Hugging Face's logo

bs-la
/
bloom-560m_az_bitfit_10000samples_-1vocab_original-frozen

Text Generation
Transformers
PyTorch
bloom
text-generation-inference
Model card Files Community
bloom-560m_az_bitfit_10000samples_-1vocab_original-frozen
File size: 2,828 Bytes 
235b66d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 3.520382881164551,
  "best_model_checkpoint": "/users/zyong2/data/zyong2/bigscience/data/processed/024/bloom-350m_az_bitfit_10000samples_-1vocab_original-frozen/checkpoint-25000",
  "epoch": 19.856519150625125,
  "global_step": 25000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.99,
      "learning_rate": 9e-05,
      "loss": 4.249,
      "step": 2500
    },
    {
      "epoch": 3.97,
      "learning_rate": 8e-05,
      "loss": 3.9172,
      "step": 5000
    },
    {
      "epoch": 3.97,
      "eval_loss": 3.8250739574432373,
      "eval_runtime": 519.4242,
      "eval_samples_per_second": 9.445,
      "eval_steps_per_second": 4.723,
      "step": 5000
    },
    {
      "epoch": 5.96,
      "learning_rate": 7e-05,
      "loss": 3.7702,
      "step": 7500
    },
    {
      "epoch": 7.94,
      "learning_rate": 6e-05,
      "loss": 3.6827,
      "step": 10000
    },
    {
      "epoch": 7.94,
      "eval_loss": 3.64797043800354,
      "eval_runtime": 519.0865,
      "eval_samples_per_second": 9.451,
      "eval_steps_per_second": 4.726,
      "step": 10000
    },
    {
      "epoch": 9.93,
      "learning_rate": 5e-05,
      "loss": 3.624,
      "step": 12500
    },
    {
      "epoch": 11.91,
      "learning_rate": 4e-05,
      "loss": 3.585,
      "step": 15000
    },
    {
      "epoch": 11.91,
      "eval_loss": 3.5690791606903076,
      "eval_runtime": 519.0226,
      "eval_samples_per_second": 9.452,
      "eval_steps_per_second": 4.726,
      "step": 15000
    },
    {
      "epoch": 13.9,
      "learning_rate": 3e-05,
      "loss": 3.5588,
      "step": 17500
    },
    {
      "epoch": 15.89,
      "learning_rate": 2e-05,
      "loss": 3.54,
      "step": 20000
    },
    {
      "epoch": 15.89,
      "eval_loss": 3.531822443008423,
      "eval_runtime": 518.4812,
      "eval_samples_per_second": 9.462,
      "eval_steps_per_second": 4.731,
      "step": 20000
    },
    {
      "epoch": 17.87,
      "learning_rate": 1e-05,
      "loss": 3.5249,
      "step": 22500
    },
    {
      "epoch": 19.86,
      "learning_rate": 0.0,
      "loss": 3.5218,
      "step": 25000
    },
    {
      "epoch": 19.86,
      "eval_loss": 3.520382881164551,
      "eval_runtime": 518.5767,
      "eval_samples_per_second": 9.461,
      "eval_steps_per_second": 4.73,
      "step": 25000
    },
    {
      "epoch": 19.86,
      "step": 25000,
      "total_flos": 3.7165924872093696e+17,
      "train_loss": 3.6973518359375,
      "train_runtime": 53135.1163,
      "train_samples_per_second": 3.764,
      "train_steps_per_second": 0.47
    }
  ],
  "max_steps": 25000,
  "num_train_epochs": 20,
  "total_flos": 3.7165924872093696e+17,
  "trial_name": null,
  "trial_params": null
}