Hugging Face's logo

jayantdocplix
/
falcon_model_finetuned

PEFT
Model card Files Community
1
jayantdocplix commited on
Commit
3e5f6b0
•
1 Parent(s): 76b2faf

Upload 11 files

Browse files
Files changed (11) hide show
  1. README.md +32 -0
  2. adapter_config.json +22 -0
  3. adapter_model.bin +3 -0
  4. optimizer.pt +3 -0
  5. rng_state.pth +3 -0
  6. scheduler.pt +3 -0
  7. special_tokens_map.json +17 -0
  8. tokenizer.json +0 -0
  9. tokenizer_config.json +7 -0
  10. trainer_state.json +316 -0
  11. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ ### Framework versions
29
+
30
+ - PEFT 0.4.0.dev0
31
+
32
+ - PEFT 0.4.0.dev0
adapter_config.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "base_model_name_or_path": "ybelkada/falcon-7b-sharded-bf16",
3
+ "bias": "none",
4
+ "fan_in_fan_out": false,
5
+ "inference_mode": true,
6
+ "init_lora_weights": true,
7
+ "layers_pattern": null,
8
+ "layers_to_transform": null,
9
+ "lora_alpha": 16,
10
+ "lora_dropout": 0.1,
11
+ "modules_to_save": null,
12
+ "peft_type": "LORA",
13
+ "r": 64,
14
+ "revision": null,
15
+ "target_modules": [
16
+ "query_key_value",
17
+ "dense",
18
+ "dense_h_to_4h",
19
+ "dense_4h_to_h"
20
+ ],
21
+ "task_type": "CAUSAL_LM"
22
+ }
adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2054b8a70f39f1311d58300ac2f9ff983723d88464d3e6c65098f7c9353cf782
3
+ size 522284877
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c48312661d3c907412387b4da9b5dcb860f1b8d364f67ff8686ec114f338b08
3
+ size 1044539909
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58e2e1749611406923859c3ac550e806510c13fbc51536779fc8dd16b1beca83
3
+ size 14575
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5efc416a6883409dd7ab6f5c779e107c7c2baa7af6e12ed9fbd9dd73b8b20784
3
+ size 627
special_tokens_map.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ ">>TITLE<<",
4
+ ">>ABSTRACT<<",
5
+ ">>INTRODUCTION<<",
6
+ ">>SUMMARY<<",
7
+ ">>COMMENT<<",
8
+ ">>ANSWER<<",
9
+ ">>QUESTION<<",
10
+ ">>DOMAIN<<",
11
+ ">>PREFIX<<",
12
+ ">>SUFFIX<<",
13
+ ">>MIDDLE<<"
14
+ ],
15
+ "eos_token": "<|endoftext|>",
16
+ "pad_token": "<|endoftext|>"
17
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "clean_up_tokenization_spaces": true,
4
+ "eos_token": "<|endoftext|>",
5
+ "model_max_length": 2048,
6
+ "tokenizer_class": "PreTrainedTokenizerFast"
7
+ }
trainer_state.json ADDED
@@ -0,0 +1,316 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.8123476848090982,
5
+ "global_step": 500,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.02,
12
+ "learning_rate": 0.0002,
13
+ "loss": 1.3234,
14
+ "step": 10
15
+ },
16
+ {
17
+ "epoch": 0.03,
18
+ "learning_rate": 0.0002,
19
+ "loss": 1.3389,
20
+ "step": 20
21
+ },
