Training in progress, step 3200
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 sha256:317d947fe6dea1dea6435f72969667b082426aef1c870390a6c001a30e0b1190
|
| 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 sha256:454fe15f47252545184d5da7f5bd46c8deb78cab44a16efd71fbe5d7da18bf3a
|
| 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 sha256:7a955dc0924e7990f36341eec83bf779b3fd05f5b9f039ee7c1a18c704ba8732
|
| 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 sha256:23d2b9337e3064d6f61fdd854a75e6d39aed16676d94aa6129531f00c8715595
|
| 3 |
size 1580230264
|
trainer_log.jsonl
CHANGED
|
@@ -599,3 +599,43 @@
|
|
| 599 |
{"current_steps": 2995, "total_steps": 3752, "loss": 0.2108, "lr": 4.772558204110724e-06, "epoch": 5.588235294117647, "percentage": 79.82, "elapsed_time": "22:03:49", "remaining_time": "5:34:36"}
|
| 600 |
{"current_steps": 3000, "total_steps": 3752, "loss": 0.2079, "lr": 4.712393210421957e-06, "epoch": 5.597572362278244, "percentage": 79.96, "elapsed_time": "22:06:07", "remaining_time": "5:32:24"}
|
| 601 |
{"current_steps": 3005, "total_steps": 3752, "loss": 0.1982, "lr": 4.652559175278062e-06, "epoch": 5.606909430438842, "percentage": 80.09, "elapsed_time": "22:09:27", "remaining_time": "5:30:29"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 599 |
{"current_steps": 2995, "total_steps": 3752, "loss": 0.2108, "lr": 4.772558204110724e-06, "epoch": 5.588235294117647, "percentage": 79.82, "elapsed_time": "22:03:49", "remaining_time": "5:34:36"}
|
| 600 |
{"current_steps": 3000, "total_steps": 3752, "loss": 0.2079, "lr": 4.712393210421957e-06, "epoch": 5.597572362278244, "percentage": 79.96, "elapsed_time": "22:06:07", "remaining_time": "5:32:24"}
|
| 601 |
{"current_steps": 3005, "total_steps": 3752, "loss": 0.1982, "lr": 4.652559175278062e-06, "epoch": 5.606909430438842, "percentage": 80.09, "elapsed_time": "22:09:27", "remaining_time": "5:30:29"}
|
| 602 |
+
{"current_steps": 3010, "total_steps": 3752, "loss": 0.2004, "lr": 4.593057394014882e-06, "epoch": 5.616246498599439, "percentage": 80.22, "elapsed_time": "22:11:29", "remaining_time": "5:28:13"}
|
| 603 |
+
{"current_steps": 3015, "total_steps": 3752, "loss": 0.2046, "lr": 4.5338891547753775e-06, "epoch": 5.625583566760037, "percentage": 80.36, "elapsed_time": "22:13:33", "remaining_time": "5:25:58"}
|
| 604 |
+
{"current_steps": 3020, "total_steps": 3752, "loss": 0.2052, "lr": 4.475055738481711e-06, "epoch": 5.634920634920634, "percentage": 80.49, "elapsed_time": "22:15:35", "remaining_time": "5:23:43"}
|
| 605 |
+
{"current_steps": 3025, "total_steps": 3752, "loss": 0.2067, "lr": 4.416558418807517e-06, "epoch": 5.644257703081233, "percentage": 80.62, "elapsed_time": "22:17:29", "remaining_time": "5:21:26"}
|
| 606 |
+
{"current_steps": 3030, "total_steps": 3752, "loss": 0.2034, "lr": 4.3583984621503596e-06, "epoch": 5.65359477124183, "percentage": 80.76, "elapsed_time": "22:19:39", "remaining_time": "5:19:13"}
|
| 607 |
+
{"current_steps": 3035, "total_steps": 3752, "loss": 0.1927, "lr": 4.300577127604269e-06, "epoch": 5.662931839402428, "percentage": 80.89, "elapsed_time": "22:21:58", "remaining_time": "5:17:02"}
|
| 608 |
+
{"current_steps": 3040, "total_steps": 3752, "loss": 0.2129, "lr": 4.243095666932531e-06, "epoch": 5.6722689075630255, "percentage": 81.02, "elapsed_time": "22:24:03", "remaining_time": "5:14:47"}
|
| 609 |
+
