remaining_time": "13:02:23"}
1444
+ {"current_steps": 768, "total_steps": 1230, "loss": 0.1776, "lr": 1.4864749294615756e-05, "epoch": 3.1154430379746834, "percentage": 62.44, "elapsed_time": "18:06:18", "remaining_time": "10:53:28"}
1445
+ {"current_steps": 677, "total_steps": 1230, "loss": 0.2566, "lr": 1.9971620672092676e-05, "epoch": 2.7453164556962024, "percentage": 55.04, "elapsed_time": "15:56:04", "remaining_time": "13:00:57"}
1446
+ {"current_steps": 769, "total_steps": 1230, "loss": 0.1631, "lr": 1.4809914234429716e-05, "epoch": 3.119493670886076, "percentage": 62.52, "elapsed_time": "18:07:34", "remaining_time": "10:51:58"}
1447
+ {"current_steps": 678, "total_steps": 1230, "loss": 0.2336, "lr": 1.991486224484123e-05, "epoch": 2.749367088607595, "percentage": 55.12, "elapsed_time": "15:57:17", "remaining_time": "12:59:23"}
1448
+ {"current_steps": 770, "total_steps": 1230, "loss": 0.1803, "lr": 1.4755120974480923e-05, "epoch": 3.1235443037974684, "percentage": 62.6, "elapsed_time": "18:08:58", "remaining_time": "10:50:33"}
1449
+ {"current_steps": 679, "total_steps": 1230, "loss": 0.2583, "lr": 1.985810450327756e-05, "epoch": 2.7534177215189874, "percentage": 55.2, "elapsed_time": "15:58:38", "remaining_time": "12:57:55"}
1450
+ {"current_steps": 771, "total_steps": 1230, "loss": 0.162, "lr": 1.4700369956066771e-05, "epoch": 3.127594936708861, "percentage": 62.68, "elapsed_time": "18:10:19", "remaining_time": "10:49:06"}
1451
+ {"current_steps": 680, "total_steps": 1230, "loss": 0.2513, "lr": 1.9801347904520706e-05, "epoch": 2.7574683544303795, "percentage": 55.28, "elapsed_time": "16:00:16", "remaining_time": "12:56:41"}
1452
+ {"current_steps": 772, "total_steps": 1230, "loss": 0.1961, "lr": 1.4645661620144413e-05, "epoch": 3.131645569620253, "percentage": 62.76, "elapsed_time": "18:11:57", "remaining_time": "10:47:49"}
1453
+ {"current_steps": 681, "total_steps": 1230, "loss": 0.2658, "lr": 1.974459290568053e-05, "epoch": 2.761518987341772, "percentage": 55.37, "elapsed_time": "16:01:48", "remaining_time": "12:55:22"}
1454
+ {"current_steps": 773, "total_steps": 1230, "loss": 0.1704, "lr": 1.4590996407327284e-05, "epoch": 3.1356962025316455, "percentage": 62.85, "elapsed_time": "18:13:14", "remaining_time": "10:46:19"}
1455
+ {"current_steps": 682, "total_steps": 1230, "loss": 0.2478, "lr": 1.968783996385397e-05, "epoch": 2.7655696202531646, "percentage": 55.45, "elapsed_time": "16:03:12", "remaining_time": "12:53:57"}
1456
+ {"current_steps": 774, "total_steps": 1230, "loss": 0.1653, "lr": 1.4536374757881487e-05, "epoch": 3.139746835443038, "percentage": 62.93, "elapsed_time": "18:14:26", "remaining_time": "10:44:47"}
1457
+ {"current_steps": 683, "total_steps": 1230, "loss": 0.2448, "lr": 1.963108953612143e-05, "epoch": 2.769620253164557, "percentage": 55.53, "elapsed_time": "16:04:37", "remaining_time": "12:52:32"}
1458
+ {"current_steps": 775, "total_steps": 1230, "loss": 0.1811, "lr": 1.4481797111722271e-05, "epoch": 3.1437974683544305, "percentage": 63.01, "elapsed_time": "18:15:57", "remaining_time": "10:43:26"}
1459
+ {"current_steps": 684, "total_steps": 1230, "loss": 0.236, "lr": 1.9574342079543056e-05, "epoch": 2.7736708860759496, "percentage": 55.61, "elapsed_time": "16:05:59", "remaining_time": "12:51:05"}
1460
+ {"current_steps": 776, "total_steps": 1230, "loss": 0.1783, "lr": 1.4427263908410507e-05, "epoch": 3.1478481012658226, "percentage": 63.09, "elapsed_time": "18:17:11", "remaining_time": "10:41:54"}
