Hugging Face's logo

ProbeX
/
Model-J__DINO__model_idx_0179

Safetensors
vit
Model card Files Community
Model-J__DINO__model_idx_0179
File size: 4,041 Bytes 
07e4357
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
 
{
  "best_metric": 0.4512,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0179/checkpoints/checkpoint-2664",
  "epoch": 8.0,
  "eval_steps": 500,
  "global_step": 2664,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 21.044530868530273,
      "learning_rate": 0.0002628378378378378,
      "loss": 3.4026,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.21946666666666667,
      "eval_loss": 2.978501558303833,
      "eval_runtime": 12.2825,
      "eval_samples_per_second": 305.312,
      "eval_steps_per_second": 4.804,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 21.74341583251953,
      "learning_rate": 0.00022533783783783783,
      "loss": 2.8208,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.25866666666666666,
      "eval_loss": 2.723285675048828,
      "eval_runtime": 11.9647,
      "eval_samples_per_second": 313.422,
      "eval_steps_per_second": 4.931,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 26.11905860900879,
      "learning_rate": 0.00018783783783783784,
      "loss": 2.5225,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.3208,
      "eval_loss": 2.475499391555786,
      "eval_runtime": 12.5134,
      "eval_samples_per_second": 299.678,
      "eval_steps_per_second": 4.715,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 37.424617767333984,
      "learning_rate": 0.00015033783783783783,
      "loss": 2.2674,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.356,
      "eval_loss": 2.3100790977478027,
      "eval_runtime": 12.4438,
      "eval_samples_per_second": 301.354,
      "eval_steps_per_second": 4.741,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 29.31073570251465,
      "learning_rate": 0.00011283783783783782,
      "loss": 1.9987,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.40346666666666664,
      "eval_loss": 2.169679880142212,
      "eval_runtime": 12.32,
      "eval_samples_per_second": 304.382,
      "eval_steps_per_second": 4.789,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 2.9640533924102783,
      "learning_rate": 7.533783783783783e-05,
      "loss": 1.7154,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.42506666666666665,
      "eval_loss": 2.0807077884674072,
      "eval_runtime": 12.1049,
      "eval_samples_per_second": 309.792,
      "eval_steps_per_second": 4.874,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": Infinity,
      "learning_rate": 3.7950450450450446e-05,
      "loss": 1.4099,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.4421333333333333,
      "eval_loss": 2.0816457271575928,
      "eval_runtime": 12.2497,
      "eval_samples_per_second": 306.13,
      "eval_steps_per_second": 4.816,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 60.36575698852539,
      "learning_rate": 4.5045045045045043e-07,
      "loss": 1.0344,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.4512,
      "eval_loss": 2.2509028911590576,
      "eval_runtime": 12.3157,
      "eval_samples_per_second": 304.489,
      "eval_steps_per_second": 4.791,
      "step": 2664
    }
  ],
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.317930564980736e+19,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}