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 sha256:51b1bf5647ba0bdb40aa0eb688d7ab15d76b1e3783facc7ee3092512540b2386
|
| 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 sha256:721f043ecb9035ea61171024da4fa407d2cb37d3ecf9847d61868ba38f8edf88
|
| 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 sha256:373b6435a895496f9b6aea8d0071ed9abb01e96b746f0f4fba7ae666b6ce5d40
|
| 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 sha256:0a93c7ee9827ad2246a12a2c9b214f41a619e7df94a96b320d0ab537b2661e9f
|
| 3 |
size 1580230264
|
trainer_log.jsonl
CHANGED
|
@@ -760,3 +760,42 @@
|
|
| 760 |
{"current_steps": 3800, "total_steps": 9128, "loss": 0.2543, "lr": 2.9006474362441962e-05, "epoch": 2.9144610663598005, "percentage": 41.63, "elapsed_time": "23:32:05", "remaining_time": "1 day, 8:59:54"}
|
| 761 |
{"current_steps": 3805, "total_steps": 9128, "loss": 0.2595, "lr": 2.8972312827401824e-05, "epoch": 2.9182968929804374, "percentage": 41.68, "elapsed_time": "23:35:00", "remaining_time": "1 day, 8:59:31"}
|
| 762 |
{"current_steps": 3810, "total_steps": 9128, "loss": 0.2533, "lr": 2.89381184882038e-05, "epoch": 2.9221327196010742, "percentage": 41.74, "elapsed_time": "23:36:37", "remaining_time": "1 day, 8:57:20"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 760 |
{"current_steps": 3800, "total_steps": 9128, "loss": 0.2543, "lr": 2.9006474362441962e-05, "epoch": 2.9144610663598005, "percentage": 41.63, "elapsed_time": "23:32:05", "remaining_time": "1 day, 8:59:54"}
|
| 761 |
{"current_steps": 3805, "total_steps": 9128, "loss": 0.2595, "lr": 2.8972312827401824e-05, "epoch": 2.9182968929804374, "percentage": 41.68, "elapsed_time": "23:35:00", "remaining_time": "1 day, 8:59:31"}
|
| 762 |
{"current_steps": 3810, "total_steps": 9128, "loss": 0.2533, "lr": 2.89381184882038e-05, "epoch": 2.9221327196010742, "percentage": 41.74, "elapsed_time": "23:36:37", "remaining_time": "1 day, 8:57:20"}
|
| 763 |
+
{"current_steps": 3815, "total_steps": 9128, "loss": 0.2534, "lr": 2.890389146986767e-05, "epoch": 2.9259685462217107, "percentage": 41.79, "elapsed_time": "23:38:14", "remaining_time": "1 day, 8:55:08"}
|
| 764 |
+
{"current_steps": 3820, "total_steps": 9128, "loss": 0.2569, "lr": 2.8869631897532676e-05, "epoch": 2.9298043728423475, "percentage": 41.85, "elapsed_time": "23:40:04", "remaining_time": "1 day, 8:53:14"}
|
| 765 |
+
{"current_steps": 3825, "total_steps": 9128, "loss": 0.2453, "lr": 2.8835339896457104e-05, "epoch": 2.9336401994629844, "percentage": 41.9, "elapsed_time": "23:41:55", "remaining_time": "1 day, 8:51:21"}
|
| 766 |
+
{"current_steps": 3830, "total_steps": 9128, "loss": 0.2408, "lr": 2.8801015592017787e-05, "epoch": 2.937476026083621, "percentage": 41.96, "elapsed_time": "23:43:38", "remaining_time": "1 day, 8:49:17"}
|
| 767 |
+
{"current_steps": 3835, "total_steps": 9128, "loss": 0.2488, "lr": 2.8766659109709664e-05, "epoch": 2.9413118527042577, "percentage": 42.01, "elapsed_time": "23:45:20", "remaining_time": "1 day, 8:47:14"}
|
| 768 |
+
{"current_steps": 3840, "total_steps": 9128, "loss": 0.2475, "lr": 2.8732270575145336e-05, "epoch": 2.9451476793248945, "percentage": 42.07, "elapsed_time": "23:47:02", "remaining_time": "1 day, 8:45:08"}
|
| 769 |
+
{"current_steps": 3845, "total_steps": 9128, "loss": 0.2376, "lr": 2.8697850114054584e-05, "epoch": 2.9489835059455314, "percentage": 42.12, "elapsed_time": "23:48:47", "remaining_time": "1 day, 8:43:08"}
|
| 770 |
+
