Training in progress, step 5000
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 sha256:93829e6a5cbfe8dfd3d58c711f65f6acf05777fe45c9303c210a83871ff95a41
|
| 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:d04b6d9dfb40ae04501f5d7fe72789c1c23c9fe6a2cfae060d26c9a4bf3d522c
|
| 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:eda937b9dfdc78695884bc5abafa957be79f488756d574fa07162ba4ef893181
|
| 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:b573c29bc6c9a070cb0ba1d8858d2f0ecf45f0bb1935cc789e0bcde532c4b2a8
|
| 3 |
size 1580230264
|
trainer_log.jsonl
CHANGED
|
@@ -981,3 +981,43 @@
|
|
| 981 |
{"current_steps": 4790, "total_steps": 6713, "loss": 0.2103, "lr": 9.203495164802027e-06, "epoch": 4.9963484611371936, "percentage": 71.35, "elapsed_time": "13:12:42", "remaining_time": "5:18:14"}
|
| 982 |
{"current_steps": 4795, "total_steps": 6713, "loss": 0.1863, "lr": 9.159755503480345e-06, "epoch": 5.001043296817945, "percentage": 71.43, "elapsed_time": "13:14:40", "remaining_time": "5:17:52"}
|
| 983 |
{"current_steps": 4800, "total_steps": 6713, "loss": 0.1582, "lr": 9.116089134891532e-06, "epoch": 5.006259780907668, "percentage": 71.5, "elapsed_time": "13:17:37", "remaining_time": "5:17:53"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 981 |
{"current_steps": 4790, "total_steps": 6713, "loss": 0.2103, "lr": 9.203495164802027e-06, "epoch": 4.9963484611371936, "percentage": 71.35, "elapsed_time": "13:12:42", "remaining_time": "5:18:14"}
|
| 982 |
{"current_steps": 4795, "total_steps": 6713, "loss": 0.1863, "lr": 9.159755503480345e-06, "epoch": 5.001043296817945, "percentage": 71.43, "elapsed_time": "13:14:40", "remaining_time": "5:17:52"}
|
| 983 |
{"current_steps": 4800, "total_steps": 6713, "loss": 0.1582, "lr": 9.116089134891532e-06, "epoch": 5.006259780907668, "percentage": 71.5, "elapsed_time": "13:17:37", "remaining_time": "5:17:53"}
|
| 984 |
+
{"current_steps": 4805, "total_steps": 6713, "loss": 0.1547, "lr": 9.072496354271307e-06, "epoch": 5.011476264997392, "percentage": 71.58, "elapsed_time": "13:21:53", "remaining_time": "5:18:25"}
|
| 985 |
+
{"current_steps": 4810, "total_steps": 6713, "loss": 0.1492, "lr": 9.028977456357872e-06, "epoch": 5.016692749087115, "percentage": 71.65, "elapsed_time": "13:24:46", "remaining_time": "5:18:23"}
|
| 986 |
+
{"current_steps": 4815, "total_steps": 6713, "loss": 0.1489, "lr": 8.985532735389873e-06, "epoch": 5.021909233176839, "percentage": 71.73, "elapsed_time": "13:27:39", "remaining_time": "5:18:21"}
|
| 987 |
+
{"current_steps": 4820, "total_steps": 6713, "loss": 0.1646, "lr": 8.942162485104436e-06, "epoch": 5.027125717266562, "percentage": 71.8, "elapsed_time": "13:30:31", "remaining_time": "5:18:19"}
|
| 988 |
+
{"current_steps": 4825, "total_steps": 6713, "loss": 0.1585, "lr": 8.898866998735195e-06, "epoch": 5.032342201356286, "percentage": 71.88, "elapsed_time": "13:33:33", "remaining_time": "5:18:20"}
|
| 989 |
+
{"current_steps": 4830, "total_steps": 6713, "loss": 0.1483, "lr": 8.85564656901028e-06, "epoch": 5.037558685446009, "percentage": 71.95, "elapsed_time": "13:36:31", "remaining_time": "5:18:19"}
|
| 990 |
+
{"current_steps": 4835, "total_steps": 6713, "loss": 0.1773, "lr": 8.81250148815035e-06, "epoch": 5.042775169535733, "percentage": 72.02, "elapsed_time": "13:39:09", "remaining_time": "5:18:10"}
|
| 991 |
+
