Training in progress, step 5400
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:dd86bc0a6f6e2a05caae935e64dd4257590a503fe32ba57eb5abb3e523a47d8a
|
| 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:ac77c8895879eef51fb5f04554397ab46b99afcccc5eb6b1f8f4e54665377fc7
|
| 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 sha256:04507b564efbe9ffb61f7d2b9bb7eb35179c68b8e6089337088267b7575527d1
|
| 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:dc764a4d353c999f11a8d817511eaf840c19cbd6d255f14ecb8254b471a4fbe9
|
| 3 |
size 1580230264
|
trainer_log.jsonl
CHANGED
|
@@ -1042,3 +1042,43 @@
|
|
| 1042 |
{"current_steps": 5200, "total_steps": 6188, "loss": 0.0904, "lr": 3.032796520757002e-06, "epoch": 5.88398415393322, "percentage": 84.03, "elapsed_time": "16:04:12", "remaining_time": "3:03:11"}
|
| 1043 |
{"current_steps": 5205, "total_steps": 6188, "loss": 0.0683, "lr": 3.0029983615014234e-06, "epoch": 5.889643463497453, "percentage": 84.11, "elapsed_time": "16:06:55", "remaining_time": "3:02:36"}
|
| 1044 |
{"current_steps": 5210, "total_steps": 6188, "loss": 0.0739, "lr": 2.9733354273568514e-06, "epoch": 5.895302773061687, "percentage": 84.2, "elapsed_time": "16:08:29", "remaining_time": "3:01:48"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1042 |
{"current_steps": 5200, "total_steps": 6188, "loss": 0.0904, "lr": 3.032796520757002e-06, "epoch": 5.88398415393322, "percentage": 84.03, "elapsed_time": "16:04:12", "remaining_time": "3:03:11"}
|
| 1043 |
{"current_steps": 5205, "total_steps": 6188, "loss": 0.0683, "lr": 3.0029983615014234e-06, "epoch": 5.889643463497453, "percentage": 84.11, "elapsed_time": "16:06:55", "remaining_time": "3:02:36"}
|
| 1044 |
{"current_steps": 5210, "total_steps": 6188, "loss": 0.0739, "lr": 2.9733354273568514e-06, "epoch": 5.895302773061687, "percentage": 84.2, "elapsed_time": "16:08:29", "remaining_time": "3:01:48"}
|
| 1045 |
+
{"current_steps": 5215, "total_steps": 6188, "loss": 0.0768, "lr": 2.9438079543162914e-06, "epoch": 5.900962082625919, "percentage": 84.28, "elapsed_time": "16:10:08", "remaining_time": "3:01:00"}
|
| 1046 |
+
{"current_steps": 5220, "total_steps": 6188, "loss": 0.104, "lr": 2.9144161772950564e-06, "epoch": 5.906621392190153, "percentage": 84.36, "elapsed_time": "16:12:08", "remaining_time": "3:00:16"}
|
| 1047 |
+
{"current_steps": 5225, "total_steps": 6188, "loss": 0.0935, "lr": 2.885160330128871e-06, "epoch": 5.912280701754386, "percentage": 84.44, "elapsed_time": "16:14:07", "remaining_time": "2:59:32"}
|
| 1048 |
+
{"current_steps": 5230, "total_steps": 6188, "loss": 0.0698, "lr": 2.8560406455720333e-06, "epoch": 5.917940011318619, "percentage": 84.52, "elapsed_time": "16:15:45", "remaining_time": "2:58:43"}
|
| 1049 |
+
{"current_steps": 5235, "total_steps": 6188, "loss": 0.072, "lr": 2.8270573552955616e-06, "epoch": 5.923599320882852, "percentage": 84.6, "elapsed_time": "16:17:16", "remaining_time": "2:57:54"}
|
| 1050 |
+
{"current_steps": 5240, "total_steps": 6188, "loss": 0.0684, "lr": 2.798210689885337e-06, "epoch": 5.929258630447086, "percentage": 84.68, "elapsed_time": "16:18:49", "remaining_time": "2:57:05"}
|
| 1051 |
+
{"current_steps": 5245, "total_steps": 6188, "loss": 0.0606, "lr": 2.7695008788402765e-06, "epoch": 5.934917940011319, "percentage": 84.76, "elapsed_time": "16:20:18", "remaining_time": "2:56:15"}
|
| 1052 |
+
