Hugging Face's logo

ProbeX
/
Model-J__ResNet__model_idx_0221

Image Classification
Transformers
Safetensors
resnet
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__ResNet__model_idx_0221
File size: 2,368 Bytes
5094bdb
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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_0221/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": 72.95460510253906,
      "learning_rate": 0.0003,
      "loss": 1.5822,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8112,
      "eval_loss": 0.6189942955970764,
      "eval_runtime": 7.9836,
      "eval_samples_per_second": 469.713,
      "eval_steps_per_second": 7.39,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 53.085304260253906,
      "learning_rate": 0.0003,
      "loss": 0.4636,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8610666666666666,
      "eval_loss": 0.4616861045360565,
      "eval_runtime": 7.6551,
      "eval_samples_per_second": 489.869,
      "eval_steps_per_second": 7.707,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 92.92632293701172,
      "learning_rate": 0.0003,
      "loss": 0.3048,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8672,
      "eval_loss": 0.4460427165031433,
      "eval_runtime": 7.8135,
      "eval_samples_per_second": 479.938,
      "eval_steps_per_second": 7.551,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 61.92770767211914,
      "learning_rate": 0.0003,
      "loss": 0.2134,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.88,
      "eval_loss": 0.41429445147514343,
      "eval_runtime": 8.6503,
      "eval_samples_per_second": 433.511,
      "eval_steps_per_second": 6.821,
      "step": 1332
    }
  ],
  "logging_steps": 500,
  "max_steps": 2331,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 7,
  "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
}