{"current_steps": 4840, "total_steps": 6713, "loss": 0.1491, "lr": 8.769432047866608e-06, "epoch": 5.0479916536254565, "percentage": 72.1, "elapsed_time": "13:42:07", "remaining_time": "5:18:08"}
|
| 992 |
+
{"current_steps": 4845, "total_steps": 6713, "loss": 0.1599, "lr": 8.72643853935887e-06, "epoch": 5.05320813771518, "percentage": 72.17, "elapsed_time": "13:45:12", "remaining_time": "5:18:09"}
|
| 993 |
+
{"current_steps": 4850, "total_steps": 6713, "loss": 0.1473, "lr": 8.683521253313527e-06, "epoch": 5.058424621804903, "percentage": 72.25, "elapsed_time": "13:47:57", "remaining_time": "5:18:02"}
|
| 994 |
+
{"current_steps": 4855, "total_steps": 6713, "loss": 0.1566, "lr": 8.640680479901648e-06, "epoch": 5.063641105894627, "percentage": 72.32, "elapsed_time": "13:50:53", "remaining_time": "5:17:58"}
|
| 995 |
+
{"current_steps": 4860, "total_steps": 6713, "loss": 0.1433, "lr": 8.597916508776958e-06, "epoch": 5.068857589984351, "percentage": 72.4, "elapsed_time": "13:53:55", "remaining_time": "5:17:57"}
|
| 996 |
+
{"current_steps": 4865, "total_steps": 6713, "loss": 0.1428, "lr": 8.55522962907394e-06, "epoch": 5.074074074074074, "percentage": 72.47, "elapsed_time": "13:56:45", "remaining_time": "5:17:50"}
|
| 997 |
+
{"current_steps": 4870, "total_steps": 6713, "loss": 0.1412, "lr": 8.512620129405816e-06, "epoch": 5.079290558163797, "percentage": 72.55, "elapsed_time": "13:59:35", "remaining_time": "5:17:43"}
|
| 998 |
+
{"current_steps": 4875, "total_steps": 6713, "loss": 0.1534, "lr": 8.470088297862669e-06, "epoch": 5.084507042253521, "percentage": 72.62, "elapsed_time": "14:02:31", "remaining_time": "5:17:39"}
|
| 999 |
+
{"current_steps": 4880, "total_steps": 6713, "loss": 0.1483, "lr": 8.427634422009399e-06, "epoch": 5.089723526343245, "percentage": 72.69, "elapsed_time": "14:05:21", "remaining_time": "5:17:31"}
|
| 1000 |
+
{"current_steps": 4885, "total_steps": 6713, "loss": 0.1333, "lr": 8.385258788883889e-06, "epoch": 5.0949400104329685, "percentage": 72.77, "elapsed_time": "14:08:27", "remaining_time": "5:17:30"}
|
| 1001 |
+
{"current_steps": 4890, "total_steps": 6713, "loss": 0.142, "lr": 8.342961684994975e-06, "epoch": 5.100156494522691, "percentage": 72.84, "elapsed_time": "14:11:26", "remaining_time": "5:17:24"}
|
| 1002 |
+
{"current_steps": 4895, "total_steps": 6713, "loss": 0.1599, "lr": 8.300743396320566e-06, "epoch": 5.105372978612415, "percentage": 72.92, "elapsed_time": "14:14:27", "remaining_time": "5:17:20"}
|
| 1003 |
+
{"current_steps": 4900, "total_steps": 6713, "loss": 0.1624, "lr": 8.25860420830567e-06, "epoch": 5.110589462702139, "percentage": 72.99, "elapsed_time": "14:17:24", "remaining_time": "5:17:14"}
|
| 1004 |
+
{"current_steps": 4905, "total_steps": 6713, "loss": 0.144, "lr": 8.216544405860482e-06, "epoch": 5.115805946791863, "percentage": 73.07, "elapsed_time": "14:20:18", "remaining_time": "5:17:06"}
|
| 1005 |
+
{"current_steps": 4910, "total_steps": 6713, "loss": 0.1516, "lr": 8.17456427335848e-06, "epoch": 5.1210224308815855, "percentage": 73.14, "elapsed_time": "14:23:18", "remaining_time": "5:17:01"}
|
| 1006 |
+
{"current_steps": 4915, "total_steps": 6713, "loss": 0.1646, "lr": 8.132664094634452e-06, "epoch": 5.126238914971309, "percentage": 73.22, "elapsed_time": "14:26:13", "remaining_time": "5:16:52"}
|
| 1007 |
+
{"current_steps": 4920, "total_steps": 6713, "loss": 0.1837, "lr": 8.090844152982628e-06, "epoch": 5.131455399061033, "percentage": 73.29, "elapsed_time": "14:29:14", "remaining_time": "5:16:46"}
