File size: 2,337 Bytes
9cfcf56
 
 
 
 
 
 
 
 
 
 
 
b64856f
 
 
 
 
9cfcf56
 
 
 
b64856f
 
 
9cfcf56
 
 
 
b64856f
 
 
 
 
9cfcf56
 
 
 
b64856f
 
 
 
 
9cfcf56
 
 
 
b64856f
 
 
9cfcf56
 
 
 
b64856f
 
 
 
 
9cfcf56
 
 
 
b64856f
 
 
9cfcf56
 
 
 
b64856f
9cfcf56
b64856f
9cfcf56
 
 
 
 
 
 
 
 
 
 
 
 
b64856f
9cfcf56
 
 
b64856f
 
 
9cfcf56
 
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
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 4.716981132075472,
  "eval_steps": 500,
  "global_step": 1500,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_accuracy": 0.6758064516129032,
      "eval_loss": 0.40983492136001587,
      "eval_runtime": 5.8092,
      "eval_samples_per_second": 533.639,
      "eval_steps_per_second": 11.189,
      "step": 318
    },
    {
      "epoch": 1.5723270440251573,
      "grad_norm": 0.86518794298172,
      "learning_rate": 1.606918238993711e-05,
      "loss": 0.645,
      "step": 500
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8412903225806452,
      "eval_loss": 0.142293781042099,
      "eval_runtime": 6.1991,
      "eval_samples_per_second": 500.073,
      "eval_steps_per_second": 10.485,
      "step": 636
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8938709677419355,
      "eval_loss": 0.07486626505851746,
      "eval_runtime": 5.5967,
      "eval_samples_per_second": 553.895,
      "eval_steps_per_second": 11.614,
      "step": 954
    },
    {
      "epoch": 3.1446540880503147,
      "grad_norm": 0.7068584561347961,
      "learning_rate": 1.2138364779874214e-05,
      "loss": 0.1671,
      "step": 1000
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9141935483870968,
      "eval_loss": 0.053671687841415405,
      "eval_runtime": 5.7734,
      "eval_samples_per_second": 536.949,
      "eval_steps_per_second": 11.259,
      "step": 1272
    },
    {
      "epoch": 4.716981132075472,
      "grad_norm": 0.464497447013855,
      "learning_rate": 8.207547169811321e-06,
      "loss": 0.0849,
      "step": 1500
    }
  ],
  "logging_steps": 500,
  "max_steps": 2544,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 8,
  "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": 438885076748160.0,
  "train_batch_size": 48,
  "trial_name": null,
  "trial_params": {
    "alpha": 0.3417365166940647,
    "num_train_epochs": 8,
    "temperature": 2
  }
}