File size: 3,178 Bytes
f4e3f32
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 2.0204577445983887,
  "best_model_checkpoint": "./output/clip-finetuned-csu-p14-336-e3l55-l/checkpoint-3000",
  "epoch": 0.5525879535826119,
  "eval_steps": 500,
  "global_step": 3000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.09209799226376865,
      "grad_norm": 0.009597355499863625,
      "learning_rate": 4.846503346227052e-05,
      "loss": 0.7336,
      "step": 500
    },
    {
      "epoch": 0.09209799226376865,
      "eval_loss": 2.0780556201934814,
      "eval_runtime": 77.1404,
      "eval_samples_per_second": 15.634,
      "eval_steps_per_second": 1.957,
      "step": 500
    },
    {
      "epoch": 0.1841959845275373,
      "grad_norm": 0.10049372166395187,
      "learning_rate": 4.693006692454105e-05,
      "loss": 0.6953,
      "step": 1000
    },
    {
      "epoch": 0.1841959845275373,
      "eval_loss": 2.0782744884490967,
      "eval_runtime": 77.8965,
      "eval_samples_per_second": 15.482,
      "eval_steps_per_second": 1.938,
      "step": 1000
    },
    {
      "epoch": 0.27629397679130596,
      "grad_norm": 0.0041180383414030075,
      "learning_rate": 4.539510038681157e-05,
      "loss": 0.6953,
      "step": 1500
    },
    {
      "epoch": 0.27629397679130596,
      "eval_loss": 2.077699899673462,
      "eval_runtime": 78.9586,
      "eval_samples_per_second": 15.274,
      "eval_steps_per_second": 1.912,
      "step": 1500
    },
    {
      "epoch": 0.3683919690550746,
      "grad_norm": 0.29397013783454895,
      "learning_rate": 4.386013384908209e-05,
      "loss": 0.6932,
      "step": 2000
    },
    {
      "epoch": 0.3683919690550746,
      "eval_loss": 2.0721774101257324,
      "eval_runtime": 77.349,
      "eval_samples_per_second": 15.592,
      "eval_steps_per_second": 1.952,
      "step": 2000
    },
    {
      "epoch": 0.46048996131884323,
      "grad_norm": 0.9136261343955994,
      "learning_rate": 4.232516731135262e-05,
      "loss": 0.6907,
      "step": 2500
    },
    {
      "epoch": 0.46048996131884323,
      "eval_loss": 2.079211711883545,
      "eval_runtime": 79.3204,
      "eval_samples_per_second": 15.204,
      "eval_steps_per_second": 1.904,
      "step": 2500
    },
    {
      "epoch": 0.5525879535826119,
      "grad_norm": 4.484213829040527,
      "learning_rate": 4.079020077362314e-05,
      "loss": 0.7043,
      "step": 3000
    },
    {
      "epoch": 0.5525879535826119,
      "eval_loss": 2.0204577445983887,
      "eval_runtime": 78.612,
      "eval_samples_per_second": 15.341,
      "eval_steps_per_second": 1.921,
      "step": 3000
    }
  ],
  "logging_steps": 500,
  "max_steps": 16287,
  "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
}