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 sha256:7a7a7cc06a73c8bb971864a06b6b82eee03e192e4f8773ff71c07b45132df4d4
|
| 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 sha256:6925ac51b01a679c215d8854672e1bac4de9b6ac5405ba4b1fafac6e3696a083
|
| 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 sha256:125fdf4814fdf6ad7c217028b241b16bc9171571f0df59178e9617fca0325c1c
|
| 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:fe6ca5f2afc5c6402fe52855ac202edc153133e8d4c23ba1888dc32226a01b8b
|
| 3 |
size 1580230264
|
trainer_log.jsonl
CHANGED
|
@@ -963,3 +963,43 @@
|
|
| 963 |
{"current_steps": 4790, "total_steps": 6188, "loss": 0.0799, "lr": 5.911817481900832e-06, "epoch": 5.419920769666101, "percentage": 77.41, "elapsed_time": "12:20:40", "remaining_time": "3:36:10"}
|
| 964 |
{"current_steps": 4795, "total_steps": 6188, "loss": 0.0697, "lr": 5.871832560305573e-06, "epoch": 5.425580079230334, "percentage": 77.49, "elapsed_time": "12:22:24", "remaining_time": "3:35:40"}
|
| 965 |
{"current_steps": 4800, "total_steps": 6188, "loss": 0.0614, "lr": 5.831960039888533e-06, "epoch": 5.431239388794567, "percentage": 77.57, "elapsed_time": "12:24:03", "remaining_time": "3:35:09"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 963 |
{"current_steps": 4790, "total_steps": 6188, "loss": 0.0799, "lr": 5.911817481900832e-06, "epoch": 5.419920769666101, "percentage": 77.41, "elapsed_time": "12:20:40", "remaining_time": "3:36:10"}
|
| 964 |
{"current_steps": 4795, "total_steps": 6188, "loss": 0.0697, "lr": 5.871832560305573e-06, "epoch": 5.425580079230334, "percentage": 77.49, "elapsed_time": "12:22:24", "remaining_time": "3:35:40"}
|
| 965 |
{"current_steps": 4800, "total_steps": 6188, "loss": 0.0614, "lr": 5.831960039888533e-06, "epoch": 5.431239388794567, "percentage": 77.57, "elapsed_time": "12:24:03", "remaining_time": "3:35:09"}
|
| 966 |
+
{"current_steps": 4805, "total_steps": 6188, "loss": 0.0828, "lr": 5.792200237868361e-06, "epoch": 5.4368986983588, "percentage": 77.65, "elapsed_time": "12:27:02", "remaining_time": "3:35:01"}
|
| 967 |
+
{"current_steps": 4810, "total_steps": 6188, "loss": 0.0697, "lr": 5.752553470566957e-06, "epoch": 5.442558007923034, "percentage": 77.73, "elapsed_time": "12:28:47", "remaining_time": "3:34:31"}
|
| 968 |
+
{"current_steps": 4815, "total_steps": 6188, "loss": 0.0982, "lr": 5.713020053406917e-06, "epoch": 5.448217317487266, "percentage": 77.81, "elapsed_time": "12:30:34", "remaining_time": "3:34:01"}
|
| 969 |
+
{"current_steps": 4820, "total_steps": 6188, "loss": 0.0837, "lr": 5.673600300909053e-06, "epoch": 5.4538766270515, "percentage": 77.89, "elapsed_time": "12:32:14", "remaining_time": "3:33:29"}
|
| 970 |
+
{"current_steps": 4825, "total_steps": 6188, "loss": 0.0885, "lr": 5.634294526689872e-06, "epoch": 5.459535936615733, "percentage": 77.97, "elapsed_time": "12:33:50", "remaining_time": "3:32:56"}
|
| 971 |
+
{"current_steps": 4830, "total_steps": 6188, "loss": 0.0677, "lr": 5.595103043459109e-06, "epoch": 5.465195246179966, "percentage": 78.05, "elapsed_time": "12:35:21", "remaining_time": "3:32:22"}
|
| 972 |
+
{"current_steps": 4835, "total_steps": 6188, "loss": 0.0772, "lr": 5.556026163017205e-06, "epoch": 5.470854555744199, "percentage": 78.14, "elapsed_time": "12:36:58", "remaining_time": "3:31:49"}
|
| 973 |
+
