Training in progress, step 8800
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 sha256:3678c246b0c544502d09d0df8232b622361f8d445e369a5bd9563fdc6afec285
|
| 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 sha256:30f5add51c1c220daf2aacad6a2104153f2106052fa2a3d2a20884dce75a4501
|
| 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 sha256:1c77b57898eedc3c19f6227aa1c8d7f35c538960e12a3b70ff81847eb3575beb
|
| 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 sha256:6db990d8b83ec36ba7c747815fb996569b3b3348ec2f378fa5157c4ebbfcb157
|
| 3 |
size 1580230264
|
trainer_log.jsonl
CHANGED
|
@@ -1732,3 +1732,43 @@
|
|
| 1732 |
{"current_steps": 8590, "total_steps": 9625, "loss": 0.0965, "lr": 1.3952990013963264e-06, "epoch": 6.2480902146235, "percentage": 89.25, "elapsed_time": "9:11:30", "remaining_time": "1:06:27"}
|
| 1733 |
{"current_steps": 8595, "total_steps": 9625, "loss": 0.0738, "lr": 1.3820202930666148e-06, "epoch": 6.251727901054929, "percentage": 89.3, "elapsed_time": "9:13:06", "remaining_time": "1:06:17"}
|
| 1734 |
{"current_steps": 8600, "total_steps": 9625, "loss": 0.0642, "lr": 1.3688028107286888e-06, "epoch": 6.2553655874863585, "percentage": 89.35, "elapsed_time": "9:14:40", "remaining_time": "1:06:06"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1732 |
{"current_steps": 8590, "total_steps": 9625, "loss": 0.0965, "lr": 1.3952990013963264e-06, "epoch": 6.2480902146235, "percentage": 89.25, "elapsed_time": "9:11:30", "remaining_time": "1:06:27"}
|
| 1733 |
{"current_steps": 8595, "total_steps": 9625, "loss": 0.0738, "lr": 1.3820202930666148e-06, "epoch": 6.251727901054929, "percentage": 89.3, "elapsed_time": "9:13:06", "remaining_time": "1:06:17"}
|
| 1734 |
{"current_steps": 8600, "total_steps": 9625, "loss": 0.0642, "lr": 1.3688028107286888e-06, "epoch": 6.2553655874863585, "percentage": 89.35, "elapsed_time": "9:14:40", "remaining_time": "1:06:06"}
|
| 1735 |
+
{"current_steps": 8605, "total_steps": 9625, "loss": 0.0784, "lr": 1.355646597848772e-06, "epoch": 6.259003273917788, "percentage": 89.4, "elapsed_time": "9:17:41", "remaining_time": "1:06:06"}
|
| 1736 |
+
{"current_steps": 8610, "total_steps": 9625, "loss": 0.088, "lr": 1.342551697691623e-06, "epoch": 6.262640960349218, "percentage": 89.45, "elapsed_time": "9:19:35", "remaining_time": "1:05:58"}
|
| 1737 |
+
{"current_steps": 8615, "total_steps": 9625, "loss": 0.0576, "lr": 1.329518153320346e-06, "epoch": 6.2662786467806475, "percentage": 89.51, "elapsed_time": "9:21:06", "remaining_time": "1:05:46"}
|
| 1738 |
+
{"current_steps": 8620, "total_steps": 9625, "loss": 0.0766, "lr": 1.3165460075963022e-06, "epoch": 6.269916333212077, "percentage": 89.56, "elapsed_time": "9:23:11", "remaining_time": "1:05:39"}
|
| 1739 |
+
{"current_steps": 8625, "total_steps": 9625, "loss": 0.0673, "lr": 1.303635303178914e-06, "epoch": 6.273554019643507, "percentage": 89.61, "elapsed_time": "9:24:53", "remaining_time": "1:05:29"}
|
| 1740 |
+
{"current_steps": 8630, "total_steps": 9625, "loss": 0.0591, "lr": 1.2907860825255747e-06, "epoch": 6.2771917060749365, "percentage": 89.66, "elapsed_time": "9:26:31", "remaining_time": "1:05:19"}
|
| 1741 |
+
{"current_steps": 8635, "total_steps": 9625, "loss": 0.0803, "lr": 1.2779983878914637e-06, "epoch": 6.280829392506366, "percentage": 89.71, "elapsed_time": "9:28:10", "remaining_time": "1:05:08"}
|
| 1742 |
+
