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 sha256:792992549bc7d3644b538e5a3ed3c71ba5b5c000bcfcf68070311573fe87f006
|
| 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 sha256:38417203f8b83879d0abf7861950ddd02674ba0484eeb13cb035ab44c767eb0d
|
| 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 sha256:69165d5c2b797a12518ee45117ed4b34aab95805c2e6bb13824692c41edb60fe
|
| 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 sha256:8b05809d9bf678dc4641f69e5255834e349246ed83421a7eb6b39ae259ef2aed
|
| 3 |
size 1580230264
|
trainer_log.jsonl
CHANGED
|
@@ -958,3 +958,43 @@
|
|
| 958 |
{"current_steps": 4790, "total_steps": 6713, "loss": 0.175, "lr": 9.203495164802027e-06, "epoch": 4.9963484611371936, "percentage": 71.35, "elapsed_time": "20:13:02", "remaining_time": "8:06:59"}
|
| 959 |
{"current_steps": 4795, "total_steps": 6713, "loss": 0.183, "lr": 9.159755503480345e-06, "epoch": 5.001043296817945, "percentage": 71.43, "elapsed_time": "20:15:08", "remaining_time": "8:06:03"}
|
| 960 |
{"current_steps": 4800, "total_steps": 6713, "loss": 0.1824, "lr": 9.116089134891532e-06, "epoch": 5.006259780907668, "percentage": 71.5, "elapsed_time": "20:17:42", "remaining_time": "8:05:18"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 958 |
{"current_steps": 4790, "total_steps": 6713, "loss": 0.175, "lr": 9.203495164802027e-06, "epoch": 4.9963484611371936, "percentage": 71.35, "elapsed_time": "20:13:02", "remaining_time": "8:06:59"}
|
| 959 |
{"current_steps": 4795, "total_steps": 6713, "loss": 0.183, "lr": 9.159755503480345e-06, "epoch": 5.001043296817945, "percentage": 71.43, "elapsed_time": "20:15:08", "remaining_time": "8:06:03"}
|
| 960 |
{"current_steps": 4800, "total_steps": 6713, "loss": 0.1824, "lr": 9.116089134891532e-06, "epoch": 5.006259780907668, "percentage": 71.5, "elapsed_time": "20:17:42", "remaining_time": "8:05:18"}
|
| 961 |
+
{"current_steps": 4805, "total_steps": 6713, "loss": 0.18, "lr": 9.072496354271307e-06, "epoch": 5.011476264997392, "percentage": 71.58, "elapsed_time": "20:21:43", "remaining_time": "8:05:07"}
|
| 962 |
+
{"current_steps": 4810, "total_steps": 6713, "loss": 0.1696, "lr": 9.028977456357872e-06, "epoch": 5.016692749087115, "percentage": 71.65, "elapsed_time": "20:24:35", "remaining_time": "8:04:29"}
|
| 963 |
+
{"current_steps": 4815, "total_steps": 6713, "loss": 0.1756, "lr": 8.985532735389873e-06, "epoch": 5.021909233176839, "percentage": 71.73, "elapsed_time": "20:27:20", "remaining_time": "8:03:47"}
|
| 964 |
+
{"current_steps": 4820, "total_steps": 6713, "loss": 0.1737, "lr": 8.942162485104436e-06, "epoch": 5.027125717266562, "percentage": 71.8, "elapsed_time": "20:29:58", "remaining_time": "8:03:03"}
|
| 965 |
+
{"current_steps": 4825, "total_steps": 6713, "loss": 0.1844, "lr": 8.898866998735195e-06, "epoch": 5.032342201356286, "percentage": 71.88, "elapsed_time": "20:32:48", "remaining_time": "8:02:23"}
|
| 966 |
+
{"current_steps": 4830, "total_steps": 6713, "loss": 0.2003, "lr": 8.85564656901028e-06, "epoch": 5.037558685446009, "percentage": 71.95, "elapsed_time": "20:35:32", "remaining_time": "8:01:41"}
|
| 967 |
+
{"current_steps": 4835, "total_steps": 6713, "loss": 0.1722, "lr": 8.81250148815035e-06, "epoch": 5.042775169535733, "percentage": 72.02, "elapsed_time": "20:38:17", "remaining_time": "8:00:58"}
|
| 968 |
+
