Hugging Face's logo

Hanzalwi
/
XGLM-2.9b-finetuned-aings-validation-data-2

PEFT
TensorBoard
Safetensors
xglm
Model card Files Metrics Community
XGLM-2.9b-finetuned-aings-validation-data-2
File size: 3,226 Bytes 
0be20bb
38e6bc5
 
 
0be20bb
38e6bc5
0be20bb
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4dd90fb
 
 
 
 
 
 
 
 
 
 
 
 
 
e017dfc
 
 
 
 
 
 
 
 
 
 
 
 
 
5efebf5
 
 
 
 
 
 
 
 
 
 
 
 
 
d29508d
 
 
 
 
 
 
 
 
 
 
 
 
 
c287821
 
 
 
 
 
 
 
 
 
 
 
 
 
796f79a
 
 
 
 
 
 
 
 
 
 
 
 
 
0b3e10f
 
 
 
 
 
 
 
 
 
 
 
 
 
38e6bc5
 
 
 
 
 
 
 
 
 
 
 
 
 
0be20bb
 
 
 
 
 
 
38e6bc5
0be20bb
 
 
 
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
134
135
136
137
138
139
140
141
142
143
144
145
146
147
 
{
  "best_metric": 1.007003903388977,
  "best_model_checkpoint": "./outputs/checkpoint-900",
  "epoch": 1.2,
  "eval_steps": 100,
  "global_step": 900,
  "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": 1.0608,
      "step": 100
    },
    {
      "epoch": 0.13,
      "eval_loss": 1.0753934383392334,
      "eval_runtime": 354.351,
      "eval_samples_per_second": 5.447,
      "eval_steps_per_second": 0.683,
      "step": 100
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0002,
      "loss": 0.9182,
      "step": 200
    },
    {
      "epoch": 0.27,
      "eval_loss": 1.05315363407135,
      "eval_runtime": 352.7918,
      "eval_samples_per_second": 5.471,
      "eval_steps_per_second": 0.686,
      "step": 200
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0002,
      "loss": 0.9037,
      "step": 300
    },
    {
      "epoch": 0.4,
      "eval_loss": 1.0414820909500122,
      "eval_runtime": 353.1451,
      "eval_samples_per_second": 5.465,
      "eval_steps_per_second": 0.685,
      "step": 300
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0002,
      "loss": 0.8943,
      "step": 400
    },
    {
      "epoch": 0.53,
      "eval_loss": 1.0332194566726685,
      "eval_runtime": 353.4062,
      "eval_samples_per_second": 5.461,
      "eval_steps_per_second": 0.685,
      "step": 400
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0002,
      "loss": 0.8814,
      "step": 500
    },
    {
      "epoch": 0.67,
      "eval_loss": 1.0276169776916504,
      "eval_runtime": 353.0472,
      "eval_samples_per_second": 5.467,
      "eval_steps_per_second": 0.685,
      "step": 500
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0002,
      "loss": 0.8819,
      "step": 600
    },
    {
      "epoch": 0.8,
      "eval_loss": 1.0176780223846436,
      "eval_runtime": 352.9946,
      "eval_samples_per_second": 5.468,
      "eval_steps_per_second": 0.686,
      "step": 600
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0002,
      "loss": 0.8786,
      "step": 700
    },
    {
      "epoch": 0.93,
      "eval_loss": 1.0153926610946655,
      "eval_runtime": 353.3606,
      "eval_samples_per_second": 5.462,
      "eval_steps_per_second": 0.685,
      "step": 700
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.0002,
      "loss": 0.8684,
      "step": 800
    },
    {
      "epoch": 1.07,
      "eval_loss": 1.0099254846572876,
      "eval_runtime": 353.3411,
      "eval_samples_per_second": 5.462,
      "eval_steps_per_second": 0.685,
      "step": 800
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.0002,
      "loss": 0.8637,
      "step": 900
    },
    {
      "epoch": 1.2,
      "eval_loss": 1.007003903388977,
      "eval_runtime": 353.8068,
      "eval_samples_per_second": 5.455,
      "eval_steps_per_second": 0.684,
      "step": 900
    }
  ],
  "logging_steps": 100,
  "max_steps": 2250,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 100,
  "total_flos": 2.545011713639301e+17,
  "trial_name": null,
  "trial_params": null
}