Hugging Face's logo

Chat-Error
/
Blind-test01

Model card Files
xet
 Community
Blind-test01
File size: 2,922 Bytes
c4fc286
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
{
  "best_metric": 2.066981077194214,
  "best_model_checkpoint": "./qlora-out-kimiko-test2/checkpoint-20",
  "epoch": 0.5169628432956381,
  "eval_steps": 10,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03,
      "learning_rate": 1e-05,
      "loss": 1.5707,
      "step": 1
    },
    {
      "epoch": 0.05,
      "learning_rate": 2e-05,
      "loss": 1.5621,
      "step": 2
    },
    {
      "epoch": 0.08,
      "learning_rate": 3e-05,
      "loss": 1.4812,
      "step": 3
    },
    {
      "epoch": 0.1,
      "learning_rate": 4e-05,
      "loss": 1.5197,
      "step": 4
    },
    {
      "epoch": 0.13,
      "learning_rate": 5e-05,
      "loss": 1.5567,
      "step": 5
    },
    {
      "epoch": 0.16,
      "learning_rate": 5e-05,
      "loss": 1.4645,
      "step": 6
    },
    {
      "epoch": 0.18,
      "learning_rate": 5e-05,
      "loss": 1.6122,
      "step": 7
    },
    {
      "epoch": 0.21,
      "learning_rate": 5e-05,
      "loss": 1.5596,
      "step": 8
    },
    {
      "epoch": 0.23,
      "learning_rate": 5e-05,
      "loss": 1.5608,
      "step": 9
    },
    {
      "epoch": 0.26,
      "learning_rate": 5e-05,
      "loss": 1.5456,
      "step": 10
    },
    {
      "epoch": 0.26,
      "eval_loss": 2.098437547683716,
      "eval_runtime": 119.6161,
      "eval_samples_per_second": 1.555,
      "eval_steps_per_second": 0.777,
      "step": 10
    },
    {
      "epoch": 0.28,
      "learning_rate": 5e-05,
      "loss": 1.5645,
      "step": 11
    },
    {
      "epoch": 0.31,
      "learning_rate": 5e-05,
      "loss": 1.538,
      "step": 12
    },
    {
      "epoch": 0.34,
      "learning_rate": 5e-05,
      "loss": 1.6388,
      "step": 13
    },
    {
      "epoch": 0.36,
      "learning_rate": 5e-05,
      "loss": 1.4943,
      "step": 14
    },
    {
      "epoch": 0.39,
      "learning_rate": 5e-05,
      "loss": 1.5469,
      "step": 15
    },
    {
      "epoch": 0.41,
      "learning_rate": 5e-05,
      "loss": 1.6149,
      "step": 16
    },
    {
      "epoch": 0.44,
      "learning_rate": 5e-05,
      "loss": 1.5345,
      "step": 17
    },
    {
      "epoch": 0.47,
      "learning_rate": 5e-05,
      "loss": 1.4903,
      "step": 18
    },
    {
      "epoch": 0.49,
      "learning_rate": 5e-05,
      "loss": 1.5499,
      "step": 19
    },
    {
      "epoch": 0.52,
      "learning_rate": 5e-05,
      "loss": 1.5934,
      "step": 20
    },
    {
      "epoch": 0.52,
      "eval_loss": 2.066981077194214,
      "eval_runtime": 119.5781,
      "eval_samples_per_second": 1.555,
      "eval_steps_per_second": 0.778,
      "step": 20
    }
  ],
  "logging_steps": 1,
  "max_steps": 114,
  "num_train_epochs": 3,
  "save_steps": 10,
  "total_flos": 9.195307914756096e+16,
  "trial_name": null,
  "trial_params": null
}