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 sha256:9e90bae9b4d8168d937aa2d168e9b79ac41a9ebdfc64142d362bd16f00e89b9b
|
| 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:c1d84d2dce38c1f58d50915b1029f9816c5ea1c686dee0a74436adb3b639aecb
|
| 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:c8bb2af314e367b1dd5d502c84fcf15e7e1e7cf5ce46bd3bc01e7d667159ef9a
|
| 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:b8b0daec93e8547e4017b7b582930e4fb625e8d62f3e58ca4fe14702a358cc09
|
| 3 |
size 1580230264
|
trainer_log.jsonl
CHANGED
|
@@ -760,3 +760,43 @@
|
|
| 760 |
{"current_steps": 3790, "total_steps": 6188, "loss": 0.1833, "lr": 1.568482452586929e-05, "epoch": 4.288624787775891, "percentage": 61.25, "elapsed_time": "5:45:36", "remaining_time": "3:38:40"}
|
| 761 |
{"current_steps": 3795, "total_steps": 6188, "loss": 0.1505, "lr": 1.5629758306415652e-05, "epoch": 4.294284097340125, "percentage": 61.33, "elapsed_time": "5:48:32", "remaining_time": "3:39:46"}
|
| 762 |
{"current_steps": 3800, "total_steps": 6188, "loss": 0.16, "lr": 1.5574726855824827e-05, "epoch": 4.299943406904358, "percentage": 61.41, "elapsed_time": "5:51:35", "remaining_time": "3:40:56"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 760 |
{"current_steps": 3790, "total_steps": 6188, "loss": 0.1833, "lr": 1.568482452586929e-05, "epoch": 4.288624787775891, "percentage": 61.25, "elapsed_time": "5:45:36", "remaining_time": "3:38:40"}
|
| 761 |
{"current_steps": 3795, "total_steps": 6188, "loss": 0.1505, "lr": 1.5629758306415652e-05, "epoch": 4.294284097340125, "percentage": 61.33, "elapsed_time": "5:48:32", "remaining_time": "3:39:46"}
|
| 762 |
{"current_steps": 3800, "total_steps": 6188, "loss": 0.16, "lr": 1.5574726855824827e-05, "epoch": 4.299943406904358, "percentage": 61.41, "elapsed_time": "5:51:35", "remaining_time": "3:40:56"}
|
| 763 |
+
{"current_steps": 3805, "total_steps": 6188, "loss": 0.1617, "lr": 1.5519730611917206e-05, "epoch": 4.305602716468591, "percentage": 61.49, "elapsed_time": "5:55:53", "remaining_time": "3:42:53"}
|
| 764 |
+
{"current_steps": 3810, "total_steps": 6188, "loss": 0.1729, "lr": 1.546477001223309e-05, "epoch": 4.311262026032824, "percentage": 61.57, "elapsed_time": "5:58:59", "remaining_time": "3:44:03"}
|
| 765 |
+
{"current_steps": 3815, "total_steps": 6188, "loss": 0.1567, "lr": 1.5409845494029208e-05, "epoch": 4.3169213355970575, "percentage": 61.65, "elapsed_time": "6:02:05", "remaining_time": "3:45:13"}
|
| 766 |
+
{"current_steps": 3820, "total_steps": 6188, "loss": 0.1639, "lr": 1.5354957494275207e-05, "epoch": 4.32258064516129, "percentage": 61.73, "elapsed_time": "6:05:06", "remaining_time": "3:46:19"}
|
| 767 |
+
{"current_steps": 3825, "total_steps": 6188, "loss": 0.16, "lr": 1.5300106449650234e-05, "epoch": 4.3282399547255235, "percentage": 61.81, "elapsed_time": "6:08:09", "remaining_time": "3:47:26"}
|
| 768 |
+
{"current_steps": 3830, "total_steps": 6188, "loss": 0.1447, "lr": 1.524529279653939e-05, "epoch": 4.333899264289757, "percentage": 61.89, "elapsed_time": "6:11:10", "remaining_time": "3:48:31"}
|
| 769 |
+
{"current_steps": 3835, "total_steps": 6188, "loss": 0.1545, "lr": 1.5190516971030324e-05, "epoch": 4.3395585738539895, "percentage": 61.97, "elapsed_time": "6:14:15", "remaining_time": "3:49:37"}
|
| 770 |
+
