Hugging Face's logo

ProbeX
/
Model-J__SupViT__model_idx_0547

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__SupViT__model_idx_0547
File size: 3,672 Bytes 
64bf7a1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.9058666666666667,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0547/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": 0.0004810825448943271,
      "loss": 0.8334,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8013333333333333,
      "eval_loss": 0.654427707195282,
      "eval_runtime": 11.6857,
      "eval_samples_per_second": 320.904,
      "eval_steps_per_second": 5.049,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 23.984512329101562,
      "learning_rate": 0.0004269850409335979,
      "loss": 0.4836,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8290666666666666,
      "eval_loss": 0.5913998484611511,
      "eval_runtime": 11.8463,
      "eval_samples_per_second": 316.554,
      "eval_steps_per_second": 4.98,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.07459646463394165,
      "learning_rate": 0.0003459431688641196,
      "loss": 0.3144,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.824,
      "eval_loss": 0.6351537704467773,
      "eval_runtime": 11.2309,
      "eval_samples_per_second": 333.901,
      "eval_steps_per_second": 5.253,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.42198115587234497,
      "learning_rate": 0.00025029481906207064,
      "loss": 0.1893,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8624,
      "eval_loss": 0.4875201880931854,
      "eval_runtime": 11.3571,
      "eval_samples_per_second": 330.191,
      "eval_steps_per_second": 5.195,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 36.80768585205078,
      "learning_rate": 0.00015460158573036287,
      "loss": 0.0931,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8773333333333333,
      "eval_loss": 0.49527812004089355,
      "eval_runtime": 11.2075,
      "eval_samples_per_second": 334.596,
      "eval_steps_per_second": 5.264,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.21955284476280212,
      "learning_rate": 7.343189618242854e-05,
      "loss": 0.0334,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8925333333333333,
      "eval_loss": 0.4616575539112091,
      "eval_runtime": 12.2957,
      "eval_samples_per_second": 304.984,
      "eval_steps_per_second": 4.798,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.7152529358863831,
      "learning_rate": 1.9143099846872597e-05,
      "loss": 0.0075,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.9058666666666667,
      "eval_loss": 0.411781907081604,
      "eval_runtime": 11.012,
      "eval_samples_per_second": 340.538,
      "eval_steps_per_second": 5.358,
      "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
}