Training in progress, step 3600
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:b072d70b85be7646f7c771ae94c05893ed00a165c4dcd87ce37cf50e2312bced
|
| 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 sha256:11f3a9b511268a9ed8ee2963a1c076d749fc9c24703249d34789b63b430cd0a4
|
| 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 sha256:7b2d2e4042770f75a970d5480d44f4b3e9266e5e90579a4668bcb855a901015b
|
| 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 sha256:3cd9154a5a3386b31a2e2568e320d916d70372cf3e6b8b58d8867ce92244b52f
|
| 3 |
size 1580230264
|
trainer_log.jsonl
CHANGED
|
@@ -681,3 +681,41 @@
|
|
| 681 |
{"current_steps": 3405, "total_steps": 3752, "loss": 0.1984, "lr": 1.039572170487606e-06, "epoch": 6.352941176470588, "percentage": 90.75, "elapsed_time": "1 day, 1:04:13", "remaining_time": "2:33:17"}
|
| 682 |
{"current_steps": 3410, "total_steps": 3752, "loss": 0.1907, "lr": 1.0101662709467841e-06, "epoch": 6.362278244631185, "percentage": 90.88, "elapsed_time": "1 day, 1:06:19", "remaining_time": "2:31:04"}
|
| 683 |
{"current_steps": 3415, "total_steps": 3752, "loss": 0.193, "lr": 9.811714787705528e-07, "epoch": 6.371615312791784, "percentage": 91.02, "elapsed_time": "1 day, 1:08:42", "remaining_time": "2:28:52"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 681 |
{"current_steps": 3405, "total_steps": 3752, "loss": 0.1984, "lr": 1.039572170487606e-06, "epoch": 6.352941176470588, "percentage": 90.75, "elapsed_time": "1 day, 1:04:13", "remaining_time": "2:33:17"}
|
| 682 |
{"current_steps": 3410, "total_steps": 3752, "loss": 0.1907, "lr": 1.0101662709467841e-06, "epoch": 6.362278244631185, "percentage": 90.88, "elapsed_time": "1 day, 1:06:19", "remaining_time": "2:31:04"}
|
| 683 |
{"current_steps": 3415, "total_steps": 3752, "loss": 0.193, "lr": 9.811714787705528e-07, "epoch": 6.371615312791784, "percentage": 91.02, "elapsed_time": "1 day, 1:08:42", "remaining_time": "2:28:52"}
|
| 684 |
+
{"current_steps": 3420, "total_steps": 3752, "loss": 0.1894, "lr": 9.525884216617575e-07, "epoch": 6.380952380952381, "percentage": 91.15, "elapsed_time": "1 day, 1:10:57", "remaining_time": "2:26:40"}
|
| 685 |
+
{"current_steps": 3425, "total_steps": 3752, "loss": 0.2012, "lr": 9.244177184096603e-07, "epoch": 6.390289449112979, "percentage": 91.28, "elapsed_time": "1 day, 1:13:11", "remaining_time": "2:24:28"}
|
| 686 |
+
{"current_steps": 3430, "total_steps": 3752, "loss": 0.1891, "lr": 8.96659978876564e-07, "epoch": 6.3996265172735765, "percentage": 91.42, "elapsed_time": "1 day, 1:15:27", "remaining_time": "2:22:16"}
|
| 687 |
+
{"current_steps": 3435, "total_steps": 3752, "loss": 0.1915, "lr": 8.693158039845851e-07, "epoch": 6.408963585434174, "percentage": 91.55, "elapsed_time": "1 day, 1:17:43", "remaining_time": "2:20:03"}
|
| 688 |
+
{"current_steps": 3440, "total_steps": 3752, "loss": 0.1975, "lr": 8.423857857026574e-07, "epoch": 6.4183006535947715, "percentage": 91.68, "elapsed_time": "1 day, 1:20:05", "remaining_time": "2:17:52"}
|
| 689 |
+
{"current_steps": 3445, "total_steps": 3752, "loss": 0.1975, "lr": 8.158705070337181e-07, "epoch": 6.427637721755369, "percentage": 91.82, "elapsed_time": "1 day, 1:22:20", "remaining_time": "2:15:39"}
|
| 690 |
+
{"current_steps": 3450, "total_steps": 3752, "loss": 0.1961, "lr": 7.897705420020863e-07, "epoch": 6.436974789915967, "percentage": 91.95, "elapsed_time": "1 day, 1:24:15", "remaining_time": "2:13:25"}
