Training in progress, step 320
Browse files- model-00001-of-00002.safetensors +1 -1
- model-00002-of-00002.safetensors +1 -1
- trainer_log.jsonl +34 -0
model-00001-of-00002.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4969539560
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fbb5a892c7bcd146f6eee0ac485a21efd55a8ffbc4d42c3ed0640fc44f041c63
|
| 3 |
size 4969539560
|
model-00002-of-00002.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1912795688
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0f51a049f43d70a0eb667a892f9ae752e6fde71c884bf47a93a4de8f13fcb645
|
| 3 |
size 1912795688
|
trainer_log.jsonl
CHANGED
|
@@ -798,3 +798,37 @@
|
|
| 798 |
{"current_steps": 303, "total_steps": 400, "loss": 0.6863, "lr": 2.547734369542718e-08, "epoch": 75.87272727272727, "percentage": 75.75, "elapsed_time": "0:36:54", "remaining_time": "0:11:49"}
|
| 799 |
{"current_steps": 304, "total_steps": 400, "loss": 0.648, "lr": 2.5182097830291825e-08, "epoch": 76.0, "percentage": 76.0, "elapsed_time": "0:36:58", "remaining_time": "0:11:40"}
|
| 800 |
{"current_steps": 304, "total_steps": 400, "eval_loss": 0.6407743096351624, "epoch": 76.0, "percentage": 76.0, "elapsed_time": "0:36:58", "remaining_time": "0:11:40"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 798 |
{"current_steps": 303, "total_steps": 400, "loss": 0.6863, "lr": 2.547734369542718e-08, "epoch": 75.87272727272727, "percentage": 75.75, "elapsed_time": "0:36:54", "remaining_time": "0:11:49"}
|
| 799 |
{"current_steps": 304, "total_steps": 400, "loss": 0.648, "lr": 2.5182097830291825e-08, "epoch": 76.0, "percentage": 76.0, "elapsed_time": "0:36:58", "remaining_time": "0:11:40"}
|
| 800 |
{"current_steps": 304, "total_steps": 400, "eval_loss": 0.6407743096351624, "epoch": 76.0, "percentage": 76.0, "elapsed_time": "0:36:58", "remaining_time": "0:11:40"}
|
| 801 |
+
{"current_steps": 305, "total_steps": 400, "loss": 0.6552, "lr": 2.4889122713851394e-08, "epoch": 76.2909090909091, "percentage": 76.25, "elapsed_time": "0:37:24", "remaining_time": "0:11:38"}
|
| 802 |
+
{"current_steps": 306, "total_steps": 400, "loss": 0.6147, "lr": 2.4598440657295288e-08, "epoch": 76.58181818181818, "percentage": 76.5, "elapsed_time": "0:37:30", "remaining_time": "0:11:31"}
|
| 803 |
+
{"current_steps": 307, "total_steps": 400, "loss": 0.7181, "lr": 2.4310073797187574e-08, "epoch": 76.87272727272727, "percentage": 76.75, "elapsed_time": "0:37:37", "remaining_time": "0:11:23"}
|
| 804 |
+
{"current_steps": 308, "total_steps": 400, "loss": 0.6115, "lr": 2.4024044093781064e-08, "epoch": 77.0, "percentage": 77.0, "elapsed_time": "0:37:40", "remaining_time": "0:11:15"}
|
| 805 |
+
{"current_steps": 309, "total_steps": 400, "loss": 0.7065, "lr": 2.3740373329345117e-08, "epoch": 77.2909090909091, "percentage": 77.25, "elapsed_time": "0:37:47", "remaining_time": "0:11:07"}
|
| 806 |
+
{"current_steps": 310, "total_steps": 400, "loss": 0.6265, "lr": 2.3459083106506712e-08, "epoch": 77.58181818181818, "percentage": 77.5, "elapsed_time": "0:37:54", "remaining_time": "0:11:00"}
|
| 807 |
+
{"current_steps": 311, "total_steps": 400, "loss": 0.629, "lr": 2.3180194846605363e-08, "epoch": 77.87272727272727, "percentage": 77.75, "elapsed_time": "0:38:01", "remaining_time": "0:10:52"}
|
| 808 |
+
{"current_steps": 312, "total_steps": 400, "loss": 0.6626, "lr": 2.2903729788061836e-08, "epoch": 78.0, "percentage": 78.0, "elapsed_time": "0:38:04", "remaining_time": "0:10:44"}
|
| 809 |
+
{"current_steps": 313, "total_steps": 400, "loss": 0.7006, "lr": 2.2629708984760707e-08, "epoch": 78.2909090909091, "percentage": 78.25, "elapsed_time": "0:38:11", "remaining_time": "0:10:36"}
|
| 810 |
+
{"current_steps": 314, "total_steps": 400, "loss": 0.6363, "lr": 2.2358153304447067e-08, "epoch": 78.58181818181818, "percentage": 78.5, "elapsed_time": "0:38:18", "remaining_time": "0:10:29"}
|
| 811 |
+
{"current_steps": 315, "total_steps": 400, "loss": 0.6307, "lr": 2.2089083427137328e-08, "epoch": 78.87272727272727, "percentage": 78.75, "elapsed_time": "0:38:24", "remaining_time": "0:10:21"}
|
| 812 |
+
{"current_steps": 316, "total_steps": 400, "loss": 0.6594, "lr": 2.182251984354442e-08, "epoch": 79.0, "percentage": 79.0, "elapsed_time": "0:38:27", "remaining_time": "0:10:13"}
|
| 813 |
+
