Hugging Face's logo

Lustyrobo
/
results

Question Answering
PEFT
TensorBoard
English
Llama
Model card Files
xet
Metrics Community
Lustyrobo commited on
Commit
4db4522
路
verified 路
1 Parent(s): 8d084d8

Upload 22 files

Browse files
Files changed (22) hide show
  1. README.md +272 -0
  2. adapter_config (1).json +21 -0
  3. added_tokens.json +3 -0
  4. events.out.tfevents.1722267239.80c456c5842f.227.0 +3 -0
  5. events.out.tfevents.1722267421.80c456c5842f.227.1 +3 -0
  6. events.out.tfevents.1722267452.80c456c5842f.227.2 +3 -0
  7. events.out.tfevents.1722267484.80c456c5842f.227.3 +3 -0
  8. events.out.tfevents.1722267518.80c456c5842f.227.4 +3 -0
  9. events.out.tfevents.1722267551.80c456c5842f.227.5 +3 -0
  10. events.out.tfevents.1722267584.80c456c5842f.227.6 +3 -0
  11. events.out.tfevents.1722267620.80c456c5842f.227.7 +3 -0
  12. events.out.tfevents.1722267654.80c456c5842f.227.8 +3 -0
  13. events.out.tfevents.1722267690.80c456c5842f.227.9 +3 -0
  14. events.out.tfevents.1722267724.80c456c5842f.227.10 +3 -0
  15. rng_state.pth +3 -0
  16. scheduler.pt +3 -0
  17. special_tokens_map.json +24 -0
  18. tokenizer.json +0 -0
  19. tokenizer.model +3 -0
  20. tokenizer_config.json +32 -0
  21. trainer_state.json +22 -0
  22. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,272 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ ---
4
+ ## Training procedure
5
+
6
+
7
+ The following `bitsandbytes` quantization config was used during training:
8
+ - load_in_8bit: False
9
+ - load_in_4bit: True
10
+ - llm_int8_threshold: 6.0
11
+ - llm_int8_skip_modules: None
12
+ - llm_int8_enable_fp32_cpu_offload: False
13
+ - llm_int8_has_fp16_weight: False
14
+ - bnb_4bit_quant_type: nf4
15
+ - bnb_4bit_use_double_quant: False
16
+ - bnb_4bit_compute_dtype: float16
17
+
18
+ The following `bitsandbytes` quantization config was used during training:
19
+ - load_in_8bit: False
20
+ - load_in_4bit: True
21
+ - llm_int8_threshold: 6.0
22
+ - llm_int8_skip_modules: None
23
+ - llm_int8_enable_fp32_cpu_offload: False
24
+ - llm_int8_has_fp16_weight: False
25
+ - bnb_4bit_quant_type: nf4
26
+ - bnb_4bit_use_double_quant: False
27
+ - bnb_4bit_compute_dtype: float16
28
+
29
+ The following `bitsandbytes` quantization config was used during training:
30
+ - load_in_8bit: False
31
+ - load_in_4bit: True
32
+ - llm_int8_threshold: 6.0
33
+ - llm_int8_skip_modules: None
34
+ - llm_int8_enable_fp32_cpu_offload: False
35
+ - llm_int8_has_fp16_weight: False
36
+ - bnb_4bit_quant_type: nf4
37
+ - bnb_4bit_use_double_quant: False
38
+ - bnb_4bit_compute_dtype: float16
39
+
40
+ The following `bitsandbytes` quantization config was used during training:
41
+ - load_in_8bit: False
42
+ - load_in_4bit: True
43
+ - llm_int8_threshold: 6.0
44
+ - llm_int8_skip_modules: None
45
+ - llm_int8_enable_fp32_cpu_offload: False
46
+ - llm_int8_has_fp16_weight: False
47
+ - bnb_4bit_quant_type: nf4
48
+ - bnb_4bit_use_double_quant: False
49
+ - bnb_4bit_compute_dtype: float16
50
+
51
+ The following `bitsandbytes` quantization config was used during training:
52
+ - load_in_8bit: False
53
+ - load_in_4bit: True
54
+ - llm_int8_threshold: 6.0
55
+ - llm_int8_skip_modules: None
56
+ - llm_int8_enable_fp32_cpu_offload: False
57
+ - llm_int8_has_fp16_weight: False
58
+ - bnb_4bit_quant_type: nf4
59
+ - bnb_4bit_use_double_quant: False
60
+ - bnb_4bit_compute_dtype: float16
61
+
62
+ The following `bitsandbytes` quantization config was used during training:
63
+ - load_in_8bit: False
64
+ - load_in_4bit: True
65
+ - llm_int8_threshold: 6.0
66
+ - llm_int8_skip_modules: None
67
+ - llm_int8_enable_fp32_cpu_offload: False
68
+ - llm_int8_has_fp16_weight: False
69
+ - bnb_4bit_quant_type: nf4
70
+ - bnb_4bit_use_double_quant: False
71
+ - bnb_4bit_compute_dtype: float16
