File size: 2,245 Bytes
fbc3971
 
 
ace63f5
2aa97b8
ace63f5
fbc3971
 
 
 
 
bd15ba9
 
2aa97b8
 
 
fbc3971
2aa97b8
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ace63f5
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
fbc3971
 
bd15ba9
2aa97b8
fbc3971
 
2aa97b8
fbc3971
 
 
 
 
 
 
2aa97b8
fbc3971
 
 
 
ace63f5
bd15ba9
fbc3971
 
 
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
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.00829743098771342,
  "eval_steps": 10,
  "global_step": 26,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00031913196106590075,
      "eval_loss": 0.6470243334770203,
      "eval_runtime": 43.757,
      "eval_samples_per_second": 30.167,
      "eval_steps_per_second": 15.083,
      "step": 1
    },
    {
      "epoch": 0.0015956598053295037,
      "grad_norm": 0.10389410704374313,
      "learning_rate": 5e-05,
      "loss": 0.5954,
      "step": 5
    },
    {
      "epoch": 0.0031913196106590075,
      "grad_norm": 0.10804926604032516,
      "learning_rate": 0.0001,
      "loss": 0.584,
      "step": 10
    },
    {
      "epoch": 0.0031913196106590075,
      "eval_loss": 0.6408673524856567,
      "eval_runtime": 43.8281,
      "eval_samples_per_second": 30.118,
      "eval_steps_per_second": 15.059,
      "step": 10
    },
    {
      "epoch": 0.004786979415988511,
      "grad_norm": 0.13882894814014435,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.603,
      "step": 15
    },
    {
      "epoch": 0.006382639221318015,
      "grad_norm": 0.1524791419506073,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.6305,
      "step": 20
    },
    {
      "epoch": 0.006382639221318015,
      "eval_loss": 0.6011084318161011,
      "eval_runtime": 43.967,
      "eval_samples_per_second": 30.023,
      "eval_steps_per_second": 15.011,
      "step": 20
    },
    {
      "epoch": 0.007978299026647519,
      "grad_norm": 0.13234758377075195,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.5891,
      "step": 25
    }
  ],
  "logging_steps": 5,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 13,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1310933888532480.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}