Training in progress, step 6000
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 sha256:5e1f4c4fa59f36da7d4a95d5d23997fdd02c3b225cb9d0bf0d812f8df0a2c5d8
|
| 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 sha256:0feab729e8b327684f1400c0c09231b0b51900ede29ef912a9b99f561dbbc6a7
|
| 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 sha256:7e52c46bd0be7d9723677ebebed3ab8ad95a55c19b00b238538f0c6bfd123b7e
|
| 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:c50978ad80fb792d992da3ccb28825188b883c0787077e8d9c4b82641a4f9c51
|
| 3 |
size 1580230264
|
trainer_log.jsonl
CHANGED
|
@@ -1160,3 +1160,44 @@
|
|
| 1160 |
{"current_steps": 5800, "total_steps": 9128, "loss": 0.1382, "lr": 1.4133267445964118e-05, "epoch": 4.448024549290372, "percentage": 63.54, "elapsed_time": "1 day, 12:10:32", "remaining_time": "20:45:26"}
|
| 1161 |
{"current_steps": 5805, "total_steps": 9128, "loss": 0.1403, "lr": 1.40967183448443e-05, "epoch": 4.451860375911009, "percentage": 63.6, "elapsed_time": "1 day, 12:13:02", "remaining_time": "20:43:56"}
|
| 1162 |
{"current_steps": 5810, "total_steps": 9128, "loss": 0.1457, "lr": 1.4060190827031605e-05, "epoch": 4.455696202531645, "percentage": 63.65, "elapsed_time": "1 day, 12:14:19", "remaining_time": "20:41:43"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1160 |
{"current_steps": 5800, "total_steps": 9128, "loss": 0.1382, "lr": 1.4133267445964118e-05, "epoch": 4.448024549290372, "percentage": 63.54, "elapsed_time": "1 day, 12:10:32", "remaining_time": "20:45:26"}
|
| 1161 |
{"current_steps": 5805, "total_steps": 9128, "loss": 0.1403, "lr": 1.40967183448443e-05, "epoch": 4.451860375911009, "percentage": 63.6, "elapsed_time": "1 day, 12:13:02", "remaining_time": "20:43:56"}
|
| 1162 |
{"current_steps": 5810, "total_steps": 9128, "loss": 0.1457, "lr": 1.4060190827031605e-05, "epoch": 4.455696202531645, "percentage": 63.65, "elapsed_time": "1 day, 12:14:19", "remaining_time": "20:41:43"}
|
| 1163 |
+
{"current_steps": 5815, "total_steps": 9128, "loss": 0.1391, "lr": 1.4023685026076278e-05, "epoch": 4.459532029152283, "percentage": 63.71, "elapsed_time": "1 day, 12:15:36", "remaining_time": "20:39:31"}
|
| 1164 |
+
{"current_steps": 5820, "total_steps": 9128, "loss": 0.1356, "lr": 1.3987201075449153e-05, "epoch": 4.463367855772919, "percentage": 63.76, "elapsed_time": "1 day, 12:16:50", "remaining_time": "20:37:17"}
|
| 1165 |
+
{"current_steps": 5825, "total_steps": 9128, "loss": 0.1387, "lr": 1.3950739108541158e-05, "epoch": 4.4672036823935555, "percentage": 63.81, "elapsed_time": "1 day, 12:18:05", "remaining_time": "20:35:03"}
|
| 1166 |
+
{"current_steps": 5830, "total_steps": 9128, "loss": 0.1377, "lr": 1.3914299258662873e-05, "epoch": 4.471039509014193, "percentage": 63.87, "elapsed_time": "1 day, 12:19:18", "remaining_time": "20:32:49"}
|
| 1167 |
+
{"current_steps": 5835, "total_steps": 9128, "loss": 0.1447, "lr": 1.3877881659044006e-05, "epoch": 4.474875335634829, "percentage": 63.92, "elapsed_time": "1 day, 12:20:33", "remaining_time": "20:30:36"}
|
| 1168 |
+
{"current_steps": 5840, "total_steps": 9128, "loss": 0.1462, "lr": 1.3841486442832897e-05, "epoch": 4.4787111622554665, "percentage": 63.98, "elapsed_time": "1 day, 12:21:50", "remaining_time": "20:28:24"}
|
| 1169 |
+
{"current_steps": 5845, "total_steps": 9128, "loss": 0.1428, "lr": 1.3805113743096082e-05, "epoch": 4.482546988876103, "percentage": 64.03, "elapsed_time": "1 day, 12:23:09", "remaining_time": "20:26:13"}
|
| 1170 |
+
{"current_steps": 5850, "total_steps": 9128, "loss": 0.1433, "lr": 1.3768763692817734e-05, "epoch": 4.486382815496739, "percentage": 64.09, "elapsed_time": "1 day, 12:24:24", "remaining_time": "20:24:00"}
