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:d414606f39cff16063ea195679033f455fa27b6b61143f4d23d233a6a42ac9f0
|
| 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:da2376e026b5a77f7307d11f0a0c93da9fa758baf07e4a6d05d50fa36e4cfc93
|
| 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 sha256:97064aca29b2a360b41328ee5cbd4f2531fc383aef6aa17062e1874cea76a5ff
|
| 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 sha256:0c6d5b2cc48d4326b71807003667dcc09cb5f892ddbd72de5a7c50f9a55c36ca
|
| 3 |
size 1580230264
|
trainer_log.jsonl
CHANGED
|
@@ -680,3 +680,42 @@
|
|
| 680 |
{"current_steps": 3400, "total_steps": 9128, "loss": 0.2731, "lr": 3.162227342750359e-05, "epoch": 2.607594936708861, "percentage": 37.25, "elapsed_time": "21:15:29", "remaining_time": "1 day, 11:48:50"}
|
| 681 |
{"current_steps": 3405, "total_steps": 9128, "loss": 0.2654, "lr": 3.15911298814034e-05, "epoch": 2.6114307633294978, "percentage": 37.3, "elapsed_time": "21:18:31", "remaining_time": "1 day, 11:48:53"}
|
| 682 |
{"current_steps": 3410, "total_steps": 9128, "loss": 0.2665, "lr": 3.1559943956346764e-05, "epoch": 2.615266589950134, "percentage": 37.36, "elapsed_time": "21:20:12", "remaining_time": "1 day, 11:46:41"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 680 |
{"current_steps": 3400, "total_steps": 9128, "loss": 0.2731, "lr": 3.162227342750359e-05, "epoch": 2.607594936708861, "percentage": 37.25, "elapsed_time": "21:15:29", "remaining_time": "1 day, 11:48:50"}
|
| 681 |
{"current_steps": 3405, "total_steps": 9128, "loss": 0.2654, "lr": 3.15911298814034e-05, "epoch": 2.6114307633294978, "percentage": 37.3, "elapsed_time": "21:18:31", "remaining_time": "1 day, 11:48:53"}
|
| 682 |
{"current_steps": 3410, "total_steps": 9128, "loss": 0.2665, "lr": 3.1559943956346764e-05, "epoch": 2.615266589950134, "percentage": 37.36, "elapsed_time": "21:20:12", "remaining_time": "1 day, 11:46:41"}
|
| 683 |
+
{"current_steps": 3415, "total_steps": 9128, "loss": 0.2798, "lr": 3.15287157663542e-05, "epoch": 2.619102416570771, "percentage": 37.41, "elapsed_time": "21:21:50", "remaining_time": "1 day, 11:44:24"}
|
| 684 |
+
{"current_steps": 3420, "total_steps": 9128, "loss": 0.273, "lr": 3.1497445425600795e-05, "epoch": 2.622938243191408, "percentage": 37.47, "elapsed_time": "21:23:27", "remaining_time": "1 day, 11:42:06"}
|
| 685 |
+
{"current_steps": 3425, "total_steps": 9128, "loss": 0.2643, "lr": 3.146613304841575e-05, "epoch": 2.6267740698120443, "percentage": 37.52, "elapsed_time": "21:25:12", "remaining_time": "1 day, 11:40:01"}
|
| 686 |
+
{"current_steps": 3430, "total_steps": 9128, "loss": 0.2713, "lr": 3.143477874928191e-05, "epoch": 2.630609896432681, "percentage": 37.58, "elapsed_time": "21:26:51", "remaining_time": "1 day, 11:37:45"}
|
| 687 |
+
{"current_steps": 3435, "total_steps": 9128, "loss": 0.2606, "lr": 3.140338264283544e-05, "epoch": 2.634445723053318, "percentage": 37.63, "elapsed_time": "21:28:34", "remaining_time": "1 day, 11:35:37"}
|
| 688 |
+
{"current_steps": 3440, "total_steps": 9128, "loss": 0.2482, "lr": 3.137194484386534e-05, "epoch": 2.638281549673955, "percentage": 37.69, "elapsed_time": "21:30:14", "remaining_time": "1 day, 11:33:24"}
|
| 689 |
+
{"current_steps": 3445, "total_steps": 9128, "loss": 0.2632, "lr": 3.134046546731304e-05, "epoch": 2.6421173762945918, "percentage": 37.74, "elapsed_time": "21:31:53", "remaining_time": "1 day, 11:31:08"}
|
| 690 |
+
