penfever commited on
Commit
b61c1cb
·
verified ·
1 Parent(s): 1be6bc1

Training in progress, step 3600

Browse files
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fc993fdd01a09b520ec832fb24610d1ce0e2842b765077f2674334bc6bfe18c8
3
  size 4902257696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89da512e50172d9c310632118360ff1aec089d10d4258f0e06737d884f3b9bd0
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:b1a1fe155a80d2ef486cc1906a123f619c30f1896659ae85741c33b3d0b598ce
3
  size 4915960368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07cb051324cc2c4d66e1d47782d42885e502c8a9c14d59335ee65e04444d840a
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:db48171ec06151fb4191ac2ecb6c537dbe0c9b4341e3d83f83a53af8304c17eb
3
  size 4983068496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4f9e6a5964be70e8651982d916ec3cadecfc982dd59a2d96db4ec3d4eef7fb0
3
  size 4983068496
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7524fe06622c2ee77bab3c857718f6f3c14a72610b5db2f3cb64be410c7d7c2f
3
  size 1580230264
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7cc8ebcbc168509f33285cd56036ac45e7a22573eeb84f3afc086e97b992bff3
3
  size 1580230264
trainer_log.jsonl CHANGED
@@ -680,3 +680,43 @@
680
  {"current_steps": 3390, "total_steps": 6188, "loss": 0.0715, "lr": 2.0163593411733533e-05, "epoch": 3.835314091680815, "percentage": 54.78, "elapsed_time": "2:22:46", "remaining_time": "1:57:50"}
681
  {"current_steps": 3395, "total_steps": 6188, "loss": 0.0893, "lr": 2.0107182572626897e-05, "epoch": 3.8409734012450483, "percentage": 54.86, "elapsed_time": "2:24:48", "remaining_time": "1:59:08"}
682
  {"current_steps": 3400, "total_steps": 6188, "loss": 0.0863, "lr": 2.0050770880794843e-05, "epoch": 3.8466327108092813, "percentage": 54.95, "elapsed_time": "2:26:30", "remaining_time": "2:00:07"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
680
  {"current_steps": 3390, "total_steps": 6188, "loss": 0.0715, "lr": 2.0163593411733533e-05, "epoch": 3.835314091680815, "percentage": 54.78, "elapsed_time": "2:22:46", "remaining_time": "1:57:50"}
681
  {"current_steps": 3395, "total_steps": 6188, "loss": 0.0893, "lr": 2.0107182572626897e-05, "epoch": 3.8409734012450483, "percentage": 54.86, "elapsed_time": "2:24:48", "remaining_time": "1:59:08"}
682
  {"current_steps": 3400, "total_steps": 6188, "loss": 0.0863, "lr": 2.0050770880794843e-05, "epoch": 3.8466327108092813, "percentage": 54.95, "elapsed_time": "2:26:30", "remaining_time": "2:00:07"}
683
+ {"current_steps": 3405, "total_steps": 6188, "loss": 0.0707, "lr": 1.9994358785038736e-05, "epoch": 3.8522920203735147, "percentage": 55.03, "elapsed_time": "2:29:23", "remaining_time": "2:02:06"}
684
+ {"current_steps": 3410, "total_steps": 6188, "loss": 0.0945, "lr": 1.9937946734163117e-05, "epoch": 3.8579513299377477, "percentage": 55.11, "elapsed_time": "2:31:02", "remaining_time": "2:03:03"}
685
+ {"current_steps": 3415, "total_steps": 6188, "loss": 0.0778, "lr": 1.98815351769722e-05, "epoch": 3.8636106395019807, "percentage": 55.19, "elapsed_time": "2:32:45", "remaining_time": "2:04:02"}
686
+ {"current_steps": 3420, "total_steps": 6188, "loss": 0.1177, "lr": 1.982512456226628e-05, "epoch": 3.869269949066214, "percentage": 55.27, "elapsed_time": "2:34:32", "remaining_time": "2:05:04"}
687
+ {"current_steps": 3425, "total_steps": 6188, "loss": 0.1064, "lr": 1.976871533883812e-05, "epoch": 3.874929258630447, "percentage": 55.35, "elapsed_time": "2:36:09", "remaining_time": "2:05:58"}
688
