Hugging Face's logo

ProbeX
/
Model-J__DINO__model_idx_0702

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__DINO__model_idx_0702
File size: 3,890 Bytes 
2ce5ca7
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
 
{
  "best_metric": 0.8453333333333334,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0702/checkpoints/checkpoint-2664",
  "epoch": 8.0,
  "eval_steps": 500,
  "global_step": 2664,
  "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": 0.0001,
      "loss": 0.946,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8112,
      "eval_loss": 0.6392398476600647,
      "eval_runtime": 13.3762,
      "eval_samples_per_second": 280.349,
      "eval_steps_per_second": 4.411,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.4604071378707886,
      "learning_rate": 0.0001,
      "loss": 0.4005,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8317333333333333,
      "eval_loss": 0.5749013423919678,
      "eval_runtime": 13.2989,
      "eval_samples_per_second": 281.978,
      "eval_steps_per_second": 4.436,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 63.05999755859375,
      "learning_rate": 0.0001,
      "loss": 0.2805,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8424,
      "eval_loss": 0.5639004111289978,
      "eval_runtime": 13.2901,
      "eval_samples_per_second": 282.164,
      "eval_steps_per_second": 4.439,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 1.2397186756134033,
      "learning_rate": 0.0001,
      "loss": 0.2086,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8304,
      "eval_loss": 0.6406498551368713,
      "eval_runtime": 13.3441,
      "eval_samples_per_second": 281.023,
      "eval_steps_per_second": 4.421,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 7.314879894256592,
      "learning_rate": 0.0001,
      "loss": 0.1665,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.828,
      "eval_loss": 0.6785334348678589,
      "eval_runtime": 13.5021,
      "eval_samples_per_second": 277.736,
      "eval_steps_per_second": 4.37,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.034189701080322266,
      "learning_rate": 0.0001,
      "loss": 0.1587,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8392,
      "eval_loss": 0.631488561630249,
      "eval_runtime": 13.4094,
      "eval_samples_per_second": 279.654,
      "eval_steps_per_second": 4.4,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 33.375999450683594,
      "learning_rate": 0.0001,
      "loss": 0.132,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.8232,
      "eval_loss": 0.7299953103065491,
      "eval_runtime": 13.4099,
      "eval_samples_per_second": 279.643,
      "eval_steps_per_second": 4.4,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 8.396727561950684,
      "learning_rate": 0.0001,
      "loss": 0.1319,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.8453333333333334,
      "eval_loss": 0.6151342391967773,
      "eval_runtime": 13.9753,
      "eval_samples_per_second": 268.331,
      "eval_steps_per_second": 4.222,
      "step": 2664
    }
  ],
  "logging_steps": 500,
  "max_steps": 2997,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 9,
  "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": 1.317930564980736e+19,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}