{"current_steps": 5250, "total_steps": 6188, "loss": 0.0882, "lr": 2.740928150570512e-06, "epoch": 5.9405772495755516, "percentage": 84.84, "elapsed_time": "16:21:47", "remaining_time": "2:55:24"}
|
| 1053 |
+
{"current_steps": 5255, "total_steps": 6188, "loss": 0.062, "lr": 2.712492732395575e-06, "epoch": 5.946236559139785, "percentage": 84.92, "elapsed_time": "16:23:23", "remaining_time": "2:54:35"}
|
| 1054 |
+
{"current_steps": 5260, "total_steps": 6188, "loss": 0.0701, "lr": 2.6841948505425765e-06, "epoch": 5.951895868704018, "percentage": 85.0, "elapsed_time": "16:24:55", "remaining_time": "2:53:45"}
|
| 1055 |
+
{"current_steps": 5265, "total_steps": 6188, "loss": 0.0692, "lr": 2.6560347301444035e-06, "epoch": 5.957555178268251, "percentage": 85.08, "elapsed_time": "16:26:31", "remaining_time": "2:52:56"}
|
| 1056 |
+
{"current_steps": 5270, "total_steps": 6188, "loss": 0.0727, "lr": 2.6280125952379567e-06, "epoch": 5.963214487832484, "percentage": 85.16, "elapsed_time": "16:28:21", "remaining_time": "2:52:09"}
|
| 1057 |
+
{"current_steps": 5275, "total_steps": 6188, "loss": 0.0623, "lr": 2.6001286687623382e-06, "epoch": 5.968873797396718, "percentage": 85.25, "elapsed_time": "16:30:04", "remaining_time": "2:51:21"}
|
| 1058 |
+
{"current_steps": 5280, "total_steps": 6188, "loss": 0.068, "lr": 2.5723831725570848e-06, "epoch": 5.97453310696095, "percentage": 85.33, "elapsed_time": "16:31:51", "remaining_time": "2:50:34"}
|
| 1059 |
+
{"current_steps": 5285, "total_steps": 6188, "loss": 0.118, "lr": 2.544776327360419e-06, "epoch": 5.980192416525184, "percentage": 85.41, "elapsed_time": "16:34:30", "remaining_time": "2:49:55"}
|
| 1060 |
+
{"current_steps": 5290, "total_steps": 6188, "loss": 0.1098, "lr": 2.5173083528074683e-06, "epoch": 5.985851726089417, "percentage": 85.49, "elapsed_time": "16:36:36", "remaining_time": "2:49:10"}
|
| 1061 |
+
{"current_steps": 5295, "total_steps": 6188, "loss": 0.0742, "lr": 2.489979467428532e-06, "epoch": 5.99151103565365, "percentage": 85.57, "elapsed_time": "16:38:22", "remaining_time": "2:48:22"}
|
| 1062 |
+
{"current_steps": 5300, "total_steps": 6188, "loss": 0.0656, "lr": 2.4627898886473522e-06, "epoch": 5.997170345217883, "percentage": 85.65, "elapsed_time": "16:39:56", "remaining_time": "2:47:32"}
|
| 1063 |
+
{"current_steps": 5305, "total_steps": 6188, "loss": 0.138, "lr": 2.435739832779358e-06, "epoch": 6.002263723825693, "percentage": 85.73, "elapsed_time": "16:42:19", "remaining_time": "2:46:50"}
|
| 1064 |
+
{"current_steps": 5310, "total_steps": 6188, "loss": 0.1559, "lr": 2.408829515029969e-06, "epoch": 6.007923033389926, "percentage": 85.81, "elapsed_time": "16:45:11", "remaining_time": "2:46:12"}
|
| 1065 |
+
{"current_steps": 5315, "total_steps": 6188, "loss": 0.1493, "lr": 2.3820591494928635e-06, "epoch": 6.01358234295416, "percentage": 85.89, "elapsed_time": "16:48:08", "remaining_time": "2:45:35"}
|
| 1066 |
+
{"current_steps": 5320, "total_steps": 6188, "loss": 0.1456, "lr": 2.3554289491482996e-06, "epoch": 6.019241652518393, "percentage": 85.97, "elapsed_time": "16:51:01", "remaining_time": "2:44:57"}
|
| 1067 |
+
{"current_steps": 5325, "total_steps": 6188, "loss": 0.1508, "lr": 2.3289391258613938e-06, "epoch": 6.024900962082626, "percentage": 86.05, "elapsed_time": "16:53:52", "remaining_time": "2:44:18"}
|
| 1068 |
+
{"current_steps": 5330, "total_steps": 6188, "loss": 0.1563, "lr": 2.3025898903804467e-06, "epoch": 6.030560271646859, "percentage": 86.13, "elapsed_time": "16:56:48", "remaining_time": "2:43:40"}
