Hugging Face's logo

ProbeX
/
Model-J__MAE__model_idx_0144

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__MAE__model_idx_0144
File size: 3,928 Bytes 
e150395
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.7338666666666667,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0144/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": 3.0142,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.3317333333333333,
      "eval_loss": 2.4446511268615723,
      "eval_runtime": 6.9101,
      "eval_samples_per_second": 542.683,
      "eval_steps_per_second": 8.538,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": Infinity,
      "learning_rate": 0.0003,
      "loss": 2.0367,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.5242666666666667,
      "eval_loss": 1.6700263023376465,
      "eval_runtime": 7.326,
      "eval_samples_per_second": 511.879,
      "eval_steps_per_second": 8.054,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 30.791719436645508,
      "learning_rate": 0.0003,
      "loss": 1.3001,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.6338666666666667,
      "eval_loss": 1.2377504110336304,
      "eval_runtime": 7.0037,
      "eval_samples_per_second": 535.43,
      "eval_steps_per_second": 8.424,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 9.224142074584961,
      "learning_rate": 0.0003,
      "loss": 0.8585,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.7077333333333333,
      "eval_loss": 0.9948379397392273,
      "eval_runtime": 7.1025,
      "eval_samples_per_second": 527.983,
      "eval_steps_per_second": 8.307,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 12.106545448303223,
      "learning_rate": 0.0003,
      "loss": 0.5785,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.7141333333333333,
      "eval_loss": 0.9909039735794067,
      "eval_runtime": 7.4324,
      "eval_samples_per_second": 504.544,
      "eval_steps_per_second": 7.938,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": Infinity,
      "learning_rate": 0.0003,
      "loss": 0.4111,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.7245333333333334,
      "eval_loss": 0.9978923201560974,
      "eval_runtime": 6.7989,
      "eval_samples_per_second": 551.561,
      "eval_steps_per_second": 8.678,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.4835818409919739,
      "learning_rate": 0.0003,
      "loss": 0.2816,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.7008,
      "eval_loss": 1.1199567317962646,
      "eval_runtime": 6.8766,
      "eval_samples_per_second": 545.329,
      "eval_steps_per_second": 8.58,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 10.845196723937988,
      "learning_rate": 0.0003,
      "loss": 0.2168,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.7338666666666667,
      "eval_loss": 1.0653594732284546,
      "eval_runtime": 7.0608,
      "eval_samples_per_second": 531.102,
      "eval_steps_per_second": 8.356,
      "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
}