Hugging Face's logo

rizkyjun
/
bloom-1b-finetuned-aings-adapters-chat-1

PEFT
TensorBoard
Safetensors
Model card Files Metrics Community
bloom-1b-finetuned-aings-adapters-chat-1
File size: 2,920 Bytes 
8f6e248
2d49566
 
 
8f6e248
2d49566
8f6e248
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
aaa6615
 
 
 
 
 
 
 
 
 
 
 
 
 
cf15307
 
 
 
 
 
 
 
 
 
 
 
 
 
04d3adc
 
 
 
 
 
 
 
 
 
 
 
 
 
c83491a
 
 
 
 
 
 
 
 
 
 
 
 
 
58cd1b7
 
 
 
 
 
 
 
 
 
 
 
 
 
a2050f4
 
 
 
 
 
 
 
 
 
 
 
 
 
2d49566
 
 
 
 
 
 
 
 
 
 
 
 
 
8f6e248
 
 
 
 
 
2d49566
8f6e248
 
 
 
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": 2.506831645965576,
  "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": 2.8179,
      "step": 100
    },
    {
      "epoch": 0.07,
      "eval_loss": 2.723731517791748,
      "eval_runtime": 208.4619,
      "eval_samples_per_second": 30.097,
      "eval_steps_per_second": 3.766,
      "step": 100
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0002,
      "loss": 2.6952,
      "step": 200
    },
    {
      "epoch": 0.15,
      "eval_loss": 2.6728808879852295,
      "eval_runtime": 204.3784,
      "eval_samples_per_second": 30.698,
      "eval_steps_per_second": 3.841,
      "step": 200
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0002,
      "loss": 2.6508,
      "step": 300
    },
    {
      "epoch": 0.22,
      "eval_loss": 2.6387226581573486,
      "eval_runtime": 205.5464,
      "eval_samples_per_second": 30.524,
      "eval_steps_per_second": 3.819,
      "step": 300
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0002,
      "loss": 2.6247,
      "step": 400
    },
    {
      "epoch": 0.29,
      "eval_loss": 2.6044600009918213,
      "eval_runtime": 204.5115,
      "eval_samples_per_second": 30.678,
      "eval_steps_per_second": 3.838,
      "step": 400
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0002,
      "loss": 2.5814,
      "step": 500
    },
    {
      "epoch": 0.36,
      "eval_loss": 2.5784292221069336,
      "eval_runtime": 204.5265,
      "eval_samples_per_second": 30.676,
      "eval_steps_per_second": 3.838,
      "step": 500
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0002,
      "loss": 2.5538,
      "step": 600
    },
    {
      "epoch": 0.44,
      "eval_loss": 2.5523250102996826,
      "eval_runtime": 205.1078,
      "eval_samples_per_second": 30.589,
      "eval_steps_per_second": 3.827,
      "step": 600
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0002,
      "loss": 2.5382,
      "step": 700
    },
    {
      "epoch": 0.51,
      "eval_loss": 2.5274579524993896,
      "eval_runtime": 204.8352,
      "eval_samples_per_second": 30.63,
      "eval_steps_per_second": 3.832,
      "step": 700
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0002,
      "loss": 2.5141,
      "step": 800
    },
    {
      "epoch": 0.58,
      "eval_loss": 2.506831645965576,
      "eval_runtime": 204.4886,
      "eval_samples_per_second": 30.681,
      "eval_steps_per_second": 3.839,
      "step": 800
    }
  ],
  "logging_steps": 100,
  "max_steps": 4116,
  "num_train_epochs": 3,
  "save_steps": 100,
  "total_flos": 2.277701378039808e+16,
  "trial_name": null,
  "trial_params": null
}