File size: 2,365 Bytes
e30beec
 
 
086e6c6
f183e36
086e6c6
e30beec
 
 
 
 
f183e36
 
 
 
e30beec
 
 
f183e36
 
 
 
 
e30beec
f183e36
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
086e6c6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
e30beec
 
 
f183e36
e30beec
 
f183e36
e30beec
 
 
 
 
 
 
f183e36
e30beec
 
 
 
086e6c6
f183e36
e30beec
 
 
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": 0.0033651149747616375,
  "eval_steps": 3,
  "global_step": 6,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005608524957936063,
      "grad_norm": 0.014698871411383152,
      "learning_rate": 2e-05,
      "loss": 11.9315,
      "step": 1
    },
    {
      "epoch": 0.0005608524957936063,
      "eval_loss": 11.931306838989258,
      "eval_runtime": 2.6652,
      "eval_samples_per_second": 281.781,
      "eval_steps_per_second": 141.078,
      "step": 1
    },
    {
      "epoch": 0.0011217049915872126,
      "grad_norm": 0.009716438129544258,
      "learning_rate": 4e-05,
      "loss": 11.9304,
      "step": 2
    },
    {
      "epoch": 0.0016825574873808188,
      "grad_norm": 0.013599561527371407,
      "learning_rate": 6e-05,
      "loss": 11.9319,
      "step": 3
    },
    {
      "epoch": 0.0016825574873808188,
      "eval_loss": 11.931304931640625,
      "eval_runtime": 2.7015,
      "eval_samples_per_second": 277.993,
      "eval_steps_per_second": 139.182,
      "step": 3
    },
    {
      "epoch": 0.002243409983174425,
      "grad_norm": 0.015706632286310196,
      "learning_rate": 8e-05,
      "loss": 11.9328,
      "step": 4
    },
    {
      "epoch": 0.0028042624789680315,
      "grad_norm": 0.01860496774315834,
      "learning_rate": 0.0001,
      "loss": 11.9248,
      "step": 5
    },
    {
      "epoch": 0.0033651149747616375,
      "grad_norm": 0.008887482807040215,
      "learning_rate": 0.00012,
      "loss": 11.926,
      "step": 6
    },
    {
      "epoch": 0.0033651149747616375,
      "eval_loss": 11.931286811828613,
      "eval_runtime": 2.7509,
      "eval_samples_per_second": 273.003,
      "eval_steps_per_second": 136.683,
      "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": 738508800.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}