File size: 2,582 Bytes
a100808
aabac57
 
 
a100808
aabac57
a100808
 
 
 
 
 
aabac57
 
 
a100808
 
 
 
 
aabac57
 
 
 
a100808
 
 
 
aabac57
 
 
a100808
 
 
 
 
aabac57
 
 
 
a100808
 
 
 
aabac57
 
 
a100808
 
 
 
 
aabac57
 
 
 
a100808
 
 
aabac57
 
 
 
 
 
 
a100808
 
 
aabac57
a100808
aabac57
a100808
 
 
 
 
 
 
 
aabac57
a100808
 
 
 
 
 
 
 
 
 
 
 
 
aabac57
a100808
 
 
 
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
{
  "best_metric": 0.09350258857011795,
  "best_model_checkpoint": "vit-large-patch16-224-dungeon-geo-morphs-008/checkpoint-30",
  "epoch": 19.857142857142858,
  "eval_steps": 10,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 6.571428571428571,
      "grad_norm": 0.04094718024134636,
      "learning_rate": 7.4074074074074075e-06,
      "loss": 0.0018,
      "step": 10
    },
    {
      "epoch": 6.571428571428571,
      "eval_accuracy": 0.9722222222222222,
      "eval_loss": 0.11066238582134247,
      "eval_runtime": 0.505,
      "eval_samples_per_second": 71.287,
      "eval_steps_per_second": 9.901,
      "step": 10
    },
    {
      "epoch": 13.285714285714286,
      "grad_norm": 0.009387318976223469,
      "learning_rate": 3.7037037037037037e-06,
      "loss": 0.0002,
      "step": 20
    },
    {
      "epoch": 13.285714285714286,
      "eval_accuracy": 0.9722222222222222,
      "eval_loss": 0.10644031316041946,
      "eval_runtime": 0.5796,
      "eval_samples_per_second": 62.117,
      "eval_steps_per_second": 8.627,
      "step": 20
    },
    {
      "epoch": 19.857142857142858,
      "grad_norm": 0.008829403668642044,
      "learning_rate": 0.0,
      "loss": 0.0001,
      "step": 30
    },
    {
      "epoch": 19.857142857142858,
      "eval_accuracy": 0.9722222222222222,
      "eval_loss": 0.09350258857011795,
      "eval_runtime": 0.5948,
      "eval_samples_per_second": 60.523,
      "eval_steps_per_second": 8.406,
      "step": 30
    },
    {
      "epoch": 19.857142857142858,
      "step": 30,
      "total_flos": 2.6297770138730496e+17,
      "train_loss": 0.000703394537170728,
      "train_runtime": 205.6889,
      "train_samples_per_second": 7.293,
      "train_steps_per_second": 0.146
    }
  ],
  "logging_steps": 10,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 30,
  "save_steps": 10,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "early_stopping_threshold": 0.01
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.6297770138730496e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}