Training in progress, step 3800
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:c45affa1c1aefc01695d4a38a42133fe22d3d44c710382a159eab726a0770d18
|
| 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 sha256:938d2cca0bd4d331d70bdf8230e233bd179ec0089959e676789b04e4543efbec
|
| 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 sha256:6912ace6c9b019bd2b40688a5acec21c158e7aa385eee428d089716f012cba56
|
| 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 sha256:8ab5af8d38dc87e73a6e3c1fb2d349e7d7052aa31e4a183759e28f23682e4c3e
|
| 3 |
size 1580230264
|
trainer_log.jsonl
CHANGED
|
@@ -719,3 +719,43 @@
|
|
| 719 |
{"current_steps": 3595, "total_steps": 3850, "loss": 0.1855, "lr": 5.363182604878803e-07, "epoch": 6.536851683348498, "percentage": 93.38, "elapsed_time": "1 day, 0:03:45", "remaining_time": "1:42:24"}
|
| 720 |
{"current_steps": 3600, "total_steps": 3850, "loss": 0.1914, "lr": 5.156625367104973e-07, "epoch": 6.545950864422202, "percentage": 93.51, "elapsed_time": "1 day, 0:05:51", "remaining_time": "1:40:24"}
|
| 721 |
{"current_steps": 3605, "total_steps": 3850, "loss": 0.1788, "lr": 4.954072351587646e-07, "epoch": 6.555050045495905, "percentage": 93.64, "elapsed_time": "1 day, 0:09:10", "remaining_time": "1:38:29"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 719 |
{"current_steps": 3595, "total_steps": 3850, "loss": 0.1855, "lr": 5.363182604878803e-07, "epoch": 6.536851683348498, "percentage": 93.38, "elapsed_time": "1 day, 0:03:45", "remaining_time": "1:42:24"}
|
| 720 |
{"current_steps": 3600, "total_steps": 3850, "loss": 0.1914, "lr": 5.156625367104973e-07, "epoch": 6.545950864422202, "percentage": 93.51, "elapsed_time": "1 day, 0:05:51", "remaining_time": "1:40:24"}
|
| 721 |
{"current_steps": 3605, "total_steps": 3850, "loss": 0.1788, "lr": 4.954072351587646e-07, "epoch": 6.555050045495905, "percentage": 93.64, "elapsed_time": "1 day, 0:09:10", "remaining_time": "1:38:29"}
|
| 722 |
+
{"current_steps": 3610, "total_steps": 3850, "loss": 0.1937, "lr": 4.75552772098975e-07, "epoch": 6.564149226569609, "percentage": 93.77, "elapsed_time": "1 day, 0:11:11", "remaining_time": "1:36:28"}
|
| 723 |
+
{"current_steps": 3615, "total_steps": 3850, "loss": 0.1814, "lr": 4.560995555597969e-07, "epoch": 6.573248407643312, "percentage": 93.9, "elapsed_time": "1 day, 0:13:14", "remaining_time": "1:34:28"}
|
| 724 |
+
{"current_steps": 3620, "total_steps": 3850, "loss": 0.1846, "lr": 4.3704798532388624e-07, "epoch": 6.582347588717015, "percentage": 94.03, "elapsed_time": "1 day, 0:15:03", "remaining_time": "1:32:26"}
|
| 725 |
+
{"current_steps": 3625, "total_steps": 3850, "loss": 0.1878, "lr": 4.1839845291968607e-07, "epoch": 6.591446769790719, "percentage": 94.16, "elapsed_time": "1 day, 0:17:05", "remaining_time": "1:30:26"}
|
| 726 |
+
{"current_steps": 3630, "total_steps": 3850, "loss": 0.177, "lr": 4.001513416133551e-07, "epoch": 6.600545950864422, "percentage": 94.29, "elapsed_time": "1 day, 0:19:10", "remaining_time": "1:28:26"}
|
| 727 |
+
{"current_steps": 3635, "total_steps": 3850, "loss": 0.1786, "lr": 3.823070264009099e-07, "epoch": 6.609645131938126, "percentage": 94.42, "elapsed_time": "1 day, 0:21:19", "remaining_time": "1:26:26"}
|
| 728 |
+
{"current_steps": 3640, "total_steps": 3850, "loss": 0.18, "lr": 3.648658740005107e-07, "epoch": 6.618744313011829, "percentage": 94.55, "elapsed_time": "1 day, 0:23:23", "remaining_time": "1:24:25"}
|
| 729 |
+
