File size: 3,167 Bytes
ee07ee2
eeff7d8
ee07ee2
 
 
 
 
 
 
 
 
 
eeff7d8
ee07ee2
 
 
 
 
 
eeff7d8
 
 
 
ee07ee2
 
 
 
eeff7d8
ee07ee2
eeff7d8
ee07ee2
 
 
 
eeff7d8
 
 
 
ee07ee2
 
 
 
eeff7d8
ee07ee2
eeff7d8
ee07ee2
 
 
 
eeff7d8
 
 
 
ee07ee2
 
 
 
eeff7d8
ee07ee2
 
 
 
 
 
eeff7d8
 
 
 
ee07ee2
 
 
 
eeff7d8
ee07ee2
eeff7d8
ee07ee2
 
 
 
eeff7d8
 
 
 
ee07ee2
 
 
 
eeff7d8
ee07ee2
eeff7d8
ee07ee2
 
 
 
eeff7d8
 
 
 
ee07ee2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 1.069318175315857,
  "best_model_checkpoint": "./output/clip-finetuned-csu-p14-336-e3l17-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": 246.1711883544922,
      "learning_rate": 9.822241183162683e-08,
      "loss": 0.4515,
      "step": 500
    },
    {
      "epoch": 0.05332764505119454,
      "eval_loss": 1.3850886821746826,
      "eval_runtime": 63.8439,
      "eval_samples_per_second": 15.46,
      "eval_steps_per_second": 1.942,
      "step": 500
    },
    {
      "epoch": 0.10665529010238908,
      "grad_norm": 81.48503875732422,
      "learning_rate": 9.64448236632537e-08,
      "loss": 0.4148,
      "step": 1000
    },
    {
      "epoch": 0.10665529010238908,
      "eval_loss": 1.284144401550293,
      "eval_runtime": 63.853,
      "eval_samples_per_second": 15.457,
      "eval_steps_per_second": 1.942,
      "step": 1000
    },
    {
      "epoch": 0.1599829351535836,
      "grad_norm": 718.367919921875,
      "learning_rate": 9.466723549488054e-08,
      "loss": 0.3281,
      "step": 1500
    },
    {
      "epoch": 0.1599829351535836,
      "eval_loss": 1.2112621068954468,
      "eval_runtime": 64.127,
      "eval_samples_per_second": 15.391,
      "eval_steps_per_second": 1.934,
      "step": 1500
    },
    {
      "epoch": 0.21331058020477817,
      "grad_norm": 4.5923566818237305,
      "learning_rate": 9.288964732650739e-08,
      "loss": 0.2912,
      "step": 2000
    },
    {
      "epoch": 0.21331058020477817,
      "eval_loss": 1.159011960029602,
      "eval_runtime": 63.7062,
      "eval_samples_per_second": 15.493,
      "eval_steps_per_second": 1.946,
      "step": 2000
    },
    {
      "epoch": 0.2666382252559727,
      "grad_norm": 319.4483642578125,
      "learning_rate": 9.111205915813424e-08,
      "loss": 0.3073,
      "step": 2500
    },
    {
      "epoch": 0.2666382252559727,
      "eval_loss": 1.1095446348190308,
      "eval_runtime": 63.9925,
      "eval_samples_per_second": 15.424,
      "eval_steps_per_second": 1.938,
      "step": 2500
    },
    {
      "epoch": 0.3199658703071672,
      "grad_norm": 0.00027541385497897863,
      "learning_rate": 8.933447098976109e-08,
      "loss": 0.2446,
      "step": 3000
    },
    {
      "epoch": 0.3199658703071672,
      "eval_loss": 1.069318175315857,
      "eval_runtime": 64.1107,
      "eval_samples_per_second": 15.395,
      "eval_steps_per_second": 1.934,
      "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
}