Hugging Face's logo

slplab
/
kogpt_pretrained-asd

PEFT
TensorBoard
Safetensors
Generated from Trainer
Model card Files Metrics Community
slplab commited on
Commit
b6e2b70
·
verified ·
1 Parent(s): ec619bd

End of training

Browse files
Files changed (6) hide show
  1. README.md +57 -0
  2. adapter_config.json +195 -0
  3. adapter_model.safetensors +3 -0
  4. runs/Aug17_13-55-19_oem-WS-C621E-SAGE-Series/events.out.tfevents.1723870522.oem-WS-C621E-SAGE-Series.3587736.0 +3 -0
  5. runs/Aug18_02-41-27_oem-WS-C621E-SAGE-Series/events.out.tfevents.1723916488.oem-WS-C621E-SAGE-Series.592469.0 +3 -0
  6. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: cc-by-nc-nd-4.0
3
+ library_name: peft
4
+ tags:
5
+ - generated_from_trainer
6
+ base_model: kakaobrain/kogpt
7
+ model-index:
8
+ - name: kogpt_pretrained-asd
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ # kogpt_pretrained-asd
16
+
17
+ This model is a fine-tuned version of [kakaobrain/kogpt](https://huggingface.co/kakaobrain/kogpt) on the None dataset.
18
+
19
+ ## Model description
20
+
21
+ More information needed
22
+
23
+ ## Intended uses & limitations
24
+
25
+ More information needed
26
+
27
+ ## Training and evaluation data
28
+
29
+ More information needed
30
+
31
+ ## Training procedure
32
+
33
+ ### Training hyperparameters
34
+
35
+ The following hyperparameters were used during training:
36
+ - learning_rate: 2e-05
37
+ - train_batch_size: 1
38
+ - eval_batch_size: 8
39
+ - seed: 42
40
+ - gradient_accumulation_steps: 8
41
+ - total_train_batch_size: 8
42
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
43
+ - lr_scheduler_type: linear
44
+ - num_epochs: 1
45
+ - mixed_precision_training: Native AMP
46
+
47
+ ### Training results
48
+
49
+
50
+
51
+ ### Framework versions
52
+
53
+ - PEFT 0.11.1
54
+ - Transformers 4.41.1
55
+ - Pytorch 2.3.0+cu121
56
+ - Datasets 2.19.1
57
+ - Tokenizers 0.19.1
adapter_config.json ADDED
@@ -0,0 +1,195 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "kakaobrain/kogpt",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 16,
14
+ "lora_dropout": 0.05,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 8,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "transformer.h.7.attn.v_proj",
24
+ "transformer.h.16.attn.v_proj",
25
+ "transformer.h.24.attn.out_proj",
26
+ "transformer.h.11.attn.q_proj",
27
+ "transformer.h.23.attn.v_proj",
28
+ "transformer.h.20.attn.out_proj",
29
+ "transformer.h.16.mlp.fc_in",
30
+ "transformer.h.9.mlp.fc_out",
31
+ "transformer.h.16.attn.q_proj",
32
+ "transformer.h.18.mlp.fc_in",
33
+ "transformer.h.6.attn.k_proj",
34
+ "transformer.h.4.attn.out_proj",
35
+ "transformer.h.0.mlp.fc_in",
36
+ "transformer.h.23.attn.out_proj",
37
+ "transformer.h.21.attn.k_proj",
38
+ "transformer.h.25.attn.q_proj",
39
+ "transformer.h.5.attn.v_proj",
40
+ "transformer.h.23.attn.q_proj",
41
+ "transformer.h.12.attn.q_proj",
42
+ "transformer.h.7.attn.q_proj",
43
+ "transformer.h.1.attn.k_proj",
44
+ "transformer.h.18.mlp.fc_out",
45
+ "transformer.h.3.attn.k_proj",
46
+ "transformer.h.20.attn.k_proj",
47
