Hugging Face's logo

ProbeX
/
Model-J__MAE__model_idx_0470

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__MAE__model_idx_0470
File size: 3,898 Bytes 
fdc1f8e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.6392,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0470/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": 0.0003,
      "loss": 3.1816,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.2576,
      "eval_loss": 2.7553770542144775,
      "eval_runtime": 13.4769,
      "eval_samples_per_second": 278.254,
      "eval_steps_per_second": 4.378,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": Infinity,
      "learning_rate": 0.0003,
      "loss": 2.4547,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.38106666666666666,
      "eval_loss": 2.2235708236694336,
      "eval_runtime": 13.4091,
      "eval_samples_per_second": 279.66,
      "eval_steps_per_second": 4.4,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 20.560142517089844,
      "learning_rate": 0.0003,
      "loss": 1.9405,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.45466666666666666,
      "eval_loss": 1.9064422845840454,
      "eval_runtime": 13.4494,
      "eval_samples_per_second": 278.822,
      "eval_steps_per_second": 4.387,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": Infinity,
      "learning_rate": 0.0003,
      "loss": 1.5468,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.5277333333333334,
      "eval_loss": 1.624471664428711,
      "eval_runtime": 13.468,
      "eval_samples_per_second": 278.439,
      "eval_steps_per_second": 4.381,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 29.08803939819336,
      "learning_rate": 0.0003,
      "loss": 1.2077,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.5896,
      "eval_loss": 1.4181841611862183,
      "eval_runtime": 13.5357,
      "eval_samples_per_second": 277.045,
      "eval_steps_per_second": 4.359,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 12.208731651306152,
      "learning_rate": 0.0003,
      "loss": 0.9147,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.6189333333333333,
      "eval_loss": 1.3513823747634888,
      "eval_runtime": 13.6447,
      "eval_samples_per_second": 274.832,
      "eval_steps_per_second": 4.324,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 29.409605026245117,
      "learning_rate": 0.0003,
      "loss": 0.688,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.6298666666666667,
      "eval_loss": 1.3171590566635132,
      "eval_runtime": 13.4917,
      "eval_samples_per_second": 277.948,
      "eval_steps_per_second": 4.373,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 19.712005615234375,
      "learning_rate": 0.0003,
      "loss": 0.5145,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.6392,
      "eval_loss": 1.349707007408142,
      "eval_runtime": 13.3611,
      "eval_samples_per_second": 280.666,
      "eval_steps_per_second": 4.416,
      "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
}