Training in progress, step 5200
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 sha256:55e494e92dd17b4eed76a8e5c70ab0c77fa39279b6122cf82bbd64b7dba5c056
|
| 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 sha256:214616fbf87a73a9c4018a07f799ed8183b225d8bb6abddf5e5fed36c3c22b54
|
| 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 sha256:8536a155a321858aafac2acbd7be14eb40155abdb29b9170626763decf5422dc
|
| 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:c2477f96b052a531c304cdbe7011f3d042991e9ed1f408226648c7cd8c47d41b
|
| 3 |
size 1580230264
|
trainer_log.jsonl
CHANGED
|
@@ -1002,3 +1002,42 @@
|
|
| 1002 |
{"current_steps": 5010, "total_steps": 9128, "loss": 0.2245, "lr": 2.008795666234061e-05, "epoch": 3.84234752589183, "percentage": 54.89, "elapsed_time": "1 day, 7:03:02", "remaining_time": "1 day, 1:31:20"}
|
| 1003 |
{"current_steps": 5015, "total_steps": 9128, "loss": 0.2201, "lr": 2.0049714744294865e-05, "epoch": 3.8461833525124662, "percentage": 54.94, "elapsed_time": "1 day, 7:04:45", "remaining_time": "1 day, 1:29:21"}
|
| 1004 |
{"current_steps": 5020, "total_steps": 9128, "loss": 0.2163, "lr": 2.001147264448435e-05, "epoch": 3.850019179133103, "percentage": 55.0, "elapsed_time": "1 day, 7:06:26", "remaining_time": "1 day, 1:27:21"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1002 |
{"current_steps": 5010, "total_steps": 9128, "loss": 0.2245, "lr": 2.008795666234061e-05, "epoch": 3.84234752589183, "percentage": 54.89, "elapsed_time": "1 day, 7:03:02", "remaining_time": "1 day, 1:31:20"}
|
| 1003 |
{"current_steps": 5015, "total_steps": 9128, "loss": 0.2201, "lr": 2.0049714744294865e-05, "epoch": 3.8461833525124662, "percentage": 54.94, "elapsed_time": "1 day, 7:04:45", "remaining_time": "1 day, 1:29:21"}
|
| 1004 |
{"current_steps": 5020, "total_steps": 9128, "loss": 0.2163, "lr": 2.001147264448435e-05, "epoch": 3.850019179133103, "percentage": 55.0, "elapsed_time": "1 day, 7:06:26", "remaining_time": "1 day, 1:27:21"}
|
| 1005 |
+
{"current_steps": 5025, "total_steps": 9128, "loss": 0.2361, "lr": 1.9973230502728087e-05, "epoch": 3.85385500575374, "percentage": 55.05, "elapsed_time": "1 day, 7:08:12", "remaining_time": "1 day, 1:25:25"}
|
| 1006 |
+
{"current_steps": 5030, "total_steps": 9128, "loss": 0.2316, "lr": 1.9934988458845227e-05, "epoch": 3.857690832374377, "percentage": 55.11, "elapsed_time": "1 day, 7:09:49", "remaining_time": "1 day, 1:23:22"}
|
| 1007 |
+
{"current_steps": 5035, "total_steps": 9128, "loss": 0.2374, "lr": 1.9896746652654574e-05, "epoch": 3.8615266589950137, "percentage": 55.16, "elapsed_time": "1 day, 7:11:31", "remaining_time": "1 day, 1:21:22"}
|
| 1008 |
+
{"current_steps": 5040, "total_steps": 9128, "loss": 0.2365, "lr": 1.985850522397407e-05, "epoch": 3.86536248561565, "percentage": 55.21, "elapsed_time": "1 day, 7:13:07", "remaining_time": "1 day, 1:19:18"}
|
| 1009 |
+
{"current_steps": 5045, "total_steps": 9128, "loss": 0.2331, "lr": 1.982026431262026e-05, "epoch": 3.869198312236287, "percentage": 55.27, "elapsed_time": "1 day, 7:14:47", "remaining_time": "1 day, 1:17:18"}
|
| 1010 |
+
{"current_steps": 5050, "total_steps": 9128, "loss": 0.2375, "lr": 1.978202405840781e-05, "epoch": 3.873034138856924, "percentage": 55.32, "elapsed_time": "1 day, 7:16:31", "remaining_time": "1 day, 1:15:20"}
|
| 1011 |
+
{"current_steps": 5055, "total_steps": 9128, "loss": 0.2399, "lr": 1.9743784601148988e-05, "epoch": 3.8768699654775602, "percentage": 55.38, "elapsed_time": "1 day, 7:18:09", "remaining_time": "1 day, 1:13:18"}
|
| 1012 |