+ "transformer.h.5.mlp.fc_out",
48
+ "transformer.h.2.attn.v_proj",
49
+ "transformer.h.12.attn.v_proj",
50
+ "transformer.h.13.attn.k_proj",
51
+ "transformer.h.5.attn.out_proj",
52
+ "transformer.h.18.attn.out_proj",
53
+ "transformer.h.17.attn.q_proj",
54
+ "transformer.h.11.attn.v_proj",
55
+ "transformer.h.16.attn.out_proj",
56
+ "transformer.h.22.mlp.fc_out",
57
+ "transformer.h.21.attn.out_proj",
58
+ "transformer.h.14.attn.q_proj",
59
+ "transformer.h.10.attn.k_proj",
60
+ "transformer.h.10.attn.v_proj",
61
+ "transformer.h.14.mlp.fc_out",
62
+ "transformer.h.0.mlp.fc_out",
63
+ "transformer.h.2.attn.q_proj",
64
+ "transformer.h.0.attn.v_proj",
65
+ "transformer.h.2.attn.out_proj",
66
+ "transformer.h.13.attn.v_proj",
67
+ "transformer.h.27.mlp.fc_in",
68
+ "transformer.h.26.mlp.fc_out",
69
+ "transformer.h.10.attn.out_proj",
70
+ "transformer.h.21.attn.v_proj",
71
+ "transformer.h.27.attn.out_proj",
72
+ "transformer.h.22.attn.q_proj",
73
+ "transformer.h.8.attn.k_proj",
74
+ "transformer.h.15.mlp.fc_in",
75
+ "transformer.h.24.mlp.fc_out",
76
+ "transformer.h.12.attn.out_proj",
77
+ "transformer.h.7.attn.k_proj",
78
+ "transformer.h.0.attn.q_proj",
79
+ "transformer.h.10.attn.q_proj",
80
+ "transformer.h.3.attn.out_proj",
81
+ "transformer.h.1.attn.out_proj",
82
+ "transformer.h.6.mlp.fc_in",
83
+ "transformer.h.18.attn.v_proj",
84
+ "transformer.h.3.attn.v_proj",
85
+ "transformer.h.4.attn.v_proj",
86
+ "transformer.h.22.attn.k_proj",
87
+ "transformer.h.20.mlp.fc_out",
88
+ "transformer.h.19.mlp.fc_out",
89
+ "transformer.h.25.attn.k_proj",
90
+ "transformer.h.27.attn.v_proj",
91
+ "transformer.h.5.attn.k_proj",
92
+ "transformer.h.4.attn.q_proj",
93
+ "transformer.h.22.attn.v_proj",
94
+ "transformer.h.9.mlp.fc_in",
95
+ "transformer.h.20.attn.v_proj",
96
+ "transformer.h.22.attn.out_proj",
97
+ "transformer.h.19.attn.v_proj",
98
+ "transformer.h.7.attn.out_proj",
99
+ "transformer.h.7.mlp.fc_in",
100
+ "transformer.h.8.mlp.fc_out",
101
+ "transformer.h.15.attn.v_proj",
102
+ "transformer.h.1.attn.q_proj",
103
+ "transformer.h.1.mlp.fc_out",
104
+ "transformer.h.11.attn.out_proj",
105
+ "transformer.h.25.mlp.fc_in",
106
+ "transformer.h.19.attn.q_proj",
107
+ "transformer.h.18.attn.k_proj",
108
+ "transformer.h.20.attn.q_proj",
109
+ "transformer.h.2.mlp.fc_in",
110
+ "transformer.h.9.attn.out_proj",
111
+ "transformer.h.21.mlp.fc_out",
112
+ "transformer.h.24.mlp.fc_in",
113
+ "transformer.h.10.mlp.fc_in",
114
+ "transformer.h.10.mlp.fc_out",
115
+ "transformer.h.18.attn.q_proj",
116
+ "transformer.h.8.attn.v_proj",
117
+ "transformer.h.9.attn.k_proj",
118
+ "transformer.h.17.attn.v_proj",
119
+ "transformer.h.4.mlp.fc_in",
120
+ "transformer.h.0.attn.k_proj",
121
+ "transformer.h.5.attn.q_proj",
122
+ "transformer.h.11.mlp.fc_out",
123
+ "transformer.h.19.attn.out_proj",
124
+ "transformer.h.2.mlp.fc_out",
125
+ "transformer.h.19.mlp.fc_in",
126
+ "transformer.h.25.attn.v_proj",
127
+ "transformer.h.9.attn.v_proj",
128
+ "transformer.h.3.mlp.fc_out",
129
+ "transformer.h.1.attn.v_proj",
130
+ "transformer.h.12.attn.k_proj",
