Hugging Face's logo

Dmitriy007
/
Socrat_batch3_epochs5

Text Generation
Transformers
PyTorch
TensorBoard
gpt2
text-generation-inference
Inference Endpoints
Model card Files Metrics Community
1
Socrat_batch3_epochs5
File size: 3,032 Bytes 
63123e4
 
 
dd06878
 
63123e4
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
986fa5a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
40f38bd
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ce2ae74
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
dd06878
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
63123e4
 
 
 
dd06878
63123e4
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.500750375187594,
  "global_step": 6000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.13,
      "learning_rate": 1.949974987493747e-05,
      "loss": 2.8007,
      "step": 500
    },
    {
      "epoch": 0.25,
      "learning_rate": 1.8999499749874938e-05,
      "loss": 2.7961,
      "step": 1000
    },
    {
      "epoch": 0.25,
      "eval_loss": 3.1374855041503906,
      "eval_runtime": 136.8005,
      "eval_samples_per_second": 15.475,
      "eval_steps_per_second": 5.161,
      "step": 1000
    },
    {
      "epoch": 0.38,
      "learning_rate": 1.8499249624812408e-05,
      "loss": 2.8083,
      "step": 1500
    },
    {
      "epoch": 0.5,
      "learning_rate": 1.7998999499749875e-05,
      "loss": 2.8023,
      "step": 2000
    },
    {
      "epoch": 0.5,
      "eval_loss": 3.1418557167053223,
      "eval_runtime": 136.6543,
      "eval_samples_per_second": 15.492,
      "eval_steps_per_second": 5.166,
      "step": 2000
    },
    {
      "epoch": 0.63,
      "learning_rate": 1.7498749374687345e-05,
      "loss": 2.8088,
      "step": 2500
    },
    {
      "epoch": 0.75,
      "learning_rate": 1.6998499249624815e-05,
      "loss": 2.826,
      "step": 3000
    },
    {
      "epoch": 0.75,
      "eval_loss": 3.1343915462493896,
      "eval_runtime": 137.3583,
      "eval_samples_per_second": 15.412,
      "eval_steps_per_second": 5.14,
      "step": 3000
    },
    {
      "epoch": 0.88,
      "learning_rate": 1.649824912456228e-05,
      "loss": 2.8317,
      "step": 3500
    },
    {
      "epoch": 1.0,
      "learning_rate": 1.599799899949975e-05,
      "loss": 2.8097,
      "step": 4000
    },
    {
      "epoch": 1.0,
      "eval_loss": 3.1229424476623535,
      "eval_runtime": 136.4395,
      "eval_samples_per_second": 15.516,
      "eval_steps_per_second": 5.174,
      "step": 4000
    },
    {
      "epoch": 1.13,
      "learning_rate": 1.5497748874437218e-05,
      "loss": 2.5641,
      "step": 4500
    },
    {
      "epoch": 1.25,
      "learning_rate": 1.4997498749374688e-05,
      "loss": 2.5279,
      "step": 5000
    },
    {
      "epoch": 1.25,
      "eval_loss": 3.182180881500244,
      "eval_runtime": 136.5938,
      "eval_samples_per_second": 15.499,
      "eval_steps_per_second": 5.169,
      "step": 5000
    },
    {
      "epoch": 1.38,
      "learning_rate": 1.4497248624312156e-05,
      "loss": 2.5623,
      "step": 5500
    },
    {
      "epoch": 1.5,
      "learning_rate": 1.3996998499249626e-05,
      "loss": 2.5847,
      "step": 6000
    },
    {
      "epoch": 1.5,
      "eval_loss": 3.1701245307922363,
      "eval_runtime": 136.5649,
      "eval_samples_per_second": 15.502,
      "eval_steps_per_second": 5.17,
      "step": 6000
    }
  ],
  "max_steps": 19990,
  "num_train_epochs": 5,
  "total_flos": 8488904785920000.0,
  "trial_name": null,
  "trial_params": null
}