Hugging Face's logo

ProbeX
/
Model-J__DINO__model_idx_0769

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__DINO__model_idx_0769
File size: 3,552 Bytes 
534bef5
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.29733333333333334,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0769/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": 16.956422805786133,
      "learning_rate": 0.0005,
      "loss": 3.4813,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.164,
      "eval_loss": 3.1941323280334473,
      "eval_runtime": 11.8546,
      "eval_samples_per_second": 316.334,
      "eval_steps_per_second": 4.977,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 17.473468780517578,
      "learning_rate": 0.0005,
      "loss": 2.9921,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.20693333333333333,
      "eval_loss": 2.9714255332946777,
      "eval_runtime": 10.9532,
      "eval_samples_per_second": 342.364,
      "eval_steps_per_second": 5.387,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 19.289810180664062,
      "learning_rate": 0.0005,
      "loss": 2.8543,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.23413333333333333,
      "eval_loss": 2.841240406036377,
      "eval_runtime": 10.7492,
      "eval_samples_per_second": 348.862,
      "eval_steps_per_second": 5.489,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 16.206716537475586,
      "learning_rate": 0.0005,
      "loss": 2.7276,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.23546666666666666,
      "eval_loss": 2.854818344116211,
      "eval_runtime": 10.924,
      "eval_samples_per_second": 343.281,
      "eval_steps_per_second": 5.401,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 15.837252616882324,
      "learning_rate": 0.0005,
      "loss": 2.6261,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.2704,
      "eval_loss": 2.6913750171661377,
      "eval_runtime": 10.8879,
      "eval_samples_per_second": 344.419,
      "eval_steps_per_second": 5.419,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 18.208751678466797,
      "learning_rate": 0.0005,
      "loss": 2.523,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.292,
      "eval_loss": 2.60981822013855,
      "eval_runtime": 10.8479,
      "eval_samples_per_second": 345.688,
      "eval_steps_per_second": 5.439,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 15.938803672790527,
      "learning_rate": 0.0005,
      "loss": 2.4475,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.29733333333333334,
      "eval_loss": 2.658367395401001,
      "eval_runtime": 10.7933,
      "eval_samples_per_second": 347.437,
      "eval_steps_per_second": 5.466,
      "step": 2331
    }
  ],
  "logging_steps": 500,
  "max_steps": 2331,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 7,
  "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": 1.153189244358144e+19,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}