Training in progress, step 8000
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 sha256:65663a3fb866e565e1da266e961382253abf13d47cb222dc6b29d8b44550662a
|
| 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 sha256:5a82e08cd1e86595e57b3065f952eef2191017aa5cace5920dbedc7fb477fdc0
|
| 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:c1ad200cc66c09d1673f8dd6a22ce705231d94b58f05e674d73b40e9ea116e13
|
| 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 sha256:132f370b52e8f4c41560c1008cfe67b89e1a4be3ebade5e7b9ad68c074110afa
|
| 3 |
size 1580230264
|
trainer_log.jsonl
CHANGED
|
@@ -2272,3 +2272,44 @@
|
|
| 2272 |
{"current_steps": 7805, "total_steps": 8169, "loss": 0.1218, "lr": 2.427693771276274e-07, "epoch": 6.68808911739503, "percentage": 95.54, "elapsed_time": "3:51:45", "remaining_time": "0:10:48"}
|
| 2273 |
{"current_steps": 7810, "total_steps": 8169, "loss": 0.1339, "lr": 2.3617674968909876e-07, "epoch": 6.692373607540703, "percentage": 95.61, "elapsed_time": "3:54:31", "remaining_time": "0:10:46"}
|
| 2274 |
{"current_steps": 7815, "total_steps": 8169, "loss": 0.1118, "lr": 2.2967434157139756e-07, "epoch": 6.696658097686376, "percentage": 95.67, "elapsed_time": "3:57:19", "remaining_time": "0:10:45"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2272 |
{"current_steps": 7805, "total_steps": 8169, "loss": 0.1218, "lr": 2.427693771276274e-07, "epoch": 6.68808911739503, "percentage": 95.54, "elapsed_time": "3:51:45", "remaining_time": "0:10:48"}
|
| 2273 |
{"current_steps": 7810, "total_steps": 8169, "loss": 0.1339, "lr": 2.3617674968909876e-07, "epoch": 6.692373607540703, "percentage": 95.61, "elapsed_time": "3:54:31", "remaining_time": "0:10:46"}
|
| 2274 |
{"current_steps": 7815, "total_steps": 8169, "loss": 0.1118, "lr": 2.2967434157139756e-07, "epoch": 6.696658097686376, "percentage": 95.67, "elapsed_time": "3:57:19", "remaining_time": "0:10:45"}
|
| 2275 |
+
{"current_steps": 7820, "total_steps": 8169, "loss": 0.1358, "lr": 2.2326218245718455e-07, "epoch": 6.700942587832048, "percentage": 95.73, "elapsed_time": "4:00:01", "remaining_time": "0:10:42"}
|
| 2276 |
+
{"current_steps": 7825, "total_steps": 8169, "loss": 0.1352, "lr": 2.1694030161714118e-07, "epoch": 6.705227077977721, "percentage": 95.79, "elapsed_time": "4:02:47", "remaining_time": "0:10:40"}
|
| 2277 |
+
{"current_steps": 7830, "total_steps": 8169, "loss": 0.1353, "lr": 2.107087279098452e-07, "epoch": 6.709511568123394, "percentage": 95.85, "elapsed_time": "4:05:30", "remaining_time": "0:10:37"}
|
| 2278 |
+
{"current_steps": 7835, "total_steps": 8169, "loss": 0.127, "lr": 2.0456748978163299e-07, "epoch": 6.713796058269066, "percentage": 95.91, "elapsed_time": "4:08:24", "remaining_time": "0:10:35"}
|
| 2279 |
+
{"current_steps": 7840, "total_steps": 8169, "loss": 0.1318, "lr": 1.9851661526646638e-07, "epoch": 6.718080548414739, "percentage": 95.97, "elapsed_time": "4:11:03", "remaining_time": "0:10:32"}
|
| 2280 |
+
{"current_steps": 7845, "total_steps": 8169, "loss": 0.1318, "lr": 1.9255613198581934e-07, "epoch": 6.722365038560412, "percentage": 96.03, "elapsed_time": "4:13:55", "remaining_time": "0:10:29"}
|
| 2281 |
+
{"current_steps": 7850, "total_steps": 8169, "loss": 0.1229, "lr": 1.866860671485271e-07, "epoch": 6.726649528706084, "percentage": 96.09, "elapsed_time": "4:16:49", "remaining_time": "0:10:26"}
|
| 2282 |
+
{"current_steps": 7855, "total_steps": 8169, "loss": 0.1265, "lr": 1.809064475506883e-07, "epoch": 6.730934018851757, "percentage": 96.16, "elapsed_time": "4:19:38", "remaining_time": "0:10:22"}
