Hugging Face's logo

Reverent
/
llama3-8b-code-extended

Safetensors
llama
Model card Files
xet
 Community
Reverent commited on
Commit
93a3b6b
·
verified ·
1 Parent(s): 42b8663

Training in progress, step 4000

Browse files
Files changed (2) hide show
  1. model.safetensors +1 -1
  2. training_log.txt +202 -502
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:aa9ef2aa7261a5f02b27064ed1c6ec352155c587bdaece18e6c6ee53b8025053
3
  size 16060556616
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b97b930bed72713201df23e0c478a65f7432d1a963a1e8f39536b8fe9c1d94f
3
  size 16060556616
training_log.txt CHANGED
@@ -1,506 +1,206 @@
1
 
2
  ==================================================
3
- Training started at: 2026-03-31 08:16:52
4
  ==================================================
5
 
6
- [2026-03-31 08:17:11] Step 1: loss: 0.4856, grad_norm: 0.3262, learning_rate: 0.0000, epoch: 0.0000
7
- [2026-03-31 08:18:26] Step 10: loss: 0.4935, grad_norm: 0.3633, learning_rate: 0.0000, epoch: 0.0001
8
- [2026-03-31 08:19:51] Step 20: loss: 0.7041, grad_norm: 0.3691, learning_rate: 0.0000, epoch: 0.0001
9
- [2026-03-31 08:21:16] Step 30: loss: 0.7839, grad_norm: 0.3457, learning_rate: 0.0000, epoch: 0.0001
10
- [2026-03-31 08:22:41] Step 40: loss: 0.7918, grad_norm: 0.3379, learning_rate: 0.0000, epoch: 0.0002
11
- [2026-03-31 08:24:07] Step 50: loss: 0.7794, grad_norm: 0.2891, learning_rate: 0.0000, epoch: 0.0003
12
- [2026-03-31 08:25:32] Step 60: loss: 0.6740, grad_norm: 0.3613, learning_rate: 0.0000, epoch: 0.0003
13
- [2026-03-31 08:26:57] Step 70: loss: 0.8364, grad_norm: 0.2754, learning_rate: 0.0000, epoch: 0.0003
14
- [2026-03-31 08:28:22] Step 80: loss: 0.8727, grad_norm: 0.2754, learning_rate: 0.0000, epoch: 0.0004
15
- [2026-03-31 08:29:47] Step 90: loss: 0.8064, grad_norm: 0.2432, learning_rate: 0.0000, epoch: 0.0004
16
- [2026-03-31 08:31:13] Step 100: loss: 0.8027, grad_norm: 0.2559, learning_rate: 0.0000, epoch: 0.0005
17
- [2026-03-31 08:32:38] Step 110: loss: 0.7824, grad_norm: 0.2734, learning_rate: 0.0000, epoch: 0.0006
18
- [2026-03-31 08:34:04] Step 120: loss: 0.6427, grad_norm: 0.2490, learning_rate: 0.0000, epoch: 0.0006
19
- [2026-03-31 08:35:29] Step 130: loss: 0.7531, grad_norm: 0.2402, learning_rate: 0.0000, epoch: 0.0006
20
- [2026-03-31 08:36:54] Step 140: loss: 0.7713, grad_norm: 0.3105, learning_rate: 0.0000, epoch: 0.0007
21
- [2026-03-31 08:38:20] Step 150: loss: 0.6974, grad_norm: 0.3379, learning_rate: 0.0000, epoch: 0.0008
22
- [2026-03-31 08:39:45] Step 160: loss: 0.8217, grad_norm: 0.2637, learning_rate: 0.0000, epoch: 0.0008
23
- [2026-03-31 08:41:10] Step 170: loss: 0.7848, grad_norm: 0.2949, learning_rate: 0.0000, epoch: 0.0008
24
- [2026-03-31 08:42:35] Step 180: loss: 0.5520, grad_norm: 0.2812, learning_rate: 0.0000, epoch: 0.0009
25
- [2026-03-31 08:44:00] Step 190: loss: 0.7036, grad_norm: 0.2461, learning_rate: 0.0000, epoch: 0.0009
26
- [2026-03-31 08:45:26] Step 200: loss: 0.6809, grad_norm: 0.2852, learning_rate: 0.0000, epoch: 0.0010
27
- [2026-03-31 08:46:49] Step 210: loss: 1.0168, grad_norm: 0.2871, learning_rate: 0.0000, epoch: 0.0010
28
- [2026-03-31 08:48:14] Step 220: loss: 0.6431, grad_norm: 0.4023, learning_rate: 0.0000, epoch: 0.0011
29
- [2026-03-31 08:49:40] Step 230: loss: 0.6609, grad_norm: 0.2451, learning_rate: 0.0000, epoch: 0.0011
30
- [2026-03-31 08:51:06] Step 240: loss: 0.7392, grad_norm: 0.3105, learning_rate: 0.0000, epoch: 0.0012
31
- [2026-03-31 08:52:30] Step 250: loss: 0.5720, grad_norm: 0.2393, learning_rate: 0.0000, epoch: 0.0013
32
- [2026-03-31 08:53:56] Step 260: loss: 0.6997, grad_norm: 0.3672, learning_rate: 0.0000, epoch: 0.0013
33
- [2026-03-31 08:55:22] Step 270: loss: 0.7542, grad_norm: 0.3965, learning_rate: 0.0000, epoch: 0.0014
34
- [2026-03-31 08:56:47] Step 280: loss: 0.6787, grad_norm: 0.2256, learning_rate: 0.0000, epoch: 0.0014
35
- [2026-03-31 08:58:11] Step 290: loss: 0.7189, grad_norm: 0.2480, learning_rate: 0.0000, epoch: 0.0014
36
- [2026-03-31 08:59:36] Step 300: loss: 0.6372, grad_norm: 0.3105, learning_rate: 0.0000, epoch: 0.0015
37
- [2026-03-31 09:01:00] Step 310: loss: 0.8779, grad_norm: 0.3359, learning_rate: 0.0000, epoch: 0.0015
38
- [2026-03-31 09:02:25] Step 320: loss: 0.7311, grad_norm: 0.2373, learning_rate: 0.0000, epoch: 0.0016
39
- [2026-03-31 09:03:50] Step 330: loss: 0.6870, grad_norm: 0.2168, learning_rate: 0.0000, epoch: 0.0016
40
- [2026-03-31 09:05:15] Step 340: loss: 0.7427, grad_norm: 0.3223, learning_rate: 0.0000, epoch: 0.0017
41
- [2026-03-31 09:06:40] Step 350: loss: 0.6358, grad_norm: 0.2598, learning_rate: 0.0000, epoch: 0.0018
42
- [2026-03-31 09:08:05] Step 360: loss: 0.6055, grad_norm: 0.5273, learning_rate: 0.0000, epoch: 0.0018
43
- [2026-03-31 09:09:30] Step 370: loss: 0.7457, grad_norm: 0.2910, learning_rate: 0.0000, epoch: 0.0019
44
- [2026-03-31 09:10:56] Step 380: loss: 0.6991, grad_norm: 0.2656, learning_rate: 0.0000, epoch: 0.0019
45
- [2026-03-31 09:12:20] Step 390: loss: 0.6431, grad_norm: 0.3164, learning_rate: 0.0000, epoch: 0.0019
46
- [2026-03-31 09:13:46] Step 400: loss: 0.7399, grad_norm: 0.2295, learning_rate: 0.0000, epoch: 0.0020
47
- [2026-03-31 09:15:10] Step 410: loss: 0.5857, grad_norm: 0.2832, learning_rate: 0.0000, epoch: 0.0021
48
- [2026-03-31 09:16:35] Step 420: loss: 0.5672, grad_norm: 0.2969, learning_rate: 0.0000, epoch: 0.0021
49
- [2026-03-31 09:18:00] Step 430: loss: 0.6545, grad_norm: 0.2500, learning_rate: 0.0000, epoch: 0.0022
50
- [2026-03-31 09:19:25] Step 440: loss: 0.7182, grad_norm: 0.3711, learning_rate: 0.0000, epoch: 0.0022
51
- [2026-03-31 09:20:50] Step 450: loss: 0.8341, grad_norm: 0.4199, learning_rate: 0.0000, epoch: 0.0022
52
- [2026-03-31 09:22:16] Step 460: loss: 0.6405, grad_norm: 0.2520, learning_rate: 0.0000, epoch: 0.0023
53
- [2026-03-31 09:23:40] Step 470: loss: 0.7988, grad_norm: 0.2490, learning_rate: 0.0000, epoch: 0.0024
54
- [2026-03-31 09:25:05] Step 480: loss: 0.6173, grad_norm: 0.2617, learning_rate: 0.0000, epoch: 0.0024
55
- [2026-03-31 09:26:30] Step 490: loss: 0.6820, grad_norm: 0.3027, learning_rate: 0.0000, epoch: 0.0024
56
- [2026-03-31 09:27:55] Step 500: loss: 0.8783, grad_norm: 0.3281, learning_rate: 0.0000, epoch: 0.0025
57
- [2026-03-31 09:29:20] Step 510: loss: 0.6884, grad_norm: 0.2080, learning_rate: 0.0000, epoch: 0.0026
58
- [2026-03-31 09:30:45] Step 520: loss: 0.6329, grad_norm: 0.2773, learning_rate: 0.0000, epoch: 0.0026
59
- [2026-03-31 09:32:10] Step 530: loss: 0.6798, grad_norm: 0.2461, learning_rate: 0.0000, epoch: 0.0027
60
- [2026-03-31 09:33:35] Step 540: loss: 0.6928, grad_norm: 0.2559, learning_rate: 0.0000, epoch: 0.0027
61
- [2026-03-31 09:35:00] Step 550: loss: 0.5219, grad_norm: 0.2188, learning_rate: 0.0000, epoch: 0.0027
62
- [2026-03-31 09:36:25] Step 560: loss: 0.7163, grad_norm: 0.2754, learning_rate: 0.0000, epoch: 0.0028
63
- [2026-03-31 09:37:51] Step 570: loss: 0.7411, grad_norm: 0.2734, learning_rate: 0.0000, epoch: 0.0029
64
- [2026-03-31 09:39:16] Step 580: loss: 0.6572, grad_norm: 0.2559, learning_rate: 0.0000, epoch: 0.0029
65
- [2026-03-31 09:40:41] Step 590: loss: 0.6766, grad_norm: 0.2812, learning_rate: 0.0000, epoch: 0.0029
66
- [2026-03-31 09:42:06] Step 600: loss: 0.6357, grad_norm: 0.2793, learning_rate: 0.0000, epoch: 0.0030
67
- [2026-03-31 09:43:31] Step 610: loss: 0.6393, grad_norm: 0.2520, learning_rate: 0.0000, epoch: 0.0031
68
- [2026-03-31 09:44:56] Step 620: loss: 1.1964, grad_norm: 1.6875, learning_rate: 0.0000, epoch: 0.0031
69
- [2026-03-31 09:46:21] Step 630: loss: 0.5934, grad_norm: 0.2734, learning_rate: 0.0000, epoch: 0.0032
70
- [2026-03-31 09:47:47] Step 640: loss: 0.5975, grad_norm: 0.2637, learning_rate: 0.0000, epoch: 0.0032
71
- [2026-03-31 09:49:13] Step 650: loss: 0.6148, grad_norm: 0.2070, learning_rate: 0.0000, epoch: 0.0032
72
- [2026-03-31 09:50:38] Step 660: loss: 0.5560, grad_norm: 0.2578, learning_rate: 0.0000, epoch: 0.0033
73
- [2026-03-31 09:52:03] Step 670: loss: 0.7115, grad_norm: 0.2373, learning_rate: 0.0000, epoch: 0.0034
74
- [2026-03-31 09:53:27] Step 680: loss: 0.5798, grad_norm: 0.3457, learning_rate: 0.0000, epoch: 0.0034
75
- [2026-03-31 09:54:53] Step 690: loss: 0.6946, grad_norm: 0.2637, learning_rate: 0.0000, epoch: 0.0034
76
- [2026-03-31 09:56:18] Step 700: loss: 0.5445, grad_norm: 0.2373, learning_rate: 0.0000, epoch: 0.0035
77
- [2026-03-31 09:57:43] Step 710: loss: 0.4948, grad_norm: 0.1396, learning_rate: 0.0000, epoch: 0.0036
78
- [2026-03-31 09:59:08] Step 720: loss: 0.4899, grad_norm: 0.1738, learning_rate: 0.0000, epoch: 0.0036
79
- [2026-03-31 10:00:33] Step 730: loss: 0.6395, grad_norm: 0.2539, learning_rate: 0.0000, epoch: 0.0037
80
- [2026-03-31 10:01:58] Step 740: loss: 0.6532, grad_norm: 0.2832, learning_rate: 0.0000, epoch: 0.0037
81
- [2026-03-31 10:03:23] Step 750: loss: 0.6393, grad_norm: 0.2871, learning_rate: 0.0000, epoch: 0.0037
82
- [2026-03-31 10:04:49] Step 760: loss: 0.6307, grad_norm: 0.2393, learning_rate: 0.0000, epoch: 0.0038
83
- [2026-03-31 10:06:13] Step 770: loss: 0.8382, grad_norm: 0.4180, learning_rate: 0.0000, epoch: 0.0039
84
- [2026-03-31 10:07:37] Step 780: loss: 0.5211, grad_norm: 0.2852, learning_rate: 0.0000, epoch: 0.0039
85
- [2026-03-31 10:09:03] Step 790: loss: 0.6344, grad_norm: 0.4316, learning_rate: 0.0000, epoch: 0.0040
86
- [2026-03-31 10:10:27] Step 800: loss: 0.6520, grad_norm: 0.3066, learning_rate: 0.0000, epoch: 0.0040
87
- [2026-03-31 10:11:53] Step 810: loss: 0.6001, grad_norm: 0.1895, learning_rate: 0.0000, epoch: 0.0040
88
- [2026-03-31 10:13:18] Step 820: loss: 0.6037, grad_norm: 0.2451, learning_rate: 0.0000, epoch: 0.0041
