Hugging Face's logo

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

PEFT
TensorBoard
Safetensors
Model card Files Metrics Community
bloom-1b-finetuned-aings-adapters-delimiter-2
File size: 2,610 Bytes 
fb251b7
0d3f6ad
 
 
fb251b7
0d3f6ad
fb251b7
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6c94f80
 
 
 
 
 
 
 
 
 
 
 
 
 
59abe4f
 
 
 
 
 
 
 
 
 
 
 
 
 
dcfc5bb
 
 
 
 
 
 
 
 
 
 
 
 
 
269425a
 
 
 
 
 
 
 
 
 
 
 
 
 
e7143f8
 
 
 
 
 
 
 
 
 
 
 
 
 
0d3f6ad
 
 
 
 
 
 
 
 
 
 
 
 
 
fb251b7
 
 
 
 
 
0d3f6ad
fb251b7
 
 
 
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
 
{
  "best_metric": 2.421610116958618,
  "best_model_checkpoint": "./outputs/checkpoint-700",
  "epoch": 0.5100182149362478,
  "eval_steps": 100,
  "global_step": 700,
  "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": 2.7202,
      "step": 100
    },
    {
      "epoch": 0.07,
      "eval_loss": 2.6173269748687744,
      "eval_runtime": 210.4944,
      "eval_samples_per_second": 29.806,
      "eval_steps_per_second": 3.729,
      "step": 100
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0002,
      "loss": 2.5807,
      "step": 200
    },
    {
      "epoch": 0.15,
      "eval_loss": 2.566875696182251,
      "eval_runtime": 206.05,
      "eval_samples_per_second": 30.449,
      "eval_steps_per_second": 3.81,
      "step": 200
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0002,
      "loss": 2.5403,
      "step": 300
    },
    {
      "epoch": 0.22,
      "eval_loss": 2.531456708908081,
      "eval_runtime": 205.7527,
      "eval_samples_per_second": 30.493,
      "eval_steps_per_second": 3.815,
      "step": 300
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0002,
      "loss": 2.5135,
      "step": 400
    },
    {
      "epoch": 0.29,
      "eval_loss": 2.4987542629241943,
      "eval_runtime": 205.7584,
      "eval_samples_per_second": 30.492,
      "eval_steps_per_second": 3.815,
      "step": 400
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0002,
      "loss": 2.4703,
      "step": 500
    },
    {
      "epoch": 0.36,
      "eval_loss": 2.4730148315429688,
      "eval_runtime": 205.8153,
      "eval_samples_per_second": 30.484,
      "eval_steps_per_second": 3.814,
      "step": 500
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0002,
      "loss": 2.4449,
      "step": 600
    },
    {
      "epoch": 0.44,
      "eval_loss": 2.4445066452026367,
      "eval_runtime": 205.9496,
      "eval_samples_per_second": 30.464,
      "eval_steps_per_second": 3.812,
      "step": 600
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0002,
      "loss": 2.4265,
      "step": 700
    },
    {
      "epoch": 0.51,
      "eval_loss": 2.421610116958618,
      "eval_runtime": 206.1548,
      "eval_samples_per_second": 30.433,
      "eval_steps_per_second": 3.808,
      "step": 700
    }
  ],
  "logging_steps": 100,
  "max_steps": 4116,
  "num_train_epochs": 3,
  "save_steps": 100,
  "total_flos": 2.055883980423168e+16,
  "trial_name": null,
  "trial_params": null
}