Hugging Face's logo

Efficient-Large-Model
/
NVILA-Lite-8B-quantumn-qa-train

Safetensors
Model card Files
xet
Community
NVILA-Lite-8B-quantumn-qa-train
File size: 2,946 Bytes
342f304
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 13,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.08,
      "grad_norm": 130.75577214745246,
      "learning_rate": 2e-05,
      "loss": 1.2648,
      "step": 1
    },
    {
      "epoch": 0.15,
      "grad_norm": 126.67616596972118,
      "learning_rate": 1.9659258262890683e-05,
      "loss": 1.2283,
      "step": 2
    },
    {
      "epoch": 0.23,
      "grad_norm": 56.84219933724937,
      "learning_rate": 1.866025403784439e-05,
      "loss": 0.4188,
      "step": 3
    },
    {
      "epoch": 0.31,
      "grad_norm": 89.42666319016989,
      "learning_rate": 1.7071067811865477e-05,
      "loss": 2.4789,
      "step": 4
    },
    {
      "epoch": 0.38,
      "grad_norm": 72.41844398977439,
      "learning_rate": 1.5000000000000002e-05,
      "loss": 0.7853,
      "step": 5
    },
    {
      "epoch": 0.46,
      "grad_norm": 799.0148731599335,
      "learning_rate": 1.2588190451025209e-05,
      "loss": 8.2197,
      "step": 6
    },
    {
      "epoch": 0.54,
      "grad_norm": 34.525610403243014,
      "learning_rate": 1e-05,
      "loss": 0.3008,
      "step": 7
    },
    {
      "epoch": 0.62,
      "grad_norm": 64.98250527603693,
      "learning_rate": 7.411809548974792e-06,
      "loss": 0.3999,
      "step": 8
    },
    {
      "epoch": 0.69,
      "grad_norm": 11.46902235575636,
      "learning_rate": 5.000000000000003e-06,
      "loss": 0.2575,
      "step": 9
    },
    {
      "epoch": 0.77,
      "grad_norm": 42.63293180170212,
      "learning_rate": 2.9289321881345257e-06,
      "loss": 0.3174,
      "step": 10
    },
    {
      "epoch": 0.85,
      "grad_norm": 40.64988981794197,
      "learning_rate": 1.339745962155613e-06,
      "loss": 0.3054,
      "step": 11
    },
    {
      "epoch": 0.92,
      "grad_norm": 27.588182133457394,
      "learning_rate": 3.4074173710931804e-07,
      "loss": 0.2827,
      "step": 12
    },
    {
      "epoch": 1.0,
      "grad_norm": 17.48926557604337,
      "learning_rate": 0.0,
      "loss": 0.2751,
      "step": 13
    },
    {
      "epoch": 1.0,
      "step": 13,
      "total_flos": 0.0,
      "train_loss": 1.2718768601234143,
      "train_runtime": 323.0635,
      "train_samples_per_second": 41.206,
      "train_steps_per_second": 0.04
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 13,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": false,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}