Training in progress, step 4000
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 sha256:815ecdc95f7a5beb413d8c14b8d3a754263e3ee116d3edd0ef78f2d90364dc39
|
| 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:ca495972ac8e16ee0b46c12742c2f851b126d5063faa7498991de37fe2a222d2
|
| 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:bed0b890c99c700853d0309386871dfe61798252ff9aa38db0b9b25f92ffdff6
|
| 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 sha256:6f534755dcea0e087973e8d0f3fe1d00446667426886019296460277ad48658c
|
| 3 |
size 1580230264
|
trainer_log.jsonl
CHANGED
|
@@ -763,3 +763,43 @@
|
|
| 763 |
{"current_steps": 3790, "total_steps": 6188, "loss": 0.0924, "lr": 1.568482452586929e-05, "epoch": 4.288624787775891, "percentage": 61.25, "elapsed_time": "4:52:49", "remaining_time": "3:05:16"}
|
| 764 |
{"current_steps": 3795, "total_steps": 6188, "loss": 0.0858, "lr": 1.5629758306415652e-05, "epoch": 4.294284097340125, "percentage": 61.33, "elapsed_time": "4:54:53", "remaining_time": "3:05:57"}
|
| 765 |
{"current_steps": 3800, "total_steps": 6188, "loss": 0.0765, "lr": 1.5574726855824827e-05, "epoch": 4.299943406904358, "percentage": 61.41, "elapsed_time": "4:56:35", "remaining_time": "3:06:23"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 763 |
{"current_steps": 3790, "total_steps": 6188, "loss": 0.0924, "lr": 1.568482452586929e-05, "epoch": 4.288624787775891, "percentage": 61.25, "elapsed_time": "4:52:49", "remaining_time": "3:05:16"}
|
| 764 |
{"current_steps": 3795, "total_steps": 6188, "loss": 0.0858, "lr": 1.5629758306415652e-05, "epoch": 4.294284097340125, "percentage": 61.33, "elapsed_time": "4:54:53", "remaining_time": "3:05:57"}
|
| 765 |
{"current_steps": 3800, "total_steps": 6188, "loss": 0.0765, "lr": 1.5574726855824827e-05, "epoch": 4.299943406904358, "percentage": 61.41, "elapsed_time": "4:56:35", "remaining_time": "3:06:23"}
|
| 766 |
+
{"current_steps": 3805, "total_steps": 6188, "loss": 0.0753, "lr": 1.5519730611917206e-05, "epoch": 4.305602716468591, "percentage": 61.49, "elapsed_time": "4:59:49", "remaining_time": "3:07:46"}
|
| 767 |
+
{"current_steps": 3810, "total_steps": 6188, "loss": 0.0819, "lr": 1.546477001223309e-05, "epoch": 4.311262026032824, "percentage": 61.57, "elapsed_time": "5:01:29", "remaining_time": "3:08:10"}
|
| 768 |
+
{"current_steps": 3815, "total_steps": 6188, "loss": 0.102, "lr": 1.5409845494029208e-05, "epoch": 4.3169213355970575, "percentage": 61.65, "elapsed_time": "5:03:56", "remaining_time": "3:09:03"}
|
| 769 |
+
{"current_steps": 3820, "total_steps": 6188, "loss": 0.0857, "lr": 1.5354957494275207e-05, "epoch": 4.32258064516129, "percentage": 61.73, "elapsed_time": "5:05:31", "remaining_time": "3:09:23"}
|
| 770 |
+
{"current_steps": 3825, "total_steps": 6188, "loss": 0.0973, "lr": 1.5300106449650234e-05, "epoch": 4.3282399547255235, "percentage": 61.81, "elapsed_time": "5:07:06", "remaining_time": "3:09:43"}
|
| 771 |
+
{"current_steps": 3830, "total_steps": 6188, "loss": 0.0693, "lr": 1.524529279653939e-05, "epoch": 4.333899264289757, "percentage": 61.89, "elapsed_time": "5:08:44", "remaining_time": "3:10:04"}
|
| 772 |
+
{"current_steps": 3835, "total_steps": 6188, "loss": 0.0909, "lr": 1.5190516971030324e-05, "epoch": 4.3395585738539895, "percentage": 61.97, "elapsed_time": "5:10:33", "remaining_time": "3:10:32"}
|
| 773 |
+