{"current_steps": 3850, "total_steps": 9128, "loss": 0.2406, "lr": 2.8663397852283904e-05, "epoch": 2.9528193325661682, "percentage": 42.18, "elapsed_time": "23:50:24", "remaining_time": "1 day, 8:40:58"}
|
| 771 |
+
{"current_steps": 3855, "total_steps": 9128, "loss": 0.2509, "lr": 2.8628913915796083e-05, "epoch": 2.9566551591868047, "percentage": 42.23, "elapsed_time": "23:52:02", "remaining_time": "1 day, 8:38:47"}
|
| 772 |
+
{"current_steps": 3860, "total_steps": 9128, "loss": 0.2446, "lr": 2.8594398430669697e-05, "epoch": 2.9604909858074415, "percentage": 42.29, "elapsed_time": "23:53:43", "remaining_time": "1 day, 8:36:42"}
|
| 773 |
+
{"current_steps": 3865, "total_steps": 9128, "loss": 0.2744, "lr": 2.8559851523098695e-05, "epoch": 2.9643268124280784, "percentage": 42.34, "elapsed_time": "23:55:20", "remaining_time": "1 day, 8:34:31"}
|
| 774 |
+
{"current_steps": 3870, "total_steps": 9128, "loss": 0.2439, "lr": 2.8525273319391868e-05, "epoch": 2.968162639048715, "percentage": 42.4, "elapsed_time": "23:56:57", "remaining_time": "1 day, 8:32:20"}
|
| 775 |
+
{"current_steps": 3875, "total_steps": 9128, "loss": 0.2447, "lr": 2.8490663945972467e-05, "epoch": 2.9719984656693517, "percentage": 42.45, "elapsed_time": "23:58:38", "remaining_time": "1 day, 8:30:14"}
|
| 776 |
+
{"current_steps": 3880, "total_steps": 9128, "loss": 0.2435, "lr": 2.84560235293777e-05, "epoch": 2.9758342922899885, "percentage": 42.51, "elapsed_time": "1 day, 0:00:15", "remaining_time": "1 day, 8:28:03"}
|
| 777 |
+
{"current_steps": 3885, "total_steps": 9128, "loss": 0.2524, "lr": 2.842135219625826e-05, "epoch": 2.9796701189106254, "percentage": 42.56, "elapsed_time": "1 day, 0:01:53", "remaining_time": "1 day, 8:25:53"}
|
| 778 |
+
{"current_steps": 3890, "total_steps": 9128, "loss": 0.2517, "lr": 2.838665007337788e-05, "epoch": 2.9835059455312622, "percentage": 42.62, "elapsed_time": "1 day, 0:03:32", "remaining_time": "1 day, 8:23:45"}
|
| 779 |
+
{"current_steps": 3895, "total_steps": 9128, "loss": 0.2561, "lr": 2.8351917287612858e-05, "epoch": 2.9873417721518987, "percentage": 42.67, "elapsed_time": "1 day, 0:05:13", "remaining_time": "1 day, 8:21:40"}
|
| 780 |
+
{"current_steps": 3900, "total_steps": 9128, "loss": 0.2525, "lr": 2.8317153965951628e-05, "epoch": 2.9911775987725355, "percentage": 42.73, "elapsed_time": "1 day, 0:06:52", "remaining_time": "1 day, 8:19:33"}
|
| 781 |
+
{"current_steps": 3905, "total_steps": 9128, "loss": 0.2528, "lr": 2.8282360235494244e-05, "epoch": 2.9950134253931724, "percentage": 42.78, "elapsed_time": "1 day, 0:08:30", "remaining_time": "1 day, 8:17:24"}
|
| 782 |
+
{"current_steps": 3910, "total_steps": 9128, "loss": 0.2536, "lr": 2.8247536223451935e-05, "epoch": 2.998849252013809, "percentage": 42.84, "elapsed_time": "1 day, 0:10:11", "remaining_time": "1 day, 8:15:19"}
|
| 783 |
+
{"current_steps": 3915, "total_steps": 9128, "loss": 0.2096, "lr": 2.8212682057146666e-05, "epoch": 3.002301495972382, "percentage": 42.89, "elapsed_time": "1 day, 0:12:42", "remaining_time": "1 day, 8:14:20"}
|
| 784 |
+
{"current_steps": 3920, "total_steps": 9128, "loss": 0.2067, "lr": 2.817779786401063e-05, "epoch": 3.006137322593019, "percentage": 42.94, "elapsed_time": "1 day, 0:15:38", "remaining_time": "1 day, 8:13:55"}
|
| 785 |
+
{"current_steps": 3925, "total_steps": 9128, "loss": 0.1999, "lr": 2.814288377158582e-05, "epoch": 3.0099731492136557, "percentage": 43.0, "elapsed_time": "1 day, 0:18:20", "remaining_time": "1 day, 8:13:11"}
|
| 786 |
+
