Hugging Face's logo

AlekseyKorshuk
/
dalio-6.7b-test

Text Generation
Transformers
PyTorch
opt
Generated from Trainer
text-generation-inference
Inference Endpoints
Model card Files Community
dalio-6.7b-test
File size: 2,710 Bytes 
f2dac18
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "global_step": 104,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02,
      "learning_rate": 0,
      "loss": 2.6804,
      "step": 1
    },
    {
      "epoch": 0.31,
      "learning_rate": 5e-05,
      "loss": 2.5958,
      "step": 16
    },
    {
      "epoch": 0.31,
      "eval_accuracy": 0.06585978124439663,
      "eval_loss": 2.537109375,
      "eval_runtime": 16.98,
      "eval_samples_per_second": 4.594,
      "eval_steps_per_second": 0.589,
      "step": 16
    },
    {
      "epoch": 0.62,
      "learning_rate": 5e-05,
      "loss": 2.3784,
      "step": 32
    },
    {
      "epoch": 0.62,
      "eval_accuracy": 0.06695355926125157,
      "eval_loss": 2.50390625,
      "eval_runtime": 17.6527,
      "eval_samples_per_second": 4.419,
      "eval_steps_per_second": 0.566,
      "step": 32
    },
    {
      "epoch": 0.92,
      "learning_rate": 5e-05,
      "loss": 2.3578,
      "step": 48
    },
    {
      "epoch": 0.92,
      "eval_accuracy": 0.06535771920387305,
      "eval_loss": 2.607421875,
      "eval_runtime": 17.1023,
      "eval_samples_per_second": 4.561,
      "eval_steps_per_second": 0.585,
      "step": 48
    },
    {
      "epoch": 1.23,
      "learning_rate": 5e-05,
      "loss": 1.3819,
      "step": 64
    },
    {
      "epoch": 1.23,
      "eval_accuracy": 0.06575219652142729,
      "eval_loss": 2.66796875,
      "eval_runtime": 16.8667,
      "eval_samples_per_second": 4.625,
      "eval_steps_per_second": 0.593,
      "step": 64
    },
    {
      "epoch": 1.54,
      "learning_rate": 5e-05,
      "loss": 1.1529,
      "step": 80
    },
    {
      "epoch": 1.54,
      "eval_accuracy": 0.06650528958221266,
      "eval_loss": 2.673828125,
      "eval_runtime": 17.3671,
      "eval_samples_per_second": 4.491,
      "eval_steps_per_second": 0.576,
      "step": 80
    },
    {
      "epoch": 1.85,
      "learning_rate": 5e-05,
      "loss": 1.2938,
      "step": 96
    },
    {
      "epoch": 1.85,
      "eval_accuracy": 0.06621839698762776,
      "eval_loss": 2.6640625,
      "eval_runtime": 17.6569,
      "eval_samples_per_second": 4.418,
      "eval_steps_per_second": 0.566,
      "step": 96
    },
    {
      "epoch": 2.0,
      "step": 104,
      "total_flos": 7482848575488.0,
      "train_loss": 1.82276857816256,
      "train_runtime": 1007.1646,
      "train_samples_per_second": 0.826,
      "train_steps_per_second": 0.103
    }
  ],
  "max_steps": 104,
  "num_train_epochs": 2,
  "total_flos": 7482848575488.0,
  "trial_name": null,
  "trial_params": null
}