Hugging Face's logo

Jianshu001
/
Routing-ft

Safetensors
qwen2
Model card Files
xet
Community
Routing-ft
File size: 3,716 Bytes 
64cc715
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
162
163
164
165
166
167
168
169
170
171
172
173
174
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 10.0,
  "eval_steps": 500,
  "global_step": 10240,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.48828125,
      "grad_norm": 14.348142623901367,
      "learning_rate": 2e-05,
      "loss": 0.718,
      "step": 500
    },
    {
      "epoch": 0.9765625,
      "grad_norm": 12.407145500183105,
      "learning_rate": 2e-05,
      "loss": 0.6899,
      "step": 1000
    },
    {
      "epoch": 1.46484375,
      "grad_norm": 9.278654098510742,
      "learning_rate": 2e-05,
      "loss": 0.3397,
      "step": 1500
    },
    {
      "epoch": 1.953125,
      "grad_norm": 8.198233604431152,
      "learning_rate": 2e-05,
      "loss": 0.3419,
      "step": 2000
    },
    {
      "epoch": 2.44140625,
      "grad_norm": 4.592423915863037,
      "learning_rate": 2e-05,
      "loss": 0.1915,
      "step": 2500
    },
    {
      "epoch": 2.9296875,
      "grad_norm": 8.893723487854004,
      "learning_rate": 2e-05,
      "loss": 0.1922,
      "step": 3000
    },
    {
      "epoch": 3.41796875,
      "grad_norm": 8.089862823486328,
      "learning_rate": 2e-05,
      "loss": 0.1263,
      "step": 3500
    },
    {
      "epoch": 3.90625,
      "grad_norm": 6.3830485343933105,
      "learning_rate": 2e-05,
      "loss": 0.121,
      "step": 4000
    },
    {
      "epoch": 4.39453125,
      "grad_norm": 7.365416049957275,
      "learning_rate": 2e-05,
      "loss": 0.0897,
      "step": 4500
    },
    {
      "epoch": 4.8828125,
      "grad_norm": 7.9196600914001465,
      "learning_rate": 2e-05,
      "loss": 0.087,
      "step": 5000
    },
    {
      "epoch": 5.37109375,
      "grad_norm": 3.7600364685058594,
      "learning_rate": 2e-05,
      "loss": 0.0665,
      "step": 5500
    },
    {
      "epoch": 5.859375,
      "grad_norm": 4.597715854644775,
      "learning_rate": 2e-05,
      "loss": 0.0639,
      "step": 6000
    },
    {
      "epoch": 6.34765625,
      "grad_norm": 4.1985182762146,
      "learning_rate": 2e-05,
      "loss": 0.0543,
      "step": 6500
    },
    {
      "epoch": 6.8359375,
      "grad_norm": 5.26850700378418,
      "learning_rate": 2e-05,
      "loss": 0.0506,
      "step": 7000
    },
    {
      "epoch": 7.32421875,
      "grad_norm": 3.8958706855773926,
      "learning_rate": 2e-05,
      "loss": 0.049,
      "step": 7500
    },
    {
      "epoch": 7.8125,
      "grad_norm": 6.896234035491943,
      "learning_rate": 2e-05,
      "loss": 0.0451,
      "step": 8000
    },
    {
      "epoch": 8.30078125,
      "grad_norm": 3.6532912254333496,
      "learning_rate": 2e-05,
      "loss": 0.0431,
      "step": 8500
    },
    {
      "epoch": 8.7890625,
      "grad_norm": 4.900750160217285,
      "learning_rate": 2e-05,
      "loss": 0.0402,
      "step": 9000
    },
    {
      "epoch": 9.27734375,
      "grad_norm": 1.2737749814987183,
      "learning_rate": 2e-05,
      "loss": 0.0367,
      "step": 9500
    },
    {
      "epoch": 9.765625,
      "grad_norm": 5.822772026062012,
      "learning_rate": 2e-05,
      "loss": 0.0391,
      "step": 10000
    }
  ],
  "logging_steps": 500,
  "max_steps": 10240,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 1000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.3193555713038746e+17,
  "train_batch_size": 3,
  "trial_name": null,
  "trial_params": null
}