|
| 1171 |
+
{"current_steps": 5855, "total_steps": 9128, "loss": 0.1317, "lr": 1.373243642489925e-05, "epoch": 4.490218642117377, "percentage": 64.14, "elapsed_time": "1 day, 12:25:36", "remaining_time": "20:21:46"}
|
| 1172 |
+
{"current_steps": 5860, "total_steps": 9128, "loss": 0.1331, "lr": 1.3696132072158722e-05, "epoch": 4.494054468738013, "percentage": 64.2, "elapsed_time": "1 day, 12:26:52", "remaining_time": "20:19:34"}
|
| 1173 |
+
{"current_steps": 5865, "total_steps": 9128, "loss": 0.1401, "lr": 1.3659850767330438e-05, "epoch": 4.4978902953586495, "percentage": 64.25, "elapsed_time": "1 day, 12:28:06", "remaining_time": "20:17:21"}
|
| 1174 |
+
{"current_steps": 5870, "total_steps": 9128, "loss": 0.134, "lr": 1.3623592643064453e-05, "epoch": 4.501726121979287, "percentage": 64.31, "elapsed_time": "1 day, 12:29:21", "remaining_time": "20:15:08"}
|
| 1175 |
+
{"current_steps": 5875, "total_steps": 9128, "loss": 0.1302, "lr": 1.3587357831926049e-05, "epoch": 4.505561948599923, "percentage": 64.36, "elapsed_time": "1 day, 12:30:35", "remaining_time": "20:12:56"}
|
| 1176 |
+
{"current_steps": 5880, "total_steps": 9128, "loss": 0.1388, "lr": 1.3551146466395283e-05, "epoch": 4.50939777522056, "percentage": 64.42, "elapsed_time": "1 day, 12:31:50", "remaining_time": "20:10:43"}
|
| 1177 |
+
{"current_steps": 5885, "total_steps": 9128, "loss": 0.1468, "lr": 1.3514958678866472e-05, "epoch": 4.513233601841197, "percentage": 64.47, "elapsed_time": "1 day, 12:33:06", "remaining_time": "20:08:32"}
|
| 1178 |
+
{"current_steps": 5890, "total_steps": 9128, "loss": 0.1313, "lr": 1.3478794601647764e-05, "epoch": 4.517069428461833, "percentage": 64.53, "elapsed_time": "1 day, 12:34:23", "remaining_time": "20:06:21"}
|
| 1179 |
+
{"current_steps": 5895, "total_steps": 9128, "loss": 0.1373, "lr": 1.3442654366960577e-05, "epoch": 4.520905255082471, "percentage": 64.58, "elapsed_time": "1 day, 12:35:43", "remaining_time": "20:04:12"}
|
| 1180 |
+
{"current_steps": 5900, "total_steps": 9128, "loss": 0.1225, "lr": 1.340653810693918e-05, "epoch": 4.524741081703107, "percentage": 64.64, "elapsed_time": "1 day, 12:37:04", "remaining_time": "20:02:03"}
|
| 1181 |
+
{"current_steps": 5905, "total_steps": 9128, "loss": 0.1337, "lr": 1.3370445953630195e-05, "epoch": 4.5285769083237435, "percentage": 64.69, "elapsed_time": "1 day, 12:38:17", "remaining_time": "19:59:51"}
|
| 1182 |
+
{"current_steps": 5910, "total_steps": 9128, "loss": 0.1331, "lr": 1.3334378038992078e-05, "epoch": 4.532412734944381, "percentage": 64.75, "elapsed_time": "1 day, 12:39:32", "remaining_time": "19:57:39"}
|
| 1183 |
+
{"current_steps": 5915, "total_steps": 9128, "loss": 0.1362, "lr": 1.329833449489469e-05, "epoch": 4.536248561565017, "percentage": 64.8, "elapsed_time": "1 day, 12:40:48", "remaining_time": "19:55:28"}
|
| 1184 |
+
{"current_steps": 5920, "total_steps": 9128, "loss": 0.1385, "lr": 1.326231545311879e-05, "epoch": 4.540084388185654, "percentage": 64.86, "elapsed_time": "1 day, 12:42:04", "remaining_time": "19:53:16"}
|
| 1185 |
+
{"current_steps": 5925, "total_steps": 9128, "loss": 0.1392, "lr": 1.3226321045355524e-05, "epoch": 4.543920214806291, "percentage": 64.91, "elapsed_time": "1 day, 12:43:19", "remaining_time": "19:51:05"}
|
| 1186 |
+
{"current_steps": 5930, "total_steps": 9128, "loss": 0.1386, "lr": 1.3190351403206005e-05, "epoch": 4.547756041426927, "percentage": 64.96, "elapsed_time": "1 day, 12:44:34", "remaining_time": "19:48:54"}
|
| 1187 |
+
