Hugging Face's logo

ProbeX
/
Model-J__DINO__model_idx_0349

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__DINO__model_idx_0349
File size: 3,270 Bytes 
dfd1d46
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.9165333333333333,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0349/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": 8.809326171875,
      "learning_rate": 2.5015015015015015e-05,
      "loss": 0.8173,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8701333333333333,
      "eval_loss": 0.4194171726703644,
      "eval_runtime": 11.7931,
      "eval_samples_per_second": 317.981,
      "eval_steps_per_second": 5.003,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 6.131776332855225,
      "learning_rate": 2.0015015015015016e-05,
      "loss": 0.21,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9024,
      "eval_loss": 0.3079501688480377,
      "eval_runtime": 11.4935,
      "eval_samples_per_second": 326.272,
      "eval_steps_per_second": 5.133,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.3190288245677948,
      "learning_rate": 1.5015015015015016e-05,
      "loss": 0.0894,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9013333333333333,
      "eval_loss": 0.3323608338832855,
      "eval_runtime": 11.6005,
      "eval_samples_per_second": 323.263,
      "eval_steps_per_second": 5.086,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.004387297201901674,
      "learning_rate": 1.0015015015015017e-05,
      "loss": 0.0427,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9149333333333334,
      "eval_loss": 0.3049583435058594,
      "eval_runtime": 11.0212,
      "eval_samples_per_second": 340.254,
      "eval_steps_per_second": 5.353,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.006259611342102289,
      "learning_rate": 5.0150150150150156e-06,
      "loss": 0.0185,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9112,
      "eval_loss": 0.31098473072052,
      "eval_runtime": 11.6505,
      "eval_samples_per_second": 321.874,
      "eval_steps_per_second": 5.064,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.029622534289956093,
      "learning_rate": 1.5015015015015016e-08,
      "loss": 0.0082,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9165333333333333,
      "eval_loss": 0.298772931098938,
      "eval_runtime": 12.0873,
      "eval_samples_per_second": 310.243,
      "eval_steps_per_second": 4.881,
      "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
}