Hugging Face's logo

ProbeX
/
Model-J__DINO__model_idx_0032

Safetensors
vit
Model card Files Community
Model-J__DINO__model_idx_0032
File size: 3,933 Bytes 
8c7c74e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.43546666666666667,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0032/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": Infinity,
      "learning_rate": 0.0003,
      "loss": 3.2976,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.22826666666666667,
      "eval_loss": 2.8975749015808105,
      "eval_runtime": 13.0548,
      "eval_samples_per_second": 287.251,
      "eval_steps_per_second": 4.519,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 21.59611701965332,
      "learning_rate": 0.0003,
      "loss": 2.7505,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.2928,
      "eval_loss": 2.630790948867798,
      "eval_runtime": 11.9992,
      "eval_samples_per_second": 312.521,
      "eval_steps_per_second": 4.917,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 24.062456130981445,
      "learning_rate": 0.0003,
      "loss": 2.5177,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.3138666666666667,
      "eval_loss": 2.5008890628814697,
      "eval_runtime": 12.175,
      "eval_samples_per_second": 308.007,
      "eval_steps_per_second": 4.846,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 27.035898208618164,
      "learning_rate": 0.0003,
      "loss": 2.3505,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.3344,
      "eval_loss": 2.4544920921325684,
      "eval_runtime": 12.5532,
      "eval_samples_per_second": 298.728,
      "eval_steps_per_second": 4.7,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 24.694316864013672,
      "learning_rate": 0.0003,
      "loss": 2.1837,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.3658666666666667,
      "eval_loss": 2.276373863220215,
      "eval_runtime": 12.1772,
      "eval_samples_per_second": 307.952,
      "eval_steps_per_second": 4.845,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 16.867450714111328,
      "learning_rate": 0.0003,
      "loss": 2.0426,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.3973333333333333,
      "eval_loss": 2.1897079944610596,
      "eval_runtime": 12.1427,
      "eval_samples_per_second": 308.829,
      "eval_steps_per_second": 4.859,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 34.3739013671875,
      "learning_rate": 0.0003,
      "loss": 1.9154,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.41573333333333334,
      "eval_loss": 2.1101248264312744,
      "eval_runtime": 12.2551,
      "eval_samples_per_second": 305.996,
      "eval_steps_per_second": 4.814,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": Infinity,
      "learning_rate": 0.0003,
      "loss": 1.8021,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.43546666666666667,
      "eval_loss": 2.014970302581787,
      "eval_runtime": 13.8233,
      "eval_samples_per_second": 271.281,
      "eval_steps_per_second": 4.268,
      "step": 2664
    }
  ],
  "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": 1.317930564980736e+19,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}