+
{"current_steps": 5060, "total_steps": 9128, "loss": 0.2278, "lr": 1.9705546080653128e-05, "epoch": 3.880705792098197, "percentage": 55.43, "elapsed_time": "1 day, 7:19:57", "remaining_time": "1 day, 1:11:23"}
|
| 1013 |
+
{"current_steps": 5065, "total_steps": 9128, "loss": 0.2286, "lr": 1.966730863672616e-05, "epoch": 3.884541618718834, "percentage": 55.49, "elapsed_time": "1 day, 7:21:35", "remaining_time": "1 day, 1:09:21"}
|
| 1014 |
+
{"current_steps": 5070, "total_steps": 9128, "loss": 0.2383, "lr": 1.9629072409170075e-05, "epoch": 3.8883774453394704, "percentage": 55.54, "elapsed_time": "1 day, 7:23:13", "remaining_time": "1 day, 1:07:19"}
|
| 1015 |
+
{"current_steps": 5075, "total_steps": 9128, "loss": 0.2297, "lr": 1.9590837537782394e-05, "epoch": 3.8922132719601072, "percentage": 55.6, "elapsed_time": "1 day, 7:24:49", "remaining_time": "1 day, 1:05:15"}
|
| 1016 |
+
{"current_steps": 5080, "total_steps": 9128, "loss": 0.2289, "lr": 1.95526041623557e-05, "epoch": 3.896049098580744, "percentage": 55.65, "elapsed_time": "1 day, 7:26:29", "remaining_time": "1 day, 1:03:15"}
|
| 1017 |
+
{"current_steps": 5085, "total_steps": 9128, "loss": 0.217, "lr": 1.9514372422677126e-05, "epoch": 3.899884925201381, "percentage": 55.71, "elapsed_time": "1 day, 7:28:14", "remaining_time": "1 day, 1:01:18"}
|
| 1018 |
+
{"current_steps": 5090, "total_steps": 9128, "loss": 0.2333, "lr": 1.9476142458527777e-05, "epoch": 3.903720751822018, "percentage": 55.76, "elapsed_time": "1 day, 7:29:58", "remaining_time": "1 day, 0:59:21"}
|
| 1019 |
+
{"current_steps": 5095, "total_steps": 9128, "loss": 0.2117, "lr": 1.94379144096823e-05, "epoch": 3.9075565784426542, "percentage": 55.82, "elapsed_time": "1 day, 7:31:39", "remaining_time": "1 day, 0:57:21"}
|
| 1020 |
+
{"current_steps": 5100, "total_steps": 9128, "loss": 0.236, "lr": 1.9399688415908333e-05, "epoch": 3.911392405063291, "percentage": 55.87, "elapsed_time": "1 day, 7:33:17", "remaining_time": "1 day, 0:55:19"}
|
| 1021 |
+
{"current_steps": 5105, "total_steps": 9128, "loss": 0.2269, "lr": 1.9361464616965994e-05, "epoch": 3.915228231683928, "percentage": 55.93, "elapsed_time": "1 day, 7:34:58", "remaining_time": "1 day, 0:53:20"}
|
| 1022 |
+
{"current_steps": 5110, "total_steps": 9128, "loss": 0.2329, "lr": 1.9323243152607388e-05, "epoch": 3.9190640583045644, "percentage": 55.98, "elapsed_time": "1 day, 7:36:36", "remaining_time": "1 day, 0:51:18"}
|
| 1023 |
+
{"current_steps": 5115, "total_steps": 9128, "loss": 0.2205, "lr": 1.928502416257606e-05, "epoch": 3.9228998849252013, "percentage": 56.04, "elapsed_time": "1 day, 7:38:13", "remaining_time": "1 day, 0:49:15"}
|
| 1024 |
+
{"current_steps": 5120, "total_steps": 9128, "loss": 0.2339, "lr": 1.9246807786606534e-05, "epoch": 3.926735711545838, "percentage": 56.09, "elapsed_time": "1 day, 7:39:54", "remaining_time": "1 day, 0:47:16"}
|
| 1025 |
+
{"current_steps": 5125, "total_steps": 9128, "loss": 0.227, "lr": 1.920859416442378e-05, "epoch": 3.930571538166475, "percentage": 56.15, "elapsed_time": "1 day, 7:41:40", "remaining_time": "1 day, 0:45:20"}
|
| 1026 |
+
{"current_steps": 5130, "total_steps": 9128, "loss": 0.2204, "lr": 1.917038343574267e-05, "epoch": 3.934407364787112, "percentage": 56.2, "elapsed_time": "1 day, 7:43:27", "remaining_time": "1 day, 0:43:26"}
|
| 1027 |
+
{"current_steps": 5135, "total_steps": 9128, "loss": 0.218, "lr": 1.913217574026752e-05, "epoch": 3.9382431914077483, "percentage": 56.26, "elapsed_time": "1 day, 7:45:11", "remaining_time": "1 day, 0:41:29"}
|
| 1028 |
