Training in progress, step 400
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 4877660776
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e5a0f7e819b2bf7a7ed25d5d0ff6558dcaa3323cea4c2be461d8135af1a6b67
|
3 |
size 4877660776
|
model-00002-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4932751008
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ca50f2773893a82dc3517bfd6f5f6320cc3dc7d9a08ee96b58f08aa01b2229f2
|
3 |
size 4932751008
|
model-00003-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4330865200
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c6d3eb870b06196637ea090b5b8217aae5d231ad21fee0b046ac24712935b1e1
|
3 |
size 4330865200
|
model-00004-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1089994880
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3141b3d2f4fa8450a2bd3b27838edc6e5cc7999655bab678c4faa451b9055950
|
3 |
size 1089994880
|
trainer_log.jsonl
CHANGED
@@ -18,3 +18,24 @@
|
|
18 |
{"current_steps": 180, "total_steps": 400, "loss": 0.0815, "lr": 6.710100716628345e-06, "epoch": 2.2242990654205608, "percentage": 45.0, "elapsed_time": "11:46:29", "remaining_time": "14:23:29"}
|
19 |
{"current_steps": 190, "total_steps": 400, "loss": 0.0833, "lr": 6.294095225512604e-06, "epoch": 2.3489096573208723, "percentage": 47.5, "elapsed_time": "12:26:11", "remaining_time": "13:44:44"}
|
20 |
{"current_steps": 200, "total_steps": 400, "loss": 0.0831, "lr": 5.8682408883346535e-06, "epoch": 2.473520249221184, "percentage": 50.0, "elapsed_time": "13:05:05", "remaining_time": "13:05:05"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
18 |
{"current_steps": 180, "total_steps": 400, "loss": 0.0815, "lr": 6.710100716628345e-06, "epoch": 2.2242990654205608, "percentage": 45.0, "elapsed_time": "11:46:29", "remaining_time": "14:23:29"}
|
19 |
{"current_steps": 190, "total_steps": 400, "loss": 0.0833, "lr": 6.294095225512604e-06, "epoch": 2.3489096573208723, "percentage": 47.5, "elapsed_time": "12:26:11", "remaining_time": "13:44:44"}
|
20 |
{"current_steps": 200, "total_steps": 400, "loss": 0.0831, "lr": 5.8682408883346535e-06, "epoch": 2.473520249221184, "percentage": 50.0, "elapsed_time": "13:05:05", "remaining_time": "13:05:05"}
|
21 |
+
{"current_steps": 210, "total_steps": 400, "loss": 0.0959, "lr": 5.435778713738292e-06, "epoch": 2.5981308411214954, "percentage": 52.5, "elapsed_time": "13:46:31", "remaining_time": "12:27:48"}
|
22 |
+
{"current_steps": 220, "total_steps": 400, "loss": 0.079, "lr": 5e-06, "epoch": 2.722741433021807, "percentage": 55.0, "elapsed_time": "14:26:08", "remaining_time": "11:48:39"}
|
23 |
+
{"current_steps": 230, "total_steps": 400, "loss": 0.0775, "lr": 4.564221286261709e-06, "epoch": 2.8473520249221185, "percentage": 57.5, "elapsed_time": "15:06:02", "remaining_time": "11:09:41"}
|
24 |
+
{"current_steps": 240, "total_steps": 400, "loss": 0.0887, "lr": 4.131759111665349e-06, "epoch": 2.97196261682243, "percentage": 60.0, "elapsed_time": "15:46:34", "remaining_time": "10:31:02"}
|
25 |
+
{"current_steps": 250, "total_steps": 400, "loss": 0.0675, "lr": 3.705904774487396e-06, "epoch": 3.087227414330218, "percentage": 62.5, "elapsed_time": "16:23:20", "remaining_time": "9:50:00"}
|
26 |