{"current_steps": 3045, "total_steps": 3752, "loss": 0.206, "lr": 4.18595532454055e-06, "epoch": 5.681605975723623, "percentage": 81.16, "elapsed_time": "22:26:10", "remaining_time": "5:12:33"}
|
| 610 |
+
{"current_steps": 3050, "total_steps": 3752, "loss": 0.2064, "lr": 4.129157337448926e-06, "epoch": 5.690943043884221, "percentage": 81.29, "elapsed_time": "22:28:20", "remaining_time": "5:10:20"}
|
| 611 |
+
{"current_steps": 3055, "total_steps": 3752, "loss": 0.206, "lr": 4.072702935266677e-06, "epoch": 5.700280112044818, "percentage": 81.42, "elapsed_time": "22:30:26", "remaining_time": "5:08:06"}
|
| 612 |
+
{"current_steps": 3060, "total_steps": 3752, "loss": 0.2044, "lr": 4.016593340164618e-06, "epoch": 5.709617180205416, "percentage": 81.56, "elapsed_time": "22:32:46", "remaining_time": "5:05:55"}
|
| 613 |
+
{"current_steps": 3065, "total_steps": 3752, "loss": 0.2067, "lr": 3.960829766848893e-06, "epoch": 5.718954248366013, "percentage": 81.69, "elapsed_time": "22:35:04", "remaining_time": "5:03:43"}
|
| 614 |
+
{"current_steps": 3070, "total_steps": 3752, "loss": 0.1982, "lr": 3.905413422534696e-06, "epoch": 5.728291316526611, "percentage": 81.82, "elapsed_time": "22:37:17", "remaining_time": "5:01:31"}
|
| 615 |
+
{"current_steps": 3075, "total_steps": 3752, "loss": 0.207, "lr": 3.85034550692011e-06, "epoch": 5.737628384687208, "percentage": 81.96, "elapsed_time": "22:39:36", "remaining_time": "4:59:20"}
|
| 616 |
+
{"current_steps": 3080, "total_steps": 3752, "loss": 0.2182, "lr": 3.7956272121601555e-06, "epoch": 5.746965452847806, "percentage": 82.09, "elapsed_time": "22:41:43", "remaining_time": "4:57:06"}
|
| 617 |
+
{"current_steps": 3085, "total_steps": 3752, "loss": 0.2055, "lr": 3.7412597228409884e-06, "epoch": 5.756302521008403, "percentage": 82.22, "elapsed_time": "22:43:59", "remaining_time": "4:54:54"}
|
| 618 |
+
{"current_steps": 3090, "total_steps": 3752, "loss": 0.2068, "lr": 3.687244215954222e-06, "epoch": 5.765639589169001, "percentage": 82.36, "elapsed_time": "22:46:05", "remaining_time": "4:52:40"}
|
| 619 |
+
{"current_steps": 3095, "total_steps": 3752, "loss": 0.2051, "lr": 3.633581860871491e-06, "epoch": 5.774976657329598, "percentage": 82.49, "elapsed_time": "22:48:23", "remaining_time": "4:50:28"}
|
| 620 |
+
{"current_steps": 3100, "total_steps": 3752, "loss": 0.2154, "lr": 3.5802738193190954e-06, "epoch": 5.784313725490196, "percentage": 82.62, "elapsed_time": "22:50:31", "remaining_time": "4:48:15"}
|
| 621 |
+
{"current_steps": 3105, "total_steps": 3752, "loss": 0.1957, "lr": 3.5273212453528705e-06, "epoch": 5.7936507936507935, "percentage": 82.76, "elapsed_time": "22:52:47", "remaining_time": "4:46:03"}
|
| 622 |
+
{"current_steps": 3110, "total_steps": 3752, "loss": 0.2033, "lr": 3.4747252853332004e-06, "epoch": 5.802987861811391, "percentage": 82.89, "elapsed_time": "22:54:57", "remaining_time": "4:43:50"}
|
| 623 |
+
{"current_steps": 3115, "total_steps": 3752, "loss": 0.2034, "lr": 3.4224870779002117e-06, "epoch": 5.812324929971989, "percentage": 83.02, "elapsed_time": "22:57:11", "remaining_time": "4:41:37"}
|
| 624 |
+
{"current_steps": 3120, "total_steps": 3752, "loss": 0.2118, "lr": 3.3706077539490933e-06, "epoch": 5.821661998132586, "percentage": 83.16, "elapsed_time": "22:59:17", "remaining_time": "4:39:23"}
|
| 625 |
+
{"current_steps": 3125, "total_steps": 3752, "loss": 0.2058, "lr": 3.3190884366056532e-06, "epoch": 5.830999066293184, "percentage": 83.29, "elapsed_time": "23:01:31", "remaining_time": "4:37:11"}