{"current_steps": 3645, "total_steps": 3850, "loss": 0.1802, "lr": 3.4782824284492975e-07, "epoch": 6.627843494085532, "percentage": 94.68, "elapsed_time": "1 day, 0:25:22", "remaining_time": "1:22:24"}
|
| 730 |
+
{"current_steps": 3650, "total_steps": 3850, "loss": 0.1736, "lr": 3.31194483074182e-07, "epoch": 6.6369426751592355, "percentage": 94.81, "elapsed_time": "1 day, 0:27:25", "remaining_time": "1:20:24"}
|
| 731 |
+
{"current_steps": 3655, "total_steps": 3850, "loss": 0.1821, "lr": 3.149649365283258e-07, "epoch": 6.646041856232939, "percentage": 94.94, "elapsed_time": "1 day, 0:29:13", "remaining_time": "1:18:23"}
|
| 732 |
+
{"current_steps": 3660, "total_steps": 3850, "loss": 0.1848, "lr": 2.9913993674044904e-07, "epoch": 6.655141037306643, "percentage": 95.06, "elapsed_time": "1 day, 0:31:30", "remaining_time": "1:16:23"}
|
| 733 |
+
{"current_steps": 3665, "total_steps": 3850, "loss": 0.1859, "lr": 2.8371980892979436e-07, "epoch": 6.664240218380346, "percentage": 95.19, "elapsed_time": "1 day, 0:33:38", "remaining_time": "1:14:23"}
|
| 734 |
+
{"current_steps": 3670, "total_steps": 3850, "loss": 0.191, "lr": 2.687048699951067e-07, "epoch": 6.673339399454049, "percentage": 95.32, "elapsed_time": "1 day, 0:35:45", "remaining_time": "1:12:22"}
|
| 735 |
+
{"current_steps": 3675, "total_steps": 3850, "loss": 0.1877, "lr": 2.5409542850808765e-07, "epoch": 6.682438580527752, "percentage": 95.45, "elapsed_time": "1 day, 0:37:46", "remaining_time": "1:10:22"}
|
| 736 |
+
{"current_steps": 3680, "total_steps": 3850, "loss": 0.18, "lr": 2.3989178470707364e-07, "epoch": 6.691537761601456, "percentage": 95.58, "elapsed_time": "1 day, 0:39:45", "remaining_time": "1:08:21"}
|
| 737 |
+
{"current_steps": 3685, "total_steps": 3850, "loss": 0.1881, "lr": 2.260942304908609e-07, "epoch": 6.7006369426751595, "percentage": 95.71, "elapsed_time": "1 day, 0:41:35", "remaining_time": "1:06:20"}
|
| 738 |
+
{"current_steps": 3690, "total_steps": 3850, "loss": 0.2003, "lr": 2.1270304941271025e-07, "epoch": 6.709736123748863, "percentage": 95.84, "elapsed_time": "1 day, 0:43:24", "remaining_time": "1:04:19"}
|
| 739 |
+
{"current_steps": 3695, "total_steps": 3850, "loss": 0.193, "lr": 1.9971851667451413e-07, "epoch": 6.718835304822566, "percentage": 95.97, "elapsed_time": "1 day, 0:45:22", "remaining_time": "1:02:18"}
|
| 740 |
+
{"current_steps": 3700, "total_steps": 3850, "loss": 0.187, "lr": 1.8714089912113876e-07, "epoch": 6.727934485896269, "percentage": 96.1, "elapsed_time": "1 day, 0:47:22", "remaining_time": "1:00:17"}
|
| 741 |
+
{"current_steps": 3705, "total_steps": 3850, "loss": 0.1944, "lr": 1.749704552349507e-07, "epoch": 6.737033666969973, "percentage": 96.23, "elapsed_time": "1 day, 0:49:24", "remaining_time": "0:58:17"}
|
| 742 |
+
{"current_steps": 3710, "total_steps": 3850, "loss": 0.1774, "lr": 1.6320743513049686e-07, "epoch": 6.746132848043676, "percentage": 96.36, "elapsed_time": "1 day, 0:51:21", "remaining_time": "0:56:16"}
|
| 743 |
+
{"current_steps": 3715, "total_steps": 3850, "loss": 0.1839, "lr": 1.5185208054936394e-07, "epoch": 6.755232029117379, "percentage": 96.49, "elapsed_time": "1 day, 0:53:29", "remaining_time": "0:54:16"}
|
| 744 |
+
{"current_steps": 3720, "total_steps": 3850, "loss": 0.1892, "lr": 1.4090462485521816e-07, "epoch": 6.764331210191083, "percentage": 96.62, "elapsed_time": "1 day, 0:55:27", "remaining_time": "0:52:15"}
|
| 745 |
+
{"current_steps": 3725, "total_steps": 3850, "loss": 0.1857, "lr": 1.303652930289956e-07, "epoch": 6.773430391264786, "percentage": 96.75, "elapsed_time": "1 day, 0:57:21", "remaining_time": "0:50:14"}
