Hugging Face's logo

ProbeX
/
Model-J__DINO__model_idx_0187

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__DINO__model_idx_0187
File size: 3,664 Bytes 
c8b3308
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.9424,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0187/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": 2.908839464187622,
      "learning_rate": 2.886495269365963e-05,
      "loss": 0.7643,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8866666666666667,
      "eval_loss": 0.3777833878993988,
      "eval_runtime": 6.8506,
      "eval_samples_per_second": 547.397,
      "eval_steps_per_second": 8.612,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 3.489156484603882,
      "learning_rate": 2.5619102456015873e-05,
      "loss": 0.1746,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9018666666666667,
      "eval_loss": 0.3219033181667328,
      "eval_runtime": 7.2088,
      "eval_samples_per_second": 520.196,
      "eval_steps_per_second": 8.184,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 3.5666627883911133,
      "learning_rate": 2.0756590131847176e-05,
      "loss": 0.0783,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9154666666666667,
      "eval_loss": 0.30058178305625916,
      "eval_runtime": 7.4461,
      "eval_samples_per_second": 503.618,
      "eval_steps_per_second": 7.924,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.10608753561973572,
      "learning_rate": 1.5017689143724237e-05,
      "loss": 0.0331,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9232,
      "eval_loss": 0.3046155273914337,
      "eval_runtime": 7.3143,
      "eval_samples_per_second": 512.695,
      "eval_steps_per_second": 8.066,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 2.3222718238830566,
      "learning_rate": 9.276095143821772e-06,
      "loss": 0.013,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9346666666666666,
      "eval_loss": 0.2656921148300171,
      "eval_runtime": 7.7004,
      "eval_samples_per_second": 486.985,
      "eval_steps_per_second": 7.662,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.0015815470833331347,
      "learning_rate": 4.4059137709457125e-06,
      "loss": 0.0037,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9373333333333334,
      "eval_loss": 0.2541326880455017,
      "eval_runtime": 7.3734,
      "eval_samples_per_second": 508.587,
      "eval_steps_per_second": 8.002,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.018114319071173668,
      "learning_rate": 1.1485859908123557e-06,
      "loss": 0.0014,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.9424,
      "eval_loss": 0.2530508041381836,
      "eval_runtime": 7.9492,
      "eval_samples_per_second": 471.744,
      "eval_steps_per_second": 7.422,
      "step": 2331
    }
  ],
  "logging_steps": 500,
  "max_steps": 2664,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 8,
  "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": 1.153189244358144e+19,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}