Hugging Face's logo

Kartik305
/
starcoder2-lora-stack-smol-py

Safetensors
Model card Files
xet
Community
starcoder2-lora-stack-smol-py
File size: 1,931 Bytes
0c41562
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.08,
  "eval_steps": 500,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "grad_norm": 0.07421875,
      "learning_rate": 1e-05,
      "loss": 1.0535,
      "step": 10
    },
    {
      "epoch": 0.02,
      "grad_norm": 0.05810546875,
      "learning_rate": 2e-05,
      "loss": 1.0094,
      "step": 20
    },
    {
      "epoch": 0.02,
      "grad_norm": 0.057373046875,
      "learning_rate": 1.9238795325112867e-05,
      "loss": 1.1218,
      "step": 30
    },
    {
      "epoch": 0.03,
      "grad_norm": 0.09326171875,
      "learning_rate": 1.7071067811865477e-05,
      "loss": 1.1462,
      "step": 40
    },
    {
      "epoch": 0.04,
      "grad_norm": 0.0810546875,
      "learning_rate": 1.3826834323650899e-05,
      "loss": 1.1941,
      "step": 50
    },
    {
      "epoch": 0.05,
      "grad_norm": 0.11474609375,
      "learning_rate": 1e-05,
      "loss": 1.1372,
      "step": 60
    },
    {
      "epoch": 0.06,
      "grad_norm": 0.1240234375,
      "learning_rate": 6.173165676349103e-06,
      "loss": 1.0662,
      "step": 70
    },
    {
      "epoch": 0.06,
      "grad_norm": 0.130859375,
      "learning_rate": 2.9289321881345257e-06,
      "loss": 1.1987,
      "step": 80
    },
    {
      "epoch": 0.07,
      "grad_norm": 0.11083984375,
      "learning_rate": 7.612046748871327e-07,
      "loss": 1.1803,
      "step": 90
    },
    {
      "epoch": 0.08,
      "grad_norm": 0.193359375,
      "learning_rate": 0.0,
      "loss": 1.1585,
      "step": 100
    }
  ],
  "logging_steps": 10,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "total_flos": 2.174140845706445e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}