Hugging Face's logo

quintic
/
finetune_lean_2b

Text Generation
Transformers
PyTorch
Safetensors
codegen
Inference Endpoints
Model card Files Community
1
finetune_lean_2b
File size: 2,975 Bytes 
234adcf
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 20.0,
  "global_step": 580,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "learning_rate": 3.6559821951932435e-06,
      "loss": 2.0662,
      "step": 29
    },
    {
      "epoch": 2.0,
      "learning_rate": 5.463687482021196e-06,
      "loss": 1.413,
      "step": 58
    },
    {
      "epoch": 3.0,
      "learning_rate": 6.2507068274056945e-06,
      "loss": 1.1678,
      "step": 87
    },
    {
      "epoch": 4.0,
      "learning_rate": 6.760687110038668e-06,
      "loss": 1.0382,
      "step": 116
    },
    {
      "epoch": 5.0,
      "learning_rate": 7.13867309942701e-06,
      "loss": 0.954,
      "step": 145
    },
    {
      "epoch": 6.0,
      "learning_rate": 7.439130415804967e-06,
      "loss": 0.8951,
      "step": 174
    },
    {
      "epoch": 7.0,
      "learning_rate": 7.688512885309291e-06,
      "loss": 0.8487,
      "step": 203
    },
    {
      "epoch": 8.0,
      "learning_rate": 7.901687980648141e-06,
      "loss": 0.8119,
      "step": 232
    },
    {
      "epoch": 9.0,
      "learning_rate": 8.087848755754509e-06,
      "loss": 0.7811,
      "step": 261
    },
    {
      "epoch": 10.0,
      "learning_rate": 8.253078243154342e-06,
      "loss": 0.7546,
      "step": 290
    },
    {
      "epoch": 11.0,
      "learning_rate": 8.401611184973133e-06,
      "loss": 0.7308,
      "step": 319
    },
    {
      "epoch": 12.0,
      "learning_rate": 8.53651443066959e-06,
      "loss": 0.7102,
      "step": 348
    },
    {
      "epoch": 13.0,
      "learning_rate": 8.66008046615066e-06,
      "loss": 0.6909,
      "step": 377
    },
    {
      "epoch": 14.0,
      "learning_rate": 8.774067992353493e-06,
      "loss": 0.6728,
      "step": 406
    },
    {
      "epoch": 15.0,
      "learning_rate": 8.879855771890845e-06,
      "loss": 0.6564,
      "step": 435
    },
    {
      "epoch": 16.0,
      "learning_rate": 8.9785447549646e-06,
      "loss": 0.64,
      "step": 464
    },
    {
      "epoch": 17.0,
      "learning_rate": 9.071028041604564e-06,
      "loss": 0.6247,
      "step": 493
    },
    {
      "epoch": 18.0,
      "learning_rate": 9.15804011885607e-06,
      "loss": 0.611,
      "step": 522
    },
    {
      "epoch": 19.0,
      "learning_rate": 9.240192329946528e-06,
      "loss": 0.5964,
      "step": 551
    },
    {
      "epoch": 20.0,
      "learning_rate": 9.317998951644404e-06,
      "loss": 0.5837,
      "step": 580
    },
    {
      "epoch": 20.0,
      "step": 580,
      "total_flos": 1134007009935360.0,
      "train_loss": 0.8623725891113281,
      "train_runtime": 17895.3422,
      "train_samples_per_second": 8.201,
      "train_steps_per_second": 0.032
    }
  ],
  "max_steps": 580,
  "num_train_epochs": 20,
  "total_flos": 1134007009935360.0,
  "trial_name": null,
  "trial_params": null
}