Hugging Face's logo

ProbeX
/
Model-J__MAE__model_idx_0209

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__MAE__model_idx_0209
File size: 3,261 Bytes 
8fad533
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": 0.8973333333333333,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0209/checkpoints/checkpoint-1998",
  "epoch": 6.0,
  "eval_steps": 500,
  "global_step": 1998,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 20.49451446533203,
      "learning_rate": 6.531088913245535e-05,
      "loss": 1.5907,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8106666666666666,
      "eval_loss": 0.6963186860084534,
      "eval_runtime": 4.0216,
      "eval_samples_per_second": 932.461,
      "eval_steps_per_second": 14.671,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.554215908050537,
      "learning_rate": 5.2499999999999995e-05,
      "loss": 0.4565,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8389333333333333,
      "eval_loss": 0.5471352934837341,
      "eval_runtime": 5.1822,
      "eval_samples_per_second": 723.636,
      "eval_steps_per_second": 11.385,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.3414994776248932,
      "learning_rate": 3.5e-05,
      "loss": 0.2058,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8706666666666667,
      "eval_loss": 0.44446367025375366,
      "eval_runtime": 4.1048,
      "eval_samples_per_second": 913.558,
      "eval_steps_per_second": 14.373,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.5348691344261169,
      "learning_rate": 1.7500000000000005e-05,
      "loss": 0.0852,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8914666666666666,
      "eval_loss": 0.3835009038448334,
      "eval_runtime": 4.3264,
      "eval_samples_per_second": 866.771,
      "eval_steps_per_second": 13.637,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 13.123217582702637,
      "learning_rate": 4.689110867544645e-06,
      "loss": 0.0275,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8962666666666667,
      "eval_loss": 0.36997297406196594,
      "eval_runtime": 3.9664,
      "eval_samples_per_second": 945.433,
      "eval_steps_per_second": 14.875,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.08215875923633575,
      "learning_rate": 0.0,
      "loss": 0.014,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8973333333333333,
      "eval_loss": 0.368045836687088,
      "eval_runtime": 3.9758,
      "eval_samples_per_second": 943.217,
      "eval_steps_per_second": 14.84,
      "step": 1998
    }
  ],
  "logging_steps": 500,
  "max_steps": 1998,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 6,
  "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": 9.88447923735552e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}