Hugging Face's logo

ProbeX
/
Model-J__DINO__model_idx_0310

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__DINO__model_idx_0310
File size: 3,669 Bytes 
e4e4545
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.9021333333333333,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0310/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": Infinity,
      "learning_rate": 4.851018993780429e-05,
      "loss": 0.8796,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8309333333333333,
      "eval_loss": 0.5021674633026123,
      "eval_runtime": 6.4427,
      "eval_samples_per_second": 582.051,
      "eval_steps_per_second": 9.158,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 53.686614990234375,
      "learning_rate": 4.4184758936602036e-05,
      "loss": 0.2976,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8528,
      "eval_loss": 0.4695923924446106,
      "eval_runtime": 7.1158,
      "eval_samples_per_second": 526.995,
      "eval_steps_per_second": 8.291,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.013101628050208092,
      "learning_rate": 3.7545362870758595e-05,
      "loss": 0.1536,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8658666666666667,
      "eval_loss": 0.4508969485759735,
      "eval_runtime": 6.4521,
      "eval_samples_per_second": 581.204,
      "eval_steps_per_second": 9.144,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.17559736967086792,
      "learning_rate": 2.9392810892864702e-05,
      "loss": 0.083,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8770666666666667,
      "eval_loss": 0.42143282294273376,
      "eval_runtime": 6.7815,
      "eval_samples_per_second": 552.976,
      "eval_steps_per_second": 8.7,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.008988650515675545,
      "learning_rate": 2.0710421090307246e-05,
      "loss": 0.0474,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8864,
      "eval_loss": 0.4432026147842407,
      "eval_runtime": 6.9919,
      "eval_samples_per_second": 536.339,
      "eval_steps_per_second": 8.438,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.17322728037834167,
      "learning_rate": 1.2545417811701016e-05,
      "loss": 0.0198,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8877333333333334,
      "eval_loss": 0.4568477272987366,
      "eval_runtime": 5.8804,
      "eval_samples_per_second": 637.709,
      "eval_steps_per_second": 10.033,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.0700274109840393,
      "learning_rate": 5.882620955060414e-06,
      "loss": 0.0074,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.9021333333333333,
      "eval_loss": 0.42737382650375366,
      "eval_runtime": 5.8405,
      "eval_samples_per_second": 642.064,
      "eval_steps_per_second": 10.102,
      "step": 2331
    }
  ],
  "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": 1.153189244358144e+19,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}