Training in progress, step 7400
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 sha256:6e2c45306981e5c74f700425c572edf461ef9fcf600583b67e22e52837ec5f06
|
| 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:db8f15a5201ab6cc445c8a4a097991d0614fda600812bd1269e0419f37d47f03
|
| 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 sha256:1bacb5fb4250e7fc9e487028d3308866772a5f2dc36ab8dd98da2e931a3b16fe
|
| 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 sha256:57a55495ae17b6bb8c82dad01a9f10f2eeed43cc8c5b989fcf6ce5d0b78df101
|
| 3 |
size 1580230264
|
trainer_log.jsonl
CHANGED
|
@@ -1441,3 +1441,41 @@
|
|
| 1441 |
{"current_steps": 7205, "total_steps": 8603, "loss": 0.0917, "lr": 3.137139089159109e-06, "epoch": 5.862840862840863, "percentage": 83.75, "elapsed_time": "1 day, 20:17:47", "remaining_time": "8:35:41"}
|
| 1442 |
{"current_steps": 7210, "total_steps": 8603, "loss": 0.0711, "lr": 3.1153551504550397e-06, "epoch": 5.866910866910867, "percentage": 83.81, "elapsed_time": "1 day, 20:19:23", "remaining_time": "8:33:48"}
|
| 1443 |
{"current_steps": 7215, "total_steps": 8603, "loss": 0.0659, "lr": 3.0936407182159333e-06, "epoch": 5.870980870980871, "percentage": 83.87, "elapsed_time": "1 day, 20:20:57", "remaining_time": "8:31:54"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1441 |
{"current_steps": 7205, "total_steps": 8603, "loss": 0.0917, "lr": 3.137139089159109e-06, "epoch": 5.862840862840863, "percentage": 83.75, "elapsed_time": "1 day, 20:17:47", "remaining_time": "8:35:41"}
|
| 1442 |
{"current_steps": 7210, "total_steps": 8603, "loss": 0.0711, "lr": 3.1153551504550397e-06, "epoch": 5.866910866910867, "percentage": 83.81, "elapsed_time": "1 day, 20:19:23", "remaining_time": "8:33:48"}
|
| 1443 |
{"current_steps": 7215, "total_steps": 8603, "loss": 0.0659, "lr": 3.0936407182159333e-06, "epoch": 5.870980870980871, "percentage": 83.87, "elapsed_time": "1 day, 20:20:57", "remaining_time": "8:31:54"}
|
| 1444 |
+
{"current_steps": 7220, "total_steps": 8603, "loss": 0.0841, "lr": 3.0719958818303165e-06, "epoch": 5.875050875050875, "percentage": 83.92, "elapsed_time": "1 day, 20:22:50", "remaining_time": "8:30:04"}
|
| 1445 |
+
{"current_steps": 7225, "total_steps": 8603, "loss": 0.0782, "lr": 3.050420730400212e-06, "epoch": 5.8791208791208796, "percentage": 83.98, "elapsed_time": "1 day, 20:24:31", "remaining_time": "8:28:11"}
|
| 1446 |
+
{"current_steps": 7230, "total_steps": 8603, "loss": 0.0613, "lr": 3.0289153527407842e-06, "epoch": 5.883190883190883, "percentage": 84.04, "elapsed_time": "1 day, 20:26:13", "remaining_time": "8:26:19"}
|
| 1447 |
+
{"current_steps": 7235, "total_steps": 8603, "loss": 0.0713, "lr": 3.007479837379974e-06, "epoch": 5.887260887260887, "percentage": 84.1, "elapsed_time": "1 day, 20:28:09", "remaining_time": "8:24:29"}
|
| 1448 |
+
{"current_steps": 7240, "total_steps": 8603, "loss": 0.068, "lr": 2.9861142725581225e-06, "epoch": 5.891330891330892, "percentage": 84.16, "elapsed_time": "1 day, 20:29:50", "remaining_time": "8:22:37"}
|
| 1449 |
+
{"current_steps": 7245, "total_steps": 8603, "loss": 0.0586, "lr": 2.96481874622762e-06, "epoch": 5.895400895400895, "percentage": 84.21, "elapsed_time": "1 day, 20:31:27", "remaining_time": "8:20:44"}
|
| 1450 |
+
{"current_steps": 7250, "total_steps": 8603, "loss": 0.082, "lr": 2.94359334605254e-06, "epoch": 5.8994708994708995, "percentage": 84.27, "elapsed_time": "1 day, 20:33:07", "remaining_time": "8:18:51"}
