Hugging Face's logo

Reverent
/
llama3-8b-code-extended

Safetensors
llama
Model card Files
xet
 Community
Reverent commited on
Commit
e4e93c4
·
verified ·
1 Parent(s): fb1d257

Training in progress, step 2000

Browse files
Files changed (5) hide show
  1. config.json +36 -0
  2. generation_config.json +9 -0
  3. model.safetensors +3 -0
  4. training_args.bin +3 -0
  5. training_log.txt +207 -0
config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 128000,
8
+ "dtype": "bfloat16",
9
+ "eos_token_id": 128001,
10
+ "head_dim": 128,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 4096,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 14336,
15
+ "max_position_embeddings": 131072,
16
+ "mlp_bias": false,
17
+ "model_type": "llama",
18
+ "num_attention_heads": 32,
19
+ "num_hidden_layers": 32,
20
+ "num_key_value_heads": 8,
21
+ "pad_token_id": null,
22
+ "pretraining_tp": 1,
23
+ "rms_norm_eps": 1e-05,
24
+ "rope_parameters": {
25
+ "factor": 8.0,
26
+ "high_freq_factor": 4.0,
27
+ "low_freq_factor": 1.0,
28
+ "original_max_position_embeddings": 8192,
29
+ "rope_theta": 500000.0,
30
+ "rope_type": "llama3"
31
+ },
32
+ "tie_word_embeddings": false,
33
+ "transformers_version": "5.2.0",
34
+ "use_cache": false,
35
+ "vocab_size": 128256
36
+ }
generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 128000,
4
+ "do_sample": true,
5
+ "eos_token_id": 128001,
6
+ "temperature": 0.6,
7
+ "top_p": 0.9,
8
+ "transformers_version": "5.2.0"
9
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ef214873b47923bbff3b6a16bda1b3cfe344d019708ac5f65f80c2a3eaf98b7
3
+ size 16060556616
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:acd33fa241d0c5dd6160e08ee46e01513ae5bebee0f9534d3642432eb735bdad
3
+ size 5265
training_log.txt ADDED
@@ -0,0 +1,207 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ ==================================================
3
+ Training started at: 2026-03-19 01:25:13
4
+ ==================================================
5
+
6
+ [2026-03-19 01:25:32] Step 1: loss: 0.4856, grad_norm: 0.3262, learning_rate: 0.0000, epoch: 0.0000
7
+ [2026-03-19 01:26:48] Step 10: loss: 0.4935, grad_norm: 0.3594, learning_rate: 0.0000, epoch: 0.0001
8
+ [2026-03-19 01:28:14] Step 20: loss: 0.7041, grad_norm: 0.3750, learning_rate: 0.0000, epoch: 0.0001
9
+ [2026-03-19 01:29:41] Step 30: loss: 0.7840, grad_norm: 0.3438, learning_rate: 0.0000, epoch: 0.0001
10
+ [2026-03-19 01:31:07] Step 40: loss: 0.7918, grad_norm: 0.3359, learning_rate: 0.0000, epoch: 0.0002
11
+ [2026-03-19 01:32:33] Step 50: loss: 0.7794, grad_norm: 0.2852, learning_rate: 0.0000, epoch: 0.0003
12
+ [2026-03-19 01:34:00] Step 60: loss: 0.6740, grad_norm: 0.3633, learning_rate: 0.0000, epoch: 0.0003
13
+ [2026-03-19 01:35:26] Step 70: loss: 0.8364, grad_norm: 0.2793, learning_rate: 0.0000, epoch: 0.0003
14
+ [2026-03-19 01:36:52] Step 80: loss: 0.8728, grad_norm: 0.2754, learning_rate: 0.0000, epoch: 0.0004
15