1461
+ {"current_steps": 685, "total_steps": 1230, "loss": 0.2324, "lr": 1.9517598051155046e-05, "epoch": 2.7777215189873417, "percentage": 55.69, "elapsed_time": "16:07:05", "remaining_time": "12:49:26"}
1462
+ {"current_steps": 777, "total_steps": 1230, "loss": 0.1681, "lr": 1.4372775587149108e-05, "epoch": 3.151898734177215, "percentage": 63.17, "elapsed_time": "18:18:35", "remaining_time": "10:40:29"}
1463
+ {"current_steps": 686, "total_steps": 1230, "loss": 0.252, "lr": 1.9460857907966025e-05, "epoch": 2.781772151898734, "percentage": 55.77, "elapsed_time": "16:08:27", "remaining_time": "12:47:59"}
1464
+ {"current_steps": 778, "total_steps": 1230, "loss": 0.1982, "lr": 1.4318332586779522e-05, "epoch": 3.1559493670886076, "percentage": 63.25, "elapsed_time": "18:20:08", "remaining_time": "10:39:09"}
1465
+ {"current_steps": 687, "total_steps": 1230, "loss": 0.2569, "lr": 1.9404122106953285e-05, "epoch": 2.7858227848101267, "percentage": 55.85, "elapsed_time": "16:10:06", "remaining_time": "12:46:45"}
1466
+ {"current_steps": 779, "total_steps": 1230, "loss": 0.174, "lr": 1.4263935345778202e-05, "epoch": 3.16, "percentage": 63.33, "elapsed_time": "18:21:34", "remaining_time": "10:37:45"}
1467
+ {"current_steps": 688, "total_steps": 1230, "loss": 0.2469, "lr": 1.9347391105059176e-05, "epoch": 2.7898734177215188, "percentage": 55.93, "elapsed_time": "16:11:31", "remaining_time": "12:45:21"}
1468
+ {"current_steps": 780, "total_steps": 1230, "loss": 0.1631, "lr": 1.420958430225303e-05, "epoch": 3.164050632911392, "percentage": 63.41, "elapsed_time": "18:22:48", "remaining_time": "10:36:13"}
1469
+ {"current_steps": 689, "total_steps": 1230, "loss": 0.278, "lr": 1.92906653591874e-05, "epoch": 2.7939240506329113, "percentage": 56.02, "elapsed_time": "16:13:04", "remaining_time": "12:44:03"}
1470
+ {"current_steps": 781, "total_steps": 1230, "loss": 0.1737, "lr": 1.415527989393985e-05, "epoch": 3.1681012658227847, "percentage": 63.5, "elapsed_time": "18:24:14", "remaining_time": "10:34:49"}
1471
+ {"current_steps": 782, "total_steps": 1230, "loss": 0.1582, "lr": 1.410102255819891e-05, "epoch": 3.1721518987341772, "percentage": 63.58, "elapsed_time": "18:25:16", "remaining_time": "10:33:11"}
1472
+ {"current_steps": 690, "total_steps": 1230, "loss": 0.2506, "lr": 1.9233945326199295e-05, "epoch": 2.797974683544304, "percentage": 56.1, "elapsed_time": "16:14:33", "remaining_time": "12:42:41"}
1473
+ {"current_steps": 783, "total_steps": 1230, "loss": 0.188, "lr": 1.404681273201131e-05, "epoch": 3.1762025316455698, "percentage": 63.66, "elapsed_time": "18:26:37", "remaining_time": "10:31:45"}
1474
+ {"current_steps": 691, "total_steps": 1230, "loss": 0.2444, "lr": 1.917723146291022e-05, "epoch": 2.8020253164556963, "percentage": 56.18, "elapsed_time": "16:15:52", "remaining_time": "12:41:12"}
1475
+ {"current_steps": 784, "total_steps": 1230, "loss": 0.1796, "lr": 1.399265085197556e-05, "epoch": 3.180253164556962, "percentage": 63.74, "elapsed_time": "18:27:59", "remaining_time": "10:30:18"}
1476
+ {"current_steps": 692, "total_steps": 1230, "loss": 0.2474, "lr": 1.912052422608584e-05, "epoch": 2.806075949367089, "percentage": 56.26, "elapsed_time": "16:17:14", "remaining_time": "12:39:45"}
1477
+ {"current_steps": 785, "total_steps": 1230, "loss": 0.187, "lr": 1.393853735430398e-05, "epoch": 3.1843037974683543, "percentage": 63.82, "elapsed_time": "18:29:34", "remaining_time": "10:28:59"}
