Hugging Face's logo

ProbeX
/
Model-J__MAE__model_idx_0794

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__MAE__model_idx_0794
File size: 3,899 Bytes 
01ef075
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.8816,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0794/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": 7e-05,
      "loss": 1.6182,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8125333333333333,
      "eval_loss": 0.6865555047988892,
      "eval_runtime": 5.771,
      "eval_samples_per_second": 649.802,
      "eval_steps_per_second": 10.224,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.670511782169342,
      "learning_rate": 7e-05,
      "loss": 0.5123,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8544,
      "eval_loss": 0.5036649107933044,
      "eval_runtime": 5.9006,
      "eval_samples_per_second": 635.524,
      "eval_steps_per_second": 9.999,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 7.2545647621154785,
      "learning_rate": 7e-05,
      "loss": 0.3004,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8581333333333333,
      "eval_loss": 0.500713586807251,
      "eval_runtime": 6.3311,
      "eval_samples_per_second": 592.313,
      "eval_steps_per_second": 9.319,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 7.212543487548828,
      "learning_rate": 7e-05,
      "loss": 0.2049,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8709333333333333,
      "eval_loss": 0.45927900075912476,
      "eval_runtime": 5.7547,
      "eval_samples_per_second": 651.642,
      "eval_steps_per_second": 10.252,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.564225435256958,
      "learning_rate": 7e-05,
      "loss": 0.15,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8728,
      "eval_loss": 0.4660601019859314,
      "eval_runtime": 5.8868,
      "eval_samples_per_second": 637.018,
      "eval_steps_per_second": 10.022,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.16182473301887512,
      "learning_rate": 7e-05,
      "loss": 0.1085,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8744,
      "eval_loss": 0.45742350816726685,
      "eval_runtime": 5.6836,
      "eval_samples_per_second": 659.794,
      "eval_steps_per_second": 10.381,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.42810118198394775,
      "learning_rate": 7e-05,
      "loss": 0.086,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.8770666666666667,
      "eval_loss": 0.4690202474594116,
      "eval_runtime": 6.4747,
      "eval_samples_per_second": 579.175,
      "eval_steps_per_second": 9.112,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.034715887159109116,
      "learning_rate": 7e-05,
      "loss": 0.0719,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.8816,
      "eval_loss": 0.47455671429634094,
      "eval_runtime": 5.748,
      "eval_samples_per_second": 652.406,
      "eval_steps_per_second": 10.265,
      "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
}