Training in progress, step 4400
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 sha256:1fdb0d88dba94bda115b8076c9c9fed07f60529f2632b9ac3ede6ef4a4004b94
|
| 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 sha256:4d06b2a67c483fb669bb623ce2d309118418e1f32c74af771c37e40f5a4be986
|
| 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 sha256:490fc7d650d8991596e1f662260f42cd924198aac91d6533fbaabb761114939c
|
| 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:eee6b9e463b905ff82652296fd02b9d52f709114ef3ecaadd8133da915b0dfd6
|
| 3 |
size 1580230264
|
trainer_log.jsonl
CHANGED
|
@@ -841,3 +841,44 @@
|
|
| 841 |
{"current_steps": 4205, "total_steps": 9128, "loss": 0.1714, "lr": 2.6143958165209695e-05, "epoch": 3.2247794399693133, "percentage": 46.07, "elapsed_time": "1 day, 2:54:37", "remaining_time": "1 day, 7:30:18"}
|
| 842 |
{"current_steps": 4210, "total_steps": 9128, "loss": 0.1685, "lr": 2.6107553979662906e-05, "epoch": 3.22861526658995, "percentage": 46.12, "elapsed_time": "1 day, 2:55:52", "remaining_time": "1 day, 7:27:36"}
|
| 843 |
{"current_steps": 4215, "total_steps": 9128, "loss": 0.1774, "lr": 2.60711274639579e-05, "epoch": 3.232451093210587, "percentage": 46.18, "elapsed_time": "1 day, 2:57:12", "remaining_time": "1 day, 7:25:00"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 841 |
{"current_steps": 4205, "total_steps": 9128, "loss": 0.1714, "lr": 2.6143958165209695e-05, "epoch": 3.2247794399693133, "percentage": 46.07, "elapsed_time": "1 day, 2:54:37", "remaining_time": "1 day, 7:30:18"}
|
| 842 |
{"current_steps": 4210, "total_steps": 9128, "loss": 0.1685, "lr": 2.6107553979662906e-05, "epoch": 3.22861526658995, "percentage": 46.12, "elapsed_time": "1 day, 2:55:52", "remaining_time": "1 day, 7:27:36"}
|
| 843 |
{"current_steps": 4215, "total_steps": 9128, "loss": 0.1774, "lr": 2.60711274639579e-05, "epoch": 3.232451093210587, "percentage": 46.18, "elapsed_time": "1 day, 2:57:12", "remaining_time": "1 day, 7:25:00"}
|
| 844 |
+
{"current_steps": 4220, "total_steps": 9128, "loss": 0.1742, "lr": 2.603467875127563e-05, "epoch": 3.2362869198312234, "percentage": 46.23, "elapsed_time": "1 day, 2:58:27", "remaining_time": "1 day, 7:22:18"}
|
| 845 |
+
{"current_steps": 4225, "total_steps": 9128, "loss": 0.1611, "lr": 2.5998207974878202e-05, "epoch": 3.2401227464518603, "percentage": 46.29, "elapsed_time": "1 day, 2:59:41", "remaining_time": "1 day, 7:19:36"}
|
| 846 |
+
{"current_steps": 4230, "total_steps": 9128, "loss": 0.1803, "lr": 2.5961715268108395e-05, "epoch": 3.243958573072497, "percentage": 46.34, "elapsed_time": "1 day, 3:00:55", "remaining_time": "1 day, 7:16:54"}
|
| 847 |
+
{"current_steps": 4235, "total_steps": 9128, "loss": 0.1663, "lr": 2.5925200764389163e-05, "epoch": 3.247794399693134, "percentage": 46.4, "elapsed_time": "1 day, 3:02:09", "remaining_time": "1 day, 7:14:11"}
|
| 848 |
+
{"current_steps": 4240, "total_steps": 9128, "loss": 0.169, "lr": 2.5888664597223168e-05, "epoch": 3.251630226313771, "percentage": 46.45, "elapsed_time": "1 day, 3:03:25", "remaining_time": "1 day, 7:11:32"}
|
| 849 |
+
{"current_steps": 4245, "total_steps": 9128, "loss": 0.1689, "lr": 2.585210690019225e-05, "epoch": 3.2554660529344073, "percentage": 46.51, "elapsed_time": "1 day, 3:04:42", "remaining_time": "1 day, 7:08:54"}
|
| 850 |
+
{"current_steps": 4250, "total_steps": 9128, "loss": 0.1657, "lr": 2.5815527806956984e-05, "epoch": 3.259301879555044, "percentage": 46.56, "elapsed_time": "1 day, 3:05:59", "remaining_time": "1 day, 7:06:15"}
|
| 851 |
+
{"current_steps": 4255, "total_steps": 9128, "loss": 0.1601, "lr": 2.577892745125618e-05, "epoch": 3.263137706175681, "percentage": 46.61, "elapsed_time": "1 day, 3:07:13", "remaining_time": "1 day, 7:03:34"}