|
| 1008 |
+
{"current_steps": 4925, "total_steps": 6713, "loss": 0.1716, "lr": 8.049104731154722e-06, "epoch": 5.136671883150757, "percentage": 73.37, "elapsed_time": "14:32:17", "remaining_time": "5:16:40"}
|
| 1009 |
+
{"current_steps": 4930, "total_steps": 6713, "loss": 0.1521, "lr": 8.007446111358066e-06, "epoch": 5.14188836724048, "percentage": 73.44, "elapsed_time": "14:35:23", "remaining_time": "5:16:35"}
|
| 1010 |
+
{"current_steps": 4935, "total_steps": 6713, "loss": 0.1524, "lr": 7.965868575253632e-06, "epoch": 5.147104851330203, "percentage": 73.51, "elapsed_time": "14:38:27", "remaining_time": "5:16:29"}
|
| 1011 |
+
{"current_steps": 4940, "total_steps": 6713, "loss": 0.1591, "lr": 7.92437240395422e-06, "epoch": 5.152321335419927, "percentage": 73.59, "elapsed_time": "14:41:26", "remaining_time": "5:16:21"}
|
| 1012 |
+
{"current_steps": 4945, "total_steps": 6713, "loss": 0.1543, "lr": 7.882957878022472e-06, "epoch": 5.157537819509651, "percentage": 73.66, "elapsed_time": "14:44:23", "remaining_time": "5:16:12"}
|
| 1013 |
+
{"current_steps": 4950, "total_steps": 6713, "loss": 0.1557, "lr": 7.841625277469043e-06, "epoch": 5.162754303599374, "percentage": 73.74, "elapsed_time": "14:47:31", "remaining_time": "5:16:06"}
|
| 1014 |
+
{"current_steps": 4955, "total_steps": 6713, "loss": 0.1627, "lr": 7.800374881750644e-06, "epoch": 5.1679707876890975, "percentage": 73.81, "elapsed_time": "14:50:36", "remaining_time": "5:15:58"}
|
| 1015 |
+
{"current_steps": 4960, "total_steps": 6713, "loss": 0.1566, "lr": 7.759206969768216e-06, "epoch": 5.173187271778821, "percentage": 73.89, "elapsed_time": "14:53:34", "remaining_time": "5:15:48"}
|
| 1016 |
+
{"current_steps": 4965, "total_steps": 6713, "loss": 0.1412, "lr": 7.718121819864983e-06, "epoch": 5.178403755868545, "percentage": 73.96, "elapsed_time": "14:56:29", "remaining_time": "5:15:37"}
|
| 1017 |
+
{"current_steps": 4970, "total_steps": 6713, "loss": 0.1362, "lr": 7.677119709824635e-06, "epoch": 5.183620239958268, "percentage": 74.04, "elapsed_time": "14:59:37", "remaining_time": "5:15:29"}
|
| 1018 |
+
{"current_steps": 4975, "total_steps": 6713, "loss": 0.1627, "lr": 7.636200916869387e-06, "epoch": 5.188836724047992, "percentage": 74.11, "elapsed_time": "15:02:40", "remaining_time": "5:15:20"}
|
| 1019 |
+
{"current_steps": 4980, "total_steps": 6713, "loss": 0.1582, "lr": 7.595365717658143e-06, "epoch": 5.194053208137715, "percentage": 74.18, "elapsed_time": "15:05:34", "remaining_time": "5:15:07"}
|
| 1020 |
+
{"current_steps": 4985, "total_steps": 6713, "loss": 0.1503, "lr": 7.554614388284609e-06, "epoch": 5.199269692227439, "percentage": 74.26, "elapsed_time": "15:08:33", "remaining_time": "5:14:56"}
|
| 1021 |
+
{"current_steps": 4990, "total_steps": 6713, "loss": 0.1523, "lr": 7.513947204275453e-06, "epoch": 5.204486176317162, "percentage": 74.33, "elapsed_time": "15:11:18", "remaining_time": "5:14:39"}
|
| 1022 |
+
{"current_steps": 4995, "total_steps": 6713, "loss": 0.1411, "lr": 7.473364440588404e-06, "epoch": 5.209702660406886, "percentage": 74.41, "elapsed_time": "15:14:17", "remaining_time": "5:14:27"}
|
| 1023 |
+
{"current_steps": 5000, "total_steps": 6713, "loss": 0.1531, "lr": 7.432866371610403e-06, "epoch": 5.214919144496609, "percentage": 74.48, "elapsed_time": "15:17:12", "remaining_time": "5:14:14"}
|