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:c76bacd7863e36c5b727d4b56c419dbd5e20011a23b691e25315cfd983223bd3
|
| 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 sha256:9f690a86e02a619741f04a82ab678d8e7bc38550057d25e9c3b84c36c9b65369
|
| 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 sha256:8f0f034f950e0537b5bc1137b221820481758851ae724cb1e6120592f0dd3401
|
| 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 sha256:0e5814ebbc37b919945a084e2a53a531fdb76b4aacd6c6c7b74a155659f461d9
|
| 3 |
size 1580230264
|
trainer_log.jsonl
CHANGED
|
@@ -639,3 +639,45 @@
|
|
| 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"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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"}
|
| 642 |
+
{"current_steps": 3210, "total_steps": 3752, "loss": 0.2046, "lr": 2.4993912333315605e-06, "epoch": 5.989729225023343, "percentage": 85.55, "elapsed_time": "23:39:38", "remaining_time": "3:59:42"}
|
| 643 |
+
{"current_steps": 3215, "total_steps": 3752, "loss": 0.2054, "lr": 2.4545350902598464e-06, "epoch": 5.99906629318394, "percentage": 85.69, "elapsed_time": "23:41:42", "remaining_time": "3:57:27"}
|
| 644 |
+
{"current_steps": 3220, "total_steps": 3752, "loss": 0.2008, "lr": 2.4100587856818458e-06, "epoch": 6.007469654528478, "percentage": 85.82, "elapsed_time": "23:43:40", "remaining_time": "3:55:13"}
|
| 645 |
+
{"current_steps": 3225, "total_steps": 3752, "loss": 0.1927, "lr": 2.3659632824567823e-06, "epoch": 6.016806722689076, "percentage": 85.95, "elapsed_time": "23:46:03", "remaining_time": "3:53:02"}
|
| 646 |
+
{"current_steps": 3230, "total_steps": 3752, "loss": 0.189, "lr": 2.322249535199965e-06, "epoch": 6.026143790849673, "percentage": 86.09, "elapsed_time": "23:48:14", "remaining_time": "3:50:49"}
|
| 647 |
+
{"current_steps": 3235, "total_steps": 3752, "loss": 0.1929, "lr": 2.278918490262143e-06, "epoch": 6.035480859010271, "percentage": 86.22, "elapsed_time": "23:50:36", "remaining_time": "3:48:37"}
|
| 648 |
+
{"current_steps": 3240, "total_steps": 3752, "loss": 0.1919, "lr": 2.235971085709028e-06, "epoch": 6.044817927170868, "percentage": 86.35, "elapsed_time": "23:52:29", "remaining_time": "3:46:22"}
|
| 649 |
+
{"current_steps": 3245, "total_steps": 3752, "loss": 0.1927, "lr": 2.193408251300948e-06, "epoch": 6.054154995331466, "percentage": 86.49, "elapsed_time": "23:54:33", "remaining_time": "3:44:08"}
|
| 650 |
+
{"current_steps": 3250, "total_steps": 3752, "loss": 0.1995, "lr": 2.1512309084727724e-06, "epoch": 6.063492063492063, "percentage": 86.62, "elapsed_time": "23:57:07", "remaining_time": "3:41:58"}
|
| 651 |
+
{"current_steps": 3255, "total_steps": 3752, "loss": 0.193, "lr": 2.1094399703139113e-06, "epoch": 6.072829131652661, "percentage": 86.75, "elapsed_time": "23:59:27", "remaining_time": "3:39:47"}
|
| 652 |
+
{"current_steps": 3260, "total_steps": 3752, "loss": 0.2035, "lr": 2.068036341548585e-06, "epoch": 6.082166199813258, "percentage": 86.89, "elapsed_time": "1 day, 0:01:38", "remaining_time": "3:37:34"}
|
| 653 |
+
{"current_steps": 3265, "total_steps": 3752, "loss": 0.2014, "lr": 2.027020918516216e-06, "epoch": 6.091503267973856, "percentage": 87.02, "elapsed_time": "1 day, 0:03:34", "remaining_time": "3:35:19"}
