Hugging Face's logo

ProbeX
/
Model-J__ResNet__model_idx_0573

Image Classification
Transformers
Safetensors
resnet
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__ResNet__model_idx_0573
File size: 3,553 Bytes 
0942e3b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.9184,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0573/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": 58.874351501464844,
      "learning_rate": 0.0002625,
      "loss": 1.4992,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8544,
      "eval_loss": 0.4956533908843994,
      "eval_runtime": 7.171,
      "eval_samples_per_second": 522.94,
      "eval_steps_per_second": 8.228,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 39.330650329589844,
      "learning_rate": 0.000225,
      "loss": 0.38,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8898666666666667,
      "eval_loss": 0.35987281799316406,
      "eval_runtime": 7.1083,
      "eval_samples_per_second": 527.556,
      "eval_steps_per_second": 8.3,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 29.70055389404297,
      "learning_rate": 0.00018749999999999998,
      "loss": 0.2221,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8936,
      "eval_loss": 0.3579879701137543,
      "eval_runtime": 7.0609,
      "eval_samples_per_second": 531.095,
      "eval_steps_per_second": 8.356,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 42.42390823364258,
      "learning_rate": 0.00015,
      "loss": 0.137,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9066666666666666,
      "eval_loss": 0.3296903371810913,
      "eval_runtime": 7.2352,
      "eval_samples_per_second": 518.298,
      "eval_steps_per_second": 8.155,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 52.43452072143555,
      "learning_rate": 0.0001125,
      "loss": 0.095,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9090666666666667,
      "eval_loss": 0.3313167691230774,
      "eval_runtime": 7.089,
      "eval_samples_per_second": 528.99,
      "eval_steps_per_second": 8.323,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 36.34873580932617,
      "learning_rate": 7.5e-05,
      "loss": 0.056,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9154666666666667,
      "eval_loss": 0.3340315520763397,
      "eval_runtime": 7.3154,
      "eval_samples_per_second": 512.616,
      "eval_steps_per_second": 8.065,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 65.05775451660156,
      "learning_rate": 3.75e-05,
      "loss": 0.0381,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.9184,
      "eval_loss": 0.31702953577041626,
      "eval_runtime": 7.2807,
      "eval_samples_per_second": 515.062,
      "eval_steps_per_second": 8.104,
      "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
}