|
| 852 |
+
{"current_steps": 4260, "total_steps": 9128, "loss": 0.1595, "lr": 2.5742305966906374e-05, "epoch": 3.2669735327963174, "percentage": 46.67, "elapsed_time": "1 day, 3:08:27", "remaining_time": "1 day, 7:00:52"}
|
| 853 |
+
{"current_steps": 4265, "total_steps": 9128, "loss": 0.1584, "lr": 2.5705663487801347e-05, "epoch": 3.2708093594169543, "percentage": 46.72, "elapsed_time": "1 day, 3:09:42", "remaining_time": "1 day, 6:58:13"}
|
| 854 |
+
{"current_steps": 4270, "total_steps": 9128, "loss": 0.1694, "lr": 2.5669000147911645e-05, "epoch": 3.274645186037591, "percentage": 46.78, "elapsed_time": "1 day, 3:10:59", "remaining_time": "1 day, 6:55:35"}
|
| 855 |
+
{"current_steps": 4275, "total_steps": 9128, "loss": 0.1707, "lr": 2.56323160812841e-05, "epoch": 3.278481012658228, "percentage": 46.83, "elapsed_time": "1 day, 3:12:17", "remaining_time": "1 day, 6:52:59"}
|
| 856 |
+
{"current_steps": 4280, "total_steps": 9128, "loss": 0.1769, "lr": 2.5595611422041308e-05, "epoch": 3.2823168392788644, "percentage": 46.89, "elapsed_time": "1 day, 3:13:32", "remaining_time": "1 day, 6:50:19"}
|
| 857 |
+
{"current_steps": 4285, "total_steps": 9128, "loss": 0.1615, "lr": 2.5558886304381142e-05, "epoch": 3.2861526658995013, "percentage": 46.94, "elapsed_time": "1 day, 3:14:48", "remaining_time": "1 day, 6:47:42"}
|
| 858 |
+
{"current_steps": 4290, "total_steps": 9128, "loss": 0.1667, "lr": 2.5522140862576307e-05, "epoch": 3.289988492520138, "percentage": 47.0, "elapsed_time": "1 day, 3:16:07", "remaining_time": "1 day, 6:45:07"}
|
| 859 |
+
{"current_steps": 4295, "total_steps": 9128, "loss": 0.1722, "lr": 2.5485375230973796e-05, "epoch": 3.293824319140775, "percentage": 47.05, "elapsed_time": "1 day, 3:17:28", "remaining_time": "1 day, 6:42:35"}
|
| 860 |
+
{"current_steps": 4300, "total_steps": 9128, "loss": 0.1655, "lr": 2.544858954399442e-05, "epoch": 3.2976601457614114, "percentage": 47.11, "elapsed_time": "1 day, 3:18:44", "remaining_time": "1 day, 6:39:58"}
|
| 861 |
+
{"current_steps": 4305, "total_steps": 9128, "loss": 0.159, "lr": 2.5411783936132305e-05, "epoch": 3.3014959723820483, "percentage": 47.16, "elapsed_time": "1 day, 3:19:58", "remaining_time": "1 day, 6:37:18"}
|
| 862 |
+
{"current_steps": 4310, "total_steps": 9128, "loss": 0.1619, "lr": 2.5374958541954443e-05, "epoch": 3.305331799002685, "percentage": 47.22, "elapsed_time": "1 day, 3:21:11", "remaining_time": "1 day, 6:34:37"}
|
| 863 |
+
{"current_steps": 4315, "total_steps": 9128, "loss": 0.1627, "lr": 2.5338113496100136e-05, "epoch": 3.309167625623322, "percentage": 47.27, "elapsed_time": "1 day, 3:22:28", "remaining_time": "1 day, 6:32:01"}
|
| 864 |
+
{"current_steps": 4320, "total_steps": 9128, "loss": 0.1633, "lr": 2.530124893328055e-05, "epoch": 3.3130034522439584, "percentage": 47.33, "elapsed_time": "1 day, 3:23:42", "remaining_time": "1 day, 6:29:22"}
|
| 865 |
+
{"current_steps": 4325, "total_steps": 9128, "loss": 0.1646, "lr": 2.5264364988278215e-05, "epoch": 3.3168392788645953, "percentage": 47.38, "elapsed_time": "1 day, 3:25:01", "remaining_time": "1 day, 6:26:50"}
|
| 866 |
+
{"current_steps": 4330, "total_steps": 9128, "loss": 0.1672, "lr": 2.52274617959465e-05, "epoch": 3.320675105485232, "percentage": 47.44, "elapsed_time": "1 day, 3:26:18", "remaining_time": "1 day, 6:24:14"}
|
| 867 |
+
{"current_steps": 4335, "total_steps": 9128, "loss": 0.1605, "lr": 2.519053949120917e-05, "epoch": 3.324510932105869, "percentage": 47.49, "elapsed_time": "1 day, 3:27:32", "remaining_time": "1 day, 6:21:36"}
|
| 868 |
+
