Hugging Face's logo

Hanzalwi
/
bloom-1b-finetuned-aings-validation-data-2

PEFT
TensorBoard
Safetensors
bloom
Model card Files Metrics Community
bloom-1b-finetuned-aings-validation-data-2
File size: 2,945 Bytes 
9220046
096538a
 
 
9220046
096538a
9220046
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4d01f16
 
 
 
 
 
 
 
 
 
 
 
 
 
b3c7627
 
 
 
 
 
 
 
 
 
 
 
 
 
88207f9
 
 
 
 
 
 
 
 
 
 
 
 
 
88073b2
 
 
 
 
 
 
 
 
 
 
 
 
 
ea6cbf5
 
 
 
 
 
 
 
 
 
 
 
 
 
615ad9c
 
 
 
 
 
 
 
 
 
 
 
 
 
096538a
 
 
 
 
 
 
 
 
 
 
 
 
 
9220046
 
 
 
 
 
 
096538a
9220046
 
 
 
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
 
{
  "best_metric": 1.1482728719711304,
  "best_model_checkpoint": "./outputs/checkpoint-800",
  "epoch": 1.0666666666666667,
  "eval_steps": 100,
  "global_step": 800,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.13,
      "learning_rate": 0.0002,
      "loss": 1.1592,
      "step": 100
    },
    {
      "epoch": 0.13,
      "eval_loss": 1.2453653812408447,
      "eval_runtime": 180.2468,
      "eval_samples_per_second": 10.708,
      "eval_steps_per_second": 1.343,
      "step": 100
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0002,
      "loss": 1.022,
      "step": 200
    },
    {
      "epoch": 0.27,
      "eval_loss": 1.2181000709533691,
      "eval_runtime": 176.9082,
      "eval_samples_per_second": 10.91,
      "eval_steps_per_second": 1.368,
      "step": 200
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0002,
      "loss": 1.0046,
      "step": 300
    },
    {
      "epoch": 0.4,
      "eval_loss": 1.2017920017242432,
      "eval_runtime": 176.9998,
      "eval_samples_per_second": 10.904,
      "eval_steps_per_second": 1.367,
      "step": 300
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0002,
      "loss": 0.9924,
      "step": 400
    },
    {
      "epoch": 0.53,
      "eval_loss": 1.1916158199310303,
      "eval_runtime": 177.494,
      "eval_samples_per_second": 10.874,
      "eval_steps_per_second": 1.363,
      "step": 400
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0002,
      "loss": 0.9773,
      "step": 500
    },
    {
      "epoch": 0.67,
      "eval_loss": 1.1772679090499878,
      "eval_runtime": 193.3709,
      "eval_samples_per_second": 9.981,
      "eval_steps_per_second": 1.251,
      "step": 500
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0002,
      "loss": 0.9722,
      "step": 600
    },
    {
      "epoch": 0.8,
      "eval_loss": 1.1649450063705444,
      "eval_runtime": 190.0877,
      "eval_samples_per_second": 10.153,
      "eval_steps_per_second": 1.273,
      "step": 600
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0002,
      "loss": 0.9654,
      "step": 700
    },
    {
      "epoch": 0.93,
      "eval_loss": 1.161731481552124,
      "eval_runtime": 177.4185,
      "eval_samples_per_second": 10.878,
      "eval_steps_per_second": 1.364,
      "step": 700
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.0002,
      "loss": 0.9511,
      "step": 800
    },
    {
      "epoch": 1.07,
      "eval_loss": 1.1482728719711304,
      "eval_runtime": 177.4285,
      "eval_samples_per_second": 10.878,
      "eval_steps_per_second": 1.364,
      "step": 800
    }
  ],
  "logging_steps": 100,
  "max_steps": 2250,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 100,
  "total_flos": 5.976702787313664e+16,
  "trial_name": null,
  "trial_params": null
}