Hugging Face's logo

k1h0
/
DeepSeek-Coder-7B-Instruct-query_nsx_8_1

Text Generation
Transformers
Safetensors
llama
llama-factory
freeze
Generated from Trainer
conversational
text-generation-inference
Model card Files
xet
Community
DeepSeek-Coder-7B-Instruct-query_nsx_8_1
File size: 3,588 Bytes 
fbd8905
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9795918367346939,
  "eval_steps": 500,
  "global_step": 12,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.08163265306122448,
      "grad_norm": 0.5826467275619507,
      "learning_rate": 4.914814565722671e-05,
      "loss": 0.848,
      "num_input_tokens_seen": 2097152,
      "step": 1
    },
    {
      "epoch": 0.16326530612244897,
      "grad_norm": 0.5116532444953918,
      "learning_rate": 4.665063509461097e-05,
      "loss": 0.8111,
      "num_input_tokens_seen": 4194304,
      "step": 2
    },
    {
      "epoch": 0.24489795918367346,
      "grad_norm": 0.46351540088653564,
      "learning_rate": 4.267766952966369e-05,
      "loss": 0.7984,
      "num_input_tokens_seen": 6291456,
      "step": 3
    },
    {
      "epoch": 0.32653061224489793,
      "grad_norm": 0.39698782563209534,
      "learning_rate": 3.7500000000000003e-05,
      "loss": 0.7649,
      "num_input_tokens_seen": 8388608,
      "step": 4
    },
    {
      "epoch": 0.40816326530612246,
      "grad_norm": 0.3687557578086853,
      "learning_rate": 3.147047612756302e-05,
      "loss": 0.7687,
      "num_input_tokens_seen": 10485760,
      "step": 5
    },
    {
      "epoch": 0.4897959183673469,
      "grad_norm": 0.3421611785888672,
      "learning_rate": 2.5e-05,
      "loss": 0.7696,
      "num_input_tokens_seen": 12582912,
      "step": 6
    },
    {
      "epoch": 0.5714285714285714,
      "grad_norm": 0.3205947279930115,
      "learning_rate": 1.852952387243698e-05,
      "loss": 0.7488,
      "num_input_tokens_seen": 14680064,
      "step": 7
    },
    {
      "epoch": 0.6530612244897959,
      "grad_norm": 0.2887260913848877,
      "learning_rate": 1.2500000000000006e-05,
      "loss": 0.7368,
      "num_input_tokens_seen": 16777216,
      "step": 8
    },
    {
      "epoch": 0.7346938775510204,
      "grad_norm": 0.3012808561325073,
      "learning_rate": 7.3223304703363135e-06,
      "loss": 0.7088,
      "num_input_tokens_seen": 18874368,
      "step": 9
    },
    {
      "epoch": 0.8163265306122449,
      "grad_norm": 0.3112427592277527,
      "learning_rate": 3.3493649053890326e-06,
      "loss": 0.7054,
      "num_input_tokens_seen": 20971520,
      "step": 10
    },
    {
      "epoch": 0.8979591836734694,
      "grad_norm": 0.29755619168281555,
      "learning_rate": 8.51854342773295e-07,
      "loss": 0.7032,
      "num_input_tokens_seen": 23068672,
      "step": 11
    },
    {
      "epoch": 0.9795918367346939,
      "grad_norm": 0.30344462394714355,
      "learning_rate": 0.0,
      "loss": 0.7144,
      "num_input_tokens_seen": 25165824,
      "step": 12
    },
    {
      "epoch": 0.9795918367346939,
      "num_input_tokens_seen": 25165824,
      "step": 12,
      "total_flos": 9.800984115271434e+17,
      "train_loss": 0.7565137396256129,
      "train_runtime": 1221.0904,
      "train_samples_per_second": 5.136,
      "train_steps_per_second": 0.01
    }
  ],
  "logging_steps": 1,
  "max_steps": 12,
  "num_input_tokens_seen": 25165824,
  "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": 9.800984115271434e+17,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}