Training in progress, step 3600
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 sha256:61c0d7b1745cc8835434a9160868141ffd6f6e20a9d9ddf030a0551a07f67945
|
| 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 sha256:15a2b359361e74cb5815b5486b4141613a3d47af1fec2be820d835377aa1f0c6
|
| 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 sha256:1a5470da6120e1c836c3c99a792d49c8857b3847e0c058b103e512d010569e6e
|
| 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:bb4114dbe0cebe9208006a0bcd8354b7bddbd1eab3af3c02b844ec22ff20b64d
|
| 3 |
size 1580230264
|
trainer_log.jsonl
CHANGED
|
@@ -701,3 +701,43 @@
|
|
| 701 |
{"current_steps": 3390, "total_steps": 6713, "loss": 0.2249, "lr": 2.314358404282699e-05, "epoch": 3.535211267605634, "percentage": 50.5, "elapsed_time": "3:27:13", "remaining_time": "3:23:07"}
|
| 702 |
{"current_steps": 3395, "total_steps": 6713, "loss": 0.239, "lr": 2.309221537116906e-05, "epoch": 3.5404277516953573, "percentage": 50.57, "elapsed_time": "3:28:53", "remaining_time": "3:24:09"}
|
| 703 |
{"current_steps": 3400, "total_steps": 6713, "loss": 0.2318, "lr": 2.3040825792518188e-05, "epoch": 3.5456442357850806, "percentage": 50.65, "elapsed_time": "3:30:33", "remaining_time": "3:25:10"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 701 |
{"current_steps": 3390, "total_steps": 6713, "loss": 0.2249, "lr": 2.314358404282699e-05, "epoch": 3.535211267605634, "percentage": 50.5, "elapsed_time": "3:27:13", "remaining_time": "3:23:07"}
|
| 702 |
{"current_steps": 3395, "total_steps": 6713, "loss": 0.239, "lr": 2.309221537116906e-05, "epoch": 3.5404277516953573, "percentage": 50.57, "elapsed_time": "3:28:53", "remaining_time": "3:24:09"}
|
| 703 |
{"current_steps": 3400, "total_steps": 6713, "loss": 0.2318, "lr": 2.3040825792518188e-05, "epoch": 3.5456442357850806, "percentage": 50.65, "elapsed_time": "3:30:33", "remaining_time": "3:25:10"}
|
| 704 |
+
{"current_steps": 3405, "total_steps": 6713, "loss": 0.2324, "lr": 2.298941565432804e-05, "epoch": 3.5508607198748043, "percentage": 50.72, "elapsed_time": "3:33:26", "remaining_time": "3:27:21"}
|
| 705 |
+
{"current_steps": 3410, "total_steps": 6713, "loss": 0.2323, "lr": 2.2937985304191285e-05, "epoch": 3.556077203964528, "percentage": 50.8, "elapsed_time": "3:35:05", "remaining_time": "3:28:20"}
|
| 706 |
+
{"current_steps": 3415, "total_steps": 6713, "loss": 0.2364, "lr": 2.2886535089837247e-05, "epoch": 3.5612936880542514, "percentage": 50.87, "elapsed_time": "3:36:51", "remaining_time": "3:29:26"}
|
| 707 |
+
{"current_steps": 3420, "total_steps": 6713, "loss": 0.2314, "lr": 2.2835065359129564e-05, "epoch": 3.5665101721439747, "percentage": 50.95, "elapsed_time": "3:38:27", "remaining_time": "3:30:20"}
|
| 708 |
+
{"current_steps": 3425, "total_steps": 6713, "loss": 0.2402, "lr": 2.278357646006381e-05, "epoch": 3.5717266562336984, "percentage": 51.02, "elapsed_time": "3:40:06", "remaining_time": "3:31:17"}
|
| 709 |
+
{"current_steps": 3430, "total_steps": 6713, "loss": 0.2436, "lr": 2.273206874076518e-05, "epoch": 3.576943140323422, "percentage": 51.09, "elapsed_time": "3:41:42", "remaining_time": "3:32:11"}
|
| 710 |
+
{"current_steps": 3435, "total_steps": 6713, "loss": 0.2282, "lr": 2.26805425494861e-05, "epoch": 3.5821596244131455, "percentage": 51.17, "elapsed_time": "3:43:29", "remaining_time": "3:33:16"}
|
| 711 |
+