131
+ "transformer.h.6.mlp.fc_out",
132
+ "transformer.h.26.mlp.fc_in",
133
+ "transformer.h.9.attn.q_proj",
134
+ "transformer.h.17.mlp.fc_in",
135
+ "transformer.h.16.attn.k_proj",
136
+ "transformer.h.24.attn.k_proj",
137
+ "transformer.h.8.attn.q_proj",
138
+ "transformer.h.11.attn.k_proj",
139
+ "transformer.h.13.mlp.fc_out",
140
+ "transformer.h.16.mlp.fc_out",
141
+ "transformer.h.15.mlp.fc_out",
142
+ "transformer.h.6.attn.out_proj",
143
+ "transformer.h.23.attn.k_proj",
144
+ "transformer.h.27.attn.q_proj",
145
+ "transformer.h.0.attn.out_proj",
146
+ "transformer.h.4.attn.k_proj",
147
+ "transformer.h.14.attn.v_proj",
148
+ "transformer.h.15.attn.k_proj",
149
+ "transformer.h.3.attn.q_proj",
150
+ "transformer.h.22.mlp.fc_in",
151
+ "transformer.h.21.attn.q_proj",
152
+ "transformer.h.23.mlp.fc_out",
153
+ "transformer.h.6.attn.q_proj",
154
+ "transformer.h.17.attn.out_proj",
155
+ "transformer.h.26.attn.out_proj",
156
+ "transformer.h.17.mlp.fc_out",
157
+ "transformer.h.26.attn.q_proj",
158
+ "transformer.h.13.mlp.fc_in",
159
+ "transformer.h.11.mlp.fc_in",
160
+ "transformer.h.17.attn.k_proj",
161
+ "transformer.h.8.mlp.fc_in",
162
+ "transformer.h.12.mlp.fc_in",
163
+ "transformer.h.1.mlp.fc_in",
164
+ "transformer.h.27.mlp.fc_out",
165
+ "transformer.h.7.mlp.fc_out",
166
+ "transformer.h.21.mlp.fc_in",
167
+ "transformer.h.24.attn.q_proj",
168
+ "transformer.h.5.mlp.fc_in",
169
+ "transformer.h.20.mlp.fc_in",
170
+ "transformer.h.24.attn.v_proj",
171
+ "transformer.h.13.attn.q_proj",
172
+ "transformer.h.27.attn.k_proj",
173
+ "transformer.h.15.attn.q_proj",
174
+ "transformer.h.2.attn.k_proj",
175
+ "transformer.h.25.attn.out_proj",
176
+ "transformer.h.25.mlp.fc_out",
177
+ "transformer.h.26.attn.k_proj",
178
+ "transformer.h.6.attn.v_proj",
179
+ "transformer.h.15.attn.out_proj",
180
+ "transformer.h.14.attn.out_proj",
181
+ "transformer.h.4.mlp.fc_out",
182
+ "transformer.h.13.attn.out_proj",
183
+ "transformer.h.14.attn.k_proj",
184
+ "transformer.h.23.mlp.fc_in",
185
+ "transformer.h.8.attn.out_proj",
186
+ "transformer.h.14.mlp.fc_in",
187
+ "transformer.h.19.attn.k_proj",
188
+ "transformer.h.26.attn.v_proj",
189
+ "transformer.h.12.mlp.fc_out",
190
+ "transformer.h.3.mlp.fc_in"
191
+ ],
192
+ "task_type": "CAUSAL_LM",
193
+ "use_dora": false,
194
+ "use_rslora": false
195
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2476d25b2abea5668675455bcbe6997bd1c6a11e66e27f2584359227a6f8c112
3
+ size 66103768
runs/Aug17_13-55-19_oem-WS-C621E-SAGE-Series/events.out.tfevents.1723870522.oem-WS-C621E-SAGE-Series.3587736.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:940a93e0257b67b899065a60da4d5a718f083d383c5e5853855fe3b9823e896b
3
+ size 5274
runs/Aug18_02-41-27_oem-WS-C621E-SAGE-Series/events.out.tfevents.1723916488.oem-WS-C621E-SAGE-Series.592469.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da7fadcafa798ec261f498693a6a0ce943b3d3a1c7357316168d530baa26d1b8
3
+ size 5835
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:875b0661fec2aec99827fdb2a00764839ebc19e3ba2ddaf767a7c1832fc96458
3
+ size 5240