Hugging Face's logo

cosail-knu
/
pythia-12b-draft-1.4b-code

Safetensors
gpt_neox
Model card Files
xet
 Community
pythia-12b-draft-1.4b-code
File size: 4,789 Bytes
9af8bb9
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 222,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.13513513513513514,
      "grad_norm": 4.732686519622803,
      "learning_rate": 2.9985590229902075e-05,
      "loss": 0.7417,
      "step": 10
    },
    {
      "epoch": 0.2702702702702703,
      "grad_norm": 3.3680124282836914,
      "learning_rate": 2.9730185992421254e-05,
      "loss": 0.7908,
      "step": 20
    },
    {
      "epoch": 0.40540540540540543,
      "grad_norm": 3.0871238708496094,
      "learning_rate": 2.9160833414327637e-05,
      "loss": 0.7802,
      "step": 30
    },
    {
      "epoch": 0.5405405405405406,
      "grad_norm": 3.7732794284820557,
      "learning_rate": 2.828966725734167e-05,
      "loss": 0.7226,
      "step": 40
    },
    {
      "epoch": 0.6756756756756757,
      "grad_norm": 2.8783252239227295,
      "learning_rate": 2.7135254915624213e-05,
      "loss": 0.7014,
      "step": 50
    },
    {
      "epoch": 0.8108108108108109,
      "grad_norm": 2.532087564468384,
      "learning_rate": 2.5722200684005718e-05,
      "loss": 0.7439,
      "step": 60
    },
    {
      "epoch": 0.9459459459459459,
      "grad_norm": 2.4696850776672363,
      "learning_rate": 2.408062136015872e-05,
      "loss": 0.6379,
      "step": 70
    },
    {
      "epoch": 1.0810810810810811,
      "grad_norm": 2.8075332641601562,
      "learning_rate": 2.224550435734272e-05,
      "loss": 0.5366,
      "step": 80
    },
    {
      "epoch": 1.2162162162162162,
      "grad_norm": 2.7424261569976807,
      "learning_rate": 2.025596200843394e-05,
      "loss": 0.4058,
      "step": 90
    },
    {
      "epoch": 1.3513513513513513,
      "grad_norm": 2.1651532649993896,
      "learning_rate": 1.8154397954454996e-05,
      "loss": 0.3565,
      "step": 100
    },
    {
      "epoch": 1.4864864864864864,
      "grad_norm": 2.214755058288574,
      "learning_rate": 1.5985603384585545e-05,
      "loss": 0.3433,
      "step": 110
    },
    {
      "epoch": 1.6216216216216215,
      "grad_norm": 2.32694149017334,
      "learning_rate": 1.3795802389729185e-05,
      "loss": 0.3638,
      "step": 120
    },
    {
      "epoch": 1.7567567567567568,
      "grad_norm": 2.7102766036987305,
      "learning_rate": 1.1631666776267804e-05,
      "loss": 0.3596,
      "step": 130
    },
    {
      "epoch": 1.8918918918918919,
      "grad_norm": 2.407752752304077,
      "learning_rate": 9.5393213375378e-06,
      "loss": 0.3402,
      "step": 140
    },
    {
      "epoch": 2.027027027027027,
      "grad_norm": 1.9417186975479126,
      "learning_rate": 7.563360783939724e-06,
      "loss": 0.3151,
      "step": 150
    },
    {
      "epoch": 2.1621621621621623,
      "grad_norm": 1.993277668952942,
      "learning_rate": 5.7458992841091544e-06,
      "loss": 0.1574,
      "step": 160
    },
    {
      "epoch": 2.2972972972972974,
      "grad_norm": 2.380396842956543,
      "learning_rate": 4.125672874528797e-06,
      "loss": 0.1328,
      "step": 170
    },
    {
      "epoch": 2.4324324324324325,
      "grad_norm": 1.8678067922592163,
      "learning_rate": 2.7372138681624246e-06,
      "loss": 0.1513,
      "step": 180
    },
    {
      "epoch": 2.5675675675675675,
      "grad_norm": 2.369248390197754,
      "learning_rate": 1.6101148581573276e-06,
      "loss": 0.1439,
      "step": 190
    },
    {
      "epoch": 2.7027027027027026,
      "grad_norm": 2.006781578063965,
      "learning_rate": 7.683980030985655e-07,
      "loss": 0.1269,
      "step": 200
    },
    {
      "epoch": 2.8378378378378377,
      "grad_norm": 1.7674449682235718,
      "learning_rate": 2.300030364048139e-07,
      "loss": 0.1388,
      "step": 210
    },
    {
      "epoch": 2.972972972972973,
      "grad_norm": 1.7466319799423218,
      "learning_rate": 6.404912056610091e-09,
      "loss": 0.14,
      "step": 220
    },
    {
      "epoch": 3.0,
      "step": 222,
      "total_flos": 2.842963155615744e+16,
      "train_loss": 0.41255371541053326,
      "train_runtime": 985.4369,
      "train_samples_per_second": 3.58,
      "train_steps_per_second": 0.225
    }
  ],
  "logging_steps": 10,
  "max_steps": 222,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": false,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.842963155615744e+16,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}