89
- [2026-03-31 10:14:42] Step 830: loss: 0.7808, grad_norm: 0.3516, learning_rate: 0.0000, epoch: 0.0042
90
- [2026-03-31 10:16:07] Step 840: loss: 0.7404, grad_norm: 0.4434, learning_rate: 0.0000, epoch: 0.0042
91
- [2026-03-31 10:17:32] Step 850: loss: 0.6896, grad_norm: 0.2656, learning_rate: 0.0000, epoch: 0.0043
92
- [2026-03-31 10:18:58] Step 860: loss: 0.6981, grad_norm: 0.2695, learning_rate: 0.0000, epoch: 0.0043
93
- [2026-03-31 10:20:23] Step 870: loss: 0.6826, grad_norm: 0.3457, learning_rate: 0.0000, epoch: 0.0043
94
- [2026-03-31 10:21:49] Step 880: loss: 0.6869, grad_norm: 0.2227, learning_rate: 0.0000, epoch: 0.0044
95
- [2026-03-31 10:23:14] Step 890: loss: 0.6261, grad_norm: 0.2119, learning_rate: 0.0000, epoch: 0.0044
96
- [2026-03-31 10:24:38] Step 900: loss: 0.5443, grad_norm: 0.2598, learning_rate: 0.0000, epoch: 0.0045
97
- [2026-03-31 10:26:03] Step 910: loss: 0.5575, grad_norm: 1.7969, learning_rate: 0.0000, epoch: 0.0046
98
- [2026-03-31 10:27:28] Step 920: loss: 0.5836, grad_norm: 0.2871, learning_rate: 0.0000, epoch: 0.0046
99
- [2026-03-31 10:28:54] Step 930: loss: 0.6810, grad_norm: 0.2422, learning_rate: 0.0000, epoch: 0.0046
100
- [2026-03-31 10:30:18] Step 940: loss: 0.5828, grad_norm: 1.3047, learning_rate: 0.0000, epoch: 0.0047
101
- [2026-03-31 10:31:43] Step 950: loss: 0.7119, grad_norm: 0.2227, learning_rate: 0.0000, epoch: 0.0047
102
- [2026-03-31 10:33:08] Step 960: loss: 0.6437, grad_norm: 0.2168, learning_rate: 0.0000, epoch: 0.0048
103
- [2026-03-31 10:34:34] Step 970: loss: 0.6974, grad_norm: 0.3047, learning_rate: 0.0000, epoch: 0.0049
104
- [2026-03-31 10:35:59] Step 980: loss: 0.6215, grad_norm: 0.2158, learning_rate: 0.0000, epoch: 0.0049
105
- [2026-03-31 10:37:24] Step 990: loss: 0.6327, grad_norm: 0.4902, learning_rate: 0.0000, epoch: 0.0050
106
- [2026-03-31 10:38:49] Step 1000: loss: 0.7849, grad_norm: 0.2441, learning_rate: 0.0000, epoch: 0.0050
107
- [2026-03-31 10:40:14] Step 1010: loss: 0.6728, grad_norm: 0.1797, learning_rate: 0.0000, epoch: 0.0050
108
- [2026-03-31 10:41:40] Step 1020: loss: 0.6218, grad_norm: 0.2656, learning_rate: 0.0000, epoch: 0.0051
109
- [2026-03-31 10:43:05] Step 1030: loss: 0.7025, grad_norm: 0.2070, learning_rate: 0.0000, epoch: 0.0052
110
- [2026-03-31 10:44:31] Step 1040: loss: 0.6721, grad_norm: 0.2734, learning_rate: 0.0000, epoch: 0.0052
111
- [2026-03-31 10:45:56] Step 1050: loss: 0.7102, grad_norm: 0.2041, learning_rate: 0.0000, epoch: 0.0053
112
- [2026-03-31 10:47:21] Step 1060: loss: 0.6343, grad_norm: 0.2754, learning_rate: 0.0000, epoch: 0.0053
113
- [2026-03-31 10:48:46] Step 1070: loss: 0.6268, grad_norm: 0.1934, learning_rate: 0.0000, epoch: 0.0053
114
- [2026-03-31 10:50:11] Step 1080: loss: 0.6331, grad_norm: 0.3438, learning_rate: 0.0000, epoch: 0.0054
115
- [2026-03-31 10:51:37] Step 1090: loss: 0.6211, grad_norm: 0.2051, learning_rate: 0.0000, epoch: 0.0054
116
- [2026-03-31 10:53:02] Step 1100: loss: 0.6418, grad_norm: 0.2598, learning_rate: 0.0000, epoch: 0.0055
117
- [2026-03-31 10:54:27] Step 1110: loss: 0.5138, grad_norm: 0.3418, learning_rate: 0.0000, epoch: 0.0056
118
- [2026-03-31 10:55:53] Step 1120: loss: 0.5801, grad_norm: 0.2100, learning_rate: 0.0000, epoch: 0.0056
119
- [2026-03-31 10:57:18] Step 1130: loss: 0.8137, grad_norm: 0.4297, learning_rate: 0.0000, epoch: 0.0056
120
- [2026-03-31 10:58:43] Step 1140: loss: 0.5223, grad_norm: 0.1602, learning_rate: 0.0000, epoch: 0.0057
121
- [2026-03-31 11:00:06] Step 1150: loss: 0.6581, grad_norm: 0.3594, learning_rate: 0.0000, epoch: 0.0057
122
- [2026-03-31 11:01:32] Step 1160: loss: 0.6478, grad_norm: 0.3633, learning_rate: 0.0000, epoch: 0.0058
123
- [2026-03-31 11:02:58] Step 1170: loss: 0.7135, grad_norm: 0.2383, learning_rate: 0.0000, epoch: 0.0059
124
- [2026-03-31 11:04:22] Step 1180: loss: 0.5748, grad_norm: 0.3164, learning_rate: 0.0000, epoch: 0.0059
125
- [2026-03-31 11:05:47] Step 1190: loss: 0.8228, grad_norm: 0.3066, learning_rate: 0.0000, epoch: 0.0060
126
- [2026-03-31 11:07:13] Step 1200: loss: 0.6403, grad_norm: 0.3496, learning_rate: 0.0000, epoch: 0.0060
127
- [2026-03-31 11:08:37] Step 1210: loss: 0.7723, grad_norm: 0.3281, learning_rate: 0.0000, epoch: 0.0060
128
- [2026-03-31 11:10:03] Step 1220: loss: 0.5371, grad_norm: 0.2832, learning_rate: 0.0000, epoch: 0.0061
129
- [2026-03-31 11:11:28] Step 1230: loss: 0.6469, grad_norm: 0.3438, learning_rate: 0.0000, epoch: 0.0062
130
- [2026-03-31 11:12:53] Step 1240: loss: 0.7745, grad_norm: 0.3789, learning_rate: 0.0000, epoch: 0.0062
131
- [2026-03-31 11:14:18] Step 1250: loss: 0.7750, grad_norm: 0.2256, learning_rate: 0.0000, epoch: 0.0063
132
- [2026-03-31 11:15:43] Step 1260: loss: 0.6599, grad_norm: 0.2432, learning_rate: 0.0000, epoch: 0.0063
133
- [2026-03-31 11:17:09] Step 1270: loss: 0.7615, grad_norm: 0.2412, learning_rate: 0.0000, epoch: 0.0063
134
- [2026-03-31 11:18:35] Step 1280: loss: 0.6346, grad_norm: 0.3359, learning_rate: 0.0000, epoch: 0.0064
135
- [2026-03-31 11:20:01] Step 1290: loss: 0.6891, grad_norm: 0.2080, learning_rate: 0.0000, epoch: 0.0065
136
- [2026-03-31 11:21:25] Step 1300: loss: 0.5364, grad_norm: 0.1924, learning_rate: 0.0000, epoch: 0.0065
137
- [2026-03-31 11:22:50] Step 1310: loss: 0.6557, grad_norm: 0.2227, learning_rate: 0.0000, epoch: 0.0066
138
- [2026-03-31 11:24:15] Step 1320: loss: 0.6950, grad_norm: 0.2188, learning_rate: 0.0000, epoch: 0.0066
139
- [2026-03-31 11:25:40] Step 1330: loss: 0.5492, grad_norm: 0.2109, learning_rate: 0.0000, epoch: 0.0066
140
- [2026-03-31 11:27:07] Step 1340: loss: 0.6115, grad_norm: 0.2334, learning_rate: 0.0000, epoch: 0.0067
141
- [2026-03-31 11:28:32] Step 1350: loss: 0.6028, grad_norm: 0.6836, learning_rate: 0.0000, epoch: 0.0067
142
- [2026-03-31 11:29:57] Step 1360: loss: 0.6276, grad_norm: 0.2695, learning_rate: 0.0000, epoch: 0.0068
143
- [2026-03-31 11:31:23] Step 1370: loss: 0.7336, grad_norm: 1.3047, learning_rate: 0.0000, epoch: 0.0069
144
- [2026-03-31 11:32:47] Step 1380: loss: 1.3252, grad_norm: 0.8008, learning_rate: 0.0000, epoch: 0.0069
145
- [2026-03-31 11:34:13] Step 1390: loss: 0.9259, grad_norm: 0.4219, learning_rate: 0.0000, epoch: 0.0069
146
- [2026-03-31 11:35:39] Step 1400: loss: 1.0405, grad_norm: 10.6250, learning_rate: 0.0000, epoch: 0.0070
147
- [2026-03-31 11:37:03] Step 1410: loss: 1.0480, grad_norm: 0.2344, learning_rate: 0.0000, epoch: 0.0070
148
- [2026-03-31 11:38:27] Step 1420: loss: 0.9915, grad_norm: 1.0312, learning_rate: 0.0000, epoch: 0.0071
149
- [2026-03-31 11:39:51] Step 1430: loss: 1.6014, grad_norm: 5.3750, learning_rate: 0.0000, epoch: 0.0072
150
- [2026-03-31 11:41:16] Step 1440: loss: 1.3907, grad_norm: 0.3320, learning_rate: 0.0000, epoch: 0.0072
151
- [2026-03-31 11:42:41] Step 1450: loss: 0.9233, grad_norm: 14.9375, learning_rate: 0.0000, epoch: 0.0073
152
- [2026-03-31 11:44:06] Step 1460: loss: 0.9192, grad_norm: 0.4785, learning_rate: 0.0000, epoch: 0.0073
153
- [2026-03-31 11:45:30] Step 1470: loss: 1.1676, grad_norm: 1.3359, learning_rate: 0.0000, epoch: 0.0073
154
- [2026-03-31 11:46:54] Step 1480: loss: 1.2556, grad_norm: 0.5078, learning_rate: 0.0000, epoch: 0.0074
155
- [2026-03-31 11:48:17] Step 1490: loss: 1.2209, grad_norm: 0.5430, learning_rate: 0.0000, epoch: 0.0075
156
- [2026-03-31 11:49:40] Step 1500: loss: 1.1793, grad_norm: 0.4043, learning_rate: 0.0000, epoch: 0.0075
157
- [2026-03-31 11:51:04] Step 1510: loss: 1.2793, grad_norm: 0.4863, learning_rate: 0.0000, epoch: 0.0076
158
- [2026-03-31 11:52:27] Step 1520: loss: 1.1655, grad_norm: 0.3652, learning_rate: 0.0000, epoch: 0.0076
159
- [2026-03-31 11:53:51] Step 1530: loss: 1.2192, grad_norm: 0.4668, learning_rate: 0.0000, epoch: 0.0076
160
- [2026-03-31 11:55:15] Step 1540: loss: 1.1440, grad_norm: 0.2773, learning_rate: 0.0000, epoch: 0.0077
161
- [2026-03-31 11:56:38] Step 1550: loss: 1.1770, grad_norm: 0.3672, learning_rate: 0.0000, epoch: 0.0077
162
- [2026-03-31 11:58:02] Step 1560: loss: 1.3346, grad_norm: 13.4375, learning_rate: 0.0000, epoch: 0.0078
163
- [2026-03-31 11:59:26] Step 1570: loss: 1.1318, grad_norm: 0.2852, learning_rate: 0.0000, epoch: 0.0078
164
- [2026-03-31 12:00:49] Step 1580: loss: 1.1090, grad_norm: 0.3281, learning_rate: 0.0000, epoch: 0.0079
165
- [2026-03-31 12:02:13] Step 1590: loss: 1.2041, grad_norm: 0.3828, learning_rate: 0.0000, epoch: 0.0080
166
- [2026-03-31 12:03:37] Step 1600: loss: 1.3424, grad_norm: 0.3730, learning_rate: 0.0000, epoch: 0.0080
167
- [2026-03-31 12:05:00] Step 1610: loss: 1.2635, grad_norm: 1.0234, learning_rate: 0.0000, epoch: 0.0080
168
- [2026-03-31 12:06:24] Step 1620: loss: 1.3925, grad_norm: 1.1875, learning_rate: 0.0000, epoch: 0.0081
169
- [2026-03-31 12:07:48] Step 1630: loss: 1.5539, grad_norm: 0.4062, learning_rate: 0.0000, epoch: 0.0081
170
- [2026-03-31 12:09:12] Step 1640: loss: 1.7835, grad_norm: 0.4941, learning_rate: 0.0000, epoch: 0.0082
171
- [2026-03-31 12:10:36] Step 1650: loss: 1.3603, grad_norm: 4.0000, learning_rate: 0.0000, epoch: 0.0083
172
- [2026-03-31 12:12:00] Step 1660: loss: 1.6906, grad_norm: 0.4629, learning_rate: 0.0000, epoch: 0.0083
173
- [2026-03-31 12:13:25] Step 1670: loss: 1.4568, grad_norm: 0.3789, learning_rate: 0.0000, epoch: 0.0083
174
- [2026-03-31 12:14:49] Step 1680: loss: 1.3137, grad_norm: 0.4277, learning_rate: 0.0000, epoch: 0.0084
175
- [2026-03-31 12:16:13] Step 1690: loss: 1.4152, grad_norm: 0.4824, learning_rate: 0.0000, epoch: 0.0084
176
- [2026-03-31 12:17:37] Step 1700: loss: 1.6497, grad_norm: 0.4863, learning_rate: 0.0000, epoch: 0.0085
177
- [2026-03-31 12:19:01] Step 1710: loss: 1.5483, grad_norm: 2.0781, learning_rate: 0.0000, epoch: 0.0086
