Hugging Face's logo

ProbeX
/
Model-J__DINO__model_idx_0754

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__DINO__model_idx_0754
File size: 3,670 Bytes 
8cb5d4b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.9272,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0754/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": 0.4825332760810852,
      "learning_rate": 4.850126564054637e-05,
      "loss": 0.7521,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8781333333333333,
      "eval_loss": 0.4015870988368988,
      "eval_runtime": 11.9005,
      "eval_samples_per_second": 315.113,
      "eval_steps_per_second": 4.958,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 2.315068483352661,
      "learning_rate": 4.416794553834106e-05,
      "loss": 0.1905,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8861333333333333,
      "eval_loss": 0.39841556549072266,
      "eval_runtime": 11.8252,
      "eval_samples_per_second": 317.118,
      "eval_steps_per_second": 4.989,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.8009848594665527,
      "learning_rate": 3.7545362870758595e-05,
      "loss": 0.0794,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8864,
      "eval_loss": 0.42285624146461487,
      "eval_runtime": 11.8609,
      "eval_samples_per_second": 316.166,
      "eval_steps_per_second": 4.974,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 1.2681430578231812,
      "learning_rate": 2.9392810892864702e-05,
      "loss": 0.0364,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9018666666666667,
      "eval_loss": 0.39912649989128113,
      "eval_runtime": 11.8541,
      "eval_samples_per_second": 316.345,
      "eval_steps_per_second": 4.977,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.18273214995861053,
      "learning_rate": 2.0710421090307246e-05,
      "loss": 0.015,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9181333333333334,
      "eval_loss": 0.3560587167739868,
      "eval_runtime": 12.2842,
      "eval_samples_per_second": 305.269,
      "eval_steps_per_second": 4.803,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.04033947363495827,
      "learning_rate": 1.2545417811701016e-05,
      "loss": 0.0035,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9242666666666667,
      "eval_loss": 0.3286890387535095,
      "eval_runtime": 11.7827,
      "eval_samples_per_second": 318.262,
      "eval_steps_per_second": 5.007,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.002035548910498619,
      "learning_rate": 5.882620955060414e-06,
      "loss": 0.0008,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.9272,
      "eval_loss": 0.3284943997859955,
      "eval_runtime": 11.888,
      "eval_samples_per_second": 315.443,
      "eval_steps_per_second": 4.963,
      "step": 2331
    }
  ],
  "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": 1.153189244358144e+19,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}