Training in progress, step 6600
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 sha256:3f2ea4c122345cdf37367364d6c723e779ec9a8cefe6ceead39bf2cfe5b47566
|
| 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:cad91c13539915c93cf434d7864a7f90f89449b00a9a1d1d48d24ee9c46d6080
|
| 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 sha256:4eb4dbc3e697714c2e3dd149ff0b6352bdbdf2167e9f0d311af4102f88719c1f
|
| 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 sha256:7d73be9e5577f6b419722e40f0ad0dfee69c1fb5c93b796e8bedd40554832bb3
|
| 3 |
size 1580230264
|
trainer_log.jsonl
CHANGED
|
@@ -1282,3 +1282,41 @@
|
|
| 1282 |
{"current_steps": 6410, "total_steps": 9128, "loss": 0.2062, "lr": 9.87221561162577e-06, "epoch": 4.915995397008055, "percentage": 70.22, "elapsed_time": "1 day, 15:37:10", "remaining_time": "16:47:58"}
|
| 1283 |
{"current_steps": 6415, "total_steps": 9128, "loss": 0.2098, "lr": 9.83925774760068e-06, "epoch": 4.919831223628692, "percentage": 70.28, "elapsed_time": "1 day, 15:38:52", "remaining_time": "16:46:03"}
|
| 1284 |
{"current_steps": 6420, "total_steps": 9128, "loss": 0.2053, "lr": 9.806337032814533e-06, "epoch": 4.923667050249328, "percentage": 70.33, "elapsed_time": "1 day, 15:40:28", "remaining_time": "16:44:06"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1282 |
{"current_steps": 6410, "total_steps": 9128, "loss": 0.2062, "lr": 9.87221561162577e-06, "epoch": 4.915995397008055, "percentage": 70.22, "elapsed_time": "1 day, 15:37:10", "remaining_time": "16:47:58"}
|
| 1283 |
{"current_steps": 6415, "total_steps": 9128, "loss": 0.2098, "lr": 9.83925774760068e-06, "epoch": 4.919831223628692, "percentage": 70.28, "elapsed_time": "1 day, 15:38:52", "remaining_time": "16:46:03"}
|
| 1284 |
{"current_steps": 6420, "total_steps": 9128, "loss": 0.2053, "lr": 9.806337032814533e-06, "epoch": 4.923667050249328, "percentage": 70.33, "elapsed_time": "1 day, 15:40:28", "remaining_time": "16:44:06"}
|
| 1285 |
+
{"current_steps": 6425, "total_steps": 9128, "loss": 0.2058, "lr": 9.773453587630536e-06, "epoch": 4.927502876869966, "percentage": 70.39, "elapsed_time": "1 day, 15:42:13", "remaining_time": "16:42:12"}
|
| 1286 |
+
{"current_steps": 6430, "total_steps": 9128, "loss": 0.2038, "lr": 9.740607532275603e-06, "epoch": 4.931338703490602, "percentage": 70.44, "elapsed_time": "1 day, 15:44:01", "remaining_time": "16:40:19"}
|
| 1287 |
+
{"current_steps": 6435, "total_steps": 9128, "loss": 0.1994, "lr": 9.707798986840003e-06, "epoch": 4.935174530111239, "percentage": 70.5, "elapsed_time": "1 day, 15:45:48", "remaining_time": "16:38:26"}
|
| 1288 |
+
{"current_steps": 6440, "total_steps": 9128, "loss": 0.2017, "lr": 9.675028071276826e-06, "epoch": 4.939010356731876, "percentage": 70.55, "elapsed_time": "1 day, 15:47:30", "remaining_time": "16:36:31"}
|
| 1289 |
+
{"current_steps": 6445, "total_steps": 9128, "loss": 0.2046, "lr": 9.642294905401565e-06, "epoch": 4.942846183352512, "percentage": 70.61, "elapsed_time": "1 day, 15:49:15", "remaining_time": "16:34:37"}
|
| 1290 |
+
{"current_steps": 6450, "total_steps": 9128, "loss": 0.1964, "lr": 9.609599608891744e-06, "epoch": 4.946682009973149, "percentage": 70.66, "elapsed_time": "1 day, 15:50:57", "remaining_time": "16:32:42"}
|
| 1291 |
+
{"current_steps": 6455, "total_steps": 9128, "loss": 0.1959, "lr": 9.576942301286393e-06, "epoch": 4.950517836593786, "percentage": 70.72, "elapsed_time": "1 day, 15:52:37", "remaining_time": "16:30:47"}
