Hugging Face's logo

ProbeX
/
Model-J__MAE__model_idx_0907

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__MAE__model_idx_0907
File size: 3,675 Bytes 
2b3230d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": 0.8866666666666667,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0907/checkpoints/checkpoint-2331",
  "epoch": 7.0,
  "eval_steps": 500,
  "global_step": 2331,
  "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": 7.71814671814672e-05,
      "loss": 1.5739,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7992,
      "eval_loss": 0.7126836776733398,
      "eval_runtime": 11.9337,
      "eval_samples_per_second": 314.236,
      "eval_steps_per_second": 4.944,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.5888947248458862,
      "learning_rate": 6.432432432432433e-05,
      "loss": 0.4669,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8450666666666666,
      "eval_loss": 0.5052319169044495,
      "eval_runtime": 12.0675,
      "eval_samples_per_second": 310.751,
      "eval_steps_per_second": 4.889,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 9.211109161376953,
      "learning_rate": 5.146718146718148e-05,
      "loss": 0.2344,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8674666666666667,
      "eval_loss": 0.46071574091911316,
      "eval_runtime": 11.9172,
      "eval_samples_per_second": 314.672,
      "eval_steps_per_second": 4.951,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 19.53057289123535,
      "learning_rate": 3.861003861003861e-05,
      "loss": 0.1153,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8621333333333333,
      "eval_loss": 0.4848562777042389,
      "eval_runtime": 12.0517,
      "eval_samples_per_second": 311.161,
      "eval_steps_per_second": 4.896,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.29247623682022095,
      "learning_rate": 2.5752895752895757e-05,
      "loss": 0.0491,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8789333333333333,
      "eval_loss": 0.4464973509311676,
      "eval_runtime": 11.9347,
      "eval_samples_per_second": 314.21,
      "eval_steps_per_second": 4.944,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 1.9735946655273438,
      "learning_rate": 1.2895752895752896e-05,
      "loss": 0.018,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8802666666666666,
      "eval_loss": 0.4528120160102844,
      "eval_runtime": 11.6612,
      "eval_samples_per_second": 321.58,
      "eval_steps_per_second": 5.06,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.05883270129561424,
      "learning_rate": 3.861003861003861e-08,
      "loss": 0.0079,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.8866666666666667,
      "eval_loss": 0.43983861804008484,
      "eval_runtime": 11.9327,
      "eval_samples_per_second": 314.263,
      "eval_steps_per_second": 4.944,
      "step": 2331
    }
  ],
  "logging_steps": 500,
  "max_steps": 2331,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 7,
  "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": 1.153189244358144e+19,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}