File size: 1,904 Bytes
5ed175a
 
 
f6084ac
5ed175a
f6084ac
5ed175a
 
 
 
 
f6084ac
 
5ed175a
f6084ac
5ed175a
 
 
f6084ac
 
 
 
 
5ed175a
 
f6084ac
 
 
 
 
5ed175a
 
 
f6084ac
 
 
 
 
5ed175a
 
f6084ac
 
 
 
 
 
 
 
 
 
 
 
 
5ed175a
 
f6084ac
 
 
 
 
 
5ed175a
 
f6084ac
 
 
 
 
 
 
5ed175a
 
 
f6084ac
5ed175a
 
 
f6084ac
5ed175a
 
 
 
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
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.7272727272727275,
  "eval_steps": 500,
  "global_step": 15,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.18,
      "grad_norm": 7.793758473406165,
      "learning_rate": 1e-05,
      "loss": 1.4406,
      "step": 1
    },
    {
      "epoch": 0.91,
      "grad_norm": 2.8267893418386913,
      "learning_rate": 1.7485107481711014e-05,
      "loss": 1.2821,
      "step": 5
    },
    {
      "epoch": 0.91,
      "eval_loss": 1.1136233806610107,
      "eval_runtime": 1.3266,
      "eval_samples_per_second": 10.553,
      "eval_steps_per_second": 0.754,
      "step": 5
    },
    {
      "epoch": 1.82,
      "grad_norm": 2.7191793787610057,
      "learning_rate": 6.453951129574644e-06,
      "loss": 0.9973,
      "step": 10
    },
    {
      "epoch": 2.0,
      "eval_loss": 1.0571211576461792,
      "eval_runtime": 1.3822,
      "eval_samples_per_second": 10.129,
      "eval_steps_per_second": 0.723,
      "step": 11
    },
    {
      "epoch": 2.73,
      "grad_norm": 1.7371058324616164,
      "learning_rate": 0.0,
      "loss": 0.82,
      "step": 15
    },
    {
      "epoch": 2.73,
      "eval_loss": 1.045231580734253,
      "eval_runtime": 1.3746,
      "eval_samples_per_second": 10.185,
      "eval_steps_per_second": 0.727,
      "step": 15
    },
    {
      "epoch": 2.73,
      "step": 15,
      "total_flos": 3088349921280.0,
      "train_loss": 1.0436887741088867,
      "train_runtime": 249.1645,
      "train_samples_per_second": 4.142,
      "train_steps_per_second": 0.06
    }
  ],
  "logging_steps": 5,
  "max_steps": 15,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "total_flos": 3088349921280.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}