Hugging Face's logo

qgyd2021
/
few_shot_intent_gpt2_base

Text Generation
Transformers
Safetensors
gpt2
text-generation-inference
Inference Endpoints
Model card Files Community
few_shot_intent_gpt2_base
File size: 2,809 Bytes 
e636b4e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": 1.2666095495224,
  "best_model_checkpoint": "/data/tianxing/PycharmProjects/Transformers/examples/conversational/few_shot_intent/file_dir/serialization_dir/checkpoint-6000",
  "epoch": 0.17463054724847743,
  "eval_steps": 1000,
  "global_step": 6000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03,
      "grad_norm": 0.6197968125343323,
      "learning_rate": 0.0002,
      "loss": 1.7096,
      "step": 1000
    },
    {
      "epoch": 0.03,
      "eval_loss": 1.4217256307601929,
      "eval_runtime": 2455.1897,
      "eval_samples_per_second": 118.455,
      "eval_steps_per_second": 14.807,
      "step": 1000
    },
    {
      "epoch": 0.06,
      "grad_norm": 0.3991679549217224,
      "learning_rate": 0.00019400443671682956,
      "loss": 1.2426,
      "step": 2000
    },
    {
      "epoch": 0.06,
      "eval_loss": 1.3142809867858887,
      "eval_runtime": 2454.5071,
      "eval_samples_per_second": 118.488,
      "eval_steps_per_second": 14.811,
      "step": 2000
    },
    {
      "epoch": 0.09,
      "grad_norm": 0.3880527913570404,
      "learning_rate": 0.0001880088734336591,
      "loss": 1.1529,
      "step": 3000
    },
    {
      "epoch": 0.09,
      "eval_loss": 1.2872347831726074,
      "eval_runtime": 2455.0423,
      "eval_samples_per_second": 118.462,
      "eval_steps_per_second": 14.808,
      "step": 3000
    },
    {
      "epoch": 0.12,
      "grad_norm": 0.3351105749607086,
      "learning_rate": 0.00018201331015048865,
      "loss": 1.0968,
      "step": 4000
    },
    {
      "epoch": 0.12,
      "eval_loss": 1.2708055973052979,
      "eval_runtime": 2454.672,
      "eval_samples_per_second": 118.48,
      "eval_steps_per_second": 14.81,
      "step": 4000
    },
    {
      "epoch": 0.15,
      "grad_norm": 0.42601627111434937,
      "learning_rate": 0.0001760177468673182,
      "loss": 1.0568,
      "step": 5000
    },
    {
      "epoch": 0.15,
      "eval_loss": 1.2738263607025146,
      "eval_runtime": 2454.9426,
      "eval_samples_per_second": 118.467,
      "eval_steps_per_second": 14.808,
      "step": 5000
    },
    {
      "epoch": 0.17,
      "grad_norm": 0.3943077027797699,
      "learning_rate": 0.00017002218358414775,
      "loss": 1.0274,
      "step": 6000
    },
    {
      "epoch": 0.17,
      "eval_loss": 1.2666095495224,
      "eval_runtime": 2453.7183,
      "eval_samples_per_second": 118.526,
      "eval_steps_per_second": 14.816,
      "step": 6000
    }
  ],
  "logging_steps": 1000,
  "max_steps": 34358,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 1000,
  "total_flos": 1.9766892483628237e+17,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}