Hugging Face's logo

zirui3
/
gpt_1.4B_oa_instruct

Text Generation
Transformers
PyTorch
gpt_neox
text-generation-inference
Inference Endpoints
Model card Files Community
1
gpt_1.4B_oa_instruct
File size: 2,478 Bytes 
f5b6f8f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "global_step": 1671,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.12,
      "eval_loss": 0.49560546875,
      "eval_runtime": 8.4829,
      "eval_samples_per_second": 63.657,
      "eval_steps_per_second": 8.016,
      "step": 200
    },
    {
      "epoch": 0.24,
      "eval_loss": 0.479248046875,
      "eval_runtime": 8.8248,
      "eval_samples_per_second": 61.191,
      "eval_steps_per_second": 7.706,
      "step": 400
    },
    {
      "epoch": 0.3,
      "learning_rate": 5e-06,
      "loss": 1.6261,
      "step": 500
    },
    {
      "epoch": 0.36,
      "eval_loss": 0.47021484375,
      "eval_runtime": 7.5494,
      "eval_samples_per_second": 71.529,
      "eval_steps_per_second": 9.007,
      "step": 600
    },
    {
      "epoch": 0.48,
      "eval_loss": 0.465087890625,
      "eval_runtime": 8.7604,
      "eval_samples_per_second": 61.641,
      "eval_steps_per_second": 7.762,
      "step": 800
    },
    {
      "epoch": 0.6,
      "learning_rate": 5e-06,
      "loss": 0.4577,
      "step": 1000
    },
    {
      "epoch": 0.6,
      "eval_loss": 0.46044921875,
      "eval_runtime": 7.9849,
      "eval_samples_per_second": 67.627,
      "eval_steps_per_second": 8.516,
      "step": 1000
    },
    {
      "epoch": 0.72,
      "eval_loss": 0.455322265625,
      "eval_runtime": 8.5578,
      "eval_samples_per_second": 63.1,
      "eval_steps_per_second": 7.946,
      "step": 1200
    },
    {
      "epoch": 0.84,
      "eval_loss": 0.45263671875,
      "eval_runtime": 7.841,
      "eval_samples_per_second": 68.868,
      "eval_steps_per_second": 8.672,
      "step": 1400
    },
    {
      "epoch": 0.9,
      "learning_rate": 5e-06,
      "loss": 0.4486,
      "step": 1500
    },
    {
      "epoch": 0.96,
      "eval_loss": 0.450439453125,
      "eval_runtime": 10.8958,
      "eval_samples_per_second": 49.56,
      "eval_steps_per_second": 6.241,
      "step": 1600
    },
    {
      "epoch": 1.0,
      "step": 1671,
      "total_flos": 1.1778474718632346e+17,
      "train_loss": 0.8031303182039198,
      "train_runtime": 6338.6403,
      "train_samples_per_second": 8.433,
      "train_steps_per_second": 0.264
    }
  ],
  "max_steps": 1671,
  "num_train_epochs": 1,
  "total_flos": 1.1778474718632346e+17,
  "trial_name": null,
  "trial_params": null
}