Hugging Face's logo

JerryFan011018
/
Qwen-Code-7B_2

TensorBoard
Safetensors
qwen2
4-bit precision
bitsandbytes
Model card Files
xet
 Metrics Community
Qwen-Code-7B_2
File size: 2,832 Bytes
0f60832
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
{
  "best_global_step": 75,
  "best_metric": 0.4043419659137726,
  "best_model_checkpoint": "/content/output/checkpoint-75",
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 75,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.13333333333333333,
      "grad_norm": 1.7940553426742554,
      "learning_rate": 5.917159763313609e-06,
      "loss": 1.3972,
      "mean_token_accuracy": 0.7618847399950027,
      "num_tokens": 31152.0,
      "step": 10
    },
    {
      "epoch": 0.26666666666666666,
      "grad_norm": 1.0511088371276855,
      "learning_rate": 1.1834319526627219e-05,
      "loss": 1.2288,
      "mean_token_accuracy": 0.7673537939786911,
      "num_tokens": 61773.0,
      "step": 20
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.8096975088119507,
      "learning_rate": 1.7751479289940828e-05,
      "loss": 0.9255,
      "mean_token_accuracy": 0.7948055118322372,
      "num_tokens": 94758.0,
      "step": 30
    },
    {
      "epoch": 0.5333333333333333,
      "grad_norm": 0.6213255524635315,
      "learning_rate": 2.3668639053254438e-05,
      "loss": 0.7366,
      "mean_token_accuracy": 0.8212289035320282,
      "num_tokens": 125915.0,
      "step": 40
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 0.42887863516807556,
      "learning_rate": 2.958579881656805e-05,
      "loss": 0.5556,
      "mean_token_accuracy": 0.8463607966899872,
      "num_tokens": 159364.0,
      "step": 50
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.5108550786972046,
      "learning_rate": 3.5502958579881656e-05,
      "loss": 0.4676,
      "mean_token_accuracy": 0.8614094287157059,
      "num_tokens": 190374.0,
      "step": 60
    },
    {
      "epoch": 0.9333333333333333,
      "grad_norm": 0.4310983121395111,
      "learning_rate": 4.142011834319527e-05,
      "loss": 0.4214,
      "mean_token_accuracy": 0.8710317760705948,
      "num_tokens": 222156.0,
      "step": 70
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.4043419659137726,
      "eval_mean_token_accuracy": 0.8734077858924866,
      "eval_num_tokens": 238011.0,
      "eval_runtime": 50.8925,
      "eval_samples_per_second": 1.965,
      "eval_steps_per_second": 0.491,
      "step": 75
    }
  ],
  "logging_steps": 10,
  "max_steps": 1125,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 15,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.4265270326931456e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}