Hugging Face's logo

ProbeX
/
Model-J__DINO__model_idx_0889

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__DINO__model_idx_0889
File size: 3,290 Bytes 
8a78045
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.9034666666666666,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0889/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": 0.13092045485973358,
      "learning_rate": 9.334052586261965e-05,
      "loss": 0.9288,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8173333333333334,
      "eval_loss": 0.5767544507980347,
      "eval_runtime": 7.3783,
      "eval_samples_per_second": 508.248,
      "eval_steps_per_second": 7.996,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.23297905921936035,
      "learning_rate": 7.506805462938029e-05,
      "loss": 0.313,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8325333333333333,
      "eval_loss": 0.5593457818031311,
      "eval_runtime": 6.9538,
      "eval_samples_per_second": 539.277,
      "eval_steps_per_second": 8.485,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 2.5079262256622314,
      "learning_rate": 5.007861840237923e-05,
      "loss": 0.1351,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8613333333333333,
      "eval_loss": 0.5354680418968201,
      "eval_runtime": 6.8495,
      "eval_samples_per_second": 547.487,
      "eval_steps_per_second": 8.614,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.002494129817932844,
      "learning_rate": 2.506811643795042e-05,
      "loss": 0.0461,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8834666666666666,
      "eval_loss": 0.4986306428909302,
      "eval_runtime": 7.1161,
      "eval_samples_per_second": 526.973,
      "eval_steps_per_second": 8.291,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.020856967195868492,
      "learning_rate": 6.738092539759589e-06,
      "loss": 0.0076,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9005333333333333,
      "eval_loss": 0.43117111921310425,
      "eval_runtime": 7.7729,
      "eval_samples_per_second": 482.442,
      "eval_steps_per_second": 7.59,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 3.65373158454895,
      "learning_rate": 6.180857012871855e-11,
      "loss": 0.0014,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9034666666666666,
      "eval_loss": 0.42426878213882446,
      "eval_runtime": 6.9011,
      "eval_samples_per_second": 543.391,
      "eval_steps_per_second": 8.549,
      "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
}