File size: 1,718 Bytes
d0836b0
9767285
 
 
d0836b0
9767285
d0836b0
 
 
 
 
 
 
1bd31f2
d0836b0
 
 
 
1bd31f2
 
 
 
d0836b0
8728efa
 
 
 
 
 
 
 
 
 
 
 
 
 
2d2ff6c
 
 
 
 
 
 
 
 
 
 
 
 
 
9767285
 
 
 
 
 
 
 
 
 
 
 
 
 
d0836b0
 
 
 
 
 
 
9767285
d0836b0
 
 
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
{
  "best_metric": 1.4979034662246704,
  "best_model_checkpoint": "./outputs/checkpoint-400",
  "epoch": 0.5333333333333333,
  "eval_steps": 100,
  "global_step": 400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.13,
      "learning_rate": 0.0002,
      "loss": 1.4578,
      "step": 100
    },
    {
      "epoch": 0.13,
      "eval_loss": 1.567879319190979,
      "eval_runtime": 93.4626,
      "eval_samples_per_second": 15.525,
      "eval_steps_per_second": 1.947,
      "step": 100
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0002,
      "loss": 1.2977,
      "step": 200
    },
    {
      "epoch": 0.27,
      "eval_loss": 1.5340639352798462,
      "eval_runtime": 93.3831,
      "eval_samples_per_second": 15.538,
      "eval_steps_per_second": 1.949,
      "step": 200
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0002,
      "loss": 1.2762,
      "step": 300
    },
    {
      "epoch": 0.4,
      "eval_loss": 1.5129507780075073,
      "eval_runtime": 93.3176,
      "eval_samples_per_second": 15.549,
      "eval_steps_per_second": 1.95,
      "step": 300
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0002,
      "loss": 1.2673,
      "step": 400
    },
    {
      "epoch": 0.53,
      "eval_loss": 1.4979034662246704,
      "eval_runtime": 93.4276,
      "eval_samples_per_second": 15.531,
      "eval_steps_per_second": 1.948,
      "step": 400
    }
  ],
  "logging_steps": 100,
  "max_steps": 2250,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 100,
  "total_flos": 2.340946069733376e+16,
  "trial_name": null,
  "trial_params": null
}