Hugging Face's logo

ProbeX
/
Model-J__DINO__model_idx_0221

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__DINO__model_idx_0221
File size: 3,662 Bytes 
21fc300
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.9208,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0221/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": 48.45054626464844,
      "learning_rate": 8.661507935327383e-05,
      "loss": 0.8032,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8592,
      "eval_loss": 0.48078104853630066,
      "eval_runtime": 6.2209,
      "eval_samples_per_second": 602.808,
      "eval_steps_per_second": 9.484,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.3851782083511353,
      "learning_rate": 7.689476527896773e-05,
      "loss": 0.2648,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8637333333333334,
      "eval_loss": 0.4972417950630188,
      "eval_runtime": 6.255,
      "eval_samples_per_second": 599.518,
      "eval_steps_per_second": 9.432,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 43.53612518310547,
      "learning_rate": 6.231876231770601e-05,
      "loss": 0.1405,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8661333333333333,
      "eval_loss": 0.5204830169677734,
      "eval_runtime": 6.2547,
      "eval_samples_per_second": 599.551,
      "eval_steps_per_second": 9.433,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.011021789163351059,
      "learning_rate": 4.510613478854492e-05,
      "loss": 0.0701,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8901333333333333,
      "eval_loss": 0.4364476501941681,
      "eval_runtime": 6.7889,
      "eval_samples_per_second": 552.37,
      "eval_steps_per_second": 8.691,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.000544319802429527,
      "learning_rate": 2.7877349199942123e-05,
      "loss": 0.0277,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9069333333333334,
      "eval_loss": 0.3994794189929962,
      "eval_runtime": 6.2995,
      "eval_samples_per_second": 595.288,
      "eval_steps_per_second": 9.366,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.00033232022542506456,
      "learning_rate": 1.3255331978432106e-05,
      "loss": 0.0045,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9146666666666666,
      "eval_loss": 0.3691798746585846,
      "eval_runtime": 7.4099,
      "eval_samples_per_second": 506.081,
      "eval_steps_per_second": 7.962,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.0005573926027864218,
      "learning_rate": 3.4661526970736e-06,
      "loss": 0.0013,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.9208,
      "eval_loss": 0.3570408523082733,
      "eval_runtime": 6.0328,
      "eval_samples_per_second": 621.602,
      "eval_steps_per_second": 9.78,
      "step": 2331
    }
  ],
  "logging_steps": 500,
  "max_steps": 2664,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 8,
  "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
}