+ {"current_steps": 3430, "total_steps": 6188, "loss": 0.0865, "lr": 1.971230795546944e-05, "epoch": 3.88058856819468, "percentage": 55.43, "elapsed_time": "2:37:42", "remaining_time": "2:06:48"}
689
+ {"current_steps": 3435, "total_steps": 6188, "loss": 0.0925, "lr": 1.965590286092731e-05, "epoch": 3.8862478777589136, "percentage": 55.51, "elapsed_time": "2:39:14", "remaining_time": "2:07:37"}
690
+ {"current_steps": 3440, "total_steps": 6188, "loss": 0.0849, "lr": 1.9599500503960596e-05, "epoch": 3.8919071873231466, "percentage": 55.59, "elapsed_time": "2:40:51", "remaining_time": "2:08:29"}
691
+ {"current_steps": 3445, "total_steps": 6188, "loss": 0.0919, "lr": 1.954310133329639e-05, "epoch": 3.8975664968873796, "percentage": 55.67, "elapsed_time": "2:42:19", "remaining_time": "2:09:14"}
692
+ {"current_steps": 3450, "total_steps": 6188, "loss": 0.1126, "lr": 1.948670579763641e-05, "epoch": 3.903225806451613, "percentage": 55.75, "elapsed_time": "2:44:07", "remaining_time": "2:10:15"}
693
+ {"current_steps": 3455, "total_steps": 6188, "loss": 0.1174, "lr": 1.9430314345653486e-05, "epoch": 3.908885116015846, "percentage": 55.83, "elapsed_time": "2:46:02", "remaining_time": "2:11:20"}
694
+ {"current_steps": 3460, "total_steps": 6188, "loss": 0.0964, "lr": 1.9373927425987928e-05, "epoch": 3.914544425580079, "percentage": 55.91, "elapsed_time": "2:47:56", "remaining_time": "2:12:24"}
695
+ {"current_steps": 3465, "total_steps": 6188, "loss": 0.0949, "lr": 1.9317545487244016e-05, "epoch": 3.9202037351443124, "percentage": 56.0, "elapsed_time": "2:49:35", "remaining_time": "2:13:16"}
696
+ {"current_steps": 3470, "total_steps": 6188, "loss": 0.0838, "lr": 1.926116897798639e-05, "epoch": 3.9258630447085454, "percentage": 56.08, "elapsed_time": "2:51:06", "remaining_time": "2:14:01"}
697
+ {"current_steps": 3475, "total_steps": 6188, "loss": 0.083, "lr": 1.9204798346736485e-05, "epoch": 3.931522354272779, "percentage": 56.16, "elapsed_time": "2:52:38", "remaining_time": "2:14:47"}
698
+ {"current_steps": 3480, "total_steps": 6188, "loss": 0.083, "lr": 1.914843404196899e-05, "epoch": 3.937181663837012, "percentage": 56.24, "elapsed_time": "2:54:10", "remaining_time": "2:15:32"}
699
+ {"current_steps": 3485, "total_steps": 6188, "loss": 0.0993, "lr": 1.9092076512108253e-05, "epoch": 3.9428409734012453, "percentage": 56.32, "elapsed_time": "2:55:40", "remaining_time": "2:16:15"}
700
+ {"current_steps": 3490, "total_steps": 6188, "loss": 0.0802, "lr": 1.903572620552471e-05, "epoch": 3.9485002829654783, "percentage": 56.4, "elapsed_time": "2:57:14", "remaining_time": "2:17:01"}
701
+ {"current_steps": 3495, "total_steps": 6188, "loss": 0.0804, "lr": 1.8979383570531358e-05, "epoch": 3.9541595925297113, "percentage": 56.48, "elapsed_time": "2:58:50", "remaining_time": "2:17:48"}
702
+ {"current_steps": 3500, "total_steps": 6188, "loss": 0.0945, "lr": 1.8923049055380128e-05, "epoch": 3.9598189020939447, "percentage": 56.56, "elapsed_time": "3:00:23", "remaining_time": "2:18:32"}
703
+ {"current_steps": 3505, "total_steps": 6188, "loss": 0.0747, "lr": 1.8866723108258376e-05, "epoch": 3.9654782116581777, "percentage": 56.64, "elapsed_time": "3:02:20", "remaining_time": "2:19:34"}
704
+ {"current_steps": 3510, "total_steps": 6188, "loss": 0.081, "lr": 1.8810406177285282e-05, "epoch": 3.9711375212224107, "percentage": 56.72, "elapsed_time": "3:04:04", "remaining_time": "2:20:26"}
705
+ {"current_steps": 3515, "total_steps": 6188, "loss": 0.0846, "lr": 1.8754098710508294e-05, "epoch": 3.976796830786644, "percentage": 56.8, "elapsed_time": "3:05:58", "remaining_time": "2:21:25"}