|
| 626 |
+
{"current_steps": 3130, "total_steps": 3752, "loss": 0.2043, "lr": 3.2679302412019665e-06, "epoch": 5.840336134453781, "percentage": 83.42, "elapsed_time": "23:03:44", "remaining_time": "4:34:58"}
|
| 627 |
+
{"current_steps": 3135, "total_steps": 3752, "loss": 0.2018, "lr": 3.2171342752522494e-06, "epoch": 5.849673202614379, "percentage": 83.56, "elapsed_time": "23:05:54", "remaining_time": "4:32:45"}
|
| 628 |
+
{"current_steps": 3140, "total_steps": 3752, "loss": 0.1884, "lr": 3.166701638428895e-06, "epoch": 5.859010270774976, "percentage": 83.69, "elapsed_time": "23:08:06", "remaining_time": "4:30:32"}
|
| 629 |
+
{"current_steps": 3145, "total_steps": 3752, "loss": 0.1992, "lr": 3.1166334225386306e-06, "epoch": 5.868347338935575, "percentage": 83.82, "elapsed_time": "23:10:16", "remaining_time": "4:28:19"}
|
| 630 |
+
{"current_steps": 3150, "total_steps": 3752, "loss": 0.1878, "lr": 3.066930711498921e-06, "epoch": 5.877684407096172, "percentage": 83.96, "elapsed_time": "23:12:40", "remaining_time": "4:26:09"}
|
| 631 |
+
{"current_steps": 3155, "total_steps": 3752, "loss": 0.2113, "lr": 3.0175945813144668e-06, "epoch": 5.88702147525677, "percentage": 84.09, "elapsed_time": "23:14:45", "remaining_time": "4:23:55"}
|
| 632 |
+
{"current_steps": 3160, "total_steps": 3752, "loss": 0.1986, "lr": 2.9686261000539484e-06, "epoch": 5.896358543417367, "percentage": 84.22, "elapsed_time": "23:16:56", "remaining_time": "4:21:42"}
|
| 633 |
+
{"current_steps": 3165, "total_steps": 3752, "loss": 0.2135, "lr": 2.920026327826866e-06, "epoch": 5.905695611577965, "percentage": 84.36, "elapsed_time": "23:18:47", "remaining_time": "4:19:25"}
|
| 634 |
+
{"current_steps": 3170, "total_steps": 3752, "loss": 0.1994, "lr": 2.87179631676062e-06, "epoch": 5.915032679738562, "percentage": 84.49, "elapsed_time": "23:20:54", "remaining_time": "4:17:12"}
|
| 635 |
+
{"current_steps": 3175, "total_steps": 3752, "loss": 0.2092, "lr": 2.8239371109777127e-06, "epoch": 5.92436974789916, "percentage": 84.62, "elapsed_time": "23:23:00", "remaining_time": "4:14:58"}
|
| 636 |
+
{"current_steps": 3180, "total_steps": 3752, "loss": 0.2015, "lr": 2.7764497465731487e-06, "epoch": 5.9337068160597575, "percentage": 84.75, "elapsed_time": "23:25:09", "remaining_time": "4:12:45"}
|
| 637 |
+
{"current_steps": 3185, "total_steps": 3752, "loss": 0.2074, "lr": 2.72933525159202e-06, "epoch": 5.943043884220355, "percentage": 84.89, "elapsed_time": "23:27:19", "remaining_time": "4:10:32"}
|
| 638 |
+
{"current_steps": 3190, "total_steps": 3752, "loss": 0.2063, "lr": 2.6825946460072237e-06, "epoch": 5.9523809523809526, "percentage": 85.02, "elapsed_time": "23:29:31", "remaining_time": "4:08:19"}
|
| 639 |
+
{"current_steps": 3195, "total_steps": 3752, "loss": 0.2042, "lr": 2.636228941697414e-06, "epoch": 5.96171802054155, "percentage": 85.15, "elapsed_time": "23:32:00", "remaining_time": "4:06:09"}
|
| 640 |
+
{"current_steps": 3200, "total_steps": 3752, "loss": 0.2067, "lr": 2.5902391424250573e-06, "epoch": 5.971055088702148, "percentage": 85.29, "elapsed_time": "23:34:08", "remaining_time": "4:03:56"}
|
| 641 |
+
{"current_steps": 3205, "total_steps": 3752, "loss": 0.2111, "lr": 2.544626243814732e-06, "epoch": 5.980392156862745, "percentage": 85.42, "elapsed_time": "23:37:15", "remaining_time": "4:01:53"}
|