Hugging Face's logo

ProbeX
/
Model-J__MAE__model_idx_0756

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__MAE__model_idx_0756
File size: 3,918 Bytes 
7a5a1d9
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.8578666666666667,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0756/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": 9e-05,
      "loss": 1.6336,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7816,
      "eval_loss": 0.7746593952178955,
      "eval_runtime": 13.0404,
      "eval_samples_per_second": 287.569,
      "eval_steps_per_second": 4.524,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": Infinity,
      "learning_rate": 9e-05,
      "loss": 0.5533,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8226666666666667,
      "eval_loss": 0.6041274070739746,
      "eval_runtime": 11.8615,
      "eval_samples_per_second": 316.148,
      "eval_steps_per_second": 4.974,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.498008668422699,
      "learning_rate": 9e-05,
      "loss": 0.3469,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8397333333333333,
      "eval_loss": 0.5387245416641235,
      "eval_runtime": 11.7421,
      "eval_samples_per_second": 319.363,
      "eval_steps_per_second": 5.025,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 44.818511962890625,
      "learning_rate": 9e-05,
      "loss": 0.2415,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8488,
      "eval_loss": 0.4997638761997223,
      "eval_runtime": 10.8674,
      "eval_samples_per_second": 345.068,
      "eval_steps_per_second": 5.429,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 9.301494598388672,
      "learning_rate": 9e-05,
      "loss": 0.1665,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8506666666666667,
      "eval_loss": 0.5286375880241394,
      "eval_runtime": 11.3751,
      "eval_samples_per_second": 329.666,
      "eval_steps_per_second": 5.187,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 17.187318801879883,
      "learning_rate": 9e-05,
      "loss": 0.1348,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8568,
      "eval_loss": 0.5180009603500366,
      "eval_runtime": 11.0437,
      "eval_samples_per_second": 339.559,
      "eval_steps_per_second": 5.342,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.022252211347222328,
      "learning_rate": 9e-05,
      "loss": 0.1011,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.8330666666666666,
      "eval_loss": 0.6375243067741394,
      "eval_runtime": 11.8375,
      "eval_samples_per_second": 316.789,
      "eval_steps_per_second": 4.984,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.02206488884985447,
      "learning_rate": 9e-05,
      "loss": 0.0884,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.8578666666666667,
      "eval_loss": 0.5686238408088684,
      "eval_runtime": 14.1816,
      "eval_samples_per_second": 264.426,
      "eval_steps_per_second": 4.16,
      "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
}