+ [2026-03-19 01:38:18] Step 90: loss: 0.8064, grad_norm: 0.2432, learning_rate: 0.0000, epoch: 0.0004
16
+ [2026-03-19 01:39:45] Step 100: loss: 0.8027, grad_norm: 0.2559, learning_rate: 0.0000, epoch: 0.0005
17
+ [2026-03-19 01:41:12] Step 110: loss: 0.7824, grad_norm: 0.2754, learning_rate: 0.0000, epoch: 0.0006
18
+ [2026-03-19 01:42:38] Step 120: loss: 0.6427, grad_norm: 0.2461, learning_rate: 0.0000, epoch: 0.0006
19
+ [2026-03-19 01:44:04] Step 130: loss: 0.7531, grad_norm: 0.2412, learning_rate: 0.0000, epoch: 0.0006
20
+ [2026-03-19 01:45:30] Step 140: loss: 0.7714, grad_norm: 0.3164, learning_rate: 0.0000, epoch: 0.0007
21
+ [2026-03-19 01:46:57] Step 150: loss: 0.6974, grad_norm: 0.3281, learning_rate: 0.0000, epoch: 0.0008
22
+ [2026-03-19 01:48:23] Step 160: loss: 0.8218, grad_norm: 0.2617, learning_rate: 0.0000, epoch: 0.0008
23
+ [2026-03-19 01:49:50] Step 170: loss: 0.7847, grad_norm: 0.2930, learning_rate: 0.0000, epoch: 0.0008
24
+ [2026-03-19 01:51:16] Step 180: loss: 0.5521, grad_norm: 0.2832, learning_rate: 0.0000, epoch: 0.0009
25
+ [2026-03-19 01:52:42] Step 190: loss: 0.7037, grad_norm: 0.2500, learning_rate: 0.0000, epoch: 0.0009
26
+ [2026-03-19 01:54:09] Step 200: loss: 0.6810, grad_norm: 0.2852, learning_rate: 0.0000, epoch: 0.0010
27
+ [2026-03-19 01:55:34] Step 210: loss: 1.0168, grad_norm: 0.2871, learning_rate: 0.0000, epoch: 0.0010
28
+ [2026-03-19 01:57:00] Step 220: loss: 0.6432, grad_norm: 0.3945, learning_rate: 0.0000, epoch: 0.0011
29
+ [2026-03-19 01:58:26] Step 230: loss: 0.6609, grad_norm: 0.2471, learning_rate: 0.0000, epoch: 0.0011
30
+ [2026-03-19 01:59:53] Step 240: loss: 0.7392, grad_norm: 0.3086, learning_rate: 0.0000, epoch: 0.0012
31
+ [2026-03-19 02:01:20] Step 250: loss: 0.5720, grad_norm: 0.2393, learning_rate: 0.0000, epoch: 0.0013
32
+ [2026-03-19 02:02:46] Step 260: loss: 0.6996, grad_norm: 0.3613, learning_rate: 0.0000, epoch: 0.0013
33
+ [2026-03-19 02:04:13] Step 270: loss: 0.7542, grad_norm: 0.3945, learning_rate: 0.0000, epoch: 0.0014
34
+ [2026-03-19 02:05:40] Step 280: loss: 0.6788, grad_norm: 0.2246, learning_rate: 0.0000, epoch: 0.0014
35
+ [2026-03-19 02:07:05] Step 290: loss: 0.7190, grad_norm: 0.2520, learning_rate: 0.0000, epoch: 0.0014
36
+ [2026-03-19 02:08:31] Step 300: loss: 0.6371, grad_norm: 0.3164, learning_rate: 0.0000, epoch: 0.0015
37
+ [2026-03-19 02:09:57] Step 310: loss: 0.8777, grad_norm: 0.3281, learning_rate: 0.0000, epoch: 0.0015
38
+ [2026-03-19 02:11:23] Step 320: loss: 0.7312, grad_norm: 0.2402, learning_rate: 0.0000, epoch: 0.0016
39
+ [2026-03-19 02:12:50] Step 330: loss: 0.6872, grad_norm: 0.2383, learning_rate: 0.0000, epoch: 0.0016
40
+ [2026-03-19 02:14:16] Step 340: loss: 0.7424, grad_norm: 0.3457, learning_rate: 0.0000, epoch: 0.0017
41
+ [2026-03-19 02:15:42] Step 350: loss: 0.6354, grad_norm: 0.2500, learning_rate: 0.0000, epoch: 0.0018
42
+ [2026-03-19 02:17:08] Step 360: loss: 0.6052, grad_norm: 0.5391, learning_rate: 0.0000, epoch: 0.0018
43