178
- [2026-03-31 12:20:25] Step 1720: loss: 1.7335, grad_norm: 9.3750, learning_rate: 0.0000, epoch: 0.0086
179
- [2026-03-31 12:21:50] Step 1730: loss: 1.6119, grad_norm: 1.1641, learning_rate: 0.0000, epoch: 0.0086
180
- [2026-03-31 12:23:13] Step 1740: loss: 2.9970, grad_norm: 0.7227, learning_rate: 0.0000, epoch: 0.0087
181
- [2026-03-31 12:24:37] Step 1750: loss: 1.6688, grad_norm: 0.6797, learning_rate: 0.0000, epoch: 0.0088
182
- [2026-03-31 12:26:00] Step 1760: loss: 2.3359, grad_norm: 0.4023, learning_rate: 0.0000, epoch: 0.0088
183
- [2026-03-31 12:27:24] Step 1770: loss: 1.4465, grad_norm: 0.4082, learning_rate: 0.0000, epoch: 0.0089
184
- [2026-03-31 12:28:49] Step 1780: loss: 1.3555, grad_norm: 0.5938, learning_rate: 0.0000, epoch: 0.0089
185
- [2026-03-31 12:30:13] Step 1790: loss: 1.4815, grad_norm: 0.5430, learning_rate: 0.0000, epoch: 0.0089
186
- [2026-03-31 12:31:37] Step 1800: loss: 1.5430, grad_norm: 0.3320, learning_rate: 0.0000, epoch: 0.0090
187
- [2026-03-31 12:33:02] Step 1810: loss: 1.3603, grad_norm: 1.7188, learning_rate: 0.0000, epoch: 0.0091
188
- [2026-03-31 12:34:26] Step 1820: loss: 1.2443, grad_norm: 0.2793, learning_rate: 0.0000, epoch: 0.0091
189
- [2026-03-31 12:35:50] Step 1830: loss: 1.1791, grad_norm: 0.3652, learning_rate: 0.0000, epoch: 0.0092
190
- [2026-03-31 12:37:13] Step 1840: loss: 1.4843, grad_norm: 1.3359, learning_rate: 0.0000, epoch: 0.0092
191
- [2026-03-31 12:38:37] Step 1850: loss: 1.2835, grad_norm: 4.5312, learning_rate: 0.0000, epoch: 0.0092
192
- [2026-03-31 12:40:01] Step 1860: loss: 1.5371, grad_norm: 0.2949, learning_rate: 0.0000, epoch: 0.0093
193
- [2026-03-31 12:41:25] Step 1870: loss: 1.3208, grad_norm: 0.2695, learning_rate: 0.0000, epoch: 0.0094
194
- [2026-03-31 12:42:49] Step 1880: loss: 1.2831, grad_norm: 0.3398, learning_rate: 0.0000, epoch: 0.0094
195
- [2026-03-31 12:44:13] Step 1890: loss: 1.2004, grad_norm: 0.3301, learning_rate: 0.0000, epoch: 0.0095
196
- [2026-03-31 12:45:37] Step 1900: loss: 1.0956, grad_norm: 0.3496, learning_rate: 0.0000, epoch: 0.0095
197
- [2026-03-31 12:47:01] Step 1910: loss: 1.4427, grad_norm: 1.7422, learning_rate: 0.0000, epoch: 0.0095
198
- [2026-03-31 12:48:25] Step 1920: loss: 1.1851, grad_norm: 0.6797, learning_rate: 0.0000, epoch: 0.0096
199
- [2026-03-31 12:49:49] Step 1930: loss: 1.0941, grad_norm: 0.2969, learning_rate: 0.0000, epoch: 0.0097
200
- [2026-03-31 12:51:13] Step 1940: loss: 1.6182, grad_norm: 0.5195, learning_rate: 0.0000, epoch: 0.0097
201
- [2026-03-31 12:52:37] Step 1950: loss: 1.2811, grad_norm: 0.6562, learning_rate: 0.0000, epoch: 0.0097
202
- [2026-03-31 12:54:01] Step 1960: loss: 1.3100, grad_norm: 0.2871, learning_rate: 0.0000, epoch: 0.0098
203
- [2026-03-31 12:55:25] Step 1970: loss: 1.1823, grad_norm: 0.6680, learning_rate: 0.0000, epoch: 0.0098
204
- [2026-03-31 12:56:50] Step 1980: loss: 1.1825, grad_norm: 0.4395, learning_rate: 0.0000, epoch: 0.0099
205
- [2026-03-31 12:58:15] Step 1990: loss: 1.0992, grad_norm: 0.3828, learning_rate: 0.0000, epoch: 0.0100
206
- [2026-03-31 12:59:39] Step 2000: loss: 1.1698, grad_norm: 0.4863, learning_rate: 0.0000, epoch: 0.0100
207
- [2026-03-31 13:01:03] Step 2010: loss: 1.2657, grad_norm: 0.4238, learning_rate: 0.0000, epoch: 0.0100
208
- [2026-03-31 13:02:28] Step 2020: loss: 1.0027, grad_norm: 0.5195, learning_rate: 0.0000, epoch: 0.0101
209
- [2026-03-31 13:03:51] Step 2030: loss: 1.1940, grad_norm: 0.3379, learning_rate: 0.0000, epoch: 0.0101
210
- [2026-03-31 13:05:15] Step 2040: loss: 1.4490, grad_norm: 0.3066, learning_rate: 0.0000, epoch: 0.0102
211
- [2026-03-31 13:06:40] Step 2050: loss: 1.1737, grad_norm: 0.4531, learning_rate: 0.0000, epoch: 0.0103
212
- [2026-03-31 13:08:05] Step 2060: loss: 1.1079, grad_norm: 0.5000, learning_rate: 0.0000, epoch: 0.0103
213
- [2026-03-31 13:09:29] Step 2070: loss: 1.2216, grad_norm: 0.3008, learning_rate: 0.0000, epoch: 0.0103
214
- [2026-03-31 13:10:53] Step 2080: loss: 1.1185, grad_norm: 0.2559, learning_rate: 0.0000, epoch: 0.0104
215
- [2026-03-31 13:12:17] Step 2090: loss: 1.3267, grad_norm: 0.5820, learning_rate: 0.0000, epoch: 0.0104
216
- [2026-03-31 13:13:42] Step 2100: loss: 1.5635, grad_norm: 0.7656, learning_rate: 0.0000, epoch: 0.0105
217
- [2026-03-31 13:15:05] Step 2110: loss: 1.0361, grad_norm: 0.2969, learning_rate: 0.0000, epoch: 0.0106
218
- [2026-03-31 13:16:29] Step 2120: loss: 1.0532, grad_norm: 1.3906, learning_rate: 0.0000, epoch: 0.0106
219
- [2026-03-31 13:17:54] Step 2130: loss: 1.0644, grad_norm: 0.2324, learning_rate: 0.0000, epoch: 0.0106
220
- [2026-03-31 13:19:18] Step 2140: loss: 1.0322, grad_norm: 0.2520, learning_rate: 0.0000, epoch: 0.0107
221
- [2026-03-31 13:20:42] Step 2150: loss: 1.4070, grad_norm: 0.4805, learning_rate: 0.0000, epoch: 0.0107
222
- [2026-03-31 13:22:07] Step 2160: loss: 1.3160, grad_norm: 1.1016, learning_rate: 0.0000, epoch: 0.0108
223
- [2026-03-31 13:23:31] Step 2170: loss: 1.1469, grad_norm: 0.3711, learning_rate: 0.0000, epoch: 0.0109
224
- [2026-03-31 13:24:55] Step 2180: loss: 1.0909, grad_norm: 0.2793, learning_rate: 0.0000, epoch: 0.0109
225
- [2026-03-31 13:26:20] Step 2190: loss: 0.9834, grad_norm: 0.2969, learning_rate: 0.0000, epoch: 0.0109
226
- [2026-03-31 13:27:44] Step 2200: loss: 1.1768, grad_norm: 0.3359, learning_rate: 0.0000, epoch: 0.0110
227
- [2026-03-31 13:29:08] Step 2210: loss: 1.0558, grad_norm: 0.4531, learning_rate: 0.0000, epoch: 0.0111
228
- [2026-03-31 13:30:33] Step 2220: loss: 0.9522, grad_norm: 0.2500, learning_rate: 0.0000, epoch: 0.0111
229
- [2026-03-31 13:31:57] Step 2230: loss: 0.8136, grad_norm: 0.3008, learning_rate: 0.0000, epoch: 0.0112
230
- [2026-03-31 13:33:21] Step 2240: loss: 1.0795, grad_norm: 0.4082, learning_rate: 0.0000, epoch: 0.0112
231
- [2026-03-31 13:34:45] Step 2250: loss: 0.9262, grad_norm: 1.2500, learning_rate: 0.0000, epoch: 0.0112
232
- [2026-03-31 13:36:10] Step 2260: loss: 0.9367, grad_norm: 0.2480, learning_rate: 0.0000, epoch: 0.0113
233
- [2026-03-31 13:37:34] Step 2270: loss: 0.9101, grad_norm: 0.2178, learning_rate: 0.0000, epoch: 0.0114
234
- [2026-03-31 13:38:58] Step 2280: loss: 0.9367, grad_norm: 0.2305, learning_rate: 0.0000, epoch: 0.0114
235
- [2026-03-31 13:40:22] Step 2290: loss: 0.9764, grad_norm: 0.2383, learning_rate: 0.0000, epoch: 0.0115
236
- [2026-03-31 13:41:46] Step 2300: loss: 0.9531, grad_norm: 0.2256, learning_rate: 0.0000, epoch: 0.0115
237
- [2026-03-31 13:43:11] Step 2310: loss: 0.9336, grad_norm: 0.2266, learning_rate: 0.0000, epoch: 0.0115
238
- [2026-03-31 13:44:35] Step 2320: loss: 1.0024, grad_norm: 0.2451, learning_rate: 0.0000, epoch: 0.0116
239
- [2026-03-31 13:45:59] Step 2330: loss: 1.1485, grad_norm: 3.6719, learning_rate: 0.0000, epoch: 0.0117
240
- [2026-03-31 13:47:23] Step 2340: loss: 0.9640, grad_norm: 0.3320, learning_rate: 0.0000, epoch: 0.0117
241
- [2026-03-31 13:48:47] Step 2350: loss: 1.0453, grad_norm: 0.7852, learning_rate: 0.0000, epoch: 0.0118
242
- [2026-03-31 13:50:11] Step 2360: loss: 0.9072, grad_norm: 0.2910, learning_rate: 0.0000, epoch: 0.0118
243
- [2026-03-31 13:51:36] Step 2370: loss: 0.8404, grad_norm: 0.1699, learning_rate: 0.0000, epoch: 0.0118
244
- [2026-03-31 13:53:00] Step 2380: loss: 0.9135, grad_norm: 0.2695, learning_rate: 0.0000, epoch: 0.0119
245
- [2026-03-31 13:54:24] Step 2390: loss: 0.9864, grad_norm: 0.2578, learning_rate: 0.0000, epoch: 0.0120
246
- [2026-03-31 13:55:48] Step 2400: loss: 0.8803, grad_norm: 0.2578, learning_rate: 0.0000, epoch: 0.0120
247
- [2026-03-31 13:57:12] Step 2410: loss: 0.8425, grad_norm: 0.2734, learning_rate: 0.0000, epoch: 0.0120
248
- [2026-03-31 13:58:37] Step 2420: loss: 0.9706, grad_norm: 0.3008, learning_rate: 0.0000, epoch: 0.0121
249
- [2026-03-31 14:00:01] Step 2430: loss: 0.8751, grad_norm: 0.2461, learning_rate: 0.0000, epoch: 0.0121
250
- [2026-03-31 14:01:26] Step 2440: loss: 0.9805, grad_norm: 0.9375, learning_rate: 0.0000, epoch: 0.0122
251
- [2026-03-31 14:02:50] Step 2450: loss: 0.8812, grad_norm: 0.3164, learning_rate: 0.0000, epoch: 0.0123
252
- [2026-03-31 14:04:14] Step 2460: loss: 0.8169, grad_norm: 0.2637, learning_rate: 0.0000, epoch: 0.0123
253
- [2026-03-31 14:05:38] Step 2470: loss: 0.9798, grad_norm: 0.2266, learning_rate: 0.0000, epoch: 0.0123
254
- [2026-03-31 14:07:03] Step 2480: loss: 0.8950, grad_norm: 0.2676, learning_rate: 0.0000, epoch: 0.0124
255
- [2026-03-31 14:08:27] Step 2490: loss: 0.8163, grad_norm: 0.2432, learning_rate: 0.0000, epoch: 0.0124
256
- [2026-03-31 14:09:51] Step 2500: loss: 0.7961, grad_norm: 0.1855, learning_rate: 0.0000, epoch: 0.0125
257
- [2026-03-31 14:11:16] Step 2510: loss: 1.0739, grad_norm: 0.3184, learning_rate: 0.0000, epoch: 0.0126
258
- [2026-03-31 14:12:40] Step 2520: loss: 0.8903, grad_norm: 0.2139, learning_rate: 0.0000, epoch: 0.0126
259
- [2026-03-31 14:14:05] Step 2530: loss: 0.9089, grad_norm: 0.2148, learning_rate: 0.0000, epoch: 0.0126
260
- [2026-03-31 14:15:28] Step 2540: loss: 0.5330, grad_norm: 0.2852, learning_rate: 0.0000, epoch: 0.0127
261
- [2026-03-31 14:16:52] Step 2550: loss: 1.0004, grad_norm: 0.2324, learning_rate: 0.0000, epoch: 0.0127
262
- [2026-03-31 14:18:16] Step 2560: loss: 0.9046, grad_norm: 0.2734, learning_rate: 0.0000, epoch: 0.0128
263
- [2026-03-31 14:19:40] Step 2570: loss: 0.9581, grad_norm: 0.5195, learning_rate: 0.0000, epoch: 0.0129
264
- [2026-03-31 14:21:05] Step 2580: loss: 0.9202, grad_norm: 0.2598, learning_rate: 0.0000, epoch: 0.0129
265
- [2026-03-31 14:22:29] Step 2590: loss: 0.9269, grad_norm: 0.3203, learning_rate: 0.0000, epoch: 0.0129
266
