Hugging Face's logo

hoang14
/
test_mistral_tool_1536ctx

PEFT
Model card Files
xet
 Community
hoang14 commited on
Commit
4102053
·
1 Parent(s): f307e5a

Upload 12 files

Browse files
Files changed (12) hide show
  1. README.md +21 -0
  2. adapter_config.json +21 -0
  3. adapter_model.bin +3 -0
  4. added_tokens.json +5 -0
  5. optimizer.pt +3 -0
  6. rng_state.pth +3 -0
  7. scheduler.pt +3 -0
  8. special_tokens_map.json +11 -0
  9. tokenizer.model +3 -0
  10. tokenizer_config.json +48 -0
  11. trainer_state.json +289 -0
  12. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ ---
4
+ ## Training procedure
5
+
6
+
7
+ The following `bitsandbytes` quantization config was used during training:
8
+ - quant_method: bitsandbytes
9
+ - load_in_8bit: False
10
+ - load_in_4bit: True
11
+ - llm_int8_threshold: 6.0
12
+ - llm_int8_skip_modules: None
13
+ - llm_int8_enable_fp32_cpu_offload: False
14
+ - llm_int8_has_fp16_weight: False
15
+ - bnb_4bit_quant_type: nf4
16
+ - bnb_4bit_use_double_quant: True
17
+ - bnb_4bit_compute_dtype: float32
18
+ ### Framework versions
19
+
20
+
21
+ - PEFT 0.5.0
adapter_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_mapping": null,
3
+ "base_model_name_or_path": "mistralai/Mistral-7B-v0.1",
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": 0.01,
12
+ "modules_to_save": null,
13
+ "peft_type": "LORA",
14
+ "r": 32,
15
+ "revision": null,
16
+ "target_modules": [
17
+ "q_proj",
18
+ "v_proj"
19
+ ],
20
+ "task_type": "CAUSAL_LM"
21
+ }
adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7967d87893846d4170cc184288721c3a2aadba1eb8af70cda83e167ebf6d1fd8
3
+ size 54571917
added_tokens.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "</s>": 2,
3
+ "<s>": 1,
4
+ "<unk>": 0
5
+ }
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f5e4b4b7bb7b1ae5b63c2a9603f514441f4eec8bb7b24e768d7dd6fb7b541b5
3
+ size 109159493
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f000d7d1a0af31f1ef5d27eacb194214ed821a2b75dc5e584ec7fe69cec626d7
3
+ size 14575
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a950982fca6b7d8b1babd20b831d6b2d2ad0d30b0aef284fa43f2dffd9b9c97
3
+ size 627
special_tokens_map.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<unk>",
4
+ "<s>",
5
+ "</s>"
6
+ ],
7
+ "bos_token": "<s>",
8
+ "eos_token": "</s>",
9
+ "pad_token": "<unk>",
10
+ "unk_token": "<unk>"
11
+ }
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
tokenizer_config.json ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ }
29
+ },
30
+ "additional_special_tokens": [
31
+ "<unk>",
32
+ "<s>",
33
+ "</s>"
34
+ ],
35
+ "bos_token": "<s>",
36
+ "clean_up_tokenization_spaces": false,
37
+ "eos_token": "</s>",
38
+ "legacy": true,
39
+ "model_max_length": 1600,
40
+ "pad_token": "<unk>",
41
+ "padding_side": "right",
42
+ "sp_model_kwargs": {},
