Hugging Face's logo

ProbeX
/
Model-J__ResNet__model_idx_0430

Image Classification
Transformers
Safetensors
resnet
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__ResNet__model_idx_0430
File size: 2,459 Bytes 
946f45c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": 0.8933333333333333,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0430/checkpoints/checkpoint-1332",
  "epoch": 4.0,
  "eval_steps": 500,
  "global_step": 1332,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 66.11095428466797,
      "learning_rate": 0.0004522542485937369,
      "loss": 1.4004,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7954666666666667,
      "eval_loss": 0.6626428961753845,
      "eval_runtime": 8.2484,
      "eval_samples_per_second": 454.634,
      "eval_steps_per_second": 7.153,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 38.69468688964844,
      "learning_rate": 0.00032725424859373687,
      "loss": 0.4893,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8472,
      "eval_loss": 0.4974001944065094,
      "eval_runtime": 8.2103,
      "eval_samples_per_second": 456.741,
      "eval_steps_per_second": 7.186,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 40.75434494018555,
      "learning_rate": 0.00017274575140626317,
      "loss": 0.2862,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8832,
      "eval_loss": 0.39541393518447876,
      "eval_runtime": 8.611,
      "eval_samples_per_second": 435.491,
      "eval_steps_per_second": 6.852,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 79.84575653076172,
      "learning_rate": 4.7745751406263163e-05,
      "loss": 0.1633,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8933333333333333,
      "eval_loss": 0.37728092074394226,
      "eval_runtime": 8.1198,
      "eval_samples_per_second": 461.837,
      "eval_steps_per_second": 7.266,
      "step": 1332
    }
  ],
  "logging_steps": 500,
  "max_steps": 1665,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "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": 3.2705716958208e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}