Hugging Face's logo

bs-la
/
bloom-560m_my_sft_100000samples_-1vocab_original-frozen

Text Generation
Transformers
PyTorch
bloom
text-generation-inference
Inference Endpoints
Model card Files Community
1
bloom-560m_my_sft_100000samples_-1vocab_original-frozen
File size: 3,082 Bytes 
fc3e573
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
133
134
135
136
 
{
  "best_metric": 0.7879278063774109,
  "best_model_checkpoint": "/home/khalid/Documents/github_rep/bigscience/data/processed/35/bloom-560m_my_sft_100000samples_-1vocab_original-frozen/checkpoint-25000",
  "epoch": 0.39631741854686253,
  "global_step": 25000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04,
      "l1_reg_loss": 0.0,
      "learning_rate": 9e-05,
      "loss": 1.0457,
      "step": 2500
    },
    {
      "epoch": 0.08,
      "l1_reg_loss": 0.0,
      "learning_rate": 8e-05,
      "loss": 0.8994,
      "step": 5000
    },
    {
      "epoch": 0.08,
      "eval_loss": 0.8788017630577087,
      "eval_runtime": 2668.4849,
      "eval_samples_per_second": 9.399,
      "eval_steps_per_second": 4.7,
      "step": 5000
    },
    {
      "epoch": 0.12,
      "l1_reg_loss": 0.0,
      "learning_rate": 7e-05,
      "loss": 0.8556,
      "step": 7500
    },
    {
      "epoch": 0.16,
      "l1_reg_loss": 0.0,
      "learning_rate": 6e-05,
      "loss": 0.8299,
      "step": 10000
    },
    {
      "epoch": 0.16,
      "eval_loss": 0.8276682496070862,
      "eval_runtime": 2661.8009,
      "eval_samples_per_second": 9.423,
      "eval_steps_per_second": 4.711,
      "step": 10000
    },
    {
      "epoch": 0.2,
      "l1_reg_loss": 0.0,
      "learning_rate": 5e-05,
      "loss": 0.815,
      "step": 12500
    },
    {
      "epoch": 0.24,
      "l1_reg_loss": 0.0,
      "learning_rate": 4e-05,
      "loss": 0.8019,
      "step": 15000
    },
    {
      "epoch": 0.24,
      "eval_loss": 0.804674506187439,
      "eval_runtime": 2658.9167,
      "eval_samples_per_second": 9.433,
      "eval_steps_per_second": 4.717,
      "step": 15000
    },
    {
      "epoch": 0.28,
      "l1_reg_loss": 0.0,
      "learning_rate": 3e-05,
      "loss": 0.7965,
      "step": 17500
    },
    {
      "epoch": 0.32,
      "l1_reg_loss": 0.0,
      "learning_rate": 2e-05,
      "loss": 0.7875,
      "step": 20000
    },
    {
      "epoch": 0.32,
      "eval_loss": 0.7925558686256409,
      "eval_runtime": 2660.1365,
      "eval_samples_per_second": 9.428,
      "eval_steps_per_second": 4.714,
      "step": 20000
    },
    {
      "epoch": 0.36,
      "l1_reg_loss": 0.0,
      "learning_rate": 1e-05,
      "loss": 0.7866,
      "step": 22500
    },
    {
      "epoch": 0.4,
      "l1_reg_loss": 0.0,
      "learning_rate": 0.0,
      "loss": 0.7835,
      "step": 25000
    },
    {
      "epoch": 0.4,
      "eval_loss": 0.7879278063774109,
      "eval_runtime": 2660.4205,
      "eval_samples_per_second": 9.427,
      "eval_steps_per_second": 4.714,
      "step": 25000
    },
    {
      "epoch": 0.4,
      "step": 25000,
      "total_flos": 3.714827943936e+17,
      "train_loss": 0.8401528125,
      "train_runtime": 72520.074,
      "train_samples_per_second": 2.758,
      "train_steps_per_second": 0.345
    }
  ],
  "max_steps": 25000,
  "num_train_epochs": 1,
  "total_flos": 3.714827943936e+17,
  "trial_name": null,
  "trial_params": null
}