{"current_steps": 3450, "total_steps": 9128, "loss": 0.2691, "lr": 3.1308944628271986e-05, "epoch": 2.645953202915228, "percentage": 37.8, "elapsed_time": "21:33:30", "remaining_time": "1 day, 11:28:51"}
|
| 691 |
+
{"current_steps": 3455, "total_steps": 9128, "loss": 0.2598, "lr": 3.127738244198724e-05, "epoch": 2.649789029535865, "percentage": 37.85, "elapsed_time": "21:35:11", "remaining_time": "1 day, 11:26:39"}
|
| 692 |
+
{"current_steps": 3460, "total_steps": 9128, "loss": 0.2611, "lr": 3.1245779023854996e-05, "epoch": 2.653624856156502, "percentage": 37.91, "elapsed_time": "21:36:50", "remaining_time": "1 day, 11:24:25"}
|
| 693 |
+
{"current_steps": 3465, "total_steps": 9128, "loss": 0.2526, "lr": 3.121413448942223e-05, "epoch": 2.6574606827771383, "percentage": 37.96, "elapsed_time": "21:38:28", "remaining_time": "1 day, 11:22:09"}
|
| 694 |
+
{"current_steps": 3470, "total_steps": 9128, "loss": 0.2694, "lr": 3.1182448954386234e-05, "epoch": 2.661296509397775, "percentage": 38.01, "elapsed_time": "21:40:10", "remaining_time": "1 day, 11:19:59"}
|
| 695 |
+
{"current_steps": 3475, "total_steps": 9128, "loss": 0.2516, "lr": 3.115072253459421e-05, "epoch": 2.665132336018412, "percentage": 38.07, "elapsed_time": "21:41:50", "remaining_time": "1 day, 11:17:47"}
|
| 696 |
+
{"current_steps": 3480, "total_steps": 9128, "loss": 0.2573, "lr": 3.111895534604284e-05, "epoch": 2.6689681626390485, "percentage": 38.12, "elapsed_time": "21:43:29", "remaining_time": "1 day, 11:15:33"}
|
| 697 |
+
{"current_steps": 3485, "total_steps": 9128, "loss": 0.2565, "lr": 3.1087147504877835e-05, "epoch": 2.6728039892596853, "percentage": 38.18, "elapsed_time": "21:45:07", "remaining_time": "1 day, 11:13:18"}
|
| 698 |
+
{"current_steps": 3490, "total_steps": 9128, "loss": 0.2632, "lr": 3.105529912739358e-05, "epoch": 2.676639815880322, "percentage": 38.23, "elapsed_time": "21:46:49", "remaining_time": "1 day, 11:11:08"}
|
| 699 |
+
{"current_steps": 3495, "total_steps": 9128, "loss": 0.256, "lr": 3.1023410330032645e-05, "epoch": 2.680475642500959, "percentage": 38.29, "elapsed_time": "21:48:27", "remaining_time": "1 day, 11:08:53"}
|
| 700 |
+
{"current_steps": 3500, "total_steps": 9128, "loss": 0.266, "lr": 3.099148122938539e-05, "epoch": 2.684311469121596, "percentage": 38.34, "elapsed_time": "21:50:05", "remaining_time": "1 day, 11:06:38"}
|
| 701 |
+
{"current_steps": 3505, "total_steps": 9128, "loss": 0.2637, "lr": 3.095951194218953e-05, "epoch": 2.6881472957422323, "percentage": 38.4, "elapsed_time": "21:51:40", "remaining_time": "1 day, 11:04:16"}
|
| 702 |
+
{"current_steps": 3510, "total_steps": 9128, "loss": 0.2583, "lr": 3.092750258532968e-05, "epoch": 2.691983122362869, "percentage": 38.45, "elapsed_time": "21:53:22", "remaining_time": "1 day, 11:02:08"}
|
| 703 |
+
{"current_steps": 3515, "total_steps": 9128, "loss": 0.2543, "lr": 3.089545327583701e-05, "epoch": 2.695818948983506, "percentage": 38.51, "elapsed_time": "21:55:03", "remaining_time": "1 day, 10:59:59"}
|
| 704 |
+
{"current_steps": 3520, "total_steps": 9128, "loss": 0.2628, "lr": 3.086336413088872e-05, "epoch": 2.6996547756041425, "percentage": 38.56, "elapsed_time": "21:56:46", "remaining_time": "1 day, 10:57:51"}
|
| 705 |
+
{"current_steps": 3525, "total_steps": 9128, "loss": 0.2582, "lr": 3.083123526780767e-05, "epoch": 2.7034906022247793, "percentage": 38.62, "elapsed_time": "21:58:30", "remaining_time": "1 day, 10:55:46"}
|
| 706 |
+
