Hugging Face's logo

ProbeX
/
Model-J__DINO__model_idx_0590

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__DINO__model_idx_0590
File size: 2,444 Bytes 
112b44a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": 0.9328,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0590/checkpoints/checkpoint-1332",
  "epoch": 4.0,
  "eval_steps": 500,
  "global_step": 1332,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 0.03547203913331032,
      "learning_rate": 6.756756756756757e-05,
      "loss": 0.7255,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8674666666666667,
      "eval_loss": 0.4538843333721161,
      "eval_runtime": 12.5436,
      "eval_samples_per_second": 298.957,
      "eval_steps_per_second": 4.704,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 12.279327392578125,
      "learning_rate": 4.5067567567567564e-05,
      "loss": 0.1887,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8933333333333333,
      "eval_loss": 0.37443411350250244,
      "eval_runtime": 12.8079,
      "eval_samples_per_second": 292.788,
      "eval_steps_per_second": 4.607,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": Infinity,
      "learning_rate": 2.2635135135135137e-05,
      "loss": 0.0621,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9152,
      "eval_loss": 0.31955039501190186,
      "eval_runtime": 13.133,
      "eval_samples_per_second": 285.54,
      "eval_steps_per_second": 4.492,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.010655202902853489,
      "learning_rate": 1.3513513513513515e-07,
      "loss": 0.0121,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9328,
      "eval_loss": 0.2547186613082886,
      "eval_runtime": 13.0798,
      "eval_samples_per_second": 286.702,
      "eval_steps_per_second": 4.511,
      "step": 1332
    }
  ],
  "logging_steps": 500,
  "max_steps": 1332,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "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": 6.58965282490368e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}