{"current_steps": 8640, "total_steps": 9625, "loss": 0.0678, "lr": 1.2652722613294465e-06, "epoch": 6.284467078937795, "percentage": 89.77, "elapsed_time": "9:29:54", "remaining_time": "1:04:58"}
|
| 1743 |
+
{"current_steps": 8645, "total_steps": 9625, "loss": 0.0958, "lr": 1.2526077446899177e-06, "epoch": 6.2881047653692255, "percentage": 89.82, "elapsed_time": "9:31:40", "remaining_time": "1:04:48"}
|
| 1744 |
+
{"current_steps": 8650, "total_steps": 9625, "loss": 0.0825, "lr": 1.240004879620651e-06, "epoch": 6.291742451800655, "percentage": 89.87, "elapsed_time": "9:33:19", "remaining_time": "1:04:37"}
|
| 1745 |
+
{"current_steps": 8655, "total_steps": 9625, "loss": 0.0864, "lr": 1.2274637075666962e-06, "epoch": 6.295380138232084, "percentage": 89.92, "elapsed_time": "9:34:54", "remaining_time": "1:04:25"}
|
| 1746 |
+
{"current_steps": 8660, "total_steps": 9625, "loss": 0.0658, "lr": 1.214984269770203e-06, "epoch": 6.299017824663514, "percentage": 89.97, "elapsed_time": "9:36:26", "remaining_time": "1:04:14"}
|
| 1747 |
+
{"current_steps": 8665, "total_steps": 9625, "loss": 0.075, "lr": 1.2025666072703234e-06, "epoch": 6.302655511094944, "percentage": 90.03, "elapsed_time": "9:38:03", "remaining_time": "1:04:02"}
|
| 1748 |
+
{"current_steps": 8670, "total_steps": 9625, "loss": 0.0711, "lr": 1.1902107609030522e-06, "epoch": 6.306293197526373, "percentage": 90.08, "elapsed_time": "9:39:32", "remaining_time": "1:03:50"}
|
| 1749 |
+
{"current_steps": 8675, "total_steps": 9625, "loss": 0.0953, "lr": 1.177916771301091e-06, "epoch": 6.3099308839578025, "percentage": 90.13, "elapsed_time": "9:41:25", "remaining_time": "1:03:40"}
|
| 1750 |
+
{"current_steps": 8680, "total_steps": 9625, "loss": 0.0969, "lr": 1.1656846788937392e-06, "epoch": 6.313568570389233, "percentage": 90.18, "elapsed_time": "9:43:29", "remaining_time": "1:03:31"}
|
| 1751 |
+
{"current_steps": 8685, "total_steps": 9625, "loss": 0.0761, "lr": 1.1535145239067224e-06, "epoch": 6.317206256820662, "percentage": 90.23, "elapsed_time": "9:45:21", "remaining_time": "1:03:21"}
|
| 1752 |
+
{"current_steps": 8690, "total_steps": 9625, "loss": 0.0722, "lr": 1.1414063463621105e-06, "epoch": 6.3208439432520915, "percentage": 90.29, "elapsed_time": "9:46:54", "remaining_time": "1:03:08"}
|
| 1753 |
+
{"current_steps": 8695, "total_steps": 9625, "loss": 0.0703, "lr": 1.1293601860781366e-06, "epoch": 6.324481629683521, "percentage": 90.34, "elapsed_time": "9:48:25", "remaining_time": "1:02:56"}
|
| 1754 |
+
{"current_steps": 8700, "total_steps": 9625, "loss": 0.062, "lr": 1.1173760826690927e-06, "epoch": 6.328119316114951, "percentage": 90.39, "elapsed_time": "9:49:56", "remaining_time": "1:02:43"}
|
| 1755 |
+
{"current_steps": 8705, "total_steps": 9625, "loss": 0.0716, "lr": 1.1054540755451936e-06, "epoch": 6.3317570025463805, "percentage": 90.44, "elapsed_time": "9:51:25", "remaining_time": "1:02:30"}
|
| 1756 |
+
{"current_steps": 8710, "total_steps": 9625, "loss": 0.0717, "lr": 1.093594203912456e-06, "epoch": 6.33539468897781, "percentage": 90.49, "elapsed_time": "9:52:58", "remaining_time": "1:02:17"}
|
| 1757 |
+
{"current_steps": 8715, "total_steps": 9625, "loss": 0.0654, "lr": 1.0817965067725544e-06, "epoch": 6.33903237540924, "percentage": 90.55, "elapsed_time": "9:54:31", "remaining_time": "1:02:04"}
|
| 1758 |
+
{"current_steps": 8720, "total_steps": 9625, "loss": 0.0655, "lr": 1.0700610229226992e-06, "epoch": 6.3426700618406695, "percentage": 90.6, "elapsed_time": "9:56:07", "remaining_time": "1:01:52"}
