Hugging Face's logo

megha-shroff
/
mistral-augmentation-digikey-rand

PEFT
Safetensors
trl
sft
Generated from Trainer
Model card Files Community
megha-shroff commited on
Commit
2de8e0c
•
1 Parent(s): b6f2352

End of training

Browse files
Files changed (8) hide show
  1. README.md +198 -0
  2. adapter_config.json +26 -0
  3. adapter_model.safetensors +3 -0
  4. special_tokens_map.json +24 -0
  5. tokenizer.json +0 -0
  6. tokenizer.model +3 -0
  7. tokenizer_config.json +42 -0
  8. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,198 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ library_name: peft
4
+ tags:
5
+ - trl
6
+ - sft
7
+ - generated_from_trainer
8
+ base_model: TheBloke/Mistral-7B-v0.1-GPTQ
9
+ model-index:
10
+ - name: mistral-augmentation-digikey-rand
11
+ results: []
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ # mistral-augmentation-digikey-rand
18
+
19
+ This model is a fine-tuned version of [TheBloke/Mistral-7B-v0.1-GPTQ](https://huggingface.co/TheBloke/Mistral-7B-v0.1-GPTQ) on the None dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 0.4955
22
+
23
+ ## Model description
24
+
25
+ More information needed
26
+
27
+ ## Intended uses & limitations
28
+
29
+ More information needed
30
+
31
+ ## Training and evaluation data
32
+
33
+ More information needed
34
+
35
+ ## Training procedure
36
+
37
+ ### Training hyperparameters
38
+
39
+ The following hyperparameters were used during training:
40
+ - learning_rate: 2e-05
41
+ - train_batch_size: 4
42
+ - eval_batch_size: 8
43
+ - seed: 42
44
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
+ - lr_scheduler_type: cosine
46
+ - num_epochs: 15
47
+ - mixed_precision_training: Native AMP
48
+
49
+ ### Training results
50
+
51
+ | Training Loss | Epoch | Step | Validation Loss |
52
+ |:-------------:|:-----:|:----:|:---------------:|
53
+ | 2.0496 | 0.01 | 50 | 1.1570 |
54
+ | 0.9361 | 0.03 | 100 | 0.8592 |
55
+ | 0.7691 | 0.04 | 150 | 0.7989 |
56
+ | 0.7555 | 0.06 | 200 | 0.7768 |
57
+ | 0.7213 | 0.07 | 250 | 0.7575 |
58
+ | 0.6993 | 0.09 | 300 | 0.7440 |
59
+ | 0.6905 | 0.1 | 350 | 0.7291 |
60
+ | 0.6855 | 0.12 | 400 | 0.7210 |
61
+ | 0.6732 | 0.13 | 450 | 0.7076 |
62
+ | 0.6516 | 0.15 | 500 | 0.7005 |
63
+ | 0.639 | 0.16 | 550 | 0.6920 |
64
+ | 0.6322 | 0.18 | 600 | 0.6829 |
65
+ | 0.6164 | 0.19 | 650 | 0.6755 |
66
+ | 0.6185 | 0.21 | 700 | 0.6704 |
67
+ | 0.6457 | 0.22 | 750 | 0.6667 |
68
+ | 0.6238 | 0.24 | 800 | 0.6630 |
69
+ | 0.6173 | 0.25 | 850 | 0.6570 |
70
+ | 0.6076 | 0.27 | 900 | 0.6562 |
71
+ | 0.6097 | 0.28 | 950 | 0.6493 |
72
+ | 0.5693 | 0.3 | 1000 | 0.6423 |
73
+ | 0.5887 | 0.31 | 1050 | 0.6404 |
74
+ | 0.5869 | 0.33 | 1100 | 0.6361 |
75
+ | 0.5964 | 0.34 | 1150 | 0.6341 |
76
+ | 0.5373 | 0.36 | 1200 | 0.6281 |
77
+ | 0.5684 | 0.37 | 1250 | 0.6277 |
78
+ | 0.5746 | 0.39 | 1300 | 0.6183 |
79
+ | 0.5703 | 0.4 | 1350 | 0.6221 |
80
+ | 0.5851 | 0.42 | 1400 | 0.6175 |
81
+ | 0.5519 | 0.43 | 1450 | 0.6167 |
82
+ | 0.5716 | 0.45 | 1500 | 0.6115 |
