Hugging Face's logo

ProbeX
/
Model-J__DINO__model_idx_0695

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__DINO__model_idx_0695
File size: 3,247 Bytes 
1ba7eb3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.9136,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0695/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": 14.306386947631836,
      "learning_rate": 4.2878592878592884e-05,
      "loss": 0.8206,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8613333333333333,
      "eval_loss": 0.4550783932209015,
      "eval_runtime": 13.3228,
      "eval_samples_per_second": 281.472,
      "eval_steps_per_second": 4.428,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 37.43409729003906,
      "learning_rate": 3.573573573573574e-05,
      "loss": 0.2474,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8736,
      "eval_loss": 0.3982352912425995,
      "eval_runtime": 13.1137,
      "eval_samples_per_second": 285.959,
      "eval_steps_per_second": 4.499,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 3.9315435886383057,
      "learning_rate": 2.8592878592878596e-05,
      "loss": 0.1043,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.888,
      "eval_loss": 0.38039442896842957,
      "eval_runtime": 17.8016,
      "eval_samples_per_second": 210.655,
      "eval_steps_per_second": 3.314,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.0545400008559227,
      "learning_rate": 2.1450021450021453e-05,
      "loss": 0.0519,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9005333333333333,
      "eval_loss": 0.36097225546836853,
      "eval_runtime": 13.0776,
      "eval_samples_per_second": 286.749,
      "eval_steps_per_second": 4.512,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 52.24064636230469,
      "learning_rate": 1.4307164307164309e-05,
      "loss": 0.0216,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9037333333333334,
      "eval_loss": 0.3738444745540619,
      "eval_runtime": 13.0908,
      "eval_samples_per_second": 286.461,
      "eval_steps_per_second": 4.507,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.03491303697228432,
      "learning_rate": 7.164307164307164e-06,
      "loss": 0.0072,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9136,
      "eval_loss": 0.3495083153247833,
      "eval_runtime": 13.127,
      "eval_samples_per_second": 285.67,
      "eval_steps_per_second": 4.495,
      "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
}