43
+ "spaces_between_special_tokens": false,
44
+ "tokenizer_class": "LlamaTokenizer",
45
+ "tokenizer_file": "/root/.cache/huggingface/hub/models--mistralai--Mistral-7B-v0.1/snapshots/5e9c98b96d071dce59368012254c55b0ec6f8658/tokenizer.json",
46
+ "unk_token": "<unk>",
47
+ "use_default_system_prompt": true
48
+ }
trainer_state.json ADDED
@@ -0,0 +1,289 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.170731707317073,
5
+ "eval_steps": 500,
6
+ "global_step": 900,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.03,
13
+ "learning_rate": 8e-05,
14
+ "loss": 0.5555,
15
+ "step": 20
16
+ },
17
+ {
18
+ "epoch": 0.05,
19
+ "learning_rate": 8e-05,
20
+ "loss": 0.4856,
21
+ "step": 40
22
+ },
23
+ {
24
+ "epoch": 0.08,
25
+ "learning_rate": 8e-05,
26
+ "loss": 0.427,
27
+ "step": 60
28
+ },
29
+ {
30
+ "epoch": 0.1,
31
+ "learning_rate": 8e-05,
32
+ "loss": 0.4319,
33
+ "step": 80
34
+ },
35
+ {
36
+ "epoch": 0.13,
37
+ "learning_rate": 8e-05,
38
+ "loss": 0.4089,
39
+ "step": 100
40
+ },
41
+ {
42
+ "epoch": 0.16,
43
+ "learning_rate": 8e-05,
44
+ "loss": 0.3895,
45
+ "step": 120
46
+ },
47
+ {
48
+ "epoch": 0.18,
49
+ "learning_rate": 8e-05,
50
+ "loss": 0.3859,
51
+ "step": 140
52
+ },
53
+ {
54
+ "epoch": 0.21,
55
+ "learning_rate": 8e-05,
56
+ "loss": 0.3714,
57
+ "step": 160
58
+ },
59
+ {
60
+ "epoch": 0.23,
61
+ "learning_rate": 8e-05,
62
+ "loss": 0.3563,
63
+ "step": 180
64
+ },
65
+ {
66
+ "epoch": 0.26,
67
+ "learning_rate": 8e-05,
68
+ "loss": 0.3631,
69
+ "step": 200
70
+ },
71
+ {
72
+ "epoch": 0.29,
73
+ "learning_rate": 8e-05,
74
+ "loss": 0.3691,
75
+ "step": 220
76
+ },
77
+ {
78
+ "epoch": 0.31,
79
+ "learning_rate": 8e-05,
80
+ "loss": 0.3657,
81
+ "step": 240
82
+ },
83
+ {
84
+ "epoch": 0.34,
85
+ "learning_rate": 8e-05,
86
+ "loss": 0.3652,
87
+ "step": 260
88
+ },
89
+ {
90
+ "epoch": 0.36,
91
+ "learning_rate": 8e-05,
92
+ "loss": 0.3474,
93
+ "step": 280
94
+ },
95
+ {
96
+ "epoch": 0.39,
97
+ "learning_rate": 8e-05,
98
+ "loss": 0.3553,
99
+ "step": 300
100
+ },
101
+ {
102
+ "epoch": 0.42,
103
+ "learning_rate": 8e-05,
104
+ "loss": 0.3438,
105
+ "step": 320
106
+ },
107
+ {
108
+ "epoch": 0.44,
109
+ "learning_rate": 8e-05,
110
+ "loss": 0.3713,
111
+ "step": 340
112
+ },
113
+ {
114
+ "epoch": 0.47,
115
+ "learning_rate": 8e-05,
116
+ "loss": 0.3454,
117
+ "step": 360
118
+ },
119
+ {
120
+ "epoch": 0.49,
121
+ "learning_rate": 8e-05,
122
+ "loss": 0.3594,
123
+ "step": 380
124
+ },
125
+ {
126
+ "epoch": 0.52,
127
+ "learning_rate": 8e-05,
128
+ "loss": 0.3613,
129
+ "step": 400
130
+ },
131
+ {
132
+ "epoch": 0.55,
133
+ "learning_rate": 8e-05,
134
+ "loss": 0.3329,
135
+ "step": 420
136
+ },
137
+ {
138
+ "epoch": 0.57,
139
+ "learning_rate": 8e-05,
140
+ "loss": 0.3466,
141
+ "step": 440
142
+ },
143
+ {
144
