Training in progress, step 4400
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 sha256:66cbe5d951a6365939bd1abd1203c2a5a363e29a5465b0ee5a10a38c5dab08b0
|
| 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 sha256:5ef0b39fe92c9f29ba1d7da9aca7a59f1356a489ac1f313e26cc8f32aec3152f
|
| 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 sha256:3d4053ff464d9547b8cb6f65df00c702733e7598532c6bd14e49863215093d0b
|
| 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 sha256:340503bb0c1affe971fec422e9fb5e143d59011e7af27476ad8382ecebf4e823
|
| 3 |
size 1580230264
|
trainer_log.jsonl
CHANGED
|
@@ -861,3 +861,43 @@
|
|
| 861 |
{"current_steps": 4190, "total_steps": 6713, "loss": 0.1605, "lr": 1.4893140729954402e-05, "epoch": 4.37037037037037, "percentage": 62.42, "elapsed_time": "9:33:08", "remaining_time": "5:45:07"}
|
| 862 |
{"current_steps": 4195, "total_steps": 6713, "loss": 0.1423, "lr": 1.4842877458820644e-05, "epoch": 4.375586854460094, "percentage": 62.49, "elapsed_time": "9:36:13", "remaining_time": "5:45:52"}
|
| 863 |
{"current_steps": 4200, "total_steps": 6713, "loss": 0.1617, "lr": 1.4792649055867668e-05, "epoch": 4.380803338549818, "percentage": 62.57, "elapsed_time": "9:39:20", "remaining_time": "5:46:38"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 861 |
{"current_steps": 4190, "total_steps": 6713, "loss": 0.1605, "lr": 1.4893140729954402e-05, "epoch": 4.37037037037037, "percentage": 62.42, "elapsed_time": "9:33:08", "remaining_time": "5:45:07"}
|
| 862 |
{"current_steps": 4195, "total_steps": 6713, "loss": 0.1423, "lr": 1.4842877458820644e-05, "epoch": 4.375586854460094, "percentage": 62.49, "elapsed_time": "9:36:13", "remaining_time": "5:45:52"}
|
| 863 |
{"current_steps": 4200, "total_steps": 6713, "loss": 0.1617, "lr": 1.4792649055867668e-05, "epoch": 4.380803338549818, "percentage": 62.57, "elapsed_time": "9:39:20", "remaining_time": "5:46:38"}
|
| 864 |
+
{"current_steps": 4205, "total_steps": 6713, "loss": 0.1646, "lr": 1.474245586069822e-05, "epoch": 4.386019822639541, "percentage": 62.64, "elapsed_time": "9:43:45", "remaining_time": "5:48:10"}
|
| 865 |
+
{"current_steps": 4210, "total_steps": 6713, "loss": 0.1995, "lr": 1.4692298212677018e-05, "epoch": 4.391236306729264, "percentage": 62.71, "elapsed_time": "9:46:31", "remaining_time": "5:48:42"}
|
| 866 |
+
{"current_steps": 4215, "total_steps": 6713, "loss": 0.2238, "lr": 1.464217645092843e-05, "epoch": 4.396452790818988, "percentage": 62.79, "elapsed_time": "9:48:38", "remaining_time": "5:48:51"}
|
| 867 |
+
{"current_steps": 4220, "total_steps": 6713, "loss": 0.2311, "lr": 1.4592090914334206e-05, "epoch": 4.401669274908712, "percentage": 62.86, "elapsed_time": "9:51:04", "remaining_time": "5:49:11"}
|
| 868 |
+
{"current_steps": 4225, "total_steps": 6713, "loss": 0.2172, "lr": 1.4542041941531136e-05, "epoch": 4.406885758998435, "percentage": 62.94, "elapsed_time": "9:53:27", "remaining_time": "5:49:28"}
|
| 869 |
+
{"current_steps": 4230, "total_steps": 6713, "loss": 0.2244, "lr": 1.4492029870908835e-05, "epoch": 4.4121022430881585, "percentage": 63.01, "elapsed_time": "9:55:50", "remaining_time": "5:49:45"}
|
| 870 |
+
{"current_steps": 4235, "total_steps": 6713, "loss": 0.2386, "lr": 1.4442055040607402e-05, "epoch": 4.417318727177882, "percentage": 63.09, "elapsed_time": "9:58:13", "remaining_time": "5:50:02"}
|
| 871 |
+