- [2026-03-31 14:23:53] Step 2600: loss: 0.9212, grad_norm: 0.2598, learning_rate: 0.0000, epoch: 0.0130
267
- [2026-03-31 14:25:17] Step 2610: loss: 0.8384, grad_norm: 0.3203, learning_rate: 0.0000, epoch: 0.0131
268
- [2026-03-31 14:26:41] Step 2620: loss: 0.7916, grad_norm: 0.1846, learning_rate: 0.0000, epoch: 0.0131
269
- [2026-03-31 14:28:06] Step 2630: loss: 0.8990, grad_norm: 0.2275, learning_rate: 0.0000, epoch: 0.0132
270
- [2026-03-31 14:29:30] Step 2640: loss: 0.8468, grad_norm: 0.2334, learning_rate: 0.0000, epoch: 0.0132
271
- [2026-03-31 14:30:54] Step 2650: loss: 0.9808, grad_norm: 0.2402, learning_rate: 0.0000, epoch: 0.0132
272
- [2026-03-31 14:32:18] Step 2660: loss: 0.8761, grad_norm: 0.2012, learning_rate: 0.0000, epoch: 0.0133
273
- [2026-03-31 14:33:42] Step 2670: loss: 0.9009, grad_norm: 1.6328, learning_rate: 0.0000, epoch: 0.0134
274
- [2026-03-31 14:35:07] Step 2680: loss: 0.8481, grad_norm: 0.2715, learning_rate: 0.0000, epoch: 0.0134
275
- [2026-03-31 14:36:31] Step 2690: loss: 0.8816, grad_norm: 0.2461, learning_rate: 0.0000, epoch: 0.0135
276
- [2026-03-31 14:37:55] Step 2700: loss: 1.1318, grad_norm: 0.2090, learning_rate: 0.0000, epoch: 0.0135
277
- [2026-03-31 14:39:20] Step 2710: loss: 0.9612, grad_norm: 0.2676, learning_rate: 0.0000, epoch: 0.0135
278
- [2026-03-31 14:40:44] Step 2720: loss: 0.8793, grad_norm: 0.4551, learning_rate: 0.0000, epoch: 0.0136
279
- [2026-03-31 14:42:09] Step 2730: loss: 0.8833, grad_norm: 0.2324, learning_rate: 0.0000, epoch: 0.0137
280
- [2026-03-31 14:43:33] Step 2740: loss: 0.9257, grad_norm: 0.3516, learning_rate: 0.0000, epoch: 0.0137
281
- [2026-03-31 14:44:57] Step 2750: loss: 0.8887, grad_norm: 0.6445, learning_rate: 0.0000, epoch: 0.0138
282
- [2026-03-31 14:46:22] Step 2760: loss: 0.8589, grad_norm: 2.2812, learning_rate: 0.0000, epoch: 0.0138
283
- [2026-03-31 14:47:46] Step 2770: loss: 0.8785, grad_norm: 1.1016, learning_rate: 0.0000, epoch: 0.0138
284
- [2026-03-31 14:49:09] Step 2780: loss: 0.7189, grad_norm: 0.2061, learning_rate: 0.0000, epoch: 0.0139
285
- [2026-03-31 14:50:34] Step 2790: loss: 0.8549, grad_norm: 0.7891, learning_rate: 0.0000, epoch: 0.0140
286
- [2026-03-31 14:51:58] Step 2800: loss: 0.9150, grad_norm: 0.2734, learning_rate: 0.0000, epoch: 0.0140
287
- [2026-03-31 14:53:22] Step 2810: loss: 0.9147, grad_norm: 0.2158, learning_rate: 0.0000, epoch: 0.0140
288
- [2026-03-31 14:54:46] Step 2820: loss: 0.8828, grad_norm: 0.2012, learning_rate: 0.0000, epoch: 0.0141
289
- [2026-03-31 14:56:10] Step 2830: loss: 0.9843, grad_norm: 2.1094, learning_rate: 0.0000, epoch: 0.0141
290
- [2026-03-31 14:57:34] Step 2840: loss: 0.8710, grad_norm: 0.1416, learning_rate: 0.0000, epoch: 0.0142
291
- [2026-03-31 14:58:59] Step 2850: loss: 1.0107, grad_norm: 0.2480, learning_rate: 0.0000, epoch: 0.0143
292
- [2026-03-31 15:00:23] Step 2860: loss: 0.8816, grad_norm: 0.2363, learning_rate: 0.0000, epoch: 0.0143
293
- [2026-03-31 15:01:47] Step 2870: loss: 0.8672, grad_norm: 0.2930, learning_rate: 0.0000, epoch: 0.0143
294
- [2026-03-31 15:03:10] Step 2880: loss: 0.8050, grad_norm: 0.2002, learning_rate: 0.0000, epoch: 0.0144
295
- [2026-03-31 15:04:34] Step 2890: loss: 1.1084, grad_norm: 0.3613, learning_rate: 0.0000, epoch: 0.0144
296
- [2026-03-31 15:05:59] Step 2900: loss: 0.9335, grad_norm: 0.4688, learning_rate: 0.0000, epoch: 0.0145
297
- [2026-03-31 15:07:23] Step 2910: loss: 0.9287, grad_norm: 0.2891, learning_rate: 0.0000, epoch: 0.0146
298
- [2026-03-31 15:08:47] Step 2920: loss: 0.8159, grad_norm: 1.1719, learning_rate: 0.0000, epoch: 0.0146
299
- [2026-03-31 15:10:11] Step 2930: loss: 0.9082, grad_norm: 0.1699, learning_rate: 0.0000, epoch: 0.0146
300
- [2026-03-31 15:11:35] Step 2940: loss: 0.9660, grad_norm: 0.2041, learning_rate: 0.0000, epoch: 0.0147
301
- [2026-03-31 15:13:00] Step 2950: loss: 0.7883, grad_norm: 0.2676, learning_rate: 0.0000, epoch: 0.0147
302
- [2026-03-31 15:14:24] Step 2960: loss: 0.8419, grad_norm: 0.1992, learning_rate: 0.0000, epoch: 0.0148
303
- [2026-03-31 15:15:48] Step 2970: loss: 0.9337, grad_norm: 0.2285, learning_rate: 0.0000, epoch: 0.0149
304
- [2026-03-31 15:17:13] Step 2980: loss: 0.8750, grad_norm: 0.1953, learning_rate: 0.0000, epoch: 0.0149
305
- [2026-03-31 15:18:37] Step 2990: loss: 0.8789, grad_norm: 0.2168, learning_rate: 0.0000, epoch: 0.0149
306
- [2026-03-31 15:20:01] Step 3000: loss: 0.9561, grad_norm: 0.1797, learning_rate: 0.0000, epoch: 0.0150
307
- [2026-03-31 15:21:25] Step 3010: loss: 0.9642, grad_norm: 0.3496, learning_rate: 0.0000, epoch: 0.0150
308
- [2026-03-31 15:22:49] Step 3020: loss: 1.0347, grad_norm: 0.2656, learning_rate: 0.0000, epoch: 0.0151
309
- [2026-03-31 15:24:13] Step 3030: loss: 0.9259, grad_norm: 0.1924, learning_rate: 0.0000, epoch: 0.0152
310
- [2026-03-31 15:25:37] Step 3040: loss: 0.9136, grad_norm: 0.2285, learning_rate: 0.0000, epoch: 0.0152
311
- [2026-03-31 15:27:02] Step 3050: loss: 0.9276, grad_norm: 0.2598, learning_rate: 0.0000, epoch: 0.0152
312
- [2026-03-31 15:28:26] Step 3060: loss: 0.8269, grad_norm: 0.1494, learning_rate: 0.0000, epoch: 0.0153
313
- [2026-03-31 15:29:50] Step 3070: loss: 0.9138, grad_norm: 0.2109, learning_rate: 0.0000, epoch: 0.0154
314
- [2026-03-31 15:31:14] Step 3080: loss: 1.0753, grad_norm: 0.2275, learning_rate: 0.0000, epoch: 0.0154
315
- [2026-03-31 15:32:38] Step 3090: loss: 0.9903, grad_norm: 0.2227, learning_rate: 0.0000, epoch: 0.0155
316
- [2026-03-31 15:34:03] Step 3100: loss: 0.9186, grad_norm: 0.2617, learning_rate: 0.0000, epoch: 0.0155
317
- [2026-03-31 15:35:27] Step 3110: loss: 0.9422, grad_norm: 0.1680, learning_rate: 0.0000, epoch: 0.0155
318
- [2026-03-31 15:36:52] Step 3120: loss: 0.9539, grad_norm: 0.4414, learning_rate: 0.0000, epoch: 0.0156
319
- [2026-03-31 15:38:16] Step 3130: loss: 0.8632, grad_norm: 0.1807, learning_rate: 0.0000, epoch: 0.0157
320
- [2026-03-31 15:39:40] Step 3140: loss: 1.0032, grad_norm: 0.2012, learning_rate: 0.0000, epoch: 0.0157
321
- [2026-03-31 15:41:05] Step 3150: loss: 1.0542, grad_norm: 0.1982, learning_rate: 0.0000, epoch: 0.0158
322
- [2026-03-31 15:42:30] Step 3160: loss: 1.0788, grad_norm: 0.2715, learning_rate: 0.0000, epoch: 0.0158
323
- [2026-03-31 15:43:55] Step 3170: loss: 0.9620, grad_norm: 0.1738, learning_rate: 0.0000, epoch: 0.0158
324
- [2026-03-31 15:45:19] Step 3180: loss: 0.9879, grad_norm: 0.1670, learning_rate: 0.0000, epoch: 0.0159
325
- [2026-03-31 15:46:44] Step 3190: loss: 0.8974, grad_norm: 0.2119, learning_rate: 0.0000, epoch: 0.0159
326
- [2026-03-31 15:48:09] Step 3200: loss: 0.8947, grad_norm: 0.5977, learning_rate: 0.0000, epoch: 0.0160
327
- [2026-03-31 15:49:33] Step 3210: loss: 0.7498, grad_norm: 0.2793, learning_rate: 0.0000, epoch: 0.0160
328
- [2026-03-31 15:50:58] Step 3220: loss: 0.8955, grad_norm: 0.1680, learning_rate: 0.0000, epoch: 0.0161
329
- [2026-03-31 15:52:23] Step 3230: loss: 0.9516, grad_norm: 0.2471, learning_rate: 0.0000, epoch: 0.0162
330
- [2026-03-31 15:53:47] Step 3240: loss: 0.8910, grad_norm: 0.2002, learning_rate: 0.0000, epoch: 0.0162
331
- [2026-03-31 15:55:12] Step 3250: loss: 0.8762, grad_norm: 0.2207, learning_rate: 0.0000, epoch: 0.0163
332
- [2026-03-31 15:56:35] Step 3260: loss: 0.9899, grad_norm: 0.4258, learning_rate: 0.0000, epoch: 0.0163
333
- [2026-03-31 15:58:00] Step 3270: loss: 0.8093, grad_norm: 0.2598, learning_rate: 0.0000, epoch: 0.0163
334
- [2026-03-31 15:59:25] Step 3280: loss: 0.8794, grad_norm: 0.3125, learning_rate: 0.0000, epoch: 0.0164
335
- [2026-03-31 16:00:49] Step 3290: loss: 0.8551, grad_norm: 0.1768, learning_rate: 0.0000, epoch: 0.0164
336
- [2026-03-31 16:02:13] Step 3300: loss: 1.1321, grad_norm: 0.1748, learning_rate: 0.0000, epoch: 0.0165
337
- [2026-03-31 16:03:38] Step 3310: loss: 0.9119, grad_norm: 0.3984, learning_rate: 0.0000, epoch: 0.0165
338
- [2026-03-31 16:05:03] Step 3320: loss: 0.8985, grad_norm: 0.1787, learning_rate: 0.0000, epoch: 0.0166
339
- [2026-03-31 16:06:27] Step 3330: loss: 0.8375, grad_norm: 0.1631, learning_rate: 0.0000, epoch: 0.0167
340
- [2026-03-31 16:07:52] Step 3340: loss: 0.9068, grad_norm: 0.2432, learning_rate: 0.0000, epoch: 0.0167
341
- [2026-03-31 16:09:17] Step 3350: loss: 0.9024, grad_norm: 0.1885, learning_rate: 0.0000, epoch: 0.0168
342
- [2026-03-31 16:10:41] Step 3360: loss: 0.8532, grad_norm: 0.1748, learning_rate: 0.0000, epoch: 0.0168
343
- [2026-03-31 16:12:06] Step 3370: loss: 0.8744, grad_norm: 0.1875, learning_rate: 0.0000, epoch: 0.0169
344
- [2026-03-31 16:13:31] Step 3380: loss: 0.7658, grad_norm: 0.1494, learning_rate: 0.0000, epoch: 0.0169
345
- [2026-03-31 16:14:55] Step 3390: loss: 0.8695, grad_norm: 0.1475, learning_rate: 0.0000, epoch: 0.0169
346
- [2026-03-31 16:16:20] Step 3400: loss: 0.8754, grad_norm: 0.1816, learning_rate: 0.0000, epoch: 0.0170
347
- [2026-03-31 16:17:44] Step 3410: loss: 0.9383, grad_norm: 0.2256, learning_rate: 0.0000, epoch: 0.0170
348
- [2026-03-31 16:19:09] Step 3420: loss: 0.9612, grad_norm: 0.2207, learning_rate: 0.0000, epoch: 0.0171
349
- [2026-03-31 16:20:34] Step 3430: loss: 0.8932, grad_norm: 0.1768, learning_rate: 0.0000, epoch: 0.0171
350
- [2026-03-31 16:21:58] Step 3440: loss: 0.9117, grad_norm: 0.1924, learning_rate: 0.0000, epoch: 0.0172
351
- [2026-03-31 16:23:22] Step 3450: loss: 0.9146, grad_norm: 0.1777, learning_rate: 0.0000, epoch: 0.0173
352
- [2026-03-31 16:24:47] Step 3460: loss: 0.8657, grad_norm: 0.5508, learning_rate: 0.0000, epoch: 0.0173
353
- [2026-03-31 16:26:12] Step 3470: loss: 0.9556, grad_norm: 0.3516, learning_rate: 0.0000, epoch: 0.0174
354
- [2026-03-31 16:27:36] Step 3480: loss: 0.9741, grad_norm: 0.3984, learning_rate: 0.0000, epoch: 0.0174
