File size: 2,611 Bytes
430d0fd
bb67ecb
f074bc5
 
430d0fd
f074bc5
430d0fd
 
 
 
 
f074bc5
bb67ecb
f074bc5
bb67ecb
430d0fd
 
 
f074bc5
bb67ecb
f074bc5
bb67ecb
430d0fd
 
 
f074bc5
bb67ecb
f074bc5
bb67ecb
430d0fd
 
 
f074bc5
bb67ecb
f074bc5
bb67ecb
430d0fd
 
 
f074bc5
bb67ecb
f074bc5
bb67ecb
430d0fd
 
 
f074bc5
bb67ecb
f074bc5
bb67ecb
430d0fd
 
 
f074bc5
bb67ecb
f074bc5
bb67ecb
430d0fd
 
 
f074bc5
bb67ecb
 
 
 
 
430d0fd
 
 
f074bc5
 
 
bb67ecb
 
 
 
535f563
 
f074bc5
bb67ecb
 
 
 
 
f074bc5
24220f6
 
f074bc5
bb67ecb
 
 
 
 
9c3ee56
430d0fd
 
 
f074bc5
430d0fd
 
 
f074bc5
430d0fd
 
 
 
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
{
  "best_metric": 0.5285714285714286,
  "best_model_checkpoint": "videomae-base-finetuned-ucf101-subset/checkpoint-75",
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 75,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.13,
      "grad_norm": 9.097260475158691,
      "learning_rate": 4.850746268656717e-05,
      "loss": 2.3267,
      "step": 10
    },
    {
      "epoch": 0.27,
      "grad_norm": 9.448296546936035,
      "learning_rate": 4.104477611940299e-05,
      "loss": 2.1526,
      "step": 20
    },
    {
      "epoch": 0.4,
      "grad_norm": 8.596159934997559,
      "learning_rate": 3.358208955223881e-05,
      "loss": 2.1627,
      "step": 30
    },
    {
      "epoch": 0.53,
      "grad_norm": 9.472164154052734,
      "learning_rate": 2.6119402985074626e-05,
      "loss": 2.0586,
      "step": 40
    },
    {
      "epoch": 0.67,
      "grad_norm": 13.980053901672363,
      "learning_rate": 1.865671641791045e-05,
      "loss": 2.1303,
      "step": 50
    },
    {
      "epoch": 0.8,
      "grad_norm": 8.99145793914795,
      "learning_rate": 1.119402985074627e-05,
      "loss": 1.8887,
      "step": 60
    },
    {
      "epoch": 0.93,
      "grad_norm": 13.135601043701172,
      "learning_rate": 3.7313432835820893e-06,
      "loss": 1.841,
      "step": 70
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.5285714285714286,
      "eval_loss": 1.7372936010360718,
      "eval_runtime": 13.1282,
      "eval_samples_per_second": 5.332,
      "eval_steps_per_second": 1.371,
      "step": 75
    },
    {
      "epoch": 1.0,
      "step": 75,
      "total_flos": 3.73846047031296e+17,
      "train_loss": 2.053947308858236,
      "train_runtime": 151.5596,
      "train_samples_per_second": 1.979,
      "train_steps_per_second": 0.495
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.432258064516129,
      "eval_loss": 1.8792027235031128,
      "eval_runtime": 29.2338,
      "eval_samples_per_second": 5.302,
      "eval_steps_per_second": 1.334,
      "step": 75
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.432258064516129,
      "eval_loss": 1.879202961921692,
      "eval_runtime": 28.2061,
      "eval_samples_per_second": 5.495,
      "eval_steps_per_second": 1.383,
      "step": 75
    }
  ],
  "logging_steps": 10,
  "max_steps": 75,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 9223372036854775807,
  "save_steps": 500,
  "total_flos": 3.73846047031296e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}