72
+
73
+ The following `bitsandbytes` quantization config was used during training:
74
+ - load_in_8bit: False
75
+ - load_in_4bit: True
76
+ - llm_int8_threshold: 6.0
77
+ - llm_int8_skip_modules: None
78
+ - llm_int8_enable_fp32_cpu_offload: False
79
+ - llm_int8_has_fp16_weight: False
80
+ - bnb_4bit_quant_type: nf4
81
+ - bnb_4bit_use_double_quant: False
82
+ - bnb_4bit_compute_dtype: float16
83
+
84
+ The following `bitsandbytes` quantization config was used during training:
85
+ - load_in_8bit: False
86
+ - load_in_4bit: True
87
+ - llm_int8_threshold: 6.0
88
+ - llm_int8_skip_modules: None
89
+ - llm_int8_enable_fp32_cpu_offload: False
90
+ - llm_int8_has_fp16_weight: False
91
+ - bnb_4bit_quant_type: nf4
92
+ - bnb_4bit_use_double_quant: False
93
+ - bnb_4bit_compute_dtype: float16
94
+
95
+ The following `bitsandbytes` quantization config was used during training:
96
+ - load_in_8bit: False
97
+ - load_in_4bit: True
98
+ - llm_int8_threshold: 6.0
99
+ - llm_int8_skip_modules: None
100
+ - llm_int8_enable_fp32_cpu_offload: False
101
+ - llm_int8_has_fp16_weight: False
102
+ - bnb_4bit_quant_type: nf4
103
+ - bnb_4bit_use_double_quant: False
104
+ - bnb_4bit_compute_dtype: float16
105
+
106
+ The following `bitsandbytes` quantization config was used during training:
107
+ - load_in_8bit: False
108
+ - load_in_4bit: True
109
+ - llm_int8_threshold: 6.0
110
+ - llm_int8_skip_modules: None
111
+ - llm_int8_enable_fp32_cpu_offload: False
112
+ - llm_int8_has_fp16_weight: False
113
+ - bnb_4bit_quant_type: nf4
114
+ - bnb_4bit_use_double_quant: False
115
+ - bnb_4bit_compute_dtype: float16
116
+
117
+ The following `bitsandbytes` quantization config was used during training:
118
+ - load_in_8bit: False
119
+ - load_in_4bit: True
120
+ - llm_int8_threshold: 6.0
121
+ - llm_int8_skip_modules: None
122
+ - llm_int8_enable_fp32_cpu_offload: False
123
+ - llm_int8_has_fp16_weight: False
124
+ - bnb_4bit_quant_type: nf4
125
+ - bnb_4bit_use_double_quant: False
126
+ - bnb_4bit_compute_dtype: float16
127
+
128
+ The following `bitsandbytes` quantization config was used during training:
129
+ - load_in_8bit: False
130
+ - load_in_4bit: True
131
+ - llm_int8_threshold: 6.0
132
+ - llm_int8_skip_modules: None
133
+ - llm_int8_enable_fp32_cpu_offload: False
134
+ - llm_int8_has_fp16_weight: False
135
+ - bnb_4bit_quant_type: nf4
136
+ - bnb_4bit_use_double_quant: False
137
+ - bnb_4bit_compute_dtype: float16
138
+
139
+ The following `bitsandbytes` quantization config was used during training:
140
+ - load_in_8bit: False
141
+ - load_in_4bit: True
142
+ - llm_int8_threshold: 6.0
143
+ - llm_int8_skip_modules: None
144
+ - llm_int8_enable_fp32_cpu_offload: False
145
+ - llm_int8_has_fp16_weight: False
146
+ - bnb_4bit_quant_type: nf4
147
+ - bnb_4bit_use_double_quant: False
148
+ - bnb_4bit_compute_dtype: float16
149
+
150
+ The following `bitsandbytes` quantization config was used during training:
151
+ - load_in_8bit: False
152
+ - load_in_4bit: True
153
+ - llm_int8_threshold: 6.0
154
+ - llm_int8_skip_modules: None
155
+ - llm_int8_enable_fp32_cpu_offload: False
156
+ - llm_int8_has_fp16_weight: False
157
+ - bnb_4bit_quant_type: nf4
158
+ - bnb_4bit_use_double_quant: False
159
+ - bnb_4bit_compute_dtype: float16
160
+
161
+ The following `bitsandbytes` quantization config was used during training:
162
+ - load_in_8bit: False
163
+ - load_in_4bit: True
164
+ - llm_int8_threshold: 6.0
165
+ - llm_int8_skip_modules: None
166
+ - llm_int8_enable_fp32_cpu_offload: False
167
+ - llm_int8_has_fp16_weight: False
168
+ - bnb_4bit_quant_type: nf4
169
+ - bnb_4bit_use_double_quant: False
170
+ - bnb_4bit_compute_dtype: float16
171
+
172
+ The following `bitsandbytes` quantization config was used during training:
173