|
| 1451 |
+
{"current_steps": 7255, "total_steps": 8603, "loss": 0.0917, "lr": 2.9224381594082807e-06, "epoch": 5.903540903540904, "percentage": 84.33, "elapsed_time": "1 day, 20:35:01", "remaining_time": "8:17:01"}
|
| 1452 |
+
{"current_steps": 7260, "total_steps": 8603, "loss": 0.0702, "lr": 2.9013532733812e-06, "epoch": 5.907610907610907, "percentage": 84.39, "elapsed_time": "1 day, 20:36:41", "remaining_time": "8:15:09"}
|
| 1453 |
+
{"current_steps": 7265, "total_steps": 8603, "loss": 0.0819, "lr": 2.880338774768263e-06, "epoch": 5.911680911680912, "percentage": 84.45, "elapsed_time": "1 day, 20:38:22", "remaining_time": "8:13:16"}
|
| 1454 |
+
{"current_steps": 7270, "total_steps": 8603, "loss": 0.0921, "lr": 2.8593947500766805e-06, "epoch": 5.915750915750916, "percentage": 84.51, "elapsed_time": "1 day, 20:39:58", "remaining_time": "8:11:23"}
|
| 1455 |
+
{"current_steps": 7275, "total_steps": 8603, "loss": 0.0668, "lr": 2.8385212855235477e-06, "epoch": 5.9198209198209195, "percentage": 84.56, "elapsed_time": "1 day, 20:41:28", "remaining_time": "8:09:29"}
|
| 1456 |
+
{"current_steps": 7280, "total_steps": 8603, "loss": 0.0741, "lr": 2.8177184670355063e-06, "epoch": 5.923890923890924, "percentage": 84.62, "elapsed_time": "1 day, 20:43:00", "remaining_time": "8:07:35"}
|
| 1457 |
+
{"current_steps": 7285, "total_steps": 8603, "loss": 0.0666, "lr": 2.7969863802483676e-06, "epoch": 5.927960927960928, "percentage": 84.68, "elapsed_time": "1 day, 20:44:33", "remaining_time": "8:05:41"}
|
| 1458 |
+
{"current_steps": 7290, "total_steps": 8603, "loss": 0.1139, "lr": 2.7763251105067813e-06, "epoch": 5.932030932030932, "percentage": 84.74, "elapsed_time": "1 day, 20:46:26", "remaining_time": "8:03:51"}
|
| 1459 |
+
{"current_steps": 7295, "total_steps": 8603, "loss": 0.0935, "lr": 2.755734742863876e-06, "epoch": 5.936100936100936, "percentage": 84.8, "elapsed_time": "1 day, 20:48:31", "remaining_time": "8:02:03"}
|
| 1460 |
+
{"current_steps": 7300, "total_steps": 8603, "loss": 0.0704, "lr": 2.7352153620809053e-06, "epoch": 5.94017094017094, "percentage": 84.85, "elapsed_time": "1 day, 20:50:08", "remaining_time": "8:00:10"}
|
| 1461 |
+
{"current_steps": 7305, "total_steps": 8603, "loss": 0.0699, "lr": 2.7147670526268986e-06, "epoch": 5.944240944240944, "percentage": 84.91, "elapsed_time": "1 day, 20:51:42", "remaining_time": "7:58:16"}
|
| 1462 |
+
{"current_steps": 7310, "total_steps": 8603, "loss": 0.07, "lr": 2.694389898678327e-06, "epoch": 5.948310948310948, "percentage": 84.97, "elapsed_time": "1 day, 20:53:14", "remaining_time": "7:56:22"}
|
| 1463 |
+
{"current_steps": 7315, "total_steps": 8603, "loss": 0.0641, "lr": 2.674083984118736e-06, "epoch": 5.9523809523809526, "percentage": 85.03, "elapsed_time": "1 day, 20:54:43", "remaining_time": "7:54:28"}
|
| 1464 |
+
{"current_steps": 7320, "total_steps": 8603, "loss": 0.0865, "lr": 2.65384939253841e-06, "epoch": 5.956450956450956, "percentage": 85.09, "elapsed_time": "1 day, 20:56:15", "remaining_time": "7:52:34"}
|
| 1465 |
+
{"current_steps": 7325, "total_steps": 8603, "loss": 0.0624, "lr": 2.6336862072340343e-06, "epoch": 5.96052096052096, "percentage": 85.14, "elapsed_time": "1 day, 20:57:51", "remaining_time": "7:50:41"}
|
| 1466 |
+