|
| 691 |
+
{"current_steps": 3455, "total_steps": 3752, "loss": 0.1926, "lr": 7.640864556410311e-07, "epoch": 6.446311858076564, "percentage": 92.08, "elapsed_time": "1 day, 1:26:17", "remaining_time": "2:11:12"}
|
| 692 |
+
{"current_steps": 3460, "total_steps": 3752, "loss": 0.1921, "lr": 7.388188039805455e-07, "epoch": 6.455648926237162, "percentage": 92.22, "elapsed_time": "1 day, 1:28:23", "remaining_time": "2:08:59"}
|
| 693 |
+
{"current_steps": 3465, "total_steps": 3752, "loss": 0.1937, "lr": 7.139681340352966e-07, "epoch": 6.464985994397759, "percentage": 92.35, "elapsed_time": "1 day, 1:30:25", "remaining_time": "2:06:45"}
|
| 694 |
+
{"current_steps": 3470, "total_steps": 3752, "loss": 0.1985, "lr": 6.895349837928033e-07, "epoch": 6.474323062558357, "percentage": 92.48, "elapsed_time": "1 day, 1:32:27", "remaining_time": "2:04:32"}
|
| 695 |
+
{"current_steps": 3475, "total_steps": 3752, "loss": 0.1965, "lr": 6.655198822017661e-07, "epoch": 6.483660130718954, "percentage": 92.62, "elapsed_time": "1 day, 1:34:29", "remaining_time": "2:02:19"}
|
| 696 |
+
{"current_steps": 3480, "total_steps": 3752, "loss": 0.1977, "lr": 6.419233491606403e-07, "epoch": 6.492997198879552, "percentage": 92.75, "elapsed_time": "1 day, 1:36:43", "remaining_time": "2:00:06"}
|
| 697 |
+
{"current_steps": 3485, "total_steps": 3752, "loss": 0.1965, "lr": 6.187458955063652e-07, "epoch": 6.502334267040149, "percentage": 92.88, "elapsed_time": "1 day, 1:39:08", "remaining_time": "1:57:55"}
|
| 698 |
+
{"current_steps": 3490, "total_steps": 3752, "loss": 0.2, "lr": 5.959880230033043e-07, "epoch": 6.511671335200747, "percentage": 93.02, "elapsed_time": "1 day, 1:41:17", "remaining_time": "1:55:42"}
|
| 699 |
+
{"current_steps": 3495, "total_steps": 3752, "loss": 0.1968, "lr": 5.736502243323894e-07, "epoch": 6.5210084033613445, "percentage": 93.15, "elapsed_time": "1 day, 1:43:44", "remaining_time": "1:53:31"}
|
| 700 |
+
{"current_steps": 3500, "total_steps": 3752, "loss": 0.1948, "lr": 5.517329830804552e-07, "epoch": 6.530345471521942, "percentage": 93.28, "elapsed_time": "1 day, 1:45:51", "remaining_time": "1:51:18"}
|
| 701 |
+
{"current_steps": 3505, "total_steps": 3752, "loss": 0.2037, "lr": 5.302367737297642e-07, "epoch": 6.5396825396825395, "percentage": 93.42, "elapsed_time": "1 day, 1:47:54", "remaining_time": "1:49:04"}
|
| 702 |
+
{"current_steps": 3510, "total_steps": 3752, "loss": 0.2028, "lr": 5.091620616477366e-07, "epoch": 6.549019607843137, "percentage": 93.55, "elapsed_time": "1 day, 1:49:51", "remaining_time": "1:46:51"}
|
| 703 |
+
{"current_steps": 3515, "total_steps": 3752, "loss": 0.1906, "lr": 4.88509303076885e-07, "epoch": 6.558356676003735, "percentage": 93.68, "elapsed_time": "1 day, 1:52:06", "remaining_time": "1:44:39"}
|
| 704 |
+
{"current_steps": 3520, "total_steps": 3752, "loss": 0.1887, "lr": 4.6827894512491814e-07, "epoch": 6.567693744164332, "percentage": 93.82, "elapsed_time": "1 day, 1:54:27", "remaining_time": "1:42:27"}
|
| 705 |
+
{"current_steps": 3525, "total_steps": 3752, "loss": 0.1983, "lr": 4.4847142575507706e-07, "epoch": 6.57703081232493, "percentage": 93.95, "elapsed_time": "1 day, 1:56:44", "remaining_time": "1:40:15"}
|
| 706 |
+