355
- [2026-03-31 16:29:01] Step 3490: loss: 0.9079, grad_norm: 0.1885, learning_rate: 0.0000, epoch: 0.0175
356
- [2026-03-31 16:30:25] Step 3500: loss: 0.8970, grad_norm: 0.1787, learning_rate: 0.0000, epoch: 0.0175
357
- [2026-03-31 16:31:50] Step 3510: loss: 0.8500, grad_norm: 0.5078, learning_rate: 0.0000, epoch: 0.0175
358
- [2026-03-31 16:33:14] Step 3520: loss: 0.8806, grad_norm: 0.1582, learning_rate: 0.0000, epoch: 0.0176
359
- [2026-03-31 16:34:38] Step 3530: loss: 0.9168, grad_norm: 0.2461, learning_rate: 0.0000, epoch: 0.0176
360
- [2026-03-31 16:36:03] Step 3540: loss: 0.9057, grad_norm: 0.1992, learning_rate: 0.0000, epoch: 0.0177
361
- [2026-03-31 16:37:27] Step 3550: loss: 1.0234, grad_norm: 0.1865, learning_rate: 0.0000, epoch: 0.0177
362
- [2026-03-31 16:38:51] Step 3560: loss: 0.8210, grad_norm: 0.1729, learning_rate: 0.0000, epoch: 0.0178
363
- [2026-03-31 16:40:16] Step 3570: loss: 0.8790, grad_norm: 0.1875, learning_rate: 0.0000, epoch: 0.0179
364
- [2026-03-31 16:41:40] Step 3580: loss: 0.8225, grad_norm: 0.1416, learning_rate: 0.0000, epoch: 0.0179
365
- [2026-03-31 16:43:05] Step 3590: loss: 0.9980, grad_norm: 0.1670, learning_rate: 0.0000, epoch: 0.0180
366
- [2026-03-31 16:44:30] Step 3600: loss: 0.8671, grad_norm: 0.2539, learning_rate: 0.0000, epoch: 0.0180
367
- [2026-03-31 16:45:54] Step 3610: loss: 0.8107, grad_norm: 0.3477, learning_rate: 0.0000, epoch: 0.0181
368
- [2026-03-31 16:47:18] Step 3620: loss: 0.7576, grad_norm: 0.2559, learning_rate: 0.0000, epoch: 0.0181
369
- [2026-03-31 16:48:42] Step 3630: loss: 0.9383, grad_norm: 2.0156, learning_rate: 0.0000, epoch: 0.0181
370
- [2026-03-31 16:50:06] Step 3640: loss: 0.8580, grad_norm: 0.2432, learning_rate: 0.0000, epoch: 0.0182
371
- [2026-03-31 16:51:30] Step 3650: loss: 0.9007, grad_norm: 0.2988, learning_rate: 0.0000, epoch: 0.0182
372
- [2026-03-31 16:52:55] Step 3660: loss: 0.8176, grad_norm: 0.2129, learning_rate: 0.0000, epoch: 0.0183
373
- [2026-03-31 16:54:19] Step 3670: loss: 0.9369, grad_norm: 0.1982, learning_rate: 0.0000, epoch: 0.0184
374
- [2026-03-31 16:55:43] Step 3680: loss: 1.1911, grad_norm: 0.7070, learning_rate: 0.0000, epoch: 0.0184
375
- [2026-03-31 16:57:08] Step 3690: loss: 1.0193, grad_norm: 0.2012, learning_rate: 0.0000, epoch: 0.0185
376
- [2026-03-31 16:58:32] Step 3700: loss: 1.0052, grad_norm: 0.1924, learning_rate: 0.0000, epoch: 0.0185
377
- [2026-03-31 16:59:57] Step 3710: loss: 1.0500, grad_norm: 0.1768, learning_rate: 0.0000, epoch: 0.0186
378
- [2026-03-31 17:01:21] Step 3720: loss: 0.9210, grad_norm: 0.2090, learning_rate: 0.0000, epoch: 0.0186
379
- [2026-03-31 17:02:45] Step 3730: loss: 0.9981, grad_norm: 0.2578, learning_rate: 0.0000, epoch: 0.0186
380
- [2026-03-31 17:04:10] Step 3740: loss: 0.8967, grad_norm: 0.2188, learning_rate: 0.0000, epoch: 0.0187
381
- [2026-03-31 17:05:34] Step 3750: loss: 0.8784, grad_norm: 0.1826, learning_rate: 0.0000, epoch: 0.0187
382
- [2026-03-31 17:06:59] Step 3760: loss: 0.8947, grad_norm: 0.1953, learning_rate: 0.0000, epoch: 0.0188
383
- [2026-03-31 17:08:23] Step 3770: loss: 0.9104, grad_norm: 0.2559, learning_rate: 0.0000, epoch: 0.0188
384
- [2026-03-31 17:09:48] Step 3780: loss: 1.0458, grad_norm: 0.2471, learning_rate: 0.0000, epoch: 0.0189
385
- [2026-03-31 17:11:11] Step 3790: loss: 0.7790, grad_norm: 0.2373, learning_rate: 0.0000, epoch: 0.0190
386
- [2026-03-31 17:12:36] Step 3800: loss: 0.7284, grad_norm: 0.1992, learning_rate: 0.0000, epoch: 0.0190
387
- [2026-03-31 17:14:00] Step 3810: loss: 0.9255, grad_norm: 0.1924, learning_rate: 0.0000, epoch: 0.0191
388
- [2026-03-31 17:15:24] Step 3820: loss: 0.8977, grad_norm: 0.1680, learning_rate: 0.0000, epoch: 0.0191
389
- [2026-03-31 17:16:49] Step 3830: loss: 0.9002, grad_norm: 0.2490, learning_rate: 0.0000, epoch: 0.0192
390
- [2026-03-31 17:18:13] Step 3840: loss: 1.0609, grad_norm: 0.2061, learning_rate: 0.0000, epoch: 0.0192
391
- [2026-03-31 17:19:38] Step 3850: loss: 1.0644, grad_norm: 0.1992, learning_rate: 0.0000, epoch: 0.0192
392
- [2026-03-31 17:21:02] Step 3860: loss: 0.8270, grad_norm: 0.2197, learning_rate: 0.0000, epoch: 0.0193
393
- [2026-03-31 17:22:27] Step 3870: loss: 0.9838, grad_norm: 0.1729, learning_rate: 0.0000, epoch: 0.0193
394
- [2026-03-31 17:23:51] Step 3880: loss: 0.8780, grad_norm: 0.1689, learning_rate: 0.0000, epoch: 0.0194
395
- [2026-03-31 17:25:15] Step 3890: loss: 0.9309, grad_norm: 0.1611, learning_rate: 0.0000, epoch: 0.0194
396
- [2026-03-31 17:26:40] Step 3900: loss: 0.8935, grad_norm: 0.2236, learning_rate: 0.0000, epoch: 0.0195
397
- [2026-03-31 17:28:04] Step 3910: loss: 1.0017, grad_norm: 0.2012, learning_rate: 0.0000, epoch: 0.0196
398
- [2026-03-31 17:29:29] Step 3920: loss: 0.9719, grad_norm: 0.2158, learning_rate: 0.0000, epoch: 0.0196
399
- [2026-03-31 17:30:54] Step 3930: loss: 0.8408, grad_norm: 0.1504, learning_rate: 0.0000, epoch: 0.0197
400
- [2026-03-31 17:32:18] Step 3940: loss: 0.9504, grad_norm: 0.1973, learning_rate: 0.0000, epoch: 0.0197
401
- [2026-03-31 17:33:42] Step 3950: loss: 1.0454, grad_norm: 0.2129, learning_rate: 0.0000, epoch: 0.0198
402
- [2026-03-31 17:35:06] Step 3960: loss: 0.9728, grad_norm: 0.2109, learning_rate: 0.0000, epoch: 0.0198
403
- [2026-03-31 17:36:30] Step 3970: loss: 0.8852, grad_norm: 0.2168, learning_rate: 0.0000, epoch: 0.0198
404
- [2026-03-31 17:37:55] Step 3980: loss: 0.9254, grad_norm: 0.1914, learning_rate: 0.0000, epoch: 0.0199
405
- [2026-03-31 17:39:19] Step 3990: loss: 0.8751, grad_norm: 0.2559, learning_rate: 0.0000, epoch: 0.0199
406
- [2026-03-31 17:40:44] Step 4000: loss: 0.9173, grad_norm: 0.3281, learning_rate: 0.0000, epoch: 0.0200
407
- [2026-03-31 17:42:08] Step 4010: loss: 0.9351, grad_norm: 0.2520, learning_rate: 0.0000, epoch: 0.0200
408
- [2026-03-31 17:43:32] Step 4020: loss: 0.8773, grad_norm: 0.1943, learning_rate: 0.0000, epoch: 0.0201
409
- [2026-03-31 17:44:57] Step 4030: loss: 0.8618, grad_norm: 0.1582, learning_rate: 0.0000, epoch: 0.0202
410
- [2026-03-31 17:46:21] Step 4040: loss: 0.8500, grad_norm: 0.1719, learning_rate: 0.0000, epoch: 0.0202
411
- [2026-03-31 17:47:45] Step 4050: loss: 0.8936, grad_norm: 0.2578, learning_rate: 0.0000, epoch: 0.0203
412
- [2026-03-31 17:49:09] Step 4060: loss: 0.8683, grad_norm: 0.1953, learning_rate: 0.0000, epoch: 0.0203
413
- [2026-03-31 17:50:34] Step 4070: loss: 0.7832, grad_norm: 0.1328, learning_rate: 0.0000, epoch: 0.0204
414
- [2026-03-31 17:51:58] Step 4080: loss: 0.6775, grad_norm: 0.2061, learning_rate: 0.0000, epoch: 0.0204
415
- [2026-03-31 17:53:23] Step 4090: loss: 0.9338, grad_norm: 0.2480, learning_rate: 0.0000, epoch: 0.0204
416
- [2026-03-31 17:54:47] Step 4100: loss: 0.7835, grad_norm: 0.2520, learning_rate: 0.0000, epoch: 0.0205
417
- [2026-03-31 17:56:12] Step 4110: loss: 0.8946, grad_norm: 0.1533, learning_rate: 0.0000, epoch: 0.0205
418
- [2026-03-31 17:57:36] Step 4120: loss: 0.8517, grad_norm: 0.2266, learning_rate: 0.0000, epoch: 0.0206
419
- [2026-03-31 17:59:01] Step 4130: loss: 0.8826, grad_norm: 0.1631, learning_rate: 0.0000, epoch: 0.0207
420
- [2026-03-31 18:00:25] Step 4140: loss: 0.8173, grad_norm: 0.2754, learning_rate: 0.0000, epoch: 0.0207
421
- [2026-03-31 18:01:49] Step 4150: loss: 0.8839, grad_norm: 0.2100, learning_rate: 0.0000, epoch: 0.0208
422
- [2026-03-31 18:03:14] Step 4160: loss: 0.8888, grad_norm: 0.1475, learning_rate: 0.0000, epoch: 0.0208
423
- [2026-03-31 18:04:38] Step 4170: loss: 0.9064, grad_norm: 0.1807, learning_rate: 0.0000, epoch: 0.0209
424
- [2026-03-31 18:06:02] Step 4180: loss: 0.8271, grad_norm: 0.2578, learning_rate: 0.0000, epoch: 0.0209
425
- [2026-03-31 18:07:27] Step 4190: loss: 0.9239, grad_norm: 0.2021, learning_rate: 0.0000, epoch: 0.0209
426
- [2026-03-31 18:08:51] Step 4200: loss: 0.9820, grad_norm: 0.2305, learning_rate: 0.0000, epoch: 0.0210
427
- [2026-03-31 18:10:15] Step 4210: loss: 0.8543, grad_norm: 0.1523, learning_rate: 0.0000, epoch: 0.0210
428
- [2026-03-31 18:11:39] Step 4220: loss: 0.9517, grad_norm: 0.2793, learning_rate: 0.0000, epoch: 0.0211
429
- [2026-03-31 18:13:04] Step 4230: loss: 0.8595, grad_norm: 0.2031, learning_rate: 0.0000, epoch: 0.0211
430
- [2026-03-31 18:14:28] Step 4240: loss: 0.8872, grad_norm: 0.2051, learning_rate: 0.0000, epoch: 0.0212
431
- [2026-03-31 18:15:53] Step 4250: loss: 0.8650, grad_norm: 0.1289, learning_rate: 0.0000, epoch: 0.0213
432
- [2026-03-31 18:17:17] Step 4260: loss: 0.9305, grad_norm: 0.2432, learning_rate: 0.0000, epoch: 0.0213
433
- [2026-03-31 18:18:41] Step 4270: loss: 0.9319, grad_norm: 0.1855, learning_rate: 0.0000, epoch: 0.0214
434
- [2026-03-31 18:20:05] Step 4280: loss: 0.8637, grad_norm: 0.1885, learning_rate: 0.0000, epoch: 0.0214
435
- [2026-03-31 18:21:29] Step 4290: loss: 0.8701, grad_norm: 0.2305, learning_rate: 0.0000, epoch: 0.0215
436
- [2026-03-31 18:22:53] Step 4300: loss: 0.9087, grad_norm: 0.1895, learning_rate: 0.0000, epoch: 0.0215
437
- [2026-03-31 18:24:17] Step 4310: loss: 0.9215, grad_norm: 0.1738, learning_rate: 0.0000, epoch: 0.0215
438
- [2026-03-31 18:25:42] Step 4320: loss: 0.9207, grad_norm: 0.2012, learning_rate: 0.0000, epoch: 0.0216
439
- [2026-03-31 18:27:06] Step 4330: loss: 0.9114, grad_norm: 0.6992, learning_rate: 0.0000, epoch: 0.0216
440
- [2026-03-31 18:28:30] Step 4340: loss: 0.9899, grad_norm: 0.2041, learning_rate: 0.0000, epoch: 0.0217
441
- [2026-03-31 18:29:54] Step 4350: loss: 1.0729, grad_norm: 2.7656, learning_rate: 0.0000, epoch: 0.0217
442
- [2026-03-31 18:31:19] Step 4360: loss: 0.8625, grad_norm: 0.1738, learning_rate: 0.0000, epoch: 0.0218
443