{"current_steps": 3930, "total_steps": 9128, "loss": 0.1939, "lr": 2.810793990752352e-05, "epoch": 3.013808975834292, "percentage": 43.05, "elapsed_time": "1 day, 0:21:24", "remaining_time": "1 day, 8:12:56"}
|
| 787 |
+
{"current_steps": 3935, "total_steps": 9128, "loss": 0.1951, "lr": 2.8072966399583897e-05, "epoch": 3.017644802454929, "percentage": 43.11, "elapsed_time": "1 day, 0:24:28", "remaining_time": "1 day, 8:12:39"}
|
| 788 |
+
{"current_steps": 3940, "total_steps": 9128, "loss": 0.1958, "lr": 2.8037963375635473e-05, "epoch": 3.021480629075566, "percentage": 43.16, "elapsed_time": "1 day, 0:27:33", "remaining_time": "1 day, 8:12:24"}
|
| 789 |
+
{"current_steps": 3945, "total_steps": 9128, "loss": 0.2118, "lr": 2.8002930963654705e-05, "epoch": 3.0253164556962027, "percentage": 43.22, "elapsed_time": "1 day, 0:30:32", "remaining_time": "1 day, 8:12:00"}
|
| 790 |
+
{"current_steps": 3950, "total_steps": 9128, "loss": 0.1976, "lr": 2.7967869291725474e-05, "epoch": 3.029152282316839, "percentage": 43.27, "elapsed_time": "1 day, 0:33:26", "remaining_time": "1 day, 8:11:31"}
|
| 791 |
+
{"current_steps": 3955, "total_steps": 9128, "loss": 0.1916, "lr": 2.793277848803867e-05, "epoch": 3.032988108937476, "percentage": 43.33, "elapsed_time": "1 day, 0:36:15", "remaining_time": "1 day, 8:10:53"}
|
| 792 |
+
{"current_steps": 3960, "total_steps": 9128, "loss": 0.1804, "lr": 2.789765868089167e-05, "epoch": 3.036823935558113, "percentage": 43.38, "elapsed_time": "1 day, 0:38:47", "remaining_time": "1 day, 8:09:53"}
|
| 793 |
+
{"current_steps": 3965, "total_steps": 9128, "loss": 0.1939, "lr": 2.7862509998687895e-05, "epoch": 3.0406597621787497, "percentage": 43.44, "elapsed_time": "1 day, 0:41:43", "remaining_time": "1 day, 8:09:24"}
|
| 794 |
+
{"current_steps": 3970, "total_steps": 9128, "loss": 0.1847, "lr": 2.7827332569936345e-05, "epoch": 3.044495588799386, "percentage": 43.49, "elapsed_time": "1 day, 0:44:29", "remaining_time": "1 day, 8:08:43"}
|
| 795 |
+
{"current_steps": 3975, "total_steps": 9128, "loss": 0.1951, "lr": 2.7792126523251122e-05, "epoch": 3.048331415420023, "percentage": 43.55, "elapsed_time": "1 day, 0:47:18", "remaining_time": "1 day, 8:08:04"}
|
| 796 |
+
{"current_steps": 3980, "total_steps": 9128, "loss": 0.1819, "lr": 2.7756891987350945e-05, "epoch": 3.05216724204066, "percentage": 43.6, "elapsed_time": "1 day, 0:50:06", "remaining_time": "1 day, 8:07:24"}
|
| 797 |
+
{"current_steps": 3985, "total_steps": 9128, "loss": 0.1859, "lr": 2.7721629091058724e-05, "epoch": 3.0560030686612967, "percentage": 43.66, "elapsed_time": "1 day, 0:52:51", "remaining_time": "1 day, 8:06:39"}
|
| 798 |
+
{"current_steps": 3990, "total_steps": 9128, "loss": 0.1934, "lr": 2.7686337963301027e-05, "epoch": 3.059838895281933, "percentage": 43.71, "elapsed_time": "1 day, 0:55:38", "remaining_time": "1 day, 8:05:58"}
|
| 799 |
+
{"current_steps": 3995, "total_steps": 9128, "loss": 0.1847, "lr": 2.765101873310765e-05, "epoch": 3.06367472190257, "percentage": 43.77, "elapsed_time": "1 day, 0:58:28", "remaining_time": "1 day, 8:05:19"}
|
| 800 |
+
{"current_steps": 4000, "total_steps": 9128, "loss": 0.1901, "lr": 2.761567152961115e-05, "epoch": 3.067510548523207, "percentage": 43.82, "elapsed_time": "1 day, 1:01:24", "remaining_time": "1 day, 8:04:47"}
|
| 801 |
+
{"current_steps": 4005, "total_steps": 9128, "loss": 0.2044, "lr": 2.758029648204635e-05, "epoch": 3.0713463751438437, "percentage": 43.88, "elapsed_time": "1 day, 1:05:22", "remaining_time": "1 day, 8:05:36"}
|