Hugging Face's logo

ProbeX
/
Model-J__DINO__model_idx_0833

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__DINO__model_idx_0833
File size: 3,697 Bytes 
3e0744b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.4245333333333333,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0833/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": 20.952621459960938,
      "learning_rate": 0.0002887841425059038,
      "loss": 3.386,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.19866666666666666,
      "eval_loss": 2.990161418914795,
      "eval_runtime": 10.9539,
      "eval_samples_per_second": 342.343,
      "eval_steps_per_second": 5.386,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 21.175504684448242,
      "learning_rate": 0.0002564405961135417,
      "loss": 2.8443,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.26613333333333333,
      "eval_loss": 2.707578659057617,
      "eval_runtime": 10.8603,
      "eval_samples_per_second": 345.294,
      "eval_steps_per_second": 5.433,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 25.48911476135254,
      "learning_rate": 0.0002078924338492993,
      "loss": 2.5585,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.3221333333333333,
      "eval_loss": 2.4773309230804443,
      "eval_runtime": 10.8301,
      "eval_samples_per_second": 346.258,
      "eval_steps_per_second": 5.448,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 24.555652618408203,
      "learning_rate": 0.00015053067332772077,
      "loss": 2.2852,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.37146666666666667,
      "eval_loss": 2.281773328781128,
      "eval_runtime": 10.855,
      "eval_samples_per_second": 345.464,
      "eval_steps_per_second": 5.435,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 32.06581497192383,
      "learning_rate": 9.308812260256249e-05,
      "loss": 1.9778,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.3957333333333333,
      "eval_loss": 2.2004384994506836,
      "eval_runtime": 10.8553,
      "eval_samples_per_second": 345.454,
      "eval_steps_per_second": 5.435,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 24.560232162475586,
      "learning_rate": 4.4309889303710674e-05,
      "loss": 1.6037,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.42213333333333336,
      "eval_loss": 2.187387466430664,
      "eval_runtime": 10.8831,
      "eval_samples_per_second": 344.572,
      "eval_steps_per_second": 5.421,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 14.999958038330078,
      "learning_rate": 1.1622017275129708e-05,
      "loss": 1.1678,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.4245333333333333,
      "eval_loss": 2.3592259883880615,
      "eval_runtime": 11.3521,
      "eval_samples_per_second": 330.334,
      "eval_steps_per_second": 5.197,
      "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
}