{"current_steps": 3840, "total_steps": 6188, "loss": 0.2007, "lr": 1.5135779408909732e-05, "epoch": 4.345217883418223, "percentage": 62.06, "elapsed_time": "6:17:19", "remaining_time": "3:50:43"}
|
| 771 |
+
{"current_steps": 3845, "total_steps": 6188, "loss": 0.1487, "lr": 1.5081080545659874e-05, "epoch": 4.350877192982456, "percentage": 62.14, "elapsed_time": "6:20:24", "remaining_time": "3:51:48"}
|
| 772 |
+
{"current_steps": 3850, "total_steps": 6188, "loss": 0.1598, "lr": 1.5026420816455156e-05, "epoch": 4.356536502546689, "percentage": 62.22, "elapsed_time": "6:23:18", "remaining_time": "3:52:46"}
|
| 773 |
+
{"current_steps": 3855, "total_steps": 6188, "loss": 0.1657, "lr": 1.4971800656158624e-05, "epoch": 4.362195812110922, "percentage": 62.3, "elapsed_time": "6:26:21", "remaining_time": "3:53:49"}
|
| 774 |
+
{"current_steps": 3860, "total_steps": 6188, "loss": 0.1435, "lr": 1.4917220499318506e-05, "epoch": 4.367855121675156, "percentage": 62.38, "elapsed_time": "6:29:24", "remaining_time": "3:54:51"}
|
| 775 |
+
{"current_steps": 3865, "total_steps": 6188, "loss": 0.1478, "lr": 1.4862680780164805e-05, "epoch": 4.373514431239389, "percentage": 62.46, "elapsed_time": "6:32:26", "remaining_time": "3:55:52"}
|
| 776 |
+
{"current_steps": 3870, "total_steps": 6188, "loss": 0.1392, "lr": 1.4808181932605787e-05, "epoch": 4.379173740803622, "percentage": 62.54, "elapsed_time": "6:35:29", "remaining_time": "3:56:53"}
|
| 777 |
+
{"current_steps": 3875, "total_steps": 6188, "loss": 0.1586, "lr": 1.4753724390224551e-05, "epoch": 4.384833050367855, "percentage": 62.62, "elapsed_time": "6:38:30", "remaining_time": "3:57:52"}
|
| 778 |
+
{"current_steps": 3880, "total_steps": 6188, "loss": 0.148, "lr": 1.4699308586275591e-05, "epoch": 4.390492359932089, "percentage": 62.7, "elapsed_time": "6:41:27", "remaining_time": "3:58:48"}
|
| 779 |
+
{"current_steps": 3885, "total_steps": 6188, "loss": 0.1497, "lr": 1.464493495368132e-05, "epoch": 4.396151669496321, "percentage": 62.78, "elapsed_time": "6:44:31", "remaining_time": "3:59:48"}
|
| 780 |
+
{"current_steps": 3890, "total_steps": 6188, "loss": 0.1577, "lr": 1.459060392502866e-05, "epoch": 4.401810979060555, "percentage": 62.86, "elapsed_time": "6:47:32", "remaining_time": "4:00:44"}
|
| 781 |
+
{"current_steps": 3895, "total_steps": 6188, "loss": 0.1413, "lr": 1.4536315932565575e-05, "epoch": 4.407470288624788, "percentage": 62.94, "elapsed_time": "6:50:37", "remaining_time": "4:01:43"}
|
| 782 |
+
{"current_steps": 3900, "total_steps": 6188, "loss": 0.1618, "lr": 1.448207140819764e-05, "epoch": 4.413129598189021, "percentage": 63.03, "elapsed_time": "6:53:43", "remaining_time": "4:02:43"}
|
| 783 |
+
{"current_steps": 3905, "total_steps": 6188, "loss": 0.1642, "lr": 1.4427870783484613e-05, "epoch": 4.418788907753254, "percentage": 63.11, "elapsed_time": "6:56:46", "remaining_time": "4:03:39"}
|
| 784 |
+
{"current_steps": 3910, "total_steps": 6188, "loss": 0.1375, "lr": 1.4373714489636985e-05, "epoch": 4.4244482173174875, "percentage": 63.19, "elapsed_time": "6:59:14", "remaining_time": "4:04:15"}
|
| 785 |
+
{"current_steps": 3915, "total_steps": 6188, "loss": 0.106, "lr": 1.4319602957512564e-05, "epoch": 4.43010752688172, "percentage": 63.27, "elapsed_time": "7:00:58", "remaining_time": "4:04:24"}
|
| 786 |
+
{"current_steps": 3920, "total_steps": 6188, "loss": 0.0807, "lr": 1.4265536617613043e-05, "epoch": 4.4357668364459535, "percentage": 63.35, "elapsed_time": "7:02:40", "remaining_time": "4:04:33"}
