Hugging Face's logo

ProbeX
/
Model-J__MAE__model_idx_0092

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__MAE__model_idx_0092
File size: 3,252 Bytes
f2fab11
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.8898666666666667,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0092/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": Infinity,
      "learning_rate": 2.9100759384327822e-05,
      "loss": 2.3036,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7677333333333334,
      "eval_loss": 1.1068979501724243,
      "eval_runtime": 10.603,
      "eval_samples_per_second": 353.673,
      "eval_steps_per_second": 5.564,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": Infinity,
      "learning_rate": 2.6510855361961218e-05,
      "loss": 0.7769,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8496,
      "eval_loss": 0.6056557893753052,
      "eval_runtime": 10.2766,
      "eval_samples_per_second": 364.907,
      "eval_steps_per_second": 5.741,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 2.1918864250183105,
      "learning_rate": 2.2527217722455156e-05,
      "loss": 0.4095,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8597333333333333,
      "eval_loss": 0.49450215697288513,
      "eval_runtime": 10.522,
      "eval_samples_per_second": 356.398,
      "eval_steps_per_second": 5.607,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 3.4804248809814453,
      "learning_rate": 1.763568653571882e-05,
      "loss": 0.2505,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8709333333333333,
      "eval_loss": 0.4374520182609558,
      "eval_runtime": 10.9602,
      "eval_samples_per_second": 342.148,
      "eval_steps_per_second": 5.383,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 2.060694932937622,
      "learning_rate": 1.2426252654184347e-05,
      "loss": 0.1495,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.884,
      "eval_loss": 0.3929799497127533,
      "eval_runtime": 11.7128,
      "eval_samples_per_second": 320.163,
      "eval_steps_per_second": 5.037,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.39135849475860596,
      "learning_rate": 7.5272506870206094e-06,
      "loss": 0.0921,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8898666666666667,
      "eval_loss": 0.392263263463974,
      "eval_runtime": 10.5206,
      "eval_samples_per_second": 356.444,
      "eval_steps_per_second": 5.608,
      "step": 1998
    }
  ],
  "logging_steps": 500,
  "max_steps": 2997,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 9,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 9.88447923735552e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}