sedrickkeh commited on
Commit
59eab0b
·
verified ·
1 Parent(s): 89e1cad

Training in progress, epoch 2

Browse files
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c191c8a4c1a879bf825a6a9e687639776658c910e36a145c554ea80ddb1fa918
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7499ffd4bbb0963e814dc8507a249678cbb7aa3d7e2d481a1f379492446d0d4f
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fa010cb30bb4c8c3d609fb85914f2d9fc3412ca932a90e6cc08f5530ad408a82
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d39aeb48cd5c85f7e076e9808aff73fe03674f27c03f46b603c11e43f4dc686
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:954c093209b321e4c93b8b61e76733f5f3eeed94c57f070ce51cdb9403261278
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f8179c15e0321543d50df79b1a1c1731be34dfe4ca2f0922a99de67e0c280c8
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:41b0570c0621adb407899d2303c49c4c239ac24013f29d1b655ef4d2455ec2c6
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9cd408b853b714886f9d5d51597c9937b8a2e9b5f3b9198029496d733e432b6
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -54,3 +54,29 @@
54
  {"current_steps": 530, "total_steps": 804, "loss": 0.6844, "lr": 5e-06, "epoch": 1.9711761971176198, "percentage": 65.92, "elapsed_time": "8:34:01", "remaining_time": "4:25:44"}
55
  {"current_steps": 537, "total_steps": 804, "eval_loss": 0.7266745567321777, "epoch": 1.9972105997210599, "percentage": 66.79, "elapsed_time": "8:46:07", "remaining_time": "4:21:35"}
56
  {"current_steps": 540, "total_steps": 804, "loss": 0.6783, "lr": 5e-06, "epoch": 2.00836820083682, "percentage": 67.16, "elapsed_time": "8:49:36", "remaining_time": "4:18:55"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
54
  {"current_steps": 530, "total_steps": 804, "loss": 0.6844, "lr": 5e-06, "epoch": 1.9711761971176198, "percentage": 65.92, "elapsed_time": "8:34:01", "remaining_time": "4:25:44"}
55
  {"current_steps": 537, "total_steps": 804, "eval_loss": 0.7266745567321777, "epoch": 1.9972105997210599, "percentage": 66.79, "elapsed_time": "8:46:07", "remaining_time": "4:21:35"}
56
  {"current_steps": 540, "total_steps": 804, "loss": 0.6783, "lr": 5e-06, "epoch": 2.00836820083682, "percentage": 67.16, "elapsed_time": "8:49:36", "remaining_time": "4:18:55"}
57
+ {"current_steps": 550, "total_steps": 804, "loss": 0.6332, "lr": 5e-06, "epoch": 2.0455602045560206, "percentage": 68.41, "elapsed_time": "8:59:12", "remaining_time": "4:09:01"}
58
+ {"current_steps": 560, "total_steps": 804, "loss": 0.6296, "lr": 5e-06, "epoch": 2.082752208275221, "percentage": 69.65, "elapsed_time": "9:08:47", "remaining_time": "3:59:07"}
59
+ {"current_steps": 570, "total_steps": 804, "loss": 0.6285, "lr": 5e-06, "epoch": 2.1199442119944214, "percentage": 70.9, "elapsed_time": "9:18:24", "remaining_time": "3:49:14"}
60
+ {"current_steps": 580, "total_steps": 804, "loss": 0.6297, "lr": 5e-06, "epoch": 2.1571362157136216, "percentage": 72.14, "elapsed_time": "9:28:00", "remaining_time": "3:39:22"}
61
+ {"current_steps": 590, "total_steps": 804, "loss": 0.6327, "lr": 5e-06, "epoch": 2.1943282194328217, "percentage": 73.38, "elapsed_time": "9:37:36", "remaining_time": "3:29:30"}
62
+ {"current_steps": 600, "total_steps": 804, "loss": 0.6313, "lr": 5e-06, "epoch": 2.2315202231520224, "percentage": 74.63, "elapsed_time": "9:47:12", "remaining_time": "3:19:39"}
63
+ {"current_steps": 610, "total_steps": 804, "loss": 0.6343, "lr": 5e-06, "epoch": 2.2687122268712225, "percentage": 75.87, "elapsed_time": "9:56:47", "remaining_time": "3:09:47"}
