File size: 2,787 Bytes
c495cde
821a205
c495cde
821a205
c495cde
 
 
 
 
 
 
821a205
 
 
 
c495cde
 
 
821a205
 
 
 
 
c495cde
 
 
821a205
 
 
 
c495cde
 
 
821a205
 
 
 
 
c495cde
 
 
821a205
 
 
 
c495cde
 
 
821a205
 
 
 
 
c495cde
 
 
821a205
 
 
 
c495cde
 
 
821a205
 
 
 
 
c495cde
 
 
821a205
 
 
 
c495cde
 
 
821a205
 
 
 
 
c495cde
 
 
 
821a205
c495cde
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
108
109
{
  "best_metric": 0.830047070980072,
  "best_model_checkpoint": "./output/clip-finetuned-csu-p14-336-e4l57-l/checkpoint-2500",
  "epoch": 0.2814364516492176,
  "eval_steps": 500,
  "global_step": 2500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.056287290329843524,
      "grad_norm": 150.1642303466797,
      "learning_rate": 4.929640887087696e-07,
      "loss": 0.3486,
      "step": 500
    },
    {
      "epoch": 0.056287290329843524,
      "eval_loss": 1.1265727281570435,
      "eval_runtime": 123.7806,
      "eval_samples_per_second": 15.948,
      "eval_steps_per_second": 1.995,
      "step": 500
    },
    {
      "epoch": 0.11257458065968705,
      "grad_norm": 366.6913146972656,
      "learning_rate": 4.859281774175391e-07,
      "loss": 0.2733,
      "step": 1000
    },
    {
      "epoch": 0.11257458065968705,
      "eval_loss": 0.9742079377174377,
      "eval_runtime": 125.8047,
      "eval_samples_per_second": 15.691,
      "eval_steps_per_second": 1.963,
      "step": 1000
    },
    {
      "epoch": 0.16886187098953057,
      "grad_norm": 555.5016479492188,
      "learning_rate": 4.788922661263087e-07,
      "loss": 0.1851,
      "step": 1500
    },
    {
      "epoch": 0.16886187098953057,
      "eval_loss": 0.9162159562110901,
      "eval_runtime": 126.7606,
      "eval_samples_per_second": 15.573,
      "eval_steps_per_second": 1.949,
      "step": 1500
    },
    {
      "epoch": 0.2251491613193741,
      "grad_norm": 0.423260897397995,
      "learning_rate": 4.7185635483507824e-07,
      "loss": 0.1973,
      "step": 2000
    },
    {
      "epoch": 0.2251491613193741,
      "eval_loss": 0.8716973662376404,
      "eval_runtime": 127.6955,
      "eval_samples_per_second": 15.459,
      "eval_steps_per_second": 1.934,
      "step": 2000
    },
    {
      "epoch": 0.2814364516492176,
      "grad_norm": 6.840139389038086,
      "learning_rate": 4.6482044354384774e-07,
      "loss": 0.1881,
      "step": 2500
    },
    {
      "epoch": 0.2814364516492176,
      "eval_loss": 0.830047070980072,
      "eval_runtime": 128.0771,
      "eval_samples_per_second": 15.413,
      "eval_steps_per_second": 1.929,
      "step": 2500
    }
  ],
  "logging_steps": 500,
  "max_steps": 35532,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 900115394852520.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}