{"current_steps": 317, "total_steps": 400, "loss": 0.6261, "lr": 2.1558482853517254e-08, "epoch": 79.2909090909091, "percentage": 79.25, "elapsed_time": "0:38:34", "remaining_time": "0:10:06"}
|
| 814 |
+
{"current_steps": 318, "total_steps": 400, "loss": 0.6303, "lr": 2.1296992564494903e-08, "epoch": 79.58181818181818, "percentage": 79.5, "elapsed_time": "0:38:41", "remaining_time": "0:09:58"}
|
| 815 |
+
{"current_steps": 319, "total_steps": 400, "loss": 0.6847, "lr": 2.103806888997526e-08, "epoch": 79.87272727272727, "percentage": 79.75, "elapsed_time": "0:38:47", "remaining_time": "0:09:51"}
|
| 816 |
+
{"current_steps": 320, "total_steps": 400, "loss": 0.704, "lr": 2.078173154799861e-08, "epoch": 80.0, "percentage": 80.0, "elapsed_time": "0:38:51", "remaining_time": "0:09:42"}
|
| 817 |
+
{"current_steps": 320, "total_steps": 400, "eval_loss": 0.6397803425788879, "epoch": 80.0, "percentage": 80.0, "elapsed_time": "0:38:51", "remaining_time": "0:09:42"}
|
| 818 |
+
{"current_steps": 321, "total_steps": 400, "loss": 0.6742, "lr": 2.0528000059645996e-08, "epoch": 80.2909090909091, "percentage": 80.25, "elapsed_time": "0:39:22", "remaining_time": "0:09:41"}
|
| 819 |
+
{"current_steps": 322, "total_steps": 400, "loss": 0.6589, "lr": 2.027689374755261e-08, "epoch": 80.58181818181818, "percentage": 80.5, "elapsed_time": "0:39:29", "remaining_time": "0:09:33"}
|
| 820 |
+
{"current_steps": 323, "total_steps": 400, "loss": 0.6384, "lr": 2.0028431734436306e-08, "epoch": 80.87272727272727, "percentage": 80.75, "elapsed_time": "0:39:37", "remaining_time": "0:09:26"}
|
| 821 |
+
{"current_steps": 324, "total_steps": 400, "loss": 0.6523, "lr": 1.9782632941641373e-08, "epoch": 81.0, "percentage": 81.0, "elapsed_time": "0:39:40", "remaining_time": "0:09:18"}
|
| 822 |
+
{"current_steps": 325, "total_steps": 400, "loss": 0.7186, "lr": 1.9539516087697516e-08, "epoch": 81.2909090909091, "percentage": 81.25, "elapsed_time": "0:39:47", "remaining_time": "0:09:10"}
|
| 823 |
+
{"current_steps": 326, "total_steps": 400, "loss": 0.7155, "lr": 1.9299099686894422e-08, "epoch": 81.58181818181818, "percentage": 81.5, "elapsed_time": "0:39:54", "remaining_time": "0:09:03"}
|
| 824 |
+
{"current_steps": 327, "total_steps": 400, "loss": 0.5796, "lr": 1.9061402047871834e-08, "epoch": 81.87272727272727, "percentage": 81.75, "elapsed_time": "0:40:01", "remaining_time": "0:08:56"}
|
| 825 |
+
{"current_steps": 328, "total_steps": 400, "loss": 0.5744, "lr": 1.8826441272225223e-08, "epoch": 82.0, "percentage": 82.0, "elapsed_time": "0:40:04", "remaining_time": "0:08:47"}
|
| 826 |
+
{"current_steps": 329, "total_steps": 400, "loss": 0.6681, "lr": 1.8594235253127372e-08, "epoch": 82.2909090909091, "percentage": 82.25, "elapsed_time": "0:40:11", "remaining_time": "0:08:40"}
|
| 827 |
+
{"current_steps": 330, "total_steps": 400, "loss": 0.7103, "lr": 1.8364801673965642e-08, "epoch": 82.58181818181818, "percentage": 82.5, "elapsed_time": "0:40:17", "remaining_time": "0:08:32"}
|
| 828 |
+
{"current_steps": 331, "total_steps": 400, "loss": 0.5704, "lr": 1.8138158006995365e-08, "epoch": 82.87272727272727, "percentage": 82.75, "elapsed_time": "0:40:25", "remaining_time": "0:08:25"}
|
| 829 |
+
{"current_steps": 332, "total_steps": 400, "loss": 0.7128, "lr": 1.7914321512009295e-08, "epoch": 83.0, "percentage": 83.0, "elapsed_time": "0:40:28", "remaining_time": "0:08:17"}
|
| 830 |
+
{"current_steps": 333, "total_steps": 400, "loss": 0.6072, "lr": 1.7693309235023126e-08, "epoch": 83.2909090909091, "percentage": 83.25, "elapsed_time": "0:40:35", "remaining_time": "0:08:09"}
|
| 831 |
+
{"current_steps": 334, "total_steps": 400, "loss": 0.6525, "lr": 1.7475138006977434e-08, "epoch": 83.58181818181818, "percentage": 83.5, "elapsed_time": "0:40:42", "remaining_time": "0:08:02"}
|
| 832 |
+
{"current_steps": 335, "total_steps": 400, "loss": 0.7323, "lr": 1.7259824442455922e-08, "epoch": 83.87272727272727, "percentage": 83.75, "elapsed_time": "0:40:48", "remaining_time": "0:07:55"}
|
| 833 |
+
{"current_steps": 336, "total_steps": 400, "loss": 0.6316, "lr": 1.704738493842015e-08, "epoch": 84.0, "percentage": 84.0, "elapsed_time": "0:40:51", "remaining_time": "0:07:47"}
|
| 834 |
+
{"current_steps": 336, "total_steps": 400, "eval_loss": 0.6387331485748291, "epoch": 84.0, "percentage": 84.0, "elapsed_time": "0:40:52", "remaining_time": "0:07:47"}
|