Hugging Face's logo

ProbeX
/
Model-J__ResNet__model_idx_0538

Image Classification
Transformers
Safetensors
resnet
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__ResNet__model_idx_0538
File size: 3,556 Bytes 
f215e96
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.8829333333333333,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0538/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": 33.34249496459961,
      "learning_rate": 0.0005,
      "loss": 1.2749,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8136,
      "eval_loss": 0.593638002872467,
      "eval_runtime": 8.8737,
      "eval_samples_per_second": 422.599,
      "eval_steps_per_second": 6.649,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 29.67953109741211,
      "learning_rate": 0.0005,
      "loss": 0.4554,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8624,
      "eval_loss": 0.439903199672699,
      "eval_runtime": 8.7782,
      "eval_samples_per_second": 427.194,
      "eval_steps_per_second": 6.721,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 18.25173568725586,
      "learning_rate": 0.0005,
      "loss": 0.3034,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8645333333333334,
      "eval_loss": 0.45186159014701843,
      "eval_runtime": 8.7409,
      "eval_samples_per_second": 429.018,
      "eval_steps_per_second": 6.75,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 26.695377349853516,
      "learning_rate": 0.0005,
      "loss": 0.2195,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8690666666666667,
      "eval_loss": 0.47704780101776123,
      "eval_runtime": 8.8554,
      "eval_samples_per_second": 423.473,
      "eval_steps_per_second": 6.663,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 16.018360137939453,
      "learning_rate": 0.0005,
      "loss": 0.1662,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8682666666666666,
      "eval_loss": 0.4901309907436371,
      "eval_runtime": 8.793,
      "eval_samples_per_second": 426.473,
      "eval_steps_per_second": 6.71,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 13.674880981445312,
      "learning_rate": 0.0005,
      "loss": 0.1314,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8754666666666666,
      "eval_loss": 0.4527912735939026,
      "eval_runtime": 8.807,
      "eval_samples_per_second": 425.796,
      "eval_steps_per_second": 6.699,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 16.61445426940918,
      "learning_rate": 0.0005,
      "loss": 0.0999,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.8829333333333333,
      "eval_loss": 0.47210872173309326,
      "eval_runtime": 8.8075,
      "eval_samples_per_second": 425.773,
      "eval_steps_per_second": 6.699,
      "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": 5.7235004676864e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}