|
| 2283 |
+
{"current_steps": 7860, "total_steps": 8169, "loss": 0.1371, "lr": 1.7521729957552302e-07, "epoch": 6.73521850899743, "percentage": 96.22, "elapsed_time": "4:22:28", "remaining_time": "0:10:19"}
|
| 2284 |
+
{"current_steps": 7865, "total_steps": 8169, "loss": 0.1412, "lr": 1.6961864919326166e-07, "epoch": 6.739502999143102, "percentage": 96.28, "elapsed_time": "4:25:20", "remaining_time": "0:10:15"}
|
| 2285 |
+
{"current_steps": 7870, "total_steps": 8169, "loss": 0.1284, "lr": 1.641105219610295e-07, "epoch": 6.743787489288774, "percentage": 96.34, "elapsed_time": "4:28:13", "remaining_time": "0:10:11"}
|
| 2286 |
+
{"current_steps": 7875, "total_steps": 8169, "loss": 0.1322, "lr": 1.586929430227202e-07, "epoch": 6.748071979434448, "percentage": 96.4, "elapsed_time": "4:31:03", "remaining_time": "0:10:07"}
|
| 2287 |
+
{"current_steps": 7880, "total_steps": 8169, "loss": 0.1276, "lr": 1.5336593710888914e-07, "epoch": 6.7523564695801195, "percentage": 96.46, "elapsed_time": "4:33:52", "remaining_time": "0:10:02"}
|
| 2288 |
+
{"current_steps": 7885, "total_steps": 8169, "loss": 0.1251, "lr": 1.4812952853663132e-07, "epoch": 6.756640959725793, "percentage": 96.52, "elapsed_time": "4:36:42", "remaining_time": "0:09:57"}
|
| 2289 |
+
{"current_steps": 7890, "total_steps": 8169, "loss": 0.126, "lr": 1.4298374120948588e-07, "epoch": 6.760925449871465, "percentage": 96.58, "elapsed_time": "4:39:35", "remaining_time": "0:09:53"}
|
| 2290 |
+
{"current_steps": 7895, "total_steps": 8169, "loss": 0.1273, "lr": 1.3792859861730955e-07, "epoch": 6.765209940017138, "percentage": 96.65, "elapsed_time": "4:42:20", "remaining_time": "0:09:47"}
|
| 2291 |
+
{"current_steps": 7900, "total_steps": 8169, "loss": 0.1246, "lr": 1.3296412383617896e-07, "epoch": 6.76949443016281, "percentage": 96.71, "elapsed_time": "4:45:10", "remaining_time": "0:09:42"}
|
| 2292 |
+
{"current_steps": 7905, "total_steps": 8169, "loss": 0.1309, "lr": 1.2809033952829065e-07, "epoch": 6.773778920308484, "percentage": 96.77, "elapsed_time": "4:47:59", "remaining_time": "0:09:37"}
|
| 2293 |
+
{"current_steps": 7910, "total_steps": 8169, "loss": 0.1296, "lr": 1.2330726794184124e-07, "epoch": 6.7780634104541555, "percentage": 96.83, "elapsed_time": "4:50:54", "remaining_time": "0:09:31"}
|
| 2294 |
+
{"current_steps": 7915, "total_steps": 8169, "loss": 0.1286, "lr": 1.1861493091094078e-07, "epoch": 6.782347900599829, "percentage": 96.89, "elapsed_time": "4:53:43", "remaining_time": "0:09:25"}
|
| 2295 |
+
{"current_steps": 7920, "total_steps": 8169, "loss": 0.1333, "lr": 1.1401334985550849e-07, "epoch": 6.786632390745501, "percentage": 96.95, "elapsed_time": "4:56:29", "remaining_time": "0:09:19"}
|
| 2296 |
+
{"current_steps": 7925, "total_steps": 8169, "loss": 0.1393, "lr": 1.0950254578117047e-07, "epoch": 6.790916880891174, "percentage": 97.01, "elapsed_time": "4:59:18", "remaining_time": "0:09:12"}
|
| 2297 |
+
{"current_steps": 7930, "total_steps": 8169, "loss": 0.1215, "lr": 1.0508253927916878e-07, "epoch": 6.795201371036846, "percentage": 97.07, "elapsed_time": "5:02:00", "remaining_time": "0:09:06"}
|
| 2298 |
+
{"current_steps": 7935, "total_steps": 8169, "loss": 0.1277, "lr": 1.0075335052626811e-07, "epoch": 6.79948586118252, "percentage": 97.14, "elapsed_time": "5:04:51", "remaining_time": "0:08:59"}
|
| 2299 |
+
