Hugging Face's logo

m3hrdadfi
/
gpt2-persian-qa

Text Generation
Transformers
PyTorch
TensorFlow
Persian
gpt2
text-generation-inference
Inference Endpoints
Model card Files Community
1
gpt2-persian-qa
File size: 3,516 Bytes 
f0f702f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.9998406882268602,
  "global_step": 9414,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.32,
      "learning_rate": 2.4875e-05,
      "loss": 4.2616,
      "step": 1000
    },
    {
      "epoch": 0.32,
      "eval_loss": 2.4269070625305176,
      "eval_runtime": 59.5268,
      "eval_samples_per_second": 10.936,
      "eval_steps_per_second": 10.936,
      "step": 1000
    },
    {
      "epoch": 0.64,
      "learning_rate": 4.9850000000000006e-05,
      "loss": 1.9451,
      "step": 2000
    },
    {
      "epoch": 0.64,
      "eval_loss": 1.3068270683288574,
      "eval_runtime": 59.0527,
      "eval_samples_per_second": 11.024,
      "eval_steps_per_second": 11.024,
      "step": 2000
    },
    {
      "epoch": 0.96,
      "learning_rate": 4.329646614513084e-05,
      "loss": 1.5082,
      "step": 3000
    },
    {
      "epoch": 0.96,
      "eval_loss": 1.131048560142517,
      "eval_runtime": 59.5847,
      "eval_samples_per_second": 10.926,
      "eval_steps_per_second": 10.926,
      "step": 3000
    },
    {
      "epoch": 1.27,
      "learning_rate": 3.6559212301052064e-05,
      "loss": 1.1402,
      "step": 4000
    },
    {
      "epoch": 1.27,
      "eval_loss": 1.0661729574203491,
      "eval_runtime": 59.6476,
      "eval_samples_per_second": 10.914,
      "eval_steps_per_second": 10.914,
      "step": 4000
    },
    {
      "epoch": 1.59,
      "learning_rate": 2.9815214459131374e-05,
      "loss": 1.0806,
      "step": 5000
    },
    {
      "epoch": 1.59,
      "eval_loss": 1.0320521593093872,
      "eval_runtime": 59.5322,
      "eval_samples_per_second": 10.935,
      "eval_steps_per_second": 10.935,
      "step": 5000
    },
    {
      "epoch": 1.91,
      "learning_rate": 2.3071216617210683e-05,
      "loss": 1.0331,
      "step": 6000
    },
    {
      "epoch": 1.91,
      "eval_loss": 1.0125774145126343,
      "eval_runtime": 58.9824,
      "eval_samples_per_second": 11.037,
      "eval_steps_per_second": 11.037,
      "step": 6000
    },
    {
      "epoch": 2.23,
      "learning_rate": 1.6327218775289993e-05,
      "loss": 0.8337,
      "step": 7000
    },
    {
      "epoch": 2.23,
      "eval_loss": 1.0233821868896484,
      "eval_runtime": 59.1959,
      "eval_samples_per_second": 10.997,
      "eval_steps_per_second": 10.997,
      "step": 7000
    },
    {
      "epoch": 2.55,
      "learning_rate": 9.589964931211222e-06,
      "loss": 0.7498,
      "step": 8000
    },
    {
      "epoch": 2.55,
      "eval_loss": 1.0264060497283936,
      "eval_runtime": 59.237,
      "eval_samples_per_second": 10.99,
      "eval_steps_per_second": 10.99,
      "step": 8000
    },
    {
      "epoch": 2.87,
      "learning_rate": 2.852711087132452e-06,
      "loss": 0.7291,
      "step": 9000
    },
    {
      "epoch": 2.87,
      "eval_loss": 1.0013467073440552,
      "eval_runtime": 59.1148,
      "eval_samples_per_second": 11.012,
      "eval_steps_per_second": 11.012,
      "step": 9000
    },
    {
      "epoch": 3.0,
      "step": 9414,
      "total_flos": 9795205750726656.0,
      "train_loss": 1.4433987489647233,
      "train_runtime": 7416.9186,
      "train_samples_per_second": 2.539,
      "train_steps_per_second": 1.269
    }
  ],
  "max_steps": 9414,
  "num_train_epochs": 3,
  "total_flos": 9795205750726656.0,
  "trial_name": null,
  "trial_params": null
}