File size: 1,696 Bytes
3a3b1b6
b1477f3
 
 
3a3b1b6
b1477f3
3a3b1b6
 
 
 
 
 
 
b1477f3
3a3b1b6
 
 
 
b1477f3
 
 
 
3a3b1b6
e5c5089
 
 
 
b1477f3
e5c5089
 
 
 
b1477f3
 
 
 
e5c5089
d68298f
 
 
 
b1477f3
d68298f
 
 
 
b1477f3
 
 
 
d68298f
d27a2cf
 
 
 
b1477f3
d27a2cf
 
 
 
b1477f3
 
 
 
d27a2cf
3a3b1b6
 
 
 
 
 
b1477f3
3a3b1b6
 
 
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": 2.5257716178894043,
  "best_model_checkpoint": "./outputs/checkpoint-400",
  "epoch": 0.29143897996357016,
  "eval_steps": 100,
  "global_step": 400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 2.7401,
      "step": 100
    },
    {
      "epoch": 0.07,
      "eval_loss": 2.6424810886383057,
      "eval_runtime": 206.4108,
      "eval_samples_per_second": 30.396,
      "eval_steps_per_second": 3.803,
      "step": 100
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0002,
      "loss": 2.6061,
      "step": 200
    },
    {
      "epoch": 0.15,
      "eval_loss": 2.5929574966430664,
      "eval_runtime": 206.2177,
      "eval_samples_per_second": 30.424,
      "eval_steps_per_second": 3.807,
      "step": 200
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0002,
      "loss": 2.5643,
      "step": 300
    },
    {
      "epoch": 0.22,
      "eval_loss": 2.5578970909118652,
      "eval_runtime": 206.509,
      "eval_samples_per_second": 30.381,
      "eval_steps_per_second": 3.801,
      "step": 300
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0002,
      "loss": 2.5383,
      "step": 400
    },
    {
      "epoch": 0.29,
      "eval_loss": 2.5257716178894043,
      "eval_runtime": 206.1349,
      "eval_samples_per_second": 30.436,
      "eval_steps_per_second": 3.808,
      "step": 400
    }
  ],
  "logging_steps": 100,
  "max_steps": 4116,
  "num_train_epochs": 3,
  "save_steps": 100,
  "total_flos": 1.167856193839104e+16,
  "trial_name": null,
  "trial_params": null
}