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 sha256:823c7772b70883b46d74acd36f00d265505f3278aef9b60779640ee7ee0fde1c
|
| 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 sha256:3aece9849a5cc8b0370e51a07eb10b70c097b638de776723e0681005cf2b8511
|
| 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 sha256:3d6b8184f7e9633158eaadbdd33b40163f8b5e414f6fede19df5b56cf11d64a8
|
| 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 sha256:7b58ef549c0c87d1a42ab285e1cee8f2ed0ba67e09c4e8590d60785b6cbad199
|
| 3 |
size 1580230264
|
trainer_log.jsonl
CHANGED
|
@@ -681,3 +681,23 @@
|
|
| 681 |
{"current_steps": 3290, "total_steps": 6713, "loss": 0.2473, "lr": 2.4166033259445723e-05, "epoch": 3.4308815858111634, "percentage": 49.01, "elapsed_time": "2:50:18", "remaining_time": "2:57:11"}
|
| 682 |
{"current_steps": 3295, "total_steps": 6713, "loss": 0.2473, "lr": 2.4115155458077453e-05, "epoch": 3.4360980699008867, "percentage": 49.08, "elapsed_time": "2:52:40", "remaining_time": "2:59:07"}
|
| 683 |
{"current_steps": 3300, "total_steps": 6713, "loss": 0.245, "lr": 2.4064249833444702e-05, "epoch": 3.4413145539906105, "percentage": 49.16, "elapsed_time": "2:54:58", "remaining_time": "3:00:58"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 681 |
{"current_steps": 3290, "total_steps": 6713, "loss": 0.2473, "lr": 2.4166033259445723e-05, "epoch": 3.4308815858111634, "percentage": 49.01, "elapsed_time": "2:50:18", "remaining_time": "2:57:11"}
|
| 682 |
{"current_steps": 3295, "total_steps": 6713, "loss": 0.2473, "lr": 2.4115155458077453e-05, "epoch": 3.4360980699008867, "percentage": 49.08, "elapsed_time": "2:52:40", "remaining_time": "2:59:07"}
|
| 683 |
{"current_steps": 3300, "total_steps": 6713, "loss": 0.245, "lr": 2.4064249833444702e-05, "epoch": 3.4413145539906105, "percentage": 49.16, "elapsed_time": "2:54:58", "remaining_time": "3:00:58"}
|
| 684 |
+
{"current_steps": 3305, "total_steps": 6713, "loss": 0.2425, "lr": 2.401331672972904e-05, "epoch": 3.446531038080334, "percentage": 49.23, "elapsed_time": "2:57:26", "remaining_time": "3:02:58"}
|
| 685 |
+
{"current_steps": 3310, "total_steps": 6713, "loss": 0.2422, "lr": 2.3962356491297814e-05, "epoch": 3.4517475221700575, "percentage": 49.31, "elapsed_time": "2:59:43", "remaining_time": "3:04:46"}
|
| 686 |
+
{"current_steps": 3315, "total_steps": 6713, "loss": 0.2478, "lr": 2.391136946270186e-05, "epoch": 3.456964006259781, "percentage": 49.38, "elapsed_time": "3:01:56", "remaining_time": "3:06:29"}
|
| 687 |
+
{"current_steps": 3320, "total_steps": 6713, "loss": 0.241, "lr": 2.3860355988673122e-05, "epoch": 3.4621804903495046, "percentage": 49.46, "elapsed_time": "3:03:48", "remaining_time": "3:07:50"}
|
| 688 |
+
{"current_steps": 3325, "total_steps": 6713, "loss": 0.2519, "lr": 2.380931641412236e-05, "epoch": 3.467396974439228, "percentage": 49.53, "elapsed_time": "3:05:28", "remaining_time": "3:08:59"}
|
| 689 |
+
