Hugging Face's logo

ProbeX
/
Model-J__DINO__model_idx_0030

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__DINO__model_idx_0030
File size: 3,272 Bytes 
c93ed36
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.9186666666666666,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0030/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": Infinity,
      "learning_rate": 8.559608050575152e-05,
      "loss": 0.8828,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8184,
      "eval_loss": 0.6128016114234924,
      "eval_runtime": 7.3189,
      "eval_samples_per_second": 512.372,
      "eval_steps_per_second": 8.061,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 32.61555480957031,
      "learning_rate": 7.31517728663805e-05,
      "loss": 0.3202,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8221333333333334,
      "eval_loss": 0.6260032653808594,
      "eval_runtime": 7.1242,
      "eval_samples_per_second": 526.378,
      "eval_steps_per_second": 8.282,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.5233240723609924,
      "learning_rate": 5.5131661351986275e-05,
      "loss": 0.1648,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8765333333333334,
      "eval_loss": 0.44706210494041443,
      "eval_runtime": 7.3698,
      "eval_samples_per_second": 508.833,
      "eval_steps_per_second": 8.006,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.000917166646104306,
      "learning_rate": 3.5104850050159014e-05,
      "loss": 0.0724,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8946666666666667,
      "eval_loss": 0.40692299604415894,
      "eval_runtime": 8.243,
      "eval_samples_per_second": 454.929,
      "eval_steps_per_second": 7.158,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.00038406875682994723,
      "learning_rate": 1.703789455194791e-05,
      "loss": 0.0248,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9106666666666666,
      "eval_loss": 0.3725508749485016,
      "eval_runtime": 7.1312,
      "eval_samples_per_second": 525.86,
      "eval_steps_per_second": 8.274,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 1.3747600317001343,
      "learning_rate": 4.509176970441849e-06,
      "loss": 0.0066,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9186666666666666,
      "eval_loss": 0.34563976526260376,
      "eval_runtime": 7.2679,
      "eval_samples_per_second": 515.964,
      "eval_steps_per_second": 8.118,
      "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
}