{"current_steps": 4840, "total_steps": 6713, "loss": 0.1759, "lr": 8.769432047866608e-06, "epoch": 5.0479916536254565, "percentage": 72.1, "elapsed_time": "20:41:12", "remaining_time": "8:00:19"}
|
| 969 |
+
{"current_steps": 4845, "total_steps": 6713, "loss": 0.1662, "lr": 8.72643853935887e-06, "epoch": 5.05320813771518, "percentage": 72.17, "elapsed_time": "20:44:04", "remaining_time": "7:59:39"}
|
| 970 |
+
{"current_steps": 4850, "total_steps": 6713, "loss": 0.1683, "lr": 8.683521253313527e-06, "epoch": 5.058424621804903, "percentage": 72.25, "elapsed_time": "20:46:59", "remaining_time": "7:59:00"}
|
| 971 |
+
{"current_steps": 4855, "total_steps": 6713, "loss": 0.1754, "lr": 8.640680479901648e-06, "epoch": 5.063641105894627, "percentage": 72.32, "elapsed_time": "20:49:47", "remaining_time": "7:58:17"}
|
| 972 |
+
{"current_steps": 4860, "total_steps": 6713, "loss": 0.1736, "lr": 8.597916508776958e-06, "epoch": 5.068857589984351, "percentage": 72.4, "elapsed_time": "20:52:36", "remaining_time": "7:57:35"}
|
| 973 |
+
{"current_steps": 4865, "total_steps": 6713, "loss": 0.1769, "lr": 8.55522962907394e-06, "epoch": 5.074074074074074, "percentage": 72.47, "elapsed_time": "20:55:11", "remaining_time": "7:56:47"}
|
| 974 |
+
{"current_steps": 4870, "total_steps": 6713, "loss": 0.1727, "lr": 8.512620129405816e-06, "epoch": 5.079290558163797, "percentage": 72.55, "elapsed_time": "20:57:50", "remaining_time": "7:56:00"}
|
| 975 |
+
{"current_steps": 4875, "total_steps": 6713, "loss": 0.1748, "lr": 8.470088297862669e-06, "epoch": 5.084507042253521, "percentage": 72.62, "elapsed_time": "21:00:38", "remaining_time": "7:55:17"}
|
| 976 |
+
{"current_steps": 4880, "total_steps": 6713, "loss": 0.1691, "lr": 8.427634422009399e-06, "epoch": 5.089723526343245, "percentage": 72.69, "elapsed_time": "21:03:20", "remaining_time": "7:54:31"}
|
| 977 |
+
{"current_steps": 4885, "total_steps": 6713, "loss": 0.167, "lr": 8.385258788883889e-06, "epoch": 5.0949400104329685, "percentage": 72.77, "elapsed_time": "21:05:55", "remaining_time": "7:53:43"}
|
| 978 |
+
{"current_steps": 4890, "total_steps": 6713, "loss": 0.1868, "lr": 8.342961684994975e-06, "epoch": 5.100156494522691, "percentage": 72.84, "elapsed_time": "21:08:28", "remaining_time": "7:52:53"}
|
| 979 |
+
{"current_steps": 4895, "total_steps": 6713, "loss": 0.1695, "lr": 8.300743396320566e-06, "epoch": 5.105372978612415, "percentage": 72.92, "elapsed_time": "21:11:15", "remaining_time": "7:52:08"}
|
| 980 |
+
{"current_steps": 4900, "total_steps": 6713, "loss": 0.1843, "lr": 8.25860420830567e-06, "epoch": 5.110589462702139, "percentage": 72.99, "elapsed_time": "21:13:56", "remaining_time": "7:51:21"}
|
| 981 |
+
{"current_steps": 4905, "total_steps": 6713, "loss": 0.1784, "lr": 8.216544405860482e-06, "epoch": 5.115805946791863, "percentage": 73.07, "elapsed_time": "21:16:41", "remaining_time": "7:50:35"}
|
| 982 |
+
{"current_steps": 4910, "total_steps": 6713, "loss": 0.173, "lr": 8.17456427335848e-06, "epoch": 5.1210224308815855, "percentage": 73.14, "elapsed_time": "21:19:23", "remaining_time": "7:49:48"}
|
| 983 |
+
{"current_steps": 4915, "total_steps": 6713, "loss": 0.1774, "lr": 8.132664094634452e-06, "epoch": 5.126238914971309, "percentage": 73.22, "elapsed_time": "21:22:06", "remaining_time": "7:49:01"}
|
| 984 |
+
{"current_steps": 4920, "total_steps": 6713, "loss": 0.1748, "lr": 8.090844152982628e-06, "epoch": 5.131455399061033, "percentage": 73.29, "elapsed_time": "21:24:47", "remaining_time": "7:48:13"}