|
| 746 |
+
{"current_steps": 3730, "total_steps": 3850, "loss": 0.1913, "lr": 1.2023430166429485e-07, "epoch": 6.78252957233849, "percentage": 96.88, "elapsed_time": "1 day, 0:59:20", "remaining_time": "0:48:14"}
|
| 747 |
+
{"current_steps": 3735, "total_steps": 3850, "loss": 0.182, "lr": 1.1051185896291616e-07, "epoch": 6.791628753412192, "percentage": 97.01, "elapsed_time": "1 day, 1:01:13", "remaining_time": "0:46:13"}
|
| 748 |
+
{"current_steps": 3740, "total_steps": 3850, "loss": 0.1607, "lr": 1.011981647305782e-07, "epoch": 6.800727934485896, "percentage": 97.14, "elapsed_time": "1 day, 1:03:15", "remaining_time": "0:44:12"}
|
| 749 |
+
{"current_steps": 3745, "total_steps": 3850, "loss": 0.1792, "lr": 9.22934103728279e-08, "epoch": 6.8098271155595995, "percentage": 97.27, "elapsed_time": "1 day, 1:05:26", "remaining_time": "0:42:12"}
|
| 750 |
+
{"current_steps": 3750, "total_steps": 3850, "loss": 0.17, "lr": 8.37977788910882e-08, "epoch": 6.818926296633303, "percentage": 97.4, "elapsed_time": "1 day, 1:07:29", "remaining_time": "0:40:11"}
|
| 751 |
+
{"current_steps": 3755, "total_steps": 3850, "loss": 0.1922, "lr": 7.571144487891202e-08, "epoch": 6.828025477707007, "percentage": 97.53, "elapsed_time": "1 day, 1:09:33", "remaining_time": "0:38:11"}
|
| 752 |
+
{"current_steps": 3760, "total_steps": 3850, "loss": 0.1849, "lr": 6.803457451838746e-08, "epoch": 6.837124658780709, "percentage": 97.66, "elapsed_time": "1 day, 1:11:25", "remaining_time": "0:36:10"}
|
| 753 |
+
{"current_steps": 3765, "total_steps": 3850, "loss": 0.1717, "lr": 6.076732557672272e-08, "epoch": 6.846223839854413, "percentage": 97.79, "elapsed_time": "1 day, 1:13:13", "remaining_time": "0:34:09"}
|
| 754 |
+
{"current_steps": 3770, "total_steps": 3850, "loss": 0.1945, "lr": 5.390984740299976e-08, "epoch": 6.855323020928116, "percentage": 97.92, "elapsed_time": "1 day, 1:15:05", "remaining_time": "0:32:09"}
|
| 755 |
+
{"current_steps": 3775, "total_steps": 3850, "loss": 0.1769, "lr": 4.7462280925116847e-08, "epoch": 6.86442220200182, "percentage": 98.05, "elapsed_time": "1 day, 1:17:16", "remaining_time": "0:30:08"}
|
| 756 |
+
{"current_steps": 3780, "total_steps": 3850, "loss": 0.1898, "lr": 4.142475864688411e-08, "epoch": 6.8735213830755235, "percentage": 98.18, "elapsed_time": "1 day, 1:19:05", "remaining_time": "0:28:07"}
|
| 757 |
+
{"current_steps": 3785, "total_steps": 3850, "loss": 0.189, "lr": 3.5797404645296906e-08, "epoch": 6.882620564149226, "percentage": 98.31, "elapsed_time": "1 day, 1:21:10", "remaining_time": "0:26:07"}
|
| 758 |
+
{"current_steps": 3790, "total_steps": 3850, "loss": 0.189, "lr": 3.0580334567995585e-08, "epoch": 6.89171974522293, "percentage": 98.44, "elapsed_time": "1 day, 1:23:08", "remaining_time": "0:24:06"}
|
| 759 |
+
{"current_steps": 3795, "total_steps": 3850, "loss": 0.1956, "lr": 2.5773655630880746e-08, "epoch": 6.900818926296633, "percentage": 98.57, "elapsed_time": "1 day, 1:25:06", "remaining_time": "0:22:06"}
|
| 760 |
+
{"current_steps": 3800, "total_steps": 3850, "loss": 0.1808, "lr": 2.1377466615912778e-08, "epoch": 6.909918107370337, "percentage": 98.7, "elapsed_time": "1 day, 1:27:05", "remaining_time": "0:20:05"}
|
| 761 |
+
{"current_steps": 3805, "total_steps": 3850, "loss": 0.1794, "lr": 1.7391857869086815e-08, "epoch": 6.91901728844404, "percentage": 98.83, "elapsed_time": "1 day, 1:30:03", "remaining_time": "0:18:05"}
|