{"current_steps": 4840, "total_steps": 6188, "loss": 0.0732, "lr": 5.517064196252837e-06, "epoch": 5.476513865308433, "percentage": 78.22, "elapsed_time": "12:38:27", "remaining_time": "3:31:14"}
|
| 974 |
+
{"current_steps": 4845, "total_steps": 6188, "loss": 0.0985, "lr": 5.478217453140471e-06, "epoch": 5.482173174872665, "percentage": 78.3, "elapsed_time": "12:40:21", "remaining_time": "3:30:45"}
|
| 975 |
+
{"current_steps": 4850, "total_steps": 6188, "loss": 0.1005, "lr": 5.439486242737855e-06, "epoch": 5.487832484436899, "percentage": 78.38, "elapsed_time": "12:42:25", "remaining_time": "3:30:20"}
|
| 976 |
+
{"current_steps": 4855, "total_steps": 6188, "loss": 0.0794, "lr": 5.400870873183583e-06, "epoch": 5.493491794001132, "percentage": 78.46, "elapsed_time": "12:44:18", "remaining_time": "3:29:50"}
|
| 977 |
+
{"current_steps": 4860, "total_steps": 6188, "loss": 0.0752, "lr": 5.362371651694647e-06, "epoch": 5.499151103565365, "percentage": 78.54, "elapsed_time": "12:45:51", "remaining_time": "3:29:16"}
|
| 978 |
+
{"current_steps": 4865, "total_steps": 6188, "loss": 0.0736, "lr": 5.323988884563975e-06, "epoch": 5.504810413129598, "percentage": 78.62, "elapsed_time": "12:47:24", "remaining_time": "3:28:41"}
|
| 979 |
+
{"current_steps": 4870, "total_steps": 6188, "loss": 0.0652, "lr": 5.2857228771580105e-06, "epoch": 5.5104697226938315, "percentage": 78.7, "elapsed_time": "12:48:55", "remaining_time": "3:28:06"}
|
| 980 |
+
{"current_steps": 4875, "total_steps": 6188, "loss": 0.0759, "lr": 5.247573933914285e-06, "epoch": 5.516129032258064, "percentage": 78.78, "elapsed_time": "12:50:25", "remaining_time": "3:27:30"}
|
| 981 |
+
{"current_steps": 4880, "total_steps": 6188, "loss": 0.0752, "lr": 5.20954235833898e-06, "epoch": 5.5217883418222975, "percentage": 78.86, "elapsed_time": "12:51:58", "remaining_time": "3:26:54"}
|
| 982 |
+
{"current_steps": 4885, "total_steps": 6188, "loss": 0.0694, "lr": 5.171628453004512e-06, "epoch": 5.527447651386531, "percentage": 78.94, "elapsed_time": "12:53:31", "remaining_time": "3:26:19"}
|
| 983 |
+
{"current_steps": 4890, "total_steps": 6188, "loss": 0.0676, "lr": 5.133832519547155e-06, "epoch": 5.533106960950764, "percentage": 79.02, "elapsed_time": "12:55:08", "remaining_time": "3:25:45"}
|
| 984 |
+
{"current_steps": 4895, "total_steps": 6188, "loss": 0.0763, "lr": 5.096154858664608e-06, "epoch": 5.538766270514997, "percentage": 79.1, "elapsed_time": "12:56:45", "remaining_time": "3:25:10"}
|
| 985 |
+
{"current_steps": 4900, "total_steps": 6188, "loss": 0.0659, "lr": 5.058595770113606e-06, "epoch": 5.54442558007923, "percentage": 79.19, "elapsed_time": "12:58:49", "remaining_time": "3:24:43"}
|
| 986 |
+
{"current_steps": 4905, "total_steps": 6188, "loss": 0.0702, "lr": 5.0211555527075664e-06, "epoch": 5.550084889643464, "percentage": 79.27, "elapsed_time": "13:00:34", "remaining_time": "3:24:10"}
|
| 987 |
+
{"current_steps": 4910, "total_steps": 6188, "loss": 0.0755, "lr": 4.9838345043141665e-06, "epoch": 5.555744199207696, "percentage": 79.35, "elapsed_time": "13:02:40", "remaining_time": "3:23:43"}
|
| 988 |
+
{"current_steps": 4915, "total_steps": 6188, "loss": 0.1574, "lr": 4.946632921853009e-06, "epoch": 5.56140350877193, "percentage": 79.43, "elapsed_time": "13:05:21", "remaining_time": "3:23:24"}
|
| 989 |
+
{"current_steps": 4920, "total_steps": 6188, "loss": 0.0703, "lr": 4.909551101293238e-06, "epoch": 5.567062818336163, "percentage": 79.51, "elapsed_time": "13:07:02", "remaining_time": "3:22:50"}
