Hugging Face's logo

rizkyjun
/
bloom-1b-finetuned-aings-adapters-non-delimiter-2

PEFT
TensorBoard
Safetensors
Model card Files Metrics Community
bloom-1b-finetuned-aings-adapters-non-delimiter-2
File size: 2,917 Bytes 
ad0a28d
b72c7a9
 
 
ad0a28d
b72c7a9
ad0a28d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
43eb100
 
 
 
 
 
 
 
 
 
 
 
 
 
d0b4dc1
 
 
 
 
 
 
 
 
 
 
 
 
 
de7e553
 
 
 
 
 
 
 
 
 
 
 
 
 
7bdcf5e
 
 
 
 
 
 
 
 
 
 
 
 
 
4e1e5c0
 
 
 
 
 
 
 
 
 
 
 
 
 
6b1db44
 
 
 
 
 
 
 
 
 
 
 
 
 
b72c7a9
 
 
 
 
 
 
 
 
 
 
 
 
 
ad0a28d
 
 
 
 
 
b72c7a9
ad0a28d
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
 
{
  "best_metric": 2.4297590255737305,
  "best_model_checkpoint": "./outputs/checkpoint-800",
  "epoch": 0.5828779599271403,
  "eval_steps": 100,
  "global_step": 800,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 2.7392,
      "step": 100
    },
    {
      "epoch": 0.07,
      "eval_loss": 2.641645669937134,
      "eval_runtime": 216.5632,
      "eval_samples_per_second": 28.971,
      "eval_steps_per_second": 3.625,
      "step": 100
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0002,
      "loss": 2.6048,
      "step": 200
    },
    {
      "epoch": 0.15,
      "eval_loss": 2.5937132835388184,
      "eval_runtime": 206.5927,
      "eval_samples_per_second": 30.369,
      "eval_steps_per_second": 3.8,
      "step": 200
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0002,
      "loss": 2.5626,
      "step": 300
    },
    {
      "epoch": 0.22,
      "eval_loss": 2.556633949279785,
      "eval_runtime": 206.6295,
      "eval_samples_per_second": 30.364,
      "eval_steps_per_second": 3.799,
      "step": 300
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0002,
      "loss": 2.5359,
      "step": 400
    },
    {
      "epoch": 0.29,
      "eval_loss": 2.52408504486084,
      "eval_runtime": 206.6465,
      "eval_samples_per_second": 30.361,
      "eval_steps_per_second": 3.799,
      "step": 400
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0002,
      "loss": 2.4941,
      "step": 500
    },
    {
      "epoch": 0.36,
      "eval_loss": 2.4982783794403076,
      "eval_runtime": 206.6237,
      "eval_samples_per_second": 30.364,
      "eval_steps_per_second": 3.799,
      "step": 500
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0002,
      "loss": 2.4681,
      "step": 600
    },
    {
      "epoch": 0.44,
      "eval_loss": 2.4732720851898193,
      "eval_runtime": 206.7564,
      "eval_samples_per_second": 30.345,
      "eval_steps_per_second": 3.797,
      "step": 600
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0002,
      "loss": 2.4509,
      "step": 700
    },
    {
      "epoch": 0.51,
      "eval_loss": 2.4523911476135254,
      "eval_runtime": 206.8041,
      "eval_samples_per_second": 30.338,
      "eval_steps_per_second": 3.796,
      "step": 700
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0002,
      "loss": 2.429,
      "step": 800
    },
    {
      "epoch": 0.58,
      "eval_loss": 2.4297590255737305,
      "eval_runtime": 206.8909,
      "eval_samples_per_second": 30.325,
      "eval_steps_per_second": 3.794,
      "step": 800
    }
  ],
  "logging_steps": 100,
  "max_steps": 4116,
  "num_train_epochs": 3,
  "save_steps": 100,
  "total_flos": 2.333865205776384e+16,
  "trial_name": null,
  "trial_params": null
}