Hugging Face's logo

ProbeX
/
Model-J__SupViT__model_idx_0969

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__SupViT__model_idx_0969
File size: 3,892 Bytes 
4f306b0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
 
{
  "best_metric": 0.9568,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0969/checkpoints/checkpoint-2664",
  "epoch": 8.0,
  "eval_steps": 500,
  "global_step": 2664,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 0.9831521511077881,
      "learning_rate": 3e-05,
      "loss": 1.1764,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9352,
      "eval_loss": 0.2700672149658203,
      "eval_runtime": 6.9222,
      "eval_samples_per_second": 541.733,
      "eval_steps_per_second": 8.523,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.19097444415092468,
      "learning_rate": 3e-05,
      "loss": 0.1493,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9474666666666667,
      "eval_loss": 0.19397518038749695,
      "eval_runtime": 6.6578,
      "eval_samples_per_second": 563.249,
      "eval_steps_per_second": 8.862,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.357282817363739,
      "learning_rate": 3e-05,
      "loss": 0.0648,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9432,
      "eval_loss": 0.21096019446849823,
      "eval_runtime": 6.7507,
      "eval_samples_per_second": 555.496,
      "eval_steps_per_second": 8.74,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.11316190659999847,
      "learning_rate": 3e-05,
      "loss": 0.0325,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9493333333333334,
      "eval_loss": 0.19892506301403046,
      "eval_runtime": 6.7917,
      "eval_samples_per_second": 552.144,
      "eval_steps_per_second": 8.687,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.045326393097639084,
      "learning_rate": 3e-05,
      "loss": 0.0185,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9496,
      "eval_loss": 0.19840462505817413,
      "eval_runtime": 6.7611,
      "eval_samples_per_second": 554.647,
      "eval_steps_per_second": 8.726,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.08691786974668503,
      "learning_rate": 3e-05,
      "loss": 0.0142,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9496,
      "eval_loss": 0.2105918675661087,
      "eval_runtime": 6.8249,
      "eval_samples_per_second": 549.456,
      "eval_steps_per_second": 8.645,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": NaN,
      "learning_rate": 3e-05,
      "loss": 0.013,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.9501333333333334,
      "eval_loss": 0.2122584730386734,
      "eval_runtime": 7.0532,
      "eval_samples_per_second": 531.676,
      "eval_steps_per_second": 8.365,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.0086445864289999,
      "learning_rate": 3e-05,
      "loss": 0.0071,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.9568,
      "eval_loss": 0.20181328058242798,
      "eval_runtime": 6.8614,
      "eval_samples_per_second": 546.539,
      "eval_steps_per_second": 8.599,
      "step": 2664
    }
  ],
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.317930564980736e+19,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}