{"current_steps": 3330, "total_steps": 6713, "loss": 0.2317, "lr": 2.3758251084136794e-05, "epoch": 3.4726134585289516, "percentage": 49.61, "elapsed_time": "3:07:08", "remaining_time": "3:10:07"}
|
| 690 |
+
{"current_steps": 3335, "total_steps": 6713, "loss": 0.2409, "lr": 2.3707160343977792e-05, "epoch": 3.477829942618675, "percentage": 49.68, "elapsed_time": "3:08:49", "remaining_time": "3:11:15"}
|
| 691 |
+
{"current_steps": 3340, "total_steps": 6713, "loss": 0.2591, "lr": 2.3656044539078523e-05, "epoch": 3.4830464267083987, "percentage": 49.75, "elapsed_time": "3:10:28", "remaining_time": "3:12:20"}
|
| 692 |
+
{"current_steps": 3345, "total_steps": 6713, "loss": 0.249, "lr": 2.3604904015041617e-05, "epoch": 3.488262910798122, "percentage": 49.83, "elapsed_time": "3:12:06", "remaining_time": "3:13:25"}
|
| 693 |
+
{"current_steps": 3350, "total_steps": 6713, "loss": 0.2443, "lr": 2.3553739117636835e-05, "epoch": 3.4934793948878458, "percentage": 49.9, "elapsed_time": "3:13:55", "remaining_time": "3:14:41"}
|
| 694 |
+
{"current_steps": 3355, "total_steps": 6713, "loss": 0.2301, "lr": 2.3502550192798726e-05, "epoch": 3.498695878977569, "percentage": 49.98, "elapsed_time": "3:15:32", "remaining_time": "3:15:43"}
|
| 695 |
+
{"current_steps": 3360, "total_steps": 6713, "loss": 0.2423, "lr": 2.345133758662431e-05, "epoch": 3.5039123630672924, "percentage": 50.05, "elapsed_time": "3:17:16", "remaining_time": "3:16:51"}
|
| 696 |
+
{"current_steps": 3365, "total_steps": 6713, "loss": 0.2222, "lr": 2.3400101645370702e-05, "epoch": 3.509128847157016, "percentage": 50.13, "elapsed_time": "3:18:54", "remaining_time": "3:17:54"}
|
| 697 |
+
{"current_steps": 3370, "total_steps": 6713, "loss": 0.2428, "lr": 2.3348842715452803e-05, "epoch": 3.51434533124674, "percentage": 50.2, "elapsed_time": "3:20:32", "remaining_time": "3:18:56"}
|
| 698 |
+
{"current_steps": 3375, "total_steps": 6713, "loss": 0.2388, "lr": 2.3297561143440932e-05, "epoch": 3.519561815336463, "percentage": 50.28, "elapsed_time": "3:22:10", "remaining_time": "3:19:57"}
|
| 699 |
+
{"current_steps": 3380, "total_steps": 6713, "loss": 0.2362, "lr": 2.3246257276058507e-05, "epoch": 3.5247782994261865, "percentage": 50.35, "elapsed_time": "3:23:53", "remaining_time": "3:21:03"}
|
| 700 |
+
{"current_steps": 3385, "total_steps": 6713, "loss": 0.2442, "lr": 2.3194931460179677e-05, "epoch": 3.5299947835159102, "percentage": 50.42, "elapsed_time": "3:25:33", "remaining_time": "3:22:05"}
|
| 701 |
+
{"current_steps": 3390, "total_steps": 6713, "loss": 0.2249, "lr": 2.314358404282699e-05, "epoch": 3.535211267605634, "percentage": 50.5, "elapsed_time": "3:27:13", "remaining_time": "3:23:07"}
|
| 702 |
+
{"current_steps": 3395, "total_steps": 6713, "loss": 0.239, "lr": 2.309221537116906e-05, "epoch": 3.5404277516953573, "percentage": 50.57, "elapsed_time": "3:28:53", "remaining_time": "3:24:09"}
|
| 703 |
+
{"current_steps": 3400, "total_steps": 6713, "loss": 0.2318, "lr": 2.3040825792518188e-05, "epoch": 3.5456442357850806, "percentage": 50.65, "elapsed_time": "3:30:33", "remaining_time": "3:25:10"}
|