Hugging Face's logo

Hanzalwi
/
bloom-3b-finetuned-aings-validation-data-2

PEFT
TensorBoard
Safetensors
bloom
Model card Files Metrics Community
bloom-3b-finetuned-aings-validation-data-2
File size: 2,934 Bytes 
2463d71
04821e5
 
 
2463d71
04821e5
2463d71
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9174c38
 
 
 
 
 
 
 
 
 
 
 
 
 
9e96f75
 
 
 
 
 
 
 
 
 
 
 
 
 
e636810
 
 
 
 
 
 
 
 
 
 
 
 
 
a0eb430
 
 
 
 
 
 
 
 
 
 
 
 
 
3930d4a
 
 
 
 
 
 
 
 
 
 
 
 
 
84ab9bc
 
 
 
 
 
 
 
 
 
 
 
 
 
04821e5
 
 
 
 
 
 
 
 
 
 
 
 
 
2463d71
 
 
 
 
 
 
04821e5
2463d71
 
 
 
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": 1.001969337463379,
  "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": 1.0007,
      "step": 100
    },
    {
      "epoch": 0.13,
      "eval_loss": 1.0926419496536255,
      "eval_runtime": 890.2071,
      "eval_samples_per_second": 2.168,
      "eval_steps_per_second": 0.272,
      "step": 100
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0002,
      "loss": 0.897,
      "step": 200
    },
    {
      "epoch": 0.27,
      "eval_loss": 1.0682977437973022,
      "eval_runtime": 890.4733,
      "eval_samples_per_second": 2.167,
      "eval_steps_per_second": 0.272,
      "step": 200
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0002,
      "loss": 0.8814,
      "step": 300
    },
    {
      "epoch": 0.4,
      "eval_loss": 1.0527396202087402,
      "eval_runtime": 888.2495,
      "eval_samples_per_second": 2.173,
      "eval_steps_per_second": 0.272,
      "step": 300
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0002,
      "loss": 0.8697,
      "step": 400
    },
    {
      "epoch": 0.53,
      "eval_loss": 1.039888620376587,
      "eval_runtime": 883.1791,
      "eval_samples_per_second": 2.185,
      "eval_steps_per_second": 0.274,
      "step": 400
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0002,
      "loss": 0.8552,
      "step": 500
    },
    {
      "epoch": 0.67,
      "eval_loss": 1.0277502536773682,
      "eval_runtime": 724.238,
      "eval_samples_per_second": 2.665,
      "eval_steps_per_second": 0.334,
      "step": 500
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0002,
      "loss": 0.85,
      "step": 600
    },
    {
      "epoch": 0.8,
      "eval_loss": 1.0173273086547852,
      "eval_runtime": 724.2021,
      "eval_samples_per_second": 2.665,
      "eval_steps_per_second": 0.334,
      "step": 600
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0002,
      "loss": 0.8449,
      "step": 700
    },
    {
      "epoch": 0.93,
      "eval_loss": 1.012062430381775,
      "eval_runtime": 728.824,
      "eval_samples_per_second": 2.648,
      "eval_steps_per_second": 0.332,
      "step": 700
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.0002,
      "loss": 0.8282,
      "step": 800
    },
    {
      "epoch": 1.07,
      "eval_loss": 1.001969337463379,
      "eval_runtime": 726.4944,
      "eval_samples_per_second": 2.657,
      "eval_steps_per_second": 0.333,
      "step": 800
    }
  ],
  "logging_steps": 100,
  "max_steps": 2250,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 100,
  "total_flos": 2.0717810165526528e+17,
  "trial_name": null,
  "trial_params": null
}