1478
+ {"current_steps": 693, "total_steps": 1230, "loss": 0.2451, "lr": 1.9063824072438428e-05, "epoch": 2.810126582278481, "percentage": 56.34, "elapsed_time": "16:18:44", "remaining_time": "12:38:24"}
1479
+ {"current_steps": 786, "total_steps": 1230, "loss": 0.1663, "lr": 1.3884472674819246e-05, "epoch": 3.188354430379747, "percentage": 63.9, "elapsed_time": "18:30:52", "remaining_time": "10:27:30"}
1480
+ {"current_steps": 694, "total_steps": 1230, "loss": 0.2388, "lr": 1.9007131458623246e-05, "epoch": 2.8141772151898734, "percentage": 56.42, "elapsed_time": "16:20:03", "remaining_time": "12:36:56"}
1481
+ {"current_steps": 787, "total_steps": 1230, "loss": 0.1688, "lr": 1.3830457248950864e-05, "epoch": 3.1924050632911394, "percentage": 63.98, "elapsed_time": "18:32:05", "remaining_time": "10:25:59"}
1482
+ {"current_steps": 695, "total_steps": 1230, "loss": 0.2633, "lr": 1.895044684123479e-05, "epoch": 2.818227848101266, "percentage": 56.5, "elapsed_time": "16:21:33", "remaining_time": "12:35:34"}
1483
+ {"current_steps": 788, "total_steps": 1230, "loss": 0.188, "lr": 1.377649151173163e-05, "epoch": 3.1964556962025314, "percentage": 64.07, "elapsed_time": "18:33:37", "remaining_time": "10:24:38"}
1484
+ {"current_steps": 696, "total_steps": 1230, "loss": 0.258, "lr": 1.8893770676803194e-05, "epoch": 2.822278481012658, "percentage": 56.59, "elapsed_time": "16:22:50", "remaining_time": "12:34:04"}
1485
+ {"current_steps": 789, "total_steps": 1230, "loss": 0.1932, "lr": 1.3722575897794181e-05, "epoch": 3.200506329113924, "percentage": 64.15, "elapsed_time": "18:35:13", "remaining_time": "10:23:20"}
1486
+ {"current_steps": 697, "total_steps": 1230, "loss": 0.2521, "lr": 1.8837103421790486e-05, "epoch": 2.8263291139240505, "percentage": 56.67, "elapsed_time": "16:24:16", "remaining_time": "12:32:41"}
1487
+ {"current_steps": 790, "total_steps": 1230, "loss": 0.1805, "lr": 1.3668710841367472e-05, "epoch": 3.2045569620253165, "percentage": 64.23, "elapsed_time": "18:36:47", "remaining_time": "10:22:00"}
1488
+ {"current_steps": 698, "total_steps": 1230, "loss": 0.2644, "lr": 1.8780445532586952e-05, "epoch": 2.830379746835443, "percentage": 56.75, "elapsed_time": "16:25:54", "remaining_time": "12:31:26"}
1489
+ {"current_steps": 791, "total_steps": 1230, "loss": 0.1611, "lr": 1.361489677627324e-05, "epoch": 3.208607594936709, "percentage": 64.31, "elapsed_time": "18:37:58", "remaining_time": "10:20:27"}
1490
+ {"current_steps": 699, "total_steps": 1230, "loss": 0.2659, "lr": 1.872379746550743e-05, "epoch": 2.8344303797468355, "percentage": 56.83, "elapsed_time": "16:27:19", "remaining_time": "12:30:01"}
1491
+ {"current_steps": 792, "total_steps": 1230, "loss": 0.1695, "lr": 1.3561134135922585e-05, "epoch": 3.212658227848101, "percentage": 64.39, "elapsed_time": "18:39:14", "remaining_time": "10:18:58"}
1492
+ {"current_steps": 700, "total_steps": 1230, "loss": 0.2285, "lr": 1.866715967678769e-05, "epoch": 2.838481012658228, "percentage": 56.91, "elapsed_time": "16:28:28", "remaining_time": "12:28:24"}
1493
+ {"current_steps": 793, "total_steps": 1230, "loss": 0.1856, "lr": 1.350742335331241e-05, "epoch": 3.2167088607594936, "percentage": 64.47, "elapsed_time": "18:40:39", "remaining_time": "10:17:34"}
1494
+ {"current_steps": 701, "total_steps": 1230, "loss": 0.2374, "lr": 1.861053262258067e-05, "epoch": 2.84253164556962, "percentage": 56.99, "elapsed_time": "16:29:42", "remaining_time": "12:26:51"}
1495