{"current_steps": 4340, "total_steps": 9128, "loss": 0.1612, "lr": 2.5153598209059858e-05, "epoch": 3.3283467587265054, "percentage": 47.55, "elapsed_time": "1 day, 3:28:46", "remaining_time": "1 day, 6:18:58"}
|
| 869 |
+
{"current_steps": 4345, "total_steps": 9128, "loss": 0.168, "lr": 2.5116638084561583e-05, "epoch": 3.3321825853471423, "percentage": 47.6, "elapsed_time": "1 day, 3:30:02", "remaining_time": "1 day, 6:16:22"}
|
| 870 |
+
{"current_steps": 4350, "total_steps": 9128, "loss": 0.1557, "lr": 2.507965925284625e-05, "epoch": 3.336018411967779, "percentage": 47.66, "elapsed_time": "1 day, 3:31:15", "remaining_time": "1 day, 6:13:43"}
|
| 871 |
+
{"current_steps": 4355, "total_steps": 9128, "loss": 0.16, "lr": 2.5042661849114175e-05, "epoch": 3.3398542385884156, "percentage": 47.71, "elapsed_time": "1 day, 3:32:29", "remaining_time": "1 day, 6:11:06"}
|
| 872 |
+
{"current_steps": 4360, "total_steps": 9128, "loss": 0.1513, "lr": 2.5005646008633552e-05, "epoch": 3.3436900652090524, "percentage": 47.77, "elapsed_time": "1 day, 3:33:42", "remaining_time": "1 day, 6:08:27"}
|
| 873 |
+
{"current_steps": 4365, "total_steps": 9128, "loss": 0.1605, "lr": 2.496861186674e-05, "epoch": 3.3475258918296893, "percentage": 47.82, "elapsed_time": "1 day, 3:34:56", "remaining_time": "1 day, 6:05:50"}
|
| 874 |
+
{"current_steps": 4370, "total_steps": 9128, "loss": 0.1579, "lr": 2.4931559558836046e-05, "epoch": 3.351361718450326, "percentage": 47.87, "elapsed_time": "1 day, 3:36:10", "remaining_time": "1 day, 6:03:13"}
|
| 875 |
+
{"current_steps": 4375, "total_steps": 9128, "loss": 0.1615, "lr": 2.4894489220390648e-05, "epoch": 3.355197545070963, "percentage": 47.93, "elapsed_time": "1 day, 3:37:25", "remaining_time": "1 day, 6:00:37"}
|
| 876 |
+
{"current_steps": 4380, "total_steps": 9128, "loss": 0.1627, "lr": 2.485740098693866e-05, "epoch": 3.3590333716915994, "percentage": 47.98, "elapsed_time": "1 day, 3:38:41", "remaining_time": "1 day, 5:58:02"}
|
| 877 |
+
{"current_steps": 4385, "total_steps": 9128, "loss": 0.1624, "lr": 2.482029499408038e-05, "epoch": 3.3628691983122363, "percentage": 48.04, "elapsed_time": "1 day, 3:39:56", "remaining_time": "1 day, 5:55:27"}
|
| 878 |
+
{"current_steps": 4390, "total_steps": 9128, "loss": 0.1557, "lr": 2.4783171377481033e-05, "epoch": 3.366705024932873, "percentage": 48.09, "elapsed_time": "1 day, 3:41:10", "remaining_time": "1 day, 5:52:51"}
|
| 879 |
+
{"current_steps": 4395, "total_steps": 9128, "loss": 0.1611, "lr": 2.4746030272870284e-05, "epoch": 3.3705408515535096, "percentage": 48.15, "elapsed_time": "1 day, 3:42:27", "remaining_time": "1 day, 5:50:18"}
|
| 880 |
+
{"current_steps": 4400, "total_steps": 9128, "loss": 0.1687, "lr": 2.470887181604174e-05, "epoch": 3.3743766781741464, "percentage": 48.2, "elapsed_time": "1 day, 3:43:44", "remaining_time": "1 day, 5:47:45"}
|
| 881 |
+
{"current_steps": 4405, "total_steps": 9128, "loss": 0.1743, "lr": 2.467169614285242e-05, "epoch": 3.3782125047947833, "percentage": 48.26, "elapsed_time": "1 day, 3:46:22", "remaining_time": "1 day, 5:46:40"}
|
| 882 |
+
{"current_steps": 4410, "total_steps": 9128, "loss": 0.1573, "lr": 2.463450338922234e-05, "epoch": 3.38204833141542, "percentage": 48.31, "elapsed_time": "1 day, 3:47:38", "remaining_time": "1 day, 5:44:06"}
|
| 883 |
+
{"current_steps": 4415, "total_steps": 9128, "loss": 0.1555, "lr": 2.4597293691133918e-05, "epoch": 3.3858841580360566, "percentage": 48.37, "elapsed_time": "1 day, 3:48:55", "remaining_time": "1 day, 5:41:34"}
|
| 884 |
+
{"current_steps": 4420, "total_steps": 9128, "loss": 0.1683, "lr": 2.4560067184631555e-05, "epoch": 3.3897199846566934, "percentage": 48.42, "elapsed_time": "1 day, 3:50:11", "remaining_time": "1 day, 5:39:01"}
|