{"current_steps": 3440, "total_steps": 6713, "loss": 0.2324, "lr": 2.26289982346039e-05, "epoch": 3.587376108502869, "percentage": 51.24, "elapsed_time": "3:45:08", "remaining_time": "3:34:12"}
|
| 712 |
+
{"current_steps": 3445, "total_steps": 6713, "loss": 0.2377, "lr": 2.2577436144618438e-05, "epoch": 3.5925925925925926, "percentage": 51.32, "elapsed_time": "3:46:57", "remaining_time": "3:35:17"}
|
| 713 |
+
{"current_steps": 3450, "total_steps": 6713, "loss": 0.2442, "lr": 2.2525856628149754e-05, "epoch": 3.5978090766823163, "percentage": 51.39, "elapsed_time": "3:48:35", "remaining_time": "3:36:12"}
|
| 714 |
+
{"current_steps": 3455, "total_steps": 6713, "loss": 0.23, "lr": 2.2474260033935718e-05, "epoch": 3.6030255607720396, "percentage": 51.47, "elapsed_time": "3:50:14", "remaining_time": "3:37:06"}
|
| 715 |
+
{"current_steps": 3460, "total_steps": 6713, "loss": 0.2384, "lr": 2.2422646710829653e-05, "epoch": 3.608242044861763, "percentage": 51.54, "elapsed_time": "3:51:55", "remaining_time": "3:38:03"}
|
| 716 |
+
{"current_steps": 3465, "total_steps": 6713, "loss": 0.2329, "lr": 2.2371017007798005e-05, "epoch": 3.6134585289514867, "percentage": 51.62, "elapsed_time": "3:53:39", "remaining_time": "3:39:01"}
|
| 717 |
+
{"current_steps": 3470, "total_steps": 6713, "loss": 0.2279, "lr": 2.231937127391795e-05, "epoch": 3.6186750130412104, "percentage": 51.69, "elapsed_time": "3:55:25", "remaining_time": "3:40:01"}
|
| 718 |
+
{"current_steps": 3475, "total_steps": 6713, "loss": 0.2294, "lr": 2.226770985837507e-05, "epoch": 3.6238914971309337, "percentage": 51.77, "elapsed_time": "3:57:02", "remaining_time": "3:40:52"}
|
| 719 |
+
{"current_steps": 3480, "total_steps": 6713, "loss": 0.2413, "lr": 2.2216033110460952e-05, "epoch": 3.629107981220657, "percentage": 51.84, "elapsed_time": "3:58:44", "remaining_time": "3:41:47"}
|
| 720 |
+
{"current_steps": 3485, "total_steps": 6713, "loss": 0.232, "lr": 2.216434137957087e-05, "epoch": 3.634324465310381, "percentage": 51.91, "elapsed_time": "4:00:28", "remaining_time": "3:42:44"}
|
| 721 |
+
{"current_steps": 3490, "total_steps": 6713, "loss": 0.2414, "lr": 2.2112635015201383e-05, "epoch": 3.6395409494001045, "percentage": 51.99, "elapsed_time": "4:02:04", "remaining_time": "3:43:33"}
|
| 722 |
+
{"current_steps": 3495, "total_steps": 6713, "loss": 0.2297, "lr": 2.2060914366948004e-05, "epoch": 3.644757433489828, "percentage": 52.06, "elapsed_time": "4:03:47", "remaining_time": "3:44:28"}
|
| 723 |
+
{"current_steps": 3500, "total_steps": 6713, "loss": 0.2402, "lr": 2.2009179784502802e-05, "epoch": 3.649973917579551, "percentage": 52.14, "elapsed_time": "4:05:33", "remaining_time": "3:45:25"}
|
| 724 |
+
{"current_steps": 3505, "total_steps": 6713, "loss": 0.2289, "lr": 2.1957431617652074e-05, "epoch": 3.655190401669275, "percentage": 52.21, "elapsed_time": "4:07:10", "remaining_time": "3:46:13"}
|
| 725 |
+
{"current_steps": 3510, "total_steps": 6713, "loss": 0.237, "lr": 2.1905670216273967e-05, "epoch": 3.6604068857589986, "percentage": 52.29, "elapsed_time": "4:08:53", "remaining_time": "3:47:07"}
|
| 726 |
+
{"current_steps": 3515, "total_steps": 6713, "loss": 0.2241, "lr": 2.185389593033609e-05, "epoch": 3.665623369848722, "percentage": 52.36, "elapsed_time": "4:10:36", "remaining_time": "3:48:00"}
|
| 727 |
+
{"current_steps": 3520, "total_steps": 6713, "loss": 0.2202, "lr": 2.1802109109893184e-05, "epoch": 3.6708398539384453, "percentage": 52.44, "elapsed_time": "4:12:15", "remaining_time": "3:48:49"}