83
+ | 0.552 | 0.46 | 1550 | 0.6095 |
84
+ | 0.5885 | 0.47 | 1600 | 0.6100 |
85
+ | 0.5739 | 0.49 | 1650 | 0.6061 |
86
+ | 0.5598 | 0.5 | 1700 | 0.6061 |
87
+ | 0.5729 | 0.52 | 1750 | 0.6011 |
88
+ | 0.5575 | 0.53 | 1800 | 0.6013 |
89
+ | 0.5418 | 0.55 | 1850 | 0.6003 |
90
+ | 0.5365 | 0.56 | 1900 | 0.5940 |
91
+ | 0.5096 | 0.58 | 1950 | 0.5878 |
92
+ | 0.5458 | 0.59 | 2000 | 0.5878 |
93
+ | 0.5603 | 0.61 | 2050 | 0.5863 |
94
+ | 0.5388 | 0.62 | 2100 | 0.5854 |
95
+ | 0.5187 | 0.64 | 2150 | 0.5789 |
96
+ | 0.5402 | 0.65 | 2200 | 0.5809 |
97
+ | 0.5398 | 0.67 | 2250 | 0.5761 |
98
+ | 0.5123 | 0.68 | 2300 | 0.5751 |
99
+ | 0.4936 | 0.7 | 2350 | 0.5712 |
100
+ | 0.4899 | 0.71 | 2400 | 0.5672 |
101
+ | 0.5197 | 0.73 | 2450 | 0.5627 |
102
+ | 0.509 | 0.74 | 2500 | 0.5574 |
103
+ | 0.4963 | 0.76 | 2550 | 0.5560 |
104
+ | 0.4989 | 0.77 | 2600 | 0.5544 |
105
+ | 0.4809 | 0.79 | 2650 | 0.5526 |
106
+ | 0.49 | 0.8 | 2700 | 0.5473 |
107
+ | 0.5151 | 0.82 | 2750 | 0.5485 |
108
+ | 0.5005 | 0.83 | 2800 | 0.5469 |
109
+ | 0.5072 | 0.85 | 2850 | 0.5466 |
110
+ | 0.5008 | 0.86 | 2900 | 0.5464 |
111
+ | 0.4857 | 0.88 | 2950 | 0.5441 |
112
+ | 0.4889 | 0.89 | 3000 | 0.5429 |
113
+ | 0.4714 | 0.91 | 3050 | 0.5441 |
114
+ | 0.4618 | 0.92 | 3100 | 0.5404 |
115
+ | 0.4623 | 0.93 | 3150 | 0.5418 |
116
+ | 0.4771 | 0.95 | 3200 | 0.5396 |
117
+ | 0.4592 | 0.96 | 3250 | 0.5409 |
118
+ | 0.4783 | 0.98 | 3300 | 0.5373 |
119
+ | 0.5021 | 0.99 | 3350 | 0.5343 |
120
+ | 0.4753 | 1.01 | 3400 | 0.5350 |
121
+ | 0.4369 | 1.02 | 3450 | 0.5338 |
122
+ | 0.4651 | 1.04 | 3500 | 0.5318 |
123
+ | 0.4395 | 1.05 | 3550 | 0.5320 |
124
+ | 0.4771 | 1.07 | 3600 | 0.5311 |
125
+ | 0.4659 | 1.08 | 3650 | 0.5337 |
126
+ | 0.4699 | 1.1 | 3700 | 0.5309 |
127
+ | 0.4717 | 1.11 | 3750 | 0.5301 |
128
+ | 0.4445 | 1.13 | 3800 | 0.5282 |
129
+ | 0.4342 | 1.14 | 3850 | 0.5303 |
130
+ | 0.4599 | 1.16 | 3900 | 0.5266 |
131
+ | 0.4442 | 1.17 | 3950 | 0.5275 |
132
+ | 0.4628 | 1.19 | 4000 | 0.5260 |
133
+ | 0.4339 | 1.2 | 4050 | 0.5243 |
134
+ | 0.4577 | 1.22 | 4100 | 0.5283 |
135
+ | 0.463 | 1.23 | 4150 | 0.5253 |
136
+ | 0.4602 | 1.25 | 4200 | 0.5243 |
137
+ | 0.4411 | 1.26 | 4250 | 0.5255 |
138
+ | 0.4542 | 1.28 | 4300 | 0.5263 |
139
+ | 0.4379 | 1.29 | 4350 | 0.5213 |
140
+ | 0.4471 | 1.31 | 4400 | 0.5189 |
141
+ | 0.4372 | 1.32 | 4450 | 0.5236 |
142
+ | 0.4526 | 1.34 | 4500 | 0.5203 |
143
+ | 0.4504 | 1.35 | 4550 | 0.5198 |
144
+ | 0.4708 | 1.36 | 4600 | 0.5171 |
145
+ | 0.4748 | 1.38 | 4650 | 0.5177 |
146
+ | 0.4511 | 1.39 | 4700 | 0.5152 |
147
+ | 0.4758 | 1.41 | 4750 | 0.5179 |
148
+ | 0.4543 | 1.42 | 4800 | 0.5165 |
149
+ | 0.4506 | 1.44 | 4850 | 0.5167 |
150
+ | 0.44 | 1.45 | 4900 | 0.5152 |
151
+ | 0.4443 | 1.47 | 4950 | 0.5135 |
152
+ | 0.4538 | 1.48 | 5000 | 0.5140 |
153
+ | 0.435 | 1.5 | 5050 | 0.5142 |
154
+ | 0.439 | 1.51 | 5100 | 0.5135 |
155
+ | 0.4408 | 1.53 | 5150 | 0.5121 |
156
+ | 0.4532 | 1.54 | 5200 | 0.5137 |
157
+ | 0.4177 | 1.56 | 5250 | 0.5143 |
158