+ "epoch": 0.6,
145
+ "learning_rate": 8e-05,
146
+ "loss": 0.3408,
147
+ "step": 460
148
+ },
149
+ {
150
+ "epoch": 0.62,
151
+ "learning_rate": 8e-05,
152
+ "loss": 0.3393,
153
+ "step": 480
154
+ },
155
+ {
156
+ "epoch": 0.65,
157
+ "learning_rate": 8e-05,
158
+ "loss": 0.338,
159
+ "step": 500
160
+ },
161
+ {
162
+ "epoch": 0.68,
163
+ "learning_rate": 8e-05,
164
+ "loss": 0.328,
165
+ "step": 520
166
+ },
167
+ {
168
+ "epoch": 0.7,
169
+ "learning_rate": 8e-05,
170
+ "loss": 0.3292,
171
+ "step": 540
172
+ },
173
+ {
174
+ "epoch": 0.73,
175
+ "learning_rate": 8e-05,
176
+ "loss": 0.3321,
177
+ "step": 560
178
+ },
179
+ {
180
+ "epoch": 0.75,
181
+ "learning_rate": 8e-05,
182
+ "loss": 0.3296,
183
+ "step": 580
184
+ },
185
+ {
186
+ "epoch": 0.78,
187
+ "learning_rate": 8e-05,
188
+ "loss": 0.3328,
189
+ "step": 600
190
+ },
191
+ {
192
+ "epoch": 0.81,
193
+ "learning_rate": 8e-05,
194
+ "loss": 0.3197,
195
+ "step": 620
196
+ },
197
+ {
198
+ "epoch": 0.83,
199
+ "learning_rate": 8e-05,
200
+ "loss": 0.3401,
201
+ "step": 640
202
+ },
203
+ {
204
+ "epoch": 0.86,
205
+ "learning_rate": 8e-05,
206
+ "loss": 0.3211,
207
+ "step": 660
208
+ },
209
+ {
210
+ "epoch": 0.88,
211
+ "learning_rate": 8e-05,
212
+ "loss": 0.3383,
213
+ "step": 680
214
+ },
215
+ {
216
+ "epoch": 0.91,
217
+ "learning_rate": 8e-05,
218
+ "loss": 0.3053,
219
+ "step": 700
220
+ },
221
+ {
222
+ "epoch": 0.94,
223
+ "learning_rate": 8e-05,
224
+ "loss": 0.3252,
225
+ "step": 720
226
+ },
227
+ {
228
+ "epoch": 0.96,
229
+ "learning_rate": 8e-05,
230
+ "loss": 0.3228,
231
+ "step": 740
232
+ },
233
+ {
234
+ "epoch": 0.99,
235
+ "learning_rate": 8e-05,
236
+ "loss": 0.333,
237
+ "step": 760
238
+ },
239
+ {
240
+ "epoch": 1.01,
241
+ "learning_rate": 8e-05,
242
+ "loss": 0.3095,
243
+ "step": 780
244
+ },
245
+ {
246
+ "epoch": 1.04,
247
+ "learning_rate": 8e-05,
248
+ "loss": 0.3179,
249
+ "step": 800
250
+ },
251
+ {
252
+ "epoch": 1.07,
253
+ "learning_rate": 8e-05,
254
+ "loss": 0.2828,
255
+ "step": 820
256
+ },
257
+ {
258
+ "epoch": 1.09,
259
+ "learning_rate": 8e-05,
260
+ "loss": 0.2855,
261
+ "step": 840
262
+ },
263
+ {
264
+ "epoch": 1.12,
265
+ "learning_rate": 8e-05,
266
+ "loss": 0.3027,
267
+ "step": 860
268
+ },
269
+ {
270
+ "epoch": 1.14,
271
+ "learning_rate": 8e-05,
272
+ "loss": 0.2984,
273
+ "step": 880
274
+ },
275
+ {
276
+ "epoch": 1.17,
277
+ "learning_rate": 8e-05,
278
+ "loss": 0.2772,
279
+ "step": 900
280
+ }
281
+ ],
282
+ "logging_steps": 20,
283
+ "max_steps": 1536,
284
+ "num_train_epochs": 2,
285
+ "save_steps": 150,
286
+ "total_flos": 2.4621551714304e+17,
287
+ "trial_name": null,
288
+ "trial_params": null
289
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50f112db9673beb21a3063d7628a0fc2882d2f71175407d35146f0fd4e600801
3
+ size 4091