UndefinedCpp/phi-3-minecraft-finetuned
Browse files- README.md +136 -0
- adapter_config.json +34 -0
- adapter_model.safetensors +3 -0
- special_tokens_map.json +24 -0
- tokenizer.json +0 -0
- tokenizer_config.json +131 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,136 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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: 1.0514
|
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: 4
|
43 |
+
- seed: 42
|
44 |
+
- gradient_accumulation_steps: 8
|
45 |
+
- total_train_batch_size: 64
|
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: 2
|
50 |
+
|
51 |
+
### Training results
|
52 |
+
|
53 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
54 |
+
|:-------------:|:------:|:----:|:---------------:|
|
55 |
+
| 2.2314 | 0.0273 | 100 | 2.1230 |
|
56 |
+
| 1.5709 | 0.0546 | 200 | 1.5079 |
|
57 |
+
| 1.4201 | 0.0820 | 300 | 1.4112 |
|
58 |
+
| 1.3689 | 0.1093 | 400 | 1.3759 |
|
59 |
+
| 1.3444 | 0.1366 | 500 | 1.3509 |
|
60 |
+
| 1.3287 | 0.1639 | 600 | 1.3273 |
|
61 |
+
| 1.3019 | 0.1912 | 700 | 1.3038 |
|
62 |
+
| 1.2713 | 0.2185 | 800 | 1.2827 |
|
63 |
+
| 1.2596 | 0.2459 | 900 | 1.2630 |
|
64 |
+
| 1.2433 | 0.2732 | 1000 | 1.2459 |
|
65 |
+
| 1.2233 | 0.3005 | 1100 | 1.2310 |
|
66 |
+
| 1.2197 | 0.3278 | 1200 | 1.2177 |
|
67 |
+
| 1.2033 | 0.3551 | 1300 | 1.2055 |
|
68 |
+
| 1.1902 | 0.3825 | 1400 | 1.1963 |
|
69 |
+
| 1.1927 | 0.4098 | 1500 | 1.1876 |
|
70 |
+
| 1.1771 | 0.4371 | 1600 | 1.1791 |
|
71 |
+
| 1.1615 | 0.4644 | 1700 | 1.1702 |
|
72 |
+
| 1.1655 | 0.4917 | 1800 | 1.1641 |
|
73 |
+
| 1.1725 | 0.5191 | 1900 | 1.1585 |
|
74 |
+
| 1.1348 | 0.5464 | 2000 | 1.1522 |
|
75 |
+
| 1.1429 | 0.5737 | 2100 | 1.1464 |
|
76 |
+
| 1.141 | 0.6010 | 2200 | 1.1413 |
|
77 |
+
| 1.1458 | 0.6283 | 2300 | 1.1362 |
|
78 |
+
| 1.1268 | 0.6556 | 2400 | 1.1314 |
|
79 |
+
| 1.1218 | 0.6830 | 2500 | 1.1272 |
|
80 |
+
| 1.1277 | 0.7103 | 2600 | 1.1226 |
|
81 |
+
| 1.1092 | 0.7376 | 2700 | 1.1198 |
|
82 |
+
| 1.1282 | 0.7649 | 2800 | 1.1156 |
|
83 |
+
| 1.1027 | 0.7922 | 2900 | 1.1116 |
|
84 |
+
| 1.0951 | 0.8196 | 3000 | 1.1084 |
|
85 |
+
| 1.1001 | 0.8469 | 3100 | 1.1057 |
|
86 |
+
| 1.1027 | 0.8742 | 3200 | 1.1021 |
|
87 |
+
| 1.0989 | 0.9015 | 3300 | 1.0987 |
|
88 |
+
| 1.0917 | 0.9288 | 3400 | 1.0966 |
|
89 |
+
| 1.0832 | 0.9562 | 3500 | 1.0939 |
|
90 |
+
| 1.1074 | 0.9835 | 3600 | 1.0915 |
|
91 |
+
| 1.0692 | 1.0108 | 3700 | 1.0891 |
|
92 |
+
