Hugging Face's logo

ccore
/
getcode

Text Generation
Transformers
TensorBoard
Safetensors
opt
Generated from Trainer
text-generation-inference
Model card Files
xet
Metrics Community
getcode
File size: 2,963 Bytes
90f6285
3a9b24a
 
 
90f6285
3a9b24a
90f6285
 
 
 
 
 
 
 
 
 
 
5432bb7
 
 
 
 
 
 
 
0db0f18
 
 
 
 
 
 
 
07c1929
 
 
 
 
 
 
 
034edc6
 
 
 
 
 
 
 
9cbd46a
 
 
 
 
 
 
 
2706a07
 
 
 
 
 
 
 
0f499a9
 
 
 
 
 
 
 
5efe4fa
 
 
 
 
 
 
 
fa43713
 
 
 
 
 
 
 
3a9b24a
 
 
 
 
 
 
 
90f6285
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3a9b24a
90f6285
 
 
 
 
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
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
 
{
  "best_metric": 1.3360599279403687,
  "best_model_checkpoint": "./opt_trained/checkpoint-242",
  "epoch": 11.0,
  "eval_steps": 500,
  "global_step": 242,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_loss": 1.8587957620620728,
      "eval_runtime": 8.062,
      "eval_samples_per_second": 37.212,
      "eval_steps_per_second": 9.303,
      "step": 22
    },
    {
      "epoch": 2.0,
      "eval_loss": 1.4884560108184814,
      "eval_runtime": 8.0476,
      "eval_samples_per_second": 37.278,
      "eval_steps_per_second": 9.32,
      "step": 44
    },
    {
      "epoch": 3.0,
      "eval_loss": 1.3922361135482788,
      "eval_runtime": 8.0491,
      "eval_samples_per_second": 37.271,
      "eval_steps_per_second": 9.318,
      "step": 66
    },
    {
      "epoch": 4.0,
      "eval_loss": 1.3830264806747437,
      "eval_runtime": 8.0646,
      "eval_samples_per_second": 37.2,
      "eval_steps_per_second": 9.3,
      "step": 88
    },
    {
      "epoch": 5.0,
      "eval_loss": 1.354698896408081,
      "eval_runtime": 8.0581,
      "eval_samples_per_second": 37.23,
      "eval_steps_per_second": 9.307,
      "step": 110
    },
    {
      "epoch": 6.0,
      "eval_loss": 1.3555606603622437,
      "eval_runtime": 8.0406,
      "eval_samples_per_second": 37.311,
      "eval_steps_per_second": 9.328,
      "step": 132
    },
    {
      "epoch": 7.0,
      "eval_loss": 1.367162823677063,
      "eval_runtime": 8.0926,
      "eval_samples_per_second": 37.071,
      "eval_steps_per_second": 9.268,
      "step": 154
    },
    {
      "epoch": 8.0,
      "eval_loss": 1.350898027420044,
      "eval_runtime": 8.0696,
      "eval_samples_per_second": 37.177,
      "eval_steps_per_second": 9.294,
      "step": 176
    },
    {
      "epoch": 9.0,
      "eval_loss": 1.3414418697357178,
      "eval_runtime": 8.0548,
      "eval_samples_per_second": 37.245,
      "eval_steps_per_second": 9.311,
      "step": 198
    },
    {
      "epoch": 10.0,
      "eval_loss": 1.3427915573120117,
      "eval_runtime": 8.0486,
      "eval_samples_per_second": 37.274,
      "eval_steps_per_second": 9.318,
      "step": 220
    },
    {
      "epoch": 11.0,
      "eval_loss": 1.3360599279403687,
      "eval_runtime": 8.0639,
      "eval_samples_per_second": 37.203,
      "eval_steps_per_second": 9.301,
      "step": 242
    }
  ],
  "logging_steps": 500,
  "max_steps": 420,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 20,
  "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": 7803621264384000.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}