Hugging Face's logo

ProbeX
/
Model-J__DINO__model_idx_0096

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__DINO__model_idx_0096
File size: 3,168 Bytes 
24bc268
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": 0.2866666666666667,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0096/checkpoints/checkpoint-1998",
  "epoch": 6.0,
  "eval_steps": 500,
  "global_step": 1998,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 18.05211639404297,
      "learning_rate": 0.0005,
      "loss": 3.4786,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.17013333333333333,
      "eval_loss": 3.1218314170837402,
      "eval_runtime": 6.7286,
      "eval_samples_per_second": 557.324,
      "eval_steps_per_second": 8.769,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 18.08905792236328,
      "learning_rate": 0.0005,
      "loss": 3.0285,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.2136,
      "eval_loss": 2.9907190799713135,
      "eval_runtime": 5.9364,
      "eval_samples_per_second": 631.7,
      "eval_steps_per_second": 9.939,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 20.191009521484375,
      "learning_rate": 0.0005,
      "loss": 2.8883,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.228,
      "eval_loss": 2.8460140228271484,
      "eval_runtime": 6.0814,
      "eval_samples_per_second": 616.637,
      "eval_steps_per_second": 9.702,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 21.748201370239258,
      "learning_rate": 0.0005,
      "loss": 2.7675,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.25893333333333335,
      "eval_loss": 2.7487900257110596,
      "eval_runtime": 5.9216,
      "eval_samples_per_second": 633.271,
      "eval_steps_per_second": 9.963,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 17.646074295043945,
      "learning_rate": 0.0005,
      "loss": 2.6775,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.26106666666666667,
      "eval_loss": 2.7286477088928223,
      "eval_runtime": 6.0383,
      "eval_samples_per_second": 621.04,
      "eval_steps_per_second": 9.771,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 14.903458595275879,
      "learning_rate": 0.0005,
      "loss": 2.5656,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.2866666666666667,
      "eval_loss": 2.5900521278381348,
      "eval_runtime": 7.295,
      "eval_samples_per_second": 514.051,
      "eval_steps_per_second": 8.088,
      "step": 1998
    }
  ],
  "logging_steps": 500,
  "max_steps": 1998,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 6,
  "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": 9.88447923735552e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}