{"current_steps": 5935, "total_steps": 9128, "loss": 0.1722, "lr": 1.3154406658180782e-05, "epoch": 4.551591868047565, "percentage": 65.02, "elapsed_time": "1 day, 12:46:02", "remaining_time": "19:46:50"}
|
| 1188 |
+
{"current_steps": 5940, "total_steps": 9128, "loss": 0.2396, "lr": 1.3118486941699375e-05, "epoch": 4.555427694668201, "percentage": 65.07, "elapsed_time": "1 day, 12:48:19", "remaining_time": "19:45:12"}
|
| 1189 |
+
{"current_steps": 5945, "total_steps": 9128, "loss": 0.2304, "lr": 1.3082592385089815e-05, "epoch": 4.5592635212888375, "percentage": 65.13, "elapsed_time": "1 day, 12:50:33", "remaining_time": "19:43:33"}
|
| 1190 |
+
{"current_steps": 5950, "total_steps": 9128, "loss": 0.2256, "lr": 1.3046723119588112e-05, "epoch": 4.563099347909475, "percentage": 65.18, "elapsed_time": "1 day, 12:53:00", "remaining_time": "19:42:00"}
|
| 1191 |
+
{"current_steps": 5955, "total_steps": 9128, "loss": 0.2128, "lr": 1.301087927633784e-05, "epoch": 4.566935174530111, "percentage": 65.24, "elapsed_time": "1 day, 12:55:20", "remaining_time": "19:40:24"}
|
| 1192 |
+
{"current_steps": 5960, "total_steps": 9128, "loss": 0.2351, "lr": 1.297506098638961e-05, "epoch": 4.570771001150748, "percentage": 65.29, "elapsed_time": "1 day, 12:57:40", "remaining_time": "19:38:47"}
|
| 1193 |
+
{"current_steps": 5965, "total_steps": 9128, "loss": 0.2184, "lr": 1.29392683807006e-05, "epoch": 4.574606827771385, "percentage": 65.35, "elapsed_time": "1 day, 12:59:56", "remaining_time": "19:37:08"}
|
| 1194 |
+
{"current_steps": 5970, "total_steps": 9128, "loss": 0.2255, "lr": 1.2903501590134097e-05, "epoch": 4.578442654392021, "percentage": 65.4, "elapsed_time": "1 day, 13:02:19", "remaining_time": "19:35:33"}
|
| 1195 |
+
{"current_steps": 5975, "total_steps": 9128, "loss": 0.2172, "lr": 1.2867760745459004e-05, "epoch": 4.582278481012658, "percentage": 65.46, "elapsed_time": "1 day, 13:04:28", "remaining_time": "19:33:51"}
|
| 1196 |
+
{"current_steps": 5980, "total_steps": 9128, "loss": 0.2302, "lr": 1.2832045977349337e-05, "epoch": 4.586114307633295, "percentage": 65.51, "elapsed_time": "1 day, 13:07:00", "remaining_time": "19:32:20"}
|
| 1197 |
+
{"current_steps": 5985, "total_steps": 9128, "loss": 0.228, "lr": 1.2796357416383798e-05, "epoch": 4.5899501342539315, "percentage": 65.57, "elapsed_time": "1 day, 13:09:03", "remaining_time": "19:30:34"}
|
| 1198 |
+
{"current_steps": 5990, "total_steps": 9128, "loss": 0.2137, "lr": 1.2760695193045276e-05, "epoch": 4.593785960874569, "percentage": 65.62, "elapsed_time": "1 day, 13:11:41", "remaining_time": "19:29:07"}
|
| 1199 |
+
{"current_steps": 5995, "total_steps": 9128, "loss": 0.2254, "lr": 1.2725059437720338e-05, "epoch": 4.597621787495205, "percentage": 65.68, "elapsed_time": "1 day, 13:13:50", "remaining_time": "19:27:24"}
|
| 1200 |
+
{"current_steps": 6000, "total_steps": 9128, "loss": 0.2207, "lr": 1.2689450280698803e-05, "epoch": 4.601457614115842, "percentage": 65.73, "elapsed_time": "1 day, 13:16:03", "remaining_time": "19:25:44"}
|
| 1201 |
+
{"current_steps": 6005, "total_steps": 9128, "loss": 0.2158, "lr": 1.2653867852173223e-05, "epoch": 4.605293440736479, "percentage": 65.79, "elapsed_time": "1 day, 13:19:09", "remaining_time": "19:24:30"}
|
| 1202 |
+
{"current_steps": 6010, "total_steps": 9128, "loss": 0.2192, "lr": 1.2618312282238451e-05, "epoch": 4.609129267357115, "percentage": 65.84, "elapsed_time": "1 day, 13:20:49", "remaining_time": "19:22:32"}
|
| 1203 |
+
{"current_steps": 6015, "total_steps": 9128, "loss": 0.2113, "lr": 1.258278370089113e-05, "epoch": 4.612965093977753, "percentage": 65.9, "elapsed_time": "1 day, 13:22:32", "remaining_time": "19:20:36"}
|