|
| 654 |
+
{"current_steps": 3270, "total_steps": 3752, "loss": 0.1884, "lr": 1.9863945891520474e-06, "epoch": 6.100840336134453, "percentage": 87.15, "elapsed_time": "1 day, 0:05:45", "remaining_time": "3:33:06"}
|
| 655 |
+
{"current_steps": 3275, "total_steps": 3752, "loss": 0.2049, "lr": 1.9461582329678895e-06, "epoch": 6.110177404295051, "percentage": 87.29, "elapsed_time": "1 day, 0:07:39", "remaining_time": "3:30:51"}
|
| 656 |
+
{"current_steps": 3280, "total_steps": 3752, "loss": 0.197, "lr": 1.9063127210331145e-06, "epoch": 6.1195144724556485, "percentage": 87.42, "elapsed_time": "1 day, 0:09:48", "remaining_time": "3:28:37"}
|
| 657 |
+
{"current_steps": 3285, "total_steps": 3752, "loss": 0.1985, "lr": 1.8668589159557626e-06, "epoch": 6.128851540616246, "percentage": 87.55, "elapsed_time": "1 day, 0:11:53", "remaining_time": "3:26:24"}
|
| 658 |
+
{"current_steps": 3290, "total_steps": 3752, "loss": 0.1926, "lr": 1.8277976718638934e-06, "epoch": 6.1381886087768445, "percentage": 87.69, "elapsed_time": "1 day, 0:14:06", "remaining_time": "3:24:11"}
|
| 659 |
+
{"current_steps": 3295, "total_steps": 3752, "loss": 0.1945, "lr": 1.789129834387091e-06, "epoch": 6.147525676937442, "percentage": 87.82, "elapsed_time": "1 day, 0:16:23", "remaining_time": "3:21:59"}
|
| 660 |
+
{"current_steps": 3300, "total_steps": 3752, "loss": 0.1971, "lr": 1.7508562406381414e-06, "epoch": 6.1568627450980395, "percentage": 87.95, "elapsed_time": "1 day, 0:18:25", "remaining_time": "3:19:45"}
|
| 661 |
+
{"current_steps": 3305, "total_steps": 3752, "loss": 0.205, "lr": 1.7129777191949437e-06, "epoch": 6.166199813258637, "percentage": 88.09, "elapsed_time": "1 day, 0:20:31", "remaining_time": "3:17:32"}
|
| 662 |
+
{"current_steps": 3310, "total_steps": 3752, "loss": 0.1925, "lr": 1.6754950900825174e-06, "epoch": 6.175536881419235, "percentage": 88.22, "elapsed_time": "1 day, 0:22:46", "remaining_time": "3:15:19"}
|
| 663 |
+
{"current_steps": 3315, "total_steps": 3752, "loss": 0.1948, "lr": 1.6384091647553125e-06, "epoch": 6.184873949579832, "percentage": 88.35, "elapsed_time": "1 day, 0:25:08", "remaining_time": "3:13:08"}
|
| 664 |
+
{"current_steps": 3320, "total_steps": 3752, "loss": 0.1966, "lr": 1.601720746079598e-06, "epoch": 6.19421101774043, "percentage": 88.49, "elapsed_time": "1 day, 0:27:17", "remaining_time": "3:10:55"}
|
| 665 |
+
{"current_steps": 3325, "total_steps": 3752, "loss": 0.1801, "lr": 1.5654306283161002e-06, "epoch": 6.203548085901027, "percentage": 88.62, "elapsed_time": "1 day, 0:29:34", "remaining_time": "3:08:43"}
|
| 666 |
+
{"current_steps": 3330, "total_steps": 3752, "loss": 0.2021, "lr": 1.5295395971028094e-06, "epoch": 6.212885154061625, "percentage": 88.75, "elapsed_time": "1 day, 0:31:43", "remaining_time": "3:06:30"}
|
| 667 |
+
{"current_steps": 3335, "total_steps": 3752, "loss": 0.197, "lr": 1.4940484294379442e-06, "epoch": 6.222222222222222, "percentage": 88.89, "elapsed_time": "1 day, 0:33:57", "remaining_time": "3:04:18"}
|
| 668 |
+
{"current_steps": 3340, "total_steps": 3752, "loss": 0.2086, "lr": 1.4589578936631776e-06, "epoch": 6.23155929038282, "percentage": 89.02, "elapsed_time": "1 day, 0:35:59", "remaining_time": "3:02:04"}
