Hugging Face's logo

wesley7137
/
TinyLlama-OpenHermes-MOE-DolphiCoder-Expert-v1

PEFT
llama
Model card Files
xet
Community
wesley7137 commited on
Commit
dc3b0dd
·
verified ·
1 Parent(s): d081545

Upload 11 files

Browse files
Files changed (11) hide show
  1. README.md +32 -0
  2. adapter_config.json +26 -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 +24 -0
  8. tokenizer.json +0 -0
  9. tokenizer_config.json +33 -0
  10. trainer_state.json +376 -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
31
+
32
+ - PEFT 0.4.0
adapter_config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_mapping": null,
3
+ "base_model_name_or_path": "Tensoic/TinyLlama-1.1B-2.5T-openhermes",
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
+ "k_proj",
19
+ "v_proj",
20
+ "out_proj",
21
+ "fc_in",
22
+ "fc_out",
23
+ "wte"
24
+ ],
25
+ "task_type": "CAUSAL_LM"
26
+ }
adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3ef6d5a9f5d51db7cabda2f27d19ba0c5d0c4262d0ae598933bba79c4a3c5ea
3
+ size 49068762
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3bedbdd13c5f2ddf3c67acca8e2fd17e50b802d80251fed55c940b7d7894b0bc
3
+ size 98122618
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29e9471348f05e388cba8dae32a2a595e1f7369f6366851011a08b8c143528fb
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d77a12c6ddcb588d8eb1fffa03b3e3be8b5f25c15acdb9a618c73413f62484db
3
+ size 1064
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "</s>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
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_config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "__type": "AddedToken",
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": false,
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": false,
16
+ "rstrip": false,
17
+ "single_word": false
18
+ },
19
+ "legacy": false,
20
+ "model_max_length": 1000000000000000019884624838656,
21
+ "pad_token": null,
22
+ "padding_side": "right",
23
+ "sp_model_kwargs": {},
24
+ "tokenizer_class": "LlamaTokenizer",
25
+ "unk_token": {
26
+ "__type": "AddedToken",
27
+ "content": "<unk>",
28
+ "lstrip": false,
29
+ "normalized": false,
30
+ "rstrip": false,
31
+ "single_word": false
32
+ }
33
+ }
trainer_state.json ADDED
@@ -0,0 +1,376 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.09716599190283401,
5
+ "global_step": 300,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.0,
12
+ "learning_rate": 0.0001,
13
+ "loss": 1.6138,
14
+ "step": 5
15
+ },
16
+ {
17
+ "epoch": 0.0,
18
+ "learning_rate": 0.0001,
19
+ "loss": 1.5634,
20
+ "step": 10
21
+ },
22
+ {
23
+ "epoch": 0.0,
24
+ "learning_rate": 0.0001,
25
+ "loss": 1.5261,
26
+ "step": 15
27
+ },
28
+ {
29
+ "epoch": 0.01,
30
+ "learning_rate": 0.0001,
31
+ "loss": 1.5403,
32
+ "step": 20
33
+ },
34
+ {
35
+ "epoch": 0.01,
36
+ "learning_rate": 0.0001,
37
+ "loss": 1.5053,
38
+ "step": 25
39
+ },
40
+ {
41
+ "epoch": 0.01,
42
+ "learning_rate": 0.0001,
43
+ "loss": 1.4088,
44
+ "step": 30
45
+ },
46
+ {
47
+ "epoch": 0.01,
48
