Training in progress, step 3400
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 sha256:6bce3a201e13ab345f56f534674bdc3f744ba24cab98b28cc360b54aee74500d
|
| 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 sha256:27c23a4385e9379ec188c62a18047860da4dc1aff85145c025e47afbf8b5a7c9
|
| 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 sha256:5c74e2b8ff488388f83d986eac0a723f6c4a28d0a3df43514855a51b6ed1a2fc
|
| 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 sha256:0b226cbe886ec95ab1980be4b003a7d33e8c9116f6b21a5311a9fbf1d77e1fbb
|
| 3 |
size 1580230264
|
trainer_log.jsonl
CHANGED
|
@@ -640,3 +640,43 @@
|
|
| 640 |
{"current_steps": 3200, "total_steps": 9128, "loss": 0.1815, "lr": 3.2831975090209746e-05, "epoch": 2.454161871883391, "percentage": 35.06, "elapsed_time": "20:09:08", "remaining_time": "1 day, 13:19:56"}
|
| 641 |
{"current_steps": 3205, "total_steps": 9128, "loss": 0.1796, "lr": 3.2802618374352295e-05, "epoch": 2.4579976985040277, "percentage": 35.11, "elapsed_time": "20:11:37", "remaining_time": "1 day, 13:19:09"}
|
| 642 |
{"current_steps": 3210, "total_steps": 9128, "loss": 0.1807, "lr": 3.277321485014983e-05, "epoch": 2.461833525124664, "percentage": 35.17, "elapsed_time": "20:12:55", "remaining_time": "1 day, 13:16:09"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 640 |
{"current_steps": 3200, "total_steps": 9128, "loss": 0.1815, "lr": 3.2831975090209746e-05, "epoch": 2.454161871883391, "percentage": 35.06, "elapsed_time": "20:09:08", "remaining_time": "1 day, 13:19:56"}
|
| 641 |
{"current_steps": 3205, "total_steps": 9128, "loss": 0.1796, "lr": 3.2802618374352295e-05, "epoch": 2.4579976985040277, "percentage": 35.11, "elapsed_time": "20:11:37", "remaining_time": "1 day, 13:19:09"}
|
| 642 |
{"current_steps": 3210, "total_steps": 9128, "loss": 0.1807, "lr": 3.277321485014983e-05, "epoch": 2.461833525124664, "percentage": 35.17, "elapsed_time": "20:12:55", "remaining_time": "1 day, 13:16:09"}
|
| 643 |
+
{"current_steps": 3215, "total_steps": 9128, "loss": 0.1765, "lr": 3.274376462510616e-05, "epoch": 2.465669351745301, "percentage": 35.22, "elapsed_time": "20:14:10", "remaining_time": "1 day, 13:13:06"}
|
| 644 |
+
{"current_steps": 3220, "total_steps": 9128, "loss": 0.1883, "lr": 3.271426780689584e-05, "epoch": 2.469505178365938, "percentage": 35.28, "elapsed_time": "20:15:24", "remaining_time": "1 day, 13:10:01"}
|
| 645 |
+
{"current_steps": 3225, "total_steps": 9128, "loss": 0.1756, "lr": 3.2684724503363784e-05, "epoch": 2.4733410049865747, "percentage": 35.33, "elapsed_time": "20:16:41", "remaining_time": "1 day, 13:07:01"}
|
| 646 |
+
{"current_steps": 3230, "total_steps": 9128, "loss": 0.193, "lr": 3.265513482252487e-05, "epoch": 2.4771768316072116, "percentage": 35.39, "elapsed_time": "20:17:59", "remaining_time": "1 day, 13:04:03"}
|
| 647 |
+
{"current_steps": 3235, "total_steps": 9128, "loss": 0.1817, "lr": 3.262549887256351e-05, "epoch": 2.481012658227848, "percentage": 35.44, "elapsed_time": "20:19:18", "remaining_time": "1 day, 13:01:08"}
|
| 648 |
+
{"current_steps": 3240, "total_steps": 9128, "loss": 0.1844, "lr": 3.2595816761833326e-05, "epoch": 2.484848484848485, "percentage": 35.5, "elapsed_time": "20:20:33", "remaining_time": "1 day, 12:58:06"}
|
| 649 |
+