+ - load_in_8bit: False
174
+ - load_in_4bit: True
175
+ - llm_int8_threshold: 6.0
176
+ - llm_int8_skip_modules: None
177
+ - llm_int8_enable_fp32_cpu_offload: False
178
+ - llm_int8_has_fp16_weight: False
179
+ - bnb_4bit_quant_type: nf4
180
+ - bnb_4bit_use_double_quant: False
181
+ - bnb_4bit_compute_dtype: float16
182
+
183
+ The following `bitsandbytes` quantization config was used during training:
184
+ - load_in_8bit: False
185
+ - load_in_4bit: True
186
+ - llm_int8_threshold: 6.0
187
+ - llm_int8_skip_modules: None
188
+ - llm_int8_enable_fp32_cpu_offload: False
189
+ - llm_int8_has_fp16_weight: False
190
+ - bnb_4bit_quant_type: nf4
191
+ - bnb_4bit_use_double_quant: False
192
+ - bnb_4bit_compute_dtype: float16
193
+
194
+ The following `bitsandbytes` quantization config was used during training:
195
+ - load_in_8bit: False
196
+ - load_in_4bit: True
197
+ - llm_int8_threshold: 6.0
198
+ - llm_int8_skip_modules: None
199
+ - llm_int8_enable_fp32_cpu_offload: False
200
+ - llm_int8_has_fp16_weight: False
201
+ - bnb_4bit_quant_type: nf4
202
+ - bnb_4bit_use_double_quant: False
203
+ - bnb_4bit_compute_dtype: float16
204
+
205
+ The following `bitsandbytes` quantization config was used during training:
206
+ - load_in_8bit: False
207
+ - load_in_4bit: True
208
+ - llm_int8_threshold: 6.0
209
+ - llm_int8_skip_modules: None
210
+ - llm_int8_enable_fp32_cpu_offload: False
211
+ - llm_int8_has_fp16_weight: False
212
+ - bnb_4bit_quant_type: nf4
213
+ - bnb_4bit_use_double_quant: False
214
+ - bnb_4bit_compute_dtype: float16
215
+
216
+ The following `bitsandbytes` quantization config was used during training:
217
+ - load_in_8bit: False
218
+ - load_in_4bit: True
219
+ - llm_int8_threshold: 6.0
220
+ - llm_int8_skip_modules: None
221
+ - llm_int8_enable_fp32_cpu_offload: False
222
+ - llm_int8_has_fp16_weight: False
223
+ - bnb_4bit_quant_type: nf4
224
+ - bnb_4bit_use_double_quant: False
225
+ - bnb_4bit_compute_dtype: float16
226
+
227
+ The following `bitsandbytes` quantization config was used during training:
228
+ - load_in_8bit: False
229
+ - load_in_4bit: True
230
+ - llm_int8_threshold: 6.0
231
+ - llm_int8_skip_modules: None
232
+ - llm_int8_enable_fp32_cpu_offload: False
233
+ - llm_int8_has_fp16_weight: False
234
+ - bnb_4bit_quant_type: nf4
235
+ - bnb_4bit_use_double_quant: False
236
+ - bnb_4bit_compute_dtype: float16
237
+
238
+ The following `bitsandbytes` quantization config was used during training:
239
+ - load_in_8bit: False
240
+ - load_in_4bit: True
241
+ - llm_int8_threshold: 6.0
242
+ - llm_int8_skip_modules: None
243
+ - llm_int8_enable_fp32_cpu_offload: False
244
+ - llm_int8_has_fp16_weight: False
245
+ - bnb_4bit_quant_type: nf4
246
+ - bnb_4bit_use_double_quant: False
247
+ - bnb_4bit_compute_dtype: float16
248
+ ### Framework versions
249
+
250
+ - PEFT 0.4.0
251
+ - PEFT 0.4.0
252
+ - PEFT 0.4.0
253
+ - PEFT 0.4.0
254
+ - PEFT 0.4.0
255
+ - PEFT 0.4.0
256
+ - PEFT 0.4.0
257
+ - PEFT 0.4.0
258
+ - PEFT 0.4.0
259
+ - PEFT 0.4.0
260
+ - PEFT 0.4.0
261
+ - PEFT 0.4.0
262
+ - PEFT 0.4.0
263
+ - PEFT 0.4.0
264
+ - PEFT 0.4.0
265
+ - PEFT 0.4.0
266
+ - PEFT 0.4.0
267
+ - PEFT 0.4.0
268
+ - PEFT 0.4.0
269
+ - PEFT 0.4.0
270
+ - PEFT 0.4.0
271
+
272
+ - PEFT 0.4.0
adapter_config (1).json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_mapping": null,
3
+ "base_model_name_or_path": "NousResearch/Llama-2-7b-hf",
4
+ "bias": "none",
5
+ "fan_in_fan_out": false,
6
+ "inference_mode": true,
7
+ "init_lora_weights": true,
8
+ "layers_pattern": null,
9
+ "layers_to_transform": null,
10
+ "lora_alpha": 16,
11
+ "lora_dropout": 0.1,
12
+ "modules_to_save": null,
13
+ "peft_type": "LORA",
14
+ "r": 64,
15
+ "revision": null,
16
+ "target_modules": [
17
+ "q_proj",
18
+ "v_proj"
19
+ ],