{"current_steps": 3530, "total_steps": 9128, "loss": 0.2513, "lr": 3.079906680406192e-05, "epoch": 2.707326428845416, "percentage": 38.67, "elapsed_time": "22:00:09", "remaining_time": "1 day, 10:53:32"}
|
| 707 |
+
{"current_steps": 3535, "total_steps": 9128, "loss": 0.2681, "lr": 3.0766858857264336e-05, "epoch": 2.711162255466053, "percentage": 38.73, "elapsed_time": "22:01:48", "remaining_time": "1 day, 10:51:19"}
|
| 708 |
+
{"current_steps": 3540, "total_steps": 9128, "loss": 0.2556, "lr": 3.073461154517214e-05, "epoch": 2.71499808208669, "percentage": 38.78, "elapsed_time": "22:03:31", "remaining_time": "1 day, 10:49:12"}
|
| 709 |
+
{"current_steps": 3545, "total_steps": 9128, "loss": 0.2532, "lr": 3.070232498568647e-05, "epoch": 2.7188339087073263, "percentage": 38.84, "elapsed_time": "22:05:16", "remaining_time": "1 day, 10:47:09"}
|
| 710 |
+
{"current_steps": 3550, "total_steps": 9128, "loss": 0.2453, "lr": 3.066999929685196e-05, "epoch": 2.722669735327963, "percentage": 38.89, "elapsed_time": "22:06:51", "remaining_time": "1 day, 10:44:51"}
|
| 711 |
+
{"current_steps": 3555, "total_steps": 9128, "loss": 0.2655, "lr": 3.063763459685631e-05, "epoch": 2.7265055619486, "percentage": 38.95, "elapsed_time": "22:08:32", "remaining_time": "1 day, 10:42:41"}
|
| 712 |
+
{"current_steps": 3560, "total_steps": 9128, "loss": 0.2475, "lr": 3.060523100402984e-05, "epoch": 2.7303413885692365, "percentage": 39.0, "elapsed_time": "22:10:15", "remaining_time": "1 day, 10:40:35"}
|
| 713 |
+
{"current_steps": 3565, "total_steps": 9128, "loss": 0.2681, "lr": 3.057278863684509e-05, "epoch": 2.7341772151898733, "percentage": 39.06, "elapsed_time": "22:11:51", "remaining_time": "1 day, 10:38:17"}
|
| 714 |
+
{"current_steps": 3570, "total_steps": 9128, "loss": 0.2554, "lr": 3.054030761391634e-05, "epoch": 2.73801304181051, "percentage": 39.11, "elapsed_time": "22:13:32", "remaining_time": "1 day, 10:36:08"}
|
| 715 |
+
{"current_steps": 3575, "total_steps": 9128, "loss": 0.269, "lr": 3.0507788053999225e-05, "epoch": 2.741848868431147, "percentage": 39.17, "elapsed_time": "22:15:15", "remaining_time": "1 day, 10:34:03"}
|
| 716 |
+
{"current_steps": 3580, "total_steps": 9128, "loss": 0.2483, "lr": 3.0475230075990258e-05, "epoch": 2.745684695051784, "percentage": 39.22, "elapsed_time": "22:16:54", "remaining_time": "1 day, 10:31:49"}
|
| 717 |
+
{"current_steps": 3585, "total_steps": 9128, "loss": 0.2677, "lr": 3.0442633798926418e-05, "epoch": 2.7495205216724203, "percentage": 39.27, "elapsed_time": "22:18:34", "remaining_time": "1 day, 10:29:39"}
|
| 718 |
+
{"current_steps": 3590, "total_steps": 9128, "loss": 0.2503, "lr": 3.0409999341984734e-05, "epoch": 2.753356348293057, "percentage": 39.33, "elapsed_time": "22:20:15", "remaining_time": "1 day, 10:27:29"}
|
| 719 |
+
{"current_steps": 3595, "total_steps": 9128, "loss": 0.2456, "lr": 3.037732682448179e-05, "epoch": 2.757192174913694, "percentage": 39.38, "elapsed_time": "22:21:55", "remaining_time": "1 day, 10:25:20"}
|
| 720 |
+
{"current_steps": 3600, "total_steps": 9128, "loss": 0.2386, "lr": 3.0344616365873345e-05, "epoch": 2.7610280015343305, "percentage": 39.44, "elapsed_time": "22:23:34", "remaining_time": "1 day, 10:23:07"}
|
| 721 |
+
{"current_steps": 3605, "total_steps": 9128, "loss": 0.2645, "lr": 3.0311868085753883e-05, "epoch": 2.7648638281549673, "percentage": 39.49, "elapsed_time": "22:26:33", "remaining_time": "1 day, 10:22:58"}
|