|
| 787 |
+
{"current_steps": 3925, "total_steps": 6188, "loss": 0.078, "lr": 1.4211515900080568e-05, "epoch": 4.441426146010187, "percentage": 63.43, "elapsed_time": "7:04:11", "remaining_time": "4:04:34"}
|
| 788 |
+
{"current_steps": 3930, "total_steps": 6188, "loss": 0.0906, "lr": 1.4157541234694324e-05, "epoch": 4.44708545557442, "percentage": 63.51, "elapsed_time": "7:05:46", "remaining_time": "4:04:37"}
|
| 789 |
+
{"current_steps": 3935, "total_steps": 6188, "loss": 0.0837, "lr": 1.4103613050867117e-05, "epoch": 4.452744765138653, "percentage": 63.59, "elapsed_time": "7:07:29", "remaining_time": "4:04:45"}
|
| 790 |
+
{"current_steps": 3940, "total_steps": 6188, "loss": 0.1193, "lr": 1.4049731777641948e-05, "epoch": 4.458404074702886, "percentage": 63.67, "elapsed_time": "7:09:12", "remaining_time": "4:04:53"}
|
| 791 |
+
{"current_steps": 3945, "total_steps": 6188, "loss": 0.1011, "lr": 1.3995897843688615e-05, "epoch": 4.46406338426712, "percentage": 63.75, "elapsed_time": "7:10:52", "remaining_time": "4:04:58"}
|
| 792 |
+
{"current_steps": 3950, "total_steps": 6188, "loss": 0.0907, "lr": 1.3942111677300276e-05, "epoch": 4.469722693831352, "percentage": 63.83, "elapsed_time": "7:12:29", "remaining_time": "4:05:02"}
|
| 793 |
+
{"current_steps": 3955, "total_steps": 6188, "loss": 0.1244, "lr": 1.388837370639008e-05, "epoch": 4.475382003395586, "percentage": 63.91, "elapsed_time": "7:14:58", "remaining_time": "4:05:35"}
|
| 794 |
+
{"current_steps": 3960, "total_steps": 6188, "loss": 0.0646, "lr": 1.3834684358487731e-05, "epoch": 4.481041312959819, "percentage": 63.99, "elapsed_time": "7:16:45", "remaining_time": "4:05:43"}
|
| 795 |
+
{"current_steps": 3965, "total_steps": 6188, "loss": 0.0812, "lr": 1.3781044060736089e-05, "epoch": 4.486700622524052, "percentage": 64.08, "elapsed_time": "7:18:36", "remaining_time": "4:05:54"}
|
| 796 |
+
{"current_steps": 3970, "total_steps": 6188, "loss": 0.0802, "lr": 1.3727453239887796e-05, "epoch": 4.492359932088285, "percentage": 64.16, "elapsed_time": "7:20:25", "remaining_time": "4:06:03"}
|
| 797 |
+
{"current_steps": 3975, "total_steps": 6188, "loss": 0.1237, "lr": 1.367391232230185e-05, "epoch": 4.498019241652519, "percentage": 64.24, "elapsed_time": "7:22:18", "remaining_time": "4:06:14"}
|
| 798 |
+
{"current_steps": 3980, "total_steps": 6188, "loss": 0.0756, "lr": 1.3620421733940234e-05, "epoch": 4.503678551216751, "percentage": 64.32, "elapsed_time": "7:23:50", "remaining_time": "4:06:13"}
|
| 799 |
+
{"current_steps": 3985, "total_steps": 6188, "loss": 0.0813, "lr": 1.356698190036453e-05, "epoch": 4.509337860780985, "percentage": 64.4, "elapsed_time": "7:25:43", "remaining_time": "4:06:24"}
|
| 800 |
+
{"current_steps": 3990, "total_steps": 6188, "loss": 0.0751, "lr": 1.3513593246732506e-05, "epoch": 4.514997170345218, "percentage": 64.48, "elapsed_time": "7:27:15", "remaining_time": "4:06:22"}
|
| 801 |
+
{"current_steps": 3995, "total_steps": 6188, "loss": 0.0822, "lr": 1.3460256197794768e-05, "epoch": 4.5206564799094515, "percentage": 64.56, "elapsed_time": "7:28:47", "remaining_time": "4:06:21"}
|
| 802 |
+
{"current_steps": 4000, "total_steps": 6188, "loss": 0.0849, "lr": 1.3406971177891343e-05, "epoch": 4.526315789473684, "percentage": 64.64, "elapsed_time": "7:30:24", "remaining_time": "4:06:22"}
|