+ [2026-03-19 02:18:35] Step 370: loss: 0.7459, grad_norm: 0.2871, learning_rate: 0.0000, epoch: 0.0019
44
+ [2026-03-19 02:20:01] Step 380: loss: 0.6992, grad_norm: 0.2676, learning_rate: 0.0000, epoch: 0.0019
45
+ [2026-03-19 02:21:28] Step 390: loss: 0.6429, grad_norm: 0.3164, learning_rate: 0.0000, epoch: 0.0019
46
+ [2026-03-19 02:22:54] Step 400: loss: 0.7400, grad_norm: 0.2451, learning_rate: 0.0000, epoch: 0.0020
47
+ [2026-03-19 02:24:20] Step 410: loss: 0.5856, grad_norm: 0.2871, learning_rate: 0.0000, epoch: 0.0021
48
+ [2026-03-19 02:25:46] Step 420: loss: 0.5673, grad_norm: 0.3047, learning_rate: 0.0000, epoch: 0.0021
49
+ [2026-03-19 02:27:12] Step 430: loss: 0.6554, grad_norm: 0.2324, learning_rate: 0.0000, epoch: 0.0022
50
+ [2026-03-19 02:28:39] Step 440: loss: 0.7193, grad_norm: 0.3008, learning_rate: 0.0000, epoch: 0.0022
51
+ [2026-03-19 02:30:04] Step 450: loss: 0.8350, grad_norm: 0.4062, learning_rate: 0.0000, epoch: 0.0022
52
+ [2026-03-19 02:31:31] Step 460: loss: 0.6407, grad_norm: 0.2500, learning_rate: 0.0000, epoch: 0.0023
53
+ [2026-03-19 02:32:57] Step 470: loss: 0.7993, grad_norm: 0.2754, learning_rate: 0.0000, epoch: 0.0024
54
+ [2026-03-19 02:34:23] Step 480: loss: 0.6173, grad_norm: 0.2637, learning_rate: 0.0000, epoch: 0.0024
55
+ [2026-03-19 02:35:49] Step 490: loss: 0.6819, grad_norm: 0.2988, learning_rate: 0.0000, epoch: 0.0024
56
+ [2026-03-19 02:37:15] Step 500: loss: 0.8780, grad_norm: 0.3359, learning_rate: 0.0000, epoch: 0.0025
57
+ [2026-03-19 02:38:41] Step 510: loss: 0.6892, grad_norm: 0.2139, learning_rate: 0.0000, epoch: 0.0026
58
+ [2026-03-19 02:40:07] Step 520: loss: 0.6315, grad_norm: 0.3008, learning_rate: 0.0000, epoch: 0.0026
59
+ [2026-03-19 02:41:33] Step 530: loss: 0.6788, grad_norm: 0.2637, learning_rate: 0.0000, epoch: 0.0027
60
+ [2026-03-19 02:43:00] Step 540: loss: 0.6937, grad_norm: 0.2520, learning_rate: 0.0000, epoch: 0.0027
61
+ [2026-03-19 02:44:26] Step 550: loss: 0.5224, grad_norm: 0.2236, learning_rate: 0.0000, epoch: 0.0027
62
+ [2026-03-19 02:45:52] Step 560: loss: 0.7166, grad_norm: 0.2480, learning_rate: 0.0000, epoch: 0.0028
63
+ [2026-03-19 02:47:18] Step 570: loss: 0.7413, grad_norm: 0.2715, learning_rate: 0.0000, epoch: 0.0029
64
+ [2026-03-19 02:48:45] Step 580: loss: 0.6571, grad_norm: 0.2617, learning_rate: 0.0000, epoch: 0.0029
65
+ [2026-03-19 02:50:11] Step 590: loss: 0.6766, grad_norm: 0.2812, learning_rate: 0.0000, epoch: 0.0029
66
+ [2026-03-19 02:51:38] Step 600: loss: 0.6363, grad_norm: 0.2734, learning_rate: 0.0000, epoch: 0.0030
67
+ [2026-03-19 02:53:05] Step 610: loss: 0.6390, grad_norm: 0.3066, learning_rate: 0.0000, epoch: 0.0031
68
+ [2026-03-19 02:54:30] Step 620: loss: 1.1953, grad_norm: 1.7109, learning_rate: 0.0000, epoch: 0.0031
69
+ [2026-03-19 02:55:57] Step 630: loss: 0.5954, grad_norm: 0.2539, learning_rate: 0.0000, epoch: 0.0032
70
+ [2026-03-19 02:57:24] Step 640: loss: 0.5988, grad_norm: 0.2676, learning_rate: 0.0000, epoch: 0.0032
