File size: 2,340 Bytes
993f18c
 
 
 
 
 
 
 
 
 
 
 
83fe969
 
 
 
 
993f18c
 
 
 
83fe969
 
 
993f18c
 
 
 
83fe969
 
 
 
 
993f18c
 
 
 
83fe969
 
 
 
 
993f18c
 
 
 
83fe969
 
 
993f18c
 
 
 
83fe969
 
 
 
 
993f18c
 
 
 
83fe969
 
 
993f18c
 
 
 
83fe969
993f18c
83fe969
993f18c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
83fe969
 
42ba436
993f18c
 
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": 0.6464516129032258,
      "eval_loss": 0.2894870638847351,
      "eval_runtime": 5.1625,
      "eval_samples_per_second": 600.482,
      "eval_steps_per_second": 12.591,
      "step": 318
    },
    {
      "epoch": 1.5723270440251573,
      "grad_norm": 0.6621634364128113,
      "learning_rate": 1.606918238993711e-05,
      "loss": 0.4605,
      "step": 500
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8416129032258064,
      "eval_loss": 0.11869335174560547,
      "eval_runtime": 5.2214,
      "eval_samples_per_second": 593.71,
      "eval_steps_per_second": 12.449,
      "step": 636
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8912903225806451,
      "eval_loss": 0.0700218454003334,
      "eval_runtime": 5.1185,
      "eval_samples_per_second": 605.652,
      "eval_steps_per_second": 12.699,
      "step": 954
    },
    {
      "epoch": 3.1446540880503147,
      "grad_norm": 0.5828885436058044,
      "learning_rate": 1.2138364779874214e-05,
      "loss": 0.1397,
      "step": 1000
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9077419354838709,
      "eval_loss": 0.05109017714858055,
      "eval_runtime": 5.3994,
      "eval_samples_per_second": 574.138,
      "eval_steps_per_second": 12.038,
      "step": 1272
    },
    {
      "epoch": 4.716981132075472,
      "grad_norm": 0.38680753111839294,
      "learning_rate": 8.207547169811321e-06,
      "loss": 0.0802,
      "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": 391368939443328.0,
  "train_batch_size": 48,
  "trial_name": null,
  "trial_params": {
    "alpha": 0.6565754742921168,
    "num_train_epochs": 8,
    "temperature": 3
  }
}