+ {"current_steps": 794, "total_steps": 1230, "loss": 0.1792, "lr": 1.345376486102198e-05, "epoch": 3.220759493670886, "percentage": 64.55, "elapsed_time": "18:41:53", "remaining_time": "10:16:02"}
1496
+ {"current_steps": 702, "total_steps": 1230, "loss": 0.2481, "lr": 1.8553916758952897e-05, "epoch": 2.8465822784810126, "percentage": 57.07, "elapsed_time": "16:31:16", "remaining_time": "12:25:34"}
1497
+ {"current_steps": 795, "total_steps": 1230, "loss": 0.1763, "lr": 1.3400159091209414e-05, "epoch": 3.2248101265822786, "percentage": 64.63, "elapsed_time": "18:43:12", "remaining_time": "10:14:34"}
1498
+ {"current_steps": 703, "total_steps": 1230, "loss": 0.2638, "lr": 1.8497312541880735e-05, "epoch": 2.850632911392405, "percentage": 57.15, "elapsed_time": "16:32:39", "remaining_time": "12:24:08"}
1499
+ {"current_steps": 796, "total_steps": 1230, "loss": 0.1785, "lr": 1.3346606475608216e-05, "epoch": 3.2288607594936707, "percentage": 64.72, "elapsed_time": "18:44:36", "remaining_time": "10:13:09"}
1500
+ {"current_steps": 704, "total_steps": 1230, "loss": 0.2269, "lr": 1.8440720427246786e-05, "epoch": 2.8546835443037972, "percentage": 57.24, "elapsed_time": "16:33:55", "remaining_time": "12:22:37"}
1501
+ {"current_steps": 797, "total_steps": 1230, "loss": 0.1692, "lr": 1.3293107445523781e-05, "epoch": 3.232911392405063, "percentage": 64.8, "elapsed_time": "18:45:50", "remaining_time": "10:11:39"}
1502
+ {"current_steps": 705, "total_steps": 1230, "loss": 0.229, "lr": 1.8384140870836157e-05, "epoch": 2.8587341772151897, "percentage": 57.32, "elapsed_time": "16:35:00", "remaining_time": "12:20:57"}
1503
+ {"current_steps": 798, "total_steps": 1230, "loss": 0.1655, "lr": 1.3239662431829949e-05, "epoch": 3.2369620253164557, "percentage": 64.88, "elapsed_time": "18:47:21", "remaining_time": "10:10:17"}
1504
+ {"current_steps": 706, "total_steps": 1230, "loss": 0.2452, "lr": 1.8327574328332806e-05, "epoch": 2.8627848101265823, "percentage": 57.4, "elapsed_time": "16:36:14", "remaining_time": "12:19:25"}
1505
+ {"current_steps": 707, "total_steps": 1230, "loss": 0.2516, "lr": 1.8271021255315906e-05, "epoch": 2.8668354430379748, "percentage": 57.48, "elapsed_time": "16:37:35", "remaining_time": "12:17:57"}
1506
+ {"current_steps": 799, "total_steps": 1230, "loss": 0.1939, "lr": 1.3186271864965509e-05, "epoch": 3.2410126582278482, "percentage": 64.96, "elapsed_time": "18:48:56", "remaining_time": "10:08:58"}
1507
+ {"current_steps": 708, "total_steps": 1230, "loss": 0.2489, "lr": 1.8214482107256117e-05, "epoch": 2.8708860759493673, "percentage": 57.56, "elapsed_time": "16:39:14", "remaining_time": "12:16:44"}
1508
+ {"current_steps": 800, "total_steps": 1230, "loss": 0.1893, "lr": 1.3132936174930756e-05, "epoch": 3.2450632911392403, "percentage": 65.04, "elapsed_time": "18:50:26", "remaining_time": "10:07:36"}
1509
+ {"current_steps": 709, "total_steps": 1230, "loss": 0.2432, "lr": 1.8157957339511968e-05, "epoch": 2.8749367088607594, "percentage": 57.64, "elapsed_time": "16:40:36", "remaining_time": "12:15:16"}
1510
+ {"current_steps": 801, "total_steps": 1230, "loss": 0.1777, "lr": 1.3079655791283995e-05, "epoch": 3.249113924050633, "percentage": 65.12, "elapsed_time": "18:51:52", "remaining_time": "10:06:12"}
1511
+ {"current_steps": 802, "total_steps": 1230, "loss": 0.1683, "lr": 1.3026431143138108e-05, "epoch": 3.2531645569620253, "percentage": 65.2, "elapsed_time": "18:53:20", "remaining_time": "10:04:49"}
1512