+
{"current_steps": 5140, "total_steps": 9128, "loss": 0.223, "lr": 1.909397121769156e-05, "epoch": 3.942079018028385, "percentage": 56.31, "elapsed_time": "1 day, 7:46:56", "remaining_time": "1 day, 0:39:32"}
|
| 1029 |
+
{"current_steps": 5145, "total_steps": 9128, "loss": 0.2164, "lr": 1.9055770007696398e-05, "epoch": 3.945914844649022, "percentage": 56.37, "elapsed_time": "1 day, 7:48:37", "remaining_time": "1 day, 0:37:33"}
|
| 1030 |
+
{"current_steps": 5150, "total_steps": 9128, "loss": 0.2141, "lr": 1.9017572249951538e-05, "epoch": 3.9497506712696584, "percentage": 56.42, "elapsed_time": "1 day, 7:50:19", "remaining_time": "1 day, 0:35:35"}
|
| 1031 |
+
{"current_steps": 5155, "total_steps": 9128, "loss": 0.2173, "lr": 1.8979378084113888e-05, "epoch": 3.9535864978902953, "percentage": 56.47, "elapsed_time": "1 day, 7:51:54", "remaining_time": "1 day, 0:33:31"}
|
| 1032 |
+
{"current_steps": 5160, "total_steps": 9128, "loss": 0.2168, "lr": 1.894118764982718e-05, "epoch": 3.957422324510932, "percentage": 56.53, "elapsed_time": "1 day, 7:53:34", "remaining_time": "1 day, 0:31:31"}
|
| 1033 |
+
{"current_steps": 5165, "total_steps": 9128, "loss": 0.2261, "lr": 1.8903001086721538e-05, "epoch": 3.961258151131569, "percentage": 56.58, "elapsed_time": "1 day, 7:55:17", "remaining_time": "1 day, 0:29:33"}
|
| 1034 |
+
{"current_steps": 5170, "total_steps": 9128, "loss": 0.243, "lr": 1.8864818534412923e-05, "epoch": 3.965093977752206, "percentage": 56.64, "elapsed_time": "1 day, 7:56:50", "remaining_time": "1 day, 0:27:28"}
|
| 1035 |
+
{"current_steps": 5175, "total_steps": 9128, "loss": 0.2147, "lr": 1.8826640132502607e-05, "epoch": 3.9689298043728423, "percentage": 56.69, "elapsed_time": "1 day, 7:58:27", "remaining_time": "1 day, 0:25:26"}
|
| 1036 |
+
{"current_steps": 5180, "total_steps": 9128, "loss": 0.2184, "lr": 1.8788466020576733e-05, "epoch": 3.972765630993479, "percentage": 56.75, "elapsed_time": "1 day, 8:00:09", "remaining_time": "1 day, 0:23:28"}
|
| 1037 |
+
{"current_steps": 5185, "total_steps": 9128, "loss": 0.2193, "lr": 1.875029633820572e-05, "epoch": 3.976601457614116, "percentage": 56.8, "elapsed_time": "1 day, 8:01:47", "remaining_time": "1 day, 0:21:26"}
|
| 1038 |
+
{"current_steps": 5190, "total_steps": 9128, "loss": 0.2202, "lr": 1.8712131224943807e-05, "epoch": 3.9804372842347524, "percentage": 56.86, "elapsed_time": "1 day, 8:03:26", "remaining_time": "1 day, 0:19:26"}
|
| 1039 |
+
{"current_steps": 5195, "total_steps": 9128, "loss": 0.2315, "lr": 1.8673970820328542e-05, "epoch": 3.9842731108553893, "percentage": 56.91, "elapsed_time": "1 day, 8:05:02", "remaining_time": "1 day, 0:17:24"}
|
| 1040 |
+
{"current_steps": 5200, "total_steps": 9128, "loss": 0.2278, "lr": 1.8635815263880223e-05, "epoch": 3.988108937476026, "percentage": 56.97, "elapsed_time": "1 day, 8:06:44", "remaining_time": "1 day, 0:15:26"}
|
| 1041 |
+
{"current_steps": 5205, "total_steps": 9128, "loss": 0.2257, "lr": 1.8597664695101455e-05, "epoch": 3.991944764096663, "percentage": 57.02, "elapsed_time": "1 day, 8:09:45", "remaining_time": "1 day, 0:14:27"}
|
| 1042 |
+
{"current_steps": 5210, "total_steps": 9128, "loss": 0.228, "lr": 1.8559519253476598e-05, "epoch": 3.9957805907173, "percentage": 57.08, "elapsed_time": "1 day, 8:11:27", "remaining_time": "1 day, 0:12:29"}
|
| 1043 |
+
{"current_steps": 5215, "total_steps": 9128, "loss": 0.2322, "lr": 1.8521379078471248e-05, "epoch": 3.9996164173379363, "percentage": 57.13, "elapsed_time": "1 day, 8:13:14", "remaining_time": "1 day, 0:10:35"}
|