|
| 1292 |
+
{"current_steps": 6460, "total_steps": 9128, "loss": 0.197, "lr": 9.544323101985663e-06, "epoch": 4.954353663214423, "percentage": 70.77, "elapsed_time": "1 day, 15:54:14", "remaining_time": "16:28:49"}
|
| 1293 |
+
{"current_steps": 6465, "total_steps": 9128, "loss": 0.1955, "lr": 9.511742130250366e-06, "epoch": 4.95818948983506, "percentage": 70.83, "elapsed_time": "1 day, 15:55:53", "remaining_time": "16:26:53"}
|
| 1294 |
+
{"current_steps": 6470, "total_steps": 9128, "loss": 0.2099, "lr": 9.479199505201557e-06, "epoch": 4.962025316455696, "percentage": 70.88, "elapsed_time": "1 day, 15:57:35", "remaining_time": "16:24:58"}
|
| 1295 |
+
{"current_steps": 6475, "total_steps": 9128, "loss": 0.2147, "lr": 9.446695345820085e-06, "epoch": 4.965861143076333, "percentage": 70.94, "elapsed_time": "1 day, 15:59:08", "remaining_time": "16:23:00"}
|
| 1296 |
+
{"current_steps": 6480, "total_steps": 9128, "loss": 0.1943, "lr": 9.414229770946166e-06, "epoch": 4.96969696969697, "percentage": 70.99, "elapsed_time": "1 day, 16:00:50", "remaining_time": "16:21:05"}
|
| 1297 |
+
{"current_steps": 6485, "total_steps": 9128, "loss": 0.1915, "lr": 9.381802899278942e-06, "epoch": 4.973532796317606, "percentage": 71.05, "elapsed_time": "1 day, 16:02:28", "remaining_time": "16:19:08"}
|
| 1298 |
+
{"current_steps": 6490, "total_steps": 9128, "loss": 0.2047, "lr": 9.349414849376051e-06, "epoch": 4.9773686229382434, "percentage": 71.1, "elapsed_time": "1 day, 16:04:06", "remaining_time": "16:17:12"}
|
| 1299 |
+
{"current_steps": 6495, "total_steps": 9128, "loss": 0.1982, "lr": 9.317065739653193e-06, "epoch": 4.98120444955888, "percentage": 71.15, "elapsed_time": "1 day, 16:05:46", "remaining_time": "16:15:16"}
|
| 1300 |
+
{"current_steps": 6500, "total_steps": 9128, "loss": 0.2124, "lr": 9.284755688383695e-06, "epoch": 4.985040276179516, "percentage": 71.21, "elapsed_time": "1 day, 16:07:22", "remaining_time": "16:13:19"}
|
| 1301 |
+
{"current_steps": 6505, "total_steps": 9128, "loss": 0.2062, "lr": 9.252484813698085e-06, "epoch": 4.988876102800154, "percentage": 71.26, "elapsed_time": "1 day, 16:09:06", "remaining_time": "16:11:25"}
|
| 1302 |
+
{"current_steps": 6510, "total_steps": 9128, "loss": 0.2054, "lr": 9.220253233583649e-06, "epoch": 4.99271192942079, "percentage": 71.32, "elapsed_time": "1 day, 16:10:42", "remaining_time": "16:09:28"}
|
| 1303 |
+
{"current_steps": 6515, "total_steps": 9128, "loss": 0.2109, "lr": 9.188061065884013e-06, "epoch": 4.996547756041427, "percentage": 71.37, "elapsed_time": "1 day, 16:12:22", "remaining_time": "16:07:32"}
|
| 1304 |
+
{"current_steps": 6520, "total_steps": 9128, "loss": 0.1923, "lr": 9.155908428298696e-06, "epoch": 5.0, "percentage": 71.43, "elapsed_time": "1 day, 16:14:05", "remaining_time": "16:05:38"}
|
| 1305 |
+
{"current_steps": 6525, "total_steps": 9128, "loss": 0.1772, "lr": 9.123795438382698e-06, "epoch": 5.003835826620636, "percentage": 71.48, "elapsed_time": "1 day, 16:17:00", "remaining_time": "16:04:12"}
|
| 1306 |
+
{"current_steps": 6530, "total_steps": 9128, "loss": 0.18, "lr": 9.091722213546059e-06, "epoch": 5.007671653241274, "percentage": 71.54, "elapsed_time": "1 day, 16:19:47", "remaining_time": "16:02:43"}
|
| 1307 |
+