+ | 0.4434 | 1.57 | 5300 | 0.5139 |
159
+ | 0.4395 | 1.59 | 5350 | 0.5117 |
160
+ | 0.4327 | 1.6 | 5400 | 0.5124 |
161
+ | 0.4257 | 1.62 | 5450 | 0.5128 |
162
+ | 0.4225 | 1.63 | 5500 | 0.5106 |
163
+ | 0.4517 | 1.65 | 5550 | 0.5119 |
164
+ | 0.4632 | 1.66 | 5600 | 0.5076 |
165
+ | 0.4371 | 1.68 | 5650 | 0.5110 |
166
+ | 0.4209 | 1.69 | 5700 | 0.5082 |
167
+ | 0.4336 | 1.71 | 5750 | 0.5072 |
168
+ | 0.4269 | 1.72 | 5800 | 0.5125 |
169
+ | 0.4208 | 1.74 | 5850 | 0.5105 |
170
+ | 0.4334 | 1.75 | 5900 | 0.5074 |
171
+ | 0.4306 | 1.77 | 5950 | 0.5052 |
172
+ | 0.4454 | 1.78 | 6000 | 0.5073 |
173
+ | 0.4227 | 1.8 | 6050 | 0.5068 |
174
+ | 0.4467 | 1.81 | 6100 | 0.5041 |
175
+ | 0.4279 | 1.82 | 6150 | 0.5034 |
176
+ | 0.4368 | 1.84 | 6200 | 0.5021 |
177
+ | 0.4205 | 1.85 | 6250 | 0.5025 |
178
+ | 0.415 | 1.87 | 6300 | 0.5029 |
179
+ | 0.4213 | 1.88 | 6350 | 0.5019 |
180
+ | 0.4316 | 1.9 | 6400 | 0.5053 |
181
+ | 0.4065 | 1.91 | 6450 | 0.5004 |
182
+ | 0.4578 | 1.93 | 6500 | 0.5045 |
183
+ | 0.4479 | 1.94 | 6550 | 0.4998 |
184
+ | 0.43 | 1.96 | 6600 | 0.4947 |
185
+ | 0.4192 | 1.97 | 6650 | 0.4967 |
186
+ | 0.4061 | 1.99 | 6700 | 0.4961 |
187
+ | 0.4309 | 2.0 | 6750 | 0.4960 |
188
+ | 0.4118 | 2.02 | 6800 | 0.4979 |
189
+ | 0.4149 | 2.03 | 6850 | 0.4955 |
190
+
191
+
192
+ ### Framework versions
193
+
194
+ - PEFT 0.7.1
195
+ - Transformers 4.36.2
196
+ - Pytorch 2.1.2+cu121
197
+ - Datasets 2.16.1
198
+ - Tokenizers 0.15.0
adapter_config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "TheBloke/Mistral-7B-v0.1-GPTQ",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layers_pattern": null,
10
+ "layers_to_transform": null,
11
+ "loftq_config": {},
12
+ "lora_alpha": 32,
13
+ "lora_dropout": 0.05,
14
+ "megatron_config": null,
15
+ "megatron_core": "megatron.core",
16
+ "modules_to_save": null,
17
+ "peft_type": "LORA",
18
+ "r": 32,
19
+ "rank_pattern": {},
20
+ "revision": null,
21
+ "target_modules": [
22
+ "v_proj",
23
+ "q_proj"
24
+ ],
25
+ "task_type": "CAUSAL_LM"
26
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7dc22961a5d3a9f709d8b26f991a3eae9f99098dafe1c2e41146c97e174cf96
3
+ size 54543184
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:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
tokenizer_config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": true,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": true,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ }
29
+ },
30
+ "additional_special_tokens": [],
31
+ "bos_token": "<s>",
32
+ "clean_up_tokenization_spaces": false,
33
+ "eos_token": "</s>",
34
+ "legacy": true,
35
+ "model_max_length": 1000000000000000019884624838656,
36
+ "pad_token": "</s>",
37
+ "sp_model_kwargs": {},
38
+ "spaces_between_special_tokens": false,
39
+ "tokenizer_class": "LlamaTokenizer",
40
+ "unk_token": "<unk>",
41
+ "use_default_system_prompt": true
42
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3dc55b8a56e7218960643b8b6ea9be206eec7582f02772f5bf2f83638088886a
3
+ size 4728