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 sha256:6e473223b67b936a7f806a08bdc3306347c66cb952b87a40fe6337085606f738
|
| 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 sha256:8e5f561eda355170dba17ad17c65a2c877e58615bc8a92566bee863bbd63539f
|
| 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 sha256:32cf7e753124d6a23cbba13d9ded094ff260924b704b666eaa9d314a36d3ddfc
|
| 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 sha256:978c9839a2bf8ee0b148b7ce48da8389dc84e5599588b22d2e4efa7e5bba99ac
|
| 3 |
size 1580230264
|
trainer_log.jsonl
CHANGED
|
@@ -700,3 +700,26 @@
|
|
| 700 |
{"current_steps": 3475, "total_steps": 6188, "loss": 0.1577, "lr": 1.9204798346736485e-05, "epoch": 3.931522354272779, "percentage": 56.16, "elapsed_time": "2:45:24", "remaining_time": "2:09:08"}
|
| 701 |
{"current_steps": 3480, "total_steps": 6188, "loss": 0.1698, "lr": 1.914843404196899e-05, "epoch": 3.937181663837012, "percentage": 56.24, "elapsed_time": "2:48:23", "remaining_time": "2:11:01"}
|
| 702 |
{"current_steps": 3485, "total_steps": 6188, "loss": 0.1636, "lr": 1.9092076512108253e-05, "epoch": 3.9428409734012453, "percentage": 56.32, "elapsed_time": "2:51:27", "remaining_time": "2:12:59"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 700 |
{"current_steps": 3475, "total_steps": 6188, "loss": 0.1577, "lr": 1.9204798346736485e-05, "epoch": 3.931522354272779, "percentage": 56.16, "elapsed_time": "2:45:24", "remaining_time": "2:09:08"}
|
| 701 |
{"current_steps": 3480, "total_steps": 6188, "loss": 0.1698, "lr": 1.914843404196899e-05, "epoch": 3.937181663837012, "percentage": 56.24, "elapsed_time": "2:48:23", "remaining_time": "2:11:01"}
|
| 702 |
{"current_steps": 3485, "total_steps": 6188, "loss": 0.1636, "lr": 1.9092076512108253e-05, "epoch": 3.9428409734012453, "percentage": 56.32, "elapsed_time": "2:51:27", "remaining_time": "2:12:59"}
|
| 703 |
+
{"current_steps": 3490, "total_steps": 6188, "loss": 0.1461, "lr": 1.903572620552471e-05, "epoch": 3.9485002829654783, "percentage": 56.4, "elapsed_time": "2:54:32", "remaining_time": "2:14:56"}
|
| 704 |
+
{"current_steps": 3495, "total_steps": 6188, "loss": 0.163, "lr": 1.8979383570531358e-05, "epoch": 3.9541595925297113, "percentage": 56.48, "elapsed_time": "2:57:35", "remaining_time": "2:16:50"}
|
| 705 |
+
{"current_steps": 3500, "total_steps": 6188, "loss": 0.1548, "lr": 1.8923049055380128e-05, "epoch": 3.9598189020939447, "percentage": 56.56, "elapsed_time": "3:00:35", "remaining_time": "2:18:41"}
|
| 706 |
+
{"current_steps": 3505, "total_steps": 6188, "loss": 0.1534, "lr": 1.8866723108258376e-05, "epoch": 3.9654782116581777, "percentage": 56.64, "elapsed_time": "3:03:33", "remaining_time": "2:20:30"}
|
| 707 |
+
{"current_steps": 3510, "total_steps": 6188, "loss": 0.1584, "lr": 1.8810406177285282e-05, "epoch": 3.9711375212224107, "percentage": 56.72, "elapsed_time": "3:06:32", "remaining_time": "2:22:19"}
|
| 708 |
+
{"current_steps": 3515, "total_steps": 6188, "loss": 0.1609, "lr": 1.8754098710508294e-05, "epoch": 3.976796830786644, "percentage": 56.8, "elapsed_time": "3:09:35", "remaining_time": "2:24:10"}
|
| 709 |
+
{"current_steps": 3520, "total_steps": 6188, "loss": 0.1521, "lr": 1.869780115589957e-05, "epoch": 3.982456140350877, "percentage": 56.88, "elapsed_time": "3:12:40", "remaining_time": "2:26:02"}