+ "learning_rate": 0.0001,
49
+ "loss": 1.3717,
50
+ "step": 35
51
+ },
52
+ {
53
+ "epoch": 0.01,
54
+ "learning_rate": 0.0001,
55
+ "loss": 1.3904,
56
+ "step": 40
57
+ },
58
+ {
59
+ "epoch": 0.01,
60
+ "learning_rate": 0.0001,
61
+ "loss": 1.3868,
62
+ "step": 45
63
+ },
64
+ {
65
+ "epoch": 0.02,
66
+ "learning_rate": 0.0001,
67
+ "loss": 1.3643,
68
+ "step": 50
69
+ },
70
+ {
71
+ "epoch": 0.02,
72
+ "learning_rate": 0.0001,
73
+ "loss": 1.2856,
74
+ "step": 55
75
+ },
76
+ {
77
+ "epoch": 0.02,
78
+ "learning_rate": 0.0001,
79
+ "loss": 1.2712,
80
+ "step": 60
81
+ },
82
+ {
83
+ "epoch": 0.02,
84
+ "learning_rate": 0.0001,
85
+ "loss": 1.1833,
86
+ "step": 65
87
+ },
88
+ {
89
+ "epoch": 0.02,
90
+ "learning_rate": 0.0001,
91
+ "loss": 1.1614,
92
+ "step": 70
93
+ },
94
+ {
95
+ "epoch": 0.02,
96
+ "learning_rate": 0.0001,
97
+ "loss": 1.095,
98
+ "step": 75
99
+ },
100
+ {
101
+ "epoch": 0.03,
102
+ "learning_rate": 0.0001,
103
+ "loss": 1.0167,
104
+ "step": 80
105
+ },
106
+ {
107
+ "epoch": 0.03,
108
+ "learning_rate": 0.0001,
109
+ "loss": 1.0207,
110
+ "step": 85
111
+ },
112
+ {
113
+ "epoch": 0.03,
114
+ "learning_rate": 0.0001,
115
+ "loss": 0.9865,
116
+ "step": 90
117
+ },
118
+ {
119
+ "epoch": 0.03,
120
+ "learning_rate": 0.0001,
121
+ "loss": 0.9444,
122
+ "step": 95
123
+ },
124
+ {
125
+ "epoch": 0.03,
126
+ "learning_rate": 0.0001,
127
+ "loss": 0.9117,
128
+ "step": 100
129
+ },
130
+ {
131
+ "epoch": 0.03,
132
+ "learning_rate": 0.0001,
133
+ "loss": 1.0384,
134
+ "step": 105
135
+ },
136
+ {
137
+ "epoch": 0.04,
138
+ "learning_rate": 0.0001,
139
+ "loss": 1.0129,
140
+ "step": 110
141
+ },
142
+ {
143
+ "epoch": 0.04,
144
+ "learning_rate": 0.0001,
145
+ "loss": 1.0047,
146
+ "step": 115
147
+ },
148
+ {
149
+ "epoch": 0.04,
150
+ "learning_rate": 0.0001,
151
+ "loss": 0.9954,
152
+ "step": 120
153
+ },
154
+ {
155
+ "epoch": 0.04,
156
+ "learning_rate": 0.0001,
157
+ "loss": 1.0027,
158
+ "step": 125
159
+ },
160
+ {
161
+ "epoch": 0.04,
162
+ "learning_rate": 0.0001,
163
+ "loss": 0.9268,
164
+ "step": 130
165
+ },
166
+ {
167
+ "epoch": 0.04,
168
+ "learning_rate": 0.0001,
169
+ "loss": 0.9031,
170
+ "step": 135
171
+ },
172
+ {
173
+ "epoch": 0.05,
174
+ "learning_rate": 0.0001,
175
+ "loss": 0.8783,
176
+ "step": 140
177
+ },
178
+ {
179
+ "epoch": 0.05,
180
+ "learning_rate": 0.0001,
181
+ "loss": 0.8719,
182
+ "step": 145
183
+ },
184
+ {
185
+ "epoch": 0.05,
186
+ "learning_rate": 0.0001,
187
+ "loss": 0.8588,
188
+ "step": 150
189
+ },
190
+ {
191
+ "epoch": 0.05,
192
+ "learning_rate": 0.0001,
193
+ "loss": 0.9952,
194
+ "step": 155
195
+ },
196
+ {
197
+ "epoch": 0.05,
198
+ "learning_rate": 0.0001,
199
+ "loss": 0.9702,
200
+ "step": 160
201
+ },
202
+ {
203
+ "epoch": 0.05,
204
+ "learning_rate": 0.0001,
205
+ "loss": 0.9692,
206
+ "step": 165
207
+ },
208
+ {
209
+ "epoch": 0.06,
210
+ "learning_rate": 0.0001,
211
+ "loss": 0.9771,
212
+ "step": 170
213
+ },
214
+ {
215
+ "epoch": 0.06,
216
+ "learning_rate": 0.0001,
217
+ "loss": 0.9919,
218
