File size: 2,227 Bytes
68c0706
 
 
c537bc2
1d5514d
c537bc2
68c0706
 
 
 
 
1d5514d
68c0706
 
c537bc2
68c0706
 
 
1d5514d
c537bc2
 
 
 
68c0706
 
 
1d5514d
c537bc2
68c0706
c537bc2
68c0706
 
 
1d5514d
c537bc2
1d5514d
c537bc2
1d5514d
 
 
 
c537bc2
 
 
 
1d5514d
c537bc2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
68c0706
 
 
1d5514d
68c0706
 
1d5514d
68c0706
 
 
 
 
 
 
 
 
 
 
 
c537bc2
68c0706
 
 
 
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
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.5,
  "eval_steps": 3,
  "global_step": 6,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.08333333333333333,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 1.4924,
      "step": 1
    },
    {
      "epoch": 0.08333333333333333,
      "eval_loss": 1.4975985288619995,
      "eval_runtime": 0.1911,
      "eval_samples_per_second": 15.701,
      "eval_steps_per_second": 15.701,
      "step": 1
    },
    {
      "epoch": 0.16666666666666666,
      "grad_norm": 5.183752536773682,
      "learning_rate": 2e-05,
      "loss": 1.3074,
      "step": 2
    },
    {
      "epoch": 0.25,
      "grad_norm": 6.239664077758789,
      "learning_rate": 4e-05,
      "loss": 1.5739,
      "step": 3
    },
    {
      "epoch": 0.25,
      "eval_loss": 1.4466005563735962,
      "eval_runtime": 0.211,
      "eval_samples_per_second": 14.216,
      "eval_steps_per_second": 14.216,
      "step": 3
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 5.012392044067383,
      "learning_rate": 6e-05,
      "loss": 1.2793,
      "step": 4
    },
    {
      "epoch": 0.4166666666666667,
      "grad_norm": 3.691774845123291,
      "learning_rate": 8e-05,
      "loss": 1.3057,
      "step": 5
    },
    {
      "epoch": 0.5,
      "grad_norm": 3.0195882320404053,
      "learning_rate": 0.0001,
      "loss": 1.0885,
      "step": 6
    },
    {
      "epoch": 0.5,
      "eval_loss": 0.8231927752494812,
      "eval_runtime": 0.2024,
      "eval_samples_per_second": 14.826,
      "eval_steps_per_second": 14.826,
      "step": 6
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1109738548887552.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}