Hugging Face's logo

ProbeX
/
Model-J__DINO__model_idx_0276

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__DINO__model_idx_0276
File size: 3,628 Bytes 
399891e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.3808,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0276/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": 0.00048141860138016556,
      "loss": 3.4776,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.17813333333333334,
      "eval_loss": 3.0998218059539795,
      "eval_runtime": 7.3154,
      "eval_samples_per_second": 512.614,
      "eval_steps_per_second": 8.065,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 22.238971710205078,
      "learning_rate": 0.00042760859989611786,
      "loss": 3.0046,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.21706666666666666,
      "eval_loss": 2.9106364250183105,
      "eval_runtime": 7.5117,
      "eval_samples_per_second": 499.22,
      "eval_steps_per_second": 7.854,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 22.960695266723633,
      "learning_rate": 0.00034675929910385353,
      "loss": 2.8131,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.26,
      "eval_loss": 2.7692458629608154,
      "eval_runtime": 7.271,
      "eval_samples_per_second": 515.75,
      "eval_steps_per_second": 8.114,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 13.635702133178711,
      "learning_rate": 0.00025117927214825806,
      "loss": 2.632,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.27973333333333333,
      "eval_loss": 2.63303542137146,
      "eval_runtime": 7.276,
      "eval_samples_per_second": 515.391,
      "eval_steps_per_second": 8.109,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 18.360942840576172,
      "learning_rate": 0.00015541971169821895,
      "loss": 2.4465,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.32453333333333334,
      "eval_loss": 2.461010456085205,
      "eval_runtime": 7.4875,
      "eval_samples_per_second": 500.838,
      "eval_steps_per_second": 7.88,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 20.5378360748291,
      "learning_rate": 7.405914276967749e-05,
      "loss": 2.2476,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.3568,
      "eval_loss": 2.337297201156616,
      "eval_runtime": 7.4488,
      "eval_samples_per_second": 503.439,
      "eval_steps_per_second": 7.921,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 22.043306350708008,
      "learning_rate": 1.9483974446610292e-05,
      "loss": 2.0587,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.3808,
      "eval_loss": 2.295948028564453,
      "eval_runtime": 7.4576,
      "eval_samples_per_second": 502.841,
      "eval_steps_per_second": 7.911,
      "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
}