Hugging Face's logo

ProbeX
/
Model-J__SupViT__model_idx_0825

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__SupViT__model_idx_0825
File size: 3,282 Bytes 
6d2936d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.9421333333333334,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0825/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": 3.692373037338257,
      "learning_rate": 4.849231551964771e-05,
      "loss": 0.8929,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.92,
      "eval_loss": 0.28725337982177734,
      "eval_runtime": 13.4193,
      "eval_samples_per_second": 279.449,
      "eval_steps_per_second": 4.397,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.7728954553604126,
      "learning_rate": 4.415111107797445e-05,
      "loss": 0.159,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9301333333333334,
      "eval_loss": 0.2281317412853241,
      "eval_runtime": 13.2385,
      "eval_samples_per_second": 283.265,
      "eval_steps_per_second": 4.457,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.09836258739233017,
      "learning_rate": 3.7500000000000003e-05,
      "loss": 0.068,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9365333333333333,
      "eval_loss": 0.23109091818332672,
      "eval_runtime": 13.3541,
      "eval_samples_per_second": 280.813,
      "eval_steps_per_second": 4.418,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 3.306086301803589,
      "learning_rate": 2.9341204441673266e-05,
      "loss": 0.0307,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9370666666666667,
      "eval_loss": 0.22892820835113525,
      "eval_runtime": 13.2638,
      "eval_samples_per_second": 282.725,
      "eval_steps_per_second": 4.448,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.06654386222362518,
      "learning_rate": 2.0658795558326743e-05,
      "loss": 0.0132,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9328,
      "eval_loss": 0.25237396359443665,
      "eval_runtime": 13.2972,
      "eval_samples_per_second": 282.013,
      "eval_steps_per_second": 4.437,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.018212372437119484,
      "learning_rate": 1.2500000000000006e-05,
      "loss": 0.0057,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9421333333333334,
      "eval_loss": 0.2368641346693039,
      "eval_runtime": 13.6801,
      "eval_samples_per_second": 274.121,
      "eval_steps_per_second": 4.313,
      "step": 1998
    }
  ],
  "logging_steps": 500,
  "max_steps": 2997,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 9,
  "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": 9.88447923735552e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}