{"current_steps": 6535, "total_steps": 9128, "loss": 0.1736, "lr": 9.059688871053426e-06, "epoch": 5.01150747986191, "percentage": 71.59, "elapsed_time": "1 day, 16:22:43", "remaining_time": "16:01:18"}
|
| 1308 |
+
{"current_steps": 6540, "total_steps": 9128, "loss": 0.1684, "lr": 9.027695528023632e-06, "epoch": 5.015343306482547, "percentage": 71.65, "elapsed_time": "1 day, 16:25:46", "remaining_time": "15:59:55"}
|
| 1309 |
+
{"current_steps": 6545, "total_steps": 9128, "loss": 0.1726, "lr": 8.995742301429274e-06, "epoch": 5.019179133103184, "percentage": 71.7, "elapsed_time": "1 day, 16:28:49", "remaining_time": "15:58:32"}
|
| 1310 |
+
{"current_steps": 6550, "total_steps": 9128, "loss": 0.18, "lr": 8.963829308096266e-06, "epoch": 5.02301495972382, "percentage": 71.76, "elapsed_time": "1 day, 16:31:53", "remaining_time": "15:57:09"}
|
| 1311 |
+
{"current_steps": 6555, "total_steps": 9128, "loss": 0.184, "lr": 8.931956664703427e-06, "epoch": 5.026850786344458, "percentage": 71.81, "elapsed_time": "1 day, 16:34:46", "remaining_time": "15:55:42"}
|
| 1312 |
+
{"current_steps": 6560, "total_steps": 9128, "loss": 0.1693, "lr": 8.900124487782056e-06, "epoch": 5.030686612965094, "percentage": 71.87, "elapsed_time": "1 day, 16:37:42", "remaining_time": "15:54:16"}
|
| 1313 |
+
{"current_steps": 6565, "total_steps": 9128, "loss": 0.1648, "lr": 8.868332893715486e-06, "epoch": 5.03452243958573, "percentage": 71.92, "elapsed_time": "1 day, 16:40:11", "remaining_time": "15:52:39"}
|
| 1314 |
+
{"current_steps": 6570, "total_steps": 9128, "loss": 0.1567, "lr": 8.836581998738705e-06, "epoch": 5.038358266206368, "percentage": 71.98, "elapsed_time": "1 day, 16:43:01", "remaining_time": "15:51:10"}
|
| 1315 |
+
{"current_steps": 6575, "total_steps": 9128, "loss": 0.1721, "lr": 8.804871918937852e-06, "epoch": 5.042194092827004, "percentage": 72.03, "elapsed_time": "1 day, 16:45:51", "remaining_time": "15:49:41"}
|
| 1316 |
+
{"current_steps": 6580, "total_steps": 9128, "loss": 0.1647, "lr": 8.773202770249871e-06, "epoch": 5.046029919447641, "percentage": 72.09, "elapsed_time": "1 day, 16:48:37", "remaining_time": "15:48:11"}
|
| 1317 |
+
{"current_steps": 6585, "total_steps": 9128, "loss": 0.1668, "lr": 8.741574668462053e-06, "epoch": 5.049865746068278, "percentage": 72.14, "elapsed_time": "1 day, 16:51:27", "remaining_time": "15:46:42"}
|
| 1318 |
+
{"current_steps": 6590, "total_steps": 9128, "loss": 0.1595, "lr": 8.709987729211604e-06, "epoch": 5.053701572688914, "percentage": 72.2, "elapsed_time": "1 day, 16:54:19", "remaining_time": "15:45:13"}
|
| 1319 |
+
{"current_steps": 6595, "total_steps": 9128, "loss": 0.1673, "lr": 8.678442067985244e-06, "epoch": 5.057537399309552, "percentage": 72.25, "elapsed_time": "1 day, 16:57:01", "remaining_time": "15:43:41"}
|
| 1320 |
+
{"current_steps": 6600, "total_steps": 9128, "loss": 0.1686, "lr": 8.64693780011877e-06, "epoch": 5.061373225930188, "percentage": 72.3, "elapsed_time": "1 day, 16:59:44", "remaining_time": "15:42:09"}
|
| 1321 |
+
{"current_steps": 6605, "total_steps": 9128, "loss": 0.1635, "lr": 8.615475040796631e-06, "epoch": 5.065209052550824, "percentage": 72.36, "elapsed_time": "1 day, 17:03:53", "remaining_time": "15:41:09"}
|
| 1322 |
+
{"current_steps": 6610, "total_steps": 9128, "loss": 0.1704, "lr": 8.58405390505154e-06, "epoch": 5.069044879171462, "percentage": 72.41, "elapsed_time": "1 day, 17:06:43", "remaining_time": "15:39:40"}
|