Hugging Face's logo

ProbeX
/
Model-J__ResNet__model_idx_0056

Image Classification
Transformers
Safetensors
resnet
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__ResNet__model_idx_0056
File size: 4,349 Bytes
0a56bfc
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.8610666666666666,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0056/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": 49.85417175292969,
      "learning_rate": 0.0003,
      "loss": 1.6724,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7749333333333334,
      "eval_loss": 0.7198584079742432,
      "eval_runtime": 5.5799,
      "eval_samples_per_second": 672.057,
      "eval_steps_per_second": 10.574,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 45.70077133178711,
      "learning_rate": 0.0003,
      "loss": 0.5506,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8165333333333333,
      "eval_loss": 0.592795193195343,
      "eval_runtime": 5.5846,
      "eval_samples_per_second": 671.485,
      "eval_steps_per_second": 10.565,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 46.24968719482422,
      "learning_rate": 0.0003,
      "loss": 0.3629,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8373333333333334,
      "eval_loss": 0.5454794764518738,
      "eval_runtime": 5.5882,
      "eval_samples_per_second": 671.059,
      "eval_steps_per_second": 10.558,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 35.130191802978516,
      "learning_rate": 0.0003,
      "loss": 0.2581,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8346666666666667,
      "eval_loss": 0.5875730514526367,
      "eval_runtime": 5.5454,
      "eval_samples_per_second": 676.232,
      "eval_steps_per_second": 10.639,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 29.276952743530273,
      "learning_rate": 0.0003,
      "loss": 0.203,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8392,
      "eval_loss": 0.575366735458374,
      "eval_runtime": 5.5578,
      "eval_samples_per_second": 674.723,
      "eval_steps_per_second": 10.616,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 23.156478881835938,
      "learning_rate": 0.0003,
      "loss": 0.1434,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8530666666666666,
      "eval_loss": 0.5703803300857544,
      "eval_runtime": 5.7437,
      "eval_samples_per_second": 652.891,
      "eval_steps_per_second": 10.272,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 35.66202163696289,
      "learning_rate": 0.0003,
      "loss": 0.1258,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.8442666666666667,
      "eval_loss": 0.6184472441673279,
      "eval_runtime": 5.4379,
      "eval_samples_per_second": 689.603,
      "eval_steps_per_second": 10.85,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 17.250917434692383,
      "learning_rate": 0.0003,
      "loss": 0.0997,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.8533333333333334,
      "eval_loss": 0.5903422236442566,
      "eval_runtime": 5.7448,
      "eval_samples_per_second": 652.769,
      "eval_steps_per_second": 10.27,
      "step": 2664
    },
    {
      "epoch": 9.0,
      "grad_norm": 33.36271286010742,
      "learning_rate": 0.0003,
      "loss": 0.0948,
      "step": 2997
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.8610666666666666,
      "eval_loss": 0.6228994727134705,
      "eval_runtime": 5.7947,
      "eval_samples_per_second": 647.147,
      "eval_steps_per_second": 10.182,
      "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
}