Hugging Face's logo

bs-la
/
bloom-1b7_ru_continual-pretrain_100000samples_-1vocab_original

Text Generation
Transformers
PyTorch
bloom
text-generation-inference
Inference Endpoints
Model card Files Community
bloom-1b7_ru_continual-pretrain_100000samples_-1vocab_original
File size: 2,781 Bytes 
6f07692
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": 1.7216796875,
  "best_model_checkpoint": "/home/zhengxinyong/outputs/bloom-1b7_ru_continual-pretrain_100000samples_-1vocab_original/checkpoint-25000",
  "epoch": 1.4637002341920375,
  "global_step": 25000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.15,
      "learning_rate": 0.0001,
      "loss": 2.2537,
      "step": 2500
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0001,
      "loss": 1.9859,
      "step": 5000
    },
    {
      "epoch": 0.29,
      "eval_loss": 1.9208984375,
      "eval_runtime": 7.2654,
      "eval_samples_per_second": 187.601,
      "eval_steps_per_second": 23.536,
      "step": 5000
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0001,
      "loss": 1.896,
      "step": 7500
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0001,
      "loss": 1.853,
      "step": 10000
    },
    {
      "epoch": 0.59,
      "eval_loss": 1.82421875,
      "eval_runtime": 7.2655,
      "eval_samples_per_second": 187.599,
      "eval_steps_per_second": 23.536,
      "step": 10000
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0001,
      "loss": 1.8152,
      "step": 12500
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0001,
      "loss": 1.782,
      "step": 15000
    },
    {
      "epoch": 0.88,
      "eval_loss": 1.7744140625,
      "eval_runtime": 7.2563,
      "eval_samples_per_second": 187.838,
      "eval_steps_per_second": 23.566,
      "step": 15000
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.0001,
      "loss": 1.7434,
      "step": 17500
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.0001,
      "loss": 1.6356,
      "step": 20000
    },
    {
      "epoch": 1.17,
      "eval_loss": 1.744140625,
      "eval_runtime": 7.2585,
      "eval_samples_per_second": 187.781,
      "eval_steps_per_second": 23.559,
      "step": 20000
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.0001,
      "loss": 1.6475,
      "step": 22500
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.0001,
      "loss": 1.6398,
      "step": 25000
    },
    {
      "epoch": 1.46,
      "eval_loss": 1.7216796875,
      "eval_runtime": 7.2617,
      "eval_samples_per_second": 187.696,
      "eval_steps_per_second": 23.548,
      "step": 25000
    },
    {
      "epoch": 1.46,
      "step": 25000,
      "total_flos": 1.4851359536421274e+18,
      "train_loss": 1.8252051953125,
      "train_runtime": 6127.1413,
      "train_samples_per_second": 32.642,
      "train_steps_per_second": 4.08
    }
  ],
  "max_steps": 25000,
  "num_train_epochs": 2,
  "total_flos": 1.4851359536421274e+18,
  "trial_name": null,
  "trial_params": null
}