+
{"current_steps": 260, "total_steps": 400, "loss": 0.0653, "lr": 3.289899283371657e-06, "epoch": 3.2118380062305296, "percentage": 65.0, "elapsed_time": "17:02:28", "remaining_time": "9:10:33"}
|
27 |
+
{"current_steps": 270, "total_steps": 400, "loss": 0.0664, "lr": 2.886908691296504e-06, "epoch": 3.336448598130841, "percentage": 67.5, "elapsed_time": "17:42:10", "remaining_time": "8:31:25"}
|
28 |
+
{"current_steps": 280, "total_steps": 400, "loss": 0.0667, "lr": 2.5000000000000015e-06, "epoch": 3.4610591900311527, "percentage": 70.0, "elapsed_time": "18:22:28", "remaining_time": "7:52:29"}
|
29 |
+
{"current_steps": 290, "total_steps": 400, "loss": 0.0718, "lr": 2.132117818244771e-06, "epoch": 3.5856697819314642, "percentage": 72.5, "elapsed_time": "19:02:00", "remaining_time": "7:13:10"}
|
30 |
+
{"current_steps": 300, "total_steps": 400, "loss": 0.0671, "lr": 1.7860619515673034e-06, "epoch": 3.710280373831776, "percentage": 75.0, "elapsed_time": "19:41:38", "remaining_time": "6:33:52"}
|
31 |
+
{"current_steps": 310, "total_steps": 400, "loss": 0.0588, "lr": 1.4644660940672628e-06, "epoch": 3.8348909657320873, "percentage": 77.5, "elapsed_time": "20:21:19", "remaining_time": "5:54:34"}
|
32 |
+
{"current_steps": 320, "total_steps": 400, "loss": 0.0738, "lr": 1.1697777844051105e-06, "epoch": 3.959501557632399, "percentage": 80.0, "elapsed_time": "21:01:12", "remaining_time": "5:15:18"}
|
33 |
+
{"current_steps": 330, "total_steps": 400, "loss": 0.0573, "lr": 9.042397785550405e-07, "epoch": 4.074766355140187, "percentage": 82.5, "elapsed_time": "21:38:13", "remaining_time": "4:35:22"}
|
34 |
+
{"current_steps": 340, "total_steps": 400, "loss": 0.0514, "lr": 6.698729810778065e-07, "epoch": 4.1993769470404985, "percentage": 85.0, "elapsed_time": "22:17:30", "remaining_time": "3:56:01"}
|
35 |
+
{"current_steps": 350, "total_steps": 400, "loss": 0.0574, "lr": 4.6846106481675035e-07, "epoch": 4.32398753894081, "percentage": 87.5, "elapsed_time": "22:56:58", "remaining_time": "3:16:42"}
|
36 |
+
{"current_steps": 360, "total_steps": 400, "loss": 0.063, "lr": 3.015368960704584e-07, "epoch": 4.4485981308411215, "percentage": 90.0, "elapsed_time": "23:37:02", "remaining_time": "2:37:26"}
|
37 |
+
{"current_steps": 370, "total_steps": 400, "loss": 0.0584, "lr": 1.7037086855465902e-07, "epoch": 4.573208722741433, "percentage": 92.5, "elapsed_time": "1 day, 0:17:07", "remaining_time": "1:58:08"}
|
38 |
+
{"current_steps": 380, "total_steps": 400, "loss": 0.0551, "lr": 7.59612349389599e-08, "epoch": 4.697819314641745, "percentage": 95.0, "elapsed_time": "1 day, 0:55:55", "remaining_time": "1:18:43"}
|
39 |
+
{"current_steps": 390, "total_steps": 400, "loss": 0.0573, "lr": 1.9026509541272276e-08, "epoch": 4.822429906542056, "percentage": 97.5, "elapsed_time": "1 day, 1:35:10", "remaining_time": "0:39:21"}
|
40 |
+
{"current_steps": 400, "total_steps": 400, "loss": 0.0583, "lr": 0.0, "epoch": 4.947040498442368, "percentage": 100.0, "elapsed_time": "1 day, 2:14:50", "remaining_time": "0:00:00"}
|
41 |
+
{"current_steps": 400, "total_steps": 400, "epoch": 4.947040498442368, "percentage": 100.0, "elapsed_time": "1 day, 2:16:32", "remaining_time": "0:00:00"}
|