File size: 1,398 Bytes
c14c366
3eb9393
 
 
c14c366
3eb9393
c14c366
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
77cf445
 
 
 
 
 
 
 
 
 
 
 
 
 
3eb9393
 
 
 
 
 
 
 
 
 
 
 
 
 
c14c366
 
 
 
 
 
 
3eb9393
c14c366
 
 
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
{
  "best_metric": 1.0530365705490112,
  "best_model_checkpoint": "./outputs/checkpoint-300",
  "epoch": 0.4,
  "eval_steps": 100,
  "global_step": 300,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.13,
      "learning_rate": 0.0002,
      "loss": 0.9997,
      "step": 100
    },
    {
      "epoch": 0.13,
      "eval_loss": 1.0932432413101196,
      "eval_runtime": 721.0711,
      "eval_samples_per_second": 2.677,
      "eval_steps_per_second": 0.336,
      "step": 100
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0002,
      "loss": 0.897,
      "step": 200
    },
    {
      "epoch": 0.27,
      "eval_loss": 1.0685845613479614,
      "eval_runtime": 721.8083,
      "eval_samples_per_second": 2.674,
      "eval_steps_per_second": 0.335,
      "step": 200
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0002,
      "loss": 0.8812,
      "step": 300
    },
    {
      "epoch": 0.4,
      "eval_loss": 1.0530365705490112,
      "eval_runtime": 727.1346,
      "eval_samples_per_second": 2.654,
      "eval_steps_per_second": 0.333,
      "step": 300
    }
  ],
  "logging_steps": 100,
  "max_steps": 2250,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 100,
  "total_flos": 7.772891970699264e+16,
  "trial_name": null,
  "trial_params": null
}