Hugging Face's logo

HeZ
/
phi-3-mini-QLoRA

PEFT
Safetensors
trl
sft
Generated from Trainer
Model card Files
xet
Community
HeZ commited on
Commit
eef1a66
·
verified ·
1 Parent(s): 32a541f

HeZ/phi-3-mini-4k-qlora-ft-code-gen

Browse files
Files changed (7) hide show
  1. README.md +118 -0
  2. adapter_config.json +34 -0
  3. adapter_model.safetensors +3 -0
  4. special_tokens_map.json +24 -0
  5. tokenizer.json +0 -0
  6. tokenizer_config.json +131 -0
  7. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,118 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: microsoft/Phi-3-mini-4k-instruct
3
+ library_name: peft
4
+ license: mit
5
+ tags:
6
+ - trl
7
+ - sft
8
+ - generated_from_trainer
9
+ model-index:
10
+ - name: phi-3-mini-QLoRA
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
+ # phi-3-mini-QLoRA
18
+
19
+ This model is a fine-tuned version of [microsoft/Phi-3-mini-4k-instruct](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct) on an unknown dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 0.5739
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: 0.0001
41
+ - train_batch_size: 8
42
+ - eval_batch_size: 8
43
+ - seed: 42
44
+ - gradient_accumulation_steps: 4
45
+ - total_train_batch_size: 32
46
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
+ - lr_scheduler_type: linear
48
+ - lr_scheduler_warmup_ratio: 0.1
49
+ - num_epochs: 1
50
+
51
+ ### Training results
52
+
53
+ | Training Loss | Epoch | Step | Validation Loss |
54
+ |:-------------:|:------:|:----:|:---------------:|
55
+ | 1.0193 | 0.0181 | 10 | 1.0582 |
56
+ | 1.0408 | 0.0362 | 20 | 1.0129 |
57
+ | 0.9957 | 0.0543 | 30 | 0.9095 |
58
+ | 0.8047 | 0.0724 | 40 | 0.7711 |
59
+ | 0.699 | 0.0905 | 50 | 0.6689 |
60
+ | 0.6143 | 0.1085 | 60 | 0.6385 |
61
+ | 0.6472 | 0.1266 | 70 | 0.6175 |
62
+ | 0.6077 | 0.1447 | 80 | 0.6073 |
63
+ | 0.6028 | 0.1628 | 90 | 0.6012 |
64
+ | 0.5929 | 0.1809 | 100 | 0.5978 |
65
+ | 0.6117 | 0.1990 | 110 | 0.5948 |
66
+ | 0.5904 | 0.2171 | 120 | 0.5925 |
67
+ | 0.5852 | 0.2352 | 130 | 0.5909 |
68
+ | 0.5662 | 0.2533 | 140 | 0.5895 |
69
+ | 0.6183 | 0.2714 | 150 | 0.5880 |
70
+ | 0.5872 | 0.2895 | 160 | 0.5873 |
71
+ | 0.5807 | 0.3076 | 170 | 0.5863 |
72
+ | 0.6169 | 0.3256 | 180 | 0.5853 |
73
+ | 0.5705 | 0.3437 | 190 | 0.5841 |
74
+ | 0.6143 | 0.3618 | 200 | 0.5835 |
75
+ | 0.5705 | 0.3799 | 210 | 0.5828 |
76
+ | 0.5683 | 0.3980 | 220 | 0.5821 |
77
+ | 0.6077 | 0.4161 | 230 | 0.5818 |
78
+ | 0.586 | 0.4342 | 240 | 0.5811 |
79
+ | 0.5724 | 0.4523 | 250 | 0.5804 |
80
+ | 0.5941 | 0.4704 | 260 | 0.5799 |
81
+ | 0.5989 | 0.4885 | 270 | 0.5798 |
82
+ | 0.5582 | 0.5066 | 280 | 0.5793 |
83
+ | 0.5798 | 0.5246 | 290 | 0.5792 |
84
+ | 0.5545 | 0.5427 | 300 | 0.5785 |
85
+ | 0.597 | 0.5608 | 310 | 0.5783 |
86
+ | 0.6093 | 0.5789 | 320 | 0.5779 |
87
+ | 0.5736 | 0.5970 | 330 | 0.5778 |
88
+ | 0.5698 | 0.6151 | 340 | 0.5772 |
89
+ | 0.5659 | 0.6332 | 350 | 0.5769 |
90
+ | 0.5877 | 0.6513 | 360 | 0.5764 |
91
+ | 0.5837 | 0.6694 | 370 | 0.5763 |
92
+ | 0.5858 | 0.6875 | 380 | 0.5761 |
93
+ | 0.5877 | 0.7056 | 390 | 0.5760 |
94
+ | 0.5802 | 0.7237 | 400 | 0.5756 |
95
+ | 0.6009 | 0.7417 | 410 | 0.5754 |
96
+ | 0.5713 | 0.7598 | 420 | 0.5751 |
97
+ | 0.5509 | 0.7779 | 430 | 0.5751 |
98
+ | 0.5646 | 0.7960 | 440 | 0.5750 |
99
+ | 0.5458 | 0.8141 | 450 | 0.5748 |
100
+ | 0.5694 | 0.8322 | 460 | 0.5746 |
101
+ | 0.576 | 0.8503 | 470 | 0.5744 |
102
+ | 0.5864 | 0.8684 | 480 | 0.5742 |
103
+ | 0.5645 | 0.8865 | 490 | 0.5741 |
104
+ | 0.5531 | 0.9046 | 500 | 0.5742 |
105
+ | 0.6176 | 0.9227 | 510 | 0.5742 |
106
+ | 0.5987 | 0.9408 | 520 | 0.5742 |
107
+ | 0.5703 | 0.9588 | 530 | 0.5740 |
108
+ | 0.6023 | 0.9769 | 540 | 0.5740 |
109
+ | 0.5637 | 0.9950 | 550 | 0.5739 |
110
+
111
+
112
+ ### Framework versions
113
+
114
+ - PEFT 0.13.0
115
+ - Transformers 4.45.1