64
+ {"current_steps": 620, "total_steps": 804, "loss": 0.6304, "lr": 5e-06, "epoch": 2.305904230590423, "percentage": 77.11, "elapsed_time": "10:06:22", "remaining_time": "2:59:57"}
65
+ {"current_steps": 630, "total_steps": 804, "loss": 0.6266, "lr": 5e-06, "epoch": 2.3430962343096233, "percentage": 78.36, "elapsed_time": "10:15:59", "remaining_time": "2:50:07"}
66
+ {"current_steps": 640, "total_steps": 804, "loss": 0.6334, "lr": 5e-06, "epoch": 2.380288238028824, "percentage": 79.6, "elapsed_time": "10:25:35", "remaining_time": "2:40:18"}
67
+ {"current_steps": 650, "total_steps": 804, "loss": 0.6374, "lr": 5e-06, "epoch": 2.417480241748024, "percentage": 80.85, "elapsed_time": "10:35:10", "remaining_time": "2:30:29"}
68
+ {"current_steps": 660, "total_steps": 804, "loss": 0.6354, "lr": 5e-06, "epoch": 2.4546722454672247, "percentage": 82.09, "elapsed_time": "10:44:45", "remaining_time": "2:20:40"}
69
+ {"current_steps": 670, "total_steps": 804, "loss": 0.632, "lr": 5e-06, "epoch": 2.491864249186425, "percentage": 83.33, "elapsed_time": "10:54:21", "remaining_time": "2:10:52"}
70
+ {"current_steps": 680, "total_steps": 804, "loss": 0.6355, "lr": 5e-06, "epoch": 2.529056252905625, "percentage": 84.58, "elapsed_time": "11:03:57", "remaining_time": "2:01:04"}
71
+ {"current_steps": 690, "total_steps": 804, "loss": 0.635, "lr": 5e-06, "epoch": 2.5662482566248257, "percentage": 85.82, "elapsed_time": "11:13:34", "remaining_time": "1:51:17"}
72
+ {"current_steps": 700, "total_steps": 804, "loss": 0.6338, "lr": 5e-06, "epoch": 2.603440260344026, "percentage": 87.06, "elapsed_time": "11:23:10", "remaining_time": "1:41:30"}
73
+ {"current_steps": 710, "total_steps": 804, "loss": 0.6298, "lr": 5e-06, "epoch": 2.6406322640632265, "percentage": 88.31, "elapsed_time": "11:32:46", "remaining_time": "1:31:43"}
74
+ {"current_steps": 720, "total_steps": 804, "loss": 0.6388, "lr": 5e-06, "epoch": 2.6778242677824267, "percentage": 89.55, "elapsed_time": "11:42:21", "remaining_time": "1:21:56"}
75
+ {"current_steps": 730, "total_steps": 804, "loss": 0.6365, "lr": 5e-06, "epoch": 2.7150162715016273, "percentage": 90.8, "elapsed_time": "11:51:57", "remaining_time": "1:12:10"}
76
+ {"current_steps": 740, "total_steps": 804, "loss": 0.6418, "lr": 5e-06, "epoch": 2.7522082752208274, "percentage": 92.04, "elapsed_time": "12:01:32", "remaining_time": "1:02:24"}
77
+ {"current_steps": 750, "total_steps": 804, "loss": 0.636, "lr": 5e-06, "epoch": 2.789400278940028, "percentage": 93.28, "elapsed_time": "12:11:08", "remaining_time": "0:52:38"}
78
+ {"current_steps": 760, "total_steps": 804, "loss": 0.6359, "lr": 5e-06, "epoch": 2.8265922826592282, "percentage": 94.53, "elapsed_time": "12:20:43", "remaining_time": "0:42:53"}
79
+ {"current_steps": 770, "total_steps": 804, "loss": 0.6371, "lr": 5e-06, "epoch": 2.8637842863784284, "percentage": 95.77, "elapsed_time": "12:30:19", "remaining_time": "0:33:07"}
80
+ {"current_steps": 780, "total_steps": 804, "loss": 0.6404, "lr": 5e-06, "epoch": 2.900976290097629, "percentage": 97.01, "elapsed_time": "12:39:56", "remaining_time": "0:23:22"}
81
+ {"current_steps": 790, "total_steps": 804, "loss": 0.6339, "lr": 5e-06, "epoch": 2.9381682938168296, "percentage": 98.26, "elapsed_time": "12:49:32", "remaining_time": "0:13:38"}
82
+ {"current_steps": 800, "total_steps": 804, "loss": 0.6382, "lr": 5e-06, "epoch": 2.97536029753603, "percentage": 99.5, "elapsed_time": "12:59:08", "remaining_time": "0:03:53"}