Hugging Face's logo

Hanzalwi
/
XGLM-564M-finetuned-aings-validation-data-1

PEFT
TensorBoard
Safetensors
xglm
Model card Files Metrics Community
XGLM-564M-finetuned-aings-validation-data-1
File size: 2,944 Bytes 
481da77
1b02e20
 
 
481da77
1b02e20
481da77
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
e95b6d4
 
 
 
 
 
 
 
 
 
 
 
 
 
2892785
 
 
 
 
 
 
 
 
 
 
 
 
 
b6927a1
 
 
 
 
 
 
 
 
 
 
 
 
 
1985828
 
 
 
 
 
 
 
 
 
 
 
 
 
a0c717e
 
 
 
 
 
 
 
 
 
 
 
 
 
2b631cb
 
 
 
 
 
 
 
 
 
 
 
 
 
1b02e20
 
 
 
 
 
 
 
 
 
 
 
 
 
481da77
 
 
 
 
 
 
1b02e20
481da77
 
 
 
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": 1.2742822170257568,
  "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": 1.4919,
      "step": 100
    },
    {
      "epoch": 0.13,
      "eval_loss": 1.361365795135498,
      "eval_runtime": 127.054,
      "eval_samples_per_second": 15.19,
      "eval_steps_per_second": 1.905,
      "step": 100
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0002,
      "loss": 1.1628,
      "step": 200
    },
    {
      "epoch": 0.27,
      "eval_loss": 1.319554328918457,
      "eval_runtime": 126.2625,
      "eval_samples_per_second": 15.286,
      "eval_steps_per_second": 1.917,
      "step": 200
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0002,
      "loss": 1.1376,
      "step": 300
    },
    {
      "epoch": 0.4,
      "eval_loss": 1.3056749105453491,
      "eval_runtime": 126.1549,
      "eval_samples_per_second": 15.299,
      "eval_steps_per_second": 1.918,
      "step": 300
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0002,
      "loss": 1.1257,
      "step": 400
    },
    {
      "epoch": 0.53,
      "eval_loss": 1.2944581508636475,
      "eval_runtime": 126.2031,
      "eval_samples_per_second": 15.293,
      "eval_steps_per_second": 1.918,
      "step": 400
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0002,
      "loss": 1.1123,
      "step": 500
    },
    {
      "epoch": 0.67,
      "eval_loss": 1.2884504795074463,
      "eval_runtime": 126.384,
      "eval_samples_per_second": 15.271,
      "eval_steps_per_second": 1.915,
      "step": 500
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0002,
      "loss": 1.1146,
      "step": 600
    },
    {
      "epoch": 0.8,
      "eval_loss": 1.2814782857894897,
      "eval_runtime": 126.0146,
      "eval_samples_per_second": 15.316,
      "eval_steps_per_second": 1.92,
      "step": 600
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0002,
      "loss": 1.1083,
      "step": 700
    },
    {
      "epoch": 0.93,
      "eval_loss": 1.2781809568405151,
      "eval_runtime": 126.2703,
      "eval_samples_per_second": 15.285,
      "eval_steps_per_second": 1.917,
      "step": 700
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.0002,
      "loss": 1.0979,
      "step": 800
    },
    {
      "epoch": 1.07,
      "eval_loss": 1.2742822170257568,
      "eval_runtime": 126.1208,
      "eval_samples_per_second": 15.303,
      "eval_steps_per_second": 1.919,
      "step": 800
    }
  ],
  "logging_steps": 100,
  "max_steps": 2250,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 100,
  "total_flos": 2.836263099222835e+16,
  "trial_name": null,
  "trial_params": null
}