Hugging Face's logo

Davlan
/
bloom-560m_am_continual-pretrain_10000samples

Text Generation
Transformers
PyTorch
bloom
text-generation-inference
Inference Endpoints
Model card Files Community
1
bloom-560m_am_continual-pretrain_10000samples
File size: 2,821 Bytes 
3596cc3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 1.0630253553390503,
  "best_model_checkpoint": "/data/users/didelani/multilingual-modeling/bloom-560m_am_continual-pretrain_10000samples_-1vocab_original/checkpoint-10000",
  "epoch": 6.8417883898334075,
  "global_step": 25000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.68,
      "learning_rate": 9e-05,
      "loss": 1.3776,
      "step": 2500
    },
    {
      "epoch": 1.37,
      "learning_rate": 8e-05,
      "loss": 1.1298,
      "step": 5000
    },
    {
      "epoch": 1.37,
      "eval_loss": 1.1117359399795532,
      "eval_runtime": 419.467,
      "eval_samples_per_second": 6.847,
      "eval_steps_per_second": 3.423,
      "step": 5000
    },
    {
      "epoch": 2.05,
      "learning_rate": 7e-05,
      "loss": 1.0638,
      "step": 7500
    },
    {
      "epoch": 2.74,
      "learning_rate": 6e-05,
      "loss": 0.9777,
      "step": 10000
    },
    {
      "epoch": 2.74,
      "eval_loss": 1.0630253553390503,
      "eval_runtime": 421.4286,
      "eval_samples_per_second": 6.815,
      "eval_steps_per_second": 3.407,
      "step": 10000
    },
    {
      "epoch": 3.42,
      "learning_rate": 5e-05,
      "loss": 0.9059,
      "step": 12500
    },
    {
      "epoch": 4.11,
      "learning_rate": 4e-05,
      "loss": 0.8435,
      "step": 15000
    },
    {
      "epoch": 4.11,
      "eval_loss": 1.1998958587646484,
      "eval_runtime": 422.8876,
      "eval_samples_per_second": 6.791,
      "eval_steps_per_second": 3.396,
      "step": 15000
    },
    {
      "epoch": 4.79,
      "learning_rate": 3e-05,
      "loss": 0.7247,
      "step": 17500
    },
    {
      "epoch": 5.47,
      "learning_rate": 2e-05,
      "loss": 0.6063,
      "step": 20000
    },
    {
      "epoch": 5.47,
      "eval_loss": 1.5086530447006226,
      "eval_runtime": 417.6938,
      "eval_samples_per_second": 6.876,
      "eval_steps_per_second": 3.438,
      "step": 20000
    },
    {
      "epoch": 6.16,
      "learning_rate": 1e-05,
      "loss": 0.5155,
      "step": 22500
    },
    {
      "epoch": 6.84,
      "learning_rate": 0.0,
      "loss": 0.386,
      "step": 25000
    },
    {
      "epoch": 6.84,
      "eval_loss": 2.100792646408081,
      "eval_runtime": 418.1577,
      "eval_samples_per_second": 6.868,
      "eval_steps_per_second": 3.434,
      "step": 25000
    },
    {
      "epoch": 6.84,
      "step": 25000,
      "total_flos": 3.714939388774318e+17,
      "train_loss": 0.8530817114257813,
      "train_runtime": 94563.3332,
      "train_samples_per_second": 2.115,
      "train_steps_per_second": 0.264
    }
  ],
  "max_steps": 25000,
  "num_train_epochs": 7,
  "total_flos": 3.714939388774318e+17,
  "trial_name": null,
  "trial_params": null
}