Hugging Face's logo

ProbeX
/
Model-J__DINO__model_idx_0962

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__DINO__model_idx_0962
File size: 3,663 Bytes 
9c77453
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.3797333333333333,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0962/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": 0.0004756789480311864,
      "loss": 3.3932,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.1872,
      "eval_loss": 3.0484557151794434,
      "eval_runtime": 12.4021,
      "eval_samples_per_second": 302.368,
      "eval_steps_per_second": 4.757,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 27.146533966064453,
      "learning_rate": 0.00040666145609878347,
      "loss": 2.9281,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.21653333333333333,
      "eval_loss": 2.8504514694213867,
      "eval_runtime": 12.4096,
      "eval_samples_per_second": 302.186,
      "eval_steps_per_second": 4.754,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 13.535613059997559,
      "learning_rate": 0.0003066152414593445,
      "loss": 2.7094,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.26426666666666665,
      "eval_loss": 2.6875808238983154,
      "eval_runtime": 12.3994,
      "eval_samples_per_second": 302.434,
      "eval_steps_per_second": 4.758,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 19.036958694458008,
      "learning_rate": 0.000195355683908512,
      "loss": 2.4975,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.3024,
      "eval_loss": 2.5020968914031982,
      "eval_runtime": 12.3612,
      "eval_samples_per_second": 303.369,
      "eval_steps_per_second": 4.773,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 25.925630569458008,
      "learning_rate": 9.491910332815573e-05,
      "loss": 2.2606,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.3466666666666667,
      "eval_loss": 2.346385955810547,
      "eval_runtime": 12.3237,
      "eval_samples_per_second": 304.292,
      "eval_steps_per_second": 4.788,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 33.482521057128906,
      "learning_rate": 2.519819627604078e-05,
      "loss": 2.0177,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.3701333333333333,
      "eval_loss": 2.243748664855957,
      "eval_runtime": 12.3849,
      "eval_samples_per_second": 302.787,
      "eval_steps_per_second": 4.764,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 29.013111114501953,
      "learning_rate": 2.0434646496314548e-09,
      "loss": 1.8315,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.3797333333333333,
      "eval_loss": 2.249297857284546,
      "eval_runtime": 11.7727,
      "eval_samples_per_second": 318.532,
      "eval_steps_per_second": 5.012,
      "step": 2331
    }
  ],
  "logging_steps": 500,
  "max_steps": 2331,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 7,
  "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": 1.153189244358144e+19,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}