File size: 1,383 Bytes
3a3b1b6
2b914a2
bc04efc
 
3a3b1b6
bc04efc
3a3b1b6
 
 
 
 
 
 
bc04efc
3a3b1b6
 
 
 
2b914a2
 
 
 
3a3b1b6
e5c5089
 
 
 
2b914a2
e5c5089
 
 
 
2b914a2
 
 
 
e5c5089
d68298f
 
 
 
2b914a2
d68298f
 
 
 
2b914a2
 
 
 
d68298f
3a3b1b6
 
 
 
 
 
bc04efc
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
{
  "best_metric": 2.558687448501587,
  "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": 2.7401,
      "step": 100
    },
    {
      "epoch": 0.07,
      "eval_loss": 2.6424834728240967,
      "eval_runtime": 206.3704,
      "eval_samples_per_second": 30.402,
      "eval_steps_per_second": 3.804,
      "step": 100
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0002,
      "loss": 2.6053,
      "step": 200
    },
    {
      "epoch": 0.15,
      "eval_loss": 2.592982053756714,
      "eval_runtime": 206.2608,
      "eval_samples_per_second": 30.418,
      "eval_steps_per_second": 3.806,
      "step": 200
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0002,
      "loss": 2.5637,
      "step": 300
    },
    {
      "epoch": 0.22,
      "eval_loss": 2.558687448501587,
      "eval_runtime": 206.6302,
      "eval_samples_per_second": 30.363,
      "eval_steps_per_second": 3.799,
      "step": 300
    }
  ],
  "logging_steps": 100,
  "max_steps": 4116,
  "num_train_epochs": 3,
  "save_steps": 100,
  "total_flos": 8750270976491520.0,
  "trial_name": null,
  "trial_params": null
}