Hugging Face's logo

ProbeX
/
Model-J__DINO__model_idx_0046

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__DINO__model_idx_0046
File size: 3,270 Bytes 
690140a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": 0.42506666666666665,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0046/checkpoints/checkpoint-1998",
  "epoch": 6.0,
  "eval_steps": 500,
  "global_step": 1998,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": Infinity,
      "learning_rate": 0.0002506006006006006,
      "loss": 3.3755,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.22026666666666667,
      "eval_loss": 2.9119625091552734,
      "eval_runtime": 6.9829,
      "eval_samples_per_second": 537.025,
      "eval_steps_per_second": 8.449,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 32.121822357177734,
      "learning_rate": 0.00020060060060060058,
      "loss": 2.7734,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.27413333333333334,
      "eval_loss": 2.688741683959961,
      "eval_runtime": 6.8455,
      "eval_samples_per_second": 547.808,
      "eval_steps_per_second": 8.619,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 36.332027435302734,
      "learning_rate": 0.00015060060060060059,
      "loss": 2.5085,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.32853333333333334,
      "eval_loss": 2.4903953075408936,
      "eval_runtime": 6.3807,
      "eval_samples_per_second": 587.712,
      "eval_steps_per_second": 9.247,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 33.072200775146484,
      "learning_rate": 0.00010060060060060059,
      "loss": 2.2597,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.3528,
      "eval_loss": 2.3552920818328857,
      "eval_runtime": 6.4253,
      "eval_samples_per_second": 583.632,
      "eval_steps_per_second": 9.182,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 51.64991760253906,
      "learning_rate": 5.0600600600600595e-05,
      "loss": 1.9971,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.40213333333333334,
      "eval_loss": 2.190269708633423,
      "eval_runtime": 6.8912,
      "eval_samples_per_second": 544.169,
      "eval_steps_per_second": 8.562,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 72.71952819824219,
      "learning_rate": 6.006006006006005e-07,
      "loss": 1.6714,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.42506666666666665,
      "eval_loss": 2.1224143505096436,
      "eval_runtime": 7.0312,
      "eval_samples_per_second": 533.341,
      "eval_steps_per_second": 8.391,
      "step": 1998
    }
  ],
  "logging_steps": 500,
  "max_steps": 1998,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 6,
  "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": 9.88447923735552e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}