File size: 1,883 Bytes
8df4105
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
{
  "best_metric": 0.47560975609756095,
  "best_model_checkpoint": "MRR_image_classification_dit_29_jan_small75-finetuned-eurosat/checkpoint-30",
  "epoch": 2.926829268292683,
  "eval_steps": 500,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.98,
      "learning_rate": 3.7037037037037037e-05,
      "loss": 1.8795,
      "step": 10
    },
    {
      "epoch": 0.98,
      "eval_accuracy": 0.3048780487804878,
      "eval_loss": 1.643699288368225,
      "eval_runtime": 4.9921,
      "eval_samples_per_second": 16.426,
      "eval_steps_per_second": 2.203,
      "step": 10
    },
    {
      "epoch": 1.95,
      "learning_rate": 1.8518518518518518e-05,
      "loss": 1.6681,
      "step": 20
    },
    {
      "epoch": 1.95,
      "eval_accuracy": 0.4146341463414634,
      "eval_loss": 1.6445565223693848,
      "eval_runtime": 3.6492,
      "eval_samples_per_second": 22.471,
      "eval_steps_per_second": 3.014,
      "step": 20
    },
    {
      "epoch": 2.93,
      "learning_rate": 0.0,
      "loss": 1.5603,
      "step": 30
    },
    {
      "epoch": 2.93,
      "eval_accuracy": 0.47560975609756095,
      "eval_loss": 1.578503131866455,
      "eval_runtime": 3.4871,
      "eval_samples_per_second": 23.515,
      "eval_steps_per_second": 3.154,
      "step": 30
    },
    {
      "epoch": 2.93,
      "step": 30,
      "total_flos": 2.613596809351127e+17,
      "train_loss": 1.7026190439860025,
      "train_runtime": 204.8067,
      "train_samples_per_second": 4.761,
      "train_steps_per_second": 0.146
    }
  ],
  "logging_steps": 10,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "total_flos": 2.613596809351127e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}