|
| 1759 |
+
{"current_steps": 8725, "total_steps": 9625, "loss": 0.075, "lr": 1.0583877909555106e-06, "epoch": 6.346307748272099, "percentage": 90.65, "elapsed_time": "9:57:43", "remaining_time": "1:01:39"}
|
| 1760 |
+
{"current_steps": 8730, "total_steps": 9625, "loss": 0.0635, "lr": 1.0467768492588904e-06, "epoch": 6.349945434703528, "percentage": 90.7, "elapsed_time": "9:59:45", "remaining_time": "1:01:29"}
|
| 1761 |
+
{"current_steps": 8735, "total_steps": 9625, "loss": 0.0671, "lr": 1.0352282360159016e-06, "epoch": 6.3535831211349585, "percentage": 90.75, "elapsed_time": "10:01:31", "remaining_time": "1:01:17"}
|
| 1762 |
+
{"current_steps": 8740, "total_steps": 9625, "loss": 0.0721, "lr": 1.0237419892046364e-06, "epoch": 6.357220807566388, "percentage": 90.81, "elapsed_time": "10:03:36", "remaining_time": "1:01:07"}
|
| 1763 |
+
{"current_steps": 8745, "total_steps": 9625, "loss": 0.1557, "lr": 1.0123181465980813e-06, "epoch": 6.360858493997817, "percentage": 90.86, "elapsed_time": "10:06:16", "remaining_time": "1:01:00"}
|
| 1764 |
+
{"current_steps": 8750, "total_steps": 9625, "loss": 0.0672, "lr": 1.000956745764019e-06, "epoch": 6.364496180429247, "percentage": 90.91, "elapsed_time": "10:07:55", "remaining_time": "1:00:47"}
|
| 1765 |
+
{"current_steps": 8755, "total_steps": 9625, "loss": 0.0668, "lr": 9.89657824064878e-07, "epoch": 6.368133866860677, "percentage": 90.96, "elapsed_time": "10:09:38", "remaining_time": "1:00:34"}
|
| 1766 |
+
{"current_steps": 8760, "total_steps": 9625, "loss": 0.1042, "lr": 9.784214186576313e-07, "epoch": 6.371771553292106, "percentage": 91.01, "elapsed_time": "10:11:47", "remaining_time": "1:00:24"}
|
| 1767 |
+
{"current_steps": 8765, "total_steps": 9625, "loss": 0.1847, "lr": 9.67247566493661e-07, "epoch": 6.375409239723536, "percentage": 91.06, "elapsed_time": "10:14:50", "remaining_time": "1:00:19"}
|
| 1768 |
+
{"current_steps": 8770, "total_steps": 9625, "loss": 0.1725, "lr": 9.561363043186356e-07, "epoch": 6.379046926154966, "percentage": 91.12, "elapsed_time": "10:17:31", "remaining_time": "1:00:12"}
|
| 1769 |
+
{"current_steps": 8775, "total_steps": 9625, "loss": 0.1719, "lr": 9.450876686723975e-07, "epoch": 6.382684612586395, "percentage": 91.17, "elapsed_time": "10:20:25", "remaining_time": "1:00:05"}
|
| 1770 |
+
{"current_steps": 8780, "total_steps": 9625, "loss": 0.1674, "lr": 9.341016958888449e-07, "epoch": 6.3863222990178246, "percentage": 91.22, "elapsed_time": "10:23:30", "remaining_time": "1:00:00"}
|
| 1771 |
+
{"current_steps": 8785, "total_steps": 9625, "loss": 0.1687, "lr": 9.23178422095794e-07, "epoch": 6.389959985449254, "percentage": 91.27, "elapsed_time": "10:26:33", "remaining_time": "0:59:54"}
|
| 1772 |
+
{"current_steps": 8790, "total_steps": 9625, "loss": 0.1791, "lr": 9.12317883214886e-07, "epoch": 6.393597671880684, "percentage": 91.32, "elapsed_time": "10:29:34", "remaining_time": "0:59:48"}
|
| 1773 |
+
{"current_steps": 8795, "total_steps": 9625, "loss": 0.1781, "lr": 9.015201149614427e-07, "epoch": 6.3972353583121135, "percentage": 91.38, "elapsed_time": "10:32:36", "remaining_time": "0:59:42"}
|
| 1774 |
+
{"current_steps": 8800, "total_steps": 9625, "loss": 0.1657, "lr": 8.907851528443734e-07, "epoch": 6.400873044743543, "percentage": 91.43, "elapsed_time": "10:35:27", "remaining_time": "0:59:34"}
|