Hugging Face's logo

ProbeX
/
Model-J__ResNet__model_idx_0162

Image Classification
Transformers
Safetensors
resnet
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__ResNet__model_idx_0162
File size: 4,438 Bytes 
fc7030e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
 
{
  "best_metric": 0.8357333333333333,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0162/checkpoints/checkpoint-2997",
  "epoch": 9.0,
  "eval_steps": 500,
  "global_step": 2997,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 46.70043182373047,
      "learning_rate": 2.9095389311788626e-05,
      "loss": 3.8512,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.38133333333333336,
      "eval_loss": 3.7172813415527344,
      "eval_runtime": 8.3095,
      "eval_samples_per_second": 451.292,
      "eval_steps_per_second": 7.1,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 225.89149475097656,
      "learning_rate": 2.649066664678467e-05,
      "loss": 3.1925,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.6106666666666667,
      "eval_loss": 2.4786698818206787,
      "eval_runtime": 8.3351,
      "eval_samples_per_second": 449.905,
      "eval_steps_per_second": 7.078,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 150.00930786132812,
      "learning_rate": 2.25e-05,
      "loss": 1.7684,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.7253333333333334,
      "eval_loss": 1.2339922189712524,
      "eval_runtime": 8.3165,
      "eval_samples_per_second": 450.909,
      "eval_steps_per_second": 7.094,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 121.13233184814453,
      "learning_rate": 1.760472266500396e-05,
      "loss": 1.044,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.7968,
      "eval_loss": 0.8426409959793091,
      "eval_runtime": 8.4229,
      "eval_samples_per_second": 445.215,
      "eval_steps_per_second": 7.005,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 190.85414123535156,
      "learning_rate": 1.2395277334996045e-05,
      "loss": 0.7996,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8170666666666667,
      "eval_loss": 0.7121408581733704,
      "eval_runtime": 8.3073,
      "eval_samples_per_second": 451.412,
      "eval_steps_per_second": 7.102,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 247.42584228515625,
      "learning_rate": 7.500000000000004e-06,
      "loss": 0.6909,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8202666666666667,
      "eval_loss": 0.6670582294464111,
      "eval_runtime": 8.3461,
      "eval_samples_per_second": 449.31,
      "eval_steps_per_second": 7.069,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 135.77169799804688,
      "learning_rate": 3.5093333532153316e-06,
      "loss": 0.6344,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.8304,
      "eval_loss": 0.6295346617698669,
      "eval_runtime": 8.3335,
      "eval_samples_per_second": 449.991,
      "eval_steps_per_second": 7.08,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 180.03262329101562,
      "learning_rate": 9.046106882113753e-07,
      "loss": 0.6242,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.8346666666666667,
      "eval_loss": 0.6124721169471741,
      "eval_runtime": 7.903,
      "eval_samples_per_second": 474.505,
      "eval_steps_per_second": 7.466,
      "step": 2664
    },
    {
      "epoch": 9.0,
      "grad_norm": 164.98733520507812,
      "learning_rate": 0.0,
      "loss": 0.6071,
      "step": 2997
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.8357333333333333,
      "eval_loss": 0.5950426459312439,
      "eval_runtime": 7.9405,
      "eval_samples_per_second": 472.261,
      "eval_steps_per_second": 7.43,
      "step": 2997
    }
  ],
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 7.3587863155968e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}