|
| 728 |
+
{"current_steps": 3525, "total_steps": 6713, "loss": 0.22, "lr": 2.1750310105084725e-05, "epoch": 3.676056338028169, "percentage": 52.51, "elapsed_time": "4:13:54", "remaining_time": "3:49:38"}
|
| 729 |
+
{"current_steps": 3530, "total_steps": 6713, "loss": 0.238, "lr": 2.1698499266132585e-05, "epoch": 3.6812728221178928, "percentage": 52.58, "elapsed_time": "4:15:37", "remaining_time": "3:50:29"}
|
| 730 |
+
{"current_steps": 3535, "total_steps": 6713, "loss": 0.2322, "lr": 2.164667694333863e-05, "epoch": 3.686489306207616, "percentage": 52.66, "elapsed_time": "4:17:20", "remaining_time": "3:51:20"}
|
| 731 |
+
{"current_steps": 3540, "total_steps": 6713, "loss": 0.2362, "lr": 2.159484348708239e-05, "epoch": 3.6917057902973394, "percentage": 52.73, "elapsed_time": "4:19:11", "remaining_time": "3:52:19"}
|
| 732 |
+
{"current_steps": 3545, "total_steps": 6713, "loss": 0.2283, "lr": 2.1542999247818653e-05, "epoch": 3.696922274387063, "percentage": 52.81, "elapsed_time": "4:20:53", "remaining_time": "3:53:08"}
|
| 733 |
+
{"current_steps": 3550, "total_steps": 6713, "loss": 0.2409, "lr": 2.149114457607512e-05, "epoch": 3.702138758476787, "percentage": 52.88, "elapsed_time": "4:22:35", "remaining_time": "3:53:58"}
|
| 734 |
+
{"current_steps": 3555, "total_steps": 6713, "loss": 0.2328, "lr": 2.1439279822450034e-05, "epoch": 3.70735524256651, "percentage": 52.96, "elapsed_time": "4:24:19", "remaining_time": "3:54:48"}
|
| 735 |
+
{"current_steps": 3560, "total_steps": 6713, "loss": 0.2246, "lr": 2.1387405337609787e-05, "epoch": 3.7125717266562335, "percentage": 53.03, "elapsed_time": "4:25:57", "remaining_time": "3:55:32"}
|
| 736 |
+
{"current_steps": 3565, "total_steps": 6713, "loss": 0.2267, "lr": 2.1335521472286578e-05, "epoch": 3.7177882107459572, "percentage": 53.11, "elapsed_time": "4:27:39", "remaining_time": "3:56:20"}
|
| 737 |
+
{"current_steps": 3570, "total_steps": 6713, "loss": 0.2202, "lr": 2.1283628577276034e-05, "epoch": 3.723004694835681, "percentage": 53.18, "elapsed_time": "4:29:16", "remaining_time": "3:57:03"}
|
| 738 |
+
{"current_steps": 3575, "total_steps": 6713, "loss": 0.2205, "lr": 2.1231727003434816e-05, "epoch": 3.7282211789254043, "percentage": 53.25, "elapsed_time": "4:30:56", "remaining_time": "3:57:49"}
|
| 739 |
+
{"current_steps": 3580, "total_steps": 6713, "loss": 0.2154, "lr": 2.1179817101678272e-05, "epoch": 3.7334376630151276, "percentage": 53.33, "elapsed_time": "4:32:38", "remaining_time": "3:58:35"}
|
| 740 |
+
{"current_steps": 3585, "total_steps": 6713, "loss": 0.2115, "lr": 2.1127899222978064e-05, "epoch": 3.7386541471048513, "percentage": 53.4, "elapsed_time": "4:34:17", "remaining_time": "3:59:19"}
|
| 741 |
+
{"current_steps": 3590, "total_steps": 6713, "loss": 0.2229, "lr": 2.107597371835979e-05, "epoch": 3.743870631194575, "percentage": 53.48, "elapsed_time": "4:35:57", "remaining_time": "4:00:03"}
|
| 742 |
+
{"current_steps": 3595, "total_steps": 6713, "loss": 0.2461, "lr": 2.1024040938900586e-05, "epoch": 3.7490871152842984, "percentage": 53.55, "elapsed_time": "4:37:34", "remaining_time": "4:00:44"}
|
| 743 |
+
{"current_steps": 3600, "total_steps": 6713, "loss": 0.2212, "lr": 2.097210123572679e-05, "epoch": 3.7543035993740217, "percentage": 53.63, "elapsed_time": "4:39:15", "remaining_time": "4:01:28"}
|