{"current_steps": 3530, "total_steps": 3752, "loss": 0.1931, "lr": 4.290871737766544e-07, "epoch": 6.586367880485527, "percentage": 94.08, "elapsed_time": "1 day, 1:59:06", "remaining_time": "1:38:03"}
|
| 707 |
+
{"current_steps": 3535, "total_steps": 3752, "loss": 0.1984, "lr": 4.1012660883570146e-07, "epoch": 6.595704948646125, "percentage": 94.22, "elapsed_time": "1 day, 2:01:17", "remaining_time": "1:35:50"}
|
| 708 |
+
{"current_steps": 3540, "total_steps": 3752, "loss": 0.1987, "lr": 3.915901414059464e-07, "epoch": 6.605042016806722, "percentage": 94.35, "elapsed_time": "1 day, 2:03:18", "remaining_time": "1:33:37"}
|
| 709 |
+
{"current_steps": 3545, "total_steps": 3752, "loss": 0.1899, "lr": 3.734781727799086e-07, "epoch": 6.61437908496732, "percentage": 94.48, "elapsed_time": "1 day, 2:05:24", "remaining_time": "1:31:24"}
|
| 710 |
+
{"current_steps": 3550, "total_steps": 3752, "loss": 0.1966, "lr": 3.557910950602228e-07, "epoch": 6.623716153127917, "percentage": 94.62, "elapsed_time": "1 day, 2:07:26", "remaining_time": "1:29:11"}
|
| 711 |
+
{"current_steps": 3555, "total_steps": 3752, "loss": 0.1988, "lr": 3.3852929115112177e-07, "epoch": 6.633053221288515, "percentage": 94.75, "elapsed_time": "1 day, 2:09:35", "remaining_time": "1:26:58"}
|
| 712 |
+
{"current_steps": 3560, "total_steps": 3752, "loss": 0.1838, "lr": 3.2169313475018506e-07, "epoch": 6.642390289449113, "percentage": 94.88, "elapsed_time": "1 day, 2:11:56", "remaining_time": "1:24:46"}
|
| 713 |
+
{"current_steps": 3565, "total_steps": 3752, "loss": 0.1936, "lr": 3.0528299034021437e-07, "epoch": 6.651727357609711, "percentage": 95.02, "elapsed_time": "1 day, 2:14:20", "remaining_time": "1:22:34"}
|
| 714 |
+
{"current_steps": 3570, "total_steps": 3752, "loss": 0.1937, "lr": 2.892992131813621e-07, "epoch": 6.661064425770308, "percentage": 95.15, "elapsed_time": "1 day, 2:16:21", "remaining_time": "1:20:21"}
|
| 715 |
+
{"current_steps": 3575, "total_steps": 3752, "loss": 0.1993, "lr": 2.737421493034331e-07, "epoch": 6.670401493930906, "percentage": 95.28, "elapsed_time": "1 day, 2:18:24", "remaining_time": "1:18:08"}
|
| 716 |
+
{"current_steps": 3580, "total_steps": 3752, "loss": 0.1949, "lr": 2.586121354984017e-07, "epoch": 6.6797385620915035, "percentage": 95.42, "elapsed_time": "1 day, 2:20:39", "remaining_time": "1:15:56"}
|
| 717 |
+
{"current_steps": 3585, "total_steps": 3752, "loss": 0.1933, "lr": 2.4390949931311304e-07, "epoch": 6.689075630252101, "percentage": 95.55, "elapsed_time": "1 day, 2:22:53", "remaining_time": "1:13:44"}
|
| 718 |
+
{"current_steps": 3590, "total_steps": 3752, "loss": 0.1964, "lr": 2.296345590421889e-07, "epoch": 6.698412698412699, "percentage": 95.68, "elapsed_time": "1 day, 2:25:05", "remaining_time": "1:11:31"}
|
| 719 |
+
{"current_steps": 3595, "total_steps": 3752, "loss": 0.1944, "lr": 2.157876237211487e-07, "epoch": 6.707749766573296, "percentage": 95.82, "elapsed_time": "1 day, 2:27:20", "remaining_time": "1:09:19"}
|
| 720 |
+
{"current_steps": 3600, "total_steps": 3752, "loss": 0.1948, "lr": 2.0236899311970593e-07, "epoch": 6.717086834733894, "percentage": 95.95, "elapsed_time": "1 day, 2:29:30", "remaining_time": "1:07:06"}
|
| 721 |
+
{"current_steps": 3605, "total_steps": 3752, "loss": 0.2016, "lr": 1.8937895773529114e-07, "epoch": 6.726423902894491, "percentage": 96.08, "elapsed_time": "1 day, 2:32:39", "remaining_time": "1:04:56"}
|