{"current_steps": 4240, "total_steps": 6713, "loss": 0.2166, "lr": 1.4392117788515138e-05, "epoch": 4.422535211267606, "percentage": 63.16, "elapsed_time": "10:00:30", "remaining_time": "5:50:14"}
|
| 872 |
+
{"current_steps": 4245, "total_steps": 6713, "loss": 0.2256, "lr": 1.4342218452266284e-05, "epoch": 4.427751695357329, "percentage": 63.24, "elapsed_time": "10:02:52", "remaining_time": "5:50:30"}
|
| 873 |
+
{"current_steps": 4250, "total_steps": 6713, "loss": 0.2183, "lr": 1.4292357369238726e-05, "epoch": 4.432968179447053, "percentage": 63.31, "elapsed_time": "10:05:10", "remaining_time": "5:50:42"}
|
| 874 |
+
{"current_steps": 4255, "total_steps": 6713, "loss": 0.2333, "lr": 1.42425348765517e-05, "epoch": 4.438184663536776, "percentage": 63.38, "elapsed_time": "10:07:30", "remaining_time": "5:50:56"}
|
| 875 |
+
{"current_steps": 4260, "total_steps": 6713, "loss": 0.2203, "lr": 1.4192751311063541e-05, "epoch": 4.4434011476265, "percentage": 63.46, "elapsed_time": "10:09:48", "remaining_time": "5:51:08"}
|
| 876 |
+
{"current_steps": 4265, "total_steps": 6713, "loss": 0.2214, "lr": 1.4143007009369388e-05, "epoch": 4.448617631716223, "percentage": 63.53, "elapsed_time": "10:12:10", "remaining_time": "5:51:22"}
|
| 877 |
+
{"current_steps": 4270, "total_steps": 6713, "loss": 0.2234, "lr": 1.4093302307798906e-05, "epoch": 4.453834115805947, "percentage": 63.61, "elapsed_time": "10:14:24", "remaining_time": "5:51:31"}
|
| 878 |
+
{"current_steps": 4275, "total_steps": 6713, "loss": 0.2261, "lr": 1.4043637542414007e-05, "epoch": 4.45905059989567, "percentage": 63.68, "elapsed_time": "10:16:35", "remaining_time": "5:51:38"}
|
| 879 |
+
{"current_steps": 4280, "total_steps": 6713, "loss": 0.2216, "lr": 1.399401304900661e-05, "epoch": 4.464267083985394, "percentage": 63.76, "elapsed_time": "10:18:16", "remaining_time": "5:51:27"}
|
| 880 |
+
{"current_steps": 4285, "total_steps": 6713, "loss": 0.219, "lr": 1.3944429163096332e-05, "epoch": 4.469483568075117, "percentage": 63.83, "elapsed_time": "10:19:55", "remaining_time": "5:51:16"}
|
| 881 |
+
{"current_steps": 4290, "total_steps": 6713, "loss": 0.2132, "lr": 1.3894886219928247e-05, "epoch": 4.474700052164841, "percentage": 63.91, "elapsed_time": "10:21:39", "remaining_time": "5:51:06"}
|
| 882 |
+
{"current_steps": 4295, "total_steps": 6713, "loss": 0.2222, "lr": 1.3845384554470596e-05, "epoch": 4.4799165362545645, "percentage": 63.98, "elapsed_time": "10:23:15", "remaining_time": "5:50:52"}
|
| 883 |
+
{"current_steps": 4300, "total_steps": 6713, "loss": 0.231, "lr": 1.3795924501412542e-05, "epoch": 4.485133020344288, "percentage": 64.05, "elapsed_time": "10:24:52", "remaining_time": "5:50:39"}
|
| 884 |
+
{"current_steps": 4305, "total_steps": 6713, "loss": 0.2161, "lr": 1.3746506395161901e-05, "epoch": 4.490349504434011, "percentage": 64.13, "elapsed_time": "10:26:36", "remaining_time": "5:50:29"}
|
| 885 |
+
{"current_steps": 4310, "total_steps": 6713, "loss": 0.2246, "lr": 1.3697130569842874e-05, "epoch": 4.495565988523735, "percentage": 64.2, "elapsed_time": "10:28:19", "remaining_time": "5:50:19"}
|
| 886 |
+
{"current_steps": 4315, "total_steps": 6713, "loss": 0.2092, "lr": 1.3647797359293797e-05, "epoch": 4.500782472613459, "percentage": 64.28, "elapsed_time": "10:30:01", "remaining_time": "5:50:07"}
|
| 887 |
+
{"current_steps": 4320, "total_steps": 6713, "loss": 0.2073, "lr": 1.359850709706489e-05, "epoch": 4.505998956703182, "percentage": 64.35, "elapsed_time": "10:31:43", "remaining_time": "5:49:56"}