+ {"current_steps": 710, "total_steps": 1230, "loss": 0.2665, "lr": 1.8101447407326182e-05, "epoch": 2.878987341772152, "percentage": 57.72, "elapsed_time": "16:42:13", "remaining_time": "12:14:01"}
1513
+ {"current_steps": 711, "total_steps": 1230, "loss": 0.2289, "lr": 1.8044952765821966e-05, "epoch": 2.8830379746835444, "percentage": 57.8, "elapsed_time": "16:43:33", "remaining_time": "12:12:33"}
1514
+ {"current_steps": 803, "total_steps": 1230, "loss": 0.1947, "lr": 1.2973262659157114e-05, "epoch": 3.257215189873418, "percentage": 65.28, "elapsed_time": "18:54:51", "remaining_time": "10:03:27"}
1515
+ {"current_steps": 804, "total_steps": 1230, "loss": 0.1816, "lr": 1.2920150767552651e-05, "epoch": 3.26126582278481, "percentage": 65.37, "elapsed_time": "18:56:03", "remaining_time": "10:01:56"}
1516
+ {"current_steps": 712, "total_steps": 1230, "loss": 0.2359, "lr": 1.7988473869999407e-05, "epoch": 2.8870886075949365, "percentage": 57.89, "elapsed_time": "16:45:02", "remaining_time": "12:11:11"}
1517
+ {"current_steps": 805, "total_steps": 1230, "loss": 0.1603, "lr": 1.2867095896080607e-05, "epoch": 3.2653164556962024, "percentage": 65.45, "elapsed_time": "18:57:17", "remaining_time": "10:00:26"}
1518
+ {"current_steps": 713, "total_steps": 1230, "loss": 0.2647, "lr": 1.7932011174731764e-05, "epoch": 2.891139240506329, "percentage": 57.97, "elapsed_time": "16:46:38", "remaining_time": "12:09:55"}
1519
+ {"current_steps": 806, "total_steps": 1230, "loss": 0.17, "lr": 1.2814098472037612e-05, "epoch": 3.269367088607595, "percentage": 65.53, "elapsed_time": "18:58:44", "remaining_time": "9:59:02"}
1520
+ {"current_steps": 714, "total_steps": 1230, "loss": 0.2521, "lr": 1.7875565134761817e-05, "epoch": 2.8951898734177215, "percentage": 58.05, "elapsed_time": "16:48:06", "remaining_time": "12:08:32"}
1521
+ {"current_steps": 807, "total_steps": 1230, "loss": 0.1695, "lr": 1.276115892225764e-05, "epoch": 3.2734177215189875, "percentage": 65.61, "elapsed_time": "18:59:56", "remaining_time": "9:57:31"}
1522
+ {"current_steps": 715, "total_steps": 1230, "loss": 0.2549, "lr": 1.7819136204698226e-05, "epoch": 2.899240506329114, "percentage": 58.13, "elapsed_time": "16:49:34", "remaining_time": "12:07:10"}
1523
+ {"current_steps": 808, "total_steps": 1230, "loss": 0.1738, "lr": 1.2708277673108555e-05, "epoch": 3.27746835443038, "percentage": 65.69, "elapsed_time": "19:01:18", "remaining_time": "9:56:04"}
1524
+ {"current_steps": 716, "total_steps": 1230, "loss": 0.2506, "lr": 1.776272483901182e-05, "epoch": 2.9032911392405065, "percentage": 58.21, "elapsed_time": "16:50:55", "remaining_time": "12:05:42"}
1525
+ {"current_steps": 809, "total_steps": 1230, "loss": 0.1859, "lr": 1.2655455150488649e-05, "epoch": 3.281518987341772, "percentage": 65.77, "elapsed_time": "19:02:50", "remaining_time": "9:54:43"}
1526
+ {"current_steps": 717, "total_steps": 1230, "loss": 0.2512, "lr": 1.7706331492031995e-05, "epoch": 2.9073417721518986, "percentage": 58.29, "elapsed_time": "16:52:30", "remaining_time": "12:04:25"}
1527
+ {"current_steps": 810, "total_steps": 1230, "loss": 0.169, "lr": 1.2602691779823272e-05, "epoch": 3.2855696202531646, "percentage": 65.85, "elapsed_time": "19:04:09", "remaining_time": "9:53:15"}
1528
+ {"current_steps": 718, "total_steps": 1230, "loss": 0.2603, "lr": 1.764995661794301e-05, "epoch": 2.911392405063291, "percentage": 58.37, "elapsed_time": "16:53:47", "remaining_time": "12:02:55"}
1529
