Hugging Face's logo

ProbeX
/
Model-J__DINO__model_idx_0006

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__DINO__model_idx_0006
File size: 3,679 Bytes 
ecb4d21
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
135
136
137
138
139
140
141
142
143
144
145
146
 
{
  "best_metric": 0.9189333333333334,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0006/checkpoints/checkpoint-2331",
  "epoch": 7.0,
  "eval_steps": 500,
  "global_step": 2331,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 1.1340930461883545,
      "learning_rate": 8.559608050575152e-05,
      "loss": 0.7934,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8261333333333334,
      "eval_loss": 0.5614354610443115,
      "eval_runtime": 5.8501,
      "eval_samples_per_second": 641.017,
      "eval_steps_per_second": 10.085,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 19.052743911743164,
      "learning_rate": 7.31517728663805e-05,
      "loss": 0.278,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8432,
      "eval_loss": 0.5140930414199829,
      "eval_runtime": 5.946,
      "eval_samples_per_second": 630.681,
      "eval_steps_per_second": 9.923,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.0020932629704475403,
      "learning_rate": 5.5131661351986275e-05,
      "loss": 0.1302,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8821333333333333,
      "eval_loss": 0.42049771547317505,
      "eval_runtime": 5.7376,
      "eval_samples_per_second": 653.58,
      "eval_steps_per_second": 10.283,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 9.394673347473145,
      "learning_rate": 3.5104850050159014e-05,
      "loss": 0.0578,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9042666666666667,
      "eval_loss": 0.3749675750732422,
      "eval_runtime": 5.7669,
      "eval_samples_per_second": 650.262,
      "eval_steps_per_second": 10.231,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.015366042964160442,
      "learning_rate": 1.703789455194791e-05,
      "loss": 0.0153,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9101333333333333,
      "eval_loss": 0.35989752411842346,
      "eval_runtime": 6.0392,
      "eval_samples_per_second": 620.939,
      "eval_steps_per_second": 9.769,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.0033450990449637175,
      "learning_rate": 4.509176970441849e-06,
      "loss": 0.0021,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9176,
      "eval_loss": 0.3351859748363495,
      "eval_runtime": 5.8049,
      "eval_samples_per_second": 646.008,
      "eval_steps_per_second": 10.164,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.083200603723526,
      "learning_rate": 1.6347729569543557e-10,
      "loss": 0.0005,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.9189333333333334,
      "eval_loss": 0.33363083004951477,
      "eval_runtime": 5.5051,
      "eval_samples_per_second": 681.182,
      "eval_steps_per_second": 10.717,
      "step": 2331
    }
  ],
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.153189244358144e+19,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}