22
+ {
23
+ "epoch": 0.05,
24
+ "learning_rate": 0.0002,
25
+ "loss": 1.3999,
26
+ "step": 30
27
+ },
28
+ {
29
+ "epoch": 0.06,
30
+ "learning_rate": 0.0002,
31
+ "loss": 1.6548,
32
+ "step": 40
33
+ },
34
+ {
35
+ "epoch": 0.08,
36
+ "learning_rate": 0.0002,
37
+ "loss": 1.8545,
38
+ "step": 50
39
+ },
40
+ {
41
+ "epoch": 0.1,
42
+ "learning_rate": 0.0002,
43
+ "loss": 1.2073,
44
+ "step": 60
45
+ },
46
+ {
47
+ "epoch": 0.11,
48
+ "learning_rate": 0.0002,
49
+ "loss": 1.2975,
50
+ "step": 70
51
+ },
52
+ {
53
+ "epoch": 0.13,
54
+ "learning_rate": 0.0002,
55
+ "loss": 1.3666,
56
+ "step": 80
57
+ },
58
+ {
59
+ "epoch": 0.15,
60
+ "learning_rate": 0.0002,
61
+ "loss": 1.5847,
62
+ "step": 90
63
+ },
64
+ {
65
+ "epoch": 0.16,
66
+ "learning_rate": 0.0002,
67
+ "loss": 1.787,
68
+ "step": 100
69
+ },
70
+ {
71
+ "epoch": 0.18,
72
+ "learning_rate": 0.0002,
73
+ "loss": 1.1914,
74
+ "step": 110
75
+ },
76
+ {
77
+ "epoch": 0.19,
78
+ "learning_rate": 0.0002,
79
+ "loss": 1.2603,
80
+ "step": 120
81
+ },
82
+ {
83
+ "epoch": 0.21,
84
+ "learning_rate": 0.0002,
85
+ "loss": 1.3678,
86
+ "step": 130
87
+ },
88
+ {
89
+ "epoch": 0.23,
90
+ "learning_rate": 0.0002,
91
+ "loss": 1.4669,
92
+ "step": 140
93
+ },
94
+ {
95
+ "epoch": 0.24,
96
+ "learning_rate": 0.0002,
97
+ "loss": 1.8138,
98
+ "step": 150
99
+ },
100
+ {
101
+ "epoch": 0.26,
102
+ "learning_rate": 0.0002,
103
+ "loss": 1.209,
104
+ "step": 160
105
+ },
106
+ {
107
+ "epoch": 0.28,
108
+ "learning_rate": 0.0002,
109
+ "loss": 1.219,
110
+ "step": 170
111
+ },
112
+ {
113
+ "epoch": 0.29,
114
+ "learning_rate": 0.0002,
115
+ "loss": 1.2781,
116
+ "step": 180
117
+ },
118
+ {
119
+ "epoch": 0.31,
120
+ "learning_rate": 0.0002,
121
+ "loss": 1.5252,
122
+ "step": 190
123
+ },
124
+ {
125
+ "epoch": 0.32,
126
+ "learning_rate": 0.0002,
127
+ "loss": 1.8084,
128
+ "step": 200
129
+ },
130
+ {
131
+ "epoch": 0.34,
132
+ "learning_rate": 0.0002,
133
+ "loss": 1.1805,
134
+ "step": 210
135
+ },
136
+ {
137
+ "epoch": 0.36,
138
+ "learning_rate": 0.0002,
139
+ "loss": 1.2208,
140
+ "step": 220
141
+ },
142
+ {
143
+ "epoch": 0.37,
144
+ "learning_rate": 0.0002,
145
+ "loss": 1.3424,
146
+ "step": 230
147
+ },
148
+ {
149
+ "epoch": 0.39,
150
+ "learning_rate": 0.0002,
151
+ "loss": 1.5527,
152
+ "step": 240
153
+ },
154
+ {
155
+ "epoch": 0.41,
156
+ "learning_rate": 0.0002,
157
+ "loss": 1.7663,
158
+ "step": 250
159
+ },
160
+ {
161
+ "epoch": 0.42,
162
+ "learning_rate": 0.0002,
163
+ "loss": 1.2059,
164
+ "step": 260
165
+ },
166
+ {
167
+ "epoch": 0.44,
168
+ "learning_rate": 0.0002,
169
+ "loss": 1.2285,
170
+ "step": 270
171
+ },
172
+ {
173
+ "epoch": 0.45,
174
+ "learning_rate": 0.0002,
175
+ "loss": 1.3103,
