Hugging Face's logo

ProbeX
/
Model-J__DINO__model_idx_0061

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__DINO__model_idx_0061
File size: 3,640 Bytes 
4188a90
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.3592,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0061/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": 0.0004813069041765065,
      "loss": 3.5284,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.168,
      "eval_loss": 3.1685338020324707,
      "eval_runtime": 10.3058,
      "eval_samples_per_second": 363.872,
      "eval_steps_per_second": 5.725,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 20.043869018554688,
      "learning_rate": 0.00042740099352256953,
      "loss": 3.0972,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.20773333333333333,
      "eval_loss": 2.990967273712158,
      "eval_runtime": 10.4976,
      "eval_samples_per_second": 357.224,
      "eval_steps_per_second": 5.62,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 12.107348442077637,
      "learning_rate": 0.0003464873897488322,
      "loss": 2.9284,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.2456,
      "eval_loss": 2.8646700382232666,
      "eval_runtime": 10.57,
      "eval_samples_per_second": 354.778,
      "eval_steps_per_second": 5.582,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 14.005638122558594,
      "learning_rate": 0.00025088445554620134,
      "loss": 2.7386,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.27813333333333334,
      "eval_loss": 2.7348146438598633,
      "eval_runtime": 10.6626,
      "eval_samples_per_second": 351.696,
      "eval_steps_per_second": 5.533,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 18.529733657836914,
      "learning_rate": 0.00015514687100427082,
      "loss": 2.5624,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.3138666666666667,
      "eval_loss": 2.614886522293091,
      "eval_runtime": 10.1765,
      "eval_samples_per_second": 368.496,
      "eval_steps_per_second": 5.798,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 22.400348663330078,
      "learning_rate": 7.384981550618446e-05,
      "loss": 2.3432,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.34373333333333334,
      "eval_loss": 2.4683566093444824,
      "eval_runtime": 10.2447,
      "eval_samples_per_second": 366.042,
      "eval_steps_per_second": 5.759,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 25.454923629760742,
      "learning_rate": 1.9370028791882848e-05,
      "loss": 2.1106,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.3592,
      "eval_loss": 2.485623598098755,
      "eval_runtime": 10.5255,
      "eval_samples_per_second": 356.278,
      "eval_steps_per_second": 5.605,
      "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
}