116
+ - Pytorch 2.4.1+cu121
117
+ - Datasets 3.0.1
118
+ - Tokenizers 0.20.0
adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "microsoft/Phi-3-mini-4k-instruct",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 16,
14
+ "lora_dropout": 0.05,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 16,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "up_proj",
24
+ "q_proj",
25
+ "down_proj",
26
+ "o_proj",
27
+ "v_proj",
28
+ "k_proj",
29
+ "gate_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eaf5d8b84ce86b1df584e03c05434250bf209cb087290871a7705766b212d148
3
+ size 35668592
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": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<unk>",
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 +1,131 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_eos_token": true,
4
+ "add_prefix_space": null,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "</s>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": true,
27
+ "single_word": false,
28
+ "special": false
29
+ },
30
+ "32000": {
31
+ "content": "<|endoftext|>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": true
37
+ },
38
+ "32001": {
39
+ "content": "<|assistant|>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": true,
43
+ "single_word": false,
44
+ "special": true
45
+ },
46
+ "32002": {
47
+ "content": "<|placeholder1|>",
48
+ "lstrip": false,
49
+ "normalized": false,
50
+ "rstrip": true,
51
+ "single_word": false,
52
+ "special": true
53
+ },
54
+ "32003": {
55
+ "content": "<|placeholder2|>",
56
+ "lstrip": false,
57
+ "normalized": false,
58
+ "rstrip": true,
59
+ "single_word": false,
60
+ "special": true
61
+ },
62
+ "32004": {
63
+ "content": "<|placeholder3|>",
64
+ "lstrip": false,
65
+ "normalized": false,
66
+ "rstrip": true,
67
+ "single_word": false,
68
+ "special": true
69
+ },
70
+ "32005": {
71
+ "content": "<|placeholder4|>",
72
+ "lstrip": false,
73
+ "normalized": false,
74
+ "rstrip": true,
75
+ "single_word": false,
76
+ "special": true
77
+ },
78
+ "32006": {
79
+ "content": "<|system|>",
80
+ "lstrip": false,
81
+ "normalized": false,
82
+ "rstrip": true,
83
+ "single_word": false,
84
+ "special": true
85
+ },
86
+ "32007": {
87
+ "content": "<|end|>",
88
+ "lstrip": false,
89
+ "normalized": false,
90
+ "rstrip": true,
91
+ "single_word": false,
92
+ "special": true
93
+ },
94
+ "32008": {
95
+ "content": "<|placeholder5|>",
96
+ "lstrip": false,
97
+ "normalized": false,
98
+ "rstrip": true,
99
+ "single_word": false,
100
+ "special": true
101
+ },
102
+ "32009": {
103
+ "content": "<|placeholder6|>",
104
+ "lstrip": false,
105
+ "normalized": false,
106
+ "rstrip": true,
107
+ "single_word": false,
108
+ "special": true
109
+ },
110
+ "32010": {
111
+ "content": "<|user|>",
112
+ "lstrip": false,
113
+ "normalized": false,
114
+ "rstrip": true,
115
+ "single_word": false,
116
+ "special": true
117
+ }
118
+ },
119
+ "bos_token": "<s>",
120
+ "chat_template": "{% for message in messages %}{% if message['role'] == 'system' %}{{'<|system|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'user' %}{{'<|user|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'assistant' %}{{'<|assistant|>\n' + message['content'] + '<|end|>\n'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>\n' }}{% else %}{{ eos_token }}{% endif %}",
121
+ "clean_up_tokenization_spaces": false,
122
+ "eos_token": "<|endoftext|>",
123
+ "legacy": false,
124
+ "model_max_length": 4096,
125
+ "pad_token": "<unk>",
126
+ "padding_side": "right",
127
+ "sp_model_kwargs": {},
128
+ "tokenizer_class": "LlamaTokenizer",
129
+ "unk_token": "<unk>",
130
+ "use_default_system_prompt": false
131
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cad99856d0a2b8bb47011df1e87007be69a3d7b82c82bbfe3c5e1e3a7d2c5c05
3
+ size 5432