Hugging Face's logo

emraherden
/
vhs-llama2

Text Generation
Transformers
PyTorch
TensorBoard
llama
Trained with AutoTrain
text-generation-inference
Inference Endpoints
Model card Files Metrics Community
vhs-llama2
File size: 2,149 Bytes 
8b953ef
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "global_step": 402,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.19,
      "learning_rate": 0.00012682926829268293,
      "loss": 1.8322,
      "step": 26
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00019390581717451522,
      "loss": 1.5787,
      "step": 52
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.00017950138504155126,
      "loss": 1.4229,
      "step": 78
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00016509695290858726,
      "loss": 1.347,
      "step": 104
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.00015069252077562327,
      "loss": 1.3379,
      "step": 130
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.0001362880886426593,
      "loss": 1.358,
      "step": 156
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.00012188365650969529,
      "loss": 1.3522,
      "step": 182
    },
    {
      "epoch": 1.55,
      "learning_rate": 0.0001074792243767313,
      "loss": 1.2781,
      "step": 208
    },
    {
      "epoch": 1.75,
      "learning_rate": 9.307479224376732e-05,
      "loss": 1.3247,
      "step": 234
    },
    {
      "epoch": 1.94,
      "learning_rate": 7.867036011080334e-05,
      "loss": 1.3194,
      "step": 260
    },
    {
      "epoch": 2.13,
      "learning_rate": 6.426592797783934e-05,
      "loss": 1.274,
      "step": 286
    },
    {
      "epoch": 2.33,
      "learning_rate": 4.986149584487535e-05,
      "loss": 1.3126,
      "step": 312
    },
    {
      "epoch": 2.52,
      "learning_rate": 3.545706371191136e-05,
      "loss": 1.3317,
      "step": 338
    },
    {
      "epoch": 2.72,
      "learning_rate": 2.105263157894737e-05,
      "loss": 1.2604,
      "step": 364
    },
    {
      "epoch": 2.91,
      "learning_rate": 6.64819944598338e-06,
      "loss": 1.1841,
      "step": 390
    }
  ],
  "max_steps": 402,
  "num_train_epochs": 3,
  "total_flos": 3.324593797123277e+16,
  "trial_name": null,
  "trial_params": null
}