- [2026-03-31 18:32:43] Step 4370: loss: 0.9157, grad_norm: 0.3574, learning_rate: 0.0000, epoch: 0.0219
444
- [2026-03-31 18:34:07] Step 4380: loss: 0.8719, grad_norm: 0.1973, learning_rate: 0.0000, epoch: 0.0219
445
- [2026-03-31 18:35:31] Step 4390: loss: 0.8874, grad_norm: 0.2109, learning_rate: 0.0000, epoch: 0.0220
446
- [2026-03-31 18:36:55] Step 4400: loss: 0.9309, grad_norm: 0.1826, learning_rate: 0.0000, epoch: 0.0220
447
- [2026-03-31 18:38:20] Step 4410: loss: 0.8833, grad_norm: 0.2090, learning_rate: 0.0000, epoch: 0.0221
448
- [2026-03-31 18:39:44] Step 4420: loss: 0.7998, grad_norm: 0.1895, learning_rate: 0.0000, epoch: 0.0221
449
- [2026-03-31 18:41:08] Step 4430: loss: 0.8777, grad_norm: 0.2158, learning_rate: 0.0000, epoch: 0.0221
450
- [2026-03-31 18:42:32] Step 4440: loss: 0.8901, grad_norm: 0.4219, learning_rate: 0.0000, epoch: 0.0222
451
- [2026-03-31 18:43:56] Step 4450: loss: 0.8968, grad_norm: 0.2314, learning_rate: 0.0000, epoch: 0.0222
452
- [2026-03-31 18:45:20] Step 4460: loss: 0.8684, grad_norm: 0.1738, learning_rate: 0.0000, epoch: 0.0223
453
- [2026-03-31 18:46:45] Step 4470: loss: 0.8574, grad_norm: 0.1973, learning_rate: 0.0000, epoch: 0.0223
454
- [2026-03-31 18:48:09] Step 4480: loss: 0.9964, grad_norm: 0.1973, learning_rate: 0.0000, epoch: 0.0224
455
- [2026-03-31 18:49:33] Step 4490: loss: 0.8622, grad_norm: 0.2188, learning_rate: 0.0000, epoch: 0.0225
456
- [2026-03-31 18:50:57] Step 4500: loss: 0.7814, grad_norm: 0.2451, learning_rate: 0.0000, epoch: 0.0225
457
- [2026-03-31 18:52:21] Step 4510: loss: 0.9241, grad_norm: 0.1953, learning_rate: 0.0000, epoch: 0.0226
458
- [2026-03-31 18:53:46] Step 4520: loss: 0.8458, grad_norm: 0.2051, learning_rate: 0.0000, epoch: 0.0226
459
- [2026-03-31 18:55:10] Step 4530: loss: 1.0007, grad_norm: 0.2021, learning_rate: 0.0000, epoch: 0.0226
460
- [2026-03-31 18:56:34] Step 4540: loss: 0.9046, grad_norm: 0.2100, learning_rate: 0.0000, epoch: 0.0227
461
- [2026-03-31 18:57:58] Step 4550: loss: 0.9815, grad_norm: 0.2236, learning_rate: 0.0000, epoch: 0.0227
462
- [2026-03-31 18:59:23] Step 4560: loss: 0.9537, grad_norm: 0.2617, learning_rate: 0.0000, epoch: 0.0228
463
- [2026-03-31 19:00:47] Step 4570: loss: 0.8766, grad_norm: 0.1895, learning_rate: 0.0000, epoch: 0.0228
464
- [2026-03-31 19:02:11] Step 4580: loss: 1.0590, grad_norm: 0.5586, learning_rate: 0.0000, epoch: 0.0229
465
- [2026-03-31 19:03:35] Step 4590: loss: 0.8494, grad_norm: 0.2207, learning_rate: 0.0000, epoch: 0.0230
466
- [2026-03-31 19:04:59] Step 4600: loss: 1.0682, grad_norm: 0.2266, learning_rate: 0.0000, epoch: 0.0230
467
- [2026-03-31 19:06:23] Step 4610: loss: 1.0588, grad_norm: 0.3145, learning_rate: 0.0000, epoch: 0.0231
468
- [2026-03-31 19:07:48] Step 4620: loss: 0.8522, grad_norm: 0.2422, learning_rate: 0.0000, epoch: 0.0231
469
- [2026-03-31 19:09:12] Step 4630: loss: 1.0611, grad_norm: 0.5234, learning_rate: 0.0000, epoch: 0.0232
470
- [2026-03-31 19:10:36] Step 4640: loss: 0.9557, grad_norm: 0.2402, learning_rate: 0.0000, epoch: 0.0232
471
- [2026-03-31 19:12:00] Step 4650: loss: 1.0054, grad_norm: 36.2500, learning_rate: 0.0000, epoch: 0.0232
472
- [2026-03-31 19:13:24] Step 4660: loss: 0.9374, grad_norm: 0.3652, learning_rate: 0.0000, epoch: 0.0233
473
- [2026-03-31 19:14:49] Step 4670: loss: 1.0201, grad_norm: 0.2441, learning_rate: 0.0000, epoch: 0.0233
474
- [2026-03-31 19:16:13] Step 4680: loss: 0.9874, grad_norm: 0.2383, learning_rate: 0.0000, epoch: 0.0234
475
- [2026-03-31 19:17:37] Step 4690: loss: 1.4854, grad_norm: 0.2559, learning_rate: 0.0000, epoch: 0.0234
476
- [2026-03-31 19:19:01] Step 4700: loss: 0.8645, grad_norm: 0.1934, learning_rate: 0.0000, epoch: 0.0235
477
- [2026-03-31 19:20:26] Step 4710: loss: 1.0148, grad_norm: 0.2334, learning_rate: 0.0000, epoch: 0.0236
478
- [2026-03-31 19:21:50] Step 4720: loss: 0.8638, grad_norm: 0.5508, learning_rate: 0.0000, epoch: 0.0236
479
- [2026-03-31 19:23:14] Step 4730: loss: 0.9692, grad_norm: 0.2539, learning_rate: 0.0000, epoch: 0.0237
480
- [2026-03-31 19:24:38] Step 4740: loss: 0.9147, grad_norm: 0.7852, learning_rate: 0.0000, epoch: 0.0237
481
- [2026-03-31 19:26:01] Step 4750: loss: 0.9041, grad_norm: 0.2266, learning_rate: 0.0000, epoch: 0.0238
482
- [2026-03-31 19:27:25] Step 4760: loss: 0.9570, grad_norm: 0.2441, learning_rate: 0.0000, epoch: 0.0238
483
- [2026-03-31 19:28:50] Step 4770: loss: 0.9288, grad_norm: 0.2266, learning_rate: 0.0000, epoch: 0.0238
484
- [2026-03-31 19:30:14] Step 4780: loss: 0.9323, grad_norm: 0.1787, learning_rate: 0.0000, epoch: 0.0239
485
- [2026-03-31 19:31:39] Step 4790: loss: 0.8816, grad_norm: 1.1172, learning_rate: 0.0000, epoch: 0.0239
486
- [2026-03-31 19:33:03] Step 4800: loss: 0.9510, grad_norm: 0.2354, learning_rate: 0.0000, epoch: 0.0240
487
- [2026-03-31 19:34:27] Step 4810: loss: 0.9225, grad_norm: 0.1768, learning_rate: 0.0000, epoch: 0.0240
488
- [2026-03-31 19:35:51] Step 4820: loss: 0.9849, grad_norm: 0.1523, learning_rate: 0.0000, epoch: 0.0241
489
- [2026-03-31 19:37:16] Step 4830: loss: 0.8417, grad_norm: 0.1709, learning_rate: 0.0000, epoch: 0.0242
490
- [2026-03-31 19:38:40] Step 4840: loss: 0.8466, grad_norm: 0.1748, learning_rate: 0.0000, epoch: 0.0242
491
- [2026-03-31 19:40:04] Step 4850: loss: 0.8813, grad_norm: 0.2949, learning_rate: 0.0000, epoch: 0.0243
492
- [2026-03-31 19:41:28] Step 4860: loss: 0.9765, grad_norm: 0.1982, learning_rate: 0.0000, epoch: 0.0243
493
- [2026-03-31 19:42:52] Step 4870: loss: 0.9710, grad_norm: 0.1729, learning_rate: 0.0000, epoch: 0.0244
494
- [2026-03-31 19:44:16] Step 4880: loss: 0.9264, grad_norm: 0.2129, learning_rate: 0.0000, epoch: 0.0244
495
- [2026-03-31 19:45:40] Step 4890: loss: 0.7979, grad_norm: 0.1602, learning_rate: 0.0000, epoch: 0.0244
496
- [2026-03-31 19:47:04] Step 4900: loss: 0.9023, grad_norm: 0.1729, learning_rate: 0.0000, epoch: 0.0245
497
- [2026-03-31 19:48:28] Step 4910: loss: 0.8968, grad_norm: 1.2891, learning_rate: 0.0000, epoch: 0.0245
498
- [2026-03-31 19:49:52] Step 4920: loss: 0.7637, grad_norm: 0.2109, learning_rate: 0.0000, epoch: 0.0246
499
- [2026-03-31 19:51:17] Step 4930: loss: 0.9097, grad_norm: 0.1699, learning_rate: 0.0000, epoch: 0.0246
500
- [2026-03-31 19:52:41] Step 4940: loss: 0.8691, grad_norm: 0.1914, learning_rate: 0.0000, epoch: 0.0247
501
- [2026-03-31 19:54:05] Step 4950: loss: 0.7844, grad_norm: 0.2080, learning_rate: 0.0000, epoch: 0.0248
502
- [2026-03-31 19:55:29] Step 4960: loss: 0.7980, grad_norm: 0.6211, learning_rate: 0.0000, epoch: 0.0248
503
- [2026-03-31 19:56:53] Step 4970: loss: 0.9153, grad_norm: 0.1699, learning_rate: 0.0000, epoch: 0.0249
504
- [2026-03-31 19:58:17] Step 4980: loss: 0.9106, grad_norm: 0.2100, learning_rate: 0.0000, epoch: 0.0249
505
- [2026-03-31 19:59:42] Step 4990: loss: 0.9035, grad_norm: 0.1943, learning_rate: 0.0000, epoch: 0.0249
506
- [2026-03-31 20:01:06] Step 5000: loss: 0.8836, grad_norm: 0.2734, learning_rate: 0.0000, epoch: 0.0250
 
1
 
2
  ==================================================
3
+ Training started at: 2026-04-04 09:18:44
4
  ==================================================
5
 
6
+ [2026-04-04 09:24:56] Step 2010: loss: 2.8399, grad_norm: 1.7500, learning_rate: 0.0000, epoch: 0.0100
7
+ [2026-04-04 09:26:20] Step 2020: loss: 2.5400, grad_norm: 3.1562, learning_rate: 0.0000, epoch: 0.0101
8
+ [2026-04-04 09:27:44] Step 2030: loss: 2.2588, grad_norm: 0.6328, learning_rate: 0.0000, epoch: 0.0101
9
+ [2026-04-04 09:29:08] Step 2040: loss: 2.5586, grad_norm: 2.8906, learning_rate: 0.0000, epoch: 0.0102
10
+ [2026-04-04 09:30:32] Step 2050: loss: 1.3992, grad_norm: 0.3848, learning_rate: 0.0000, epoch: 0.0103
11
+ [2026-04-04 09:31:57] Step 2060: loss: 0.9564, grad_norm: 0.6211, learning_rate: 0.0000, epoch: 0.0103
12
+ [2026-04-04 09:33:21] Step 2070: loss: 1.0082, grad_norm: 0.3125, learning_rate: 0.0000, epoch: 0.0103
13
+ [2026-04-04 09:34:45] Step 2080: loss: 1.0009, grad_norm: 0.3047, learning_rate: 0.0000, epoch: 0.0104
14
+ [2026-04-04 09:36:10] Step 2090: loss: 1.0767, grad_norm: 4.9375, learning_rate: 0.0000, epoch: 0.0104
15
+ [2026-04-04 09:37:34] Step 2100: loss: 1.2326, grad_norm: 7.1562, learning_rate: 0.0000, epoch: 0.0105
16
+ [2026-04-04 09:38:58] Step 2110: loss: 1.0480, grad_norm: 0.3496, learning_rate: 0.0000, epoch: 0.0106
17
+ [2026-04-04 09:40:22] Step 2120: loss: 0.9334, grad_norm: 1.3828, learning_rate: 0.0000, epoch: 0.0106
18
+ [2026-04-04 09:41:46] Step 2130: loss: 0.9686, grad_norm: 0.3398, learning_rate: 0.0000, epoch: 0.0106
19
+ [2026-04-04 09:43:10] Step 2140: loss: 0.9875, grad_norm: 0.2695, learning_rate: 0.0000, epoch: 0.0107
20
+ [2026-04-04 09:44:34] Step 2150: loss: 1.0286, grad_norm: 0.4629, learning_rate: 0.0000, epoch: 0.0107
21
+ [2026-04-04 09:45:59] Step 2160: loss: 0.9684, grad_norm: 0.4922, learning_rate: 0.0000, epoch: 0.0108
22
+ [2026-04-04 09:47:23] Step 2170: loss: 1.0229, grad_norm: 0.3691, learning_rate: 0.0000, epoch: 0.0109
23
+ [2026-04-04 09:48:48] Step 2180: loss: 0.9697, grad_norm: 0.2598, learning_rate: 0.0000, epoch: 0.0109
24
+ [2026-04-04 09:50:12] Step 2190: loss: 0.9916, grad_norm: 0.2852, learning_rate: 0.0000, epoch: 0.0109
25
+ [2026-04-04 09:51:36] Step 2200: loss: 0.7603, grad_norm: 0.3242, learning_rate: 0.0000, epoch: 0.0110
26
+ [2026-04-04 09:53:00] Step 2210: loss: 0.8609, grad_norm: 0.2617, learning_rate: 0.0000, epoch: 0.0111
27
+ [2026-04-04 09:54:24] Step 2220: loss: 0.9794, grad_norm: 0.2363, learning_rate: 0.0000, epoch: 0.0111
28
+ [2026-04-04 09:55:48] Step 2230: loss: 0.8372, grad_norm: 0.2451, learning_rate: 0.0000, epoch: 0.0112
29
