File size: 2,064 Bytes
3d98438
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.4011026878015162,
  "eval_steps": 291,
  "global_step": 582,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.06891798759476224,
      "grad_norm": 47.0,
      "learning_rate": 9.88326321974139e-06,
      "loss": 0.6874,
      "step": 100
    },
    {
      "epoch": 0.13783597518952448,
      "grad_norm": 25.0,
      "learning_rate": 9.53850386931162e-06,
      "loss": 0.6895,
      "step": 200
    },
    {
      "epoch": 0.2005513439007581,
      "eval_accuracy": 0.569592611154865,
      "eval_loss": 0.6835629940032959,
      "eval_runtime": 378.97,
      "eval_samples_per_second": 221.131,
      "eval_steps_per_second": 27.643,
      "step": 291
    },
    {
      "epoch": 0.2067539627842867,
      "grad_norm": 21.625,
      "learning_rate": 8.981820387323976e-06,
      "loss": 0.6849,
      "step": 300
    },
    {
      "epoch": 0.27567195037904896,
      "grad_norm": 14.5,
      "learning_rate": 8.239206948702616e-06,
      "loss": 0.6902,
      "step": 400
    },
    {
      "epoch": 0.34458993797381116,
      "grad_norm": 23.875,
      "learning_rate": 7.345339674168113e-06,
      "loss": 0.6849,
      "step": 500
    },
    {
      "epoch": 0.4011026878015162,
      "eval_accuracy": 0.5740077802439083,
      "eval_loss": 0.6811934113502502,
      "eval_runtime": 377.4685,
      "eval_samples_per_second": 222.011,
      "eval_steps_per_second": 27.753,
      "step": 582
    }
  ],
  "logging_steps": 100,
  "max_steps": 1451,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 291,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}