Hugging Face's logo

Hanzalwi
/
XGLM-564M-finetuned-aings-validation-data-2

PEFT
TensorBoard
Safetensors
xglm
Model card Files Metrics Community
XGLM-564M-finetuned-aings-validation-data-2
File size: 2,638 Bytes 
854fe79
2c2d158
 
 
854fe79
2c2d158
854fe79
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
dde1ee2
 
 
 
 
 
 
 
 
 
 
 
 
 
66ab406
 
 
 
 
 
 
 
 
 
 
 
 
 
e9dd555
 
 
 
 
 
 
 
 
 
 
 
 
 
54469ca
 
 
 
 
 
 
 
 
 
 
 
 
 
f85a02f
 
 
 
 
 
 
 
 
 
 
 
 
 
2c2d158
 
 
 
 
 
 
 
 
 
 
 
 
 
854fe79
 
 
 
 
 
 
2c2d158
854fe79
 
 
 
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
 
{
  "best_metric": 1.2782505750656128,
  "best_model_checkpoint": "./outputs/checkpoint-700",
  "epoch": 0.9333333333333333,
  "eval_steps": 100,
  "global_step": 700,
  "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": 1.4887,
      "step": 100
    },
    {
      "epoch": 0.13,
      "eval_loss": 1.360513687133789,
      "eval_runtime": 127.6803,
      "eval_samples_per_second": 15.116,
      "eval_steps_per_second": 1.895,
      "step": 100
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0002,
      "loss": 1.1616,
      "step": 200
    },
    {
      "epoch": 0.27,
      "eval_loss": 1.3187366724014282,
      "eval_runtime": 126.439,
      "eval_samples_per_second": 15.264,
      "eval_steps_per_second": 1.914,
      "step": 200
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0002,
      "loss": 1.1374,
      "step": 300
    },
    {
      "epoch": 0.4,
      "eval_loss": 1.3053778409957886,
      "eval_runtime": 126.588,
      "eval_samples_per_second": 15.246,
      "eval_steps_per_second": 1.912,
      "step": 300
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0002,
      "loss": 1.125,
      "step": 400
    },
    {
      "epoch": 0.53,
      "eval_loss": 1.2945491075515747,
      "eval_runtime": 126.4785,
      "eval_samples_per_second": 15.26,
      "eval_steps_per_second": 1.913,
      "step": 400
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0002,
      "loss": 1.1119,
      "step": 500
    },
    {
      "epoch": 0.67,
      "eval_loss": 1.2894083261489868,
      "eval_runtime": 126.4649,
      "eval_samples_per_second": 15.261,
      "eval_steps_per_second": 1.914,
      "step": 500
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0002,
      "loss": 1.1142,
      "step": 600
    },
    {
      "epoch": 0.8,
      "eval_loss": 1.2811017036437988,
      "eval_runtime": 126.9356,
      "eval_samples_per_second": 15.205,
      "eval_steps_per_second": 1.906,
      "step": 600
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0002,
      "loss": 1.1078,
      "step": 700
    },
    {
      "epoch": 0.93,
      "eval_loss": 1.2782505750656128,
      "eval_runtime": 126.2875,
      "eval_samples_per_second": 15.283,
      "eval_steps_per_second": 1.916,
      "step": 700
    }
  ],
  "logging_steps": 100,
  "max_steps": 2250,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 100,
  "total_flos": 2.482400846458061e+16,
  "trial_name": null,
  "trial_params": null
}