+ [2026-04-04 09:57:13] Step 2240: loss: 1.0379, grad_norm: 0.2090, learning_rate: 0.0000, epoch: 0.0112
30
+ [2026-04-04 09:58:37] Step 2250: loss: 0.9140, grad_norm: 0.5703, learning_rate: 0.0000, epoch: 0.0112
31
+ [2026-04-04 10:00:02] Step 2260: loss: 0.9224, grad_norm: 0.2041, learning_rate: 0.0000, epoch: 0.0113
32
+ [2026-04-04 10:01:26] Step 2270: loss: 0.9180, grad_norm: 0.2061, learning_rate: 0.0000, epoch: 0.0114
33
+ [2026-04-04 10:02:50] Step 2280: loss: 0.9332, grad_norm: 0.2324, learning_rate: 0.0000, epoch: 0.0114
34
+ [2026-04-04 10:04:15] Step 2290: loss: 1.0547, grad_norm: 0.2490, learning_rate: 0.0000, epoch: 0.0115
35
+ [2026-04-04 10:05:38] Step 2300: loss: 0.9023, grad_norm: 0.2402, learning_rate: 0.0000, epoch: 0.0115
36
+ [2026-04-04 10:07:03] Step 2310: loss: 0.9282, grad_norm: 0.2471, learning_rate: 0.0000, epoch: 0.0115
37
+ [2026-04-04 10:08:27] Step 2320: loss: 1.0646, grad_norm: 0.3613, learning_rate: 0.0000, epoch: 0.0116
38
+ [2026-04-04 10:09:51] Step 2330: loss: 1.0843, grad_norm: 0.2295, learning_rate: 0.0000, epoch: 0.0117
39
+ [2026-04-04 10:11:15] Step 2340: loss: 0.8962, grad_norm: 0.4238, learning_rate: 0.0000, epoch: 0.0117
40
+ [2026-04-04 10:12:39] Step 2350: loss: 1.1290, grad_norm: 0.2246, learning_rate: 0.0000, epoch: 0.0118
41
+ [2026-04-04 10:14:03] Step 2360: loss: 0.8712, grad_norm: 0.3027, learning_rate: 0.0000, epoch: 0.0118
42
+ [2026-04-04 10:15:28] Step 2370: loss: 0.8248, grad_norm: 0.1875, learning_rate: 0.0000, epoch: 0.0118
43
+ [2026-04-04 10:16:52] Step 2380: loss: 0.8929, grad_norm: 0.2314, learning_rate: 0.0000, epoch: 0.0119
44
+ [2026-04-04 10:18:16] Step 2390: loss: 0.9730, grad_norm: 0.2129, learning_rate: 0.0000, epoch: 0.0120
45
+ [2026-04-04 10:19:40] Step 2400: loss: 0.8794, grad_norm: 0.3340, learning_rate: 0.0000, epoch: 0.0120
46
+ [2026-04-04 10:21:04] Step 2410: loss: 0.8079, grad_norm: 0.2637, learning_rate: 0.0000, epoch: 0.0120
47
+ [2026-04-04 10:22:29] Step 2420: loss: 0.9668, grad_norm: 0.2490, learning_rate: 0.0000, epoch: 0.0121
48
+ [2026-04-04 10:23:53] Step 2430: loss: 0.8787, grad_norm: 0.2969, learning_rate: 0.0000, epoch: 0.0121
49
+ [2026-04-04 10:25:17] Step 2440: loss: 0.8943, grad_norm: 0.2852, learning_rate: 0.0000, epoch: 0.0122
50
+ [2026-04-04 10:26:41] Step 2450: loss: 0.9024, grad_norm: 0.2637, learning_rate: 0.0000, epoch: 0.0123
51
+ [2026-04-04 10:28:05] Step 2460: loss: 0.7944, grad_norm: 0.3672, learning_rate: 0.0000, epoch: 0.0123
52
+ [2026-04-04 10:29:30] Step 2470: loss: 0.9620, grad_norm: 0.2109, learning_rate: 0.0000, epoch: 0.0123
53
+ [2026-04-04 10:30:54] Step 2480: loss: 0.8795, grad_norm: 0.2637, learning_rate: 0.0000, epoch: 0.0124
54
+ [2026-04-04 10:32:19] Step 2490: loss: 0.8035, grad_norm: 0.2295, learning_rate: 0.0000, epoch: 0.0124
55
+ [2026-04-04 10:33:43] Step 2500: loss: 0.7863, grad_norm: 0.3164, learning_rate: 0.0000, epoch: 0.0125
56
+ [2026-04-04 10:35:07] Step 2510: loss: 1.0078, grad_norm: 0.5156, learning_rate: 0.0000, epoch: 0.0126
57
+ [2026-04-04 10:36:32] Step 2520: loss: 0.8982, grad_norm: 0.2559, learning_rate: 0.0000, epoch: 0.0126
58
+ [2026-04-04 10:37:56] Step 2530: loss: 0.9230, grad_norm: 0.2070, learning_rate: 0.0000, epoch: 0.0126
59
+ [2026-04-04 10:39:19] Step 2540: loss: 0.4966, grad_norm: 0.2969, learning_rate: 0.0000, epoch: 0.0127
60
+ [2026-04-04 10:40:43] Step 2550: loss: 0.9865, grad_norm: 0.2305, learning_rate: 0.0000, epoch: 0.0127
61
+ [2026-04-04 10:42:07] Step 2560: loss: 0.8903, grad_norm: 0.2402, learning_rate: 0.0000, epoch: 0.0128
62
+ [2026-04-04 10:43:31] Step 2570: loss: 0.9468, grad_norm: 0.4883, learning_rate: 0.0000, epoch: 0.0129
63
+ [2026-04-04 10:44:56] Step 2580: loss: 0.9083, grad_norm: 0.2490, learning_rate: 0.0000, epoch: 0.0129
64
+ [2026-04-04 10:46:20] Step 2590: loss: 0.9190, grad_norm: 0.2041, learning_rate: 0.0000, epoch: 0.0129
65
+ [2026-04-04 10:47:44] Step 2600: loss: 0.9126, grad_norm: 0.2373, learning_rate: 0.0000, epoch: 0.0130
66
+ [2026-04-04 10:49:09] Step 2610: loss: 0.8419, grad_norm: 0.3125, learning_rate: 0.0000, epoch: 0.0131
67
+ [2026-04-04 10:50:33] Step 2620: loss: 0.7891, grad_norm: 0.1816, learning_rate: 0.0000, epoch: 0.0131
68
+ [2026-04-04 10:51:57] Step 2630: loss: 0.8950, grad_norm: 0.2314, learning_rate: 0.0000, epoch: 0.0132
69
+ [2026-04-04 10:53:21] Step 2640: loss: 0.8428, grad_norm: 0.2539, learning_rate: 0.0000, epoch: 0.0132
70
+ [2026-04-04 10:54:45] Step 2650: loss: 0.9133, grad_norm: 0.2734, learning_rate: 0.0000, epoch: 0.0132
71
+ [2026-04-04 10:56:09] Step 2660: loss: 1.2072, grad_norm: 0.2793, learning_rate: 0.0000, epoch: 0.0133
72
+ [2026-04-04 10:57:34] Step 2670: loss: 0.9179, grad_norm: 1.3750, learning_rate: 0.0000, epoch: 0.0134
73
+ [2026-04-04 10:58:58] Step 2680: loss: 0.8475, grad_norm: 0.2266, learning_rate: 0.0000, epoch: 0.0134
74
+ [2026-04-04 11:00:22] Step 2690: loss: 0.8865, grad_norm: 0.3066, learning_rate: 0.0000, epoch: 0.0135
75
+ [2026-04-04 11:01:47] Step 2700: loss: 1.1335, grad_norm: 0.2578, learning_rate: 0.0000, epoch: 0.0135
76
+ [2026-04-04 11:03:11] Step 2710: loss: 0.8892, grad_norm: 0.3223, learning_rate: 0.0000, epoch: 0.0135
77
+ [2026-04-04 11:04:35] Step 2720: loss: 0.8915, grad_norm: 0.3145, learning_rate: 0.0000, epoch: 0.0136
78
+ [2026-04-04 11:06:00] Step 2730: loss: 0.8971, grad_norm: 0.2383, learning_rate: 0.0000, epoch: 0.0137
79
+ [2026-04-04 11:07:24] Step 2740: loss: 0.9294, grad_norm: 0.2695, learning_rate: 0.0000, epoch: 0.0137
80
+ [2026-04-04 11:08:48] Step 2750: loss: 0.8750, grad_norm: 0.1738, learning_rate: 0.0000, epoch: 0.0138
81
+ [2026-04-04 11:10:12] Step 2760: loss: 0.8538, grad_norm: 0.9219, learning_rate: 0.0000, epoch: 0.0138
82
+ [2026-04-04 11:11:36] Step 2770: loss: 0.8476, grad_norm: 0.2754, learning_rate: 0.0000, epoch: 0.0138
83
+ [2026-04-04 11:13:00] Step 2780: loss: 0.7105, grad_norm: 0.2656, learning_rate: 0.0000, epoch: 0.0139
84
+ [2026-04-04 11:14:24] Step 2790: loss: 0.8698, grad_norm: 0.5781, learning_rate: 0.0000, epoch: 0.0140
85
+ [2026-04-04 11:15:48] Step 2800: loss: 0.9280, grad_norm: 0.2305, learning_rate: 0.0000, epoch: 0.0140
86
+ [2026-04-04 11:17:12] Step 2810: loss: 0.9404, grad_norm: 0.2236, learning_rate: 0.0000, epoch: 0.0140
87
+ [2026-04-04 11:18:36] Step 2820: loss: 0.8950, grad_norm: 0.2188, learning_rate: 0.0000, epoch: 0.0141
88
+ [2026-04-04 11:20:00] Step 2830: loss: 0.9473, grad_norm: 1.7734, learning_rate: 0.0000, epoch: 0.0141
89
+ [2026-04-04 11:21:24] Step 2840: loss: 0.8666, grad_norm: 0.1504, learning_rate: 0.0000, epoch: 0.0142
90
+ [2026-04-04 11:22:48] Step 2850: loss: 0.9285, grad_norm: 0.2275, learning_rate: 0.0000, epoch: 0.0143
91
+ [2026-04-04 11:24:12] Step 2860: loss: 0.8818, grad_norm: 0.2598, learning_rate: 0.0000, epoch: 0.0143
92
+ [2026-04-04 11:25:36] Step 2870: loss: 0.8695, grad_norm: 0.3086, learning_rate: 0.0000, epoch: 0.0143
93
+ [2026-04-04 11:27:00] Step 2880: loss: 0.8156, grad_norm: 0.2432, learning_rate: 0.0000, epoch: 0.0144
94
+ [2026-04-04 11:28:24] Step 2890: loss: 1.0572, grad_norm: 0.2012, learning_rate: 0.0000, epoch: 0.0144
95
+ [2026-04-04 11:29:48] Step 2900: loss: 0.9074, grad_norm: 0.3926, learning_rate: 0.0000, epoch: 0.0145
96
+ [2026-04-04 11:31:12] Step 2910: loss: 0.9228, grad_norm: 0.3008, learning_rate: 0.0000, epoch: 0.0146
97
+ [2026-04-04 11:32:36] Step 2920: loss: 0.7711, grad_norm: 0.2148, learning_rate: 0.0000, epoch: 0.0146
98
+ [2026-04-04 11:33:59] Step 2930: loss: 0.8896, grad_norm: 0.1621, learning_rate: 0.0000, epoch: 0.0146
99
+ [2026-04-04 11:35:24] Step 2940: loss: 0.8782, grad_norm: 0.2031, learning_rate: 0.0000, epoch: 0.0147
100
+ [2026-04-04 11:36:47] Step 2950: loss: 0.8114, grad_norm: 0.3398, learning_rate: 0.0000, epoch: 0.0147
101
+ [2026-04-04 11:38:12] Step 2960: loss: 0.8362, grad_norm: 0.1992, learning_rate: 0.0000, epoch: 0.0148
102
+ [2026-04-04 11:39:36] Step 2970: loss: 0.9280, grad_norm: 0.2402, learning_rate: 0.0000, epoch: 0.0149
103
+ [2026-04-04 11:41:00] Step 2980: loss: 0.8748, grad_norm: 0.1982, learning_rate: 0.0000, epoch: 0.0149
104
+ [2026-04-04 11:42:24] Step 2990: loss: 0.8827, grad_norm: 0.2451, learning_rate: 0.0000, epoch: 0.0149
105
+ [2026-04-04 11:43:48] Step 3000: loss: 0.8786, grad_norm: 0.6719, learning_rate: 0.0000, epoch: 0.0150
106
+ [2026-04-04 11:45:12] Step 3010: loss: 0.9199, grad_norm: 10.9375, learning_rate: 0.0000, epoch: 0.0150
107
+ [2026-04-04 11:46:36] Step 3020: loss: 0.9592, grad_norm: 0.3965, learning_rate: 0.0000, epoch: 0.0151
108
+ [2026-04-04 11:48:00] Step 3030: loss: 0.9399, grad_norm: 0.2031, learning_rate: 0.0000, epoch: 0.0152
109
+ [2026-04-04 11:49:24] Step 3040: loss: 0.9260, grad_norm: 0.2617, learning_rate: 0.0000, epoch: 0.0152
110
+ [2026-04-04 11:50:48] Step 3050: loss: 0.8369, grad_norm: 0.2695, learning_rate: 0.0000, epoch: 0.0152
111
+ [2026-04-04 11:52:13] Step 3060: loss: 0.8429, grad_norm: 0.2285, learning_rate: 0.0000, epoch: 0.0153
112
+ [2026-04-04 11:53:37] Step 3070: loss: 0.9259, grad_norm: 0.2637, learning_rate: 0.0000, epoch: 0.0154
113
+ [2026-04-04 11:55:01] Step 3080: loss: 0.9881, grad_norm: 0.2412, learning_rate: 0.0000, epoch: 0.0154
114
+ [2026-04-04 11:56:25] Step 3090: loss: 0.9997, grad_norm: 0.2207, learning_rate: 0.0000, epoch: 0.0155
115
+ [2026-04-04 11:57:49] Step 3100: loss: 0.8810, grad_norm: 0.4238, learning_rate: 0.0000, epoch: 0.0155
116
+ [2026-04-04 11:59:14] Step 3110: loss: 0.8769, grad_norm: 0.2500, learning_rate: 0.0000, epoch: 0.0155
117
+ [2026-04-04 12:00:39] Step 3120: loss: 0.8588, grad_norm: 0.2598, learning_rate: 0.0000, epoch: 0.0156
118
