Hugging Face's logo

GanymedeNil
/
gemma-2b-technology-news-title-generation-lora

Text Generation
TensorBoard
Safetensors
Chinese
unsloth
Model card Files Metrics Community
1
gemma-2b-technology-news-title-generation-lora
File size: 2,339 Bytes 
89ce1a9
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": 2.126384735107422,
  "best_model_checkpoint": "saves/Gemma-2B/lora/train_2024-03-01-04-36-32/checkpoint-100",
  "epoch": 0.17777777777777778,
  "eval_steps": 100,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02,
      "grad_norm": 6.6079277992248535,
      "learning_rate": 4.999960939662063e-05,
      "loss": 3.747,
      "step": 10
    },
    {
      "epoch": 0.04,
      "grad_norm": 3.2283411026000977,
      "learning_rate": 4.999843759868819e-05,
      "loss": 3.5789,
      "step": 20
    },
    {
      "epoch": 0.05,
      "grad_norm": 41.573001861572266,
      "learning_rate": 4.999648464281934e-05,
      "loss": 3.1683,
      "step": 30
    },
    {
      "epoch": 0.07,
      "grad_norm": 4.080965518951416,
      "learning_rate": 4.9993750590040575e-05,
      "loss": 2.8275,
      "step": 40
    },
    {
      "epoch": 0.09,
      "grad_norm": 4.576275825500488,
      "learning_rate": 4.999023552578632e-05,
      "loss": 2.6758,
      "step": 50
    },
    {
      "epoch": 0.11,
      "grad_norm": 18.012842178344727,
      "learning_rate": 4.998593955989626e-05,
      "loss": 2.6287,
      "step": 60
    },
    {
      "epoch": 0.12,
      "grad_norm": 5.738934516906738,
      "learning_rate": 4.9980862826611875e-05,
      "loss": 2.5284,
      "step": 70
    },
    {
      "epoch": 0.14,
      "grad_norm": 3.353776216506958,
      "learning_rate": 4.9975005484572305e-05,
      "loss": 2.2608,
      "step": 80
    },
    {
      "epoch": 0.16,
      "grad_norm": 4.6298699378967285,
      "learning_rate": 4.9968367716809374e-05,
      "loss": 2.2475,
      "step": 90
    },
    {
      "epoch": 0.18,
      "grad_norm": 50.594207763671875,
      "learning_rate": 4.996094973074183e-05,
      "loss": 2.2007,
      "step": 100
    },
    {
      "epoch": 0.18,
      "eval_loss": 2.126384735107422,
      "eval_runtime": 124.9221,
      "eval_samples_per_second": 8.005,
      "eval_steps_per_second": 2.001,
      "step": 100
    }
  ],
  "logging_steps": 10,
  "max_steps": 5620,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 100,
  "total_flos": 8.247898064093184e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}