+ {"current_steps": 811, "total_steps": 1230, "loss": 0.1737, "lr": 1.2549987986061355e-05, "epoch": 3.289620253164557, "percentage": 65.93, "elapsed_time": "19:05:34", "remaining_time": "9:51:51"}
1530
+ {"current_steps": 719, "total_steps": 1230, "loss": 0.2412, "lr": 1.759360067078035e-05, "epoch": 2.9154430379746836, "percentage": 58.46, "elapsed_time": "16:55:12", "remaining_time": "12:01:30"}
1531
+ {"current_steps": 812, "total_steps": 1230, "loss": 0.183, "lr": 1.2497344193672005e-05, "epoch": 3.293670886075949, "percentage": 66.02, "elapsed_time": "19:07:02", "remaining_time": "9:50:28"}
1532
+ {"current_steps": 720, "total_steps": 1230, "loss": 0.2766, "lr": 1.7537264104427064e-05, "epoch": 2.9194936708860757, "percentage": 58.54, "elapsed_time": "16:56:50", "remaining_time": "12:00:15"}
1533
+ {"current_steps": 813, "total_steps": 1230, "loss": 0.1594, "lr": 1.2444760826641092e-05, "epoch": 3.2977215189873417, "percentage": 66.1, "elapsed_time": "19:08:22", "remaining_time": "9:49:01"}
1534
+ {"current_steps": 721, "total_steps": 1230, "loss": 0.2502, "lr": 1.748094737261012e-05, "epoch": 2.923544303797468, "percentage": 58.62, "elapsed_time": "16:58:16", "remaining_time": "11:58:51"}
1535
+ {"current_steps": 814, "total_steps": 1230, "loss": 0.1592, "lr": 1.2392238308467817e-05, "epoch": 3.301772151898734, "percentage": 66.18, "elapsed_time": "19:09:41", "remaining_time": "9:47:33"}
1536
+ {"current_steps": 722, "total_steps": 1230, "loss": 0.247, "lr": 1.7424650928896726e-05, "epoch": 2.9275949367088607, "percentage": 58.7, "elapsed_time": "16:59:19", "remaining_time": "11:57:12"}
1537
+ {"current_steps": 815, "total_steps": 1230, "loss": 0.1887, "lr": 1.2339777062161326e-05, "epoch": 3.3058227848101267, "percentage": 66.26, "elapsed_time": "19:11:04", "remaining_time": "9:46:07"}
1538
+ {"current_steps": 723, "total_steps": 1230, "loss": 0.246, "lr": 1.7368375226690712e-05, "epoch": 2.9316455696202532, "percentage": 58.78, "elapsed_time": "17:00:46", "remaining_time": "11:55:48"}
1539
+ {"current_steps": 816, "total_steps": 1230, "loss": 0.1888, "lr": 1.2287377510237293e-05, "epoch": 3.309873417721519, "percentage": 66.34, "elapsed_time": "19:12:38", "remaining_time": "9:44:47"}
1540
+ {"current_steps": 724, "total_steps": 1230, "loss": 0.2235, "lr": 1.731212071922883e-05, "epoch": 2.9356962025316458, "percentage": 58.86, "elapsed_time": "17:01:58", "remaining_time": "11:54:15"}
1541
+ {"current_steps": 817, "total_steps": 1230, "loss": 0.1787, "lr": 1.2235040074714488e-05, "epoch": 3.3139240506329113, "percentage": 66.42, "elapsed_time": "19:14:01", "remaining_time": "9:43:22"}
1542
+ {"current_steps": 725, "total_steps": 1230, "loss": 0.2587, "lr": 1.7255887859577156e-05, "epoch": 2.939746835443038, "percentage": 58.94, "elapsed_time": "17:03:26", "remaining_time": "11:52:52"}
1543
+ {"current_steps": 818, "total_steps": 1230, "loss": 0.1873, "lr": 1.2182765177111434e-05, "epoch": 3.317974683544304, "percentage": 66.5, "elapsed_time": "19:15:39", "remaining_time": "9:42:04"}
1544
+ {"current_steps": 726, "total_steps": 1230, "loss": 0.2411, "lr": 1.7199677100627427e-05, "epoch": 2.9437974683544303, "percentage": 59.02, "elapsed_time": "17:04:43", "remaining_time": "11:51:22"}
1545
+ {"current_steps": 819, "total_steps": 1230, "loss": 0.1596, "lr": 1.213055323844297e-05, "epoch": 3.3220253164556963, "percentage": 66.59, "elapsed_time": "19:16:58", "remaining_time": "9:40:36"}
1546