176
+ "step": 280
177
+ },
178
+ {
179
+ "epoch": 0.47,
180
+ "learning_rate": 0.0002,
181
+ "loss": 1.5495,
182
+ "step": 290
183
+ },
184
+ {
185
+ "epoch": 0.49,
186
+ "learning_rate": 0.0002,
187
+ "loss": 1.7774,
188
+ "step": 300
189
+ },
190
+ {
191
+ "epoch": 0.5,
192
+ "learning_rate": 0.0002,
193
+ "loss": 1.205,
194
+ "step": 310
195
+ },
196
+ {
197
+ "epoch": 0.52,
198
+ "learning_rate": 0.0002,
199
+ "loss": 1.1946,
200
+ "step": 320
201
+ },
202
+ {
203
+ "epoch": 0.54,
204
+ "learning_rate": 0.0002,
205
+ "loss": 1.2776,
206
+ "step": 330
207
+ },
208
+ {
209
+ "epoch": 0.55,
210
+ "learning_rate": 0.0002,
211
+ "loss": 1.5044,
212
+ "step": 340
213
+ },
214
+ {
215
+ "epoch": 0.57,
216
+ "learning_rate": 0.0002,
217
+ "loss": 1.674,
218
+ "step": 350
219
+ },
220
+ {
221
+ "epoch": 0.58,
222
+ "learning_rate": 0.0002,
223
+ "loss": 1.1901,
224
+ "step": 360
225
+ },
226
+ {
227
+ "epoch": 0.6,
228
+ "learning_rate": 0.0002,
229
+ "loss": 1.2326,
230
+ "step": 370
231
+ },
232
+ {
233
+ "epoch": 0.62,
234
+ "learning_rate": 0.0002,
235
+ "loss": 1.3597,
236
+ "step": 380
237
+ },
238
+ {
239
+ "epoch": 0.63,
240
+ "learning_rate": 0.0002,
241
+ "loss": 1.5719,
242
+ "step": 390
243
+ },
244
+ {
245
+ "epoch": 0.65,
246
+ "learning_rate": 0.0002,
247
+ "loss": 1.727,
248
+ "step": 400
249
+ },
250
+ {
251
+ "epoch": 0.67,
252
+ "learning_rate": 0.0002,
253
+ "loss": 1.1642,
254
+ "step": 410
255
+ },
256
+ {
257
+ "epoch": 0.68,
258
+ "learning_rate": 0.0002,
259
+ "loss": 1.2354,
260
+ "step": 420
261
+ },
262
+ {
263
+ "epoch": 0.7,
264
+ "learning_rate": 0.0002,
265
+ "loss": 1.3189,
266
+ "step": 430
267
+ },
268
+ {
269
+ "epoch": 0.71,
270
+ "learning_rate": 0.0002,
271
+ "loss": 1.5433,
272
+ "step": 440
273
+ },
274
+ {
275
+ "epoch": 0.73,
276
+ "learning_rate": 0.0002,
277
+ "loss": 1.8169,
278
+ "step": 450
279
+ },
280
+ {
281
+ "epoch": 0.75,
282
+ "learning_rate": 0.0002,
283
+ "loss": 1.1461,
284
+ "step": 460
285
+ },
286
+ {
287
+ "epoch": 0.76,
288
+ "learning_rate": 0.0002,
289
+ "loss": 1.2557,
290
+ "step": 470
291
+ },
292
+ {
293
+ "epoch": 0.78,
294
+ "learning_rate": 0.0002,
295
+ "loss": 1.3328,
296
+ "step": 480
297
+ },
298
+ {
299
+ "epoch": 0.8,
300
+ "learning_rate": 0.0002,
301
+ "loss": 1.6532,
302
+ "step": 490
303
+ },
304
+ {
305
+ "epoch": 0.81,
306
+ "learning_rate": 0.0002,
307
+ "loss": 1.7721,
308
+ "step": 500
309
+ }
310
+ ],
311
+ "max_steps": 500,
312
+ "num_train_epochs": 1,
313
+ "total_flos": 5.531824689009562e+16,
314
+ "trial_name": null,
315
+ "trial_params": null
316
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00dd95671ba3e81fb44880e9a3d3ceee276294302e82002a2ade3eb27e6f042c
3
+ size 3963