71
+ [2026-03-19 02:58:50] Step 650: loss: 0.6157, grad_norm: 0.2129, learning_rate: 0.0000, epoch: 0.0032
72
+ [2026-03-19 03:00:16] Step 660: loss: 0.5548, grad_norm: 0.2715, learning_rate: 0.0000, epoch: 0.0033
73
+ [2026-03-19 03:01:43] Step 670: loss: 0.7118, grad_norm: 0.2363, learning_rate: 0.0000, epoch: 0.0034
74
+ [2026-03-19 03:03:08] Step 680: loss: 0.5809, grad_norm: 0.3633, learning_rate: 0.0000, epoch: 0.0034
75
+ [2026-03-19 03:04:34] Step 690: loss: 0.7001, grad_norm: 0.2422, learning_rate: 0.0000, epoch: 0.0034
76
+ [2026-03-19 03:06:01] Step 700: loss: 0.5441, grad_norm: 0.2334, learning_rate: 0.0000, epoch: 0.0035
77
+ [2026-03-19 03:07:27] Step 710: loss: 0.4941, grad_norm: 0.1416, learning_rate: 0.0000, epoch: 0.0036
78
+ [2026-03-19 03:08:53] Step 720: loss: 0.4908, grad_norm: 0.1709, learning_rate: 0.0000, epoch: 0.0036
79
+ [2026-03-19 03:10:19] Step 730: loss: 0.6397, grad_norm: 0.2451, learning_rate: 0.0000, epoch: 0.0037
80
+ [2026-03-19 03:11:45] Step 740: loss: 0.6564, grad_norm: 0.2812, learning_rate: 0.0000, epoch: 0.0037
81
+ [2026-03-19 03:13:12] Step 750: loss: 0.6409, grad_norm: 0.2969, learning_rate: 0.0000, epoch: 0.0037
82
+ [2026-03-19 03:14:38] Step 760: loss: 0.6319, grad_norm: 0.2422, learning_rate: 0.0000, epoch: 0.0038
83
+ [2026-03-19 03:16:04] Step 770: loss: 0.8398, grad_norm: 0.4004, learning_rate: 0.0000, epoch: 0.0039
84
+ [2026-03-19 03:17:29] Step 780: loss: 0.5221, grad_norm: 0.2695, learning_rate: 0.0000, epoch: 0.0039
85
+ [2026-03-19 03:18:56] Step 790: loss: 0.6341, grad_norm: 0.4512, learning_rate: 0.0000, epoch: 0.0040
86
+ [2026-03-19 03:20:22] Step 800: loss: 0.6544, grad_norm: 0.3086, learning_rate: 0.0000, epoch: 0.0040
87
+ [2026-03-19 03:21:48] Step 810: loss: 0.6019, grad_norm: 0.1855, learning_rate: 0.0000, epoch: 0.0040
88
+ [2026-03-19 03:23:15] Step 820: loss: 0.6041, grad_norm: 0.2373, learning_rate: 0.0000, epoch: 0.0041
89
+ [2026-03-19 03:24:39] Step 830: loss: 1.0993, grad_norm: 1.2734, learning_rate: 0.0000, epoch: 0.0042
90
+ [2026-03-19 03:26:06] Step 840: loss: 0.7238, grad_norm: 0.3281, learning_rate: 0.0000, epoch: 0.0042
91
+ [2026-03-19 03:27:31] Step 850: loss: 0.6816, grad_norm: 0.3613, learning_rate: 0.0000, epoch: 0.0043
92
+ [2026-03-19 03:28:58] Step 860: loss: 0.6853, grad_norm: 0.2617, learning_rate: 0.0000, epoch: 0.0043
93
+ [2026-03-19 03:30:25] Step 870: loss: 0.6672, grad_norm: 0.2305, learning_rate: 0.0000, epoch: 0.0043
94
+ [2026-03-19 03:31:52] Step 880: loss: 0.6758, grad_norm: 0.2129, learning_rate: 0.0000, epoch: 0.0044
95
+ [2026-03-19 03:33:18] Step 890: loss: 0.6182, grad_norm: 0.1875, learning_rate: 0.0000, epoch: 0.0044
96
+ [2026-03-19 03:34:43] Step 900: loss: 0.5506, grad_norm: 0.2275, learning_rate: 0.0000, epoch: 0.0045
97
+ [2026-03-19 03:36:10] Step 910: loss: 0.5744, grad_norm: 2.0938, learning_rate: 0.0000, epoch: 0.0046
98
+ [2026-03-19 03:37:36] Step 920: loss: 0.5925, grad_norm: 0.2559, learning_rate: 0.0000, epoch: 0.0046
