Hugging Face's logo

ProbeX
/
Model-J__DINO__model_idx_0994

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__DINO__model_idx_0994
File size: 4,061 Bytes 
bc30f85
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.48186666666666667,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0994/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": 29.221235275268555,
      "learning_rate": 0.0002911145304096916,
      "loss": 3.2955,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.23813333333333334,
      "eval_loss": 2.8717353343963623,
      "eval_runtime": 12.4954,
      "eval_samples_per_second": 300.111,
      "eval_steps_per_second": 4.722,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 28.196199417114258,
      "learning_rate": 0.00026520930752569493,
      "loss": 2.7002,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.3082666666666667,
      "eval_loss": 2.5178399085998535,
      "eval_runtime": 12.3979,
      "eval_samples_per_second": 302.471,
      "eval_steps_per_second": 4.759,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 32.66680908203125,
      "learning_rate": 0.00022540814184580826,
      "loss": 2.4153,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.3536,
      "eval_loss": 2.3441848754882812,
      "eval_runtime": 12.3546,
      "eval_samples_per_second": 303.53,
      "eval_steps_per_second": 4.776,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 29.35753059387207,
      "learning_rate": 0.00017651164135367125,
      "loss": 2.1748,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.384,
      "eval_loss": 2.1710398197174072,
      "eval_runtime": 12.4112,
      "eval_samples_per_second": 302.147,
      "eval_steps_per_second": 4.754,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 58.31713104248047,
      "learning_rate": 0.00012441744564412654,
      "loss": 1.9325,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.4301333333333333,
      "eval_loss": 2.0191152095794678,
      "eval_runtime": 12.5376,
      "eval_samples_per_second": 299.101,
      "eval_steps_per_second": 4.706,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 57.32910919189453,
      "learning_rate": 7.540888354819138e-05,
      "loss": 1.6529,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.45893333333333336,
      "eval_loss": 1.9483803510665894,
      "eval_runtime": 12.5854,
      "eval_samples_per_second": 297.965,
      "eval_steps_per_second": 4.688,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 20.08523178100586,
      "learning_rate": 3.5397110943979596e-05,
      "loss": 1.329,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.48,
      "eval_loss": 1.9742684364318848,
      "eval_runtime": 12.452,
      "eval_samples_per_second": 301.156,
      "eval_steps_per_second": 4.738,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 45.42845916748047,
      "learning_rate": 9.20813811843163e-06,
      "loss": 1.0175,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.48186666666666667,
      "eval_loss": 2.060637950897217,
      "eval_runtime": 12.5311,
      "eval_samples_per_second": 299.255,
      "eval_steps_per_second": 4.708,
      "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
}