+ "step": 175
219
+ },
220
+ {
221
+ "epoch": 0.06,
222
+ "learning_rate": 0.0001,
223
+ "loss": 0.8938,
224
+ "step": 180
225
+ },
226
+ {
227
+ "epoch": 0.06,
228
+ "learning_rate": 0.0001,
229
+ "loss": 0.8574,
230
+ "step": 185
231
+ },
232
+ {
233
+ "epoch": 0.06,
234
+ "learning_rate": 0.0001,
235
+ "loss": 0.8515,
236
+ "step": 190
237
+ },
238
+ {
239
+ "epoch": 0.06,
240
+ "learning_rate": 0.0001,
241
+ "loss": 0.8253,
242
+ "step": 195
243
+ },
244
+ {
245
+ "epoch": 0.06,
246
+ "learning_rate": 0.0001,
247
+ "loss": 0.8111,
248
+ "step": 200
249
+ },
250
+ {
251
+ "epoch": 0.07,
252
+ "learning_rate": 0.0001,
253
+ "loss": 0.928,
254
+ "step": 205
255
+ },
256
+ {
257
+ "epoch": 0.07,
258
+ "learning_rate": 0.0001,
259
+ "loss": 0.9445,
260
+ "step": 210
261
+ },
262
+ {
263
+ "epoch": 0.07,
264
+ "learning_rate": 0.0001,
265
+ "loss": 0.9658,
266
+ "step": 215
267
+ },
268
+ {
269
+ "epoch": 0.07,
270
+ "learning_rate": 0.0001,
271
+ "loss": 0.9692,
272
+ "step": 220
273
+ },
274
+ {
275
+ "epoch": 0.07,
276
+ "learning_rate": 0.0001,
277
+ "loss": 0.9329,
278
+ "step": 225
279
+ },
280
+ {
281
+ "epoch": 0.07,
282
+ "learning_rate": 0.0001,
283
+ "loss": 0.8539,
284
+ "step": 230
285
+ },
286
+ {
287
+ "epoch": 0.08,
288
+ "learning_rate": 0.0001,
289
+ "loss": 0.8677,
290
+ "step": 235
291
+ },
292
+ {
293
+ "epoch": 0.08,
294
+ "learning_rate": 0.0001,
295
+ "loss": 0.8409,
296
+ "step": 240
297
+ },
298
+ {
299
+ "epoch": 0.08,
300
+ "learning_rate": 0.0001,
301
+ "loss": 0.8217,
302
+ "step": 245
303
+ },
304
+ {
305
+ "epoch": 0.08,
306
+ "learning_rate": 0.0001,
307
+ "loss": 0.7753,
308
+ "step": 250
309
+ },
310
+ {
311
+ "epoch": 0.08,
312
+ "learning_rate": 0.0001,
313
+ "loss": 0.9381,
314
+ "step": 255
315
+ },
316
+ {
317
+ "epoch": 0.08,
318
+ "learning_rate": 0.0001,
319
+ "loss": 0.9178,
320
+ "step": 260
321
+ },
322
+ {
323
+ "epoch": 0.09,
324
+ "learning_rate": 0.0001,
325
+ "loss": 0.9088,
326
+ "step": 265
327
+ },
328
+ {
329
+ "epoch": 0.09,
330
+ "learning_rate": 0.0001,
331
+ "loss": 0.9249,
332
+ "step": 270
333
+ },
334
+ {
335
+ "epoch": 0.09,
336
+ "learning_rate": 0.0001,
337
+ "loss": 0.9504,
338
+ "step": 275
339
+ },
340
+ {
341
+ "epoch": 0.09,
342
+ "learning_rate": 0.0001,
343
+ "loss": 0.8712,
344
+ "step": 280
345
+ },
346
+ {
347
+ "epoch": 0.09,
348
+ "learning_rate": 0.0001,
349
+ "loss": 0.8469,
350
+ "step": 285
351
+ },
352
+ {
353
+ "epoch": 0.09,
354
+ "learning_rate": 0.0001,
355
+ "loss": 0.7907,
356
+ "step": 290
357
+ },
358
+ {
359
+ "epoch": 0.1,
360
+ "learning_rate": 0.0001,
361
+ "loss": 0.8205,
362
+ "step": 295
363
+ },
364
+ {
365
+ "epoch": 0.1,
366
+ "learning_rate": 0.0001,
367
+ "loss": 0.7836,
368
+ "step": 300
369
+ }
370
+ ],
371
+ "max_steps": 6174,
372
+ "num_train_epochs": 2,
373
+ "total_flos": 2.2488355107618816e+16,
374
+ "trial_name": null,
375
+ "trial_params": null
376
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5fcda629a7b0880becdc7d9b4bac06c43d914bf1e3c44a77e103d9e29f06f6d
3
+ size 4536