Hugging Face's logo

ProbeX
/
Model-J__DINO__model_idx_0157

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__DINO__model_idx_0157
File size: 3,267 Bytes 
beefca5
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.9114666666666666,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0157/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": 0.16674651205539703,
      "learning_rate": 8.580008580008581e-05,
      "loss": 1.1012,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8197333333333333,
      "eval_loss": 0.575306236743927,
      "eval_runtime": 6.79,
      "eval_samples_per_second": 552.286,
      "eval_steps_per_second": 8.689,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": Infinity,
      "learning_rate": 7.155727155727156e-05,
      "loss": 0.3657,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8616,
      "eval_loss": 0.4666767120361328,
      "eval_runtime": 6.6656,
      "eval_samples_per_second": 562.588,
      "eval_steps_per_second": 8.851,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.934562087059021,
      "learning_rate": 5.727155727155728e-05,
      "loss": 0.1639,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8578666666666667,
      "eval_loss": 0.510015070438385,
      "eval_runtime": 6.7363,
      "eval_samples_per_second": 556.685,
      "eval_steps_per_second": 8.759,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.07840921729803085,
      "learning_rate": 4.298584298584299e-05,
      "loss": 0.0817,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8757333333333334,
      "eval_loss": 0.47795552015304565,
      "eval_runtime": 6.8524,
      "eval_samples_per_second": 547.251,
      "eval_steps_per_second": 8.61,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.008013253100216389,
      "learning_rate": 2.8700128700128703e-05,
      "loss": 0.0432,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8917333333333334,
      "eval_loss": 0.44084951281547546,
      "eval_runtime": 7.031,
      "eval_samples_per_second": 533.353,
      "eval_steps_per_second": 8.391,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.019317185506224632,
      "learning_rate": 1.4414414414414416e-05,
      "loss": 0.0135,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9114666666666666,
      "eval_loss": 0.3724452257156372,
      "eval_runtime": 6.6893,
      "eval_samples_per_second": 560.594,
      "eval_steps_per_second": 8.82,
      "step": 1998
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 9.88447923735552e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}