Hugging Face's logo

ProbeX
/
Model-J__DINO__model_idx_0346

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__DINO__model_idx_0346
File size: 3,666 Bytes 
be59efc
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
 
{
  "best_metric": 0.9104,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0346/checkpoints/checkpoint-2331",
  "epoch": 7.0,
  "eval_steps": 500,
  "global_step": 2331,
  "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": 4.7567894803118645e-05,
      "loss": 0.9641,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8362666666666667,
      "eval_loss": 0.5312649011611938,
      "eval_runtime": 12.709,
      "eval_samples_per_second": 295.066,
      "eval_steps_per_second": 4.642,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.23741275072097778,
      "learning_rate": 4.066614560987835e-05,
      "loss": 0.2762,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8717333333333334,
      "eval_loss": 0.42394503951072693,
      "eval_runtime": 10.8059,
      "eval_samples_per_second": 347.033,
      "eval_steps_per_second": 5.46,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 53.573429107666016,
      "learning_rate": 3.066152414593445e-05,
      "loss": 0.1265,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8901333333333333,
      "eval_loss": 0.40139710903167725,
      "eval_runtime": 10.9885,
      "eval_samples_per_second": 341.265,
      "eval_steps_per_second": 5.369,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 4.7543625831604,
      "learning_rate": 1.95355683908512e-05,
      "loss": 0.0539,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8946666666666667,
      "eval_loss": 0.4062662720680237,
      "eval_runtime": 11.5291,
      "eval_samples_per_second": 325.264,
      "eval_steps_per_second": 5.117,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.8771946430206299,
      "learning_rate": 9.491910332815573e-06,
      "loss": 0.0166,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9077333333333333,
      "eval_loss": 0.3681637942790985,
      "eval_runtime": 11.7165,
      "eval_samples_per_second": 320.061,
      "eval_steps_per_second": 5.036,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.07285254448652267,
      "learning_rate": 2.5198196276040782e-06,
      "loss": 0.0046,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9098666666666667,
      "eval_loss": 0.369238942861557,
      "eval_runtime": 11.1554,
      "eval_samples_per_second": 336.159,
      "eval_steps_per_second": 5.289,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.026230547577142715,
      "learning_rate": 2.0434646496314548e-10,
      "loss": 0.0016,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.9104,
      "eval_loss": 0.35300731658935547,
      "eval_runtime": 11.3368,
      "eval_samples_per_second": 330.782,
      "eval_steps_per_second": 5.204,
      "step": 2331
    }
  ],
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.153189244358144e+19,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}