Hugging Face's logo

ProbeX
/
Model-J__DINO__model_idx_0577

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__DINO__model_idx_0577
File size: 3,265 Bytes 
ec264e1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.9074666666666666,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0577/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": 67.03459930419922,
      "learning_rate": 9.337967438338007e-05,
      "loss": 1.0915,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8002666666666667,
      "eval_loss": 0.6531761884689331,
      "eval_runtime": 5.9755,
      "eval_samples_per_second": 627.566,
      "eval_steps_per_second": 9.874,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.16869625449180603,
      "learning_rate": 7.513604728193609e-05,
      "loss": 0.3878,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8504,
      "eval_loss": 0.5080835223197937,
      "eval_runtime": 6.2251,
      "eval_samples_per_second": 602.402,
      "eval_steps_per_second": 9.478,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 12.682330131530762,
      "learning_rate": 5.015723661038683e-05,
      "loss": 0.1838,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8637333333333334,
      "eval_loss": 0.49555304646492004,
      "eval_runtime": 7.9343,
      "eval_samples_per_second": 472.631,
      "eval_steps_per_second": 7.436,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.5212671756744385,
      "learning_rate": 2.5136294516063797e-05,
      "loss": 0.0752,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8938666666666667,
      "eval_loss": 0.411973237991333,
      "eval_runtime": 5.9895,
      "eval_samples_per_second": 626.095,
      "eval_steps_per_second": 9.851,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.00818237941712141,
      "learning_rate": 6.777562227006756e-06,
      "loss": 0.0215,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9072,
      "eval_loss": 0.3801559805870056,
      "eval_runtime": 6.2863,
      "eval_samples_per_second": 596.532,
      "eval_steps_per_second": 9.385,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.03539607673883438,
      "learning_rate": 2.472341277037771e-10,
      "loss": 0.0047,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9074666666666666,
      "eval_loss": 0.3711174428462982,
      "eval_runtime": 6.6808,
      "eval_samples_per_second": 561.311,
      "eval_steps_per_second": 8.831,
      "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
}