99
+ [2026-03-19 03:39:03] Step 930: loss: 0.6736, grad_norm: 0.2119, learning_rate: 0.0000, epoch: 0.0046
100
+ [2026-03-19 03:40:28] Step 940: loss: 0.5646, grad_norm: 0.9492, learning_rate: 0.0000, epoch: 0.0047
101
+ [2026-03-19 03:41:55] Step 950: loss: 0.7041, grad_norm: 0.2021, learning_rate: 0.0000, epoch: 0.0047
102
+ [2026-03-19 03:43:21] Step 960: loss: 0.6414, grad_norm: 0.2656, learning_rate: 0.0000, epoch: 0.0048
103
+ [2026-03-19 03:44:48] Step 970: loss: 0.6892, grad_norm: 0.2617, learning_rate: 0.0000, epoch: 0.0049
104
+ [2026-03-19 03:46:15] Step 980: loss: 0.6529, grad_norm: 3.2188, learning_rate: 0.0000, epoch: 0.0049
105
+ [2026-03-19 03:47:41] Step 990: loss: 0.7230, grad_norm: 0.3809, learning_rate: 0.0000, epoch: 0.0050
106
+ [2026-03-19 03:49:07] Step 1000: loss: 0.8274, grad_norm: 0.3379, learning_rate: 0.0000, epoch: 0.0050
107
+ [2026-03-19 03:50:33] Step 1010: loss: 0.7022, grad_norm: 0.2031, learning_rate: 0.0000, epoch: 0.0050
108
+ [2026-03-19 03:52:00] Step 1020: loss: 0.6402, grad_norm: 0.2617, learning_rate: 0.0000, epoch: 0.0051
109
+ [2026-03-19 03:53:27] Step 1030: loss: 0.7157, grad_norm: 0.2178, learning_rate: 0.0000, epoch: 0.0052
110
+ [2026-03-19 03:54:53] Step 1040: loss: 0.6922, grad_norm: 0.3047, learning_rate: 0.0000, epoch: 0.0052
111
+ [2026-03-19 03:56:19] Step 1050: loss: 0.7176, grad_norm: 0.2168, learning_rate: 0.0000, epoch: 0.0053
112
+ [2026-03-19 03:57:46] Step 1060: loss: 0.6401, grad_norm: 0.2617, learning_rate: 0.0000, epoch: 0.0053
113
+ [2026-03-19 03:59:12] Step 1070: loss: 0.6385, grad_norm: 0.1963, learning_rate: 0.0000, epoch: 0.0053
114
+ [2026-03-19 04:00:38] Step 1080: loss: 0.6388, grad_norm: 0.3438, learning_rate: 0.0000, epoch: 0.0054
115
+ [2026-03-19 04:02:05] Step 1090: loss: 0.6234, grad_norm: 0.2061, learning_rate: 0.0000, epoch: 0.0054
116
+ [2026-03-19 04:03:31] Step 1100: loss: 0.6467, grad_norm: 0.2471, learning_rate: 0.0000, epoch: 0.0055
117
+ [2026-03-19 04:04:57] Step 1110: loss: 0.5168, grad_norm: 0.3711, learning_rate: 0.0000, epoch: 0.0056
118
+ [2026-03-19 04:06:24] Step 1120: loss: 0.5770, grad_norm: 0.2139, learning_rate: 0.0000, epoch: 0.0056
119
+ [2026-03-19 04:07:50] Step 1130: loss: 0.8165, grad_norm: 0.2402, learning_rate: 0.0000, epoch: 0.0056
120
+ [2026-03-19 04:09:17] Step 1140: loss: 0.5314, grad_norm: 0.1660, learning_rate: 0.0000, epoch: 0.0057
121
+ [2026-03-19 04:10:41] Step 1150: loss: 0.7250, grad_norm: 0.3027, learning_rate: 0.0000, epoch: 0.0057
122
+ [2026-03-19 04:12:08] Step 1160: loss: 0.6012, grad_norm: 0.2295, learning_rate: 0.0000, epoch: 0.0058
123
+ [2026-03-19 04:13:35] Step 1170: loss: 0.6610, grad_norm: 0.2100, learning_rate: 0.0000, epoch: 0.0059
124
+ [2026-03-19 04:15:01] Step 1180: loss: 0.6514, grad_norm: 0.3086, learning_rate: 0.0000, epoch: 0.0059
125
+ [2026-03-19 04:16:27] Step 1190: loss: 0.8083, grad_norm: 0.2559, learning_rate: 0.0000, epoch: 0.0060
126
