Hugging Face's logo

ProbeX
/
Model-J__MAE__model_idx_0647

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__MAE__model_idx_0647
File size: 4,024 Bytes 
2743d68
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.6194666666666667,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0647/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": Infinity,
      "learning_rate": 0.0004850126564054637,
      "loss": 3.1228,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.2581333333333333,
      "eval_loss": 2.7100167274475098,
      "eval_runtime": 6.8715,
      "eval_samples_per_second": 545.732,
      "eval_steps_per_second": 8.586,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": Infinity,
      "learning_rate": 0.00044184758936602033,
      "loss": 2.4696,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.36693333333333333,
      "eval_loss": 2.298243284225464,
      "eval_runtime": 7.4126,
      "eval_samples_per_second": 505.893,
      "eval_steps_per_second": 7.959,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 7.531886100769043,
      "learning_rate": 0.0003754536287075859,
      "loss": 2.062,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.4384,
      "eval_loss": 1.9638751745224,
      "eval_runtime": 6.1969,
      "eval_samples_per_second": 605.14,
      "eval_steps_per_second": 9.521,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": Infinity,
      "learning_rate": 0.00029418606892278544,
      "loss": 1.7294,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.5013333333333333,
      "eval_loss": 1.7251099348068237,
      "eval_runtime": 6.2957,
      "eval_samples_per_second": 595.643,
      "eval_steps_per_second": 9.371,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 9.251385688781738,
      "learning_rate": 0.0002073624094068776,
      "loss": 1.3825,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.5648,
      "eval_loss": 1.5433986186981201,
      "eval_runtime": 6.2774,
      "eval_samples_per_second": 597.383,
      "eval_steps_per_second": 9.399,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 6.631048202514648,
      "learning_rate": 0.00012568147258031897,
      "loss": 1.0193,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.5853333333333334,
      "eval_loss": 1.4747322797775269,
      "eval_runtime": 6.2781,
      "eval_samples_per_second": 597.311,
      "eval_steps_per_second": 9.398,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 28.032588958740234,
      "learning_rate": 5.899518490663266e-05,
      "loss": 0.6628,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.6048,
      "eval_loss": 1.4282950162887573,
      "eval_runtime": 6.3258,
      "eval_samples_per_second": 592.814,
      "eval_steps_per_second": 9.327,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 27.564149856567383,
      "learning_rate": 1.534689686405272e-05,
      "loss": 0.4011,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.6194666666666667,
      "eval_loss": 1.4255696535110474,
      "eval_runtime": 6.2475,
      "eval_samples_per_second": 600.245,
      "eval_steps_per_second": 9.444,
      "step": 2664
    }
  ],
  "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": 1.317930564980736e+19,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}