Hugging Face's logo

PuxAI
/
ACSD_ZeroShot_Benchmark

Model card Files
xet
 Community
PuxAI commited on
Commit
09abb71
·
verified ·
1 Parent(s): d8013fb

Upload logs/train_log_Gemma3-4B-IT_seed789.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. logs/train_log_Gemma3-4B-IT_seed789.json +23 -23
logs/train_log_Gemma3-4B-IT_seed789.json CHANGED
@@ -1,80 +1,80 @@
1
  [
2
  {
3
- "loss": 4.662,
4
- "grad_norm": 5.247747421264648,
5
  "learning_rate": 0.00018,
6
  "epoch": 0.5,
7
  "step": 10
8
  },
9
  {
10
- "loss": 0.693,
11
- "grad_norm": 2.682288408279419,
12
  "learning_rate": 0.00018,
13
  "epoch": 1.0,
14
  "step": 20
15
  },
16
  {
17
- "loss": 0.2551,
18
- "grad_norm": 0.7315511703491211,
19
  "learning_rate": 0.0001577777777777778,
20
  "epoch": 1.5,
21
  "step": 30
22
  },
23
  {
24
- "loss": 0.1824,
25
- "grad_norm": 1.0467031002044678,
26
  "learning_rate": 0.00013555555555555556,
27
  "epoch": 2.0,
28
  "step": 40
29
  },
30
  {
31
- "loss": 0.1345,
32
- "grad_norm": 0.9925994277000427,
33
  "learning_rate": 0.00011333333333333334,
34
  "epoch": 2.5,
35
  "step": 50
36
  },
37
  {
38
- "loss": 0.1294,
39
- "grad_norm": 0.866705596446991,
40
  "learning_rate": 9.111111111111112e-05,
41
  "epoch": 3.0,
42
  "step": 60
43
  },
44
  {
45
  "loss": 0.1014,
46
- "grad_norm": 0.5562663674354553,
47
  "learning_rate": 6.88888888888889e-05,
48
  "epoch": 3.5,
49
  "step": 70
50
  },
51
  {
52
- "loss": 0.0787,
53
- "grad_norm": 0.7542728185653687,
54
  "learning_rate": 4.666666666666667e-05,
55
  "epoch": 4.0,
56
  "step": 80
57
  },
58
  {
59
- "loss": 0.0665,
60
- "grad_norm": 0.7343875169754028,
61
  "learning_rate": 2.4444444444444445e-05,
62
  "epoch": 4.5,
63
  "step": 90
64
  },
65
  {
66
- "loss": 0.066,
67
- "grad_norm": 1.0010170936584473,
68
  "learning_rate": 2.2222222222222225e-06,
69
  "epoch": 5.0,
70
  "step": 100
71
  },
72
  {
73
- "train_runtime": 281.3874,
74
- "train_samples_per_second": 22.318,
75
- "train_steps_per_second": 0.355,
76
  "total_flos": 2.585479150123776e+16,
77
- "train_loss": 0.6368860471248626,
78
  "epoch": 5.0,
79
  "step": 100
80
  }
 
1
  [
2
  {
3
+ "loss": 4.6746,
4
+ "grad_norm": 5.330068588256836,
5
  "learning_rate": 0.00018,
6
  "epoch": 0.5,
7
  "step": 10
8
  },
9
  {
10
+ "loss": 0.6937,
11
+ "grad_norm": 2.7009994983673096,
12
  "learning_rate": 0.00018,
13
  "epoch": 1.0,
14
  "step": 20
15
  },
16
  {
17
+ "loss": 0.2554,
18
+ "grad_norm": 0.7277244329452515,
19
  "learning_rate": 0.0001577777777777778,
20
  "epoch": 1.5,
21
  "step": 30
22
  },
23
  {
24
+ "loss": 0.183,
25
+ "grad_norm": 1.0641778707504272,
26
  "learning_rate": 0.00013555555555555556,
27
  "epoch": 2.0,
28
  "step": 40
29
  },
30
  {
31
+ "loss": 0.1349,
32
+ "grad_norm": 0.9773860573768616,
33
  "learning_rate": 0.00011333333333333334,
34
  "epoch": 2.5,
35
  "step": 50
36
  },
37
  {
38
+ "loss": 0.129,
39
+ "grad_norm": 0.8620230555534363,
40
  "learning_rate": 9.111111111111112e-05,
41
  "epoch": 3.0,
42
  "step": 60
43
  },
44
  {
45
  "loss": 0.1014,
46
+ "grad_norm": 0.5703953504562378,
47
  "learning_rate": 6.88888888888889e-05,
48
  "epoch": 3.5,
49
  "step": 70
50
  },
51
  {
52
+ "loss": 0.0786,
53
+ "grad_norm": 0.7595603466033936,
54
  "learning_rate": 4.666666666666667e-05,
55
  "epoch": 4.0,
56
  "step": 80
57
  },
58
  {
59
+ "loss": 0.0664,
60
+ "grad_norm": 0.7379135489463806,
61
  "learning_rate": 2.4444444444444445e-05,
62
  "epoch": 4.5,
63
  "step": 90
64
  },
65
  {
66
+ "loss": 0.0657,
67
+ "grad_norm": 0.9689844846725464,
68
  "learning_rate": 2.2222222222222225e-06,
69
  "epoch": 5.0,
70
  "step": 100
71
  },
72
  {
73
+ "train_runtime": 472.0078,
74
+ "train_samples_per_second": 13.305,
75
+ "train_steps_per_second": 0.212,
76
  "total_flos": 2.585479150123776e+16,
77
+ "train_loss": 0.6382734912633896,
78
  "epoch": 5.0,
79
  "step": 100
80
  }