{"current_steps": 3840, "total_steps": 6188, "loss": 0.0832, "lr": 1.5135779408909732e-05, "epoch": 4.345217883418223, "percentage": 62.06, "elapsed_time": "5:12:08", "remaining_time": "3:10:51"}
|
| 774 |
+
{"current_steps": 3845, "total_steps": 6188, "loss": 0.0754, "lr": 1.5081080545659874e-05, "epoch": 4.350877192982456, "percentage": 62.14, "elapsed_time": "5:13:46", "remaining_time": "3:11:11"}
|
| 775 |
+
{"current_steps": 3850, "total_steps": 6188, "loss": 0.0836, "lr": 1.5026420816455156e-05, "epoch": 4.356536502546689, "percentage": 62.22, "elapsed_time": "5:15:25", "remaining_time": "3:11:32"}
|
| 776 |
+
{"current_steps": 3855, "total_steps": 6188, "loss": 0.0862, "lr": 1.4971800656158624e-05, "epoch": 4.362195812110922, "percentage": 62.3, "elapsed_time": "5:17:00", "remaining_time": "3:11:51"}
|
| 777 |
+
{"current_steps": 3860, "total_steps": 6188, "loss": 0.1004, "lr": 1.4917220499318506e-05, "epoch": 4.367855121675156, "percentage": 62.38, "elapsed_time": "5:18:47", "remaining_time": "3:12:16"}
|
| 778 |
+
{"current_steps": 3865, "total_steps": 6188, "loss": 0.0831, "lr": 1.4862680780164805e-05, "epoch": 4.373514431239389, "percentage": 62.46, "elapsed_time": "5:20:26", "remaining_time": "3:12:35"}
|
| 779 |
+
{"current_steps": 3870, "total_steps": 6188, "loss": 0.1019, "lr": 1.4808181932605787e-05, "epoch": 4.379173740803622, "percentage": 62.54, "elapsed_time": "5:21:56", "remaining_time": "3:12:50"}
|
| 780 |
+
{"current_steps": 3875, "total_steps": 6188, "loss": 0.105, "lr": 1.4753724390224551e-05, "epoch": 4.384833050367855, "percentage": 62.62, "elapsed_time": "5:23:56", "remaining_time": "3:13:21"}
|
| 781 |
+
{"current_steps": 3880, "total_steps": 6188, "loss": 0.0843, "lr": 1.4699308586275591e-05, "epoch": 4.390492359932089, "percentage": 62.7, "elapsed_time": "5:25:35", "remaining_time": "3:13:40"}
|
| 782 |
+
{"current_steps": 3885, "total_steps": 6188, "loss": 0.0712, "lr": 1.464493495368132e-05, "epoch": 4.396151669496321, "percentage": 62.78, "elapsed_time": "5:27:09", "remaining_time": "3:13:56"}
|
| 783 |
+
{"current_steps": 3890, "total_steps": 6188, "loss": 0.0817, "lr": 1.459060392502866e-05, "epoch": 4.401810979060555, "percentage": 62.86, "elapsed_time": "5:28:43", "remaining_time": "3:14:11"}
|
| 784 |
+
{"current_steps": 3895, "total_steps": 6188, "loss": 0.1114, "lr": 1.4536315932565575e-05, "epoch": 4.407470288624788, "percentage": 62.94, "elapsed_time": "5:30:49", "remaining_time": "3:14:45"}
|
| 785 |
+
{"current_steps": 3900, "total_steps": 6188, "loss": 0.0681, "lr": 1.448207140819764e-05, "epoch": 4.413129598189021, "percentage": 63.03, "elapsed_time": "5:32:19", "remaining_time": "3:14:58"}
|
| 786 |
+
{"current_steps": 3905, "total_steps": 6188, "loss": 0.0845, "lr": 1.4427870783484613e-05, "epoch": 4.418788907753254, "percentage": 63.11, "elapsed_time": "5:34:24", "remaining_time": "3:15:30"}
|
| 787 |
+
{"current_steps": 3910, "total_steps": 6188, "loss": 0.0789, "lr": 1.4373714489636985e-05, "epoch": 4.4244482173174875, "percentage": 63.19, "elapsed_time": "5:36:07", "remaining_time": "3:15:49"}
|
| 788 |
+
{"current_steps": 3915, "total_steps": 6188, "loss": 0.068, "lr": 1.4319602957512564e-05, "epoch": 4.43010752688172, "percentage": 63.27, "elapsed_time": "5:37:46", "remaining_time": "3:16:06"}
|
| 789 |
+
{"current_steps": 3920, "total_steps": 6188, "loss": 0.0887, "lr": 1.4265536617613043e-05, "epoch": 4.4357668364459535, "percentage": 63.35, "elapsed_time": "5:39:27", "remaining_time": "3:16:23"}
