Hugging Face's logo

ProbeX
/
Model-J__SupViT__model_idx_0784

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__SupViT__model_idx_0784
File size: 3,682 Bytes 
c66a4ad
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.9538666666666666,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0784/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": Infinity,
      "learning_rate": 6.735155628520579e-05,
      "loss": 0.6871,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9389333333333333,
      "eval_loss": 0.22113513946533203,
      "eval_runtime": 11.3803,
      "eval_samples_per_second": 329.517,
      "eval_steps_per_second": 5.184,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.2096143513917923,
      "learning_rate": 5.9777905730703695e-05,
      "loss": 0.1052,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9394666666666667,
      "eval_loss": 0.23015227913856506,
      "eval_runtime": 10.858,
      "eval_samples_per_second": 345.367,
      "eval_steps_per_second": 5.434,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.10394734889268875,
      "learning_rate": 4.843204364097674e-05,
      "loss": 0.0355,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9464,
      "eval_loss": 0.21763688325881958,
      "eval_runtime": 11.1117,
      "eval_samples_per_second": 337.483,
      "eval_steps_per_second": 5.31,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.22136646509170532,
      "learning_rate": 3.5041274668689884e-05,
      "loss": 0.0117,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9493333333333334,
      "eval_loss": 0.2164168357849121,
      "eval_runtime": 11.6673,
      "eval_samples_per_second": 321.412,
      "eval_steps_per_second": 5.057,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.11431137472391129,
      "learning_rate": 2.16442220022508e-05,
      "loss": 0.0035,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9525333333333333,
      "eval_loss": 0.21271781623363495,
      "eval_runtime": 10.851,
      "eval_samples_per_second": 345.59,
      "eval_steps_per_second": 5.437,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.007872896268963814,
      "learning_rate": 1.0280465465539994e-05,
      "loss": 0.0018,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9528,
      "eval_loss": 0.20869088172912598,
      "eval_runtime": 10.8602,
      "eval_samples_per_second": 345.297,
      "eval_steps_per_second": 5.433,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.009580847807228565,
      "learning_rate": 2.6800339785621635e-06,
      "loss": 0.0013,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.9538666666666666,
      "eval_loss": 0.2081136405467987,
      "eval_runtime": 10.9806,
      "eval_samples_per_second": 341.511,
      "eval_steps_per_second": 5.373,
      "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
}