Hugging Face's logo

ProbeX
/
Model-J__ResNet__model_idx_0531

Image Classification
Transformers
Safetensors
resnet
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__ResNet__model_idx_0531
File size: 3,537 Bytes 
f8c43d5
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.8701333333333333,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0531/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": 91.16040802001953,
      "learning_rate": 0.0001,
      "loss": 2.9002,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.676,
      "eval_loss": 1.2175014019012451,
      "eval_runtime": 5.6198,
      "eval_samples_per_second": 667.281,
      "eval_steps_per_second": 10.499,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 129.60702514648438,
      "learning_rate": 0.0001,
      "loss": 0.878,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.7989333333333334,
      "eval_loss": 0.6494498252868652,
      "eval_runtime": 5.5197,
      "eval_samples_per_second": 679.389,
      "eval_steps_per_second": 10.689,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 87.67269897460938,
      "learning_rate": 0.0001,
      "loss": 0.582,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8330666666666666,
      "eval_loss": 0.5319434404373169,
      "eval_runtime": 5.5017,
      "eval_samples_per_second": 681.609,
      "eval_steps_per_second": 10.724,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 101.76753234863281,
      "learning_rate": 0.0001,
      "loss": 0.4486,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8456,
      "eval_loss": 0.4868689775466919,
      "eval_runtime": 5.5896,
      "eval_samples_per_second": 670.887,
      "eval_steps_per_second": 10.555,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 35.98136901855469,
      "learning_rate": 0.0001,
      "loss": 0.3398,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8608,
      "eval_loss": 0.4397899806499481,
      "eval_runtime": 5.564,
      "eval_samples_per_second": 673.972,
      "eval_steps_per_second": 10.604,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 110.56379699707031,
      "learning_rate": 0.0001,
      "loss": 0.2669,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.864,
      "eval_loss": 0.4263385534286499,
      "eval_runtime": 5.5407,
      "eval_samples_per_second": 676.806,
      "eval_steps_per_second": 10.648,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 32.488765716552734,
      "learning_rate": 0.0001,
      "loss": 0.2103,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.8701333333333333,
      "eval_loss": 0.423382043838501,
      "eval_runtime": 5.4431,
      "eval_samples_per_second": 688.949,
      "eval_steps_per_second": 10.839,
      "step": 2331
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 5.7235004676864e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}