Hugging Face's logo

PuxAI
/
ACSD_ZeroShot_Benchmark

Model card Files
xet
 Community
PuxAI commited on
Commit
35d35d0
·
verified ·
1 Parent(s): e45cb15

Upload logs/train_log_Llama-3.1-8B_seed123.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. logs/train_log_Llama-3.1-8B_seed123.json +22 -22
logs/train_log_Llama-3.1-8B_seed123.json CHANGED
@@ -1,80 +1,80 @@
1
  [
2
  {
3
- "loss": 2.3611,
4
- "grad_norm": 1.9115740060806274,
5
  "learning_rate": 0.00018,
6
  "epoch": 0.5,
7
  "step": 10
8
  },
9
  {
10
- "loss": 0.4042,
11
- "grad_norm": 1.5066324472427368,
12
  "learning_rate": 0.00018,
13
  "epoch": 1.0,
14
  "step": 20
15
  },
16
  {
17
- "loss": 0.1868,
18
- "grad_norm": 0.6329495310783386,
19
  "learning_rate": 0.0001577777777777778,
20
  "epoch": 1.5,
21
  "step": 30
22
  },
23
  {
24
- "loss": 0.153,
25
- "grad_norm": 0.8787748217582703,
26
  "learning_rate": 0.00013555555555555556,
27
  "epoch": 2.0,
28
  "step": 40
29
  },
30
  {
31
- "loss": 0.1163,
32
- "grad_norm": 0.6138646006584167,
33
  "learning_rate": 0.00011333333333333334,
34
  "epoch": 2.5,
35
  "step": 50
36
  },
37
  {
38
- "loss": 0.1006,
39
- "grad_norm": 0.6085129976272583,
40
  "learning_rate": 9.111111111111112e-05,
41
  "epoch": 3.0,
42
  "step": 60
43
  },
44
  {
45
  "loss": 0.0861,
46
- "grad_norm": 0.4830396771430969,
47
  "learning_rate": 6.88888888888889e-05,
48
  "epoch": 3.5,
49
  "step": 70
50
  },
51
  {
52
- "loss": 0.0607,
53
- "grad_norm": 0.9534498453140259,
54
  "learning_rate": 4.666666666666667e-05,
55
  "epoch": 4.0,
56
  "step": 80
57
  },
58
  {
59
  "loss": 0.0493,
60
- "grad_norm": 0.6482242941856384,
61
  "learning_rate": 2.4444444444444445e-05,
62
  "epoch": 4.5,
63
  "step": 90
64
  },
65
  {
66
- "loss": 0.0501,
67
- "grad_norm": 0.8297228217124939,
68
  "learning_rate": 2.2222222222222225e-06,
69
  "epoch": 5.0,
70
  "step": 100
71
  },
72
  {
73
- "train_runtime": 335.1443,
74
- "train_samples_per_second": 18.738,
75
- "train_steps_per_second": 0.298,
76
  "total_flos": 5.098583944986624e+16,
77
- "train_loss": 0.3568024319410324,
78
  "epoch": 5.0,
79
  "step": 100
80
  }
 
1
  [
2
  {
3
+ "loss": 2.3613,
4
+ "grad_norm": 1.9053692817687988,
5
  "learning_rate": 0.00018,
6
  "epoch": 0.5,
7
  "step": 10
8
  },
9
  {
10
+ "loss": 0.4029,
11
+ "grad_norm": 1.454684853553772,
12
  "learning_rate": 0.00018,
13
  "epoch": 1.0,
14
  "step": 20
15
  },
16
  {
17
+ "loss": 0.1859,
18
+ "grad_norm": 0.6330903172492981,
19
  "learning_rate": 0.0001577777777777778,
20
  "epoch": 1.5,
21
  "step": 30
22
  },
23
  {
24
+ "loss": 0.1523,
25
+ "grad_norm": 0.862911581993103,
26
  "learning_rate": 0.00013555555555555556,
27
  "epoch": 2.0,
28
  "step": 40
29
  },
30
  {
31
+ "loss": 0.1158,
32
+ "grad_norm": 0.6093763113021851,
33
  "learning_rate": 0.00011333333333333334,
34
  "epoch": 2.5,
35
  "step": 50
36
  },
37
  {
38
+ "loss": 0.1004,
39
+ "grad_norm": 0.6005483269691467,
40
  "learning_rate": 9.111111111111112e-05,
41
  "epoch": 3.0,
42
  "step": 60
43
  },
44
  {
45
  "loss": 0.0861,
46
+ "grad_norm": 0.47914546728134155,
47
  "learning_rate": 6.88888888888889e-05,
48
  "epoch": 3.5,
49
  "step": 70
50
  },
51
  {
52
+ "loss": 0.0604,
53
+ "grad_norm": 0.9422203302383423,
54
  "learning_rate": 4.666666666666667e-05,
55
  "epoch": 4.0,
56
  "step": 80
57
  },
58
  {
59
  "loss": 0.0493,
60
+ "grad_norm": 0.6497517824172974,
61
  "learning_rate": 2.4444444444444445e-05,
62
  "epoch": 4.5,
63
  "step": 90
64
  },
65
  {
66
+ "loss": 0.0495,
67
+ "grad_norm": 0.820516049861908,
68
  "learning_rate": 2.2222222222222225e-06,
69
  "epoch": 5.0,
70
  "step": 100
71
  },
72
  {
73
+ "train_runtime": 329.7305,
74
+ "train_samples_per_second": 19.046,
75
+ "train_steps_per_second": 0.303,
76
  "total_flos": 5.098583944986624e+16,
77
+ "train_loss": 0.3564116105437279,
78
  "epoch": 5.0,
79
  "step": 100
80
  }