Hugging Face's logo

bs-la
/
bloom-7b1_th_continual-pretrain_100000samples_-1vocab_original

Text Generation
Transformers
PyTorch
bloom
text-generation-inference
Inference Endpoints
Model card Files Community
bloom-7b1_th_continual-pretrain_100000samples_-1vocab_original
File size: 2,521 Bytes 
43d9b35
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": 1.08203125,
  "best_model_checkpoint": "/home/zhengxinyong/outputs/bloom-7b1_th_continual-pretrain_100000samples_-1vocab_original/checkpoint-25000",
  "epoch": 1.2926577042399172,
  "global_step": 25000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.13,
      "learning_rate": 0.0001,
      "loss": 1.5461,
      "step": 2500
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0001,
      "loss": 1.2551,
      "step": 5000
    },
    {
      "epoch": 0.26,
      "eval_loss": 1.248046875,
      "eval_runtime": 23.2835,
      "eval_samples_per_second": 66.442,
      "eval_steps_per_second": 8.332,
      "step": 5000
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0001,
      "loss": 1.1849,
      "step": 7500
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0001,
      "loss": 1.1396,
      "step": 10000
    },
    {
      "epoch": 0.52,
      "eval_loss": 1.1669921875,
      "eval_runtime": 23.3161,
      "eval_samples_per_second": 66.349,
      "eval_steps_per_second": 8.32,
      "step": 10000
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0001,
      "loss": 1.117,
      "step": 12500
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0001,
      "loss": 1.09,
      "step": 15000
    },
    {
      "epoch": 0.78,
      "eval_loss": 1.1279296875,
      "eval_runtime": 23.3005,
      "eval_samples_per_second": 66.393,
      "eval_steps_per_second": 8.326,
      "step": 15000
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0001,
      "loss": 1.0693,
      "step": 17500
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.0001,
      "loss": 1.0416,
      "step": 20000
    },
    {
      "epoch": 1.03,
      "eval_loss": 1.099609375,
      "eval_runtime": 23.2985,
      "eval_samples_per_second": 66.399,
      "eval_steps_per_second": 8.327,
      "step": 20000
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.0001,
      "loss": 0.9778,
      "step": 22500
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.0001,
      "loss": 0.9761,
      "step": 25000
    },
    {
      "epoch": 1.29,
      "eval_loss": 1.08203125,
      "eval_runtime": 23.3142,
      "eval_samples_per_second": 66.354,
      "eval_steps_per_second": 8.321,
      "step": 25000
    }
  ],
  "max_steps": 25000,
  "num_train_epochs": 2,
  "total_flos": 7.423686731586601e+18,
  "trial_name": null,
  "trial_params": null
}