+ [2026-03-19 04:17:54] Step 1200: loss: 0.5940, grad_norm: 0.3457, learning_rate: 0.0000, epoch: 0.0060
127
+ [2026-03-19 04:19:20] Step 1210: loss: 0.7262, grad_norm: 1.1797, learning_rate: 0.0000, epoch: 0.0060
128
+ [2026-03-19 04:20:46] Step 1220: loss: 0.5149, grad_norm: 0.2432, learning_rate: 0.0000, epoch: 0.0061
129
+ [2026-03-19 04:22:13] Step 1230: loss: 0.6235, grad_norm: 0.2539, learning_rate: 0.0000, epoch: 0.0062
130
+ [2026-03-19 04:23:39] Step 1240: loss: 0.7446, grad_norm: 0.3516, learning_rate: 0.0000, epoch: 0.0062
131
+ [2026-03-19 04:25:05] Step 1250: loss: 0.7446, grad_norm: 0.2695, learning_rate: 0.0000, epoch: 0.0063
132
+ [2026-03-19 04:26:31] Step 1260: loss: 0.6432, grad_norm: 0.2598, learning_rate: 0.0000, epoch: 0.0063
133
+ [2026-03-19 04:27:58] Step 1270: loss: 0.7489, grad_norm: 0.2471, learning_rate: 0.0000, epoch: 0.0063
134
+ [2026-03-19 04:29:25] Step 1280: loss: 0.6287, grad_norm: 0.2793, learning_rate: 0.0000, epoch: 0.0064
135
+ [2026-03-19 04:30:52] Step 1290: loss: 0.7105, grad_norm: 5.0938, learning_rate: 0.0000, epoch: 0.0065
136
+ [2026-03-19 04:32:18] Step 1300: loss: 0.5346, grad_norm: 0.1963, learning_rate: 0.0000, epoch: 0.0065
137
+ [2026-03-19 04:33:44] Step 1310: loss: 0.6538, grad_norm: 0.2148, learning_rate: 0.0000, epoch: 0.0066
138
+ [2026-03-19 04:35:10] Step 1320: loss: 0.6807, grad_norm: 0.2051, learning_rate: 0.0000, epoch: 0.0066
139
+ [2026-03-19 04:36:36] Step 1330: loss: 0.5476, grad_norm: 0.2656, learning_rate: 0.0000, epoch: 0.0066
140
+ [2026-03-19 04:38:04] Step 1340: loss: 0.6003, grad_norm: 0.2441, learning_rate: 0.0000, epoch: 0.0067
141
+ [2026-03-19 04:39:30] Step 1350: loss: 0.5730, grad_norm: 0.2402, learning_rate: 0.0000, epoch: 0.0067
142
+ [2026-03-19 04:40:56] Step 1360: loss: 0.6194, grad_norm: 0.2754, learning_rate: 0.0000, epoch: 0.0068
143
+ [2026-03-19 04:42:23] Step 1370: loss: 0.5074, grad_norm: 0.2148, learning_rate: 0.0000, epoch: 0.0069
144
+ [2026-03-19 04:43:48] Step 1380: loss: 0.6297, grad_norm: 0.7695, learning_rate: 0.0000, epoch: 0.0069
145
+ [2026-03-19 04:45:15] Step 1390: loss: 0.6137, grad_norm: 0.3750, learning_rate: 0.0000, epoch: 0.0069
146
+ [2026-03-19 04:46:42] Step 1400: loss: 0.6698, grad_norm: 0.2949, learning_rate: 0.0000, epoch: 0.0070
147
+ [2026-03-19 04:48:08] Step 1410: loss: 0.7613, grad_norm: 0.2969, learning_rate: 0.0000, epoch: 0.0070
148
+ [2026-03-19 04:49:33] Step 1420: loss: 0.6525, grad_norm: 0.5078, learning_rate: 0.0000, epoch: 0.0071
149
+ [2026-03-19 04:50:58] Step 1430: loss: 0.7535, grad_norm: 0.3164, learning_rate: 0.0000, epoch: 0.0072
150
+ [2026-03-19 04:52:25] Step 1440: loss: 0.6901, grad_norm: 0.3398, learning_rate: 0.0000, epoch: 0.0072
151
+ [2026-03-19 04:53:51] Step 1450: loss: 0.6692, grad_norm: 0.2490, learning_rate: 0.0000, epoch: 0.0073
152
+ [2026-03-19 04:55:17] Step 1460: loss: 0.6835, grad_norm: 0.2500, learning_rate: 0.0000, epoch: 0.0073
153