|
| 985 |
+
{"current_steps": 4925, "total_steps": 6713, "loss": 0.183, "lr": 8.049104731154722e-06, "epoch": 5.136671883150757, "percentage": 73.37, "elapsed_time": "21:27:25", "remaining_time": "7:47:23"}
|
| 986 |
+
{"current_steps": 4930, "total_steps": 6713, "loss": 0.1723, "lr": 8.007446111358066e-06, "epoch": 5.14188836724048, "percentage": 73.44, "elapsed_time": "21:30:03", "remaining_time": "7:46:34"}
|
| 987 |
+
{"current_steps": 4935, "total_steps": 6713, "loss": 0.1662, "lr": 7.965868575253632e-06, "epoch": 5.147104851330203, "percentage": 73.51, "elapsed_time": "21:32:59", "remaining_time": "7:45:50"}
|
| 988 |
+
{"current_steps": 4940, "total_steps": 6713, "loss": 0.1701, "lr": 7.92437240395422e-06, "epoch": 5.152321335419927, "percentage": 73.59, "elapsed_time": "21:35:37", "remaining_time": "7:45:00"}
|
| 989 |
+
{"current_steps": 4945, "total_steps": 6713, "loss": 0.17, "lr": 7.882957878022472e-06, "epoch": 5.157537819509651, "percentage": 73.66, "elapsed_time": "21:38:25", "remaining_time": "7:44:13"}
|
| 990 |
+
{"current_steps": 4950, "total_steps": 6713, "loss": 0.176, "lr": 7.841625277469043e-06, "epoch": 5.162754303599374, "percentage": 73.74, "elapsed_time": "21:41:05", "remaining_time": "7:43:23"}
|
| 991 |
+
{"current_steps": 4955, "total_steps": 6713, "loss": 0.1743, "lr": 7.800374881750644e-06, "epoch": 5.1679707876890975, "percentage": 73.81, "elapsed_time": "21:43:48", "remaining_time": "7:42:35"}
|
| 992 |
+
{"current_steps": 4960, "total_steps": 6713, "loss": 0.1661, "lr": 7.759206969768216e-06, "epoch": 5.173187271778821, "percentage": 73.89, "elapsed_time": "21:46:33", "remaining_time": "7:41:46"}
|
| 993 |
+
{"current_steps": 4965, "total_steps": 6713, "loss": 0.1705, "lr": 7.718121819864983e-06, "epoch": 5.178403755868545, "percentage": 73.96, "elapsed_time": "21:49:19", "remaining_time": "7:40:57"}
|
| 994 |
+
{"current_steps": 4970, "total_steps": 6713, "loss": 0.1736, "lr": 7.677119709824635e-06, "epoch": 5.183620239958268, "percentage": 74.04, "elapsed_time": "21:52:16", "remaining_time": "7:40:13"}
|
| 995 |
+
{"current_steps": 4975, "total_steps": 6713, "loss": 0.1677, "lr": 7.636200916869387e-06, "epoch": 5.188836724047992, "percentage": 74.11, "elapsed_time": "21:54:57", "remaining_time": "7:39:22"}
|
| 996 |
+
{"current_steps": 4980, "total_steps": 6713, "loss": 0.1844, "lr": 7.595365717658143e-06, "epoch": 5.194053208137715, "percentage": 74.18, "elapsed_time": "21:57:48", "remaining_time": "7:38:35"}
|
| 997 |
+
{"current_steps": 4985, "total_steps": 6713, "loss": 0.1851, "lr": 7.554614388284609e-06, "epoch": 5.199269692227439, "percentage": 74.26, "elapsed_time": "22:00:25", "remaining_time": "7:37:42"}
|
| 998 |
+
{"current_steps": 4990, "total_steps": 6713, "loss": 0.183, "lr": 7.513947204275453e-06, "epoch": 5.204486176317162, "percentage": 74.33, "elapsed_time": "22:03:06", "remaining_time": "7:36:51"}
|
| 999 |
+
{"current_steps": 4995, "total_steps": 6713, "loss": 0.172, "lr": 7.473364440588404e-06, "epoch": 5.209702660406886, "percentage": 74.41, "elapsed_time": "22:05:42", "remaining_time": "7:35:58"}
|
| 1000 |
+
{"current_steps": 5000, "total_steps": 6713, "loss": 0.171, "lr": 7.432866371610403e-06, "epoch": 5.214919144496609, "percentage": 74.48, "elapsed_time": "22:08:34", "remaining_time": "7:35:10"}
|