Hugging Face's logo

Hanzalwi
/
XGLM-2.9b-finetuned-aings-validation-data-1

PEFT
TensorBoard
Safetensors
xglm
Model card Files Metrics Community
XGLM-2.9b-finetuned-aings-validation-data-1
File size: 3,552 Bytes 
3fdb3f3
808e88e
 
 
3fdb3f3
808e88e
3fdb3f3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
87a0d4d
 
 
 
 
 
 
 
 
 
 
 
 
 
f0069c5
 
 
 
 
 
 
 
 
 
 
 
 
 
5dbe1ee
 
 
 
 
 
 
 
 
 
 
 
 
 
11ddf77
 
 
 
 
 
 
 
 
 
 
 
 
 
d71c9cb
 
 
 
 
 
 
 
 
 
 
 
 
 
10b8682
 
 
 
 
 
 
 
 
 
 
 
 
 
9070ab0
 
 
 
 
 
 
 
 
 
 
 
 
 
f6554a8
 
 
 
 
 
 
 
 
 
 
 
 
 
808e88e
 
 
 
 
 
 
 
 
 
 
 
 
 
3fdb3f3
 
 
 
 
 
 
808e88e
3fdb3f3
 
 
 
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
148
149
150
151
152
153
154
155
156
157
158
159
160
161
 
{
  "best_metric": 0.9995353817939758,
  "best_model_checkpoint": "./outputs/checkpoint-1000",
  "epoch": 1.3333333333333333,
  "eval_steps": 100,
  "global_step": 1000,
  "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": 1.0596,
      "step": 100
    },
    {
      "epoch": 0.13,
      "eval_loss": 1.0747358798980713,
      "eval_runtime": 354.4756,
      "eval_samples_per_second": 5.445,
      "eval_steps_per_second": 0.683,
      "step": 100
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0002,
      "loss": 0.9173,
      "step": 200
    },
    {
      "epoch": 0.27,
      "eval_loss": 1.0527141094207764,
      "eval_runtime": 353.1278,
      "eval_samples_per_second": 5.465,
      "eval_steps_per_second": 0.685,
      "step": 200
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0002,
      "loss": 0.9029,
      "step": 300
    },
    {
      "epoch": 0.4,
      "eval_loss": 1.0407249927520752,
      "eval_runtime": 353.5098,
      "eval_samples_per_second": 5.46,
      "eval_steps_per_second": 0.685,
      "step": 300
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0002,
      "loss": 0.8938,
      "step": 400
    },
    {
      "epoch": 0.53,
      "eval_loss": 1.033090591430664,
      "eval_runtime": 353.8818,
      "eval_samples_per_second": 5.454,
      "eval_steps_per_second": 0.684,
      "step": 400
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0002,
      "loss": 0.881,
      "step": 500
    },
    {
      "epoch": 0.67,
      "eval_loss": 1.0268442630767822,
      "eval_runtime": 352.5818,
      "eval_samples_per_second": 5.474,
      "eval_steps_per_second": 0.686,
      "step": 500
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0002,
      "loss": 0.8815,
      "step": 600
    },
    {
      "epoch": 0.8,
      "eval_loss": 1.0178813934326172,
      "eval_runtime": 353.5441,
      "eval_samples_per_second": 5.459,
      "eval_steps_per_second": 0.684,
      "step": 600
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0002,
      "loss": 0.8785,
      "step": 700
    },
    {
      "epoch": 0.93,
      "eval_loss": 1.0156869888305664,
      "eval_runtime": 353.6562,
      "eval_samples_per_second": 5.457,
      "eval_steps_per_second": 0.684,
      "step": 700
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.0002,
      "loss": 0.868,
      "step": 800
    },
    {
      "epoch": 1.07,
      "eval_loss": 1.0099247694015503,
      "eval_runtime": 354.1025,
      "eval_samples_per_second": 5.45,
      "eval_steps_per_second": 0.683,
      "step": 800
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.0002,
      "loss": 0.8634,
      "step": 900
    },
    {
      "epoch": 1.2,
      "eval_loss": 1.0071921348571777,
      "eval_runtime": 353.8229,
      "eval_samples_per_second": 5.455,
      "eval_steps_per_second": 0.684,
      "step": 900
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.0002,
      "loss": 0.8555,
      "step": 1000
    },
    {
      "epoch": 1.33,
      "eval_loss": 0.9995353817939758,
      "eval_runtime": 353.9933,
      "eval_samples_per_second": 5.452,
      "eval_steps_per_second": 0.684,
      "step": 1000
    }
  ],
  "logging_steps": 100,
  "max_steps": 2250,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 100,
  "total_flos": 2.8274441850197606e+17,
  "trial_name": null,
  "trial_params": null
}