+ {"current_steps": 727, "total_steps": 1230, "loss": 0.2512, "lr": 1.7143488895093343e-05, "epoch": 2.947848101265823, "percentage": 59.11, "elapsed_time": "17:06:10", "remaining_time": "11:49:59"}
1547
+ {"current_steps": 820, "total_steps": 1230, "loss": 0.1591, "lr": 1.2078404679216864e-05, "epoch": 3.3260759493670884, "percentage": 66.67, "elapsed_time": "19:18:13", "remaining_time": "9:39:06"}
1548
+ {"current_steps": 728, "total_steps": 1230, "loss": 0.2438, "lr": 1.7087323695506994e-05, "epoch": 2.951898734177215, "percentage": 59.19, "elapsed_time": "17:07:31", "remaining_time": "11:48:32"}
1549
+ {"current_steps": 821, "total_steps": 1230, "loss": 0.1736, "lr": 1.2026319919430458e-05, "epoch": 3.330126582278481, "percentage": 66.75, "elapsed_time": "19:19:42", "remaining_time": "9:37:44"}
1550
+ {"current_steps": 729, "total_steps": 1230, "loss": 0.2424, "lr": 1.7031181954215194e-05, "epoch": 2.9559493670886074, "percentage": 59.27, "elapsed_time": "17:08:45", "remaining_time": "11:47:00"}
1551
+ {"current_steps": 730, "total_steps": 1230, "loss": 0.2385, "lr": 1.6975064123375788e-05, "epoch": 2.96, "percentage": 59.35, "elapsed_time": "17:09:57", "remaining_time": "11:45:27"}
1552
+ {"current_steps": 822, "total_steps": 1230, "loss": 0.1665, "lr": 1.1974299378567227e-05, "epoch": 3.3341772151898734, "percentage": 66.83, "elapsed_time": "19:21:10", "remaining_time": "9:36:20"}
1553
+ {"current_steps": 731, "total_steps": 1230, "loss": 0.2473, "lr": 1.6918970654954084e-05, "epoch": 2.9640506329113925, "percentage": 59.43, "elapsed_time": "17:11:16", "remaining_time": "11:43:58"}
1554
+ {"current_steps": 823, "total_steps": 1230, "loss": 0.1793, "lr": 1.1922343475593462e-05, "epoch": 3.338227848101266, "percentage": 66.91, "elapsed_time": "19:22:37", "remaining_time": "9:34:57"}
1555
+ {"current_steps": 732, "total_steps": 1230, "loss": 0.2377, "lr": 1.686290200071915e-05, "epoch": 2.968101265822785, "percentage": 59.51, "elapsed_time": "17:12:25", "remaining_time": "11:42:23"}
1556
+ {"current_steps": 824, "total_steps": 1230, "loss": 0.2135, "lr": 1.187045262895488e-05, "epoch": 3.3422784810126585, "percentage": 66.99, "elapsed_time": "19:24:14", "remaining_time": "9:33:38"}
1557
+ {"current_steps": 733, "total_steps": 1230, "loss": 0.2317, "lr": 1.6806858612240234e-05, "epoch": 2.972151898734177, "percentage": 59.59, "elapsed_time": "17:13:42", "remaining_time": "11:40:53"}
1558
+ {"current_steps": 825, "total_steps": 1230, "loss": 0.1584, "lr": 1.1818627256573203e-05, "epoch": 3.3463291139240505, "percentage": 67.07, "elapsed_time": "19:25:19", "remaining_time": "9:32:04"}
1559
+ {"current_steps": 734, "total_steps": 1230, "loss": 0.2147, "lr": 1.6750840940883078e-05, "epoch": 2.9762025316455696, "percentage": 59.67, "elapsed_time": "17:14:54", "remaining_time": "11:39:20"}
1560
+ {"current_steps": 826, "total_steps": 1230, "loss": 0.1882, "lr": 1.1766867775842864e-05, "epoch": 3.350379746835443, "percentage": 67.15, "elapsed_time": "19:26:52", "remaining_time": "9:30:43"}
1561
+ {"current_steps": 735, "total_steps": 1230, "loss": 0.2347, "lr": 1.6694849437806305e-05, "epoch": 2.980253164556962, "percentage": 59.76, "elapsed_time": "17:16:00", "remaining_time": "11:37:43"}
1562
+ {"current_steps": 827, "total_steps": 1230, "loss": 0.1742, "lr": 1.1715174603627615e-05, "epoch": 3.3544303797468356, "percentage": 67.24, "elapsed_time": "19:28:04", "remaining_time": "9:29:12"}
1563