|
| 990 |
+
{"current_steps": 4925, "total_steps": 6188, "loss": 0.0701, "lr": 4.872589337651208e-06, "epoch": 5.572722127900396, "percentage": 79.59, "elapsed_time": "13:08:47", "remaining_time": "3:22:16"}
|
| 991 |
+
{"current_steps": 4930, "total_steps": 6188, "loss": 0.1065, "lr": 4.835747924988105e-06, "epoch": 5.578381437464629, "percentage": 79.67, "elapsed_time": "13:10:54", "remaining_time": "3:21:49"}
|
| 992 |
+
{"current_steps": 4935, "total_steps": 6188, "loss": 0.1613, "lr": 4.799027156407632e-06, "epoch": 5.584040747028863, "percentage": 79.75, "elapsed_time": "13:13:54", "remaining_time": "3:21:34"}
|
| 993 |
+
{"current_steps": 4940, "total_steps": 6188, "loss": 0.1543, "lr": 4.7624273240536756e-06, "epoch": 5.589700056593095, "percentage": 79.83, "elapsed_time": "13:16:51", "remaining_time": "3:21:18"}
|
| 994 |
+
{"current_steps": 4945, "total_steps": 6188, "loss": 0.1453, "lr": 4.725948719107965e-06, "epoch": 5.595359366157329, "percentage": 79.91, "elapsed_time": "13:19:50", "remaining_time": "3:21:03"}
|
| 995 |
+
{"current_steps": 4950, "total_steps": 6188, "loss": 0.144, "lr": 4.6895916317877624e-06, "epoch": 5.601018675721562, "percentage": 79.99, "elapsed_time": "13:22:46", "remaining_time": "3:20:46"}
|
| 996 |
+
{"current_steps": 4955, "total_steps": 6188, "loss": 0.1579, "lr": 4.653356351343577e-06, "epoch": 5.6066779852857955, "percentage": 80.07, "elapsed_time": "13:25:42", "remaining_time": "3:20:29"}
|
| 997 |
+
{"current_steps": 4960, "total_steps": 6188, "loss": 0.1527, "lr": 4.617243166056826e-06, "epoch": 5.612337294850028, "percentage": 80.16, "elapsed_time": "13:28:47", "remaining_time": "3:20:14"}
|
| 998 |
+
{"current_steps": 4965, "total_steps": 6188, "loss": 0.1442, "lr": 4.581252363237567e-06, "epoch": 5.6179966044142615, "percentage": 80.24, "elapsed_time": "13:31:45", "remaining_time": "3:19:57"}
|
| 999 |
+
{"current_steps": 4970, "total_steps": 6188, "loss": 0.1615, "lr": 4.545384229222196e-06, "epoch": 5.623655913978495, "percentage": 80.32, "elapsed_time": "13:34:33", "remaining_time": "3:19:37"}
|
| 1000 |
+
{"current_steps": 4975, "total_steps": 6188, "loss": 0.1462, "lr": 4.509639049371193e-06, "epoch": 5.6293152235427275, "percentage": 80.4, "elapsed_time": "13:37:32", "remaining_time": "3:19:20"}
|
| 1001 |
+
{"current_steps": 4980, "total_steps": 6188, "loss": 0.1472, "lr": 4.474017108066828e-06, "epoch": 5.634974533106961, "percentage": 80.48, "elapsed_time": "13:40:34", "remaining_time": "3:19:02"}
|
| 1002 |
+
{"current_steps": 4985, "total_steps": 6188, "loss": 0.1524, "lr": 4.438518688710898e-06, "epoch": 5.640633842671194, "percentage": 80.56, "elapsed_time": "13:43:25", "remaining_time": "3:18:42"}
|
| 1003 |
+
{"current_steps": 4990, "total_steps": 6188, "loss": 0.1455, "lr": 4.403144073722501e-06, "epoch": 5.646293152235427, "percentage": 80.64, "elapsed_time": "13:46:14", "remaining_time": "3:18:21"}
|
| 1004 |
+
{"current_steps": 4995, "total_steps": 6188, "loss": 0.1419, "lr": 4.367893544535757e-06, "epoch": 5.65195246179966, "percentage": 80.72, "elapsed_time": "13:49:18", "remaining_time": "3:18:04"}
|
| 1005 |
+
{"current_steps": 5000, "total_steps": 6188, "loss": 0.1333, "lr": 4.332767381597575e-06, "epoch": 5.657611771363894, "percentage": 80.8, "elapsed_time": "13:52:14", "remaining_time": "3:17:44"}
|