Hugging Face's logo

ProbeX
/
Model-J__DINO__model_idx_0555

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__DINO__model_idx_0555
File size: 3,693 Bytes 
5815a3f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.9013333333333333,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0555/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": 7.47520637512207,
      "learning_rate": 8.731834188804772e-05,
      "loss": 0.7819,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8346666666666667,
      "eval_loss": 0.5314040184020996,
      "eval_runtime": 9.9314,
      "eval_samples_per_second": 377.59,
      "eval_steps_per_second": 5.941,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 2.1421663761138916,
      "learning_rate": 7.953256608588366e-05,
      "loss": 0.2825,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8373333333333334,
      "eval_loss": 0.5645512938499451,
      "eval_runtime": 9.8641,
      "eval_samples_per_second": 380.167,
      "eval_steps_per_second": 5.981,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 2.978841781616211,
      "learning_rate": 6.758165316736547e-05,
      "loss": 0.1538,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8570666666666666,
      "eval_loss": 0.5473647713661194,
      "eval_runtime": 9.9857,
      "eval_samples_per_second": 375.536,
      "eval_steps_per_second": 5.908,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 122.5201644897461,
      "learning_rate": 5.2907059607156464e-05,
      "loss": 0.0825,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8573333333333333,
      "eval_loss": 0.5720833539962769,
      "eval_runtime": 9.8291,
      "eval_samples_per_second": 381.52,
      "eval_steps_per_second": 6.003,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.3150494396686554,
      "learning_rate": 3.727875796255304e-05,
      "loss": 0.0383,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8858666666666667,
      "eval_loss": 0.5161731839179993,
      "eval_runtime": 9.7452,
      "eval_samples_per_second": 384.804,
      "eval_steps_per_second": 6.054,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.023200122639536858,
      "learning_rate": 2.258175206106183e-05,
      "loss": 0.0117,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8941333333333333,
      "eval_loss": 0.49896466732025146,
      "eval_runtime": 9.7838,
      "eval_samples_per_second": 383.285,
      "eval_steps_per_second": 6.03,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.00041469797724857926,
      "learning_rate": 1.0588717719108745e-05,
      "loss": 0.0016,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.9013333333333333,
      "eval_loss": 0.4508293569087982,
      "eval_runtime": 9.8232,
      "eval_samples_per_second": 381.749,
      "eval_steps_per_second": 6.006,
      "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
}