|
| 888 |
+
{"current_steps": 4325, "total_steps": 6713, "loss": 0.2103, "lr": 1.354926011641596e-05, "epoch": 4.511215440792905, "percentage": 64.43, "elapsed_time": "10:33:19", "remaining_time": "5:49:41"}
|
| 889 |
+
{"current_steps": 4330, "total_steps": 6713, "loss": 0.2188, "lr": 1.3500056750314215e-05, "epoch": 4.516431924882629, "percentage": 64.5, "elapsed_time": "10:34:59", "remaining_time": "5:49:27"}
|
| 890 |
+
{"current_steps": 4335, "total_steps": 6713, "loss": 0.2214, "lr": 1.345089733143196e-05, "epoch": 4.521648408972353, "percentage": 64.58, "elapsed_time": "10:36:37", "remaining_time": "5:49:13"}
|
| 891 |
+
{"current_steps": 4340, "total_steps": 6713, "loss": 0.2083, "lr": 1.3401782192144372e-05, "epoch": 4.5268648930620765, "percentage": 64.65, "elapsed_time": "10:38:21", "remaining_time": "5:49:02"}
|
| 892 |
+
{"current_steps": 4345, "total_steps": 6713, "loss": 0.2095, "lr": 1.3352711664527242e-05, "epoch": 4.532081377151799, "percentage": 64.73, "elapsed_time": "10:39:59", "remaining_time": "5:48:47"}
|
| 893 |
+
{"current_steps": 4350, "total_steps": 6713, "loss": 0.2125, "lr": 1.3303686080354739e-05, "epoch": 4.537297861241523, "percentage": 64.8, "elapsed_time": "10:41:38", "remaining_time": "5:48:33"}
|
| 894 |
+
{"current_steps": 4355, "total_steps": 6713, "loss": 0.2107, "lr": 1.3254705771097154e-05, "epoch": 4.542514345331247, "percentage": 64.87, "elapsed_time": "10:43:20", "remaining_time": "5:48:20"}
|
| 895 |
+
{"current_steps": 4360, "total_steps": 6713, "loss": 0.2056, "lr": 1.3205771067918675e-05, "epoch": 4.547730829420971, "percentage": 64.95, "elapsed_time": "10:44:57", "remaining_time": "5:48:04"}
|
| 896 |
+
{"current_steps": 4365, "total_steps": 6713, "loss": 0.2121, "lr": 1.3156882301675133e-05, "epoch": 4.5529473135106935, "percentage": 65.02, "elapsed_time": "10:46:37", "remaining_time": "5:47:49"}
|
| 897 |
+
{"current_steps": 4370, "total_steps": 6713, "loss": 0.2161, "lr": 1.3108039802911776e-05, "epoch": 4.558163797600417, "percentage": 65.1, "elapsed_time": "10:48:19", "remaining_time": "5:47:36"}
|
| 898 |
+
{"current_steps": 4375, "total_steps": 6713, "loss": 0.2012, "lr": 1.3059243901861024e-05, "epoch": 4.563380281690141, "percentage": 65.17, "elapsed_time": "10:50:04", "remaining_time": "5:47:23"}
|
| 899 |
+
{"current_steps": 4380, "total_steps": 6713, "loss": 0.2191, "lr": 1.3010494928440248e-05, "epoch": 4.568596765779865, "percentage": 65.25, "elapsed_time": "10:51:38", "remaining_time": "5:47:06"}
|
| 900 |
+
{"current_steps": 4385, "total_steps": 6713, "loss": 0.2131, "lr": 1.2961793212249527e-05, "epoch": 4.573813249869588, "percentage": 65.32, "elapsed_time": "10:53:16", "remaining_time": "5:46:49"}
|
| 901 |
+
{"current_steps": 4390, "total_steps": 6713, "loss": 0.2102, "lr": 1.2913139082569434e-05, "epoch": 4.579029733959311, "percentage": 65.4, "elapsed_time": "10:54:56", "remaining_time": "5:46:34"}
|
| 902 |
+
{"current_steps": 4395, "total_steps": 6713, "loss": 0.209, "lr": 1.2864532868358799e-05, "epoch": 4.584246218049035, "percentage": 65.47, "elapsed_time": "10:56:41", "remaining_time": "5:46:20"}
|
| 903 |
+
{"current_steps": 4400, "total_steps": 6713, "loss": 0.2151, "lr": 1.2815974898252482e-05, "epoch": 4.589462702138759, "percentage": 65.54, "elapsed_time": "10:58:22", "remaining_time": "5:46:05"}
|