Hugging Face's logo

ProbeX
/
Model-J__DINO__model_idx_0248

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__DINO__model_idx_0248
File size: 3,284 Bytes 
22a62a5
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": 0.9125333333333333,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0248/checkpoints/checkpoint-1998",
  "epoch": 6.0,
  "eval_steps": 500,
  "global_step": 1998,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 0.8140482902526855,
      "learning_rate": 9.334052586261965e-05,
      "loss": 0.9709,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8133333333333334,
      "eval_loss": 0.5890428423881531,
      "eval_runtime": 7.2661,
      "eval_samples_per_second": 516.094,
      "eval_steps_per_second": 8.12,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 8.092026710510254,
      "learning_rate": 7.506805462938029e-05,
      "loss": 0.377,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8157333333333333,
      "eval_loss": 0.6201593279838562,
      "eval_runtime": 6.8288,
      "eval_samples_per_second": 549.148,
      "eval_steps_per_second": 8.64,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 30.67384910583496,
      "learning_rate": 5.015723661038683e-05,
      "loss": 0.1887,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8602666666666666,
      "eval_loss": 0.478941410779953,
      "eval_runtime": 6.8912,
      "eval_samples_per_second": 544.176,
      "eval_steps_per_second": 8.562,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.7893087267875671,
      "learning_rate": 2.5136294516063797e-05,
      "loss": 0.0719,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8893333333333333,
      "eval_loss": 0.42087000608444214,
      "eval_runtime": 8.1121,
      "eval_samples_per_second": 462.272,
      "eval_steps_per_second": 7.273,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 100.61653900146484,
      "learning_rate": 6.777562227006756e-06,
      "loss": 0.0208,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9066666666666666,
      "eval_loss": 0.36809584498405457,
      "eval_runtime": 7.0223,
      "eval_samples_per_second": 534.01,
      "eval_steps_per_second": 8.402,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.014238113537430763,
      "learning_rate": 2.472341277037771e-10,
      "loss": 0.0047,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9125333333333333,
      "eval_loss": 0.3468814492225647,
      "eval_runtime": 6.9357,
      "eval_samples_per_second": 540.683,
      "eval_steps_per_second": 8.507,
      "step": 1998
    }
  ],
  "logging_steps": 500,
  "max_steps": 1998,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 6,
  "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": 9.88447923735552e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}