Hugging Face's logo

k1h0
/
codellama-7b-ia3-java

PEFT
TensorBoard
Safetensors
Model card Files
xet
 Metrics Community
codellama-7b-ia3-java
File size: 2,468 Bytes
5890030
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.990578734858681,
  "eval_steps": 500,
  "global_step": 92,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.010767160161507403,
      "grad_norm": 0.006398230325430632,
      "learning_rate": 2e-05,
      "loss": 0.8417,
      "step": 1
    },
    {
      "epoch": 0.10767160161507403,
      "grad_norm": 0.03447544574737549,
      "learning_rate": 0.0002,
      "loss": 1.5005,
      "step": 10
    },
    {
      "epoch": 0.21534320323014805,
      "grad_norm": 0.020084939897060394,
      "learning_rate": 0.000175609756097561,
      "loss": 1.4079,
      "step": 20
    },
    {
      "epoch": 0.32301480484522205,
      "grad_norm": 0.01294423546642065,
      "learning_rate": 0.00015121951219512197,
      "loss": 1.4586,
      "step": 30
    },
    {
      "epoch": 0.4306864064602961,
      "grad_norm": 0.007237937767058611,
      "learning_rate": 0.00012682926829268293,
      "loss": 1.3782,
      "step": 40
    },
    {
      "epoch": 0.5383580080753702,
      "grad_norm": 0.022302279248833656,
      "learning_rate": 0.0001024390243902439,
      "loss": 1.4701,
      "step": 50
    },
    {
      "epoch": 0.6460296096904441,
      "grad_norm": 0.01918647438287735,
      "learning_rate": 7.804878048780489e-05,
      "loss": 1.268,
      "step": 60
    },
    {
      "epoch": 0.7537012113055181,
      "grad_norm": 0.017452461645007133,
      "learning_rate": 5.365853658536586e-05,
      "loss": 1.2663,
      "step": 70
    },
    {
      "epoch": 0.8613728129205922,
      "grad_norm": 0.012683959677815437,
      "learning_rate": 2.926829268292683e-05,
      "loss": 1.3445,
      "step": 80
    },
    {
      "epoch": 0.9690444145356663,
      "grad_norm": 0.012110305018723011,
      "learning_rate": 4.8780487804878055e-06,
      "loss": 1.3767,
      "step": 90
    }
  ],
  "logging_steps": 10,
  "max_steps": 92,
  "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": 2.325540472262492e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}