20
+ "task_type": "CAUSAL_LM"
21
+ }
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "[PAD]": 32000
3
+ }
events.out.tfevents.1722267239.80c456c5842f.227.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ca4f74b3b549bab3289542aacef46b49070444193008ee98724376f1b70d633
3
+ size 4870
events.out.tfevents.1722267421.80c456c5842f.227.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1255641916b7e3cd0ebbb068dc2c6f483fbf3bfda4be2965ffac367a9b3999e3
3
+ size 4870
events.out.tfevents.1722267452.80c456c5842f.227.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:330268798579818e8857346e0fffd88ebd75e1a4126820fea2dae404f903a021
3
+ size 4870
events.out.tfevents.1722267484.80c456c5842f.227.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:755384a204abf027f11865b0c3929698a6410b4b01db5b19c0eba99e667dea82
3
+ size 4870
events.out.tfevents.1722267518.80c456c5842f.227.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0276d336a75e3bd1a64ba38658819755f68e13ddee48ef07499b7387a6d1d161
3
+ size 4870
events.out.tfevents.1722267551.80c456c5842f.227.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3251b8fb5490bdc05da3175f211c309640aa91ef9c5ef6bfdbfb89fd31e98366
3
+ size 4870
events.out.tfevents.1722267584.80c456c5842f.227.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3566efdef95ea5044f7fbab573241dc224a10a52dbbcb3a16004d48b5c9846e
3
+ size 4870
events.out.tfevents.1722267620.80c456c5842f.227.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e29793623dc40b74d749e1c462e9bf52987a4f37fbd2000b3f2513f05777f483
3
+ size 4870
events.out.tfevents.1722267654.80c456c5842f.227.8 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f019f8b7540ed35252dcf042a366d0e99db509ddb672909e87073a908e117c1
3
+ size 4870
events.out.tfevents.1722267690.80c456c5842f.227.9 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a32e0d06e654b8c24cc8b38aa0b4a99d1c1bfdc6ed38e71b3fc016a93da4f24
3
+ size 4870
events.out.tfevents.1722267724.80c456c5842f.227.10 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4480edc8726627fa108f0e4e3439479b62b15e1864f6f481c97475d271e11e5d
3
+ size 4870
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35eef56506369582ae2d17896acf38810c628af294bd5a59628c5a37bee5b18c
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e93866edad3fbdd47247cb07511e76176c859f76e1587ddf720e22782b6ae462
3
+ size 1064
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "</s>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": true,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
tokenizer_config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "__type": "AddedToken",
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": true,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ "clean_up_tokenization_spaces": false,
11
+ "eos_token": {
12
+ "__type": "AddedToken",
13
+ "content": "</s>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false
18
+ },
19
+ "legacy": false,
20
+ "model_max_length": 1000000000000000019884624838656,
21
+ "pad_token": null,
22
+ "sp_model_kwargs": {},
23
+ "tokenizer_class": "LlamaTokenizer",
24
+ "unk_token": {
25
+ "__type": "AddedToken",
26
+ "content": "<unk>",
27
+ "lstrip": false,
28
+ "normalized": true,
29
+ "rstrip": false,
30
+ "single_word": false
31
+ }
32
+ }
trainer_state.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.8928571428571429,
5
+ "global_step": 25,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.89,
12
+ "learning_rate": 0.0002,
13
+ "loss": 0.2144,
14
+ "step": 25
15
+ }
16
+ ],
17
+ "max_steps": 28,
18
+ "num_train_epochs": 1,
19
+ "total_flos": 99800115118080.0,
20
+ "trial_name": null,
21
+ "trial_params": null
22
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a7d61465862e376be269103c031e3985fe834c7fbe2e5b50fdcd4088c928d69
3
+ size 4408