+ [2026-03-19 04:56:42] Step 1470: loss: 1.1404, grad_norm: 0.3672, learning_rate: 0.0000, epoch: 0.0073
154
+ [2026-03-19 04:58:07] Step 1480: loss: 1.2603, grad_norm: 0.3770, learning_rate: 0.0000, epoch: 0.0074
155
+ [2026-03-19 04:59:31] Step 1490: loss: 1.0873, grad_norm: 0.4590, learning_rate: 0.0000, epoch: 0.0075
156
+ [2026-03-19 05:00:55] Step 1500: loss: 1.1580, grad_norm: 0.3281, learning_rate: 0.0000, epoch: 0.0075
157
+ [2026-03-19 05:02:19] Step 1510: loss: 1.1492, grad_norm: 0.4199, learning_rate: 0.0000, epoch: 0.0076
158
+ [2026-03-19 05:03:43] Step 1520: loss: 1.0729, grad_norm: 0.3594, learning_rate: 0.0000, epoch: 0.0076
159
+ [2026-03-19 05:05:08] Step 1530: loss: 1.0263, grad_norm: 1.7109, learning_rate: 0.0000, epoch: 0.0076
160
+ [2026-03-19 05:06:32] Step 1540: loss: 1.0834, grad_norm: 0.2773, learning_rate: 0.0000, epoch: 0.0077
161
+ [2026-03-19 05:07:57] Step 1550: loss: 1.1309, grad_norm: 0.2969, learning_rate: 0.0000, epoch: 0.0077
162
+ [2026-03-19 05:09:21] Step 1560: loss: 1.0331, grad_norm: 0.8242, learning_rate: 0.0000, epoch: 0.0078
163
+ [2026-03-19 05:10:46] Step 1570: loss: 0.9899, grad_norm: 0.3379, learning_rate: 0.0000, epoch: 0.0078
164
+ [2026-03-19 05:12:10] Step 1580: loss: 1.0099, grad_norm: 0.3008, learning_rate: 0.0000, epoch: 0.0079
165
+ [2026-03-19 05:13:34] Step 1590: loss: 1.0297, grad_norm: 0.3770, learning_rate: 0.0000, epoch: 0.0080
166
+ [2026-03-19 05:14:59] Step 1600: loss: 1.0328, grad_norm: 9.0000, learning_rate: 0.0000, epoch: 0.0080
167
+ [2026-03-19 05:16:23] Step 1610: loss: 0.9803, grad_norm: 0.4141, learning_rate: 0.0000, epoch: 0.0080
168
+ [2026-03-19 05:17:48] Step 1620: loss: 1.1971, grad_norm: 0.7773, learning_rate: 0.0000, epoch: 0.0081
169
+ [2026-03-19 05:19:13] Step 1630: loss: 1.4155, grad_norm: 0.3398, learning_rate: 0.0000, epoch: 0.0081
170
+ [2026-03-19 05:20:37] Step 1640: loss: 1.3593, grad_norm: 0.5391, learning_rate: 0.0000, epoch: 0.0082
171
+ [2026-03-19 05:22:02] Step 1650: loss: 1.3674, grad_norm: 0.5938, learning_rate: 0.0000, epoch: 0.0083
172
+ [2026-03-19 05:23:27] Step 1660: loss: 1.3553, grad_norm: 0.4199, learning_rate: 0.0000, epoch: 0.0083
173
+ [2026-03-19 05:24:52] Step 1670: loss: 1.3004, grad_norm: 0.3340, learning_rate: 0.0000, epoch: 0.0083
174
+ [2026-03-19 05:26:17] Step 1680: loss: 1.2074, grad_norm: 0.3848, learning_rate: 0.0000, epoch: 0.0084
175
+ [2026-03-19 05:27:42] Step 1690: loss: 1.3860, grad_norm: 0.4629, learning_rate: 0.0000, epoch: 0.0084
176
+ [2026-03-19 05:29:08] Step 1700: loss: 1.3159, grad_norm: 0.7422, learning_rate: 0.0000, epoch: 0.0085
177
+ [2026-03-19 05:30:33] Step 1710: loss: 1.3765, grad_norm: 0.3418, learning_rate: 0.0000, epoch: 0.0086
178
+ [2026-03-19 05:31:58] Step 1720: loss: 1.3761, grad_norm: 2.1094, learning_rate: 0.0000, epoch: 0.0086
179
+ [2026-03-19 05:33:23] Step 1730: loss: 1.2393, grad_norm: 0.9492, learning_rate: 0.0000, epoch: 0.0086
180
+ [2026-03-19 05:34:47] Step 1740: loss: 1.4905, grad_norm: 1.8516, learning_rate: 0.0000, epoch: 0.0087
