File size: 3,176 Bytes
1554f7c
0f05438
1554f7c
87a0803
1554f7c
 
 
 
 
 
 
87a0803
0f05438
87a0803
0f05438
1554f7c
 
 
87a0803
0f05438
 
 
 
1554f7c
 
 
87a0803
0f05438
87a0803
0f05438
1554f7c
 
 
87a0803
0f05438
 
 
 
1554f7c
 
 
87a0803
0f05438
87a0803
0f05438
1554f7c
 
 
87a0803
0f05438
 
 
 
1554f7c
 
 
87a0803
0f05438
87a0803
0f05438
1554f7c
 
 
87a0803
0f05438
 
 
 
1554f7c
 
 
87a0803
0f05438
87a0803
0f05438
1554f7c
 
 
87a0803
0f05438
 
 
 
1554f7c
 
 
87a0803
0f05438
87a0803
0f05438
1554f7c
 
 
87a0803
0f05438
 
 
 
1554f7c
 
 
 
87a0803
1554f7c
87a0803
1554f7c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.7677457332611084,
  "best_model_checkpoint": "./output/clip-finetuned-csu-p14-336-e4l57-l/checkpoint-3000",
  "epoch": 0.3199658703071672,
  "eval_steps": 500,
  "global_step": 3000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05332764505119454,
      "grad_norm": 401.61187744140625,
      "learning_rate": 4.911120591581342e-07,
      "loss": 0.3808,
      "step": 500
    },
    {
      "epoch": 0.05332764505119454,
      "eval_loss": 1.1107642650604248,
      "eval_runtime": 62.4169,
      "eval_samples_per_second": 15.813,
      "eval_steps_per_second": 1.987,
      "step": 500
    },
    {
      "epoch": 0.10665529010238908,
      "grad_norm": 42.57551193237305,
      "learning_rate": 4.822241183162685e-07,
      "loss": 0.2666,
      "step": 1000
    },
    {
      "epoch": 0.10665529010238908,
      "eval_loss": 0.9644754528999329,
      "eval_runtime": 63.4304,
      "eval_samples_per_second": 15.56,
      "eval_steps_per_second": 1.955,
      "step": 1000
    },
    {
      "epoch": 0.1599829351535836,
      "grad_norm": 518.2286376953125,
      "learning_rate": 4.733361774744027e-07,
      "loss": 0.2085,
      "step": 1500
    },
    {
      "epoch": 0.1599829351535836,
      "eval_loss": 0.9051361680030823,
      "eval_runtime": 63.9009,
      "eval_samples_per_second": 15.446,
      "eval_steps_per_second": 1.941,
      "step": 1500
    },
    {
      "epoch": 0.21331058020477817,
      "grad_norm": 0.0223398394882679,
      "learning_rate": 4.6444823663253695e-07,
      "loss": 0.1867,
      "step": 2000
    },
    {
      "epoch": 0.21331058020477817,
      "eval_loss": 0.8611643314361572,
      "eval_runtime": 63.9649,
      "eval_samples_per_second": 15.43,
      "eval_steps_per_second": 1.939,
      "step": 2000
    },
    {
      "epoch": 0.2666382252559727,
      "grad_norm": 175.0380096435547,
      "learning_rate": 4.5556029579067116e-07,
      "loss": 0.2068,
      "step": 2500
    },
    {
      "epoch": 0.2666382252559727,
      "eval_loss": 0.7947371006011963,
      "eval_runtime": 64.0455,
      "eval_samples_per_second": 15.411,
      "eval_steps_per_second": 1.936,
      "step": 2500
    },
    {
      "epoch": 0.3199658703071672,
      "grad_norm": 9.192651084788395e-09,
      "learning_rate": 4.4667235494880547e-07,
      "loss": 0.163,
      "step": 3000
    },
    {
      "epoch": 0.3199658703071672,
      "eval_loss": 0.7677457332611084,
      "eval_runtime": 64.1593,
      "eval_samples_per_second": 15.384,
      "eval_steps_per_second": 1.933,
      "step": 3000
    }
  ],
  "logging_steps": 500,
  "max_steps": 28128,
  "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
}