Hugging Face's logo

Hanzalwi
/
bloom-1b-finetuned-aings-validation-data-3

PEFT
TensorBoard
Safetensors
bloom
Model card Files Metrics Community
bloom-1b-finetuned-aings-validation-data-3
File size: 2,947 Bytes 
94c8ac8
c33d318
 
 
94c8ac8
c33d318
94c8ac8
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5f05392
 
 
 
 
 
 
 
 
 
 
 
 
 
a88ae84
 
 
 
 
 
 
 
 
 
 
 
 
 
1538d53
 
 
 
 
 
 
 
 
 
 
 
 
 
226d685
 
 
 
 
 
 
 
 
 
 
 
 
 
84f1880
 
 
 
 
 
 
 
 
 
 
 
 
 
d9f3617
 
 
 
 
 
 
 
 
 
 
 
 
 
c33d318
 
 
 
 
 
 
 
 
 
 
 
 
 
94c8ac8
 
 
 
 
 
 
c33d318
94c8ac8
 
 
 
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": 1.1489245891571045,
  "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": 1.1585,
      "step": 100
    },
    {
      "epoch": 0.13,
      "eval_loss": 1.2452774047851562,
      "eval_runtime": 180.3075,
      "eval_samples_per_second": 10.704,
      "eval_steps_per_second": 1.342,
      "step": 100
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0002,
      "loss": 1.0217,
      "step": 200
    },
    {
      "epoch": 0.27,
      "eval_loss": 1.2180681228637695,
      "eval_runtime": 177.5054,
      "eval_samples_per_second": 10.873,
      "eval_steps_per_second": 1.363,
      "step": 200
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0002,
      "loss": 1.0048,
      "step": 300
    },
    {
      "epoch": 0.4,
      "eval_loss": 1.203295350074768,
      "eval_runtime": 177.4062,
      "eval_samples_per_second": 10.879,
      "eval_steps_per_second": 1.364,
      "step": 300
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0002,
      "loss": 0.992,
      "step": 400
    },
    {
      "epoch": 0.53,
      "eval_loss": 1.190936803817749,
      "eval_runtime": 177.5627,
      "eval_samples_per_second": 10.869,
      "eval_steps_per_second": 1.363,
      "step": 400
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0002,
      "loss": 0.9767,
      "step": 500
    },
    {
      "epoch": 0.67,
      "eval_loss": 1.1756863594055176,
      "eval_runtime": 177.0747,
      "eval_samples_per_second": 10.899,
      "eval_steps_per_second": 1.367,
      "step": 500
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0002,
      "loss": 0.9715,
      "step": 600
    },
    {
      "epoch": 0.8,
      "eval_loss": 1.1637059450149536,
      "eval_runtime": 177.4052,
      "eval_samples_per_second": 10.879,
      "eval_steps_per_second": 1.364,
      "step": 600
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0002,
      "loss": 0.9653,
      "step": 700
    },
    {
      "epoch": 0.93,
      "eval_loss": 1.1604684591293335,
      "eval_runtime": 177.5251,
      "eval_samples_per_second": 10.872,
      "eval_steps_per_second": 1.363,
      "step": 700
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.0002,
      "loss": 0.9517,
      "step": 800
    },
    {
      "epoch": 1.07,
      "eval_loss": 1.1489245891571045,
      "eval_runtime": 180.9559,
      "eval_samples_per_second": 10.666,
      "eval_steps_per_second": 1.337,
      "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
}