File size: 3,173 Bytes
6422806
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
{
  "best_metric": 0.7885717749595642,
  "best_model_checkpoint": "./output/clip-finetuned-csu-p14-336-e3l37-l/checkpoint-3000",
  "epoch": 0.552689756816507,
  "eval_steps": 500,
  "global_step": 3000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.09211495946941783,
      "grad_norm": 8.437943458557129,
      "learning_rate": 2.907885040530582e-07,
      "loss": 0.3017,
      "step": 500
    },
    {
      "epoch": 0.09211495946941783,
      "eval_loss": 1.164457082748413,
      "eval_runtime": 75.2697,
      "eval_samples_per_second": 16.036,
      "eval_steps_per_second": 2.006,
      "step": 500
    },
    {
      "epoch": 0.18422991893883567,
      "grad_norm": 14.740598678588867,
      "learning_rate": 2.815770081061164e-07,
      "loss": 0.2899,
      "step": 1000
    },
    {
      "epoch": 0.18422991893883567,
      "eval_loss": 1.01627779006958,
      "eval_runtime": 76.4934,
      "eval_samples_per_second": 15.779,
      "eval_steps_per_second": 1.974,
      "step": 1000
    },
    {
      "epoch": 0.2763448784082535,
      "grad_norm": 0.17031528055667877,
      "learning_rate": 2.723655121591746e-07,
      "loss": 0.273,
      "step": 1500
    },
    {
      "epoch": 0.2763448784082535,
      "eval_loss": 0.9395213723182678,
      "eval_runtime": 76.6256,
      "eval_samples_per_second": 15.752,
      "eval_steps_per_second": 1.971,
      "step": 1500
    },
    {
      "epoch": 0.36845983787767134,
      "grad_norm": 0.0030106802005320787,
      "learning_rate": 2.6315401621223287e-07,
      "loss": 0.1818,
      "step": 2000
    },
    {
      "epoch": 0.36845983787767134,
      "eval_loss": 0.8942967057228088,
      "eval_runtime": 76.8089,
      "eval_samples_per_second": 15.714,
      "eval_steps_per_second": 1.966,
      "step": 2000
    },
    {
      "epoch": 0.46057479734708917,
      "grad_norm": 474.4410705566406,
      "learning_rate": 2.539425202652911e-07,
      "loss": 0.2094,
      "step": 2500
    },
    {
      "epoch": 0.46057479734708917,
      "eval_loss": 0.8330363631248474,
      "eval_runtime": 76.9939,
      "eval_samples_per_second": 15.677,
      "eval_steps_per_second": 1.961,
      "step": 2500
    },
    {
      "epoch": 0.552689756816507,
      "grad_norm": 314.3533935546875,
      "learning_rate": 2.447310243183493e-07,
      "loss": 0.1949,
      "step": 3000
    },
    {
      "epoch": 0.552689756816507,
      "eval_loss": 0.7885717749595642,
      "eval_runtime": 76.7534,
      "eval_samples_per_second": 15.726,
      "eval_steps_per_second": 1.967,
      "step": 3000
    }
  ],
  "logging_steps": 500,
  "max_steps": 16284,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 1079994570482520.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}