{"current_steps": 7330, "total_steps": 8603, "loss": 0.0677, "lr": 2.6135945112083506e-06, "epoch": 5.964590964590965, "percentage": 85.2, "elapsed_time": "1 day, 20:59:21", "remaining_time": "7:48:47"}
|
| 1467 |
+
{"current_steps": 7335, "total_steps": 8603, "loss": 0.0682, "lr": 2.593574387169804e-06, "epoch": 5.968660968660968, "percentage": 85.26, "elapsed_time": "1 day, 21:00:59", "remaining_time": "7:46:55"}
|
| 1468 |
+
{"current_steps": 7340, "total_steps": 8603, "loss": 0.0731, "lr": 2.573625917532212e-06, "epoch": 5.9727309727309725, "percentage": 85.32, "elapsed_time": "1 day, 21:02:45", "remaining_time": "7:45:03"}
|
| 1469 |
+
{"current_steps": 7345, "total_steps": 8603, "loss": 0.0649, "lr": 2.553749184414429e-06, "epoch": 5.976800976800977, "percentage": 85.38, "elapsed_time": "1 day, 21:04:31", "remaining_time": "7:43:12"}
|
| 1470 |
+
{"current_steps": 7350, "total_steps": 8603, "loss": 0.0713, "lr": 2.5339442696399897e-06, "epoch": 5.980870980870981, "percentage": 85.44, "elapsed_time": "1 day, 21:06:13", "remaining_time": "7:41:20"}
|
| 1471 |
+
{"current_steps": 7355, "total_steps": 8603, "loss": 0.0932, "lr": 2.5142112547368005e-06, "epoch": 5.984940984940985, "percentage": 85.49, "elapsed_time": "1 day, 21:08:40", "remaining_time": "7:39:36"}
|
| 1472 |
+
{"current_steps": 7360, "total_steps": 8603, "loss": 0.1331, "lr": 2.494550220936773e-06, "epoch": 5.989010989010989, "percentage": 85.55, "elapsed_time": "1 day, 21:10:55", "remaining_time": "7:37:50"}
|
| 1473 |
+
{"current_steps": 7365, "total_steps": 8603, "loss": 0.0711, "lr": 2.4749612491755158e-06, "epoch": 5.993080993080993, "percentage": 85.61, "elapsed_time": "1 day, 21:12:41", "remaining_time": "7:35:58"}
|
| 1474 |
+
{"current_steps": 7370, "total_steps": 8603, "loss": 0.0662, "lr": 2.4554444200919882e-06, "epoch": 5.997150997150997, "percentage": 85.67, "elapsed_time": "1 day, 21:14:17", "remaining_time": "7:34:06"}
|
| 1475 |
+
{"current_steps": 7375, "total_steps": 8603, "loss": 0.1184, "lr": 2.4359998140281715e-06, "epoch": 6.0008140008140005, "percentage": 85.73, "elapsed_time": "1 day, 21:16:28", "remaining_time": "7:32:18"}
|
| 1476 |
+
{"current_steps": 7380, "total_steps": 8603, "loss": 0.1947, "lr": 2.416627511028733e-06, "epoch": 6.004884004884005, "percentage": 85.78, "elapsed_time": "1 day, 21:19:22", "remaining_time": "7:30:38"}
|
| 1477 |
+
{"current_steps": 7385, "total_steps": 8603, "loss": 0.1772, "lr": 2.39732759084071e-06, "epoch": 6.008954008954009, "percentage": 85.84, "elapsed_time": "1 day, 21:22:08", "remaining_time": "7:28:57"}
|
| 1478 |
+
{"current_steps": 7390, "total_steps": 8603, "loss": 0.1762, "lr": 2.3781001329131593e-06, "epoch": 6.013024013024013, "percentage": 85.9, "elapsed_time": "1 day, 21:25:04", "remaining_time": "7:27:17"}
|
| 1479 |
+
{"current_steps": 7395, "total_steps": 8603, "loss": 0.1657, "lr": 2.358945216396855e-06, "epoch": 6.017094017094017, "percentage": 85.96, "elapsed_time": "1 day, 21:28:07", "remaining_time": "7:25:39"}
|
| 1480 |
+
{"current_steps": 7400, "total_steps": 8603, "loss": 0.1706, "lr": 2.3398629201439427e-06, "epoch": 6.021164021164021, "percentage": 86.02, "elapsed_time": "1 day, 21:31:10", "remaining_time": "7:24:00"}
|
| 1481 |
+
{"current_steps": 7405, "total_steps": 8603, "loss": 0.1833, "lr": 2.3208533227076257e-06, "epoch": 6.025234025234025, "percentage": 86.07, "elapsed_time": "1 day, 21:35:18", "remaining_time": "7:22:31"}
|