{"current_steps": 3245, "total_steps": 9128, "loss": 0.1777, "lr": 3.256608859885667e-05, "epoch": 2.4886843114691217, "percentage": 35.55, "elapsed_time": "20:21:47", "remaining_time": "1 day, 12:55:02"}
|
| 650 |
+
{"current_steps": 3250, "total_steps": 9128, "loss": 0.1754, "lr": 3.2536314492324294e-05, "epoch": 2.492520138089758, "percentage": 35.6, "elapsed_time": "20:23:03", "remaining_time": "1 day, 12:52:03"}
|
| 651 |
+
{"current_steps": 3255, "total_steps": 9128, "loss": 0.1823, "lr": 3.250649455109491e-05, "epoch": 2.496355964710395, "percentage": 35.66, "elapsed_time": "20:24:20", "remaining_time": "1 day, 12:49:04"}
|
| 652 |
+
{"current_steps": 3260, "total_steps": 9128, "loss": 0.174, "lr": 3.2476628884194834e-05, "epoch": 2.500191791331032, "percentage": 35.71, "elapsed_time": "20:25:35", "remaining_time": "1 day, 12:46:03"}
|
| 653 |
+
{"current_steps": 3265, "total_steps": 9128, "loss": 0.1748, "lr": 3.244671760081752e-05, "epoch": 2.5040276179516687, "percentage": 35.77, "elapsed_time": "20:26:50", "remaining_time": "1 day, 12:43:03"}
|
| 654 |
+
{"current_steps": 3270, "total_steps": 9128, "loss": 0.1703, "lr": 3.2416760810323246e-05, "epoch": 2.5078634445723056, "percentage": 35.82, "elapsed_time": "20:28:04", "remaining_time": "1 day, 12:40:00"}
|
| 655 |
+
{"current_steps": 3275, "total_steps": 9128, "loss": 0.1858, "lr": 3.238675862223865e-05, "epoch": 2.511699271192942, "percentage": 35.88, "elapsed_time": "20:29:19", "remaining_time": "1 day, 12:37:01"}
|
| 656 |
+
{"current_steps": 3280, "total_steps": 9128, "loss": 0.1755, "lr": 3.2356711146256344e-05, "epoch": 2.515535097813579, "percentage": 35.93, "elapsed_time": "20:30:33", "remaining_time": "1 day, 12:34:00"}
|
| 657 |
+
{"current_steps": 3285, "total_steps": 9128, "loss": 0.1722, "lr": 3.232661849223455e-05, "epoch": 2.5193709244342157, "percentage": 35.99, "elapsed_time": "20:31:54", "remaining_time": "1 day, 12:31:11"}
|
| 658 |
+
{"current_steps": 3290, "total_steps": 9128, "loss": 0.1687, "lr": 3.229648077019662e-05, "epoch": 2.523206751054852, "percentage": 36.04, "elapsed_time": "20:33:15", "remaining_time": "1 day, 12:28:22"}
|
| 659 |
+
{"current_steps": 3295, "total_steps": 9128, "loss": 0.1612, "lr": 3.2266298090330725e-05, "epoch": 2.527042577675489, "percentage": 36.1, "elapsed_time": "20:34:28", "remaining_time": "1 day, 12:25:21"}
|
| 660 |
+
{"current_steps": 3300, "total_steps": 9128, "loss": 0.1802, "lr": 3.223607056298939e-05, "epoch": 2.530878404296126, "percentage": 36.15, "elapsed_time": "20:35:42", "remaining_time": "1 day, 12:22:20"}
|
| 661 |
+
{"current_steps": 3305, "total_steps": 9128, "loss": 0.179, "lr": 3.220579829868912e-05, "epoch": 2.5347142309167623, "percentage": 36.21, "elapsed_time": "20:36:59", "remaining_time": "1 day, 12:19:25"}
|
| 662 |
+
{"current_steps": 3310, "total_steps": 9128, "loss": 0.1738, "lr": 3.217548140810995e-05, "epoch": 2.538550057537399, "percentage": 36.26, "elapsed_time": "20:38:15", "remaining_time": "1 day, 12:16:29"}
|
| 663 |
+
{"current_steps": 3315, "total_steps": 9128, "loss": 0.1776, "lr": 3.2145120002095125e-05, "epoch": 2.542385884158036, "percentage": 36.32, "elapsed_time": "20:39:29", "remaining_time": "1 day, 12:13:30"}
|
| 664 |
+
{"current_steps": 3320, "total_steps": 9128, "loss": 0.1774, "lr": 3.211471419165063e-05, "epoch": 2.546221710778673, "percentage": 36.37, "elapsed_time": "20:40:45", "remaining_time": "1 day, 12:10:34"}
