Hugging Face's logo

ProbeX
/
Model-J__DINO__model_idx_0434

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__DINO__model_idx_0434
File size: 3,265 Bytes 
d96f167
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.37093333333333334,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0434/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": 13.683552742004395,
      "learning_rate": 0.0004670935782735732,
      "loss": 3.4571,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.17466666666666666,
      "eval_loss": 3.1372792720794678,
      "eval_runtime": 7.1888,
      "eval_samples_per_second": 521.643,
      "eval_steps_per_second": 8.207,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 24.0032958984375,
      "learning_rate": 0.00037601988894783115,
      "loss": 2.9609,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.2264,
      "eval_loss": 2.9172396659851074,
      "eval_runtime": 7.0034,
      "eval_samples_per_second": 535.455,
      "eval_steps_per_second": 8.424,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 11.013992309570312,
      "learning_rate": 0.00025117927214825806,
      "loss": 2.7251,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.28373333333333334,
      "eval_loss": 2.668048858642578,
      "eval_runtime": 6.9604,
      "eval_samples_per_second": 538.765,
      "eval_steps_per_second": 8.477,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 18.03095817565918,
      "learning_rate": 0.00012602267032890265,
      "loss": 2.5021,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.3264,
      "eval_loss": 2.5225186347961426,
      "eval_runtime": 6.9652,
      "eval_samples_per_second": 538.389,
      "eval_steps_per_second": 8.471,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 11.915348052978516,
      "learning_rate": 3.408569387468488e-05,
      "loss": 2.2606,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.35973333333333335,
      "eval_loss": 2.3955254554748535,
      "eval_runtime": 7.1086,
      "eval_samples_per_second": 527.531,
      "eval_steps_per_second": 8.3,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 29.063615798950195,
      "learning_rate": 2.7813810714871766e-09,
      "loss": 2.1082,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.37093333333333334,
      "eval_loss": 2.3717334270477295,
      "eval_runtime": 7.1251,
      "eval_samples_per_second": 526.307,
      "eval_steps_per_second": 8.281,
      "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
}