181
+ [2026-03-19 05:36:13] Step 1750: loss: 1.3010, grad_norm: 0.4141, learning_rate: 0.0000, epoch: 0.0088
182
+ [2026-03-19 05:37:37] Step 1760: loss: 1.8035, grad_norm: 0.3691, learning_rate: 0.0000, epoch: 0.0088
183
+ [2026-03-19 05:39:02] Step 1770: loss: 1.3515, grad_norm: 0.6133, learning_rate: 0.0000, epoch: 0.0089
184
+ [2026-03-19 05:40:27] Step 1780: loss: 1.1162, grad_norm: 0.7539, learning_rate: 0.0000, epoch: 0.0089
185
+ [2026-03-19 05:41:52] Step 1790: loss: 1.3553, grad_norm: 0.5391, learning_rate: 0.0000, epoch: 0.0089
186
+ [2026-03-19 05:43:18] Step 1800: loss: 1.2487, grad_norm: 0.3027, learning_rate: 0.0000, epoch: 0.0090
187
+ [2026-03-19 05:44:43] Step 1810: loss: 1.2575, grad_norm: 0.6680, learning_rate: 0.0000, epoch: 0.0091
188
+ [2026-03-19 05:46:08] Step 1820: loss: 1.1809, grad_norm: 0.2393, learning_rate: 0.0000, epoch: 0.0091
189
+ [2026-03-19 05:47:33] Step 1830: loss: 1.1636, grad_norm: 0.4277, learning_rate: 0.0000, epoch: 0.0092
190
+ [2026-03-19 05:48:58] Step 1840: loss: 1.1522, grad_norm: 0.2812, learning_rate: 0.0000, epoch: 0.0092
191
+ [2026-03-19 05:50:23] Step 1850: loss: 1.0624, grad_norm: 0.8398, learning_rate: 0.0000, epoch: 0.0092
192
+ [2026-03-19 05:51:48] Step 1860: loss: 1.2957, grad_norm: 0.4453, learning_rate: 0.0000, epoch: 0.0093
193
+ [2026-03-19 05:53:13] Step 1870: loss: 1.1482, grad_norm: 3.4688, learning_rate: 0.0000, epoch: 0.0094
194
+ [2026-03-19 05:54:38] Step 1880: loss: 1.2779, grad_norm: 0.4355, learning_rate: 0.0000, epoch: 0.0094
195
+ [2026-03-19 05:56:03] Step 1890: loss: 1.1939, grad_norm: 0.5352, learning_rate: 0.0000, epoch: 0.0095
196
+ [2026-03-19 05:57:27] Step 1900: loss: 1.1707, grad_norm: 0.2949, learning_rate: 0.0000, epoch: 0.0095
197
+ [2026-03-19 05:58:52] Step 1910: loss: 1.5939, grad_norm: 1.4219, learning_rate: 0.0000, epoch: 0.0095
198
+ [2026-03-19 06:00:18] Step 1920: loss: 1.1586, grad_norm: 0.4023, learning_rate: 0.0000, epoch: 0.0096
199
+ [2026-03-19 06:01:42] Step 1930: loss: 1.4298, grad_norm: 0.2773, learning_rate: 0.0000, epoch: 0.0097
200
+ [2026-03-19 06:03:08] Step 1940: loss: 1.1427, grad_norm: 0.3516, learning_rate: 0.0000, epoch: 0.0097
201
+ [2026-03-19 06:04:32] Step 1950: loss: 1.1448, grad_norm: 0.6992, learning_rate: 0.0000, epoch: 0.0097
202
+ [2026-03-19 06:05:57] Step 1960: loss: 1.3666, grad_norm: 0.5195, learning_rate: 0.0000, epoch: 0.0098
203
+ [2026-03-19 06:07:22] Step 1970: loss: 1.6696, grad_norm: 2.7031, learning_rate: 0.0000, epoch: 0.0098
204
+ [2026-03-19 06:08:48] Step 1980: loss: 3.2356, grad_norm: 1.0781, learning_rate: 0.0000, epoch: 0.0099
205
+ [2026-03-19 06:10:13] Step 1990: loss: 2.4971, grad_norm: 4.3125, learning_rate: 0.0000, epoch: 0.0100
206
+ [2026-03-19 06:11:39] Step 2000: loss: 2.5417, grad_norm: 0.8555, learning_rate: 0.0000, epoch: 0.0100
207
+ [2026-03-19 06:14:18] Step 2010: loss: 2.8378, grad_norm: 1.7422, learning_rate: 0.0000, epoch: 0.0100