706
+ {"current_steps": 3520, "total_steps": 6188, "loss": 0.1772, "lr": 1.869780115589957e-05, "epoch": 3.982456140350877, "percentage": 56.88, "elapsed_time": "3:08:56", "remaining_time": "2:23:12"}
707
+ {"current_steps": 3525, "total_steps": 6188, "loss": 0.079, "lr": 1.8641513961352396e-05, "epoch": 3.98811544991511, "percentage": 56.97, "elapsed_time": "3:10:29", "remaining_time": "2:23:54"}
708
+ {"current_steps": 3530, "total_steps": 6188, "loss": 0.0912, "lr": 1.858523757467765e-05, "epoch": 3.9937747594793436, "percentage": 57.05, "elapsed_time": "3:12:21", "remaining_time": "2:24:50"}
709
+ {"current_steps": 3535, "total_steps": 6188, "loss": 0.1144, "lr": 1.8528972443600226e-05, "epoch": 3.9994340690435766, "percentage": 57.13, "elapsed_time": "3:14:17", "remaining_time": "2:25:48"}
710
+ {"current_steps": 3540, "total_steps": 6188, "loss": 0.1864, "lr": 1.8472719015755452e-05, "epoch": 4.005659309564233, "percentage": 57.21, "elapsed_time": "3:17:26", "remaining_time": "2:27:41"}
711
+ {"current_steps": 3545, "total_steps": 6188, "loss": 0.1665, "lr": 1.8416477738685567e-05, "epoch": 4.011318619128466, "percentage": 57.29, "elapsed_time": "3:20:17", "remaining_time": "2:29:19"}
712
+ {"current_steps": 3550, "total_steps": 6188, "loss": 0.1597, "lr": 1.8360249059836123e-05, "epoch": 4.016977928692699, "percentage": 57.37, "elapsed_time": "3:23:13", "remaining_time": "2:31:00"}
713
+ {"current_steps": 3555, "total_steps": 6188, "loss": 0.156, "lr": 1.830403342655246e-05, "epoch": 4.022637238256933, "percentage": 57.45, "elapsed_time": "3:26:02", "remaining_time": "2:32:36"}
714
+ {"current_steps": 3560, "total_steps": 6188, "loss": 0.1725, "lr": 1.824783128607612e-05, "epoch": 4.028296547821165, "percentage": 57.53, "elapsed_time": "3:28:59", "remaining_time": "2:34:16"}
715
+ {"current_steps": 3565, "total_steps": 6188, "loss": 0.1671, "lr": 1.8191643085541296e-05, "epoch": 4.033955857385399, "percentage": 57.61, "elapsed_time": "3:32:00", "remaining_time": "2:35:58"}
716
+ {"current_steps": 3570, "total_steps": 6188, "loss": 0.1599, "lr": 1.813546927197129e-05, "epoch": 4.039615166949632, "percentage": 57.69, "elapsed_time": "3:34:56", "remaining_time": "2:37:37"}
717
+ {"current_steps": 3575, "total_steps": 6188, "loss": 0.1751, "lr": 1.8079310292274928e-05, "epoch": 4.045274476513866, "percentage": 57.77, "elapsed_time": "3:37:45", "remaining_time": "2:39:09"}
718
+ {"current_steps": 3580, "total_steps": 6188, "loss": 0.1649, "lr": 1.8023166593243026e-05, "epoch": 4.050933786078098, "percentage": 57.85, "elapsed_time": "3:40:34", "remaining_time": "2:40:41"}
719
+ {"current_steps": 3585, "total_steps": 6188, "loss": 0.1591, "lr": 1.7967038621544845e-05, "epoch": 4.056593095642332, "percentage": 57.93, "elapsed_time": "3:43:37", "remaining_time": "2:42:22"}
720
+ {"current_steps": 3590, "total_steps": 6188, "loss": 0.1699, "lr": 1.791092682372449e-05, "epoch": 4.062252405206565, "percentage": 58.02, "elapsed_time": "3:46:26", "remaining_time": "2:43:52"}
721
+ {"current_steps": 3595, "total_steps": 6188, "loss": 0.1597, "lr": 1.7854831646197426e-05, "epoch": 4.067911714770798, "percentage": 58.1, "elapsed_time": "3:49:17", "remaining_time": "2:45:22"}
722
+ {"current_steps": 3600, "total_steps": 6188, "loss": 0.1551, "lr": 1.7798753535246856e-05, "epoch": 4.073571024335031, "percentage": 58.18, "elapsed_time": "3:52:21", "remaining_time": "2:47:02"}