sedrickkeh commited on
Commit
d80b42f
·
verified ·
1 Parent(s): 28e61cb

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 sha256:4704ab1d8070645c245d0a9958d80c20804abf23551c8d1b9e49a9f11eb91b65
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:abe1d7028a291f3a7d1350434b3b707e46da24c47259acd152b6a9e46e483892
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:83c4240239c1a4dc18869ceb623c56037af691a1fc8f0d805899d2c488068cfc
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09ca273325a046dfbcaa930ba780a31fbbb3276244f401e229f16f593404a667
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:e0fa5cc269f05824bd9fb7c917c6695c094a1880747fdf6ab3ec07373800bc29
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2da55533aaacd7271499f2e20f902a1c2d4580c5aad3111010559479b3e720e1
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:72a147c3d6a1223e87470f8f39239c8b6ab638565778f6bcde49bf9db7f2f412
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b50c5ca69b13aac117176970abff4395aa07db5ce5fc37c1e2b318e769ec4bc
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -56,3 +56,31 @@
56
  {"current_steps": 550, "total_steps": 846, "loss": 0.6913, "lr": 5e-06, "epoch": 1.9477644975652944, "percentage": 65.01, "elapsed_time": "8:57:33", "remaining_time": "4:49:18"}
57
  {"current_steps": 560, "total_steps": 846, "loss": 0.6929, "lr": 5e-06, "epoch": 1.9831783975210269, "percentage": 66.19, "elapsed_time": "9:07:12", "remaining_time": "4:39:28"}
58
  {"current_steps": 564, "total_steps": 846, "eval_loss": 0.7246915698051453, "epoch": 1.99734395750332, "percentage": 66.67, "elapsed_time": "9:16:45", "remaining_time": "4:38:22"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
56
  {"current_steps": 550, "total_steps": 846, "loss": 0.6913, "lr": 5e-06, "epoch": 1.9477644975652944, "percentage": 65.01, "elapsed_time": "8:57:33", "remaining_time": "4:49:18"}
57
  {"current_steps": 560, "total_steps": 846, "loss": 0.6929, "lr": 5e-06, "epoch": 1.9831783975210269, "percentage": 66.19, "elapsed_time": "9:07:12", "remaining_time": "4:39:28"}
58
  {"current_steps": 564, "total_steps": 846, "eval_loss": 0.7246915698051453, "epoch": 1.99734395750332, "percentage": 66.67, "elapsed_time": "9:16:45", "remaining_time": "4:38:22"}
59
+ {"current_steps": 570, "total_steps": 846, "loss": 0.7115, "lr": 5e-06, "epoch": 2.0185922974767596, "percentage": 67.38, "elapsed_time": "9:23:08", "remaining_time": "4:32:40"}
60
+ {"current_steps": 580, "total_steps": 846, "loss": 0.6411, "lr": 5e-06, "epoch": 2.0540061974324924, "percentage": 68.56, "elapsed_time": "9:32:45", "remaining_time": "4:22:40"}
61
+ {"current_steps": 590, "total_steps": 846, "loss": 0.6429, "lr": 5e-06, "epoch": 2.089420097388225, "percentage": 69.74, "elapsed_time": "9:42:26", "remaining_time": "4:12:43"}
62
+ {"current_steps": 600, "total_steps": 846, "loss": 0.6386, "lr": 5e-06, "epoch": 2.1248339973439574, "percentage": 70.92, "elapsed_time": "9:52:05", "remaining_time": "4:02:45"}
63
+ {"current_steps": 610, "total_steps": 846, "loss": 0.6393, "lr": 5e-06, "epoch": 2.16024789729969, "percentage": 72.1, "elapsed_time": "10:01:46", "remaining_time": "3:52:48"}
64
+ {"current_steps": 620, "total_steps": 846, "loss": 0.6446, "lr": 5e-06, "epoch": 2.195661797255423, "percentage": 73.29, "elapsed_time": "10:11:26", "remaining_time": "3:42:52"}
65
+ {"current_steps": 630, "total_steps": 846, "loss": 0.6435, "lr": 5e-06, "epoch": 2.231075697211155, "percentage": 74.47, "elapsed_time": "10:21:06", "remaining_time": "3:32:56"}
66
+ {"current_steps": 640, "total_steps": 846, "loss": 0.6403, "lr": 5e-06, "epoch": 2.266489597166888, "percentage": 75.65, "elapsed_time": "10:30:46", "remaining_time": "3:23:01"}