|
| 665 |
+
{"current_steps": 3325, "total_steps": 9128, "loss": 0.1798, "lr": 3.208426408794476e-05, "epoch": 2.5500575373993097, "percentage": 36.43, "elapsed_time": "20:42:00", "remaining_time": "1 day, 12:07:38"}
|
| 666 |
+
{"current_steps": 3330, "total_steps": 9128, "loss": 0.2856, "lr": 3.2053769802307815e-05, "epoch": 2.553893364019946, "percentage": 36.48, "elapsed_time": "20:44:07", "remaining_time": "1 day, 12:06:12"}
|
| 667 |
+
{"current_steps": 3335, "total_steps": 9128, "loss": 0.2738, "lr": 3.202323144623159e-05, "epoch": 2.557729190640583, "percentage": 36.54, "elapsed_time": "20:46:16", "remaining_time": "1 day, 12:04:49"}
|
| 668 |
+
{"current_steps": 3340, "total_steps": 9128, "loss": 0.2667, "lr": 3.199264913136902e-05, "epoch": 2.56156501726122, "percentage": 36.59, "elapsed_time": "20:48:48", "remaining_time": "1 day, 12:04:06"}
|
| 669 |
+
{"current_steps": 3345, "total_steps": 9128, "loss": 0.2628, "lr": 3.196202296953375e-05, "epoch": 2.5654008438818563, "percentage": 36.65, "elapsed_time": "20:51:06", "remaining_time": "1 day, 12:02:58"}
|
| 670 |
+
{"current_steps": 3350, "total_steps": 9128, "loss": 0.2715, "lr": 3.1931353072699756e-05, "epoch": 2.569236670502493, "percentage": 36.7, "elapsed_time": "20:53:24", "remaining_time": "1 day, 12:01:50"}
|
| 671 |
+
{"current_steps": 3355, "total_steps": 9128, "loss": 0.2755, "lr": 3.1900639553000914e-05, "epoch": 2.57307249712313, "percentage": 36.76, "elapsed_time": "20:55:41", "remaining_time": "1 day, 12:00:41"}
|
| 672 |
+
{"current_steps": 3360, "total_steps": 9128, "loss": 0.2595, "lr": 3.186988252273056e-05, "epoch": 2.576908323743767, "percentage": 36.81, "elapsed_time": "20:58:08", "remaining_time": "1 day, 11:59:49"}
|
| 673 |
+
{"current_steps": 3365, "total_steps": 9128, "loss": 0.2647, "lr": 3.1839082094341156e-05, "epoch": 2.5807441503644037, "percentage": 36.86, "elapsed_time": "21:00:18", "remaining_time": "1 day, 11:58:27"}
|
| 674 |
+
{"current_steps": 3370, "total_steps": 9128, "loss": 0.2744, "lr": 3.180823838044381e-05, "epoch": 2.58457997698504, "percentage": 36.92, "elapsed_time": "21:02:44", "remaining_time": "1 day, 11:57:32"}
|
| 675 |
+
{"current_steps": 3375, "total_steps": 9128, "loss": 0.2696, "lr": 3.177735149380787e-05, "epoch": 2.588415803605677, "percentage": 36.97, "elapsed_time": "21:04:57", "remaining_time": "1 day, 11:56:14"}
|
| 676 |
+
{"current_steps": 3380, "total_steps": 9128, "loss": 0.2737, "lr": 3.174642154736058e-05, "epoch": 2.592251630226314, "percentage": 37.03, "elapsed_time": "21:07:15", "remaining_time": "1 day, 11:55:05"}
|
| 677 |
+
{"current_steps": 3385, "total_steps": 9128, "loss": 0.2604, "lr": 3.171544865418658e-05, "epoch": 2.5960874568469503, "percentage": 37.08, "elapsed_time": "21:09:49", "remaining_time": "1 day, 11:54:23"}
|
| 678 |
+
{"current_steps": 3390, "total_steps": 9128, "loss": 0.2682, "lr": 3.168443292752753e-05, "epoch": 2.599923283467587, "percentage": 37.14, "elapsed_time": "21:11:52", "remaining_time": "1 day, 11:52:48"}
|
| 679 |
+
{"current_steps": 3395, "total_steps": 9128, "loss": 0.2641, "lr": 3.165337448078171e-05, "epoch": 2.603759110088224, "percentage": 37.19, "elapsed_time": "21:13:47", "remaining_time": "1 day, 11:50:59"}
|
| 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"}
|