File size: 2,909 Bytes
96d8764
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
101
102
103
{
  "best_metric": 0.8475452196382429,
  "best_model_checkpoint": "distilhubert-finetuned-mixed-data/checkpoint-121",
  "epoch": 4.989690721649485,
  "eval_steps": 500,
  "global_step": 121,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.9896907216494846,
      "eval_accuracy": 0.6330749354005168,
      "eval_f1": 0.5595352399182605,
      "eval_loss": 0.9406359791755676,
      "eval_precision": 0.5371302620976882,
      "eval_recall": 0.6330749354005168,
      "eval_runtime": 1.7053,
      "eval_samples_per_second": 226.94,
      "eval_steps_per_second": 28.734,
      "step": 24
    },
    {
      "epoch": 1.9793814432989691,
      "eval_accuracy": 0.648578811369509,
      "eval_f1": 0.6477021416649994,
      "eval_loss": 0.780166745185852,
      "eval_precision": 0.6774262760064707,
      "eval_recall": 0.648578811369509,
      "eval_runtime": 1.7536,
      "eval_samples_per_second": 220.692,
      "eval_steps_per_second": 27.943,
      "step": 48
    },
    {
      "epoch": 2.9690721649484537,
      "eval_accuracy": 0.7622739018087855,
      "eval_f1": 0.7570575757476992,
      "eval_loss": 0.6011457443237305,
      "eval_precision": 0.7764632789142593,
      "eval_recall": 0.7622739018087855,
      "eval_runtime": 1.7377,
      "eval_samples_per_second": 222.71,
      "eval_steps_per_second": 28.198,
      "step": 72
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8165374677002584,
      "eval_f1": 0.8076125604953357,
      "eval_loss": 0.5131179690361023,
      "eval_precision": 0.8269359136036004,
      "eval_recall": 0.8165374677002584,
      "eval_runtime": 1.7268,
      "eval_samples_per_second": 224.11,
      "eval_steps_per_second": 28.376,
      "step": 97
    },
    {
      "epoch": 4.989690721649485,
      "eval_accuracy": 0.8475452196382429,
      "eval_f1": 0.8448866153449188,
      "eval_loss": 0.4369746148586273,
      "eval_precision": 0.8463304077554821,
      "eval_recall": 0.8475452196382429,
      "eval_runtime": 1.74,
      "eval_samples_per_second": 222.416,
      "eval_steps_per_second": 28.161,
      "step": 121
    }
  ],
  "logging_steps": 500,
  "max_steps": 240,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 500,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.7568400176e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}