Hugging Face's logo

noe95
/
code-reviewer

Safetensors
Model card Files
xet
 Community
code-reviewer
File size: 3,608 Bytes
f311884
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9933774834437086,
  "eval_steps": 50,
  "global_step": 75,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.06622516556291391,
      "grad_norm": 2.831176519393921,
      "learning_rate": 5e-05,
      "loss": 1.256,
      "step": 5
    },
    {
      "epoch": 0.13245033112582782,
      "grad_norm": 3.2754790782928467,
      "learning_rate": 9.994504457428558e-05,
      "loss": 0.5174,
      "step": 10
    },
    {
      "epoch": 0.1986754966887417,
      "grad_norm": 4.314864158630371,
      "learning_rate": 9.8034259378842e-05,
      "loss": 0.5304,
      "step": 15
    },
    {
      "epoch": 0.26490066225165565,
      "grad_norm": 0.8949492573738098,
      "learning_rate": 9.349531862043952e-05,
      "loss": 0.4987,
      "step": 20
    },
    {
      "epoch": 0.33112582781456956,
      "grad_norm": 1.7747893333435059,
      "learning_rate": 8.657656676318346e-05,
      "loss": 0.3812,
      "step": 25
    },
    {
      "epoch": 0.3973509933774834,
      "grad_norm": 0.8053502440452576,
      "learning_rate": 7.765655770625997e-05,
      "loss": 0.3345,
      "step": 30
    },
    {
      "epoch": 0.46357615894039733,
      "grad_norm": 1.1480026245117188,
      "learning_rate": 6.722334251421665e-05,
      "loss": 0.3257,
      "step": 35
    },
    {
      "epoch": 0.5298013245033113,
      "grad_norm": 1.200183391571045,
      "learning_rate": 5.584776609860414e-05,
      "loss": 0.28,
      "step": 40
    },
    {
      "epoch": 0.5960264900662252,
      "grad_norm": 1.2405061721801758,
      "learning_rate": 4.415223390139588e-05,
      "loss": 0.2278,
      "step": 45
    },
    {
      "epoch": 0.6622516556291391,
      "grad_norm": 1.8566575050354004,
      "learning_rate": 3.277665748578336e-05,
      "loss": 0.2934,
      "step": 50
    },
    {
      "epoch": 0.7284768211920529,
      "grad_norm": 1.3541169166564941,
      "learning_rate": 2.234344229374003e-05,
      "loss": 0.2716,
      "step": 55
    },
    {
      "epoch": 0.7947019867549668,
      "grad_norm": 2.3510825634002686,
      "learning_rate": 1.3423433236816563e-05,
      "loss": 0.2924,
      "step": 60
    },
    {
      "epoch": 0.8609271523178808,
      "grad_norm": 1.2402220964431763,
      "learning_rate": 6.50468137956049e-06,
      "loss": 0.2178,
      "step": 65
    },
    {
      "epoch": 0.9271523178807947,
      "grad_norm": 0.5436655282974243,
      "learning_rate": 1.9657406211579966e-06,
      "loss": 0.2539,
      "step": 70
    },
    {
      "epoch": 0.9933774834437086,
      "grad_norm": 1.2217155694961548,
      "learning_rate": 5.4955425714431353e-08,
      "loss": 0.2228,
      "step": 75
    },
    {
      "epoch": 0.9933774834437086,
      "step": 75,
      "total_flos": 1.0660613606866944e+16,
      "train_loss": 0.39357583204905194,
      "train_runtime": 105.2274,
      "train_samples_per_second": 2.87,
      "train_steps_per_second": 0.713
    }
  ],
  "logging_steps": 5,
  "max_steps": 75,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.0660613606866944e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}