Hugging Face's logo

ProbeX
/
Model-J__MAE__model_idx_0680

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__MAE__model_idx_0680
File size: 4,079 Bytes 
f961e87
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.9010666666666667,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0680/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": 6.127627627627627e-05,
      "loss": 1.7395,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8154666666666667,
      "eval_loss": 0.7154039144515991,
      "eval_runtime": 12.2347,
      "eval_samples_per_second": 306.505,
      "eval_steps_per_second": 4.822,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.8144007325172424,
      "learning_rate": 5.252627627627627e-05,
      "loss": 0.5276,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8477333333333333,
      "eval_loss": 0.5498841404914856,
      "eval_runtime": 12.3599,
      "eval_samples_per_second": 303.401,
      "eval_steps_per_second": 4.774,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": Infinity,
      "learning_rate": 4.3802552552552546e-05,
      "loss": 0.3004,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8698666666666667,
      "eval_loss": 0.45408788323402405,
      "eval_runtime": 11.9612,
      "eval_samples_per_second": 313.514,
      "eval_steps_per_second": 4.933,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 1.3185418844223022,
      "learning_rate": 3.5052552552552544e-05,
      "loss": 0.1713,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8714666666666666,
      "eval_loss": 0.4512695074081421,
      "eval_runtime": 11.9342,
      "eval_samples_per_second": 314.223,
      "eval_steps_per_second": 4.944,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.4788367748260498,
      "learning_rate": 2.630255255255255e-05,
      "loss": 0.0944,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8850666666666667,
      "eval_loss": 0.42022520303726196,
      "eval_runtime": 12.0098,
      "eval_samples_per_second": 312.244,
      "eval_steps_per_second": 4.913,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.24543941020965576,
      "learning_rate": 1.7552552552552552e-05,
      "loss": 0.0503,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.892,
      "eval_loss": 0.41637349128723145,
      "eval_runtime": 11.9986,
      "eval_samples_per_second": 312.537,
      "eval_steps_per_second": 4.917,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.062248069792985916,
      "learning_rate": 8.802552552552553e-06,
      "loss": 0.0236,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.8954666666666666,
      "eval_loss": 0.41382303833961487,
      "eval_runtime": 11.984,
      "eval_samples_per_second": 312.918,
      "eval_steps_per_second": 4.923,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.07221157103776932,
      "learning_rate": 5.255255255255255e-08,
      "loss": 0.0125,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.9010666666666667,
      "eval_loss": 0.3971787393093109,
      "eval_runtime": 12.2828,
      "eval_samples_per_second": 305.304,
      "eval_steps_per_second": 4.803,
      "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
}