| 1.0868 | 1.0381 | 3800 | 1.0872 |
|
93 |
+
| 1.079 | 1.0654 | 3900 | 1.0855 |
|
94 |
+
| 1.0844 | 1.0927 | 4000 | 1.0831 |
|
95 |
+
| 1.0779 | 1.1201 | 4100 | 1.0819 |
|
96 |
+
| 1.0737 | 1.1474 | 4200 | 1.0797 |
|
97 |
+
| 1.0651 | 1.1747 | 4300 | 1.0775 |
|
98 |
+
| 1.0656 | 1.2020 | 4400 | 1.0764 |
|
99 |
+
| 1.0592 | 1.2293 | 4500 | 1.0739 |
|
100 |
+
| 1.07 | 1.2567 | 4600 | 1.0729 |
|
101 |
+
| 1.068 | 1.2840 | 4700 | 1.0719 |
|
102 |
+
| 1.0623 | 1.3113 | 4800 | 1.0701 |
|
103 |
+
| 1.0622 | 1.3386 | 4900 | 1.0691 |
|
104 |
+
| 1.0579 | 1.3659 | 5000 | 1.0678 |
|
105 |
+
| 1.0652 | 1.3933 | 5100 | 1.0667 |
|
106 |
+
| 1.0655 | 1.4206 | 5200 | 1.0654 |
|
107 |
+
| 1.0619 | 1.4479 | 5300 | 1.0642 |
|
108 |
+
| 1.0521 | 1.4752 | 5400 | 1.0635 |
|
109 |
+
| 1.0563 | 1.5025 | 5500 | 1.0625 |
|
110 |
+
| 1.0554 | 1.5298 | 5600 | 1.0611 |
|
111 |
+
| 1.0577 | 1.5572 | 5700 | 1.0599 |
|
112 |
+
| 1.0427 | 1.5845 | 5800 | 1.0590 |
|
113 |
+
| 1.0489 | 1.6118 | 5900 | 1.0583 |
|
114 |
+
| 1.0444 | 1.6391 | 6000 | 1.0578 |
|
115 |
+
| 1.0573 | 1.6664 | 6100 | 1.0562 |
|
116 |
+
| 1.0494 | 1.6938 | 6200 | 1.0555 |
|
117 |
+
| 1.0355 | 1.7211 | 6300 | 1.0551 |
|
118 |
+
| 1.0531 | 1.7484 | 6400 | 1.0544 |
|
119 |
+
| 1.0542 | 1.7757 | 6500 | 1.0540 |
|
120 |
+
| 1.0324 | 1.8030 | 6600 | 1.0535 |
|
121 |
+
| 1.0497 | 1.8304 | 6700 | 1.0532 |
|
122 |
+
| 1.0415 | 1.8577 | 6800 | 1.0529 |
|
123 |
+
| 1.0414 | 1.8850 | 6900 | 1.0522 |
|
124 |
+
| 1.0588 | 1.9123 | 7000 | 1.0520 |
|
125 |
+
| 1.0347 | 1.9396 | 7100 | 1.0519 |
|
126 |
+
| 1.0346 | 1.9669 | 7200 | 1.0516 |
|
127 |
+
| 1.043 | 1.9943 | 7300 | 1.0514 |
|
128 |
+
|
129 |
+
|
130 |
+
### Framework versions
|
131 |
+
|
132 |
+
- PEFT 0.12.0
|
133 |
+
- Transformers 4.44.0
|
134 |
+
- Pytorch 2.0.1+cu118
|
135 |
+
- Datasets 2.21.0
|
136 |
+
- Tokenizers 0.19.1
|
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": 8,
|
20 |
+
"rank_pattern": {},
|
21 |
+
"revision": null,
|
22 |
+
"target_modules": [
|
23 |
+
"q_proj",
|
24 |
+
"gate_proj",
|
25 |
+
"down_proj",
|
26 |
+
"o_proj",
|
27 |
+
"up_proj",
|
28 |
+
"k_proj",
|
29 |
+
"v_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:c3159d8455c5d81bcb314ec97ff70a42e1769fbf907bc31de68b6f0f62914eef
|
3 |
+
size 17842592
|
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": "left",
|
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:ec8d25605685244eab86f853a457d94b1d968264e930a83eb691a90a9691eda6
|
3 |
+
size 4987
|