Hugging Face's logo

ProbeX
/
Model-J__ResNet__model_idx_0892

Image Classification
Transformers
Safetensors
resnet
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__ResNet__model_idx_0892
File size: 2,363 Bytes 
bc463ce
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.88,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0892/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": 547.0023803710938,
      "learning_rate": 7e-05,
      "loss": 3.2644,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.6176,
      "eval_loss": 1.7464123964309692,
      "eval_runtime": 7.0945,
      "eval_samples_per_second": 528.577,
      "eval_steps_per_second": 8.316,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 142.52182006835938,
      "learning_rate": 7e-05,
      "loss": 0.9066,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8328,
      "eval_loss": 0.5602176785469055,
      "eval_runtime": 7.1426,
      "eval_samples_per_second": 525.017,
      "eval_steps_per_second": 8.26,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 104.47779083251953,
      "learning_rate": 7e-05,
      "loss": 0.4742,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8661333333333333,
      "eval_loss": 0.4353055953979492,
      "eval_runtime": 7.1125,
      "eval_samples_per_second": 527.243,
      "eval_steps_per_second": 8.295,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 69.09544372558594,
      "learning_rate": 7e-05,
      "loss": 0.3343,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.88,
      "eval_loss": 0.3931189477443695,
      "eval_runtime": 7.5427,
      "eval_samples_per_second": 497.171,
      "eval_steps_per_second": 7.822,
      "step": 1332
    }
  ],
  "logging_steps": 500,
  "max_steps": 1332,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "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": 3.2705716958208e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}