File size: 1,389 Bytes
74a567c
7afed10
 
 
74a567c
7afed10
74a567c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4f48b61
 
 
 
 
 
 
 
 
 
 
 
 
 
7afed10
 
 
 
 
 
 
 
 
 
 
 
 
 
74a567c
 
 
 
 
 
7afed10
74a567c
 
 
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
{
  "best_metric": 2.0028491020202637,
  "best_model_checkpoint": "./outputs/checkpoint-300",
  "epoch": 0.2185792349726776,
  "eval_steps": 100,
  "global_step": 300,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 2.3152,
      "step": 100
    },
    {
      "epoch": 0.07,
      "eval_loss": 2.160670518875122,
      "eval_runtime": 143.4488,
      "eval_samples_per_second": 43.737,
      "eval_steps_per_second": 5.472,
      "step": 100
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0002,
      "loss": 2.1094,
      "step": 200
    },
    {
      "epoch": 0.15,
      "eval_loss": 2.0639851093292236,
      "eval_runtime": 143.5664,
      "eval_samples_per_second": 43.701,
      "eval_steps_per_second": 5.468,
      "step": 200
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0002,
      "loss": 2.0347,
      "step": 300
    },
    {
      "epoch": 0.22,
      "eval_loss": 2.0028491020202637,
      "eval_runtime": 143.5409,
      "eval_samples_per_second": 43.709,
      "eval_steps_per_second": 5.469,
      "step": 300
    }
  ],
  "logging_steps": 100,
  "max_steps": 4116,
  "num_train_epochs": 3,
  "save_steps": 100,
  "total_flos": 1.7869715412615168e+16,
  "trial_name": null,
  "trial_params": null
}