Hugging Face's logo

ProbeX
/
Model-J__DINO__model_idx_0706

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__DINO__model_idx_0706
File size: 3,302 Bytes 
a5f7094
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.9301333333333334,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0706/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": 21.341285705566406,
      "learning_rate": 4.7538820348083834e-05,
      "loss": 0.7774,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8661333333333333,
      "eval_loss": 0.45880475640296936,
      "eval_runtime": 11.7377,
      "eval_samples_per_second": 319.482,
      "eval_steps_per_second": 5.027,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.4442399740219116,
      "learning_rate": 4.063987381465584e-05,
      "loss": 0.2327,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8853333333333333,
      "eval_loss": 0.38525083661079407,
      "eval_runtime": 11.5992,
      "eval_samples_per_second": 323.297,
      "eval_steps_per_second": 5.087,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 58.370750427246094,
      "learning_rate": 3.0628700751103485e-05,
      "loss": 0.1019,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8997333333333334,
      "eval_loss": 0.35702675580978394,
      "eval_runtime": 11.6644,
      "eval_samples_per_second": 321.49,
      "eval_steps_per_second": 5.058,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.17564788460731506,
      "learning_rate": 1.950269447231056e-05,
      "loss": 0.0428,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9109333333333334,
      "eval_loss": 0.3443054258823395,
      "eval_runtime": 11.5027,
      "eval_samples_per_second": 326.012,
      "eval_steps_per_second": 5.129,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.06267327070236206,
      "learning_rate": 9.465496973304394e-06,
      "loss": 0.0169,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9253333333333333,
      "eval_loss": 0.3056645095348358,
      "eval_runtime": 12.1127,
      "eval_samples_per_second": 309.593,
      "eval_steps_per_second": 4.871,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.006667661014944315,
      "learning_rate": 2.5050983169121382e-06,
      "loss": 0.0029,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9301333333333334,
      "eval_loss": 0.3062782883644104,
      "eval_runtime": 11.6229,
      "eval_samples_per_second": 322.639,
      "eval_steps_per_second": 5.076,
      "step": 1998
    }
  ],
  "logging_steps": 500,
  "max_steps": 2331,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 7,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 9.88447923735552e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}