|
| 710 |
+
{"current_steps": 3525, "total_steps": 6188, "loss": 0.1643, "lr": 1.8641513961352396e-05, "epoch": 3.98811544991511, "percentage": 56.97, "elapsed_time": "3:15:45", "remaining_time": "2:27:53"}
|
| 711 |
+
{"current_steps": 3530, "total_steps": 6188, "loss": 0.1715, "lr": 1.858523757467765e-05, "epoch": 3.9937747594793436, "percentage": 57.05, "elapsed_time": "3:18:50", "remaining_time": "2:29:43"}
|
| 712 |
+
{"current_steps": 3535, "total_steps": 6188, "loss": 0.1686, "lr": 1.8528972443600226e-05, "epoch": 3.9994340690435766, "percentage": 57.13, "elapsed_time": "3:21:55", "remaining_time": "2:31:32"}
|
| 713 |
+
{"current_steps": 3540, "total_steps": 6188, "loss": 0.1482, "lr": 1.8472719015755452e-05, "epoch": 4.005659309564233, "percentage": 57.21, "elapsed_time": "3:24:03", "remaining_time": "2:32:38"}
|
| 714 |
+
{"current_steps": 3545, "total_steps": 6188, "loss": 0.0896, "lr": 1.8416477738685567e-05, "epoch": 4.011318619128466, "percentage": 57.29, "elapsed_time": "3:25:42", "remaining_time": "2:33:22"}
|
| 715 |
+
{"current_steps": 3550, "total_steps": 6188, "loss": 0.082, "lr": 1.8360249059836123e-05, "epoch": 4.016977928692699, "percentage": 57.37, "elapsed_time": "3:27:22", "remaining_time": "2:34:06"}
|
| 716 |
+
{"current_steps": 3555, "total_steps": 6188, "loss": 0.1033, "lr": 1.830403342655246e-05, "epoch": 4.022637238256933, "percentage": 57.45, "elapsed_time": "3:28:59", "remaining_time": "2:34:47"}
|
| 717 |
+
{"current_steps": 3560, "total_steps": 6188, "loss": 0.0822, "lr": 1.824783128607612e-05, "epoch": 4.028296547821165, "percentage": 57.53, "elapsed_time": "3:30:45", "remaining_time": "2:35:35"}
|
| 718 |
+
{"current_steps": 3565, "total_steps": 6188, "loss": 0.0979, "lr": 1.8191643085541296e-05, "epoch": 4.033955857385399, "percentage": 57.61, "elapsed_time": "3:32:23", "remaining_time": "2:36:16"}
|
| 719 |
+
{"current_steps": 3570, "total_steps": 6188, "loss": 0.1351, "lr": 1.813546927197129e-05, "epoch": 4.039615166949632, "percentage": 57.69, "elapsed_time": "3:34:08", "remaining_time": "2:37:01"}
|
| 720 |
+
{"current_steps": 3575, "total_steps": 6188, "loss": 0.092, "lr": 1.8079310292274928e-05, "epoch": 4.045274476513866, "percentage": 57.77, "elapsed_time": "3:35:48", "remaining_time": "2:37:44"}
|
| 721 |
+
{"current_steps": 3580, "total_steps": 6188, "loss": 0.1017, "lr": 1.8023166593243026e-05, "epoch": 4.050933786078098, "percentage": 57.85, "elapsed_time": "3:37:32", "remaining_time": "2:38:28"}
|
| 722 |
+
{"current_steps": 3585, "total_steps": 6188, "loss": 0.1065, "lr": 1.7967038621544845e-05, "epoch": 4.056593095642332, "percentage": 57.93, "elapsed_time": "3:39:55", "remaining_time": "2:39:41"}
|
| 723 |
+
{"current_steps": 3590, "total_steps": 6188, "loss": 0.0801, "lr": 1.791092682372449e-05, "epoch": 4.062252405206565, "percentage": 58.02, "elapsed_time": "3:41:46", "remaining_time": "2:40:29"}
|
| 724 |
+
{"current_steps": 3595, "total_steps": 6188, "loss": 0.0875, "lr": 1.7854831646197426e-05, "epoch": 4.067911714770798, "percentage": 58.1, "elapsed_time": "3:43:42", "remaining_time": "2:41:21"}
|
| 725 |
+
{"current_steps": 3600, "total_steps": 6188, "loss": 0.0906, "lr": 1.7798753535246856e-05, "epoch": 4.073571024335031, "percentage": 58.18, "elapsed_time": "3:45:33", "remaining_time": "2:42:09"}
|