Hugging Face's logo

PuxAI
/
ACSD_ZeroShot_Benchmark

Model card Files
xet
 Community
PuxAI commited on
Commit
00fcebe
·
verified ·
1 Parent(s): 8e505bf

Upload logs/train_log_Llama-3.1-8B_seed42.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. logs/train_log_Llama-3.1-8B_seed42.json +24 -24
logs/train_log_Llama-3.1-8B_seed42.json CHANGED
@@ -1,80 +1,80 @@
1
  [
2
  {
3
- "loss": 2.3587,
4
- "grad_norm": 1.9088549613952637,
5
  "learning_rate": 0.00018,
6
  "epoch": 0.5,
7
  "step": 10
8
  },
9
  {
10
- "loss": 0.4103,
11
- "grad_norm": 1.15037202835083,
12
  "learning_rate": 0.00018,
13
  "epoch": 1.0,
14
  "step": 20
15
  },
16
  {
17
- "loss": 0.1864,
18
- "grad_norm": 0.5771889090538025,
19
  "learning_rate": 0.0001577777777777778,
20
  "epoch": 1.5,
21
  "step": 30
22
  },
23
  {
24
- "loss": 0.1492,
25
- "grad_norm": 0.7271820902824402,
26
  "learning_rate": 0.00013555555555555556,
27
  "epoch": 2.0,
28
  "step": 40
29
  },
30
  {
31
- "loss": 0.1154,
32
- "grad_norm": 0.589566707611084,
33
  "learning_rate": 0.00011333333333333334,
34
  "epoch": 2.5,
35
  "step": 50
36
  },
37
  {
38
- "loss": 0.1002,
39
- "grad_norm": 0.654466986656189,
40
  "learning_rate": 9.111111111111112e-05,
41
  "epoch": 3.0,
42
  "step": 60
43
  },
44
  {
45
- "loss": 0.0852,
46
- "grad_norm": 0.5283945798873901,
47
  "learning_rate": 6.88888888888889e-05,
48
  "epoch": 3.5,
49
  "step": 70
50
  },
51
  {
52
- "loss": 0.0607,
53
- "grad_norm": 0.7440416812896729,
54
  "learning_rate": 4.666666666666667e-05,
55
  "epoch": 4.0,
56
  "step": 80
57
  },
58
  {
59
- "loss": 0.0487,
60
- "grad_norm": 0.6143506765365601,
61
  "learning_rate": 2.4444444444444445e-05,
62
  "epoch": 4.5,
63
  "step": 90
64
  },
65
  {
66
- "loss": 0.0477,
67
- "grad_norm": 0.8779042959213257,
68
  "learning_rate": 2.2222222222222225e-06,
69
  "epoch": 5.0,
70
  "step": 100
71
  },
72
  {
73
- "train_runtime": 342.2386,
74
- "train_samples_per_second": 18.35,
75
- "train_steps_per_second": 0.292,
76
  "total_flos": 5.098583944986624e+16,
77
- "train_loss": 0.35624706983566284,
78
  "epoch": 5.0,
79
  "step": 100
80
  }
 
1
  [
2
  {
3
+ "loss": 2.3579,
4
+ "grad_norm": 1.9009082317352295,
5
  "learning_rate": 0.00018,
6
  "epoch": 0.5,
7
  "step": 10
8
  },
9
  {
10
+ "loss": 0.4099,
11
+ "grad_norm": 1.1537445783615112,
12
  "learning_rate": 0.00018,
13
  "epoch": 1.0,
14
  "step": 20
15
  },
16
  {
17
+ "loss": 0.1866,
18
+ "grad_norm": 0.5710383057594299,
19
  "learning_rate": 0.0001577777777777778,
20
  "epoch": 1.5,
21
  "step": 30
22
  },
23
  {
24
+ "loss": 0.1493,
25
+ "grad_norm": 0.7199668288230896,
26
  "learning_rate": 0.00013555555555555556,
27
  "epoch": 2.0,
28
  "step": 40
29
  },
30
  {
31
+ "loss": 0.1152,
32
+ "grad_norm": 0.602055549621582,
33
  "learning_rate": 0.00011333333333333334,
34
  "epoch": 2.5,
35
  "step": 50
36
  },
37
  {
38
+ "loss": 0.1005,
39
+ "grad_norm": 0.6442899107933044,
40
  "learning_rate": 9.111111111111112e-05,
41
  "epoch": 3.0,
42
  "step": 60
43
  },
44
  {
45
+ "loss": 0.085,
46
+ "grad_norm": 0.5303047895431519,
47
  "learning_rate": 6.88888888888889e-05,
48
  "epoch": 3.5,
49
  "step": 70
50
  },
51
  {
52
+ "loss": 0.0603,
53
+ "grad_norm": 0.7141255736351013,
54
  "learning_rate": 4.666666666666667e-05,
55
  "epoch": 4.0,
56
  "step": 80
57
  },
58
  {
59
+ "loss": 0.0485,
60
+ "grad_norm": 0.6140527725219727,
61
  "learning_rate": 2.4444444444444445e-05,
62
  "epoch": 4.5,
63
  "step": 90
64
  },
65
  {
66
+ "loss": 0.0476,
67
+ "grad_norm": 0.868701696395874,
68
  "learning_rate": 2.2222222222222225e-06,
69
  "epoch": 5.0,
70
  "step": 100
71
  },
72
  {
73
+ "train_runtime": 351.4958,
74
+ "train_samples_per_second": 17.866,
75
+ "train_steps_per_second": 0.284,
76
  "total_flos": 5.098583944986624e+16,
77
+ "train_loss": 0.35607871145009995,
78
  "epoch": 5.0,
79
  "step": 100
80
  }