Hugging Face's logo

chenhaodev
/
yi-6b-llama-onc-v1

PEFT
Safetensors
llama-factory
lora
Generated from Trainer
Model card Files Community
yi-6b-llama-onc-v1
File size: 1,652 Bytes 
e471c8e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9828009828009828,
  "eval_steps": 500,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.1,
      "learning_rate": 0.000125,
      "loss": 1.6979,
      "step": 10
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.000375,
      "loss": 0.7265,
      "step": 20
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0004969974623692023,
      "loss": 0.1676,
      "step": 30
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0004640417248825666,
      "loss": 0.1557,
      "step": 40
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00039928964792569654,
      "loss": 0.1458,
      "step": 50
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.00031236028601449537,
      "loss": 0.1429,
      "step": 60
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0002161671750624673,
      "loss": 0.1502,
      "step": 70
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00012500000000000006,
      "loss": 0.1432,
      "step": 80
    },
    {
      "epoch": 0.88,
      "learning_rate": 5.2401832620310204e-05,
      "loss": 0.1426,
      "step": 90
    },
    {
      "epoch": 0.98,
      "learning_rate": 9.157280346029916e-06,
      "loss": 0.1354,
      "step": 100
    }
  ],
  "logging_steps": 10,
  "max_steps": 101,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "total_flos": 5.498116162505933e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}