File size: 2,342 Bytes
227b1c6
 
 
 
 
 
 
 
 
 
 
 
c9c88cd
 
 
 
 
227b1c6
 
 
 
c9c88cd
227b1c6
c9c88cd
227b1c6
 
 
 
c9c88cd
 
 
 
 
227b1c6
 
 
 
c9c88cd
 
 
 
 
227b1c6
 
 
 
c9c88cd
227b1c6
c9c88cd
227b1c6
 
 
 
c9c88cd
 
 
 
 
227b1c6
 
 
 
c9c88cd
227b1c6
c9c88cd
227b1c6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
c9c88cd
227b1c6
c9c88cd
227b1c6
 
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
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 4.716981132075472,
  "eval_steps": 500,
  "global_step": 1500,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_accuracy": 0.567741935483871,
      "eval_loss": 0.19664955139160156,
      "eval_runtime": 5.5309,
      "eval_samples_per_second": 560.487,
      "eval_steps_per_second": 11.752,
      "step": 318
    },
    {
      "epoch": 1.5723270440251573,
      "grad_norm": 0.5286217927932739,
      "learning_rate": 1.4758909853249476e-05,
      "loss": 0.3117,
      "step": 500
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8083870967741935,
      "eval_loss": 0.10034344345331192,
      "eval_runtime": 6.1068,
      "eval_samples_per_second": 507.628,
      "eval_steps_per_second": 10.644,
      "step": 636
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8664516129032258,
      "eval_loss": 0.07075813412666321,
      "eval_runtime": 5.786,
      "eval_samples_per_second": 535.779,
      "eval_steps_per_second": 11.234,
      "step": 954
    },
    {
      "epoch": 3.1446540880503147,
      "grad_norm": 0.45189452171325684,
      "learning_rate": 9.517819706498952e-06,
      "loss": 0.1157,
      "step": 1000
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8890322580645161,
      "eval_loss": 0.057840555906295776,
      "eval_runtime": 5.8497,
      "eval_samples_per_second": 529.945,
      "eval_steps_per_second": 11.112,
      "step": 1272
    },
    {
      "epoch": 4.716981132075472,
      "grad_norm": 0.327290415763855,
      "learning_rate": 4.276729559748428e-06,
      "loss": 0.0799,
      "step": 1500
    }
  ],
  "logging_steps": 500,
  "max_steps": 1908,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 6,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 391368939443328.0,
  "train_batch_size": 48,
  "trial_name": null,
  "trial_params": {
    "alpha": 0.4479260334486119,
    "num_train_epochs": 6,
    "temperature": 18
  }
}