|
| 790 |
+
{"current_steps": 3925, "total_steps": 6188, "loss": 0.0735, "lr": 1.4211515900080568e-05, "epoch": 4.441426146010187, "percentage": 63.43, "elapsed_time": "5:41:11", "remaining_time": "3:16:42"}
|
| 791 |
+
{"current_steps": 3930, "total_steps": 6188, "loss": 0.1065, "lr": 1.4157541234694324e-05, "epoch": 4.44708545557442, "percentage": 63.51, "elapsed_time": "5:42:57", "remaining_time": "3:17:02"}
|
| 792 |
+
{"current_steps": 3935, "total_steps": 6188, "loss": 0.1014, "lr": 1.4103613050867117e-05, "epoch": 4.452744765138653, "percentage": 63.59, "elapsed_time": "5:44:40", "remaining_time": "3:17:20"}
|
| 793 |
+
{"current_steps": 3940, "total_steps": 6188, "loss": 0.0687, "lr": 1.4049731777641948e-05, "epoch": 4.458404074702886, "percentage": 63.67, "elapsed_time": "5:46:13", "remaining_time": "3:17:32"}
|
| 794 |
+
{"current_steps": 3945, "total_steps": 6188, "loss": 0.0978, "lr": 1.3995897843688615e-05, "epoch": 4.46406338426712, "percentage": 63.75, "elapsed_time": "5:47:48", "remaining_time": "3:17:44"}
|
| 795 |
+
{"current_steps": 3950, "total_steps": 6188, "loss": 0.0783, "lr": 1.3942111677300276e-05, "epoch": 4.469722693831352, "percentage": 63.83, "elapsed_time": "5:49:23", "remaining_time": "3:17:57"}
|
| 796 |
+
{"current_steps": 3955, "total_steps": 6188, "loss": 0.089, "lr": 1.388837370639008e-05, "epoch": 4.475382003395586, "percentage": 63.91, "elapsed_time": "5:50:55", "remaining_time": "3:18:07"}
|
| 797 |
+
{"current_steps": 3960, "total_steps": 6188, "loss": 0.1028, "lr": 1.3834684358487731e-05, "epoch": 4.481041312959819, "percentage": 63.99, "elapsed_time": "5:52:49", "remaining_time": "3:18:30"}
|
| 798 |
+
{"current_steps": 3965, "total_steps": 6188, "loss": 0.1121, "lr": 1.3781044060736089e-05, "epoch": 4.486700622524052, "percentage": 64.08, "elapsed_time": "5:54:39", "remaining_time": "3:18:50"}
|
| 799 |
+
{"current_steps": 3970, "total_steps": 6188, "loss": 0.0869, "lr": 1.3727453239887796e-05, "epoch": 4.492359932088285, "percentage": 64.16, "elapsed_time": "5:56:42", "remaining_time": "3:19:17"}
|
| 800 |
+
{"current_steps": 3975, "total_steps": 6188, "loss": 0.0889, "lr": 1.367391232230185e-05, "epoch": 4.498019241652519, "percentage": 64.24, "elapsed_time": "5:58:22", "remaining_time": "3:19:31"}
|
| 801 |
+
{"current_steps": 3980, "total_steps": 6188, "loss": 0.0796, "lr": 1.3620421733940234e-05, "epoch": 4.503678551216751, "percentage": 64.32, "elapsed_time": "5:59:55", "remaining_time": "3:19:40"}
|
| 802 |
+
{"current_steps": 3985, "total_steps": 6188, "loss": 0.0785, "lr": 1.356698190036453e-05, "epoch": 4.509337860780985, "percentage": 64.4, "elapsed_time": "6:01:28", "remaining_time": "3:19:49"}
|
| 803 |
+
{"current_steps": 3990, "total_steps": 6188, "loss": 0.0752, "lr": 1.3513593246732506e-05, "epoch": 4.514997170345218, "percentage": 64.48, "elapsed_time": "6:02:59", "remaining_time": "3:19:58"}
|
| 804 |
+
{"current_steps": 3995, "total_steps": 6188, "loss": 0.0915, "lr": 1.3460256197794768e-05, "epoch": 4.5206564799094515, "percentage": 64.56, "elapsed_time": "6:04:32", "remaining_time": "3:20:06"}
|
| 805 |
+
{"current_steps": 4000, "total_steps": 6188, "loss": 0.0746, "lr": 1.3406971177891343e-05, "epoch": 4.526315789473684, "percentage": 64.64, "elapsed_time": "6:06:07", "remaining_time": "3:20:16"}
|