File size: 2,194 Bytes
309fa92
 
 
9bc2da5
309fa92
9bc2da5
309fa92
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
b9d6d53
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9bc2da5
 
 
 
 
 
 
309fa92
 
 
 
 
 
 
 
 
 
 
 
 
 
9bc2da5
309fa92
 
 
 
9bc2da5
309fa92
 
 
 
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
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0010654023891648577,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00021308047783297153,
      "grad_norm": 18.833036422729492,
      "learning_rate": 1e-05,
      "loss": 8.7482,
      "step": 1
    },
    {
      "epoch": 0.00021308047783297153,
      "eval_loss": 8.408291816711426,
      "eval_runtime": 202.7276,
      "eval_samples_per_second": 38.993,
      "eval_steps_per_second": 19.499,
      "step": 1
    },
    {
      "epoch": 0.00042616095566594305,
      "grad_norm": 14.874626159667969,
      "learning_rate": 2e-05,
      "loss": 8.0443,
      "step": 2
    },
    {
      "epoch": 0.00042616095566594305,
      "eval_loss": 8.203876495361328,
      "eval_runtime": 104.7813,
      "eval_samples_per_second": 75.443,
      "eval_steps_per_second": 37.726,
      "step": 2
    },
    {
      "epoch": 0.0006392414334989146,
      "grad_norm": 15.174580574035645,
      "learning_rate": 3e-05,
      "loss": 8.316,
      "step": 3
    },
    {
      "epoch": 0.0008523219113318861,
      "grad_norm": 13.973289489746094,
      "learning_rate": 4e-05,
      "loss": 7.6847,
      "step": 4
    },
    {
      "epoch": 0.0008523219113318861,
      "eval_loss": 7.609894752502441,
      "eval_runtime": 104.9595,
      "eval_samples_per_second": 75.315,
      "eval_steps_per_second": 37.662,
      "step": 4
    },
    {
      "epoch": 0.0010654023891648577,
      "grad_norm": 15.817801475524902,
      "learning_rate": 5e-05,
      "loss": 7.6037,
      "step": 5
    }
  ],
  "logging_steps": 1,
  "max_steps": 5,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 2,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1443959490478080.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}