Hugging Face's logo

sallywww
/
StarCoder_oneStep_FuzzTargets

PEFT
TensorBoard
Safetensors
Model card Files Metrics Community
StarCoder_oneStep_FuzzTargets
File size: 3,515 Bytes 
77021bd
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 9.795918367346939,
  "eval_steps": 20,
  "global_step": 120,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.82,
      "grad_norm": 0.18377472460269928,
      "learning_rate": 2.9999999999999997e-05,
      "loss": 1.861,
      "step": 10
    },
    {
      "epoch": 1.63,
      "grad_norm": 0.35202744603157043,
      "learning_rate": 5.9999999999999995e-05,
      "loss": 1.7263,
      "step": 20
    },
    {
      "epoch": 1.63,
      "eval_loss": 1.4457755088806152,
      "eval_runtime": 89.8938,
      "eval_samples_per_second": 4.305,
      "eval_steps_per_second": 0.545,
      "step": 20
    },
    {
      "epoch": 2.45,
      "grad_norm": 0.928983747959137,
      "learning_rate": 8.999999999999999e-05,
      "loss": 1.1718,
      "step": 30
    },
    {
      "epoch": 3.27,
      "grad_norm": 0.253262996673584,
      "learning_rate": 0.00011999999999999999,
      "loss": 0.4789,
      "step": 40
    },
    {
      "epoch": 3.27,
      "eval_loss": 0.3332095146179199,
      "eval_runtime": 89.9804,
      "eval_samples_per_second": 4.301,
      "eval_steps_per_second": 0.545,
      "step": 40
    },
    {
      "epoch": 4.08,
      "grad_norm": 0.12236642092466354,
      "learning_rate": 0.00015,
      "loss": 0.3568,
      "step": 50
    },
    {
      "epoch": 4.9,
      "grad_norm": 0.09160923212766647,
      "learning_rate": 0.00017999999999999998,
      "loss": 0.3256,
      "step": 60
    },
    {
      "epoch": 4.9,
      "eval_loss": 0.2753114104270935,
      "eval_runtime": 90.3206,
      "eval_samples_per_second": 4.285,
      "eval_steps_per_second": 0.543,
      "step": 60
    },
    {
      "epoch": 5.71,
      "grad_norm": 0.10242326557636261,
      "learning_rate": 0.00020999999999999998,
      "loss": 0.2841,
      "step": 70
    },
    {
      "epoch": 6.53,
      "grad_norm": 0.1305350810289383,
      "learning_rate": 0.00023999999999999998,
      "loss": 0.2615,
      "step": 80
    },
    {
      "epoch": 6.53,
      "eval_loss": 0.2476309835910797,
      "eval_runtime": 90.525,
      "eval_samples_per_second": 4.275,
      "eval_steps_per_second": 0.541,
      "step": 80
    },
    {
      "epoch": 7.35,
      "grad_norm": 0.17941106855869293,
      "learning_rate": 0.00027,
      "loss": 0.2216,
      "step": 90
    },
    {
      "epoch": 8.16,
      "grad_norm": 0.20095375180244446,
      "learning_rate": 0.0003,
      "loss": 0.1832,
      "step": 100
    },
    {
      "epoch": 8.16,
      "eval_loss": 0.2350914180278778,
      "eval_runtime": 90.3919,
      "eval_samples_per_second": 4.281,
      "eval_steps_per_second": 0.542,
      "step": 100
    },
    {
      "epoch": 8.98,
      "grad_norm": 0.2600422501564026,
      "learning_rate": 0.00029,
      "loss": 0.1441,
      "step": 110
    },
    {
      "epoch": 9.8,
      "grad_norm": 0.20544037222862244,
      "learning_rate": 0.00028,
      "loss": 0.1186,
      "step": 120
    },
    {
      "epoch": 9.8,
      "eval_loss": 0.23090216517448425,
      "eval_runtime": 90.3144,
      "eval_samples_per_second": 4.285,
      "eval_steps_per_second": 0.543,
      "step": 120
    }
  ],
  "logging_steps": 10,
  "max_steps": 400,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 34,
  "save_steps": 20,
  "total_flos": 6.887969287129006e+17,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}