Hugging Face's logo

ProbeX
/
Model-J__MAE__model_idx_0476

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__MAE__model_idx_0476
File size: 3,670 Bytes 
4e0562b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.9106666666666666,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0476/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": 9.621650897886543e-05,
      "loss": 1.45,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7885333333333333,
      "eval_loss": 0.7040959596633911,
      "eval_runtime": 6.4899,
      "eval_samples_per_second": 577.819,
      "eval_steps_per_second": 9.091,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.7182204723358154,
      "learning_rate": 8.539700818671957e-05,
      "loss": 0.5102,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8522666666666666,
      "eval_loss": 0.4994961619377136,
      "eval_runtime": 6.5106,
      "eval_samples_per_second": 575.985,
      "eval_steps_per_second": 9.062,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 2.0568087100982666,
      "learning_rate": 6.918863377282392e-05,
      "loss": 0.32,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8714666666666666,
      "eval_loss": 0.43607455492019653,
      "eval_runtime": 6.4444,
      "eval_samples_per_second": 581.904,
      "eval_steps_per_second": 9.155,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 1.3625948429107666,
      "learning_rate": 5.005896381241413e-05,
      "loss": 0.1962,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8768,
      "eval_loss": 0.40122631192207336,
      "eval_runtime": 6.5827,
      "eval_samples_per_second": 569.679,
      "eval_steps_per_second": 8.963,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.07286791503429413,
      "learning_rate": 3.0920317146072576e-05,
      "loss": 0.1134,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8933333333333333,
      "eval_loss": 0.3517906367778778,
      "eval_runtime": 6.6865,
      "eval_samples_per_second": 560.833,
      "eval_steps_per_second": 8.824,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 2.518852949142456,
      "learning_rate": 1.4686379236485708e-05,
      "loss": 0.055,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9042666666666667,
      "eval_loss": 0.3318522274494171,
      "eval_runtime": 6.4323,
      "eval_samples_per_second": 582.999,
      "eval_steps_per_second": 9.173,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.06506477296352386,
      "learning_rate": 3.82861996937452e-06,
      "loss": 0.0255,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.9106666666666666,
      "eval_loss": 0.32580918073654175,
      "eval_runtime": 6.5042,
      "eval_samples_per_second": 576.555,
      "eval_steps_per_second": 9.071,
      "step": 2331
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.153189244358144e+19,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}