Hugging Face's logo

ProbeX
/
Model-J__DINO__model_idx_0332

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__DINO__model_idx_0332
File size: 3,249 Bytes 
12417da
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.9050666666666667,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0332/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": 0.33917662501335144,
      "learning_rate": 8.343343343343344e-05,
      "loss": 0.853,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8288,
      "eval_loss": 0.5166187286376953,
      "eval_runtime": 7.8915,
      "eval_samples_per_second": 475.193,
      "eval_steps_per_second": 7.476,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 4.514943599700928,
      "learning_rate": 6.676676676676677e-05,
      "loss": 0.282,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8629333333333333,
      "eval_loss": 0.48256444931030273,
      "eval_runtime": 7.4479,
      "eval_samples_per_second": 503.498,
      "eval_steps_per_second": 7.922,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 1.0831409692764282,
      "learning_rate": 5.01001001001001e-05,
      "loss": 0.1241,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8568,
      "eval_loss": 0.5356321334838867,
      "eval_runtime": 6.3778,
      "eval_samples_per_second": 587.974,
      "eval_steps_per_second": 9.251,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 33.30329513549805,
      "learning_rate": 3.3433433433433435e-05,
      "loss": 0.0564,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8864,
      "eval_loss": 0.4194045066833496,
      "eval_runtime": 6.6439,
      "eval_samples_per_second": 564.425,
      "eval_steps_per_second": 8.88,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 7.189412593841553,
      "learning_rate": 1.6766766766766767e-05,
      "loss": 0.0177,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9029333333333334,
      "eval_loss": 0.3980278968811035,
      "eval_runtime": 7.1115,
      "eval_samples_per_second": 527.315,
      "eval_steps_per_second": 8.296,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.006817310582846403,
      "learning_rate": 1.001001001001001e-07,
      "loss": 0.003,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9050666666666667,
      "eval_loss": 0.37177354097366333,
      "eval_runtime": 7.3765,
      "eval_samples_per_second": 508.369,
      "eval_steps_per_second": 7.998,
      "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
}