|
| 669 |
+
{"current_steps": 3345, "total_steps": 3752, "loss": 0.2076, "lr": 1.424268749446962e-06, "epoch": 6.240896358543417, "percentage": 89.15, "elapsed_time": "1 day, 0:37:56", "remaining_time": "2:59:49"}
|
| 670 |
+
{"current_steps": 3350, "total_steps": 3752, "loss": 0.2038, "lr": 1.3899817477681056e-06, "epoch": 6.250233426704015, "percentage": 89.29, "elapsed_time": "1 day, 0:40:05", "remaining_time": "2:57:36"}
|
| 671 |
+
{"current_steps": 3355, "total_steps": 3752, "loss": 0.1922, "lr": 1.3560976308995065e-06, "epoch": 6.2595704948646125, "percentage": 89.42, "elapsed_time": "1 day, 0:42:03", "remaining_time": "2:55:22"}
|
| 672 |
+
{"current_steps": 3360, "total_steps": 3752, "loss": 0.2, "lr": 1.3226171323920811e-06, "epoch": 6.26890756302521, "percentage": 89.55, "elapsed_time": "1 day, 0:44:13", "remaining_time": "2:53:09"}
|
| 673 |
+
{"current_steps": 3365, "total_steps": 3752, "loss": 0.1978, "lr": 1.2895409770588874e-06, "epoch": 6.278244631185808, "percentage": 89.69, "elapsed_time": "1 day, 0:46:26", "remaining_time": "2:50:57"}
|
| 674 |
+
{"current_steps": 3370, "total_steps": 3752, "loss": 0.1913, "lr": 1.2568698809594437e-06, "epoch": 6.287581699346405, "percentage": 89.82, "elapsed_time": "1 day, 0:48:28", "remaining_time": "2:48:43"}
|
| 675 |
+
{"current_steps": 3375, "total_steps": 3752, "loss": 0.201, "lr": 1.2246045513842008e-06, "epoch": 6.296918767507003, "percentage": 89.95, "elapsed_time": "1 day, 0:50:33", "remaining_time": "2:46:30"}
|
| 676 |
+
{"current_steps": 3380, "total_steps": 3752, "loss": 0.2055, "lr": 1.1927456868392605e-06, "epoch": 6.3062558356676, "percentage": 90.09, "elapsed_time": "1 day, 0:52:32", "remaining_time": "2:44:16"}
|
| 677 |
+
{"current_steps": 3385, "total_steps": 3752, "loss": 0.194, "lr": 1.1612939770312325e-06, "epoch": 6.315592903828198, "percentage": 90.22, "elapsed_time": "1 day, 0:54:44", "remaining_time": "2:42:03"}
|
| 678 |
+
{"current_steps": 3390, "total_steps": 3752, "loss": 0.2017, "lr": 1.1302501028523039e-06, "epoch": 6.324929971988795, "percentage": 90.35, "elapsed_time": "1 day, 0:56:48", "remaining_time": "2:39:50"}
|
| 679 |
+
{"current_steps": 3395, "total_steps": 3752, "loss": 0.1906, "lr": 1.0996147363655175e-06, "epoch": 6.334267040149393, "percentage": 90.49, "elapsed_time": "1 day, 0:59:07", "remaining_time": "2:37:38"}
|
| 680 |
+
{"current_steps": 3400, "total_steps": 3752, "loss": 0.1981, "lr": 1.069388540790195e-06, "epoch": 6.34360410830999, "percentage": 90.62, "elapsed_time": "1 day, 1:01:01", "remaining_time": "2:35:24"}
|
| 681 |
+
{"current_steps": 3405, "total_steps": 3752, "loss": 0.1984, "lr": 1.039572170487606e-06, "epoch": 6.352941176470588, "percentage": 90.75, "elapsed_time": "1 day, 1:04:13", "remaining_time": "2:33:17"}
|
| 682 |
+
{"current_steps": 3410, "total_steps": 3752, "loss": 0.1907, "lr": 1.0101662709467841e-06, "epoch": 6.362278244631185, "percentage": 90.88, "elapsed_time": "1 day, 1:06:19", "remaining_time": "2:31:04"}
|
| 683 |
+
{"current_steps": 3415, "total_steps": 3752, "loss": 0.193, "lr": 9.811714787705528e-07, "epoch": 6.371615312791784, "percentage": 91.02, "elapsed_time": "1 day, 1:08:42", "remaining_time": "2:28:52"}
|