67
+ {"current_steps": 650, "total_steps": 846, "loss": 0.6449, "lr": 5e-06, "epoch": 2.3019034971226207, "percentage": 76.83, "elapsed_time": "10:40:26", "remaining_time": "3:13:07"}
68
+ {"current_steps": 660, "total_steps": 846, "loss": 0.6403, "lr": 5e-06, "epoch": 2.3373173970783534, "percentage": 78.01, "elapsed_time": "10:50:07", "remaining_time": "3:03:13"}
69
+ {"current_steps": 670, "total_steps": 846, "loss": 0.6438, "lr": 5e-06, "epoch": 2.3727312970340857, "percentage": 79.2, "elapsed_time": "10:59:49", "remaining_time": "2:53:19"}
70
+ {"current_steps": 680, "total_steps": 846, "loss": 0.6421, "lr": 5e-06, "epoch": 2.4081451969898184, "percentage": 80.38, "elapsed_time": "11:09:30", "remaining_time": "2:43:26"}
71
+ {"current_steps": 690, "total_steps": 846, "loss": 0.6412, "lr": 5e-06, "epoch": 2.443559096945551, "percentage": 81.56, "elapsed_time": "11:19:11", "remaining_time": "2:33:33"}
72
+ {"current_steps": 700, "total_steps": 846, "loss": 0.6428, "lr": 5e-06, "epoch": 2.478972996901284, "percentage": 82.74, "elapsed_time": "11:28:50", "remaining_time": "2:23:40"}
73
+ {"current_steps": 710, "total_steps": 846, "loss": 0.6438, "lr": 5e-06, "epoch": 2.514386896857016, "percentage": 83.92, "elapsed_time": "11:38:29", "remaining_time": "2:13:47"}
74
+ {"current_steps": 720, "total_steps": 846, "loss": 0.6483, "lr": 5e-06, "epoch": 2.549800796812749, "percentage": 85.11, "elapsed_time": "11:48:10", "remaining_time": "2:03:55"}
75
+ {"current_steps": 730, "total_steps": 846, "loss": 0.6389, "lr": 5e-06, "epoch": 2.5852146967684817, "percentage": 86.29, "elapsed_time": "11:57:52", "remaining_time": "1:54:04"}
76
+ {"current_steps": 740, "total_steps": 846, "loss": 0.6452, "lr": 5e-06, "epoch": 2.620628596724214, "percentage": 87.47, "elapsed_time": "12:07:31", "remaining_time": "1:44:12"}
77
+ {"current_steps": 750, "total_steps": 846, "loss": 0.6444, "lr": 5e-06, "epoch": 2.6560424966799467, "percentage": 88.65, "elapsed_time": "12:17:12", "remaining_time": "1:34:21"}
78
+ {"current_steps": 760, "total_steps": 846, "loss": 0.6466, "lr": 5e-06, "epoch": 2.6914563966356795, "percentage": 89.83, "elapsed_time": "12:26:52", "remaining_time": "1:24:30"}
79
+ {"current_steps": 770, "total_steps": 846, "loss": 0.6457, "lr": 5e-06, "epoch": 2.7268702965914122, "percentage": 91.02, "elapsed_time": "12:36:32", "remaining_time": "1:14:40"}
80
+ {"current_steps": 780, "total_steps": 846, "loss": 0.6434, "lr": 5e-06, "epoch": 2.762284196547145, "percentage": 92.2, "elapsed_time": "12:46:13", "remaining_time": "1:04:50"}
81
+ {"current_steps": 790, "total_steps": 846, "loss": 0.6416, "lr": 5e-06, "epoch": 2.7976980965028773, "percentage": 93.38, "elapsed_time": "12:55:54", "remaining_time": "0:55:00"}
82
+ {"current_steps": 800, "total_steps": 846, "loss": 0.646, "lr": 5e-06, "epoch": 2.83311199645861, "percentage": 94.56, "elapsed_time": "13:05:35", "remaining_time": "0:45:10"}
83
+ {"current_steps": 810, "total_steps": 846, "loss": 0.6423, "lr": 5e-06, "epoch": 2.8685258964143427, "percentage": 95.74, "elapsed_time": "13:15:15", "remaining_time": "0:35:20"}
84
+ {"current_steps": 820, "total_steps": 846, "loss": 0.647, "lr": 5e-06, "epoch": 2.903939796370075, "percentage": 96.93, "elapsed_time": "13:24:57", "remaining_time": "0:25:31"}
85
+ {"current_steps": 830, "total_steps": 846, "loss": 0.6494, "lr": 5e-06, "epoch": 2.939353696325808, "percentage": 98.11, "elapsed_time": "13:34:37", "remaining_time": "0:15:42"}
86
+ {"current_steps": 840, "total_steps": 846, "loss": 0.6454, "lr": 5e-06, "epoch": 2.9747675962815405, "percentage": 99.29, "elapsed_time": "13:44:16", "remaining_time": "0:05:53"}