File size: 1,921 Bytes
a638bd9
 
 
 
 
 
 
 
 
 
 
 
d2d6112
 
 
 
 
a638bd9
 
 
 
d2d6112
 
 
a638bd9
 
 
 
d2d6112
 
 
 
 
a638bd9
 
 
 
d2d6112
 
 
 
 
a638bd9
 
 
 
d2d6112
 
 
a638bd9
 
 
 
d2d6112
a638bd9
d2d6112
a638bd9
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
d2d6112
 
 
a638bd9
 
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
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.1446540880503147,
  "eval_steps": 500,
  "global_step": 1000,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_accuracy": 0.5980645161290322,
      "eval_loss": 0.2370469570159912,
      "eval_runtime": 5.131,
      "eval_samples_per_second": 604.169,
      "eval_steps_per_second": 12.668,
      "step": 318
    },
    {
      "epoch": 1.5723270440251573,
      "grad_norm": 0.5828151106834412,
      "learning_rate": 1.4758909853249476e-05,
      "loss": 0.3737,
      "step": 500
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8264516129032258,
      "eval_loss": 0.11328593641519547,
      "eval_runtime": 5.5375,
      "eval_samples_per_second": 559.823,
      "eval_steps_per_second": 11.738,
      "step": 636
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8780645161290322,
      "eval_loss": 0.0755920559167862,
      "eval_runtime": 5.1832,
      "eval_samples_per_second": 598.091,
      "eval_steps_per_second": 12.541,
      "step": 954
    },
    {
      "epoch": 3.1446540880503147,
      "grad_norm": 0.5158044099807739,
      "learning_rate": 9.517819706498952e-06,
      "loss": 0.1316,
      "step": 1000
    }
  ],
  "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": 260941334653608.0,
  "train_batch_size": 48,
  "trial_name": null,
  "trial_params": {
    "alpha": 0.4750594581069757,
    "num_train_epochs": 6,
    "temperature": 5
  }
}