{"current_steps": 7940, "total_steps": 8169, "loss": 0.1182, "lr": 9.651499928465812e-08, "epoch": 6.8037703513281915, "percentage": 97.2, "elapsed_time": "5:07:41", "remaining_time": "0:08:52"}
|
| 2300 |
+
{"current_steps": 7945, "total_steps": 8169, "loss": 0.1425, "lr": 9.23675049018713e-08, "epoch": 6.808054841473865, "percentage": 97.26, "elapsed_time": "5:10:24", "remaining_time": "0:08:45"}
|
| 2301 |
+
{"current_steps": 7950, "total_steps": 8169, "loss": 0.1296, "lr": 8.831088631068962e-08, "epoch": 6.812339331619537, "percentage": 97.32, "elapsed_time": "5:13:14", "remaining_time": "0:08:37"}
|
| 2302 |
+
{"current_steps": 7955, "total_steps": 8169, "loss": 0.1138, "lr": 8.434516202905585e-08, "epoch": 6.81662382176521, "percentage": 97.38, "elapsed_time": "5:16:03", "remaining_time": "0:08:30"}
|
| 2303 |
+
{"current_steps": 7960, "total_steps": 8169, "loss": 0.1293, "lr": 8.047035015999127e-08, "epoch": 6.820908311910882, "percentage": 97.44, "elapsed_time": "5:18:52", "remaining_time": "0:08:22"}
|
| 2304 |
+
{"current_steps": 7965, "total_steps": 8169, "loss": 0.1342, "lr": 7.668646839151584e-08, "epoch": 6.825192802056556, "percentage": 97.5, "elapsed_time": "5:21:29", "remaining_time": "0:08:14"}
|
| 2305 |
+
{"current_steps": 7970, "total_steps": 8169, "loss": 0.1343, "lr": 7.299353399656817e-08, "epoch": 6.8294772922022275, "percentage": 97.56, "elapsed_time": "5:24:19", "remaining_time": "0:08:05"}
|
| 2306 |
+
{"current_steps": 7975, "total_steps": 8169, "loss": 0.1113, "lr": 6.939156383291679e-08, "epoch": 6.8337617823479, "percentage": 97.63, "elapsed_time": "5:27:15", "remaining_time": "0:07:57"}
|
| 2307 |
+
{"current_steps": 7980, "total_steps": 8169, "loss": 0.137, "lr": 6.58805743430957e-08, "epoch": 6.838046272493573, "percentage": 97.69, "elapsed_time": "5:30:08", "remaining_time": "0:07:49"}
|
| 2308 |
+
{"current_steps": 7985, "total_steps": 8169, "loss": 0.1205, "lr": 6.246058155432444e-08, "epoch": 6.842330762639246, "percentage": 97.75, "elapsed_time": "5:32:59", "remaining_time": "0:07:40"}
|
| 2309 |
+
{"current_steps": 7990, "total_steps": 8169, "loss": 0.1132, "lr": 5.913160107842819e-08, "epoch": 6.846615252784918, "percentage": 97.81, "elapsed_time": "5:35:54", "remaining_time": "0:07:31"}
|
| 2310 |
+
{"current_steps": 7995, "total_steps": 8169, "loss": 0.1306, "lr": 5.5893648111777774e-08, "epoch": 6.850899742930591, "percentage": 97.87, "elapsed_time": "5:38:50", "remaining_time": "0:07:22"}
|
| 2311 |
+
{"current_steps": 8000, "total_steps": 8169, "loss": 0.1142, "lr": 5.274673743521197e-08, "epoch": 6.855184233076264, "percentage": 97.93, "elapsed_time": "5:41:44", "remaining_time": "0:07:13"}
|
| 2312 |
+
{"current_steps": 8005, "total_steps": 8169, "loss": 0.1291, "lr": 4.969088341397976e-08, "epoch": 6.859468723221936, "percentage": 97.99, "elapsed_time": "5:45:45", "remaining_time": "0:07:05"}
|
| 2313 |
+
{"current_steps": 8010, "total_steps": 8169, "loss": 0.1203, "lr": 4.6726099997655985e-08, "epoch": 6.863753213367609, "percentage": 98.05, "elapsed_time": "5:48:40", "remaining_time": "0:06:55"}
|
| 2314 |
+
{"current_steps": 8015, "total_steps": 8169, "loss": 0.1352, "lr": 4.385240072010355e-08, "epoch": 6.868037703513282, "percentage": 98.11, "elapsed_time": "5:51:29", "remaining_time": "0:06:45"}
|
| 2315 |
+
{"current_steps": 8020, "total_steps": 8169, "loss": 0.1321, "lr": 4.1069798699389094e-08, "epoch": 6.872322193658954, "percentage": 98.18, "elapsed_time": "5:54:19", "remaining_time": "0:06:34"}
|