+ {"current_steps": 736, "total_steps": 1230, "loss": 0.2157, "lr": 1.663888455395778e-05, "epoch": 2.984303797468354, "percentage": 59.84, "elapsed_time": "17:17:20", "remaining_time": "11:36:15"}
1564
+ {"current_steps": 828, "total_steps": 1230, "loss": 0.1773, "lr": 1.1663548156257147e-05, "epoch": 3.3584810126582276, "percentage": 67.32, "elapsed_time": "19:29:22", "remaining_time": "9:27:44"}
1565
+ {"current_steps": 737, "total_steps": 1230, "loss": 0.2218, "lr": 1.6582946740070995e-05, "epoch": 2.9883544303797467, "percentage": 59.92, "elapsed_time": "17:18:25", "remaining_time": "11:34:38"}
1566
+ {"current_steps": 829, "total_steps": 1230, "loss": 0.1606, "lr": 1.161198884952377e-05, "epoch": 3.36253164556962, "percentage": 67.4, "elapsed_time": "19:30:37", "remaining_time": "9:26:14"}
1567
+ {"current_steps": 738, "total_steps": 1230, "loss": 0.2655, "lr": 1.6527036446661396e-05, "epoch": 2.992405063291139, "percentage": 60.0, "elapsed_time": "17:19:47", "remaining_time": "11:33:11"}
1568
+ {"current_steps": 830, "total_steps": 1230, "loss": 0.1736, "lr": 1.1560497098679056e-05, "epoch": 3.3665822784810127, "percentage": 67.48, "elapsed_time": "19:31:55", "remaining_time": "9:24:47"}
1569
+ {"current_steps": 739, "total_steps": 1230, "loss": 0.2411, "lr": 1.6471154124022818e-05, "epoch": 2.9964556962025317, "percentage": 60.08, "elapsed_time": "17:21:07", "remaining_time": "11:31:44"}
1570
+ {"current_steps": 831, "total_steps": 1230, "loss": 0.1891, "lr": 1.1509073318430479e-05, "epoch": 3.370632911392405, "percentage": 67.56, "elapsed_time": "19:33:25", "remaining_time": "9:23:24"}
1571
+ {"current_steps": 832, "total_steps": 1230, "loss": 0.1542, "lr": 1.1457717922938116e-05, "epoch": 3.3746835443037977, "percentage": 67.64, "elapsed_time": "19:34:38", "remaining_time": "9:21:54"}
1572
+ {"current_steps": 740, "total_steps": 1230, "loss": 0.2258, "lr": 1.6415300222223788e-05, "epoch": 3.002025316455696, "percentage": 60.16, "elapsed_time": "17:23:32", "remaining_time": "11:30:59"}
1573
+ {"current_steps": 741, "total_steps": 1230, "loss": 0.1767, "lr": 1.6359475191103958e-05, "epoch": 3.0060759493670886, "percentage": 60.24, "elapsed_time": "17:24:52", "remaining_time": "11:29:31"}
1574
+ {"current_steps": 833, "total_steps": 1230, "loss": 0.1641, "lr": 1.1406431325811233e-05, "epoch": 3.3787341772151898, "percentage": 67.72, "elapsed_time": "19:36:04", "remaining_time": "9:20:30"}
1575
+ {"current_steps": 742, "total_steps": 1230, "loss": 0.208, "lr": 1.6303679480270466e-05, "epoch": 3.010126582278481, "percentage": 60.33, "elapsed_time": "17:26:15", "remaining_time": "11:28:05"}
1576
+ {"current_steps": 834, "total_steps": 1230, "loss": 0.1774, "lr": 1.135521394010506e-05, "epoch": 3.3827848101265823, "percentage": 67.8, "elapsed_time": "19:37:24", "remaining_time": "9:19:03"}
1577
+ {"current_steps": 743, "total_steps": 1230, "loss": 0.1758, "lr": 1.624791353909428e-05, "epoch": 3.0141772151898736, "percentage": 60.41, "elapsed_time": "17:27:31", "remaining_time": "11:26:36"}
1578
+ {"current_steps": 835, "total_steps": 1230, "loss": 0.1816, "lr": 1.1304066178317367e-05, "epoch": 3.386835443037975, "percentage": 67.89, "elapsed_time": "19:38:48", "remaining_time": "9:17:38"}
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2b109346f835356baa84e067fdb9a82cdcae7d60dd3739e1d9b7b4e6b1eca559
3
  size 7288
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fbfe2753ce890402118e13912d3877e6acebdd7767919752be931aea1065b060
3
  size 7288