Hugging Face's logo

paulo037
/
stable-code-instruct-3b-syntetic-1000

Safetensors
Model card Files Community
stable-code-instruct-3b-syntetic-1000
File size: 2,625 Bytes 
352385d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.961783439490446,
  "eval_steps": 1,
  "global_step": 117,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.97,
      "grad_norm": 1.752838134765625,
      "learning_rate": 0.00013103448275862068,
      "loss": 1.9056,
      "step": 19
    },
    {
      "epoch": 0.97,
      "eval_loss": 1.2314808368682861,
      "eval_runtime": 41.0888,
      "eval_samples_per_second": 3.407,
      "eval_steps_per_second": 3.407,
      "step": 19
    },
    {
      "epoch": 1.99,
      "grad_norm": 0.3157634139060974,
      "learning_rate": 0.000197828447339848,
      "loss": 0.7969,
      "step": 39
    },
    {
      "epoch": 1.99,
      "eval_loss": 0.6621134877204895,
      "eval_runtime": 41.1024,
      "eval_samples_per_second": 3.406,
      "eval_steps_per_second": 3.406,
      "step": 39
    },
    {
      "epoch": 2.96,
      "grad_norm": 0.46234801411628723,
      "learning_rate": 0.0001937024972855592,
      "loss": 0.564,
      "step": 58
    },
    {
      "epoch": 2.96,
      "eval_loss": 0.5718151330947876,
      "eval_runtime": 41.1043,
      "eval_samples_per_second": 3.406,
      "eval_steps_per_second": 3.406,
      "step": 58
    },
    {
      "epoch": 3.97,
      "grad_norm": 0.5510583519935608,
      "learning_rate": 0.00018935939196525515,
      "loss": 0.3962,
      "step": 78
    },
    {
      "epoch": 3.97,
      "eval_loss": 0.5229483246803284,
      "eval_runtime": 41.1671,
      "eval_samples_per_second": 3.401,
      "eval_steps_per_second": 3.401,
      "step": 78
    },
    {
      "epoch": 4.99,
      "grad_norm": 4.286730766296387,
      "learning_rate": 0.00018501628664495113,
      "loss": 0.3022,
      "step": 98
    },
    {
      "epoch": 4.99,
      "eval_loss": 0.5116992592811584,
      "eval_runtime": 41.1636,
      "eval_samples_per_second": 3.401,
      "eval_steps_per_second": 3.401,
      "step": 98
    },
    {
      "epoch": 5.96,
      "grad_norm": 0.6076149940490723,
      "learning_rate": 0.00018089033659066234,
      "loss": 0.2504,
      "step": 117
    },
    {
      "epoch": 5.96,
      "eval_loss": 0.5122354030609131,
      "eval_runtime": 41.1631,
      "eval_samples_per_second": 3.401,
      "eval_steps_per_second": 3.401,
      "step": 117
    }
  ],
  "logging_steps": 1,
  "max_steps": 950,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 50,
  "save_steps": 1,
  "total_flos": 3.950551278360576e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}