+ [2026-04-04 12:02:03] Step 3130: loss: 0.8142, grad_norm: 0.1787, learning_rate: 0.0000, epoch: 0.0157
119
+ [2026-04-04 12:03:28] Step 3140: loss: 0.8229, grad_norm: 0.1855, learning_rate: 0.0000, epoch: 0.0157
120
+ [2026-04-04 12:04:52] Step 3150: loss: 0.8981, grad_norm: 0.1797, learning_rate: 0.0000, epoch: 0.0158
121
+ [2026-04-04 12:06:17] Step 3160: loss: 0.9945, grad_norm: 0.2109, learning_rate: 0.0000, epoch: 0.0158
122
+ [2026-04-04 12:07:42] Step 3170: loss: 0.8905, grad_norm: 0.1758, learning_rate: 0.0000, epoch: 0.0158
123
+ [2026-04-04 12:09:07] Step 3180: loss: 0.8941, grad_norm: 0.1865, learning_rate: 0.0000, epoch: 0.0159
124
+ [2026-04-04 12:10:32] Step 3190: loss: 0.8214, grad_norm: 0.1826, learning_rate: 0.0000, epoch: 0.0159
125
+ [2026-04-04 12:11:56] Step 3200: loss: 0.8866, grad_norm: 0.1865, learning_rate: 0.0000, epoch: 0.0160
126
+ [2026-04-04 12:13:20] Step 3210: loss: 0.7030, grad_norm: 0.2178, learning_rate: 0.0000, epoch: 0.0160
127
+ [2026-04-04 12:14:45] Step 3220: loss: 0.8260, grad_norm: 0.1631, learning_rate: 0.0000, epoch: 0.0161
128
+ [2026-04-04 12:16:09] Step 3230: loss: 0.8487, grad_norm: 0.1768, learning_rate: 0.0000, epoch: 0.0162
129
+ [2026-04-04 12:17:34] Step 3240: loss: 0.8839, grad_norm: 1.5859, learning_rate: 0.0000, epoch: 0.0162
130
+ [2026-04-04 12:18:59] Step 3250: loss: 0.8126, grad_norm: 0.1729, learning_rate: 0.0000, epoch: 0.0163
131
+ [2026-04-04 12:20:22] Step 3260: loss: 0.8689, grad_norm: 3.5781, learning_rate: 0.0000, epoch: 0.0163
132
+ [2026-04-04 12:21:46] Step 3270: loss: 0.8413, grad_norm: 0.7891, learning_rate: 0.0000, epoch: 0.0163
133
+ [2026-04-04 12:23:11] Step 3280: loss: 0.9708, grad_norm: 0.4590, learning_rate: 0.0000, epoch: 0.0164
134
+ [2026-04-04 12:24:35] Step 3290: loss: 0.8723, grad_norm: 0.2754, learning_rate: 0.0000, epoch: 0.0164
135
+ [2026-04-04 12:26:00] Step 3300: loss: 0.9940, grad_norm: 0.2246, learning_rate: 0.0000, epoch: 0.0165
136
+ [2026-04-04 12:27:24] Step 3310: loss: 0.8340, grad_norm: 1.4609, learning_rate: 0.0000, epoch: 0.0165
137
+ [2026-04-04 12:28:49] Step 3320: loss: 0.8388, grad_norm: 0.1953, learning_rate: 0.0000, epoch: 0.0166
138
+ [2026-04-04 12:30:14] Step 3330: loss: 0.8837, grad_norm: 0.2148, learning_rate: 0.0000, epoch: 0.0167
139
+ [2026-04-04 12:31:38] Step 3340: loss: 0.8853, grad_norm: 0.2354, learning_rate: 0.0000, epoch: 0.0167
140
+ [2026-04-04 12:33:02] Step 3350: loss: 0.9380, grad_norm: 0.2168, learning_rate: 0.0000, epoch: 0.0168
141
+ [2026-04-04 12:34:27] Step 3360: loss: 0.8515, grad_norm: 0.2021, learning_rate: 0.0000, epoch: 0.0168
142
+ [2026-04-04 12:35:51] Step 3370: loss: 0.9047, grad_norm: 0.1885, learning_rate: 0.0000, epoch: 0.0169
143
+ [2026-04-04 12:37:16] Step 3380: loss: 0.7929, grad_norm: 1.0000, learning_rate: 0.0000, epoch: 0.0169
144
+ [2026-04-04 12:38:41] Step 3390: loss: 0.8338, grad_norm: 0.2012, learning_rate: 0.0000, epoch: 0.0169
145
+ [2026-04-04 12:40:05] Step 3400: loss: 0.8262, grad_norm: 0.2559, learning_rate: 0.0000, epoch: 0.0170
146
+ [2026-04-04 12:41:30] Step 3410: loss: 0.7306, grad_norm: 0.2295, learning_rate: 0.0000, epoch: 0.0170
147
+ [2026-04-04 12:42:55] Step 3420: loss: 0.9324, grad_norm: 0.2520, learning_rate: 0.0000, epoch: 0.0171
148
+ [2026-04-04 12:44:19] Step 3430: loss: 0.7892, grad_norm: 0.1533, learning_rate: 0.0000, epoch: 0.0171
149
+ [2026-04-04 12:45:43] Step 3440: loss: 0.9207, grad_norm: 0.2139, learning_rate: 0.0000, epoch: 0.0172
150
+ [2026-04-04 12:47:07] Step 3450: loss: 0.8582, grad_norm: 0.2539, learning_rate: 0.0000, epoch: 0.0173
151
+ [2026-04-04 12:48:32] Step 3460: loss: 0.8868, grad_norm: 0.3867, learning_rate: 0.0000, epoch: 0.0173
152
+ [2026-04-04 12:49:57] Step 3470: loss: 0.8362, grad_norm: 0.2148, learning_rate: 0.0000, epoch: 0.0174
153
+ [2026-04-04 12:51:21] Step 3480: loss: 0.9078, grad_norm: 0.1855, learning_rate: 0.0000, epoch: 0.0174
154
+ [2026-04-04 12:52:45] Step 3490: loss: 0.8814, grad_norm: 0.1660, learning_rate: 0.0000, epoch: 0.0175
155
+ [2026-04-04 12:54:10] Step 3500: loss: 0.8289, grad_norm: 0.1992, learning_rate: 0.0000, epoch: 0.0175
156
+ [2026-04-04 12:55:35] Step 3510: loss: 0.7498, grad_norm: 0.3477, learning_rate: 0.0000, epoch: 0.0175
157
+ [2026-04-04 12:56:59] Step 3520: loss: 0.8706, grad_norm: 0.1504, learning_rate: 0.0000, epoch: 0.0176
158
+ [2026-04-04 12:58:24] Step 3530: loss: 0.8755, grad_norm: 0.2480, learning_rate: 0.0000, epoch: 0.0176
159
+ [2026-04-04 12:59:48] Step 3540: loss: 0.8941, grad_norm: 0.2041, learning_rate: 0.0000, epoch: 0.0177
160
+ [2026-04-04 13:01:12] Step 3550: loss: 0.9034, grad_norm: 0.1914, learning_rate: 0.0000, epoch: 0.0177
161
+ [2026-04-04 13:02:37] Step 3560: loss: 0.8194, grad_norm: 0.1680, learning_rate: 0.0000, epoch: 0.0178
162
+ [2026-04-04 13:04:01] Step 3570: loss: 0.8267, grad_norm: 0.1807, learning_rate: 0.0000, epoch: 0.0179
163
+ [2026-04-04 13:05:26] Step 3580: loss: 0.8188, grad_norm: 0.1445, learning_rate: 0.0000, epoch: 0.0179
164
+ [2026-04-04 13:06:51] Step 3590: loss: 0.8666, grad_norm: 0.1797, learning_rate: 0.0000, epoch: 0.0180
165
+ [2026-04-04 13:08:15] Step 3600: loss: 0.8775, grad_norm: 0.3203, learning_rate: 0.0000, epoch: 0.0180
166
+ [2026-04-04 13:09:40] Step 3610: loss: 0.7504, grad_norm: 0.2734, learning_rate: 0.0000, epoch: 0.0181
167
+ [2026-04-04 13:11:04] Step 3620: loss: 0.7219, grad_norm: 0.2393, learning_rate: 0.0000, epoch: 0.0181
168
+ [2026-04-04 13:12:28] Step 3630: loss: 0.8402, grad_norm: 0.3105, learning_rate: 0.0000, epoch: 0.0181
169
+ [2026-04-04 13:13:52] Step 3640: loss: 0.7577, grad_norm: 0.2559, learning_rate: 0.0000, epoch: 0.0182
170
+ [2026-04-04 13:15:16] Step 3650: loss: 0.8412, grad_norm: 0.3867, learning_rate: 0.0000, epoch: 0.0182
171
+ [2026-04-04 13:16:41] Step 3660: loss: 0.7960, grad_norm: 0.1533, learning_rate: 0.0000, epoch: 0.0183
172
+ [2026-04-04 13:18:05] Step 3670: loss: 0.9164, grad_norm: 0.1787, learning_rate: 0.0000, epoch: 0.0184
173
+ [2026-04-04 13:19:30] Step 3680: loss: 0.9855, grad_norm: 0.1270, learning_rate: 0.0000, epoch: 0.0184
174
+ [2026-04-04 13:20:54] Step 3690: loss: 0.8332, grad_norm: 0.1455, learning_rate: 0.0000, epoch: 0.0185
175
+ [2026-04-04 13:22:19] Step 3700: loss: 0.8512, grad_norm: 0.1924, learning_rate: 0.0000, epoch: 0.0185
176
+ [2026-04-04 13:23:43] Step 3710: loss: 0.8994, grad_norm: 0.4375, learning_rate: 0.0000, epoch: 0.0186
177
+ [2026-04-04 13:25:08] Step 3720: loss: 0.9205, grad_norm: 0.2314, learning_rate: 0.0000, epoch: 0.0186
178
+ [2026-04-04 13:26:32] Step 3730: loss: 0.8814, grad_norm: 0.2227, learning_rate: 0.0000, epoch: 0.0186
179
+ [2026-04-04 13:27:56] Step 3740: loss: 0.8907, grad_norm: 0.2227, learning_rate: 0.0000, epoch: 0.0187
180
+ [2026-04-04 13:29:20] Step 3750: loss: 0.8737, grad_norm: 0.1475, learning_rate: 0.0000, epoch: 0.0187
181
+ [2026-04-04 13:30:45] Step 3760: loss: 0.8853, grad_norm: 0.1943, learning_rate: 0.0000, epoch: 0.0188
182
+ [2026-04-04 13:32:09] Step 3770: loss: 0.8969, grad_norm: 0.1943, learning_rate: 0.0000, epoch: 0.0188
183
+ [2026-04-04 13:33:34] Step 3780: loss: 0.8080, grad_norm: 0.1992, learning_rate: 0.0000, epoch: 0.0189
184
+ [2026-04-04 13:34:57] Step 3790: loss: 0.7392, grad_norm: 0.1592, learning_rate: 0.0000, epoch: 0.0190
185
+ [2026-04-04 13:36:21] Step 3800: loss: 0.6776, grad_norm: 0.1875, learning_rate: 0.0000, epoch: 0.0190
186
+ [2026-04-04 13:37:46] Step 3810: loss: 0.8414, grad_norm: 0.1836, learning_rate: 0.0000, epoch: 0.0191
187
+ [2026-04-04 13:39:10] Step 3820: loss: 0.8751, grad_norm: 0.1699, learning_rate: 0.0000, epoch: 0.0191
188
+ [2026-04-04 13:40:34] Step 3830: loss: 0.8723, grad_norm: 0.1738, learning_rate: 0.0000, epoch: 0.0192
189
+ [2026-04-04 13:41:59] Step 3840: loss: 0.7960, grad_norm: 0.1758, learning_rate: 0.0000, epoch: 0.0192
190
+ [2026-04-04 13:43:23] Step 3850: loss: 0.9287, grad_norm: 0.1865, learning_rate: 0.0000, epoch: 0.0192
191
+ [2026-04-04 13:44:48] Step 3860: loss: 0.8020, grad_norm: 0.1934, learning_rate: 0.0000, epoch: 0.0193
192
+ [2026-04-04 13:46:12] Step 3870: loss: 0.9291, grad_norm: 0.1758, learning_rate: 0.0000, epoch: 0.0193
193
+ [2026-04-04 13:47:36] Step 3880: loss: 0.8263, grad_norm: 0.1816, learning_rate: 0.0000, epoch: 0.0194
194
+ [2026-04-04 13:49:01] Step 3890: loss: 0.8684, grad_norm: 0.1641, learning_rate: 0.0000, epoch: 0.0194
195
+ [2026-04-04 13:50:26] Step 3900: loss: 0.8842, grad_norm: 0.2363, learning_rate: 0.0000, epoch: 0.0195
196
+ [2026-04-04 13:51:50] Step 3910: loss: 0.9238, grad_norm: 0.1885, learning_rate: 0.0000, epoch: 0.0196
197
+ [2026-04-04 13:53:15] Step 3920: loss: 0.8393, grad_norm: 0.1748, learning_rate: 0.0000, epoch: 0.0196
198
+ [2026-04-04 13:54:40] Step 3930: loss: 0.8357, grad_norm: 0.1436, learning_rate: 0.0000, epoch: 0.0197
199
+ [2026-04-04 13:56:04] Step 3940: loss: 0.8333, grad_norm: 0.2021, learning_rate: 0.0000, epoch: 0.0197
200
+ [2026-04-04 13:57:28] Step 3950: loss: 0.9847, grad_norm: 0.2031, learning_rate: 0.0000, epoch: 0.0198
201
+ [2026-04-04 13:58:52] Step 3960: loss: 0.8540, grad_norm: 0.1670, learning_rate: 0.0000, epoch: 0.0198
202
+ [2026-04-04 14:00:17] Step 3970: loss: 0.7641, grad_norm: 0.1436, learning_rate: 0.0000, epoch: 0.0198
203
+ [2026-04-04 14:01:41] Step 3980: loss: 0.7934, grad_norm: 0.1621, learning_rate: 0.0000, epoch: 0.0199
204
+ [2026-04-04 14:03:05] Step 3990: loss: 0.8577, grad_norm: 0.2070, learning_rate: 0.0000, epoch: 0.0199
205
+ [2026-04-04 14:04:30] Step 4000: loss: 0.8141, grad_norm: 0.1709, learning_rate: 0.0000, epoch: 0.0200
206
+ [2026-04-04 14:07:12] Step 4010: loss: 0.8507, grad_norm: 0.1602, learning_rate: 0.0000, epoch: 0.0200