Hugging Face's logo

SystemAdmin123
/
CodeLlama-7b-hf

Safetensors
llama
Model card Files
xet
Community
CodeLlama-7b-hf
File size: 2,573 Bytes 
0d82ec1
 
 
0a52e9f
15ca0d9
0a52e9f
0d82ec1
 
 
 
 
943b793
 
15ca0d9
 
 
0d82ec1
 
 
943b793
15ca0d9
943b793
15ca0d9
0d82ec1
 
 
943b793
15ca0d9
943b793
15ca0d9
0d82ec1
 
 
15ca0d9
 
 
 
 
 
7e59b56
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
0a52e9f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
0d82ec1
 
 
943b793
0d82ec1
943b793
15ca0d9
0d82ec1
 
 
 
 
 
 
 
 
 
 
 
0a52e9f
0d82ec1
 
 
 
 
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_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.5555555555555556,
  "eval_steps": 20,
  "global_step": 60,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.009259259259259259,
      "eval_loss": 2.1662161350250244,
      "eval_runtime": 31.2323,
      "eval_samples_per_second": 48.059,
      "eval_steps_per_second": 6.019,
      "step": 1
    },
    {
      "epoch": 0.09259259259259259,
      "grad_norm": 2.140625,
      "learning_rate": 6.666666666666667e-05,
      "loss": 1.8573,
      "step": 10
    },
    {
      "epoch": 0.18518518518518517,
      "grad_norm": 1.5390625,
      "learning_rate": 0.00013333333333333334,
      "loss": 1.8314,
      "step": 20
    },
    {
      "epoch": 0.18518518518518517,
      "eval_loss": 1.7036446332931519,
      "eval_runtime": 27.1456,
      "eval_samples_per_second": 55.294,
      "eval_steps_per_second": 6.926,
      "step": 20
    },
    {
      "epoch": 0.2777777777777778,
      "grad_norm": 1.765625,
      "learning_rate": 0.0002,
      "loss": 1.8651,
      "step": 30
    },
    {
      "epoch": 0.37037037037037035,
      "grad_norm": 1.5390625,
      "learning_rate": 0.00019984815164333163,
      "loss": 1.9748,
      "step": 40
    },
    {
      "epoch": 0.37037037037037035,
      "eval_loss": 1.8448469638824463,
      "eval_runtime": 42.3761,
      "eval_samples_per_second": 35.421,
      "eval_steps_per_second": 4.436,
      "step": 40
    },
    {
      "epoch": 0.46296296296296297,
      "grad_norm": 1.25,
      "learning_rate": 0.00019939306773179497,
      "loss": 2.0039,
      "step": 50
    },
    {
      "epoch": 0.5555555555555556,
      "grad_norm": 1.25,
      "learning_rate": 0.00019863613034027224,
      "loss": 2.0413,
      "step": 60
    },
    {
      "epoch": 0.5555555555555556,
      "eval_loss": 1.89992094039917,
      "eval_runtime": 42.6851,
      "eval_samples_per_second": 35.164,
      "eval_steps_per_second": 4.404,
      "step": 60
    }
  ],
  "logging_steps": 10,
  "max_steps": 600,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 6,
  "save_steps": 20,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.897208656730522e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}