|
| 1069 |
+
{"current_steps": 5335, "total_steps": 6188, "loss": 0.1504, "lr": 2.276381452335281e-06, "epoch": 6.036219581211093, "percentage": 86.22, "elapsed_time": "16:59:48", "remaining_time": "2:43:03"}
|
| 1070 |
+
{"current_steps": 5340, "total_steps": 6188, "loss": 0.1435, "lr": 2.2503140202355488e-06, "epoch": 6.041878890775325, "percentage": 86.3, "elapsed_time": "17:02:44", "remaining_time": "2:42:24"}
|
| 1071 |
+
{"current_steps": 5345, "total_steps": 6188, "loss": 0.1664, "lr": 2.2243878014690834e-06, "epoch": 6.047538200339559, "percentage": 86.38, "elapsed_time": "17:05:25", "remaining_time": "2:41:43"}
|
| 1072 |
+
{"current_steps": 5350, "total_steps": 6188, "loss": 0.1477, "lr": 2.1986030023002568e-06, "epoch": 6.053197509903792, "percentage": 86.46, "elapsed_time": "17:08:21", "remaining_time": "2:41:04"}
|
| 1073 |
+
{"current_steps": 5355, "total_steps": 6188, "loss": 0.1481, "lr": 2.1729598278683264e-06, "epoch": 6.058856819468025, "percentage": 86.54, "elapsed_time": "17:11:13", "remaining_time": "2:40:24"}
|
| 1074 |
+
{"current_steps": 5360, "total_steps": 6188, "loss": 0.1426, "lr": 2.147458482185807e-06, "epoch": 6.064516129032258, "percentage": 86.62, "elapsed_time": "17:14:05", "remaining_time": "2:39:44"}
|
| 1075 |
+
{"current_steps": 5365, "total_steps": 6188, "loss": 0.1506, "lr": 2.122099168136862e-06, "epoch": 6.0701754385964914, "percentage": 86.7, "elapsed_time": "17:17:05", "remaining_time": "2:39:05"}
|
| 1076 |
+
{"current_steps": 5370, "total_steps": 6188, "loss": 0.1374, "lr": 2.0968820874756625e-06, "epoch": 6.075834748160724, "percentage": 86.78, "elapsed_time": "17:20:06", "remaining_time": "2:38:26"}
|
| 1077 |
+
{"current_steps": 5375, "total_steps": 6188, "loss": 0.132, "lr": 2.0718074408247955e-06, "epoch": 6.081494057724957, "percentage": 86.86, "elapsed_time": "17:22:41", "remaining_time": "2:37:42"}
|
| 1078 |
+
{"current_steps": 5380, "total_steps": 6188, "loss": 0.1422, "lr": 2.0468754276736823e-06, "epoch": 6.087153367289191, "percentage": 86.94, "elapsed_time": "17:25:39", "remaining_time": "2:37:02"}
|
| 1079 |
+
{"current_steps": 5385, "total_steps": 6188, "loss": 0.1484, "lr": 2.0220862463769665e-06, "epoch": 6.092812676853424, "percentage": 87.02, "elapsed_time": "17:28:30", "remaining_time": "2:36:21"}
|
| 1080 |
+
{"current_steps": 5390, "total_steps": 6188, "loss": 0.1315, "lr": 1.9974400941529493e-06, "epoch": 6.098471986417657, "percentage": 87.1, "elapsed_time": "17:31:26", "remaining_time": "2:35:40"}
|
| 1081 |
+
{"current_steps": 5395, "total_steps": 6188, "loss": 0.1308, "lr": 1.972937167082014e-06, "epoch": 6.10413129598189, "percentage": 87.18, "elapsed_time": "17:34:32", "remaining_time": "2:35:00"}
|
| 1082 |
+
{"current_steps": 5400, "total_steps": 6188, "loss": 0.1324, "lr": 1.948577660105082e-06, "epoch": 6.109790605546124, "percentage": 87.27, "elapsed_time": "17:37:29", "remaining_time": "2:34:18"}
|
| 1083 |
+
{"current_steps": 5405, "total_steps": 6188, "loss": 0.1611, "lr": 1.924361767022038e-06, "epoch": 6.115449915110356, "percentage": 87.35, "elapsed_time": "17:41:34", "remaining_time": "2:33:47"}
|
| 1084 |
+
{"current_steps": 5410, "total_steps": 6188, "loss": 0.1423, "lr": 1.9002896804902039e-06, "epoch": 6.12110922467459, "percentage": 87.43, "elapsed_time": "17:44:35", "remaining_time": "2:33:05"}
|