Hugging Face's logo

tmnam20
/
gpt1_n-layer-4_xnli

Text Classification
Transformers
PyTorch
openai-gpt
Inference Endpoints
Model card Files Community
1
gpt1_n-layer-4_xnli
File size: 2,437 Bytes 
7f2afba
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": 1.099884271621704,
  "best_model_checkpoint": "/kaggle/output/checkpoint-5000",
  "epoch": 0.20371577574967406,
  "eval_steps": 1000,
  "global_step": 5000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 2.7777777777777777e-11,
      "loss": 1.0632,
      "step": 1
    },
    {
      "epoch": 0.04,
      "learning_rate": 2.7750000000000004e-08,
      "loss": 1.1913,
      "step": 1000
    },
    {
      "epoch": 0.04,
      "eval_accuracy": 0.3269461077844311,
      "eval_loss": 1.1269203424453735,
      "eval_runtime": 20.7749,
      "eval_samples_per_second": 241.156,
      "eval_steps_per_second": 30.181,
      "step": 1000
    },
    {
      "epoch": 0.08,
      "learning_rate": 5.5527777777777784e-08,
      "loss": 1.1253,
      "step": 2000
    },
    {
      "epoch": 0.08,
      "eval_accuracy": 0.32914171656686625,
      "eval_loss": 1.102368712425232,
      "eval_runtime": 20.9681,
      "eval_samples_per_second": 238.935,
      "eval_steps_per_second": 29.903,
      "step": 2000
    },
    {
      "epoch": 0.12,
      "learning_rate": 8.327777777777778e-08,
      "loss": 1.1163,
      "step": 3000
    },
    {
      "epoch": 0.12,
      "eval_accuracy": 0.3461077844311377,
      "eval_loss": 1.1018893718719482,
      "eval_runtime": 20.86,
      "eval_samples_per_second": 240.173,
      "eval_steps_per_second": 30.058,
      "step": 3000
    },
    {
      "epoch": 0.16,
      "learning_rate": 1.1105555555555557e-07,
      "loss": 1.115,
      "step": 4000
    },
    {
      "epoch": 0.16,
      "eval_accuracy": 0.3500998003992016,
      "eval_loss": 1.1005553007125854,
      "eval_runtime": 21.0518,
      "eval_samples_per_second": 237.985,
      "eval_steps_per_second": 29.784,
      "step": 4000
    },
    {
      "epoch": 0.2,
      "learning_rate": 1.3880555555555558e-07,
      "loss": 1.1162,
      "step": 5000
    },
    {
      "epoch": 0.2,
      "eval_accuracy": 0.3405189620758483,
      "eval_loss": 1.099884271621704,
      "eval_runtime": 20.9202,
      "eval_samples_per_second": 239.482,
      "eval_steps_per_second": 29.971,
      "step": 5000
    }
  ],
  "logging_steps": 1000,
  "max_steps": 10000000,
  "num_train_epochs": 408,
  "save_steps": 1000,
  "total_flos": 3484113960960000.0,
  "trial_name": null,
  "trial_params": null
}